ashishkgpian
commited on
Commit
•
d962acd
1
Parent(s):
dee98b3
Upload 12 files
Browse files- README.md +202 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- trainer_state.json +1421 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
|
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
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
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,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": "unsloth",
|
22 |
+
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
+
"o_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a58c34870ae5ef773b51d8fb7f47bdd762b0a37616f5a6ae8708960bf30933b
|
3 |
+
size 167832240
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00eee73183c9265f497dba099945739d1bbf49be42d9ca7bb3c107231324cf61
|
3 |
+
size 84570708
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec995be8da3d39228d72b8931b8e5157f0339a5f6c8af5793ddbc486f90572ed
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa41211d323a3363275f879a622aa34ba4d6b9ecee7b316b032578d61e144814
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 32768,
|
37 |
+
"pad_token": "<unk>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false
|
44 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.09142857142857143,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
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": 2.563270330429077,
|
14 |
+
"learning_rate": 4e-05,
|
15 |
+
"loss": 2.4127,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 2.333299160003662,
|
21 |
+
"learning_rate": 8e-05,
|
22 |
+
"loss": 2.3102,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0,
|
27 |
+
"grad_norm": 1.8613317012786865,
|
28 |
+
"learning_rate": 0.00012,
|
29 |
+
"loss": 2.1983,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0,
|
34 |
+
"grad_norm": 1.620126485824585,
|
35 |
+
"learning_rate": 0.00016,
|
36 |
+
"loss": 2.0917,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0,
|
41 |
+
"grad_norm": 1.0352119207382202,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 1.9613,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"grad_norm": 0.8601917624473572,
|
49 |
+
"learning_rate": 0.00019979899497487438,
|
50 |
+
"loss": 1.6927,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"grad_norm": 1.273868203163147,
|
56 |
+
"learning_rate": 0.00019959798994974876,
|
57 |
+
"loss": 1.6828,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.0,
|
62 |
+
"grad_norm": 1.0873847007751465,
|
63 |
+
"learning_rate": 0.00019939698492462313,
|
64 |
+
"loss": 1.5088,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0,
|
69 |
+
"grad_norm": 0.5800795555114746,
|
70 |
+
"learning_rate": 0.0001991959798994975,
|
71 |
+
"loss": 1.3702,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.0,
|
76 |
+
"grad_norm": 0.693160355091095,
|
77 |
+
"learning_rate": 0.00019899497487437187,
|
78 |
+
"loss": 1.3718,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.01,
|
83 |
+
"grad_norm": 0.49409618973731995,
|
84 |
+
"learning_rate": 0.00019879396984924622,
|
85 |
+
"loss": 1.3583,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"grad_norm": 0.47029319405555725,
|
91 |
+
"learning_rate": 0.00019859296482412062,
|
92 |
+
"loss": 1.2791,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.01,
|
97 |
+
"grad_norm": 0.43618088960647583,
|
98 |
+
"learning_rate": 0.000198391959798995,
|
99 |
+
"loss": 1.3161,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.01,
|
104 |
+
"grad_norm": 0.3907912075519562,
|
105 |
+
"learning_rate": 0.00019819095477386937,
|
106 |
+
"loss": 1.2954,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.01,
|
111 |
+
"grad_norm": 0.6292415857315063,
|
112 |
+
"learning_rate": 0.0001979899497487437,
|
113 |
+
"loss": 1.3397,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.01,
|
118 |
+
"grad_norm": 0.37423521280288696,
|
119 |
+
"learning_rate": 0.0001977889447236181,
|
120 |
+
"loss": 1.3983,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.01,
|
125 |
+
"grad_norm": 0.3845643699169159,
|
126 |
+
"learning_rate": 0.00019758793969849249,
|
127 |
+
"loss": 1.3349,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01,
|
132 |
+
"grad_norm": 0.3657298982143402,
|
133 |
+
"learning_rate": 0.00019738693467336683,
|
134 |
+
"loss": 1.2767,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01,
|
139 |
+
"grad_norm": 0.3727971315383911,
|
140 |
+
"learning_rate": 0.0001971859296482412,
|
141 |
+
"loss": 1.3672,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.01,
|
146 |
+
"grad_norm": 0.35123032331466675,
|
147 |
+
"learning_rate": 0.0001969849246231156,
|
148 |
+
"loss": 1.3692,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.01,
|
153 |
+
"grad_norm": 0.4003850221633911,
|
154 |
+
"learning_rate": 0.00019678391959798995,
|
155 |
+
"loss": 1.3412,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.01,
|
160 |
+
"grad_norm": 0.3638221323490143,
|
161 |
+
"learning_rate": 0.00019658291457286432,
|
162 |
+
"loss": 1.2813,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.01,
|
167 |
+
"grad_norm": 0.391216903924942,
|
168 |
+
"learning_rate": 0.0001963819095477387,
|
169 |
+
"loss": 1.2853,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.01,
|
174 |
+
"grad_norm": 0.4370620846748352,
|
175 |
+
"learning_rate": 0.0001961809045226131,
|
176 |
+
"loss": 1.2524,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.01,
|
181 |
+
"grad_norm": 0.3566085696220398,
|
182 |
+
"learning_rate": 0.00019597989949748744,
|
183 |
+
"loss": 1.3192,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.01,
|
188 |
+
"grad_norm": 0.35438084602355957,
|
189 |
+
"learning_rate": 0.00019577889447236181,
|
190 |
+
"loss": 1.2858,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.01,
|
195 |
+
"grad_norm": 0.3968108296394348,
|
196 |
+
"learning_rate": 0.0001955778894472362,
|
197 |
+
"loss": 1.3112,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.01,
|
202 |
+
"grad_norm": 0.36512017250061035,
|
203 |
+
"learning_rate": 0.00019537688442211056,
|
204 |
+
"loss": 1.278,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.01,
|
209 |
+
"grad_norm": 0.3982504606246948,
|
210 |
+
"learning_rate": 0.00019517587939698493,
|
211 |
+
"loss": 1.2392,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.01,
|
216 |
+
"grad_norm": 0.38377949595451355,
|
217 |
+
"learning_rate": 0.0001949748743718593,
|
218 |
+
"loss": 1.2843,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.01,
|
223 |
+
"grad_norm": 0.3582867980003357,
|
224 |
+
"learning_rate": 0.00019477386934673368,
|
225 |
+
"loss": 1.3008,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.01,
|
230 |
+
"grad_norm": 0.3572194576263428,
|
231 |
+
"learning_rate": 0.00019457286432160805,
|
232 |
+
"loss": 1.294,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.02,
|
237 |
+
"grad_norm": 0.35502907633781433,
|
238 |
+
"learning_rate": 0.00019437185929648243,
|
239 |
+
"loss": 1.3877,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.02,
|
244 |
+
"grad_norm": 0.3649040460586548,
|
245 |
+
"learning_rate": 0.0001941708542713568,
|
246 |
+
"loss": 1.2966,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.02,
|
251 |
+
"grad_norm": 0.3649256229400635,
|
252 |
+
"learning_rate": 0.00019396984924623117,
|
253 |
+
"loss": 1.2354,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.02,
|
258 |
+
"grad_norm": 0.36085084080696106,
|
259 |
+
"learning_rate": 0.00019376884422110552,
|
260 |
+
"loss": 1.2409,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.02,
|
265 |
+
"grad_norm": 0.35929059982299805,
|
266 |
+
"learning_rate": 0.00019356783919597992,
|
267 |
+
"loss": 1.243,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.02,
|
272 |
+
"grad_norm": 0.3897881805896759,
|
273 |
+
"learning_rate": 0.0001933668341708543,
|
274 |
+
"loss": 1.3945,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.02,
|
279 |
+
"grad_norm": 0.35484543442726135,
|
280 |
+
"learning_rate": 0.00019316582914572864,
|
281 |
+
"loss": 1.3433,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.02,
|
286 |
+
"grad_norm": 0.35691192746162415,
|
287 |
+
"learning_rate": 0.000192964824120603,
|
288 |
+
"loss": 1.3243,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.02,
|
293 |
+
"grad_norm": 0.3804129958152771,
|
294 |
+
"learning_rate": 0.0001927638190954774,
|
295 |
+
"loss": 1.2509,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.02,
|
300 |
+
"grad_norm": 0.3623339831829071,
|
301 |
+
"learning_rate": 0.00019256281407035178,
|
302 |
+
"loss": 1.1799,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.02,
|
307 |
+
"grad_norm": 0.3411855697631836,
|
308 |
+
"learning_rate": 0.00019236180904522613,
|
309 |
+
"loss": 1.2372,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.02,
|
314 |
+
"grad_norm": 0.36590930819511414,
|
315 |
+
"learning_rate": 0.0001921608040201005,
|
316 |
+
"loss": 1.2585,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.02,
|
321 |
+
"grad_norm": 0.30974116921424866,
|
322 |
+
"learning_rate": 0.0001919597989949749,
|
323 |
+
"loss": 1.2974,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.02,
|
328 |
+
"grad_norm": 0.32794803380966187,
|
329 |
+
"learning_rate": 0.00019175879396984925,
|
330 |
+
"loss": 1.2696,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.02,
|
335 |
+
"grad_norm": 0.33263906836509705,
|
336 |
+
"learning_rate": 0.00019155778894472362,
|
337 |
+
"loss": 1.3209,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.02,
|
342 |
+
"grad_norm": 0.31748828291893005,
|
343 |
+
"learning_rate": 0.000191356783919598,
|
344 |
+
"loss": 1.278,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.02,
|
349 |
+
"grad_norm": 0.34738561511039734,
|
350 |
+
"learning_rate": 0.0001911557788944724,
|
351 |
+
"loss": 1.2105,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.02,
|
356 |
+
"grad_norm": 0.3313944339752197,
|
357 |
+
"learning_rate": 0.00019095477386934674,
|
358 |
+
"loss": 1.2527,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.02,
|
363 |
+
"grad_norm": 0.33137476444244385,
|
364 |
+
"learning_rate": 0.0001907537688442211,
|
365 |
+
"loss": 1.2984,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.02,
|
370 |
+
"grad_norm": 0.31752490997314453,
|
371 |
+
"learning_rate": 0.00019055276381909548,
|
372 |
+
"loss": 1.307,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.02,
|
377 |
+
"grad_norm": 0.3111082911491394,
|
378 |
+
"learning_rate": 0.00019035175879396986,
|
379 |
+
"loss": 1.2769,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.02,
|
384 |
+
"grad_norm": 0.31065696477890015,
|
385 |
+
"learning_rate": 0.00019015075376884423,
|
386 |
+
"loss": 1.3082,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.03,
|
391 |
+
"grad_norm": 0.3382773697376251,
|
392 |
+
"learning_rate": 0.0001899497487437186,
|
393 |
+
"loss": 1.2744,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.03,
|
398 |
+
"grad_norm": 0.34320947527885437,
|
399 |
+
"learning_rate": 0.00018974874371859298,
|
400 |
+
"loss": 1.3013,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.03,
|
405 |
+
"grad_norm": 0.33131280541419983,
|
406 |
+
"learning_rate": 0.00018954773869346732,
|
407 |
+
"loss": 1.4066,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.03,
|
412 |
+
"grad_norm": 0.3357389569282532,
|
413 |
+
"learning_rate": 0.00018934673366834172,
|
414 |
+
"loss": 1.2841,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.03,
|
419 |
+
"grad_norm": 0.3200838267803192,
|
420 |
+
"learning_rate": 0.0001891457286432161,
|
421 |
+
"loss": 1.2654,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.03,
|
426 |
+
"grad_norm": 0.3336584270000458,
|
427 |
+
"learning_rate": 0.00018894472361809047,
|
428 |
+
"loss": 1.1716,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.03,
|
433 |
+
"grad_norm": 0.3128441274166107,
|
434 |
+
"learning_rate": 0.00018874371859296481,
|
435 |
+
"loss": 1.3009,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.03,
|
440 |
+
"grad_norm": 0.30249112844467163,
|
441 |
+
"learning_rate": 0.00018854271356783921,
|
442 |
+
"loss": 1.2311,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.03,
|
447 |
+
"grad_norm": 0.3263241946697235,
|
448 |
+
"learning_rate": 0.0001883417085427136,
|
449 |
+
"loss": 1.2344,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.03,
|
454 |
+
"grad_norm": 0.32348358631134033,
|
455 |
+
"learning_rate": 0.00018814070351758793,
|
456 |
+
"loss": 1.3023,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.03,
|
461 |
+
"grad_norm": 0.6508419513702393,
|
462 |
+
"learning_rate": 0.0001879396984924623,
|
463 |
+
"loss": 1.2028,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.03,
|
468 |
+
"grad_norm": 0.34560996294021606,
|
469 |
+
"learning_rate": 0.0001877386934673367,
|
470 |
+
"loss": 1.389,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.03,
|
475 |
+
"grad_norm": 0.36555996537208557,
|
476 |
+
"learning_rate": 0.00018753768844221108,
|
477 |
+
"loss": 1.3653,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.03,
|
482 |
+
"grad_norm": 0.3195466697216034,
|
483 |
+
"learning_rate": 0.00018733668341708543,
|
484 |
+
"loss": 1.2412,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.03,
|
489 |
+
"grad_norm": 0.30555933713912964,
|
490 |
+
"learning_rate": 0.0001871356783919598,
|
491 |
+
"loss": 1.2357,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.03,
|
496 |
+
"grad_norm": 0.30776411294937134,
|
497 |
+
"learning_rate": 0.0001869346733668342,
|
498 |
+
"loss": 1.3112,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.03,
|
503 |
+
"grad_norm": 0.31933915615081787,
|
504 |
+
"learning_rate": 0.00018673366834170854,
|
505 |
+
"loss": 1.1951,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.03,
|
510 |
+
"grad_norm": 0.3241545259952545,
|
511 |
+
"learning_rate": 0.00018653266331658292,
|
512 |
+
"loss": 1.2717,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.03,
|
517 |
+
"grad_norm": 0.3117482364177704,
|
518 |
+
"learning_rate": 0.0001863316582914573,
|
519 |
+
"loss": 1.3031,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.03,
|
524 |
+
"grad_norm": 0.33056551218032837,
|
525 |
+
"learning_rate": 0.0001861306532663317,
|
526 |
+
"loss": 1.2098,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.03,
|
531 |
+
"grad_norm": 0.32441195845603943,
|
532 |
+
"learning_rate": 0.00018592964824120604,
|
533 |
+
"loss": 1.2135,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.03,
|
538 |
+
"grad_norm": 0.34216779470443726,
|
539 |
+
"learning_rate": 0.0001857286432160804,
|
540 |
+
"loss": 1.2531,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.04,
|
545 |
+
"grad_norm": 0.32885247468948364,
|
546 |
+
"learning_rate": 0.00018552763819095478,
|
547 |
+
"loss": 1.3054,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.04,
|
552 |
+
"grad_norm": 0.34541794657707214,
|
553 |
+
"learning_rate": 0.00018532663316582915,
|
554 |
+
"loss": 1.3207,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.04,
|
559 |
+
"grad_norm": 0.30329057574272156,
|
560 |
+
"learning_rate": 0.00018512562814070353,
|
561 |
+
"loss": 1.2652,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.04,
|
566 |
+
"grad_norm": 0.31469491124153137,
|
567 |
+
"learning_rate": 0.0001849246231155779,
|
568 |
+
"loss": 1.1961,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.04,
|
573 |
+
"grad_norm": 0.3181230127811432,
|
574 |
+
"learning_rate": 0.00018472361809045227,
|
575 |
+
"loss": 1.3111,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.04,
|
580 |
+
"grad_norm": 0.3181725740432739,
|
581 |
+
"learning_rate": 0.00018452261306532662,
|
582 |
+
"loss": 1.3353,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.04,
|
587 |
+
"grad_norm": 0.3154084384441376,
|
588 |
+
"learning_rate": 0.00018432160804020102,
|
589 |
+
"loss": 1.2418,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.04,
|
594 |
+
"grad_norm": 0.35061103105545044,
|
595 |
+
"learning_rate": 0.0001841206030150754,
|
596 |
+
"loss": 1.2332,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.04,
|
601 |
+
"grad_norm": 0.3259966969490051,
|
602 |
+
"learning_rate": 0.00018391959798994977,
|
603 |
+
"loss": 1.3633,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.04,
|
608 |
+
"grad_norm": 0.31192857027053833,
|
609 |
+
"learning_rate": 0.0001837185929648241,
|
610 |
+
"loss": 1.1886,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.04,
|
615 |
+
"grad_norm": 0.32024237513542175,
|
616 |
+
"learning_rate": 0.0001835175879396985,
|
617 |
+
"loss": 1.2141,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.04,
|
622 |
+
"grad_norm": 0.302498459815979,
|
623 |
+
"learning_rate": 0.00018331658291457288,
|
624 |
+
"loss": 1.237,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.04,
|
629 |
+
"grad_norm": 0.3569789230823517,
|
630 |
+
"learning_rate": 0.00018311557788944723,
|
631 |
+
"loss": 1.3015,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.04,
|
636 |
+
"grad_norm": 0.3121156692504883,
|
637 |
+
"learning_rate": 0.0001829145728643216,
|
638 |
+
"loss": 1.281,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.04,
|
643 |
+
"grad_norm": 0.31279826164245605,
|
644 |
+
"learning_rate": 0.000182713567839196,
|
645 |
+
"loss": 1.2924,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.04,
|
650 |
+
"grad_norm": 0.3210877478122711,
|
651 |
+
"learning_rate": 0.00018251256281407038,
|
652 |
+
"loss": 1.3082,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.04,
|
657 |
+
"grad_norm": 0.331406831741333,
|
658 |
+
"learning_rate": 0.00018231155778894472,
|
659 |
+
"loss": 1.2434,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.04,
|
664 |
+
"grad_norm": 0.3135213255882263,
|
665 |
+
"learning_rate": 0.0001821105527638191,
|
666 |
+
"loss": 1.2188,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.04,
|
671 |
+
"grad_norm": 0.31146401166915894,
|
672 |
+
"learning_rate": 0.0001819095477386935,
|
673 |
+
"loss": 1.2484,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.04,
|
678 |
+
"grad_norm": 0.32071712613105774,
|
679 |
+
"learning_rate": 0.00018170854271356784,
|
680 |
+
"loss": 1.1927,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.04,
|
685 |
+
"grad_norm": 0.3343571722507477,
|
686 |
+
"learning_rate": 0.00018150753768844221,
|
687 |
+
"loss": 1.3443,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.04,
|
692 |
+
"grad_norm": 0.3510550558567047,
|
693 |
+
"learning_rate": 0.0001813065326633166,
|
694 |
+
"loss": 1.2832,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.05,
|
699 |
+
"grad_norm": 0.33436939120292664,
|
700 |
+
"learning_rate": 0.00018110552763819096,
|
701 |
+
"loss": 1.252,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.05,
|
706 |
+
"grad_norm": 0.3175451159477234,
|
707 |
+
"learning_rate": 0.00018090452261306533,
|
708 |
+
"loss": 1.251,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.05,
|
713 |
+
"grad_norm": 0.32603979110717773,
|
714 |
+
"learning_rate": 0.0001807035175879397,
|
715 |
+
"loss": 1.228,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.05,
|
720 |
+
"grad_norm": 0.3073003590106964,
|
721 |
+
"learning_rate": 0.00018050251256281408,
|
722 |
+
"loss": 1.2659,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.05,
|
727 |
+
"grad_norm": 0.3285619616508484,
|
728 |
+
"learning_rate": 0.00018030150753768845,
|
729 |
+
"loss": 1.2826,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.05,
|
734 |
+
"grad_norm": 0.3038572072982788,
|
735 |
+
"learning_rate": 0.00018010050251256282,
|
736 |
+
"loss": 1.217,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.05,
|
741 |
+
"grad_norm": 0.35778746008872986,
|
742 |
+
"learning_rate": 0.0001798994974874372,
|
743 |
+
"loss": 1.2901,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.05,
|
748 |
+
"grad_norm": 0.2900612950325012,
|
749 |
+
"learning_rate": 0.00017969849246231157,
|
750 |
+
"loss": 1.2651,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.05,
|
755 |
+
"grad_norm": 0.32928743958473206,
|
756 |
+
"learning_rate": 0.00017949748743718592,
|
757 |
+
"loss": 1.3143,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.05,
|
762 |
+
"grad_norm": 0.32471874356269836,
|
763 |
+
"learning_rate": 0.00017929648241206032,
|
764 |
+
"loss": 1.1834,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.05,
|
769 |
+
"grad_norm": 0.30989256501197815,
|
770 |
+
"learning_rate": 0.0001790954773869347,
|
771 |
+
"loss": 1.2216,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.05,
|
776 |
+
"grad_norm": 0.3371771275997162,
|
777 |
+
"learning_rate": 0.00017889447236180906,
|
778 |
+
"loss": 1.197,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.05,
|
783 |
+
"grad_norm": 0.31041428446769714,
|
784 |
+
"learning_rate": 0.0001786934673366834,
|
785 |
+
"loss": 1.27,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.05,
|
790 |
+
"grad_norm": 0.3152185082435608,
|
791 |
+
"learning_rate": 0.0001784924623115578,
|
792 |
+
"loss": 1.2436,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.05,
|
797 |
+
"grad_norm": 0.3227459490299225,
|
798 |
+
"learning_rate": 0.00017829145728643218,
|
799 |
+
"loss": 1.2401,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.05,
|
804 |
+
"grad_norm": 0.3246959149837494,
|
805 |
+
"learning_rate": 0.00017809045226130653,
|
806 |
+
"loss": 1.2703,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.05,
|
811 |
+
"grad_norm": 0.38032859563827515,
|
812 |
+
"learning_rate": 0.0001778894472361809,
|
813 |
+
"loss": 1.3266,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.05,
|
818 |
+
"grad_norm": 0.33325478434562683,
|
819 |
+
"learning_rate": 0.0001776884422110553,
|
820 |
+
"loss": 1.2954,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.05,
|
825 |
+
"grad_norm": 0.3178690969944,
|
826 |
+
"learning_rate": 0.00017748743718592967,
|
827 |
+
"loss": 1.1793,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.05,
|
832 |
+
"grad_norm": 0.31393784284591675,
|
833 |
+
"learning_rate": 0.00017728643216080402,
|
834 |
+
"loss": 1.277,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.05,
|
839 |
+
"grad_norm": 0.3150279223918915,
|
840 |
+
"learning_rate": 0.0001770854271356784,
|
841 |
+
"loss": 1.293,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.05,
|
846 |
+
"grad_norm": 0.32476913928985596,
|
847 |
+
"learning_rate": 0.0001768844221105528,
|
848 |
+
"loss": 1.2569,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.06,
|
853 |
+
"grad_norm": 0.36075925827026367,
|
854 |
+
"learning_rate": 0.00017668341708542714,
|
855 |
+
"loss": 1.205,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.06,
|
860 |
+
"grad_norm": 0.33134496212005615,
|
861 |
+
"learning_rate": 0.0001764824120603015,
|
862 |
+
"loss": 1.2299,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.06,
|
867 |
+
"grad_norm": 0.30507662892341614,
|
868 |
+
"learning_rate": 0.00017628140703517588,
|
869 |
+
"loss": 1.2883,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.06,
|
874 |
+
"grad_norm": 0.34049952030181885,
|
875 |
+
"learning_rate": 0.00017608040201005026,
|
876 |
+
"loss": 1.214,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.06,
|
881 |
+
"grad_norm": 0.3405919373035431,
|
882 |
+
"learning_rate": 0.00017587939698492463,
|
883 |
+
"loss": 1.2738,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.06,
|
888 |
+
"grad_norm": 0.3306083679199219,
|
889 |
+
"learning_rate": 0.000175678391959799,
|
890 |
+
"loss": 1.2415,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.06,
|
895 |
+
"grad_norm": 0.33770737051963806,
|
896 |
+
"learning_rate": 0.00017547738693467338,
|
897 |
+
"loss": 1.3233,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.06,
|
902 |
+
"grad_norm": 0.3261878788471222,
|
903 |
+
"learning_rate": 0.00017527638190954775,
|
904 |
+
"loss": 1.2695,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.06,
|
909 |
+
"grad_norm": 0.3433193266391754,
|
910 |
+
"learning_rate": 0.00017507537688442212,
|
911 |
+
"loss": 1.2052,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.06,
|
916 |
+
"grad_norm": 0.3111405670642853,
|
917 |
+
"learning_rate": 0.0001748743718592965,
|
918 |
+
"loss": 1.2798,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.06,
|
923 |
+
"grad_norm": 0.3630310297012329,
|
924 |
+
"learning_rate": 0.00017467336683417087,
|
925 |
+
"loss": 1.2567,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.06,
|
930 |
+
"grad_norm": 0.31963038444519043,
|
931 |
+
"learning_rate": 0.00017447236180904521,
|
932 |
+
"loss": 1.2455,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.06,
|
937 |
+
"grad_norm": 0.299695760011673,
|
938 |
+
"learning_rate": 0.00017427135678391961,
|
939 |
+
"loss": 1.207,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.06,
|
944 |
+
"grad_norm": 0.3167514503002167,
|
945 |
+
"learning_rate": 0.000174070351758794,
|
946 |
+
"loss": 1.2378,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.06,
|
951 |
+
"grad_norm": 0.31375688314437866,
|
952 |
+
"learning_rate": 0.00017386934673366836,
|
953 |
+
"loss": 1.2658,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.06,
|
958 |
+
"grad_norm": 0.34311383962631226,
|
959 |
+
"learning_rate": 0.0001736683417085427,
|
960 |
+
"loss": 1.2004,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.06,
|
965 |
+
"grad_norm": 0.31706517934799194,
|
966 |
+
"learning_rate": 0.0001734673366834171,
|
967 |
+
"loss": 1.1879,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.06,
|
972 |
+
"grad_norm": 0.31296172738075256,
|
973 |
+
"learning_rate": 0.00017326633165829148,
|
974 |
+
"loss": 1.1866,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.06,
|
979 |
+
"grad_norm": 0.3254072368144989,
|
980 |
+
"learning_rate": 0.00017306532663316582,
|
981 |
+
"loss": 1.1952,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.06,
|
986 |
+
"grad_norm": 0.3165453374385834,
|
987 |
+
"learning_rate": 0.0001728643216080402,
|
988 |
+
"loss": 1.3459,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.06,
|
993 |
+
"grad_norm": 0.35455992817878723,
|
994 |
+
"learning_rate": 0.0001726633165829146,
|
995 |
+
"loss": 1.2494,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.06,
|
1000 |
+
"grad_norm": 0.3116908073425293,
|
1001 |
+
"learning_rate": 0.00017246231155778897,
|
1002 |
+
"loss": 1.2225,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.07,
|
1007 |
+
"grad_norm": 0.3141638934612274,
|
1008 |
+
"learning_rate": 0.00017226130653266332,
|
1009 |
+
"loss": 1.3385,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.07,
|
1014 |
+
"grad_norm": 0.3096507787704468,
|
1015 |
+
"learning_rate": 0.0001720603015075377,
|
1016 |
+
"loss": 1.3257,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.07,
|
1021 |
+
"grad_norm": 0.3160630464553833,
|
1022 |
+
"learning_rate": 0.00017185929648241206,
|
1023 |
+
"loss": 1.2683,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.07,
|
1028 |
+
"grad_norm": 0.3342824876308441,
|
1029 |
+
"learning_rate": 0.00017165829145728644,
|
1030 |
+
"loss": 1.2551,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.07,
|
1035 |
+
"grad_norm": 0.3086145222187042,
|
1036 |
+
"learning_rate": 0.0001714572864321608,
|
1037 |
+
"loss": 1.2456,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.07,
|
1042 |
+
"grad_norm": 0.3001709282398224,
|
1043 |
+
"learning_rate": 0.00017125628140703518,
|
1044 |
+
"loss": 1.2287,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.07,
|
1049 |
+
"grad_norm": 0.3277103304862976,
|
1050 |
+
"learning_rate": 0.00017105527638190955,
|
1051 |
+
"loss": 1.3302,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.07,
|
1056 |
+
"grad_norm": 0.33616161346435547,
|
1057 |
+
"learning_rate": 0.00017085427135678393,
|
1058 |
+
"loss": 1.2604,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.07,
|
1063 |
+
"grad_norm": 0.3231915533542633,
|
1064 |
+
"learning_rate": 0.0001706532663316583,
|
1065 |
+
"loss": 1.2367,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.07,
|
1070 |
+
"grad_norm": 0.3305569291114807,
|
1071 |
+
"learning_rate": 0.00017045226130653267,
|
1072 |
+
"loss": 1.2387,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.07,
|
1077 |
+
"grad_norm": 0.35031118988990784,
|
1078 |
+
"learning_rate": 0.00017025125628140705,
|
1079 |
+
"loss": 1.2464,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.07,
|
1084 |
+
"grad_norm": 0.3142334222793579,
|
1085 |
+
"learning_rate": 0.00017005025125628142,
|
1086 |
+
"loss": 1.3614,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.07,
|
1091 |
+
"grad_norm": 0.31159430742263794,
|
1092 |
+
"learning_rate": 0.0001698492462311558,
|
1093 |
+
"loss": 1.2556,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.07,
|
1098 |
+
"grad_norm": 0.3273050785064697,
|
1099 |
+
"learning_rate": 0.00016964824120603016,
|
1100 |
+
"loss": 1.3519,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.07,
|
1105 |
+
"grad_norm": 0.3299296796321869,
|
1106 |
+
"learning_rate": 0.0001694472361809045,
|
1107 |
+
"loss": 1.1763,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.07,
|
1112 |
+
"grad_norm": 0.33138513565063477,
|
1113 |
+
"learning_rate": 0.0001692462311557789,
|
1114 |
+
"loss": 1.17,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.07,
|
1119 |
+
"grad_norm": 0.30424776673316956,
|
1120 |
+
"learning_rate": 0.00016904522613065328,
|
1121 |
+
"loss": 1.123,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.07,
|
1126 |
+
"grad_norm": 0.3452983498573303,
|
1127 |
+
"learning_rate": 0.00016884422110552766,
|
1128 |
+
"loss": 1.2999,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.07,
|
1133 |
+
"grad_norm": 0.33614206314086914,
|
1134 |
+
"learning_rate": 0.000168643216080402,
|
1135 |
+
"loss": 1.262,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.07,
|
1140 |
+
"grad_norm": 0.32416558265686035,
|
1141 |
+
"learning_rate": 0.0001684422110552764,
|
1142 |
+
"loss": 1.2514,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.07,
|
1147 |
+
"grad_norm": 0.29827457666397095,
|
1148 |
+
"learning_rate": 0.00016824120603015078,
|
1149 |
+
"loss": 1.2461,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.07,
|
1154 |
+
"grad_norm": 0.32572871446609497,
|
1155 |
+
"learning_rate": 0.00016804020100502512,
|
1156 |
+
"loss": 1.2393,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.08,
|
1161 |
+
"grad_norm": 0.32171282172203064,
|
1162 |
+
"learning_rate": 0.0001678391959798995,
|
1163 |
+
"loss": 1.3045,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.08,
|
1168 |
+
"grad_norm": 0.34592801332473755,
|
1169 |
+
"learning_rate": 0.0001676381909547739,
|
1170 |
+
"loss": 1.2669,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.08,
|
1175 |
+
"grad_norm": 0.33795440196990967,
|
1176 |
+
"learning_rate": 0.00016743718592964827,
|
1177 |
+
"loss": 1.1404,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.08,
|
1182 |
+
"grad_norm": 0.32598641514778137,
|
1183 |
+
"learning_rate": 0.0001672361809045226,
|
1184 |
+
"loss": 1.2495,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.08,
|
1189 |
+
"grad_norm": 0.31816181540489197,
|
1190 |
+
"learning_rate": 0.00016703517587939699,
|
1191 |
+
"loss": 1.3003,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.08,
|
1196 |
+
"grad_norm": 0.3340943157672882,
|
1197 |
+
"learning_rate": 0.00016683417085427136,
|
1198 |
+
"loss": 1.2615,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.08,
|
1203 |
+
"grad_norm": 0.3242477476596832,
|
1204 |
+
"learning_rate": 0.00016663316582914573,
|
1205 |
+
"loss": 1.2527,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.08,
|
1210 |
+
"grad_norm": 0.308652400970459,
|
1211 |
+
"learning_rate": 0.0001664321608040201,
|
1212 |
+
"loss": 1.3241,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.08,
|
1217 |
+
"grad_norm": 0.31818273663520813,
|
1218 |
+
"learning_rate": 0.00016623115577889448,
|
1219 |
+
"loss": 1.3712,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.08,
|
1224 |
+
"grad_norm": 0.32885751128196716,
|
1225 |
+
"learning_rate": 0.00016603015075376885,
|
1226 |
+
"loss": 1.2583,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.08,
|
1231 |
+
"grad_norm": 0.32561740279197693,
|
1232 |
+
"learning_rate": 0.00016582914572864322,
|
1233 |
+
"loss": 1.2458,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.08,
|
1238 |
+
"grad_norm": 0.3278496563434601,
|
1239 |
+
"learning_rate": 0.0001656281407035176,
|
1240 |
+
"loss": 1.2205,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.08,
|
1245 |
+
"grad_norm": 0.32530438899993896,
|
1246 |
+
"learning_rate": 0.00016542713567839197,
|
1247 |
+
"loss": 1.2235,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.08,
|
1252 |
+
"grad_norm": 0.31232836842536926,
|
1253 |
+
"learning_rate": 0.00016522613065326634,
|
1254 |
+
"loss": 1.199,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.08,
|
1259 |
+
"grad_norm": 0.3209743797779083,
|
1260 |
+
"learning_rate": 0.00016502512562814072,
|
1261 |
+
"loss": 1.2717,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.08,
|
1266 |
+
"grad_norm": 0.329940527677536,
|
1267 |
+
"learning_rate": 0.0001648241206030151,
|
1268 |
+
"loss": 1.2425,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.08,
|
1273 |
+
"grad_norm": 0.3144824802875519,
|
1274 |
+
"learning_rate": 0.00016462311557788946,
|
1275 |
+
"loss": 1.2444,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.08,
|
1280 |
+
"grad_norm": 0.3218553066253662,
|
1281 |
+
"learning_rate": 0.0001644221105527638,
|
1282 |
+
"loss": 1.2815,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.08,
|
1287 |
+
"grad_norm": 0.33460506796836853,
|
1288 |
+
"learning_rate": 0.0001642211055276382,
|
1289 |
+
"loss": 1.3774,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.08,
|
1294 |
+
"grad_norm": 0.3300727605819702,
|
1295 |
+
"learning_rate": 0.00016402010050251258,
|
1296 |
+
"loss": 1.3436,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.08,
|
1301 |
+
"grad_norm": 0.3530360460281372,
|
1302 |
+
"learning_rate": 0.00016381909547738695,
|
1303 |
+
"loss": 1.2605,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.09,
|
1308 |
+
"grad_norm": 0.3326485753059387,
|
1309 |
+
"learning_rate": 0.0001636180904522613,
|
1310 |
+
"loss": 1.2202,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.09,
|
1315 |
+
"grad_norm": 0.31355732679367065,
|
1316 |
+
"learning_rate": 0.0001634170854271357,
|
1317 |
+
"loss": 1.2798,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.09,
|
1322 |
+
"grad_norm": 0.3162304759025574,
|
1323 |
+
"learning_rate": 0.00016321608040201007,
|
1324 |
+
"loss": 1.2118,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.09,
|
1329 |
+
"grad_norm": 0.32264095544815063,
|
1330 |
+
"learning_rate": 0.00016301507537688442,
|
1331 |
+
"loss": 1.2775,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.09,
|
1336 |
+
"grad_norm": 0.30425918102264404,
|
1337 |
+
"learning_rate": 0.0001628140703517588,
|
1338 |
+
"loss": 1.1438,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.09,
|
1343 |
+
"grad_norm": 0.33907556533813477,
|
1344 |
+
"learning_rate": 0.00016261306532663316,
|
1345 |
+
"loss": 1.4077,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.09,
|
1350 |
+
"grad_norm": 0.32334232330322266,
|
1351 |
+
"learning_rate": 0.00016241206030150756,
|
1352 |
+
"loss": 1.2673,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.09,
|
1357 |
+
"grad_norm": 0.32999834418296814,
|
1358 |
+
"learning_rate": 0.0001622110552763819,
|
1359 |
+
"loss": 1.257,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.09,
|
1364 |
+
"grad_norm": 0.3223746120929718,
|
1365 |
+
"learning_rate": 0.00016201005025125628,
|
1366 |
+
"loss": 1.2125,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.09,
|
1371 |
+
"grad_norm": 0.3236989378929138,
|
1372 |
+
"learning_rate": 0.00016180904522613066,
|
1373 |
+
"loss": 1.3645,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.09,
|
1378 |
+
"grad_norm": 0.3303336203098297,
|
1379 |
+
"learning_rate": 0.00016160804020100503,
|
1380 |
+
"loss": 1.2786,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.09,
|
1385 |
+
"grad_norm": 0.3135005831718445,
|
1386 |
+
"learning_rate": 0.0001614070351758794,
|
1387 |
+
"loss": 1.2775,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.09,
|
1392 |
+
"grad_norm": 0.3185466527938843,
|
1393 |
+
"learning_rate": 0.00016120603015075378,
|
1394 |
+
"loss": 1.2128,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.09,
|
1399 |
+
"grad_norm": 0.3355714976787567,
|
1400 |
+
"learning_rate": 0.00016100502512562815,
|
1401 |
+
"loss": 1.307,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.09,
|
1406 |
+
"grad_norm": 0.339216023683548,
|
1407 |
+
"learning_rate": 0.00016080402010050252,
|
1408 |
+
"loss": 1.2845,
|
1409 |
+
"step": 200
|
1410 |
+
}
|
1411 |
+
],
|
1412 |
+
"logging_steps": 1,
|
1413 |
+
"max_steps": 1000,
|
1414 |
+
"num_input_tokens_seen": 0,
|
1415 |
+
"num_train_epochs": 1,
|
1416 |
+
"save_steps": 200,
|
1417 |
+
"total_flos": 9.299042116288512e+16,
|
1418 |
+
"train_batch_size": 4,
|
1419 |
+
"trial_name": null,
|
1420 |
+
"trial_params": null
|
1421 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa4eeaf829b7025ebff9e7e2b092d9eeb78c49b155d2e019614d1e7fc608faf
|
3 |
+
size 4856
|