Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +162 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- added_tokens.json +5 -0
- checkpoint-1130/README.md +202 -0
- checkpoint-1130/adapter_config.json +34 -0
- checkpoint-1130/adapter_model.safetensors +3 -0
- checkpoint-1130/added_tokens.json +5 -0
- checkpoint-1130/merges.txt +0 -0
- checkpoint-1130/optimizer.pt +3 -0
- checkpoint-1130/rng_state_0.pth +3 -0
- checkpoint-1130/rng_state_1.pth +3 -0
- checkpoint-1130/scheduler.pt +3 -0
- checkpoint-1130/special_tokens_map.json +20 -0
- checkpoint-1130/tokenizer.json +0 -0
- checkpoint-1130/tokenizer_config.json +43 -0
- checkpoint-1130/trainer_state.json +0 -0
- checkpoint-1130/training_args.bin +3 -0
- checkpoint-1130/vocab.json +0 -0
- checkpoint-1695/README.md +202 -0
- checkpoint-1695/adapter_config.json +34 -0
- checkpoint-1695/adapter_model.safetensors +3 -0
- checkpoint-1695/added_tokens.json +5 -0
- checkpoint-1695/merges.txt +0 -0
- checkpoint-1695/optimizer.pt +3 -0
- checkpoint-1695/rng_state_0.pth +3 -0
- checkpoint-1695/rng_state_1.pth +3 -0
- checkpoint-1695/scheduler.pt +3 -0
- checkpoint-1695/special_tokens_map.json +20 -0
- checkpoint-1695/tokenizer.json +0 -0
- checkpoint-1695/tokenizer_config.json +43 -0
- checkpoint-1695/trainer_state.json +0 -0
- checkpoint-1695/training_args.bin +3 -0
- checkpoint-1695/vocab.json +0 -0
- checkpoint-565/README.md +202 -0
- checkpoint-565/adapter_config.json +34 -0
- checkpoint-565/adapter_model.safetensors +3 -0
- checkpoint-565/added_tokens.json +5 -0
- checkpoint-565/merges.txt +0 -0
- checkpoint-565/optimizer.pt +3 -0
- checkpoint-565/rng_state_0.pth +3 -0
- checkpoint-565/rng_state_1.pth +3 -0
- checkpoint-565/scheduler.pt +3 -0
- checkpoint-565/special_tokens_map.json +20 -0
- checkpoint-565/tokenizer.json +0 -0
- checkpoint-565/tokenizer_config.json +43 -0
- checkpoint-565/trainer_state.json +4008 -0
- checkpoint-565/training_args.bin +3 -0
- checkpoint-565/vocab.json +0 -0
- config.json +42 -0
README.md
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: Qwen/Qwen1.5-7B
|
7 |
+
model-index:
|
8 |
+
- name: home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/1e-3/
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
16 |
+
<details><summary>See axolotl config</summary>
|
17 |
+
|
18 |
+
axolotl version: `0.4.0`
|
19 |
+
```yaml
|
20 |
+
# base_model: Qwen/Qwen-7B
|
21 |
+
base_model: Qwen/Qwen1.5-7B
|
22 |
+
model_type: AutoModelForCausalLM
|
23 |
+
tokenizer_type: AutoTokenizer
|
24 |
+
|
25 |
+
trust_remote_code: true
|
26 |
+
|
27 |
+
load_in_8bit: true
|
28 |
+
load_in_4bit: false
|
29 |
+
strict: false
|
30 |
+
|
31 |
+
datasets:
|
32 |
+
# - path: mhenrichsen/alpaca_2k_test
|
33 |
+
- path: /home/yujia/home/CN_Hateful/train_toxiCN_cn.json
|
34 |
+
# - path: /home/yujia/home/CN_Hateful/train_toxiCN.json
|
35 |
+
# - path: /home/yujia/home/CN_Hateful/train.json
|
36 |
+
# - path: /home/yujia/home/CN_Hateful/train_cn.json
|
37 |
+
ds_type: json
|
38 |
+
type: alpaca
|
39 |
+
dataset_prepared_path:
|
40 |
+
val_set_size: 0.05
|
41 |
+
output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/1e-3/
|
42 |
+
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/1e-5/
|
43 |
+
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/cold/3e-4/
|
44 |
+
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/cold/3e-4/
|
45 |
+
|
46 |
+
sequence_len: 256 # supports up to 8192
|
47 |
+
sample_packing: false
|
48 |
+
pad_to_sequence_len:
|
49 |
+
|
50 |
+
adapter: lora
|
51 |
+
lora_model_dir:
|
52 |
+
lora_r: 32
|
53 |
+
lora_alpha: 16
|
54 |
+
lora_dropout: 0.05
|
55 |
+
lora_target_linear: true
|
56 |
+
lora_fan_in_fan_out:
|
57 |
+
|
58 |
+
wandb_project:
|
59 |
+
wandb_entity:
|
60 |
+
wandb_watch:
|
61 |
+
wandb_name:
|
62 |
+
wandb_log_model:
|
63 |
+
|
64 |
+
gradient_accumulation_steps: 4
|
65 |
+
micro_batch_size: 2
|
66 |
+
num_epochs: 3
|
67 |
+
optimizer: adamw_bnb_8bit
|
68 |
+
lr_scheduler: cosine
|
69 |
+
learning_rate: 0.001
|
70 |
+
|
71 |
+
train_on_inputs: false
|
72 |
+
group_by_length: false
|
73 |
+
bf16: auto
|
74 |
+
fp16:
|
75 |
+
tf32: false
|
76 |
+
|
77 |
+
gradient_checkpointing: false
|
78 |
+
early_stopping_patience:
|
79 |
+
resume_from_checkpoint:
|
80 |
+
local_rank:
|
81 |
+
logging_steps: 1
|
82 |
+
xformers_attention:
|
83 |
+
flash_attention:
|
84 |
+
|
85 |
+
warmup_steps: 10
|
86 |
+
evals_per_epoch: 4
|
87 |
+
eval_table_size:
|
88 |
+
eval_max_new_tokens: 20
|
89 |
+
saves_per_epoch: 1
|
90 |
+
debug:
|
91 |
+
deepspeed:
|
92 |
+
weight_decay: 0.0
|
93 |
+
fsdp:
|
94 |
+
fsdp_config:
|
95 |
+
special_tokens:
|
96 |
+
|
97 |
+
```
|
98 |
+
|
99 |
+
</details><br>
|
100 |
+
|
101 |
+
# home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/1e-3/
|
102 |
+
|
103 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on the None dataset.
|
104 |
+
It achieves the following results on the evaluation set:
|
105 |
+
- Loss: 0.1333
|
106 |
+
|
107 |
+
## Model description
|
108 |
+
|
109 |
+
More information needed
|
110 |
+
|
111 |
+
## Intended uses & limitations
|
112 |
+
|
113 |
+
More information needed
|
114 |
+
|
115 |
+
## Training and evaluation data
|
116 |
+
|
117 |
+
More information needed
|
118 |
+
|
119 |
+
## Training procedure
|
120 |
+
|
121 |
+
### Training hyperparameters
|
122 |
+
|
123 |
+
The following hyperparameters were used during training:
|
124 |
+
- learning_rate: 0.001
|
125 |
+
- train_batch_size: 2
|
126 |
+
- eval_batch_size: 2
|
127 |
+
- seed: 42
|
128 |
+
- distributed_type: multi-GPU
|
129 |
+
- num_devices: 2
|
130 |
+
- gradient_accumulation_steps: 4
|
131 |
+
- total_train_batch_size: 16
|
132 |
+
- total_eval_batch_size: 4
|
133 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
134 |
+
- lr_scheduler_type: cosine
|
135 |
+
- lr_scheduler_warmup_steps: 10
|
136 |
+
- num_epochs: 3
|
137 |
+
|
138 |
+
### Training results
|
139 |
+
|
140 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
141 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
142 |
+
| 3.3182 | 0.0 | 1 | 3.3363 |
|
143 |
+
| 0.1432 | 0.25 | 142 | 1.5367 |
|
144 |
+
| 0.1667 | 0.5 | 284 | 0.1418 |
|
145 |
+
| 0.1329 | 0.75 | 426 | 0.1375 |
|
146 |
+
| 0.1372 | 1.0 | 568 | 0.1397 |
|
147 |
+
| 0.1369 | 1.26 | 710 | 0.1382 |
|
148 |
+
| 0.1537 | 1.51 | 852 | 0.1408 |
|
149 |
+
| 0.1204 | 1.76 | 994 | 0.1354 |
|
150 |
+
| 0.1262 | 2.01 | 1136 | 0.1343 |
|
151 |
+
| 0.12 | 2.26 | 1278 | 0.1380 |
|
152 |
+
| 0.146 | 2.51 | 1420 | 0.1335 |
|
153 |
+
| 0.1502 | 2.76 | 1562 | 0.1333 |
|
154 |
+
|
155 |
+
|
156 |
+
### Framework versions
|
157 |
+
|
158 |
+
- PEFT 0.10.0
|
159 |
+
- Transformers 4.40.0.dev0
|
160 |
+
- Pytorch 2.2.1+cu121
|
161 |
+
- Datasets 2.18.0
|
162 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:830e38ae3e35fd023a10add9d0ac7345292caf24c2129e5d06657eaea7b92d92
|
3 |
+
size 319977674
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1130/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen1.5-7B
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-1130/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-1130/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b2f36c11368d62522d332b027598c1bd25cdc0f0e76c61e91168daaa95eaf8
|
3 |
+
size 319876032
|
checkpoint-1130/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1130/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1130/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096c2ec3c1b66b84963de8dc8e04c3153d4303225cdae6d477a7024ec04d471e
|
3 |
+
size 160736532
|
checkpoint-1130/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d4901585e9d75e84023ab72e4541020015ec7f9e3a44dd30228bed49938a1bc
|
3 |
+
size 14512
|
checkpoint-1130/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52b8bbcff4bb55ccbed97b61cc7bef4a35d002ff92406d2e23baa476f0a8d21
|
3 |
+
size 14512
|
checkpoint-1130/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cff9ea3978dc9317c468c2c00769c2a61de1c01c1a4ff299627005ac129aa7f6
|
3 |
+
size 1064
|
checkpoint-1130/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-1130/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1130/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
checkpoint-1130/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1130/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:242a9177bc415e2f72dc78b8f2eb1cd29a0e78da733db42237e6bb4cd1af9c7d
|
3 |
+
size 5752
|
checkpoint-1130/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1695/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen1.5-7B
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-1695/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-1695/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d39246b5530cbaafea081381c21c915516e701ad53556b068ed5cb35cec7f477
|
3 |
+
size 319876032
|
checkpoint-1695/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-1695/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1695/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0049358da0b017afaec8df1d9c4c584032cc7c203245a00b042769b0c83a1c39
|
3 |
+
size 160736532
|
checkpoint-1695/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b55ad0de153a9394c92810ea3c27399952a305bd25451ed430aaf933a9a5e55c
|
3 |
+
size 14512
|
checkpoint-1695/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49270efca7489b54d9139d7c93770e62001cb2f4e09707c29e75b02ffb96afb7
|
3 |
+
size 14512
|
checkpoint-1695/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7323ec8a0c271f5ede6b76f43aedf644821eee5e8de58b5de06dfe7df966802d
|
3 |
+
size 1064
|
checkpoint-1695/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-1695/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1695/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
checkpoint-1695/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1695/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:242a9177bc415e2f72dc78b8f2eb1cd29a0e78da733db42237e6bb4cd1af9c7d
|
3 |
+
size 5752
|
checkpoint-1695/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-565/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Qwen/Qwen1.5-7B
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-565/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-7B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
+
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-565/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b0612ae6de3c34b90c5a1d1ceaaffbce4812950fb53caa68724381b1f03748
|
3 |
+
size 319876032
|
checkpoint-565/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
checkpoint-565/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-565/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:853f09c69b65007336bb2ab3c1759f1b22107ff09f84bcfc69cce2df88e5195a
|
3 |
+
size 160736532
|
checkpoint-565/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a681c33ffd6b61feaf98d05f702d37f2e4cea5ae28ff9fe027ab78959f6d28
|
3 |
+
size 14512
|
checkpoint-565/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:264fc0be051e80523f0b0faf9f50191b6a6d8a450a601ac7a6354029ee14de9c
|
3 |
+
size 14512
|
checkpoint-565/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e16654130fe41ba22580528fce61920c5dca76f31f760c72e1f44964e37bd87c
|
3 |
+
size 1064
|
checkpoint-565/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
checkpoint-565/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-565/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
checkpoint-565/trainer_state.json
ADDED
@@ -0,0 +1,4008 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9995577178239717,
|
5 |
+
"eval_steps": 142,
|
6 |
+
"global_step": 565,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 4.705155372619629,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 3.3182,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"eval_loss": 3.3362529277801514,
|
21 |
+
"eval_runtime": 14.4366,
|
22 |
+
"eval_samples_per_second": 33.041,
|
23 |
+
"eval_steps_per_second": 8.312,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0,
|
28 |
+
"grad_norm": 4.644563674926758,
|
29 |
+
"learning_rate": 0.0002,
|
30 |
+
"loss": 3.2788,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.01,
|
35 |
+
"grad_norm": 4.3825764656066895,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 2.9231,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.01,
|
42 |
+
"grad_norm": 2.904296636581421,
|
43 |
+
"learning_rate": 0.0004,
|
44 |
+
"loss": 1.1824,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.01,
|
49 |
+
"grad_norm": 1.6988284587860107,
|
50 |
+
"learning_rate": 0.0005,
|
51 |
+
"loss": 0.3472,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.01,
|
56 |
+
"grad_norm": 0.5742101073265076,
|
57 |
+
"learning_rate": 0.0006,
|
58 |
+
"loss": 0.1478,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.01,
|
63 |
+
"grad_norm": 0.6511944532394409,
|
64 |
+
"learning_rate": 0.0007,
|
65 |
+
"loss": 0.1532,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.01,
|
70 |
+
"grad_norm": 2.305083751678467,
|
71 |
+
"learning_rate": 0.0008,
|
72 |
+
"loss": 0.2397,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.02,
|
77 |
+
"grad_norm": 4.7435078620910645,
|
78 |
+
"learning_rate": 0.0009000000000000001,
|
79 |
+
"loss": 0.434,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.02,
|
84 |
+
"grad_norm": 0.6199779510498047,
|
85 |
+
"learning_rate": 0.001,
|
86 |
+
"loss": 0.1743,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.02,
|
91 |
+
"grad_norm": 0.14406554400920868,
|
92 |
+
"learning_rate": 0.0009999991309598973,
|
93 |
+
"loss": 0.1404,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.02,
|
98 |
+
"grad_norm": 0.1965201050043106,
|
99 |
+
"learning_rate": 0.0009999965238426103,
|
100 |
+
"loss": 0.1418,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.02,
|
105 |
+
"grad_norm": 26.520109176635742,
|
106 |
+
"learning_rate": 0.0009999921786572016,
|
107 |
+
"loss": 0.2689,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.02,
|
112 |
+
"grad_norm": 0.0870603695511818,
|
113 |
+
"learning_rate": 0.0009999860954187755,
|
114 |
+
"loss": 0.1338,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.03,
|
119 |
+
"grad_norm": 0.05200817808508873,
|
120 |
+
"learning_rate": 0.0009999782741484788,
|
121 |
+
"loss": 0.1308,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.03,
|
126 |
+
"grad_norm": 0.2145700752735138,
|
127 |
+
"learning_rate": 0.0009999687148734995,
|
128 |
+
"loss": 0.1375,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.03,
|
133 |
+
"grad_norm": 0.19921083748340607,
|
134 |
+
"learning_rate": 0.0009999574176270667,
|
135 |
+
"loss": 0.1388,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.03,
|
140 |
+
"grad_norm": 1.193419337272644,
|
141 |
+
"learning_rate": 0.0009999443824484518,
|
142 |
+
"loss": 0.1978,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.03,
|
147 |
+
"grad_norm": 0.4399484395980835,
|
148 |
+
"learning_rate": 0.0009999296093829671,
|
149 |
+
"loss": 0.1518,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.04,
|
154 |
+
"grad_norm": 44.88853073120117,
|
155 |
+
"learning_rate": 0.0009999130984819661,
|
156 |
+
"loss": 0.9033,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.04,
|
161 |
+
"grad_norm": 0.3220385015010834,
|
162 |
+
"learning_rate": 0.0009998948498028434,
|
163 |
+
"loss": 0.1234,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.04,
|
168 |
+
"grad_norm": 0.5420748591423035,
|
169 |
+
"learning_rate": 0.0009998748634090344,
|
170 |
+
"loss": 0.1602,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.04,
|
175 |
+
"grad_norm": 0.5249865651130676,
|
176 |
+
"learning_rate": 0.0009998531393700149,
|
177 |
+
"loss": 0.1538,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.04,
|
182 |
+
"grad_norm": 0.056158341467380524,
|
183 |
+
"learning_rate": 0.000999829677761301,
|
184 |
+
"loss": 0.1374,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.04,
|
189 |
+
"grad_norm": 0.19818872213363647,
|
190 |
+
"learning_rate": 0.0009998044786644492,
|
191 |
+
"loss": 0.1413,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.05,
|
196 |
+
"grad_norm": 0.27901849150657654,
|
197 |
+
"learning_rate": 0.0009997775421670557,
|
198 |
+
"loss": 0.1395,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.05,
|
203 |
+
"grad_norm": 0.22768354415893555,
|
204 |
+
"learning_rate": 0.0009997488683627558,
|
205 |
+
"loss": 0.1241,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.05,
|
210 |
+
"grad_norm": 0.14878959953784943,
|
211 |
+
"learning_rate": 0.0009997184573512245,
|
212 |
+
"loss": 0.1243,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.05,
|
217 |
+
"grad_norm": 1.0589066743850708,
|
218 |
+
"learning_rate": 0.000999686309238175,
|
219 |
+
"loss": 0.2499,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.05,
|
224 |
+
"grad_norm": 0.11455405503511429,
|
225 |
+
"learning_rate": 0.00099965242413536,
|
226 |
+
"loss": 0.1254,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.05,
|
231 |
+
"grad_norm": 0.16566088795661926,
|
232 |
+
"learning_rate": 0.000999616802160569,
|
233 |
+
"loss": 0.1416,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.06,
|
238 |
+
"grad_norm": 1.3691716194152832,
|
239 |
+
"learning_rate": 0.0009995794434376297,
|
240 |
+
"loss": 0.1465,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.06,
|
245 |
+
"grad_norm": 0.09674070030450821,
|
246 |
+
"learning_rate": 0.000999540348096407,
|
247 |
+
"loss": 0.1373,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.06,
|
252 |
+
"grad_norm": 0.5034632086753845,
|
253 |
+
"learning_rate": 0.000999499516272803,
|
254 |
+
"loss": 0.1471,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.06,
|
259 |
+
"grad_norm": 0.26572930812835693,
|
260 |
+
"learning_rate": 0.0009994569481087553,
|
261 |
+
"loss": 0.1424,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.06,
|
266 |
+
"grad_norm": 0.20631802082061768,
|
267 |
+
"learning_rate": 0.0009994126437522376,
|
268 |
+
"loss": 0.1449,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.07,
|
273 |
+
"grad_norm": 0.11268749833106995,
|
274 |
+
"learning_rate": 0.0009993666033572591,
|
275 |
+
"loss": 0.1403,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.07,
|
280 |
+
"grad_norm": 0.6610996723175049,
|
281 |
+
"learning_rate": 0.0009993188270838635,
|
282 |
+
"loss": 0.1424,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.07,
|
287 |
+
"grad_norm": 98.93838500976562,
|
288 |
+
"learning_rate": 0.0009992693150981291,
|
289 |
+
"loss": 2.775,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.07,
|
294 |
+
"grad_norm": 32.53168869018555,
|
295 |
+
"learning_rate": 0.0009992180675721671,
|
296 |
+
"loss": 0.6932,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.07,
|
301 |
+
"grad_norm": 54.8778076171875,
|
302 |
+
"learning_rate": 0.0009991650846841226,
|
303 |
+
"loss": 5.7008,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.07,
|
308 |
+
"grad_norm": 2.0524775981903076,
|
309 |
+
"learning_rate": 0.000999110366618172,
|
310 |
+
"loss": 0.1623,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.08,
|
315 |
+
"grad_norm": 0.404278427362442,
|
316 |
+
"learning_rate": 0.0009990539135645246,
|
317 |
+
"loss": 0.1427,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.08,
|
322 |
+
"grad_norm": 1.7963409423828125,
|
323 |
+
"learning_rate": 0.0009989957257194198,
|
324 |
+
"loss": 0.174,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.08,
|
329 |
+
"grad_norm": 0.11620022356510162,
|
330 |
+
"learning_rate": 0.0009989358032851284,
|
331 |
+
"loss": 0.1339,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.08,
|
336 |
+
"grad_norm": 0.5025681853294373,
|
337 |
+
"learning_rate": 0.00099887414646995,
|
338 |
+
"loss": 0.1558,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.08,
|
343 |
+
"grad_norm": 78.1165771484375,
|
344 |
+
"learning_rate": 0.0009988107554882138,
|
345 |
+
"loss": 2.2938,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.08,
|
350 |
+
"grad_norm": 0.08389786630868912,
|
351 |
+
"learning_rate": 0.0009987456305602768,
|
352 |
+
"loss": 0.1409,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.09,
|
357 |
+
"grad_norm": 7.123101711273193,
|
358 |
+
"learning_rate": 0.0009986787719125242,
|
359 |
+
"loss": 0.1524,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.09,
|
364 |
+
"grad_norm": 0.5341290235519409,
|
365 |
+
"learning_rate": 0.0009986101797773666,
|
366 |
+
"loss": 0.1598,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.09,
|
371 |
+
"grad_norm": 0.05239284038543701,
|
372 |
+
"learning_rate": 0.000998539854393242,
|
373 |
+
"loss": 0.1386,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.09,
|
378 |
+
"grad_norm": 0.0722254291176796,
|
379 |
+
"learning_rate": 0.0009984677960046123,
|
380 |
+
"loss": 0.1385,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.09,
|
385 |
+
"grad_norm": 0.11535236239433289,
|
386 |
+
"learning_rate": 0.000998394004861964,
|
387 |
+
"loss": 0.1369,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.1,
|
392 |
+
"grad_norm": 0.7584894299507141,
|
393 |
+
"learning_rate": 0.0009983184812218072,
|
394 |
+
"loss": 0.108,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.1,
|
399 |
+
"grad_norm": 0.8361538052558899,
|
400 |
+
"learning_rate": 0.000998241225346674,
|
401 |
+
"loss": 0.1703,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.1,
|
406 |
+
"grad_norm": 0.37683162093162537,
|
407 |
+
"learning_rate": 0.0009981622375051184,
|
408 |
+
"loss": 0.1368,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.1,
|
413 |
+
"grad_norm": 0.5335961580276489,
|
414 |
+
"learning_rate": 0.0009980815179717144,
|
415 |
+
"loss": 0.1559,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.1,
|
420 |
+
"grad_norm": 0.2806299328804016,
|
421 |
+
"learning_rate": 0.0009979990670270565,
|
422 |
+
"loss": 0.1397,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.1,
|
427 |
+
"grad_norm": 0.4967437982559204,
|
428 |
+
"learning_rate": 0.0009979148849577574,
|
429 |
+
"loss": 0.1543,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.11,
|
434 |
+
"grad_norm": 0.10350017994642258,
|
435 |
+
"learning_rate": 0.0009978289720564471,
|
436 |
+
"loss": 0.1367,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.11,
|
441 |
+
"grad_norm": 78.35698699951172,
|
442 |
+
"learning_rate": 0.0009977413286217727,
|
443 |
+
"loss": 2.2474,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.11,
|
448 |
+
"grad_norm": 0.15264186263084412,
|
449 |
+
"learning_rate": 0.0009976519549583973,
|
450 |
+
"loss": 0.1311,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.11,
|
455 |
+
"grad_norm": 0.31865784525871277,
|
456 |
+
"learning_rate": 0.0009975608513769975,
|
457 |
+
"loss": 0.1407,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.11,
|
462 |
+
"grad_norm": 0.32891547679901123,
|
463 |
+
"learning_rate": 0.0009974680181942645,
|
464 |
+
"loss": 0.1423,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.11,
|
469 |
+
"grad_norm": 0.15653717517852783,
|
470 |
+
"learning_rate": 0.0009973734557329008,
|
471 |
+
"loss": 0.1365,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.12,
|
476 |
+
"grad_norm": 0.3237778842449188,
|
477 |
+
"learning_rate": 0.0009972771643216212,
|
478 |
+
"loss": 0.1407,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.12,
|
483 |
+
"grad_norm": 0.13634416460990906,
|
484 |
+
"learning_rate": 0.0009971791442951496,
|
485 |
+
"loss": 0.1378,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.12,
|
490 |
+
"grad_norm": 0.3488883376121521,
|
491 |
+
"learning_rate": 0.0009970793959942197,
|
492 |
+
"loss": 0.1429,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.12,
|
497 |
+
"grad_norm": 0.5150622129440308,
|
498 |
+
"learning_rate": 0.0009969779197655725,
|
499 |
+
"loss": 0.1492,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.12,
|
504 |
+
"grad_norm": 0.3482552468776703,
|
505 |
+
"learning_rate": 0.0009968747159619555,
|
506 |
+
"loss": 0.1415,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.13,
|
511 |
+
"grad_norm": 0.22551549971103668,
|
512 |
+
"learning_rate": 0.000996769784942122,
|
513 |
+
"loss": 0.1418,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.13,
|
518 |
+
"grad_norm": 0.20759086310863495,
|
519 |
+
"learning_rate": 0.0009966631270708287,
|
520 |
+
"loss": 0.1366,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.13,
|
525 |
+
"grad_norm": 13.050313949584961,
|
526 |
+
"learning_rate": 0.0009965547427188356,
|
527 |
+
"loss": 0.1375,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.13,
|
532 |
+
"grad_norm": 0.18372055888175964,
|
533 |
+
"learning_rate": 0.0009964446322629043,
|
534 |
+
"loss": 0.1285,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.13,
|
539 |
+
"grad_norm": 0.4404817819595337,
|
540 |
+
"learning_rate": 0.000996332796085796,
|
541 |
+
"loss": 0.1501,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.13,
|
546 |
+
"grad_norm": 1.269240379333496,
|
547 |
+
"learning_rate": 0.0009962192345762716,
|
548 |
+
"loss": 0.1346,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.14,
|
553 |
+
"grad_norm": 32.20164108276367,
|
554 |
+
"learning_rate": 0.0009961039481290888,
|
555 |
+
"loss": 0.3348,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.14,
|
560 |
+
"grad_norm": 82.92976379394531,
|
561 |
+
"learning_rate": 0.0009959869371450021,
|
562 |
+
"loss": 5.8309,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.14,
|
567 |
+
"grad_norm": 0.3416314721107483,
|
568 |
+
"learning_rate": 0.0009958682020307602,
|
569 |
+
"loss": 0.1418,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.14,
|
574 |
+
"grad_norm": 31.961870193481445,
|
575 |
+
"learning_rate": 0.0009957477431991053,
|
576 |
+
"loss": 0.1899,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.14,
|
581 |
+
"grad_norm": 38.58375930786133,
|
582 |
+
"learning_rate": 0.000995625561068772,
|
583 |
+
"loss": 0.5641,
|
584 |
+
"step": 81
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.15,
|
588 |
+
"grad_norm": 0.32622194290161133,
|
589 |
+
"learning_rate": 0.0009955016560644846,
|
590 |
+
"loss": 0.1144,
|
591 |
+
"step": 82
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.15,
|
595 |
+
"grad_norm": 6.264970779418945,
|
596 |
+
"learning_rate": 0.0009953760286169572,
|
597 |
+
"loss": 0.4788,
|
598 |
+
"step": 83
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.15,
|
602 |
+
"grad_norm": 0.07168668508529663,
|
603 |
+
"learning_rate": 0.0009952486791628904,
|
604 |
+
"loss": 0.1326,
|
605 |
+
"step": 84
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.15,
|
609 |
+
"grad_norm": 35.18340301513672,
|
610 |
+
"learning_rate": 0.000995119608144972,
|
611 |
+
"loss": 0.3884,
|
612 |
+
"step": 85
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.15,
|
616 |
+
"grad_norm": 0.03896519914269447,
|
617 |
+
"learning_rate": 0.000994988816011873,
|
618 |
+
"loss": 0.1249,
|
619 |
+
"step": 86
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.15,
|
623 |
+
"grad_norm": 14.499520301818848,
|
624 |
+
"learning_rate": 0.000994856303218248,
|
625 |
+
"loss": 0.3756,
|
626 |
+
"step": 87
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.16,
|
630 |
+
"grad_norm": 0.3134947419166565,
|
631 |
+
"learning_rate": 0.000994722070224733,
|
632 |
+
"loss": 0.1539,
|
633 |
+
"step": 88
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.16,
|
637 |
+
"grad_norm": 117.39696502685547,
|
638 |
+
"learning_rate": 0.000994586117497943,
|
639 |
+
"loss": 0.5885,
|
640 |
+
"step": 89
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.16,
|
644 |
+
"grad_norm": 37.93465805053711,
|
645 |
+
"learning_rate": 0.0009944484455104716,
|
646 |
+
"loss": 0.7709,
|
647 |
+
"step": 90
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.16,
|
651 |
+
"grad_norm": 236.63330078125,
|
652 |
+
"learning_rate": 0.0009943090547408888,
|
653 |
+
"loss": 6.0182,
|
654 |
+
"step": 91
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.16,
|
658 |
+
"grad_norm": 1.1088515520095825,
|
659 |
+
"learning_rate": 0.0009941679456737394,
|
660 |
+
"loss": 0.1931,
|
661 |
+
"step": 92
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.16,
|
665 |
+
"grad_norm": 0.11310256272554398,
|
666 |
+
"learning_rate": 0.0009940251187995411,
|
667 |
+
"loss": 0.1293,
|
668 |
+
"step": 93
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.17,
|
672 |
+
"grad_norm": 0.6143047213554382,
|
673 |
+
"learning_rate": 0.0009938805746147828,
|
674 |
+
"loss": 0.2364,
|
675 |
+
"step": 94
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.17,
|
679 |
+
"grad_norm": 0.2461577206850052,
|
680 |
+
"learning_rate": 0.0009937343136219232,
|
681 |
+
"loss": 0.1504,
|
682 |
+
"step": 95
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.17,
|
686 |
+
"grad_norm": 97.17162322998047,
|
687 |
+
"learning_rate": 0.0009935863363293895,
|
688 |
+
"loss": 5.764,
|
689 |
+
"step": 96
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.17,
|
693 |
+
"grad_norm": 0.5417380928993225,
|
694 |
+
"learning_rate": 0.000993436643251574,
|
695 |
+
"loss": 0.1576,
|
696 |
+
"step": 97
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.17,
|
700 |
+
"grad_norm": 0.2737255096435547,
|
701 |
+
"learning_rate": 0.0009932852349088341,
|
702 |
+
"loss": 0.1437,
|
703 |
+
"step": 98
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.18,
|
707 |
+
"grad_norm": 138.00778198242188,
|
708 |
+
"learning_rate": 0.0009931321118274896,
|
709 |
+
"loss": 4.1331,
|
710 |
+
"step": 99
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.18,
|
714 |
+
"grad_norm": 46.4688606262207,
|
715 |
+
"learning_rate": 0.0009929772745398205,
|
716 |
+
"loss": 0.6178,
|
717 |
+
"step": 100
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.18,
|
721 |
+
"grad_norm": 0.49907386302948,
|
722 |
+
"learning_rate": 0.0009928207235840663,
|
723 |
+
"loss": 0.1445,
|
724 |
+
"step": 101
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.18,
|
728 |
+
"grad_norm": 0.33814460039138794,
|
729 |
+
"learning_rate": 0.0009926624595044233,
|
730 |
+
"loss": 0.139,
|
731 |
+
"step": 102
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.18,
|
735 |
+
"grad_norm": 0.3241071403026581,
|
736 |
+
"learning_rate": 0.0009925024828510427,
|
737 |
+
"loss": 0.1404,
|
738 |
+
"step": 103
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.18,
|
742 |
+
"grad_norm": 78.4036865234375,
|
743 |
+
"learning_rate": 0.000992340794180029,
|
744 |
+
"loss": 1.2663,
|
745 |
+
"step": 104
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.19,
|
749 |
+
"grad_norm": 1.113776445388794,
|
750 |
+
"learning_rate": 0.000992177394053438,
|
751 |
+
"loss": 0.162,
|
752 |
+
"step": 105
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.19,
|
756 |
+
"grad_norm": 16.512048721313477,
|
757 |
+
"learning_rate": 0.0009920122830392748,
|
758 |
+
"loss": 3.3373,
|
759 |
+
"step": 106
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.19,
|
763 |
+
"grad_norm": 111.53176879882812,
|
764 |
+
"learning_rate": 0.0009918454617114918,
|
765 |
+
"loss": 2.3969,
|
766 |
+
"step": 107
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.19,
|
770 |
+
"grad_norm": 14.91741943359375,
|
771 |
+
"learning_rate": 0.0009916769306499865,
|
772 |
+
"loss": 1.8837,
|
773 |
+
"step": 108
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.19,
|
777 |
+
"grad_norm": 61.30055618286133,
|
778 |
+
"learning_rate": 0.0009915066904406,
|
779 |
+
"loss": 10.4922,
|
780 |
+
"step": 109
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.19,
|
784 |
+
"grad_norm": 0.6948704123497009,
|
785 |
+
"learning_rate": 0.0009913347416751147,
|
786 |
+
"loss": 0.1536,
|
787 |
+
"step": 110
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.2,
|
791 |
+
"grad_norm": 0.7721084356307983,
|
792 |
+
"learning_rate": 0.000991161084951252,
|
793 |
+
"loss": 0.1356,
|
794 |
+
"step": 111
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.2,
|
798 |
+
"grad_norm": 0.24614596366882324,
|
799 |
+
"learning_rate": 0.0009909857208726704,
|
800 |
+
"loss": 0.1339,
|
801 |
+
"step": 112
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.2,
|
805 |
+
"grad_norm": 7.189969062805176,
|
806 |
+
"learning_rate": 0.0009908086500489638,
|
807 |
+
"loss": 0.2551,
|
808 |
+
"step": 113
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.2,
|
812 |
+
"grad_norm": 0.8675662279129028,
|
813 |
+
"learning_rate": 0.0009906298730956585,
|
814 |
+
"loss": 0.1668,
|
815 |
+
"step": 114
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.2,
|
819 |
+
"grad_norm": 0.605249285697937,
|
820 |
+
"learning_rate": 0.0009904493906342123,
|
821 |
+
"loss": 0.1478,
|
822 |
+
"step": 115
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.21,
|
826 |
+
"grad_norm": 0.8765722513198853,
|
827 |
+
"learning_rate": 0.0009902672032920106,
|
828 |
+
"loss": 0.1598,
|
829 |
+
"step": 116
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.21,
|
833 |
+
"grad_norm": 0.6021157503128052,
|
834 |
+
"learning_rate": 0.0009900833117023665,
|
835 |
+
"loss": 0.1506,
|
836 |
+
"step": 117
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.21,
|
840 |
+
"grad_norm": 0.28180792927742004,
|
841 |
+
"learning_rate": 0.000989897716504516,
|
842 |
+
"loss": 0.1389,
|
843 |
+
"step": 118
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.21,
|
847 |
+
"grad_norm": 0.21730898320674896,
|
848 |
+
"learning_rate": 0.0009897104183436184,
|
849 |
+
"loss": 0.1377,
|
850 |
+
"step": 119
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.21,
|
854 |
+
"grad_norm": 0.977118730545044,
|
855 |
+
"learning_rate": 0.0009895214178707516,
|
856 |
+
"loss": 0.1698,
|
857 |
+
"step": 120
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.21,
|
861 |
+
"grad_norm": 2.674729585647583,
|
862 |
+
"learning_rate": 0.0009893307157429118,
|
863 |
+
"loss": 0.1559,
|
864 |
+
"step": 121
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.22,
|
868 |
+
"grad_norm": 0.9852035045623779,
|
869 |
+
"learning_rate": 0.0009891383126230102,
|
870 |
+
"loss": 0.2027,
|
871 |
+
"step": 122
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.22,
|
875 |
+
"grad_norm": 0.36689773201942444,
|
876 |
+
"learning_rate": 0.0009889442091798712,
|
877 |
+
"loss": 0.1498,
|
878 |
+
"step": 123
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.22,
|
882 |
+
"grad_norm": 0.104621522128582,
|
883 |
+
"learning_rate": 0.000988748406088229,
|
884 |
+
"loss": 0.1379,
|
885 |
+
"step": 124
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.22,
|
889 |
+
"grad_norm": 74.17496490478516,
|
890 |
+
"learning_rate": 0.0009885509040287268,
|
891 |
+
"loss": 0.7724,
|
892 |
+
"step": 125
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.22,
|
896 |
+
"grad_norm": 1.2943025827407837,
|
897 |
+
"learning_rate": 0.0009883517036879132,
|
898 |
+
"loss": 0.2643,
|
899 |
+
"step": 126
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.22,
|
903 |
+
"grad_norm": 0.828774094581604,
|
904 |
+
"learning_rate": 0.000988150805758241,
|
905 |
+
"loss": 0.1852,
|
906 |
+
"step": 127
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.23,
|
910 |
+
"grad_norm": 0.13165877759456635,
|
911 |
+
"learning_rate": 0.0009879482109380632,
|
912 |
+
"loss": 0.1429,
|
913 |
+
"step": 128
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.23,
|
917 |
+
"grad_norm": 0.662426769733429,
|
918 |
+
"learning_rate": 0.0009877439199316323,
|
919 |
+
"loss": 0.1643,
|
920 |
+
"step": 129
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.23,
|
924 |
+
"grad_norm": 0.6256189942359924,
|
925 |
+
"learning_rate": 0.0009875379334490962,
|
926 |
+
"loss": 0.157,
|
927 |
+
"step": 130
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.23,
|
931 |
+
"grad_norm": 0.5049256086349487,
|
932 |
+
"learning_rate": 0.0009873302522064972,
|
933 |
+
"loss": 0.1484,
|
934 |
+
"step": 131
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.23,
|
938 |
+
"grad_norm": 1.4133671522140503,
|
939 |
+
"learning_rate": 0.0009871208769257685,
|
940 |
+
"loss": 0.1736,
|
941 |
+
"step": 132
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.24,
|
945 |
+
"grad_norm": 0.7930824756622314,
|
946 |
+
"learning_rate": 0.0009869098083347323,
|
947 |
+
"loss": 0.1543,
|
948 |
+
"step": 133
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.24,
|
952 |
+
"grad_norm": 0.5717449188232422,
|
953 |
+
"learning_rate": 0.0009866970471670965,
|
954 |
+
"loss": 0.1338,
|
955 |
+
"step": 134
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.24,
|
959 |
+
"grad_norm": 0.582081139087677,
|
960 |
+
"learning_rate": 0.0009864825941624537,
|
961 |
+
"loss": 0.1692,
|
962 |
+
"step": 135
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.24,
|
966 |
+
"grad_norm": 10.226588249206543,
|
967 |
+
"learning_rate": 0.0009862664500662763,
|
968 |
+
"loss": 0.2425,
|
969 |
+
"step": 136
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.24,
|
973 |
+
"grad_norm": 1.1186953783035278,
|
974 |
+
"learning_rate": 0.0009860486156299164,
|
975 |
+
"loss": 0.2052,
|
976 |
+
"step": 137
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.24,
|
980 |
+
"grad_norm": 0.2953661382198334,
|
981 |
+
"learning_rate": 0.000985829091610601,
|
982 |
+
"loss": 0.1408,
|
983 |
+
"step": 138
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.25,
|
987 |
+
"grad_norm": 0.8647088408470154,
|
988 |
+
"learning_rate": 0.000985607878771431,
|
989 |
+
"loss": 0.1571,
|
990 |
+
"step": 139
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.25,
|
994 |
+
"grad_norm": 0.41964420676231384,
|
995 |
+
"learning_rate": 0.0009853849778813776,
|
996 |
+
"loss": 0.1477,
|
997 |
+
"step": 140
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.25,
|
1001 |
+
"grad_norm": 0.25675931572914124,
|
1002 |
+
"learning_rate": 0.0009851603897152803,
|
1003 |
+
"loss": 0.1398,
|
1004 |
+
"step": 141
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.25,
|
1008 |
+
"grad_norm": 0.2311631143093109,
|
1009 |
+
"learning_rate": 0.0009849341150538434,
|
1010 |
+
"loss": 0.1432,
|
1011 |
+
"step": 142
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.25,
|
1015 |
+
"eval_loss": 1.5366541147232056,
|
1016 |
+
"eval_runtime": 14.6962,
|
1017 |
+
"eval_samples_per_second": 32.457,
|
1018 |
+
"eval_steps_per_second": 8.165,
|
1019 |
+
"step": 142
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.25,
|
1023 |
+
"grad_norm": 41.83562469482422,
|
1024 |
+
"learning_rate": 0.0009847061546836339,
|
1025 |
+
"loss": 1.1525,
|
1026 |
+
"step": 143
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.25,
|
1030 |
+
"grad_norm": 0.27440375089645386,
|
1031 |
+
"learning_rate": 0.0009844765093970787,
|
1032 |
+
"loss": 0.1452,
|
1033 |
+
"step": 144
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.26,
|
1037 |
+
"grad_norm": 0.27643319964408875,
|
1038 |
+
"learning_rate": 0.0009842451799924616,
|
1039 |
+
"loss": 0.1069,
|
1040 |
+
"step": 145
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.26,
|
1044 |
+
"grad_norm": 0.21519601345062256,
|
1045 |
+
"learning_rate": 0.0009840121672739207,
|
1046 |
+
"loss": 0.1358,
|
1047 |
+
"step": 146
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.26,
|
1051 |
+
"grad_norm": 0.4073689877986908,
|
1052 |
+
"learning_rate": 0.0009837774720514456,
|
1053 |
+
"loss": 0.1545,
|
1054 |
+
"step": 147
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.26,
|
1058 |
+
"grad_norm": 0.13685636222362518,
|
1059 |
+
"learning_rate": 0.0009835410951408747,
|
1060 |
+
"loss": 0.1259,
|
1061 |
+
"step": 148
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.26,
|
1065 |
+
"grad_norm": 0.07474564015865326,
|
1066 |
+
"learning_rate": 0.000983303037363892,
|
1067 |
+
"loss": 0.1356,
|
1068 |
+
"step": 149
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.27,
|
1072 |
+
"grad_norm": 0.45116662979125977,
|
1073 |
+
"learning_rate": 0.0009830632995480241,
|
1074 |
+
"loss": 0.1379,
|
1075 |
+
"step": 150
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.27,
|
1079 |
+
"grad_norm": 0.1297813504934311,
|
1080 |
+
"learning_rate": 0.0009828218825266388,
|
1081 |
+
"loss": 0.1343,
|
1082 |
+
"step": 151
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.27,
|
1086 |
+
"grad_norm": 0.5846492052078247,
|
1087 |
+
"learning_rate": 0.00098257878713894,
|
1088 |
+
"loss": 0.1563,
|
1089 |
+
"step": 152
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.27,
|
1093 |
+
"grad_norm": 0.38457778096199036,
|
1094 |
+
"learning_rate": 0.0009823340142299662,
|
1095 |
+
"loss": 0.1477,
|
1096 |
+
"step": 153
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.27,
|
1100 |
+
"grad_norm": 0.09184035658836365,
|
1101 |
+
"learning_rate": 0.0009820875646505873,
|
1102 |
+
"loss": 0.1376,
|
1103 |
+
"step": 154
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.27,
|
1107 |
+
"grad_norm": 0.5166211128234863,
|
1108 |
+
"learning_rate": 0.0009818394392575019,
|
1109 |
+
"loss": 0.1498,
|
1110 |
+
"step": 155
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.28,
|
1114 |
+
"grad_norm": 0.2788640260696411,
|
1115 |
+
"learning_rate": 0.0009815896389132332,
|
1116 |
+
"loss": 0.1434,
|
1117 |
+
"step": 156
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.28,
|
1121 |
+
"grad_norm": 0.3762676417827606,
|
1122 |
+
"learning_rate": 0.0009813381644861276,
|
1123 |
+
"loss": 0.1482,
|
1124 |
+
"step": 157
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.28,
|
1128 |
+
"grad_norm": 0.3615610897541046,
|
1129 |
+
"learning_rate": 0.0009810850168503506,
|
1130 |
+
"loss": 0.1312,
|
1131 |
+
"step": 158
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.28,
|
1135 |
+
"grad_norm": 0.03483320027589798,
|
1136 |
+
"learning_rate": 0.0009808301968858837,
|
1137 |
+
"loss": 0.1239,
|
1138 |
+
"step": 159
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.28,
|
1142 |
+
"grad_norm": 0.5616227984428406,
|
1143 |
+
"learning_rate": 0.0009805737054785222,
|
1144 |
+
"loss": 0.1881,
|
1145 |
+
"step": 160
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.28,
|
1149 |
+
"grad_norm": 0.029542161151766777,
|
1150 |
+
"learning_rate": 0.000980315543519871,
|
1151 |
+
"loss": 0.1254,
|
1152 |
+
"step": 161
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.29,
|
1156 |
+
"grad_norm": 0.142581045627594,
|
1157 |
+
"learning_rate": 0.0009800557119073433,
|
1158 |
+
"loss": 0.1258,
|
1159 |
+
"step": 162
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.29,
|
1163 |
+
"grad_norm": 0.7289375066757202,
|
1164 |
+
"learning_rate": 0.0009797942115441546,
|
1165 |
+
"loss": 0.1526,
|
1166 |
+
"step": 163
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.29,
|
1170 |
+
"grad_norm": 0.6975064873695374,
|
1171 |
+
"learning_rate": 0.0009795310433393224,
|
1172 |
+
"loss": 0.1487,
|
1173 |
+
"step": 164
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.29,
|
1177 |
+
"grad_norm": 1.3072260618209839,
|
1178 |
+
"learning_rate": 0.0009792662082076617,
|
1179 |
+
"loss": 0.1712,
|
1180 |
+
"step": 165
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.29,
|
1184 |
+
"grad_norm": 0.2993917465209961,
|
1185 |
+
"learning_rate": 0.000978999707069782,
|
1186 |
+
"loss": 0.1424,
|
1187 |
+
"step": 166
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.3,
|
1191 |
+
"grad_norm": 0.3258236050605774,
|
1192 |
+
"learning_rate": 0.0009787315408520839,
|
1193 |
+
"loss": 0.135,
|
1194 |
+
"step": 167
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.3,
|
1198 |
+
"grad_norm": 0.26566603779792786,
|
1199 |
+
"learning_rate": 0.000978461710486756,
|
1200 |
+
"loss": 0.1441,
|
1201 |
+
"step": 168
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.3,
|
1205 |
+
"grad_norm": 1.1709599494934082,
|
1206 |
+
"learning_rate": 0.0009781902169117718,
|
1207 |
+
"loss": 0.2084,
|
1208 |
+
"step": 169
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.3,
|
1212 |
+
"grad_norm": 0.6554279923439026,
|
1213 |
+
"learning_rate": 0.000977917061070887,
|
1214 |
+
"loss": 0.1634,
|
1215 |
+
"step": 170
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.3,
|
1219 |
+
"grad_norm": 0.1635073721408844,
|
1220 |
+
"learning_rate": 0.000977642243913635,
|
1221 |
+
"loss": 0.1371,
|
1222 |
+
"step": 171
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 0.3,
|
1226 |
+
"grad_norm": 0.4419834017753601,
|
1227 |
+
"learning_rate": 0.0009773657663953242,
|
1228 |
+
"loss": 0.1523,
|
1229 |
+
"step": 172
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.31,
|
1233 |
+
"grad_norm": 0.839259147644043,
|
1234 |
+
"learning_rate": 0.000977087629477035,
|
1235 |
+
"loss": 0.1628,
|
1236 |
+
"step": 173
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 0.31,
|
1240 |
+
"grad_norm": 0.1979222148656845,
|
1241 |
+
"learning_rate": 0.0009768078341256155,
|
1242 |
+
"loss": 0.1367,
|
1243 |
+
"step": 174
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 0.31,
|
1247 |
+
"grad_norm": 0.2939910888671875,
|
1248 |
+
"learning_rate": 0.0009765263813136795,
|
1249 |
+
"loss": 0.1349,
|
1250 |
+
"step": 175
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.31,
|
1254 |
+
"grad_norm": 0.19882674515247345,
|
1255 |
+
"learning_rate": 0.0009762432720196024,
|
1256 |
+
"loss": 0.1424,
|
1257 |
+
"step": 176
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.31,
|
1261 |
+
"grad_norm": 0.07146954536437988,
|
1262 |
+
"learning_rate": 0.000975958507227517,
|
1263 |
+
"loss": 0.1237,
|
1264 |
+
"step": 177
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.31,
|
1268 |
+
"grad_norm": 0.5031868815422058,
|
1269 |
+
"learning_rate": 0.0009756720879273117,
|
1270 |
+
"loss": 0.1592,
|
1271 |
+
"step": 178
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.32,
|
1275 |
+
"grad_norm": 0.14860151708126068,
|
1276 |
+
"learning_rate": 0.0009753840151146258,
|
1277 |
+
"loss": 0.1396,
|
1278 |
+
"step": 179
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.32,
|
1282 |
+
"grad_norm": 0.10280521959066391,
|
1283 |
+
"learning_rate": 0.0009750942897908468,
|
1284 |
+
"loss": 0.1333,
|
1285 |
+
"step": 180
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.32,
|
1289 |
+
"grad_norm": 0.4652903974056244,
|
1290 |
+
"learning_rate": 0.0009748029129631061,
|
1291 |
+
"loss": 0.1421,
|
1292 |
+
"step": 181
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.32,
|
1296 |
+
"grad_norm": 0.3985591530799866,
|
1297 |
+
"learning_rate": 0.0009745098856442768,
|
1298 |
+
"loss": 0.1459,
|
1299 |
+
"step": 182
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.32,
|
1303 |
+
"grad_norm": 0.20321591198444366,
|
1304 |
+
"learning_rate": 0.0009742152088529683,
|
1305 |
+
"loss": 0.1381,
|
1306 |
+
"step": 183
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.33,
|
1310 |
+
"grad_norm": 0.7694361805915833,
|
1311 |
+
"learning_rate": 0.0009739188836135246,
|
1312 |
+
"loss": 0.1676,
|
1313 |
+
"step": 184
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.33,
|
1317 |
+
"grad_norm": 0.04469340294599533,
|
1318 |
+
"learning_rate": 0.0009736209109560201,
|
1319 |
+
"loss": 0.136,
|
1320 |
+
"step": 185
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.33,
|
1324 |
+
"grad_norm": 0.08576061576604843,
|
1325 |
+
"learning_rate": 0.0009733212919162549,
|
1326 |
+
"loss": 0.1408,
|
1327 |
+
"step": 186
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.33,
|
1331 |
+
"grad_norm": 0.042906519025564194,
|
1332 |
+
"learning_rate": 0.0009730200275357535,
|
1333 |
+
"loss": 0.1364,
|
1334 |
+
"step": 187
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.33,
|
1338 |
+
"grad_norm": 0.30054494738578796,
|
1339 |
+
"learning_rate": 0.0009727171188617588,
|
1340 |
+
"loss": 0.1539,
|
1341 |
+
"step": 188
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.33,
|
1345 |
+
"grad_norm": 0.05149005725979805,
|
1346 |
+
"learning_rate": 0.0009724125669472299,
|
1347 |
+
"loss": 0.1352,
|
1348 |
+
"step": 189
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.34,
|
1352 |
+
"grad_norm": 0.1381620466709137,
|
1353 |
+
"learning_rate": 0.0009721063728508383,
|
1354 |
+
"loss": 0.1409,
|
1355 |
+
"step": 190
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.34,
|
1359 |
+
"grad_norm": 0.37344205379486084,
|
1360 |
+
"learning_rate": 0.0009717985376369639,
|
1361 |
+
"loss": 0.1299,
|
1362 |
+
"step": 191
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.34,
|
1366 |
+
"grad_norm": 0.1037706583738327,
|
1367 |
+
"learning_rate": 0.0009714890623756912,
|
1368 |
+
"loss": 0.1341,
|
1369 |
+
"step": 192
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 0.34,
|
1373 |
+
"grad_norm": 0.14189712703227997,
|
1374 |
+
"learning_rate": 0.0009711779481428056,
|
1375 |
+
"loss": 0.1418,
|
1376 |
+
"step": 193
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.34,
|
1380 |
+
"grad_norm": 0.15108801424503326,
|
1381 |
+
"learning_rate": 0.0009708651960197903,
|
1382 |
+
"loss": 0.142,
|
1383 |
+
"step": 194
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.34,
|
1387 |
+
"grad_norm": 0.037045519798994064,
|
1388 |
+
"learning_rate": 0.0009705508070938218,
|
1389 |
+
"loss": 0.1315,
|
1390 |
+
"step": 195
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.35,
|
1394 |
+
"grad_norm": 0.23301652073860168,
|
1395 |
+
"learning_rate": 0.0009702347824577666,
|
1396 |
+
"loss": 0.1396,
|
1397 |
+
"step": 196
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 0.35,
|
1401 |
+
"grad_norm": 0.08476269990205765,
|
1402 |
+
"learning_rate": 0.0009699171232101768,
|
1403 |
+
"loss": 0.1392,
|
1404 |
+
"step": 197
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.35,
|
1408 |
+
"grad_norm": 0.4222690463066101,
|
1409 |
+
"learning_rate": 0.000969597830455287,
|
1410 |
+
"loss": 0.1463,
|
1411 |
+
"step": 198
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 0.35,
|
1415 |
+
"grad_norm": 0.3234136402606964,
|
1416 |
+
"learning_rate": 0.0009692769053030099,
|
1417 |
+
"loss": 0.1257,
|
1418 |
+
"step": 199
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.35,
|
1422 |
+
"grad_norm": 0.04025443643331528,
|
1423 |
+
"learning_rate": 0.0009689543488689332,
|
1424 |
+
"loss": 0.1303,
|
1425 |
+
"step": 200
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.36,
|
1429 |
+
"grad_norm": 0.07074520736932755,
|
1430 |
+
"learning_rate": 0.0009686301622743144,
|
1431 |
+
"loss": 0.1289,
|
1432 |
+
"step": 201
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 0.36,
|
1436 |
+
"grad_norm": 0.0788850486278534,
|
1437 |
+
"learning_rate": 0.0009683043466460782,
|
1438 |
+
"loss": 0.1236,
|
1439 |
+
"step": 202
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.36,
|
1443 |
+
"grad_norm": 0.525541365146637,
|
1444 |
+
"learning_rate": 0.000967976903116812,
|
1445 |
+
"loss": 0.1564,
|
1446 |
+
"step": 203
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 0.36,
|
1450 |
+
"grad_norm": 0.6145509481430054,
|
1451 |
+
"learning_rate": 0.0009676478328247623,
|
1452 |
+
"loss": 0.156,
|
1453 |
+
"step": 204
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 0.36,
|
1457 |
+
"grad_norm": 0.230132058262825,
|
1458 |
+
"learning_rate": 0.0009673171369138296,
|
1459 |
+
"loss": 0.1425,
|
1460 |
+
"step": 205
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.36,
|
1464 |
+
"grad_norm": 0.03262978792190552,
|
1465 |
+
"learning_rate": 0.0009669848165335666,
|
1466 |
+
"loss": 0.1297,
|
1467 |
+
"step": 206
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.37,
|
1471 |
+
"grad_norm": 0.0462469644844532,
|
1472 |
+
"learning_rate": 0.0009666508728391718,
|
1473 |
+
"loss": 0.1177,
|
1474 |
+
"step": 207
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.37,
|
1478 |
+
"grad_norm": 0.06880385428667068,
|
1479 |
+
"learning_rate": 0.0009663153069914874,
|
1480 |
+
"loss": 0.1207,
|
1481 |
+
"step": 208
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.37,
|
1485 |
+
"grad_norm": 0.4248260259628296,
|
1486 |
+
"learning_rate": 0.000965978120156994,
|
1487 |
+
"loss": 0.1571,
|
1488 |
+
"step": 209
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 0.37,
|
1492 |
+
"grad_norm": 0.060492075979709625,
|
1493 |
+
"learning_rate": 0.0009656393135078068,
|
1494 |
+
"loss": 0.1219,
|
1495 |
+
"step": 210
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.37,
|
1499 |
+
"grad_norm": 0.12135621905326843,
|
1500 |
+
"learning_rate": 0.0009652988882216725,
|
1501 |
+
"loss": 0.1323,
|
1502 |
+
"step": 211
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.38,
|
1506 |
+
"grad_norm": 0.252119243144989,
|
1507 |
+
"learning_rate": 0.0009649568454819637,
|
1508 |
+
"loss": 0.1366,
|
1509 |
+
"step": 212
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.38,
|
1513 |
+
"grad_norm": 0.5283567905426025,
|
1514 |
+
"learning_rate": 0.0009646131864776761,
|
1515 |
+
"loss": 0.1246,
|
1516 |
+
"step": 213
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.38,
|
1520 |
+
"grad_norm": 2.224665880203247,
|
1521 |
+
"learning_rate": 0.0009642679124034233,
|
1522 |
+
"loss": 0.2582,
|
1523 |
+
"step": 214
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.38,
|
1527 |
+
"grad_norm": 1.9277523756027222,
|
1528 |
+
"learning_rate": 0.0009639210244594335,
|
1529 |
+
"loss": 0.2131,
|
1530 |
+
"step": 215
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.38,
|
1534 |
+
"grad_norm": 0.5668452978134155,
|
1535 |
+
"learning_rate": 0.0009635725238515446,
|
1536 |
+
"loss": 0.141,
|
1537 |
+
"step": 216
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.38,
|
1541 |
+
"grad_norm": 0.13912492990493774,
|
1542 |
+
"learning_rate": 0.000963222411791201,
|
1543 |
+
"loss": 0.1418,
|
1544 |
+
"step": 217
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.39,
|
1548 |
+
"grad_norm": 0.39307814836502075,
|
1549 |
+
"learning_rate": 0.0009628706894954479,
|
1550 |
+
"loss": 0.1477,
|
1551 |
+
"step": 218
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.39,
|
1555 |
+
"grad_norm": 0.26248928904533386,
|
1556 |
+
"learning_rate": 0.000962517358186929,
|
1557 |
+
"loss": 0.1315,
|
1558 |
+
"step": 219
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.39,
|
1562 |
+
"grad_norm": 0.2875257730484009,
|
1563 |
+
"learning_rate": 0.0009621624190938803,
|
1564 |
+
"loss": 0.1321,
|
1565 |
+
"step": 220
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 0.39,
|
1569 |
+
"grad_norm": 0.6386964917182922,
|
1570 |
+
"learning_rate": 0.0009618058734501269,
|
1571 |
+
"loss": 0.1668,
|
1572 |
+
"step": 221
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 0.39,
|
1576 |
+
"grad_norm": 0.16165001690387726,
|
1577 |
+
"learning_rate": 0.0009614477224950789,
|
1578 |
+
"loss": 0.1272,
|
1579 |
+
"step": 222
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.39,
|
1583 |
+
"grad_norm": 0.6959558129310608,
|
1584 |
+
"learning_rate": 0.0009610879674737262,
|
1585 |
+
"loss": 0.1381,
|
1586 |
+
"step": 223
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.4,
|
1590 |
+
"grad_norm": 0.1701437532901764,
|
1591 |
+
"learning_rate": 0.0009607266096366352,
|
1592 |
+
"loss": 0.1366,
|
1593 |
+
"step": 224
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.4,
|
1597 |
+
"grad_norm": 0.2511409819126129,
|
1598 |
+
"learning_rate": 0.0009603636502399437,
|
1599 |
+
"loss": 0.126,
|
1600 |
+
"step": 225
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.4,
|
1604 |
+
"grad_norm": 0.04554220288991928,
|
1605 |
+
"learning_rate": 0.0009599990905453566,
|
1606 |
+
"loss": 0.1321,
|
1607 |
+
"step": 226
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 0.4,
|
1611 |
+
"grad_norm": 0.3964705765247345,
|
1612 |
+
"learning_rate": 0.000959632931820142,
|
1613 |
+
"loss": 0.1383,
|
1614 |
+
"step": 227
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.4,
|
1618 |
+
"grad_norm": 0.10925984382629395,
|
1619 |
+
"learning_rate": 0.0009592651753371264,
|
1620 |
+
"loss": 0.1226,
|
1621 |
+
"step": 228
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.41,
|
1625 |
+
"grad_norm": 0.19012318551540375,
|
1626 |
+
"learning_rate": 0.0009588958223746903,
|
1627 |
+
"loss": 0.1255,
|
1628 |
+
"step": 229
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.41,
|
1632 |
+
"grad_norm": 0.23432157933712006,
|
1633 |
+
"learning_rate": 0.0009585248742167639,
|
1634 |
+
"loss": 0.1152,
|
1635 |
+
"step": 230
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.41,
|
1639 |
+
"grad_norm": 0.1737753301858902,
|
1640 |
+
"learning_rate": 0.0009581523321528223,
|
1641 |
+
"loss": 0.1468,
|
1642 |
+
"step": 231
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.41,
|
1646 |
+
"grad_norm": 0.2625434100627899,
|
1647 |
+
"learning_rate": 0.0009577781974778817,
|
1648 |
+
"loss": 0.1296,
|
1649 |
+
"step": 232
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 0.41,
|
1653 |
+
"grad_norm": 0.3056884706020355,
|
1654 |
+
"learning_rate": 0.000957402471492494,
|
1655 |
+
"loss": 0.1574,
|
1656 |
+
"step": 233
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.41,
|
1660 |
+
"grad_norm": 0.4111999273300171,
|
1661 |
+
"learning_rate": 0.0009570251555027432,
|
1662 |
+
"loss": 0.1434,
|
1663 |
+
"step": 234
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.42,
|
1667 |
+
"grad_norm": 0.056673482060432434,
|
1668 |
+
"learning_rate": 0.0009566462508202401,
|
1669 |
+
"loss": 0.1337,
|
1670 |
+
"step": 235
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.42,
|
1674 |
+
"grad_norm": 0.3861597180366516,
|
1675 |
+
"learning_rate": 0.0009562657587621184,
|
1676 |
+
"loss": 0.1609,
|
1677 |
+
"step": 236
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.42,
|
1681 |
+
"grad_norm": 0.35893362760543823,
|
1682 |
+
"learning_rate": 0.0009558836806510292,
|
1683 |
+
"loss": 0.1189,
|
1684 |
+
"step": 237
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.42,
|
1688 |
+
"grad_norm": 0.40538331866264343,
|
1689 |
+
"learning_rate": 0.0009555000178151374,
|
1690 |
+
"loss": 0.1504,
|
1691 |
+
"step": 238
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.42,
|
1695 |
+
"grad_norm": 81.36141967773438,
|
1696 |
+
"learning_rate": 0.0009551147715881167,
|
1697 |
+
"loss": 4.7235,
|
1698 |
+
"step": 239
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.42,
|
1702 |
+
"grad_norm": 0.21178042888641357,
|
1703 |
+
"learning_rate": 0.0009547279433091446,
|
1704 |
+
"loss": 0.1139,
|
1705 |
+
"step": 240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.43,
|
1709 |
+
"grad_norm": 0.27380529046058655,
|
1710 |
+
"learning_rate": 0.0009543395343228983,
|
1711 |
+
"loss": 0.1504,
|
1712 |
+
"step": 241
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.43,
|
1716 |
+
"grad_norm": 41.42683410644531,
|
1717 |
+
"learning_rate": 0.0009539495459795498,
|
1718 |
+
"loss": 1.2477,
|
1719 |
+
"step": 242
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.43,
|
1723 |
+
"grad_norm": 0.14853385090827942,
|
1724 |
+
"learning_rate": 0.0009535579796347612,
|
1725 |
+
"loss": 0.1343,
|
1726 |
+
"step": 243
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.43,
|
1730 |
+
"grad_norm": 0.3484509289264679,
|
1731 |
+
"learning_rate": 0.0009531648366496798,
|
1732 |
+
"loss": 0.15,
|
1733 |
+
"step": 244
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.43,
|
1737 |
+
"grad_norm": 0.20152732729911804,
|
1738 |
+
"learning_rate": 0.0009527701183909336,
|
1739 |
+
"loss": 0.1399,
|
1740 |
+
"step": 245
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.44,
|
1744 |
+
"grad_norm": 80.84031677246094,
|
1745 |
+
"learning_rate": 0.000952373826230627,
|
1746 |
+
"loss": 3.1939,
|
1747 |
+
"step": 246
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.44,
|
1751 |
+
"grad_norm": 15.475607872009277,
|
1752 |
+
"learning_rate": 0.0009519759615463346,
|
1753 |
+
"loss": 3.3935,
|
1754 |
+
"step": 247
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.44,
|
1758 |
+
"grad_norm": 77.19477081298828,
|
1759 |
+
"learning_rate": 0.0009515765257210979,
|
1760 |
+
"loss": 6.5034,
|
1761 |
+
"step": 248
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.44,
|
1765 |
+
"grad_norm": 0.1174071803689003,
|
1766 |
+
"learning_rate": 0.0009511755201434205,
|
1767 |
+
"loss": 0.1212,
|
1768 |
+
"step": 249
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.44,
|
1772 |
+
"grad_norm": 16.503982543945312,
|
1773 |
+
"learning_rate": 0.0009507729462072614,
|
1774 |
+
"loss": 0.3753,
|
1775 |
+
"step": 250
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.44,
|
1779 |
+
"grad_norm": 76.65412902832031,
|
1780 |
+
"learning_rate": 0.0009503688053120326,
|
1781 |
+
"loss": 0.9386,
|
1782 |
+
"step": 251
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.45,
|
1786 |
+
"grad_norm": 94.82160186767578,
|
1787 |
+
"learning_rate": 0.0009499630988625925,
|
1788 |
+
"loss": 4.7449,
|
1789 |
+
"step": 252
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.45,
|
1793 |
+
"grad_norm": 0.2721010148525238,
|
1794 |
+
"learning_rate": 0.0009495558282692421,
|
1795 |
+
"loss": 0.1358,
|
1796 |
+
"step": 253
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.45,
|
1800 |
+
"grad_norm": 0.5150814056396484,
|
1801 |
+
"learning_rate": 0.0009491469949477187,
|
1802 |
+
"loss": 0.1622,
|
1803 |
+
"step": 254
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.45,
|
1807 |
+
"grad_norm": 51.050167083740234,
|
1808 |
+
"learning_rate": 0.0009487366003191931,
|
1809 |
+
"loss": 0.7818,
|
1810 |
+
"step": 255
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.45,
|
1814 |
+
"grad_norm": 11.698090553283691,
|
1815 |
+
"learning_rate": 0.0009483246458102625,
|
1816 |
+
"loss": 0.3862,
|
1817 |
+
"step": 256
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.45,
|
1821 |
+
"grad_norm": 0.648543655872345,
|
1822 |
+
"learning_rate": 0.0009479111328529472,
|
1823 |
+
"loss": 0.1884,
|
1824 |
+
"step": 257
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.46,
|
1828 |
+
"grad_norm": 0.745293140411377,
|
1829 |
+
"learning_rate": 0.0009474960628846843,
|
1830 |
+
"loss": 0.1562,
|
1831 |
+
"step": 258
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.46,
|
1835 |
+
"grad_norm": 0.17890043556690216,
|
1836 |
+
"learning_rate": 0.0009470794373483235,
|
1837 |
+
"loss": 0.1425,
|
1838 |
+
"step": 259
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.46,
|
1842 |
+
"grad_norm": 0.5058090686798096,
|
1843 |
+
"learning_rate": 0.0009466612576921223,
|
1844 |
+
"loss": 0.17,
|
1845 |
+
"step": 260
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.46,
|
1849 |
+
"grad_norm": 1.3177820444107056,
|
1850 |
+
"learning_rate": 0.00094624152536974,
|
1851 |
+
"loss": 0.15,
|
1852 |
+
"step": 261
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.46,
|
1856 |
+
"grad_norm": 0.49652573466300964,
|
1857 |
+
"learning_rate": 0.0009458202418402337,
|
1858 |
+
"loss": 0.145,
|
1859 |
+
"step": 262
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.47,
|
1863 |
+
"grad_norm": 11.423394203186035,
|
1864 |
+
"learning_rate": 0.0009453974085680526,
|
1865 |
+
"loss": 0.349,
|
1866 |
+
"step": 263
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.47,
|
1870 |
+
"grad_norm": 1.5422337055206299,
|
1871 |
+
"learning_rate": 0.0009449730270230326,
|
1872 |
+
"loss": 0.211,
|
1873 |
+
"step": 264
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.47,
|
1877 |
+
"grad_norm": 103.68435668945312,
|
1878 |
+
"learning_rate": 0.0009445470986803921,
|
1879 |
+
"loss": 17.4069,
|
1880 |
+
"step": 265
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.47,
|
1884 |
+
"grad_norm": 54.51758575439453,
|
1885 |
+
"learning_rate": 0.0009441196250207267,
|
1886 |
+
"loss": 15.685,
|
1887 |
+
"step": 266
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.47,
|
1891 |
+
"grad_norm": 14.596623420715332,
|
1892 |
+
"learning_rate": 0.0009436906075300032,
|
1893 |
+
"loss": 0.791,
|
1894 |
+
"step": 267
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.47,
|
1898 |
+
"grad_norm": 3.3164780139923096,
|
1899 |
+
"learning_rate": 0.000943260047699555,
|
1900 |
+
"loss": 0.3611,
|
1901 |
+
"step": 268
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.48,
|
1905 |
+
"grad_norm": 0.3087855577468872,
|
1906 |
+
"learning_rate": 0.0009428279470260776,
|
1907 |
+
"loss": 0.1332,
|
1908 |
+
"step": 269
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.48,
|
1912 |
+
"grad_norm": 1.1544523239135742,
|
1913 |
+
"learning_rate": 0.0009423943070116219,
|
1914 |
+
"loss": 0.2405,
|
1915 |
+
"step": 270
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.48,
|
1919 |
+
"grad_norm": 0.27010253071784973,
|
1920 |
+
"learning_rate": 0.00094195912916359,
|
1921 |
+
"loss": 0.1241,
|
1922 |
+
"step": 271
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.48,
|
1926 |
+
"grad_norm": 0.2287709265947342,
|
1927 |
+
"learning_rate": 0.0009415224149947306,
|
1928 |
+
"loss": 0.1366,
|
1929 |
+
"step": 272
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.48,
|
1933 |
+
"grad_norm": 0.5216432809829712,
|
1934 |
+
"learning_rate": 0.0009410841660231316,
|
1935 |
+
"loss": 0.1641,
|
1936 |
+
"step": 273
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.48,
|
1940 |
+
"grad_norm": 1.3091949224472046,
|
1941 |
+
"learning_rate": 0.0009406443837722167,
|
1942 |
+
"loss": 0.2524,
|
1943 |
+
"step": 274
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.49,
|
1947 |
+
"grad_norm": 0.11813609302043915,
|
1948 |
+
"learning_rate": 0.0009402030697707398,
|
1949 |
+
"loss": 0.1353,
|
1950 |
+
"step": 275
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.49,
|
1954 |
+
"grad_norm": 1.3709551095962524,
|
1955 |
+
"learning_rate": 0.000939760225552779,
|
1956 |
+
"loss": 0.2714,
|
1957 |
+
"step": 276
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.49,
|
1961 |
+
"grad_norm": 8.527563095092773,
|
1962 |
+
"learning_rate": 0.0009393158526577322,
|
1963 |
+
"loss": 0.1955,
|
1964 |
+
"step": 277
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.49,
|
1968 |
+
"grad_norm": 21.874027252197266,
|
1969 |
+
"learning_rate": 0.0009388699526303105,
|
1970 |
+
"loss": 0.2398,
|
1971 |
+
"step": 278
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.49,
|
1975 |
+
"grad_norm": 51.793731689453125,
|
1976 |
+
"learning_rate": 0.0009384225270205339,
|
1977 |
+
"loss": 1.3069,
|
1978 |
+
"step": 279
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.5,
|
1982 |
+
"grad_norm": 0.6711062788963318,
|
1983 |
+
"learning_rate": 0.0009379735773837259,
|
1984 |
+
"loss": 0.1664,
|
1985 |
+
"step": 280
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 0.5,
|
1989 |
+
"grad_norm": 5.93789005279541,
|
1990 |
+
"learning_rate": 0.0009375231052805072,
|
1991 |
+
"loss": 0.2455,
|
1992 |
+
"step": 281
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 0.5,
|
1996 |
+
"grad_norm": 62.527198791503906,
|
1997 |
+
"learning_rate": 0.0009370711122767912,
|
1998 |
+
"loss": 6.6447,
|
1999 |
+
"step": 282
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 0.5,
|
2003 |
+
"grad_norm": 22.35348129272461,
|
2004 |
+
"learning_rate": 0.000936617599943778,
|
2005 |
+
"loss": 2.5015,
|
2006 |
+
"step": 283
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.5,
|
2010 |
+
"grad_norm": 0.7277780175209045,
|
2011 |
+
"learning_rate": 0.0009361625698579493,
|
2012 |
+
"loss": 0.1667,
|
2013 |
+
"step": 284
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.5,
|
2017 |
+
"eval_loss": 0.14179374277591705,
|
2018 |
+
"eval_runtime": 14.7139,
|
2019 |
+
"eval_samples_per_second": 32.418,
|
2020 |
+
"eval_steps_per_second": 8.156,
|
2021 |
+
"step": 284
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 0.5,
|
2025 |
+
"grad_norm": 0.26271358132362366,
|
2026 |
+
"learning_rate": 0.0009357060236010625,
|
2027 |
+
"loss": 0.1429,
|
2028 |
+
"step": 285
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 0.51,
|
2032 |
+
"grad_norm": 21.24464988708496,
|
2033 |
+
"learning_rate": 0.0009352479627601457,
|
2034 |
+
"loss": 2.0706,
|
2035 |
+
"step": 286
|
2036 |
+
},
|
2037 |
+
{
|
2038 |
+
"epoch": 0.51,
|
2039 |
+
"grad_norm": 6.5764265060424805,
|
2040 |
+
"learning_rate": 0.0009347883889274922,
|
2041 |
+
"loss": 0.3337,
|
2042 |
+
"step": 287
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 0.51,
|
2046 |
+
"grad_norm": 0.6868380904197693,
|
2047 |
+
"learning_rate": 0.0009343273037006539,
|
2048 |
+
"loss": 0.1994,
|
2049 |
+
"step": 288
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.51,
|
2053 |
+
"grad_norm": 0.9018234610557556,
|
2054 |
+
"learning_rate": 0.0009338647086824372,
|
2055 |
+
"loss": 0.1908,
|
2056 |
+
"step": 289
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"epoch": 0.51,
|
2060 |
+
"grad_norm": 1.7751502990722656,
|
2061 |
+
"learning_rate": 0.0009334006054808966,
|
2062 |
+
"loss": 0.2028,
|
2063 |
+
"step": 290
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 0.51,
|
2067 |
+
"grad_norm": 0.5386408567428589,
|
2068 |
+
"learning_rate": 0.0009329349957093293,
|
2069 |
+
"loss": 0.1853,
|
2070 |
+
"step": 291
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 0.52,
|
2074 |
+
"grad_norm": 1.4171103239059448,
|
2075 |
+
"learning_rate": 0.0009324678809862695,
|
2076 |
+
"loss": 0.3597,
|
2077 |
+
"step": 292
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 0.52,
|
2081 |
+
"grad_norm": 0.4105970561504364,
|
2082 |
+
"learning_rate": 0.0009319992629354827,
|
2083 |
+
"loss": 0.1344,
|
2084 |
+
"step": 293
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 0.52,
|
2088 |
+
"grad_norm": 0.26628127694129944,
|
2089 |
+
"learning_rate": 0.000931529143185961,
|
2090 |
+
"loss": 0.1453,
|
2091 |
+
"step": 294
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.52,
|
2095 |
+
"grad_norm": 14.981964111328125,
|
2096 |
+
"learning_rate": 0.0009310575233719154,
|
2097 |
+
"loss": 0.2563,
|
2098 |
+
"step": 295
|
2099 |
+
},
|
2100 |
+
{
|
2101 |
+
"epoch": 0.52,
|
2102 |
+
"grad_norm": 0.6945788264274597,
|
2103 |
+
"learning_rate": 0.0009305844051327725,
|
2104 |
+
"loss": 0.1229,
|
2105 |
+
"step": 296
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 0.53,
|
2109 |
+
"grad_norm": 31.034496307373047,
|
2110 |
+
"learning_rate": 0.000930109790113167,
|
2111 |
+
"loss": 1.2974,
|
2112 |
+
"step": 297
|
2113 |
+
},
|
2114 |
+
{
|
2115 |
+
"epoch": 0.53,
|
2116 |
+
"grad_norm": 1.5794603824615479,
|
2117 |
+
"learning_rate": 0.0009296336799629368,
|
2118 |
+
"loss": 0.22,
|
2119 |
+
"step": 298
|
2120 |
+
},
|
2121 |
+
{
|
2122 |
+
"epoch": 0.53,
|
2123 |
+
"grad_norm": 0.33219394087791443,
|
2124 |
+
"learning_rate": 0.0009291560763371172,
|
2125 |
+
"loss": 0.1262,
|
2126 |
+
"step": 299
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 0.53,
|
2130 |
+
"grad_norm": 2.597118377685547,
|
2131 |
+
"learning_rate": 0.000928676980895935,
|
2132 |
+
"loss": 0.4026,
|
2133 |
+
"step": 300
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.53,
|
2137 |
+
"grad_norm": 13.547090530395508,
|
2138 |
+
"learning_rate": 0.0009281963953048029,
|
2139 |
+
"loss": 1.3086,
|
2140 |
+
"step": 301
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"epoch": 0.53,
|
2144 |
+
"grad_norm": 1.289302945137024,
|
2145 |
+
"learning_rate": 0.0009277143212343134,
|
2146 |
+
"loss": 0.2215,
|
2147 |
+
"step": 302
|
2148 |
+
},
|
2149 |
+
{
|
2150 |
+
"epoch": 0.54,
|
2151 |
+
"grad_norm": 1.2176313400268555,
|
2152 |
+
"learning_rate": 0.0009272307603602334,
|
2153 |
+
"loss": 0.15,
|
2154 |
+
"step": 303
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 0.54,
|
2158 |
+
"grad_norm": 4.436944007873535,
|
2159 |
+
"learning_rate": 0.0009267457143634979,
|
2160 |
+
"loss": 0.514,
|
2161 |
+
"step": 304
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 0.54,
|
2165 |
+
"grad_norm": 29.960241317749023,
|
2166 |
+
"learning_rate": 0.0009262591849302047,
|
2167 |
+
"loss": 3.5389,
|
2168 |
+
"step": 305
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 0.54,
|
2172 |
+
"grad_norm": 5.514049530029297,
|
2173 |
+
"learning_rate": 0.0009257711737516082,
|
2174 |
+
"loss": 0.2902,
|
2175 |
+
"step": 306
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 0.54,
|
2179 |
+
"grad_norm": 2.331019401550293,
|
2180 |
+
"learning_rate": 0.0009252816825241135,
|
2181 |
+
"loss": 0.2775,
|
2182 |
+
"step": 307
|
2183 |
+
},
|
2184 |
+
{
|
2185 |
+
"epoch": 0.54,
|
2186 |
+
"grad_norm": 0.5708584189414978,
|
2187 |
+
"learning_rate": 0.0009247907129492707,
|
2188 |
+
"loss": 0.1438,
|
2189 |
+
"step": 308
|
2190 |
+
},
|
2191 |
+
{
|
2192 |
+
"epoch": 0.55,
|
2193 |
+
"grad_norm": 2.16607928276062,
|
2194 |
+
"learning_rate": 0.0009242982667337685,
|
2195 |
+
"loss": 0.2383,
|
2196 |
+
"step": 309
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 0.55,
|
2200 |
+
"grad_norm": 1.5346423387527466,
|
2201 |
+
"learning_rate": 0.0009238043455894293,
|
2202 |
+
"loss": 0.1793,
|
2203 |
+
"step": 310
|
2204 |
+
},
|
2205 |
+
{
|
2206 |
+
"epoch": 0.55,
|
2207 |
+
"grad_norm": 0.6200052499771118,
|
2208 |
+
"learning_rate": 0.000923308951233202,
|
2209 |
+
"loss": 0.1473,
|
2210 |
+
"step": 311
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 0.55,
|
2214 |
+
"grad_norm": 64.87612915039062,
|
2215 |
+
"learning_rate": 0.0009228120853871572,
|
2216 |
+
"loss": 0.8875,
|
2217 |
+
"step": 312
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 0.55,
|
2221 |
+
"grad_norm": 1.077471137046814,
|
2222 |
+
"learning_rate": 0.0009223137497784797,
|
2223 |
+
"loss": 0.2114,
|
2224 |
+
"step": 313
|
2225 |
+
},
|
2226 |
+
{
|
2227 |
+
"epoch": 0.56,
|
2228 |
+
"grad_norm": 3.5934722423553467,
|
2229 |
+
"learning_rate": 0.0009218139461394644,
|
2230 |
+
"loss": 0.2852,
|
2231 |
+
"step": 314
|
2232 |
+
},
|
2233 |
+
{
|
2234 |
+
"epoch": 0.56,
|
2235 |
+
"grad_norm": 0.10276800394058228,
|
2236 |
+
"learning_rate": 0.0009213126762075088,
|
2237 |
+
"loss": 0.1365,
|
2238 |
+
"step": 315
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 0.56,
|
2242 |
+
"grad_norm": 3.9422831535339355,
|
2243 |
+
"learning_rate": 0.0009208099417251077,
|
2244 |
+
"loss": 0.2949,
|
2245 |
+
"step": 316
|
2246 |
+
},
|
2247 |
+
{
|
2248 |
+
"epoch": 0.56,
|
2249 |
+
"grad_norm": 1.7574914693832397,
|
2250 |
+
"learning_rate": 0.0009203057444398468,
|
2251 |
+
"loss": 0.2621,
|
2252 |
+
"step": 317
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 0.56,
|
2256 |
+
"grad_norm": 0.29479530453681946,
|
2257 |
+
"learning_rate": 0.0009198000861043967,
|
2258 |
+
"loss": 0.1341,
|
2259 |
+
"step": 318
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.56,
|
2263 |
+
"grad_norm": 0.5362827181816101,
|
2264 |
+
"learning_rate": 0.0009192929684765068,
|
2265 |
+
"loss": 0.1398,
|
2266 |
+
"step": 319
|
2267 |
+
},
|
2268 |
+
{
|
2269 |
+
"epoch": 0.57,
|
2270 |
+
"grad_norm": 0.8159481287002563,
|
2271 |
+
"learning_rate": 0.0009187843933189994,
|
2272 |
+
"loss": 0.1863,
|
2273 |
+
"step": 320
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 0.57,
|
2277 |
+
"grad_norm": 0.9413295388221741,
|
2278 |
+
"learning_rate": 0.0009182743623997634,
|
2279 |
+
"loss": 0.2104,
|
2280 |
+
"step": 321
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"epoch": 0.57,
|
2284 |
+
"grad_norm": 0.5306220650672913,
|
2285 |
+
"learning_rate": 0.0009177628774917479,
|
2286 |
+
"loss": 0.1537,
|
2287 |
+
"step": 322
|
2288 |
+
},
|
2289 |
+
{
|
2290 |
+
"epoch": 0.57,
|
2291 |
+
"grad_norm": 0.8887706398963928,
|
2292 |
+
"learning_rate": 0.0009172499403729567,
|
2293 |
+
"loss": 0.1963,
|
2294 |
+
"step": 323
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 0.57,
|
2298 |
+
"grad_norm": 0.8467744588851929,
|
2299 |
+
"learning_rate": 0.0009167355528264414,
|
2300 |
+
"loss": 0.204,
|
2301 |
+
"step": 324
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 0.57,
|
2305 |
+
"grad_norm": 0.19867151975631714,
|
2306 |
+
"learning_rate": 0.0009162197166402956,
|
2307 |
+
"loss": 0.1407,
|
2308 |
+
"step": 325
|
2309 |
+
},
|
2310 |
+
{
|
2311 |
+
"epoch": 0.58,
|
2312 |
+
"grad_norm": 0.13638383150100708,
|
2313 |
+
"learning_rate": 0.0009157024336076487,
|
2314 |
+
"loss": 0.1408,
|
2315 |
+
"step": 326
|
2316 |
+
},
|
2317 |
+
{
|
2318 |
+
"epoch": 0.58,
|
2319 |
+
"grad_norm": 0.2027496099472046,
|
2320 |
+
"learning_rate": 0.0009151837055266594,
|
2321 |
+
"loss": 0.1444,
|
2322 |
+
"step": 327
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"epoch": 0.58,
|
2326 |
+
"grad_norm": 0.370151549577713,
|
2327 |
+
"learning_rate": 0.0009146635342005098,
|
2328 |
+
"loss": 0.158,
|
2329 |
+
"step": 328
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"epoch": 0.58,
|
2333 |
+
"grad_norm": 0.3114052414894104,
|
2334 |
+
"learning_rate": 0.000914141921437399,
|
2335 |
+
"loss": 0.1464,
|
2336 |
+
"step": 329
|
2337 |
+
},
|
2338 |
+
{
|
2339 |
+
"epoch": 0.58,
|
2340 |
+
"grad_norm": 0.15394961833953857,
|
2341 |
+
"learning_rate": 0.0009136188690505362,
|
2342 |
+
"loss": 0.1341,
|
2343 |
+
"step": 330
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 0.59,
|
2347 |
+
"grad_norm": 0.46498528122901917,
|
2348 |
+
"learning_rate": 0.0009130943788581359,
|
2349 |
+
"loss": 0.1426,
|
2350 |
+
"step": 331
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"epoch": 0.59,
|
2354 |
+
"grad_norm": 0.28067877888679504,
|
2355 |
+
"learning_rate": 0.00091256845268341,
|
2356 |
+
"loss": 0.1409,
|
2357 |
+
"step": 332
|
2358 |
+
},
|
2359 |
+
{
|
2360 |
+
"epoch": 0.59,
|
2361 |
+
"grad_norm": 0.061186857521533966,
|
2362 |
+
"learning_rate": 0.0009120410923545619,
|
2363 |
+
"loss": 0.1401,
|
2364 |
+
"step": 333
|
2365 |
+
},
|
2366 |
+
{
|
2367 |
+
"epoch": 0.59,
|
2368 |
+
"grad_norm": 0.26736098527908325,
|
2369 |
+
"learning_rate": 0.0009115122997047811,
|
2370 |
+
"loss": 0.1467,
|
2371 |
+
"step": 334
|
2372 |
+
},
|
2373 |
+
{
|
2374 |
+
"epoch": 0.59,
|
2375 |
+
"grad_norm": 0.5139696598052979,
|
2376 |
+
"learning_rate": 0.0009109820765722356,
|
2377 |
+
"loss": 0.1585,
|
2378 |
+
"step": 335
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 0.59,
|
2382 |
+
"grad_norm": 0.40007275342941284,
|
2383 |
+
"learning_rate": 0.000910450424800066,
|
2384 |
+
"loss": 0.1473,
|
2385 |
+
"step": 336
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 0.6,
|
2389 |
+
"grad_norm": 0.66825270652771,
|
2390 |
+
"learning_rate": 0.0009099173462363792,
|
2391 |
+
"loss": 0.1572,
|
2392 |
+
"step": 337
|
2393 |
+
},
|
2394 |
+
{
|
2395 |
+
"epoch": 0.6,
|
2396 |
+
"grad_norm": 0.5313024520874023,
|
2397 |
+
"learning_rate": 0.0009093828427342418,
|
2398 |
+
"loss": 0.1555,
|
2399 |
+
"step": 338
|
2400 |
+
},
|
2401 |
+
{
|
2402 |
+
"epoch": 0.6,
|
2403 |
+
"grad_norm": 0.4224655330181122,
|
2404 |
+
"learning_rate": 0.0009088469161516735,
|
2405 |
+
"loss": 0.1429,
|
2406 |
+
"step": 339
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 0.6,
|
2410 |
+
"grad_norm": 0.03462248668074608,
|
2411 |
+
"learning_rate": 0.0009083095683516414,
|
2412 |
+
"loss": 0.1325,
|
2413 |
+
"step": 340
|
2414 |
+
},
|
2415 |
+
{
|
2416 |
+
"epoch": 0.6,
|
2417 |
+
"grad_norm": 0.542322039604187,
|
2418 |
+
"learning_rate": 0.0009077708012020524,
|
2419 |
+
"loss": 0.1755,
|
2420 |
+
"step": 341
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 0.61,
|
2424 |
+
"grad_norm": 0.2164747267961502,
|
2425 |
+
"learning_rate": 0.0009072306165757476,
|
2426 |
+
"loss": 0.1458,
|
2427 |
+
"step": 342
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 0.61,
|
2431 |
+
"grad_norm": 0.27414461970329285,
|
2432 |
+
"learning_rate": 0.0009066890163504955,
|
2433 |
+
"loss": 0.1512,
|
2434 |
+
"step": 343
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"epoch": 0.61,
|
2438 |
+
"grad_norm": 0.1911482959985733,
|
2439 |
+
"learning_rate": 0.0009061460024089853,
|
2440 |
+
"loss": 0.1185,
|
2441 |
+
"step": 344
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 0.61,
|
2445 |
+
"grad_norm": 0.1287711262702942,
|
2446 |
+
"learning_rate": 0.0009056015766388205,
|
2447 |
+
"loss": 0.1372,
|
2448 |
+
"step": 345
|
2449 |
+
},
|
2450 |
+
{
|
2451 |
+
"epoch": 0.61,
|
2452 |
+
"grad_norm": 0.18598809838294983,
|
2453 |
+
"learning_rate": 0.0009050557409325125,
|
2454 |
+
"loss": 0.1341,
|
2455 |
+
"step": 346
|
2456 |
+
},
|
2457 |
+
{
|
2458 |
+
"epoch": 0.61,
|
2459 |
+
"grad_norm": 0.18694853782653809,
|
2460 |
+
"learning_rate": 0.0009045084971874737,
|
2461 |
+
"loss": 0.141,
|
2462 |
+
"step": 347
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 0.62,
|
2466 |
+
"grad_norm": 0.06479912996292114,
|
2467 |
+
"learning_rate": 0.0009039598473060113,
|
2468 |
+
"loss": 0.1368,
|
2469 |
+
"step": 348
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 0.62,
|
2473 |
+
"grad_norm": 0.17768733203411102,
|
2474 |
+
"learning_rate": 0.0009034097931953201,
|
2475 |
+
"loss": 0.1381,
|
2476 |
+
"step": 349
|
2477 |
+
},
|
2478 |
+
{
|
2479 |
+
"epoch": 0.62,
|
2480 |
+
"grad_norm": 0.28938984870910645,
|
2481 |
+
"learning_rate": 0.0009028583367674765,
|
2482 |
+
"loss": 0.1365,
|
2483 |
+
"step": 350
|
2484 |
+
},
|
2485 |
+
{
|
2486 |
+
"epoch": 0.62,
|
2487 |
+
"grad_norm": 0.2924034893512726,
|
2488 |
+
"learning_rate": 0.0009023054799394316,
|
2489 |
+
"loss": 0.1282,
|
2490 |
+
"step": 351
|
2491 |
+
},
|
2492 |
+
{
|
2493 |
+
"epoch": 0.62,
|
2494 |
+
"grad_norm": 0.28439652919769287,
|
2495 |
+
"learning_rate": 0.0009017512246330042,
|
2496 |
+
"loss": 0.151,
|
2497 |
+
"step": 352
|
2498 |
+
},
|
2499 |
+
{
|
2500 |
+
"epoch": 0.62,
|
2501 |
+
"grad_norm": 0.14329224824905396,
|
2502 |
+
"learning_rate": 0.0009011955727748749,
|
2503 |
+
"loss": 0.1419,
|
2504 |
+
"step": 353
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 0.63,
|
2508 |
+
"grad_norm": 0.15245947241783142,
|
2509 |
+
"learning_rate": 0.0009006385262965785,
|
2510 |
+
"loss": 0.1163,
|
2511 |
+
"step": 354
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 0.63,
|
2515 |
+
"grad_norm": 0.052399642765522,
|
2516 |
+
"learning_rate": 0.000900080087134498,
|
2517 |
+
"loss": 0.1241,
|
2518 |
+
"step": 355
|
2519 |
+
},
|
2520 |
+
{
|
2521 |
+
"epoch": 0.63,
|
2522 |
+
"grad_norm": 0.030301153659820557,
|
2523 |
+
"learning_rate": 0.0008995202572298575,
|
2524 |
+
"loss": 0.1232,
|
2525 |
+
"step": 356
|
2526 |
+
},
|
2527 |
+
{
|
2528 |
+
"epoch": 0.63,
|
2529 |
+
"grad_norm": 0.41738417744636536,
|
2530 |
+
"learning_rate": 0.0008989590385287155,
|
2531 |
+
"loss": 0.1675,
|
2532 |
+
"step": 357
|
2533 |
+
},
|
2534 |
+
{
|
2535 |
+
"epoch": 0.63,
|
2536 |
+
"grad_norm": 0.19307875633239746,
|
2537 |
+
"learning_rate": 0.0008983964329819583,
|
2538 |
+
"loss": 0.1328,
|
2539 |
+
"step": 358
|
2540 |
+
},
|
2541 |
+
{
|
2542 |
+
"epoch": 0.64,
|
2543 |
+
"grad_norm": 0.05682377517223358,
|
2544 |
+
"learning_rate": 0.000897832442545293,
|
2545 |
+
"loss": 0.1322,
|
2546 |
+
"step": 359
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 0.64,
|
2550 |
+
"grad_norm": 0.15418089926242828,
|
2551 |
+
"learning_rate": 0.0008972670691792409,
|
2552 |
+
"loss": 0.1414,
|
2553 |
+
"step": 360
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 0.64,
|
2557 |
+
"grad_norm": 0.07167459279298782,
|
2558 |
+
"learning_rate": 0.0008967003148491304,
|
2559 |
+
"loss": 0.1414,
|
2560 |
+
"step": 361
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 0.64,
|
2564 |
+
"grad_norm": 0.2866109609603882,
|
2565 |
+
"learning_rate": 0.0008961321815250904,
|
2566 |
+
"loss": 0.1381,
|
2567 |
+
"step": 362
|
2568 |
+
},
|
2569 |
+
{
|
2570 |
+
"epoch": 0.64,
|
2571 |
+
"grad_norm": 0.281264990568161,
|
2572 |
+
"learning_rate": 0.0008955626711820438,
|
2573 |
+
"loss": 0.1365,
|
2574 |
+
"step": 363
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 0.64,
|
2578 |
+
"grad_norm": 0.19263768196105957,
|
2579 |
+
"learning_rate": 0.0008949917857996997,
|
2580 |
+
"loss": 0.1394,
|
2581 |
+
"step": 364
|
2582 |
+
},
|
2583 |
+
{
|
2584 |
+
"epoch": 0.65,
|
2585 |
+
"grad_norm": 0.30531641840934753,
|
2586 |
+
"learning_rate": 0.0008944195273625471,
|
2587 |
+
"loss": 0.1478,
|
2588 |
+
"step": 365
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"epoch": 0.65,
|
2592 |
+
"grad_norm": 0.16229306161403656,
|
2593 |
+
"learning_rate": 0.0008938458978598483,
|
2594 |
+
"loss": 0.1412,
|
2595 |
+
"step": 366
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 0.65,
|
2599 |
+
"grad_norm": 0.09315463900566101,
|
2600 |
+
"learning_rate": 0.0008932708992856315,
|
2601 |
+
"loss": 0.1397,
|
2602 |
+
"step": 367
|
2603 |
+
},
|
2604 |
+
{
|
2605 |
+
"epoch": 0.65,
|
2606 |
+
"grad_norm": 0.04228806868195534,
|
2607 |
+
"learning_rate": 0.0008926945336386838,
|
2608 |
+
"loss": 0.1383,
|
2609 |
+
"step": 368
|
2610 |
+
},
|
2611 |
+
{
|
2612 |
+
"epoch": 0.65,
|
2613 |
+
"grad_norm": 0.2209407389163971,
|
2614 |
+
"learning_rate": 0.0008921168029225448,
|
2615 |
+
"loss": 0.1434,
|
2616 |
+
"step": 369
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 0.65,
|
2620 |
+
"grad_norm": 0.04254443198442459,
|
2621 |
+
"learning_rate": 0.0008915377091454992,
|
2622 |
+
"loss": 0.1326,
|
2623 |
+
"step": 370
|
2624 |
+
},
|
2625 |
+
{
|
2626 |
+
"epoch": 0.66,
|
2627 |
+
"grad_norm": 0.09651175886392593,
|
2628 |
+
"learning_rate": 0.0008909572543205698,
|
2629 |
+
"loss": 0.134,
|
2630 |
+
"step": 371
|
2631 |
+
},
|
2632 |
+
{
|
2633 |
+
"epoch": 0.66,
|
2634 |
+
"grad_norm": 0.2821654975414276,
|
2635 |
+
"learning_rate": 0.0008903754404655105,
|
2636 |
+
"loss": 0.1498,
|
2637 |
+
"step": 372
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 0.66,
|
2641 |
+
"grad_norm": 0.43042680621147156,
|
2642 |
+
"learning_rate": 0.0008897922696027998,
|
2643 |
+
"loss": 0.1571,
|
2644 |
+
"step": 373
|
2645 |
+
},
|
2646 |
+
{
|
2647 |
+
"epoch": 0.66,
|
2648 |
+
"grad_norm": 0.06591568142175674,
|
2649 |
+
"learning_rate": 0.0008892077437596332,
|
2650 |
+
"loss": 0.1391,
|
2651 |
+
"step": 374
|
2652 |
+
},
|
2653 |
+
{
|
2654 |
+
"epoch": 0.66,
|
2655 |
+
"grad_norm": 0.08771979063749313,
|
2656 |
+
"learning_rate": 0.0008886218649679161,
|
2657 |
+
"loss": 0.1375,
|
2658 |
+
"step": 375
|
2659 |
+
},
|
2660 |
+
{
|
2661 |
+
"epoch": 0.67,
|
2662 |
+
"grad_norm": 0.03339942544698715,
|
2663 |
+
"learning_rate": 0.0008880346352642574,
|
2664 |
+
"loss": 0.1368,
|
2665 |
+
"step": 376
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 0.67,
|
2669 |
+
"grad_norm": 0.15352453291416168,
|
2670 |
+
"learning_rate": 0.0008874460566899616,
|
2671 |
+
"loss": 0.1447,
|
2672 |
+
"step": 377
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 0.67,
|
2676 |
+
"grad_norm": 0.1778584122657776,
|
2677 |
+
"learning_rate": 0.0008868561312910222,
|
2678 |
+
"loss": 0.1189,
|
2679 |
+
"step": 378
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 0.67,
|
2683 |
+
"grad_norm": 0.11893154680728912,
|
2684 |
+
"learning_rate": 0.0008862648611181144,
|
2685 |
+
"loss": 0.1167,
|
2686 |
+
"step": 379
|
2687 |
+
},
|
2688 |
+
{
|
2689 |
+
"epoch": 0.67,
|
2690 |
+
"grad_norm": 0.4323861598968506,
|
2691 |
+
"learning_rate": 0.0008856722482265886,
|
2692 |
+
"loss": 0.1691,
|
2693 |
+
"step": 380
|
2694 |
+
},
|
2695 |
+
{
|
2696 |
+
"epoch": 0.67,
|
2697 |
+
"grad_norm": 0.28813356161117554,
|
2698 |
+
"learning_rate": 0.0008850782946764618,
|
2699 |
+
"loss": 0.1505,
|
2700 |
+
"step": 381
|
2701 |
+
},
|
2702 |
+
{
|
2703 |
+
"epoch": 0.68,
|
2704 |
+
"grad_norm": 0.5008757710456848,
|
2705 |
+
"learning_rate": 0.0008844830025324122,
|
2706 |
+
"loss": 0.1671,
|
2707 |
+
"step": 382
|
2708 |
+
},
|
2709 |
+
{
|
2710 |
+
"epoch": 0.68,
|
2711 |
+
"grad_norm": 0.12061876803636551,
|
2712 |
+
"learning_rate": 0.0008838863738637705,
|
2713 |
+
"loss": 0.1375,
|
2714 |
+
"step": 383
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 0.68,
|
2718 |
+
"grad_norm": 0.6747052073478699,
|
2719 |
+
"learning_rate": 0.0008832884107445138,
|
2720 |
+
"loss": 0.1663,
|
2721 |
+
"step": 384
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 0.68,
|
2725 |
+
"grad_norm": 0.18846777081489563,
|
2726 |
+
"learning_rate": 0.0008826891152532579,
|
2727 |
+
"loss": 0.1148,
|
2728 |
+
"step": 385
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 0.68,
|
2732 |
+
"grad_norm": 0.0950111448764801,
|
2733 |
+
"learning_rate": 0.0008820884894732497,
|
2734 |
+
"loss": 0.1138,
|
2735 |
+
"step": 386
|
2736 |
+
},
|
2737 |
+
{
|
2738 |
+
"epoch": 0.68,
|
2739 |
+
"grad_norm": 0.42371127009391785,
|
2740 |
+
"learning_rate": 0.0008814865354923613,
|
2741 |
+
"loss": 0.142,
|
2742 |
+
"step": 387
|
2743 |
+
},
|
2744 |
+
{
|
2745 |
+
"epoch": 0.69,
|
2746 |
+
"grad_norm": 0.17662374675273895,
|
2747 |
+
"learning_rate": 0.0008808832554030808,
|
2748 |
+
"loss": 0.1255,
|
2749 |
+
"step": 388
|
2750 |
+
},
|
2751 |
+
{
|
2752 |
+
"epoch": 0.69,
|
2753 |
+
"grad_norm": 0.7766286134719849,
|
2754 |
+
"learning_rate": 0.0008802786513025068,
|
2755 |
+
"loss": 0.1613,
|
2756 |
+
"step": 389
|
2757 |
+
},
|
2758 |
+
{
|
2759 |
+
"epoch": 0.69,
|
2760 |
+
"grad_norm": 0.49581214785575867,
|
2761 |
+
"learning_rate": 0.0008796727252923403,
|
2762 |
+
"loss": 0.1346,
|
2763 |
+
"step": 390
|
2764 |
+
},
|
2765 |
+
{
|
2766 |
+
"epoch": 0.69,
|
2767 |
+
"grad_norm": 0.6148929595947266,
|
2768 |
+
"learning_rate": 0.0008790654794788768,
|
2769 |
+
"loss": 0.1426,
|
2770 |
+
"step": 391
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 0.69,
|
2774 |
+
"grad_norm": 0.15860037505626678,
|
2775 |
+
"learning_rate": 0.0008784569159730007,
|
2776 |
+
"loss": 0.1382,
|
2777 |
+
"step": 392
|
2778 |
+
},
|
2779 |
+
{
|
2780 |
+
"epoch": 0.7,
|
2781 |
+
"grad_norm": 0.6793199777603149,
|
2782 |
+
"learning_rate": 0.0008778470368901761,
|
2783 |
+
"loss": 0.1398,
|
2784 |
+
"step": 393
|
2785 |
+
},
|
2786 |
+
{
|
2787 |
+
"epoch": 0.7,
|
2788 |
+
"grad_norm": 0.40314817428588867,
|
2789 |
+
"learning_rate": 0.0008772358443504404,
|
2790 |
+
"loss": 0.1428,
|
2791 |
+
"step": 394
|
2792 |
+
},
|
2793 |
+
{
|
2794 |
+
"epoch": 0.7,
|
2795 |
+
"grad_norm": 0.6403933167457581,
|
2796 |
+
"learning_rate": 0.0008766233404783974,
|
2797 |
+
"loss": 0.1556,
|
2798 |
+
"step": 395
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 0.7,
|
2802 |
+
"grad_norm": 0.33554157614707947,
|
2803 |
+
"learning_rate": 0.0008760095274032083,
|
2804 |
+
"loss": 0.1439,
|
2805 |
+
"step": 396
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 0.7,
|
2809 |
+
"grad_norm": 0.45690324902534485,
|
2810 |
+
"learning_rate": 0.000875394407258586,
|
2811 |
+
"loss": 0.1374,
|
2812 |
+
"step": 397
|
2813 |
+
},
|
2814 |
+
{
|
2815 |
+
"epoch": 0.7,
|
2816 |
+
"grad_norm": 0.0541120283305645,
|
2817 |
+
"learning_rate": 0.0008747779821827868,
|
2818 |
+
"loss": 0.1314,
|
2819 |
+
"step": 398
|
2820 |
+
},
|
2821 |
+
{
|
2822 |
+
"epoch": 0.71,
|
2823 |
+
"grad_norm": 0.6533159613609314,
|
2824 |
+
"learning_rate": 0.0008741602543186031,
|
2825 |
+
"loss": 0.169,
|
2826 |
+
"step": 399
|
2827 |
+
},
|
2828 |
+
{
|
2829 |
+
"epoch": 0.71,
|
2830 |
+
"grad_norm": 0.4919282793998718,
|
2831 |
+
"learning_rate": 0.0008735412258133561,
|
2832 |
+
"loss": 0.1569,
|
2833 |
+
"step": 400
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 0.71,
|
2837 |
+
"grad_norm": 0.30325594544410706,
|
2838 |
+
"learning_rate": 0.0008729208988188881,
|
2839 |
+
"loss": 0.1471,
|
2840 |
+
"step": 401
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 0.71,
|
2844 |
+
"grad_norm": 0.3497300148010254,
|
2845 |
+
"learning_rate": 0.0008722992754915554,
|
2846 |
+
"loss": 0.1457,
|
2847 |
+
"step": 402
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 0.71,
|
2851 |
+
"grad_norm": 0.22892774641513824,
|
2852 |
+
"learning_rate": 0.0008716763579922203,
|
2853 |
+
"loss": 0.1334,
|
2854 |
+
"step": 403
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 0.71,
|
2858 |
+
"grad_norm": 0.20050272345542908,
|
2859 |
+
"learning_rate": 0.0008710521484862439,
|
2860 |
+
"loss": 0.1446,
|
2861 |
+
"step": 404
|
2862 |
+
},
|
2863 |
+
{
|
2864 |
+
"epoch": 0.72,
|
2865 |
+
"grad_norm": 0.5029633641242981,
|
2866 |
+
"learning_rate": 0.0008704266491434787,
|
2867 |
+
"loss": 0.171,
|
2868 |
+
"step": 405
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 0.72,
|
2872 |
+
"grad_norm": 0.2720576226711273,
|
2873 |
+
"learning_rate": 0.0008697998621382607,
|
2874 |
+
"loss": 0.144,
|
2875 |
+
"step": 406
|
2876 |
+
},
|
2877 |
+
{
|
2878 |
+
"epoch": 0.72,
|
2879 |
+
"grad_norm": 0.10961242765188217,
|
2880 |
+
"learning_rate": 0.000869171789649402,
|
2881 |
+
"loss": 0.1349,
|
2882 |
+
"step": 407
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 0.72,
|
2886 |
+
"grad_norm": 0.13584192097187042,
|
2887 |
+
"learning_rate": 0.0008685424338601833,
|
2888 |
+
"loss": 0.1385,
|
2889 |
+
"step": 408
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 0.72,
|
2893 |
+
"grad_norm": 0.6586437821388245,
|
2894 |
+
"learning_rate": 0.0008679117969583464,
|
2895 |
+
"loss": 0.1459,
|
2896 |
+
"step": 409
|
2897 |
+
},
|
2898 |
+
{
|
2899 |
+
"epoch": 0.73,
|
2900 |
+
"grad_norm": 0.24006032943725586,
|
2901 |
+
"learning_rate": 0.0008672798811360864,
|
2902 |
+
"loss": 0.1344,
|
2903 |
+
"step": 410
|
2904 |
+
},
|
2905 |
+
{
|
2906 |
+
"epoch": 0.73,
|
2907 |
+
"grad_norm": 0.1859387755393982,
|
2908 |
+
"learning_rate": 0.0008666466885900438,
|
2909 |
+
"loss": 0.1358,
|
2910 |
+
"step": 411
|
2911 |
+
},
|
2912 |
+
{
|
2913 |
+
"epoch": 0.73,
|
2914 |
+
"grad_norm": 0.5095134973526001,
|
2915 |
+
"learning_rate": 0.0008660122215212977,
|
2916 |
+
"loss": 0.1387,
|
2917 |
+
"step": 412
|
2918 |
+
},
|
2919 |
+
{
|
2920 |
+
"epoch": 0.73,
|
2921 |
+
"grad_norm": 0.1827729493379593,
|
2922 |
+
"learning_rate": 0.0008653764821353573,
|
2923 |
+
"loss": 0.1377,
|
2924 |
+
"step": 413
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 0.73,
|
2928 |
+
"grad_norm": 0.14332665503025055,
|
2929 |
+
"learning_rate": 0.0008647394726421547,
|
2930 |
+
"loss": 0.131,
|
2931 |
+
"step": 414
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 0.73,
|
2935 |
+
"grad_norm": 0.383101224899292,
|
2936 |
+
"learning_rate": 0.0008641011952560371,
|
2937 |
+
"loss": 0.146,
|
2938 |
+
"step": 415
|
2939 |
+
},
|
2940 |
+
{
|
2941 |
+
"epoch": 0.74,
|
2942 |
+
"grad_norm": 0.19079791009426117,
|
2943 |
+
"learning_rate": 0.000863461652195759,
|
2944 |
+
"loss": 0.1255,
|
2945 |
+
"step": 416
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 0.74,
|
2949 |
+
"grad_norm": 0.49537310004234314,
|
2950 |
+
"learning_rate": 0.0008628208456844747,
|
2951 |
+
"loss": 0.1602,
|
2952 |
+
"step": 417
|
2953 |
+
},
|
2954 |
+
{
|
2955 |
+
"epoch": 0.74,
|
2956 |
+
"grad_norm": 0.5658069849014282,
|
2957 |
+
"learning_rate": 0.0008621787779497306,
|
2958 |
+
"loss": 0.1518,
|
2959 |
+
"step": 418
|
2960 |
+
},
|
2961 |
+
{
|
2962 |
+
"epoch": 0.74,
|
2963 |
+
"grad_norm": 0.2572256326675415,
|
2964 |
+
"learning_rate": 0.0008615354512234569,
|
2965 |
+
"loss": 0.1369,
|
2966 |
+
"step": 419
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 0.74,
|
2970 |
+
"grad_norm": 1.1088945865631104,
|
2971 |
+
"learning_rate": 0.0008608908677419605,
|
2972 |
+
"loss": 0.1773,
|
2973 |
+
"step": 420
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 0.74,
|
2977 |
+
"grad_norm": 0.35405099391937256,
|
2978 |
+
"learning_rate": 0.0008602450297459173,
|
2979 |
+
"loss": 0.1441,
|
2980 |
+
"step": 421
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 0.75,
|
2984 |
+
"grad_norm": 0.39150556921958923,
|
2985 |
+
"learning_rate": 0.0008595979394803633,
|
2986 |
+
"loss": 0.147,
|
2987 |
+
"step": 422
|
2988 |
+
},
|
2989 |
+
{
|
2990 |
+
"epoch": 0.75,
|
2991 |
+
"grad_norm": 0.07459918409585953,
|
2992 |
+
"learning_rate": 0.0008589495991946885,
|
2993 |
+
"loss": 0.1338,
|
2994 |
+
"step": 423
|
2995 |
+
},
|
2996 |
+
{
|
2997 |
+
"epoch": 0.75,
|
2998 |
+
"grad_norm": 0.2999761402606964,
|
2999 |
+
"learning_rate": 0.0008583000111426276,
|
3000 |
+
"loss": 0.1357,
|
3001 |
+
"step": 424
|
3002 |
+
},
|
3003 |
+
{
|
3004 |
+
"epoch": 0.75,
|
3005 |
+
"grad_norm": 0.28417065739631653,
|
3006 |
+
"learning_rate": 0.0008576491775822525,
|
3007 |
+
"loss": 0.1411,
|
3008 |
+
"step": 425
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 0.75,
|
3012 |
+
"grad_norm": 0.32605019211769104,
|
3013 |
+
"learning_rate": 0.0008569971007759657,
|
3014 |
+
"loss": 0.1329,
|
3015 |
+
"step": 426
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 0.75,
|
3019 |
+
"eval_loss": 0.13750587403774261,
|
3020 |
+
"eval_runtime": 15.1749,
|
3021 |
+
"eval_samples_per_second": 31.433,
|
3022 |
+
"eval_steps_per_second": 7.908,
|
3023 |
+
"step": 426
|
3024 |
+
},
|
3025 |
+
{
|
3026 |
+
"epoch": 0.76,
|
3027 |
+
"grad_norm": 0.047430120408535004,
|
3028 |
+
"learning_rate": 0.0008563437829904903,
|
3029 |
+
"loss": 0.1373,
|
3030 |
+
"step": 427
|
3031 |
+
},
|
3032 |
+
{
|
3033 |
+
"epoch": 0.76,
|
3034 |
+
"grad_norm": 0.4616542160511017,
|
3035 |
+
"learning_rate": 0.0008556892264968639,
|
3036 |
+
"loss": 0.1534,
|
3037 |
+
"step": 428
|
3038 |
+
},
|
3039 |
+
{
|
3040 |
+
"epoch": 0.76,
|
3041 |
+
"grad_norm": 0.12317585945129395,
|
3042 |
+
"learning_rate": 0.0008550334335704297,
|
3043 |
+
"loss": 0.1338,
|
3044 |
+
"step": 429
|
3045 |
+
},
|
3046 |
+
{
|
3047 |
+
"epoch": 0.76,
|
3048 |
+
"grad_norm": 0.39604276418685913,
|
3049 |
+
"learning_rate": 0.0008543764064908295,
|
3050 |
+
"loss": 0.1434,
|
3051 |
+
"step": 430
|
3052 |
+
},
|
3053 |
+
{
|
3054 |
+
"epoch": 0.76,
|
3055 |
+
"grad_norm": 0.3490678369998932,
|
3056 |
+
"learning_rate": 0.0008537181475419944,
|
3057 |
+
"loss": 0.1365,
|
3058 |
+
"step": 431
|
3059 |
+
},
|
3060 |
+
{
|
3061 |
+
"epoch": 0.76,
|
3062 |
+
"grad_norm": 0.15001270174980164,
|
3063 |
+
"learning_rate": 0.0008530586590121383,
|
3064 |
+
"loss": 0.1358,
|
3065 |
+
"step": 432
|
3066 |
+
},
|
3067 |
+
{
|
3068 |
+
"epoch": 0.77,
|
3069 |
+
"grad_norm": 0.33340635895729065,
|
3070 |
+
"learning_rate": 0.0008523979431937492,
|
3071 |
+
"loss": 0.1367,
|
3072 |
+
"step": 433
|
3073 |
+
},
|
3074 |
+
{
|
3075 |
+
"epoch": 0.77,
|
3076 |
+
"grad_norm": 0.06029750779271126,
|
3077 |
+
"learning_rate": 0.0008517360023835809,
|
3078 |
+
"loss": 0.1366,
|
3079 |
+
"step": 434
|
3080 |
+
},
|
3081 |
+
{
|
3082 |
+
"epoch": 0.77,
|
3083 |
+
"grad_norm": 0.07978738099336624,
|
3084 |
+
"learning_rate": 0.0008510728388826463,
|
3085 |
+
"loss": 0.1345,
|
3086 |
+
"step": 435
|
3087 |
+
},
|
3088 |
+
{
|
3089 |
+
"epoch": 0.77,
|
3090 |
+
"grad_norm": 0.27599036693573,
|
3091 |
+
"learning_rate": 0.0008504084549962079,
|
3092 |
+
"loss": 0.1447,
|
3093 |
+
"step": 436
|
3094 |
+
},
|
3095 |
+
{
|
3096 |
+
"epoch": 0.77,
|
3097 |
+
"grad_norm": 0.13302059471607208,
|
3098 |
+
"learning_rate": 0.0008497428530337706,
|
3099 |
+
"loss": 0.1407,
|
3100 |
+
"step": 437
|
3101 |
+
},
|
3102 |
+
{
|
3103 |
+
"epoch": 0.77,
|
3104 |
+
"grad_norm": 0.20869582891464233,
|
3105 |
+
"learning_rate": 0.0008490760353090737,
|
3106 |
+
"loss": 0.1374,
|
3107 |
+
"step": 438
|
3108 |
+
},
|
3109 |
+
{
|
3110 |
+
"epoch": 0.78,
|
3111 |
+
"grad_norm": 0.10881117731332779,
|
3112 |
+
"learning_rate": 0.0008484080041400825,
|
3113 |
+
"loss": 0.1429,
|
3114 |
+
"step": 439
|
3115 |
+
},
|
3116 |
+
{
|
3117 |
+
"epoch": 0.78,
|
3118 |
+
"grad_norm": 0.20344361662864685,
|
3119 |
+
"learning_rate": 0.0008477387618489807,
|
3120 |
+
"loss": 0.139,
|
3121 |
+
"step": 440
|
3122 |
+
},
|
3123 |
+
{
|
3124 |
+
"epoch": 0.78,
|
3125 |
+
"grad_norm": 0.07153432071208954,
|
3126 |
+
"learning_rate": 0.0008470683107621615,
|
3127 |
+
"loss": 0.1315,
|
3128 |
+
"step": 441
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 0.78,
|
3132 |
+
"grad_norm": 0.08688751608133316,
|
3133 |
+
"learning_rate": 0.0008463966532102207,
|
3134 |
+
"loss": 0.1346,
|
3135 |
+
"step": 442
|
3136 |
+
},
|
3137 |
+
{
|
3138 |
+
"epoch": 0.78,
|
3139 |
+
"grad_norm": 0.06495650112628937,
|
3140 |
+
"learning_rate": 0.0008457237915279476,
|
3141 |
+
"loss": 0.1307,
|
3142 |
+
"step": 443
|
3143 |
+
},
|
3144 |
+
{
|
3145 |
+
"epoch": 0.79,
|
3146 |
+
"grad_norm": 0.1892390102148056,
|
3147 |
+
"learning_rate": 0.0008450497280543173,
|
3148 |
+
"loss": 0.12,
|
3149 |
+
"step": 444
|
3150 |
+
},
|
3151 |
+
{
|
3152 |
+
"epoch": 0.79,
|
3153 |
+
"grad_norm": 0.2579623758792877,
|
3154 |
+
"learning_rate": 0.0008443744651324827,
|
3155 |
+
"loss": 0.1531,
|
3156 |
+
"step": 445
|
3157 |
+
},
|
3158 |
+
{
|
3159 |
+
"epoch": 0.79,
|
3160 |
+
"grad_norm": 0.149379700422287,
|
3161 |
+
"learning_rate": 0.000843698005109766,
|
3162 |
+
"loss": 0.1385,
|
3163 |
+
"step": 446
|
3164 |
+
},
|
3165 |
+
{
|
3166 |
+
"epoch": 0.79,
|
3167 |
+
"grad_norm": 0.19281132519245148,
|
3168 |
+
"learning_rate": 0.0008430203503376506,
|
3169 |
+
"loss": 0.1033,
|
3170 |
+
"step": 447
|
3171 |
+
},
|
3172 |
+
{
|
3173 |
+
"epoch": 0.79,
|
3174 |
+
"grad_norm": 0.33208444714546204,
|
3175 |
+
"learning_rate": 0.0008423415031717733,
|
3176 |
+
"loss": 0.1525,
|
3177 |
+
"step": 448
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 0.79,
|
3181 |
+
"grad_norm": 0.15149784088134766,
|
3182 |
+
"learning_rate": 0.0008416614659719157,
|
3183 |
+
"loss": 0.1282,
|
3184 |
+
"step": 449
|
3185 |
+
},
|
3186 |
+
{
|
3187 |
+
"epoch": 0.8,
|
3188 |
+
"grad_norm": 0.24646438658237457,
|
3189 |
+
"learning_rate": 0.0008409802411019962,
|
3190 |
+
"loss": 0.1393,
|
3191 |
+
"step": 450
|
3192 |
+
},
|
3193 |
+
{
|
3194 |
+
"epoch": 0.8,
|
3195 |
+
"grad_norm": 0.2505553662776947,
|
3196 |
+
"learning_rate": 0.000840297830930062,
|
3197 |
+
"loss": 0.1453,
|
3198 |
+
"step": 451
|
3199 |
+
},
|
3200 |
+
{
|
3201 |
+
"epoch": 0.8,
|
3202 |
+
"grad_norm": 0.1632508784532547,
|
3203 |
+
"learning_rate": 0.0008396142378282799,
|
3204 |
+
"loss": 0.1274,
|
3205 |
+
"step": 452
|
3206 |
+
},
|
3207 |
+
{
|
3208 |
+
"epoch": 0.8,
|
3209 |
+
"grad_norm": 0.12370573729276657,
|
3210 |
+
"learning_rate": 0.0008389294641729292,
|
3211 |
+
"loss": 0.1201,
|
3212 |
+
"step": 453
|
3213 |
+
},
|
3214 |
+
{
|
3215 |
+
"epoch": 0.8,
|
3216 |
+
"grad_norm": 0.08046772330999374,
|
3217 |
+
"learning_rate": 0.0008382435123443934,
|
3218 |
+
"loss": 0.1263,
|
3219 |
+
"step": 454
|
3220 |
+
},
|
3221 |
+
{
|
3222 |
+
"epoch": 0.8,
|
3223 |
+
"grad_norm": 0.19015488028526306,
|
3224 |
+
"learning_rate": 0.0008375563847271506,
|
3225 |
+
"loss": 0.1318,
|
3226 |
+
"step": 455
|
3227 |
+
},
|
3228 |
+
{
|
3229 |
+
"epoch": 0.81,
|
3230 |
+
"grad_norm": 0.3562954366207123,
|
3231 |
+
"learning_rate": 0.0008368680837097669,
|
3232 |
+
"loss": 0.132,
|
3233 |
+
"step": 456
|
3234 |
+
},
|
3235 |
+
{
|
3236 |
+
"epoch": 0.81,
|
3237 |
+
"grad_norm": 0.06315189599990845,
|
3238 |
+
"learning_rate": 0.000836178611684887,
|
3239 |
+
"loss": 0.1113,
|
3240 |
+
"step": 457
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 0.81,
|
3244 |
+
"grad_norm": 0.43667125701904297,
|
3245 |
+
"learning_rate": 0.0008354879710492264,
|
3246 |
+
"loss": 0.1908,
|
3247 |
+
"step": 458
|
3248 |
+
},
|
3249 |
+
{
|
3250 |
+
"epoch": 0.81,
|
3251 |
+
"grad_norm": 0.0708879753947258,
|
3252 |
+
"learning_rate": 0.0008347961642035624,
|
3253 |
+
"loss": 0.1399,
|
3254 |
+
"step": 459
|
3255 |
+
},
|
3256 |
+
{
|
3257 |
+
"epoch": 0.81,
|
3258 |
+
"grad_norm": 0.04855835437774658,
|
3259 |
+
"learning_rate": 0.0008341031935527267,
|
3260 |
+
"loss": 0.1258,
|
3261 |
+
"step": 460
|
3262 |
+
},
|
3263 |
+
{
|
3264 |
+
"epoch": 0.82,
|
3265 |
+
"grad_norm": 0.1364990919828415,
|
3266 |
+
"learning_rate": 0.0008334090615055965,
|
3267 |
+
"loss": 0.1344,
|
3268 |
+
"step": 461
|
3269 |
+
},
|
3270 |
+
{
|
3271 |
+
"epoch": 0.82,
|
3272 |
+
"grad_norm": 0.08166524022817612,
|
3273 |
+
"learning_rate": 0.0008327137704750862,
|
3274 |
+
"loss": 0.134,
|
3275 |
+
"step": 462
|
3276 |
+
},
|
3277 |
+
{
|
3278 |
+
"epoch": 0.82,
|
3279 |
+
"grad_norm": 0.09308458864688873,
|
3280 |
+
"learning_rate": 0.0008320173228781389,
|
3281 |
+
"loss": 0.1507,
|
3282 |
+
"step": 463
|
3283 |
+
},
|
3284 |
+
{
|
3285 |
+
"epoch": 0.82,
|
3286 |
+
"grad_norm": 0.07796576619148254,
|
3287 |
+
"learning_rate": 0.000831319721135718,
|
3288 |
+
"loss": 0.1284,
|
3289 |
+
"step": 464
|
3290 |
+
},
|
3291 |
+
{
|
3292 |
+
"epoch": 0.82,
|
3293 |
+
"grad_norm": 0.12168626487255096,
|
3294 |
+
"learning_rate": 0.0008306209676727993,
|
3295 |
+
"loss": 0.148,
|
3296 |
+
"step": 465
|
3297 |
+
},
|
3298 |
+
{
|
3299 |
+
"epoch": 0.82,
|
3300 |
+
"grad_norm": 0.18862847983837128,
|
3301 |
+
"learning_rate": 0.000829921064918362,
|
3302 |
+
"loss": 0.1229,
|
3303 |
+
"step": 466
|
3304 |
+
},
|
3305 |
+
{
|
3306 |
+
"epoch": 0.83,
|
3307 |
+
"grad_norm": 0.23615515232086182,
|
3308 |
+
"learning_rate": 0.00082922001530538,
|
3309 |
+
"loss": 0.1322,
|
3310 |
+
"step": 467
|
3311 |
+
},
|
3312 |
+
{
|
3313 |
+
"epoch": 0.83,
|
3314 |
+
"grad_norm": 0.34108766913414,
|
3315 |
+
"learning_rate": 0.0008285178212708142,
|
3316 |
+
"loss": 0.1338,
|
3317 |
+
"step": 468
|
3318 |
+
},
|
3319 |
+
{
|
3320 |
+
"epoch": 0.83,
|
3321 |
+
"grad_norm": 0.39579400420188904,
|
3322 |
+
"learning_rate": 0.0008278144852556042,
|
3323 |
+
"loss": 0.1341,
|
3324 |
+
"step": 469
|
3325 |
+
},
|
3326 |
+
{
|
3327 |
+
"epoch": 0.83,
|
3328 |
+
"grad_norm": 0.2620592713356018,
|
3329 |
+
"learning_rate": 0.0008271100097046585,
|
3330 |
+
"loss": 0.1395,
|
3331 |
+
"step": 470
|
3332 |
+
},
|
3333 |
+
{
|
3334 |
+
"epoch": 0.83,
|
3335 |
+
"grad_norm": 0.08778171986341476,
|
3336 |
+
"learning_rate": 0.0008264043970668469,
|
3337 |
+
"loss": 0.1328,
|
3338 |
+
"step": 471
|
3339 |
+
},
|
3340 |
+
{
|
3341 |
+
"epoch": 0.84,
|
3342 |
+
"grad_norm": 0.6086364388465881,
|
3343 |
+
"learning_rate": 0.0008256976497949924,
|
3344 |
+
"loss": 0.1271,
|
3345 |
+
"step": 472
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 0.84,
|
3349 |
+
"grad_norm": 0.08982394635677338,
|
3350 |
+
"learning_rate": 0.0008249897703458619,
|
3351 |
+
"loss": 0.1346,
|
3352 |
+
"step": 473
|
3353 |
+
},
|
3354 |
+
{
|
3355 |
+
"epoch": 0.84,
|
3356 |
+
"grad_norm": 0.054080091416835785,
|
3357 |
+
"learning_rate": 0.0008242807611801578,
|
3358 |
+
"loss": 0.1218,
|
3359 |
+
"step": 474
|
3360 |
+
},
|
3361 |
+
{
|
3362 |
+
"epoch": 0.84,
|
3363 |
+
"grad_norm": 0.5981457829475403,
|
3364 |
+
"learning_rate": 0.0008235706247625098,
|
3365 |
+
"loss": 0.1715,
|
3366 |
+
"step": 475
|
3367 |
+
},
|
3368 |
+
{
|
3369 |
+
"epoch": 0.84,
|
3370 |
+
"grad_norm": 0.9139420986175537,
|
3371 |
+
"learning_rate": 0.0008228593635614659,
|
3372 |
+
"loss": 0.1983,
|
3373 |
+
"step": 476
|
3374 |
+
},
|
3375 |
+
{
|
3376 |
+
"epoch": 0.84,
|
3377 |
+
"grad_norm": 0.05938498303294182,
|
3378 |
+
"learning_rate": 0.0008221469800494841,
|
3379 |
+
"loss": 0.1308,
|
3380 |
+
"step": 477
|
3381 |
+
},
|
3382 |
+
{
|
3383 |
+
"epoch": 0.85,
|
3384 |
+
"grad_norm": 0.11526026576757431,
|
3385 |
+
"learning_rate": 0.0008214334767029239,
|
3386 |
+
"loss": 0.1422,
|
3387 |
+
"step": 478
|
3388 |
+
},
|
3389 |
+
{
|
3390 |
+
"epoch": 0.85,
|
3391 |
+
"grad_norm": 0.3049907386302948,
|
3392 |
+
"learning_rate": 0.0008207188560020373,
|
3393 |
+
"loss": 0.1419,
|
3394 |
+
"step": 479
|
3395 |
+
},
|
3396 |
+
{
|
3397 |
+
"epoch": 0.85,
|
3398 |
+
"grad_norm": 0.04782035946846008,
|
3399 |
+
"learning_rate": 0.0008200031204309604,
|
3400 |
+
"loss": 0.138,
|
3401 |
+
"step": 480
|
3402 |
+
},
|
3403 |
+
{
|
3404 |
+
"epoch": 0.85,
|
3405 |
+
"grad_norm": 0.12950918078422546,
|
3406 |
+
"learning_rate": 0.000819286272477705,
|
3407 |
+
"loss": 0.1315,
|
3408 |
+
"step": 481
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 0.85,
|
3412 |
+
"grad_norm": 0.0429329015314579,
|
3413 |
+
"learning_rate": 0.0008185683146341496,
|
3414 |
+
"loss": 0.1354,
|
3415 |
+
"step": 482
|
3416 |
+
},
|
3417 |
+
{
|
3418 |
+
"epoch": 0.85,
|
3419 |
+
"grad_norm": 0.4792588949203491,
|
3420 |
+
"learning_rate": 0.0008178492493960308,
|
3421 |
+
"loss": 0.1476,
|
3422 |
+
"step": 483
|
3423 |
+
},
|
3424 |
+
{
|
3425 |
+
"epoch": 0.86,
|
3426 |
+
"grad_norm": 0.19784927368164062,
|
3427 |
+
"learning_rate": 0.0008171290792629346,
|
3428 |
+
"loss": 0.1394,
|
3429 |
+
"step": 484
|
3430 |
+
},
|
3431 |
+
{
|
3432 |
+
"epoch": 0.86,
|
3433 |
+
"grad_norm": 0.1172945499420166,
|
3434 |
+
"learning_rate": 0.000816407806738288,
|
3435 |
+
"loss": 0.1302,
|
3436 |
+
"step": 485
|
3437 |
+
},
|
3438 |
+
{
|
3439 |
+
"epoch": 0.86,
|
3440 |
+
"grad_norm": 0.3732689917087555,
|
3441 |
+
"learning_rate": 0.0008156854343293501,
|
3442 |
+
"loss": 0.1416,
|
3443 |
+
"step": 486
|
3444 |
+
},
|
3445 |
+
{
|
3446 |
+
"epoch": 0.86,
|
3447 |
+
"grad_norm": 0.5152392983436584,
|
3448 |
+
"learning_rate": 0.0008149619645472031,
|
3449 |
+
"loss": 0.1403,
|
3450 |
+
"step": 487
|
3451 |
+
},
|
3452 |
+
{
|
3453 |
+
"epoch": 0.86,
|
3454 |
+
"grad_norm": 0.15429601073265076,
|
3455 |
+
"learning_rate": 0.000814237399906744,
|
3456 |
+
"loss": 0.1322,
|
3457 |
+
"step": 488
|
3458 |
+
},
|
3459 |
+
{
|
3460 |
+
"epoch": 0.87,
|
3461 |
+
"grad_norm": 1.0002127885818481,
|
3462 |
+
"learning_rate": 0.0008135117429266756,
|
3463 |
+
"loss": 0.1303,
|
3464 |
+
"step": 489
|
3465 |
+
},
|
3466 |
+
{
|
3467 |
+
"epoch": 0.87,
|
3468 |
+
"grad_norm": 0.7232715487480164,
|
3469 |
+
"learning_rate": 0.0008127849961294984,
|
3470 |
+
"loss": 0.143,
|
3471 |
+
"step": 490
|
3472 |
+
},
|
3473 |
+
{
|
3474 |
+
"epoch": 0.87,
|
3475 |
+
"grad_norm": 0.13510456681251526,
|
3476 |
+
"learning_rate": 0.0008120571620415006,
|
3477 |
+
"loss": 0.1536,
|
3478 |
+
"step": 491
|
3479 |
+
},
|
3480 |
+
{
|
3481 |
+
"epoch": 0.87,
|
3482 |
+
"grad_norm": 0.5168789625167847,
|
3483 |
+
"learning_rate": 0.0008113282431927503,
|
3484 |
+
"loss": 0.1312,
|
3485 |
+
"step": 492
|
3486 |
+
},
|
3487 |
+
{
|
3488 |
+
"epoch": 0.87,
|
3489 |
+
"grad_norm": 0.7039850950241089,
|
3490 |
+
"learning_rate": 0.000810598242117086,
|
3491 |
+
"loss": 0.118,
|
3492 |
+
"step": 493
|
3493 |
+
},
|
3494 |
+
{
|
3495 |
+
"epoch": 0.87,
|
3496 |
+
"grad_norm": 1.5126641988754272,
|
3497 |
+
"learning_rate": 0.0008098671613521089,
|
3498 |
+
"loss": 0.2343,
|
3499 |
+
"step": 494
|
3500 |
+
},
|
3501 |
+
{
|
3502 |
+
"epoch": 0.88,
|
3503 |
+
"grad_norm": 0.6958308815956116,
|
3504 |
+
"learning_rate": 0.0008091350034391731,
|
3505 |
+
"loss": 0.1648,
|
3506 |
+
"step": 495
|
3507 |
+
},
|
3508 |
+
{
|
3509 |
+
"epoch": 0.88,
|
3510 |
+
"grad_norm": 6.979303359985352,
|
3511 |
+
"learning_rate": 0.0008084017709233766,
|
3512 |
+
"loss": 0.2261,
|
3513 |
+
"step": 496
|
3514 |
+
},
|
3515 |
+
{
|
3516 |
+
"epoch": 0.88,
|
3517 |
+
"grad_norm": 0.3389752507209778,
|
3518 |
+
"learning_rate": 0.0008076674663535537,
|
3519 |
+
"loss": 0.146,
|
3520 |
+
"step": 497
|
3521 |
+
},
|
3522 |
+
{
|
3523 |
+
"epoch": 0.88,
|
3524 |
+
"grad_norm": 0.19990071654319763,
|
3525 |
+
"learning_rate": 0.0008069320922822643,
|
3526 |
+
"loss": 0.1429,
|
3527 |
+
"step": 498
|
3528 |
+
},
|
3529 |
+
{
|
3530 |
+
"epoch": 0.88,
|
3531 |
+
"grad_norm": 0.33689868450164795,
|
3532 |
+
"learning_rate": 0.0008061956512657871,
|
3533 |
+
"loss": 0.147,
|
3534 |
+
"step": 499
|
3535 |
+
},
|
3536 |
+
{
|
3537 |
+
"epoch": 0.88,
|
3538 |
+
"grad_norm": 0.09925112873315811,
|
3539 |
+
"learning_rate": 0.000805458145864109,
|
3540 |
+
"loss": 0.1342,
|
3541 |
+
"step": 500
|
3542 |
+
},
|
3543 |
+
{
|
3544 |
+
"epoch": 0.89,
|
3545 |
+
"grad_norm": 1.961702585220337,
|
3546 |
+
"learning_rate": 0.0008047195786409172,
|
3547 |
+
"loss": 0.1361,
|
3548 |
+
"step": 501
|
3549 |
+
},
|
3550 |
+
{
|
3551 |
+
"epoch": 0.89,
|
3552 |
+
"grad_norm": 0.4342229962348938,
|
3553 |
+
"learning_rate": 0.0008039799521635895,
|
3554 |
+
"loss": 0.1485,
|
3555 |
+
"step": 502
|
3556 |
+
},
|
3557 |
+
{
|
3558 |
+
"epoch": 0.89,
|
3559 |
+
"grad_norm": 0.1798858642578125,
|
3560 |
+
"learning_rate": 0.0008032392690031867,
|
3561 |
+
"loss": 0.1314,
|
3562 |
+
"step": 503
|
3563 |
+
},
|
3564 |
+
{
|
3565 |
+
"epoch": 0.89,
|
3566 |
+
"grad_norm": 1.3653756380081177,
|
3567 |
+
"learning_rate": 0.0008024975317344421,
|
3568 |
+
"loss": 0.1388,
|
3569 |
+
"step": 504
|
3570 |
+
},
|
3571 |
+
{
|
3572 |
+
"epoch": 0.89,
|
3573 |
+
"grad_norm": 9.677605628967285,
|
3574 |
+
"learning_rate": 0.0008017547429357531,
|
3575 |
+
"loss": 0.4186,
|
3576 |
+
"step": 505
|
3577 |
+
},
|
3578 |
+
{
|
3579 |
+
"epoch": 0.9,
|
3580 |
+
"grad_norm": 8.348475456237793,
|
3581 |
+
"learning_rate": 0.0008010109051891731,
|
3582 |
+
"loss": 0.3806,
|
3583 |
+
"step": 506
|
3584 |
+
},
|
3585 |
+
{
|
3586 |
+
"epoch": 0.9,
|
3587 |
+
"grad_norm": 35.19770050048828,
|
3588 |
+
"learning_rate": 0.0008002660210804011,
|
3589 |
+
"loss": 3.6145,
|
3590 |
+
"step": 507
|
3591 |
+
},
|
3592 |
+
{
|
3593 |
+
"epoch": 0.9,
|
3594 |
+
"grad_norm": 9.18663501739502,
|
3595 |
+
"learning_rate": 0.0007995200931987743,
|
3596 |
+
"loss": 0.6162,
|
3597 |
+
"step": 508
|
3598 |
+
},
|
3599 |
+
{
|
3600 |
+
"epoch": 0.9,
|
3601 |
+
"grad_norm": 0.05997322499752045,
|
3602 |
+
"learning_rate": 0.0007987731241372571,
|
3603 |
+
"loss": 0.1129,
|
3604 |
+
"step": 509
|
3605 |
+
},
|
3606 |
+
{
|
3607 |
+
"epoch": 0.9,
|
3608 |
+
"grad_norm": 0.41408172249794006,
|
3609 |
+
"learning_rate": 0.000798025116492434,
|
3610 |
+
"loss": 0.1512,
|
3611 |
+
"step": 510
|
3612 |
+
},
|
3613 |
+
{
|
3614 |
+
"epoch": 0.9,
|
3615 |
+
"grad_norm": 0.4445393979549408,
|
3616 |
+
"learning_rate": 0.0007972760728644996,
|
3617 |
+
"loss": 0.1463,
|
3618 |
+
"step": 511
|
3619 |
+
},
|
3620 |
+
{
|
3621 |
+
"epoch": 0.91,
|
3622 |
+
"grad_norm": 0.19678063690662384,
|
3623 |
+
"learning_rate": 0.0007965259958572495,
|
3624 |
+
"loss": 0.1386,
|
3625 |
+
"step": 512
|
3626 |
+
},
|
3627 |
+
{
|
3628 |
+
"epoch": 0.91,
|
3629 |
+
"grad_norm": 0.45497119426727295,
|
3630 |
+
"learning_rate": 0.0007957748880780721,
|
3631 |
+
"loss": 0.1373,
|
3632 |
+
"step": 513
|
3633 |
+
},
|
3634 |
+
{
|
3635 |
+
"epoch": 0.91,
|
3636 |
+
"grad_norm": 0.6455509066581726,
|
3637 |
+
"learning_rate": 0.0007950227521379381,
|
3638 |
+
"loss": 0.1584,
|
3639 |
+
"step": 514
|
3640 |
+
},
|
3641 |
+
{
|
3642 |
+
"epoch": 0.91,
|
3643 |
+
"grad_norm": 0.3793765604496002,
|
3644 |
+
"learning_rate": 0.0007942695906513929,
|
3645 |
+
"loss": 0.1236,
|
3646 |
+
"step": 515
|
3647 |
+
},
|
3648 |
+
{
|
3649 |
+
"epoch": 0.91,
|
3650 |
+
"grad_norm": 0.20562775433063507,
|
3651 |
+
"learning_rate": 0.0007935154062365467,
|
3652 |
+
"loss": 0.1364,
|
3653 |
+
"step": 516
|
3654 |
+
},
|
3655 |
+
{
|
3656 |
+
"epoch": 0.91,
|
3657 |
+
"grad_norm": 1.3131325244903564,
|
3658 |
+
"learning_rate": 0.0007927602015150655,
|
3659 |
+
"loss": 0.1556,
|
3660 |
+
"step": 517
|
3661 |
+
},
|
3662 |
+
{
|
3663 |
+
"epoch": 0.92,
|
3664 |
+
"grad_norm": 0.1705670803785324,
|
3665 |
+
"learning_rate": 0.0007920039791121617,
|
3666 |
+
"loss": 0.1372,
|
3667 |
+
"step": 518
|
3668 |
+
},
|
3669 |
+
{
|
3670 |
+
"epoch": 0.92,
|
3671 |
+
"grad_norm": 6.6207499504089355,
|
3672 |
+
"learning_rate": 0.0007912467416565861,
|
3673 |
+
"loss": 0.22,
|
3674 |
+
"step": 519
|
3675 |
+
},
|
3676 |
+
{
|
3677 |
+
"epoch": 0.92,
|
3678 |
+
"grad_norm": 0.34343230724334717,
|
3679 |
+
"learning_rate": 0.0007904884917806173,
|
3680 |
+
"loss": 0.1453,
|
3681 |
+
"step": 520
|
3682 |
+
},
|
3683 |
+
{
|
3684 |
+
"epoch": 0.92,
|
3685 |
+
"grad_norm": 0.4290754497051239,
|
3686 |
+
"learning_rate": 0.0007897292321200537,
|
3687 |
+
"loss": 0.1177,
|
3688 |
+
"step": 521
|
3689 |
+
},
|
3690 |
+
{
|
3691 |
+
"epoch": 0.92,
|
3692 |
+
"grad_norm": 0.24469922482967377,
|
3693 |
+
"learning_rate": 0.0007889689653142036,
|
3694 |
+
"loss": 0.1369,
|
3695 |
+
"step": 522
|
3696 |
+
},
|
3697 |
+
{
|
3698 |
+
"epoch": 0.93,
|
3699 |
+
"grad_norm": 0.5307168960571289,
|
3700 |
+
"learning_rate": 0.0007882076940058763,
|
3701 |
+
"loss": 0.1542,
|
3702 |
+
"step": 523
|
3703 |
+
},
|
3704 |
+
{
|
3705 |
+
"epoch": 0.93,
|
3706 |
+
"grad_norm": 0.13802866637706757,
|
3707 |
+
"learning_rate": 0.000787445420841373,
|
3708 |
+
"loss": 0.1372,
|
3709 |
+
"step": 524
|
3710 |
+
},
|
3711 |
+
{
|
3712 |
+
"epoch": 0.93,
|
3713 |
+
"grad_norm": 0.36055922508239746,
|
3714 |
+
"learning_rate": 0.0007866821484704776,
|
3715 |
+
"loss": 0.1413,
|
3716 |
+
"step": 525
|
3717 |
+
},
|
3718 |
+
{
|
3719 |
+
"epoch": 0.93,
|
3720 |
+
"grad_norm": 0.36655113101005554,
|
3721 |
+
"learning_rate": 0.0007859178795464472,
|
3722 |
+
"loss": 0.1438,
|
3723 |
+
"step": 526
|
3724 |
+
},
|
3725 |
+
{
|
3726 |
+
"epoch": 0.93,
|
3727 |
+
"grad_norm": 0.6237390637397766,
|
3728 |
+
"learning_rate": 0.0007851526167260034,
|
3729 |
+
"loss": 0.1382,
|
3730 |
+
"step": 527
|
3731 |
+
},
|
3732 |
+
{
|
3733 |
+
"epoch": 0.93,
|
3734 |
+
"grad_norm": 0.42217007279396057,
|
3735 |
+
"learning_rate": 0.0007843863626693221,
|
3736 |
+
"loss": 0.1408,
|
3737 |
+
"step": 528
|
3738 |
+
},
|
3739 |
+
{
|
3740 |
+
"epoch": 0.94,
|
3741 |
+
"grad_norm": 24.023250579833984,
|
3742 |
+
"learning_rate": 0.0007836191200400256,
|
3743 |
+
"loss": 0.1517,
|
3744 |
+
"step": 529
|
3745 |
+
},
|
3746 |
+
{
|
3747 |
+
"epoch": 0.94,
|
3748 |
+
"grad_norm": 0.31599146127700806,
|
3749 |
+
"learning_rate": 0.0007828508915051723,
|
3750 |
+
"loss": 0.1353,
|
3751 |
+
"step": 530
|
3752 |
+
},
|
3753 |
+
{
|
3754 |
+
"epoch": 0.94,
|
3755 |
+
"grad_norm": 0.6795622706413269,
|
3756 |
+
"learning_rate": 0.0007820816797352479,
|
3757 |
+
"loss": 0.1515,
|
3758 |
+
"step": 531
|
3759 |
+
},
|
3760 |
+
{
|
3761 |
+
"epoch": 0.94,
|
3762 |
+
"grad_norm": 0.37493640184402466,
|
3763 |
+
"learning_rate": 0.0007813114874041557,
|
3764 |
+
"loss": 0.141,
|
3765 |
+
"step": 532
|
3766 |
+
},
|
3767 |
+
{
|
3768 |
+
"epoch": 0.94,
|
3769 |
+
"grad_norm": 1.7365546226501465,
|
3770 |
+
"learning_rate": 0.0007805403171892079,
|
3771 |
+
"loss": 0.1347,
|
3772 |
+
"step": 533
|
3773 |
+
},
|
3774 |
+
{
|
3775 |
+
"epoch": 0.94,
|
3776 |
+
"grad_norm": 18.393390655517578,
|
3777 |
+
"learning_rate": 0.000779768171771116,
|
3778 |
+
"loss": 0.1753,
|
3779 |
+
"step": 534
|
3780 |
+
},
|
3781 |
+
{
|
3782 |
+
"epoch": 0.95,
|
3783 |
+
"grad_norm": 2.2978413105010986,
|
3784 |
+
"learning_rate": 0.0007789950538339812,
|
3785 |
+
"loss": 0.1418,
|
3786 |
+
"step": 535
|
3787 |
+
},
|
3788 |
+
{
|
3789 |
+
"epoch": 0.95,
|
3790 |
+
"grad_norm": 0.495151162147522,
|
3791 |
+
"learning_rate": 0.0007782209660652854,
|
3792 |
+
"loss": 0.146,
|
3793 |
+
"step": 536
|
3794 |
+
},
|
3795 |
+
{
|
3796 |
+
"epoch": 0.95,
|
3797 |
+
"grad_norm": 7.705572605133057,
|
3798 |
+
"learning_rate": 0.0007774459111558821,
|
3799 |
+
"loss": 0.2042,
|
3800 |
+
"step": 537
|
3801 |
+
},
|
3802 |
+
{
|
3803 |
+
"epoch": 0.95,
|
3804 |
+
"grad_norm": 0.6036086678504944,
|
3805 |
+
"learning_rate": 0.0007766698917999862,
|
3806 |
+
"loss": 0.1695,
|
3807 |
+
"step": 538
|
3808 |
+
},
|
3809 |
+
{
|
3810 |
+
"epoch": 0.95,
|
3811 |
+
"grad_norm": 127.21215057373047,
|
3812 |
+
"learning_rate": 0.0007758929106951656,
|
3813 |
+
"loss": 18.5136,
|
3814 |
+
"step": 539
|
3815 |
+
},
|
3816 |
+
{
|
3817 |
+
"epoch": 0.96,
|
3818 |
+
"grad_norm": 40.58448791503906,
|
3819 |
+
"learning_rate": 0.0007751149705423312,
|
3820 |
+
"loss": 0.5973,
|
3821 |
+
"step": 540
|
3822 |
+
},
|
3823 |
+
{
|
3824 |
+
"epoch": 0.96,
|
3825 |
+
"grad_norm": 0.6296218633651733,
|
3826 |
+
"learning_rate": 0.0007743360740457278,
|
3827 |
+
"loss": 0.1849,
|
3828 |
+
"step": 541
|
3829 |
+
},
|
3830 |
+
{
|
3831 |
+
"epoch": 0.96,
|
3832 |
+
"grad_norm": 0.4533160924911499,
|
3833 |
+
"learning_rate": 0.0007735562239129247,
|
3834 |
+
"loss": 0.1464,
|
3835 |
+
"step": 542
|
3836 |
+
},
|
3837 |
+
{
|
3838 |
+
"epoch": 0.96,
|
3839 |
+
"grad_norm": 0.2379036247730255,
|
3840 |
+
"learning_rate": 0.0007727754228548058,
|
3841 |
+
"loss": 0.1267,
|
3842 |
+
"step": 543
|
3843 |
+
},
|
3844 |
+
{
|
3845 |
+
"epoch": 0.96,
|
3846 |
+
"grad_norm": 0.8904889225959778,
|
3847 |
+
"learning_rate": 0.000771993673585561,
|
3848 |
+
"loss": 0.2181,
|
3849 |
+
"step": 544
|
3850 |
+
},
|
3851 |
+
{
|
3852 |
+
"epoch": 0.96,
|
3853 |
+
"grad_norm": 0.8934443593025208,
|
3854 |
+
"learning_rate": 0.0007712109788226762,
|
3855 |
+
"loss": 0.2158,
|
3856 |
+
"step": 545
|
3857 |
+
},
|
3858 |
+
{
|
3859 |
+
"epoch": 0.97,
|
3860 |
+
"grad_norm": 0.3368353545665741,
|
3861 |
+
"learning_rate": 0.0007704273412869238,
|
3862 |
+
"loss": 0.1489,
|
3863 |
+
"step": 546
|
3864 |
+
},
|
3865 |
+
{
|
3866 |
+
"epoch": 0.97,
|
3867 |
+
"grad_norm": 0.2570180594921112,
|
3868 |
+
"learning_rate": 0.0007696427637023537,
|
3869 |
+
"loss": 0.144,
|
3870 |
+
"step": 547
|
3871 |
+
},
|
3872 |
+
{
|
3873 |
+
"epoch": 0.97,
|
3874 |
+
"grad_norm": 2.865034580230713,
|
3875 |
+
"learning_rate": 0.0007688572487962834,
|
3876 |
+
"loss": 0.1664,
|
3877 |
+
"step": 548
|
3878 |
+
},
|
3879 |
+
{
|
3880 |
+
"epoch": 0.97,
|
3881 |
+
"grad_norm": 0.4369525611400604,
|
3882 |
+
"learning_rate": 0.0007680707992992888,
|
3883 |
+
"loss": 0.1777,
|
3884 |
+
"step": 549
|
3885 |
+
},
|
3886 |
+
{
|
3887 |
+
"epoch": 0.97,
|
3888 |
+
"grad_norm": 0.2545509934425354,
|
3889 |
+
"learning_rate": 0.0007672834179451942,
|
3890 |
+
"loss": 0.1536,
|
3891 |
+
"step": 550
|
3892 |
+
},
|
3893 |
+
{
|
3894 |
+
"epoch": 0.97,
|
3895 |
+
"grad_norm": 0.14455465972423553,
|
3896 |
+
"learning_rate": 0.0007664951074710638,
|
3897 |
+
"loss": 0.1256,
|
3898 |
+
"step": 551
|
3899 |
+
},
|
3900 |
+
{
|
3901 |
+
"epoch": 0.98,
|
3902 |
+
"grad_norm": 0.16001886129379272,
|
3903 |
+
"learning_rate": 0.0007657058706171911,
|
3904 |
+
"loss": 0.1356,
|
3905 |
+
"step": 552
|
3906 |
+
},
|
3907 |
+
{
|
3908 |
+
"epoch": 0.98,
|
3909 |
+
"grad_norm": 0.2537885308265686,
|
3910 |
+
"learning_rate": 0.0007649157101270903,
|
3911 |
+
"loss": 0.1393,
|
3912 |
+
"step": 553
|
3913 |
+
},
|
3914 |
+
{
|
3915 |
+
"epoch": 0.98,
|
3916 |
+
"grad_norm": 0.33060047030448914,
|
3917 |
+
"learning_rate": 0.0007641246287474854,
|
3918 |
+
"loss": 0.148,
|
3919 |
+
"step": 554
|
3920 |
+
},
|
3921 |
+
{
|
3922 |
+
"epoch": 0.98,
|
3923 |
+
"grad_norm": 1.691941499710083,
|
3924 |
+
"learning_rate": 0.0007633326292283028,
|
3925 |
+
"loss": 0.1764,
|
3926 |
+
"step": 555
|
3927 |
+
},
|
3928 |
+
{
|
3929 |
+
"epoch": 0.98,
|
3930 |
+
"grad_norm": 0.20472805202007294,
|
3931 |
+
"learning_rate": 0.0007625397143226595,
|
3932 |
+
"loss": 0.1424,
|
3933 |
+
"step": 556
|
3934 |
+
},
|
3935 |
+
{
|
3936 |
+
"epoch": 0.99,
|
3937 |
+
"grad_norm": 0.7124485969543457,
|
3938 |
+
"learning_rate": 0.0007617458867868553,
|
3939 |
+
"loss": 0.1482,
|
3940 |
+
"step": 557
|
3941 |
+
},
|
3942 |
+
{
|
3943 |
+
"epoch": 0.99,
|
3944 |
+
"grad_norm": 0.09631184488534927,
|
3945 |
+
"learning_rate": 0.0007609511493803615,
|
3946 |
+
"loss": 0.1392,
|
3947 |
+
"step": 558
|
3948 |
+
},
|
3949 |
+
{
|
3950 |
+
"epoch": 0.99,
|
3951 |
+
"grad_norm": 0.20814809203147888,
|
3952 |
+
"learning_rate": 0.0007601555048658133,
|
3953 |
+
"loss": 0.1384,
|
3954 |
+
"step": 559
|
3955 |
+
},
|
3956 |
+
{
|
3957 |
+
"epoch": 0.99,
|
3958 |
+
"grad_norm": 0.19566737115383148,
|
3959 |
+
"learning_rate": 0.0007593589560089984,
|
3960 |
+
"loss": 0.1394,
|
3961 |
+
"step": 560
|
3962 |
+
},
|
3963 |
+
{
|
3964 |
+
"epoch": 0.99,
|
3965 |
+
"grad_norm": 0.13406091928482056,
|
3966 |
+
"learning_rate": 0.0007585615055788484,
|
3967 |
+
"loss": 0.1389,
|
3968 |
+
"step": 561
|
3969 |
+
},
|
3970 |
+
{
|
3971 |
+
"epoch": 0.99,
|
3972 |
+
"grad_norm": 0.07635807991027832,
|
3973 |
+
"learning_rate": 0.0007577631563474291,
|
3974 |
+
"loss": 0.1376,
|
3975 |
+
"step": 562
|
3976 |
+
},
|
3977 |
+
{
|
3978 |
+
"epoch": 1.0,
|
3979 |
+
"grad_norm": 0.11265091598033905,
|
3980 |
+
"learning_rate": 0.0007569639110899302,
|
3981 |
+
"loss": 0.1395,
|
3982 |
+
"step": 563
|
3983 |
+
},
|
3984 |
+
{
|
3985 |
+
"epoch": 1.0,
|
3986 |
+
"grad_norm": 0.31152746081352234,
|
3987 |
+
"learning_rate": 0.0007561637725846567,
|
3988 |
+
"loss": 0.1407,
|
3989 |
+
"step": 564
|
3990 |
+
},
|
3991 |
+
{
|
3992 |
+
"epoch": 1.0,
|
3993 |
+
"grad_norm": 0.13474373519420624,
|
3994 |
+
"learning_rate": 0.0007553627436130183,
|
3995 |
+
"loss": 0.1386,
|
3996 |
+
"step": 565
|
3997 |
+
}
|
3998 |
+
],
|
3999 |
+
"logging_steps": 1,
|
4000 |
+
"max_steps": 1695,
|
4001 |
+
"num_input_tokens_seen": 0,
|
4002 |
+
"num_train_epochs": 3,
|
4003 |
+
"save_steps": 565,
|
4004 |
+
"total_flos": 5.169945694856806e+16,
|
4005 |
+
"train_batch_size": 2,
|
4006 |
+
"trial_name": null,
|
4007 |
+
"trial_params": null
|
4008 |
+
}
|
checkpoint-565/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:242a9177bc415e2f72dc78b8f2eb1cd29a0e78da733db42237e6bb4cd1af9c7d
|
3 |
+
size 5752
|
checkpoint-565/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen1.5-7B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 151643,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 28,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"quantization_config": {
|
19 |
+
"_load_in_4bit": false,
|
20 |
+
"_load_in_8bit": true,
|
21 |
+
"bnb_4bit_compute_dtype": "float32",
|
22 |
+
"bnb_4bit_quant_storage": "uint8",
|
23 |
+
"bnb_4bit_quant_type": "fp4",
|
24 |
+
"bnb_4bit_use_double_quant": false,
|
25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
+
"llm_int8_has_fp16_weight": false,
|
27 |
+
"llm_int8_skip_modules": null,
|
28 |
+
"llm_int8_threshold": 6.0,
|
29 |
+
"load_in_4bit": false,
|
30 |
+
"load_in_8bit": true,
|
31 |
+
"quant_method": "bitsandbytes"
|
32 |
+
},
|
33 |
+
"rms_norm_eps": 1e-06,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"sliding_window": 32768,
|
36 |
+
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.40.0.dev0",
|
39 |
+
"use_cache": false,
|
40 |
+
"use_sliding_window": false,
|
41 |
+
"vocab_size": 151936
|
42 |
+
}
|