Training in progress, step 150, checkpoint
Browse files- checkpoint-150/README.md +202 -0
- checkpoint-150/adapter_config.json +34 -0
- checkpoint-150/adapter_model.safetensors +3 -0
- checkpoint-150/added_tokens.json +17 -0
- checkpoint-150/optimizer.pt +3 -0
- checkpoint-150/rng_state_0.pth +3 -0
- checkpoint-150/rng_state_1.pth +3 -0
- checkpoint-150/rng_state_2.pth +3 -0
- checkpoint-150/rng_state_3.pth +3 -0
- checkpoint-150/rng_state_4.pth +3 -0
- checkpoint-150/rng_state_5.pth +3 -0
- checkpoint-150/rng_state_6.pth +3 -0
- checkpoint-150/rng_state_7.pth +3 -0
- checkpoint-150/scheduler.pt +3 -0
- checkpoint-150/special_tokens_map.json +30 -0
- checkpoint-150/tokenizer.json +0 -0
- checkpoint-150/tokenizer.model +3 -0
- checkpoint-150/tokenizer_config.json +163 -0
- checkpoint-150/trainer_state.json +1115 -0
- checkpoint-150/training_args.bin +3 -0
checkpoint-150/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
3 |
+
library_name: peft
|
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 0.11.1
|
checkpoint-150/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"embed_tokens",
|
19 |
+
"lm_head"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 512,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"o_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_up_proj",
|
29 |
+
"qkv_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-150/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:099bd494934934da641a4beafc3e0da2869b731ea9d1079adb8ee8d0e2bcf5f1
|
3 |
+
size 2004651224
|
checkpoint-150/added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</plan>": 32014,
|
3 |
+
"</thinking>": 32012,
|
4 |
+
"<plan>": 32013,
|
5 |
+
"<thinking>": 32011,
|
6 |
+
"<|assistant|>": 32001,
|
7 |
+
"<|endoftext|>": 32000,
|
8 |
+
"<|end|>": 32007,
|
9 |
+
"<|placeholder1|>": 32002,
|
10 |
+
"<|placeholder2|>": 32003,
|
11 |
+
"<|placeholder3|>": 32004,
|
12 |
+
"<|placeholder4|>": 32005,
|
13 |
+
"<|placeholder5|>": 32008,
|
14 |
+
"<|placeholder6|>": 32009,
|
15 |
+
"<|system|>": 32006,
|
16 |
+
"<|user|>": 32010
|
17 |
+
}
|
checkpoint-150/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a5543e6bfa204b227fc573e0a4673791992238bff497b5a66d1e56a87d5f1e7
|
3 |
+
size 4009448634
|
checkpoint-150/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54dc8a6e3fe14a41122aa8fa3190c54300056c70a27309ba399b9023bf344e8f
|
3 |
+
size 15984
|
checkpoint-150/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1da5e02fefd938f06090ad9332db3e38dbe95fb77dcd59c20b837ee7b4bc6b56
|
3 |
+
size 15984
|
checkpoint-150/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11a02efded1bea4dc84cea0eda463cddfce0c49815985b04b4f934098bd7be33
|
3 |
+
size 15984
|
checkpoint-150/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e117f62e33df54b80a82f3d7ec47fbcbbd45db406e9ecfae128a75a5e5e2e33a
|
3 |
+
size 15984
|
checkpoint-150/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8486aa224cb4dce1729cdb863b9213ef237f6775b502f65dc4b9a008a12c3631
|
3 |
+
size 15984
|
checkpoint-150/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5d14086cde94ce32a81094c4041c93d54107c414583c4f704bc3c7cb98438e2
|
3 |
+
size 15984
|
checkpoint-150/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cf079ec38d00894bebc63d0853018a10efeda0a3c5a60bd3e14654e1929f62e
|
3 |
+
size 15984
|
checkpoint-150/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:978974b2542a74e1b6d63c4e1a14f1e5343ee69cb5550e4113b8de32cbcaab04
|
3 |
+
size 15984
|
checkpoint-150/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a1aa30e3f64f0493cbd37ece65d5b2e0d0cb65a0834c45c4f0c0c9544b68d58
|
3 |
+
size 1064
|
checkpoint-150/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": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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 |
+
}
|
checkpoint-150/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-150/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-150/tokenizer_config.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<thinking>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "</thinking>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<plan>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "</plan>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"bos_token": "<s>",
|
152 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
153 |
+
"clean_up_tokenization_spaces": false,
|
154 |
+
"eos_token": "<|endoftext|>",
|
155 |
+
"legacy": false,
|
156 |
+
"model_max_length": 4096,
|
157 |
+
"pad_token": "<|endoftext|>",
|
158 |
+
"padding_side": "left",
|
159 |
+
"sp_model_kwargs": {},
|
160 |
+
"tokenizer_class": "LlamaTokenizer",
|
161 |
+
"unk_token": "<unk>",
|
162 |
+
"use_default_system_prompt": false
|
163 |
+
}
|
checkpoint-150/trainer_state.json
ADDED
@@ -0,0 +1,1115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5050505050505051,
|
5 |
+
"eval_steps": 38,
|
6 |
+
"global_step": 150,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.003367003367003367,
|
13 |
+
"grad_norm": 2.0,
|
14 |
+
"learning_rate": 3.5714285714285716e-07,
|
15 |
+
"loss": 1.0833,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.003367003367003367,
|
20 |
+
"eval_loss": 1.032954454421997,
|
21 |
+
"eval_runtime": 8.7744,
|
22 |
+
"eval_samples_per_second": 56.984,
|
23 |
+
"eval_steps_per_second": 3.647,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006734006734006734,
|
28 |
+
"grad_norm": 2.265625,
|
29 |
+
"learning_rate": 7.142857142857143e-07,
|
30 |
+
"loss": 0.996,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.010101010101010102,
|
35 |
+
"grad_norm": 1.640625,
|
36 |
+
"learning_rate": 1.0714285714285714e-06,
|
37 |
+
"loss": 1.0487,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013468013468013467,
|
42 |
+
"grad_norm": 2.046875,
|
43 |
+
"learning_rate": 1.4285714285714286e-06,
|
44 |
+
"loss": 1.0553,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.016835016835016835,
|
49 |
+
"grad_norm": 2.453125,
|
50 |
+
"learning_rate": 1.7857142857142859e-06,
|
51 |
+
"loss": 1.0339,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.020202020202020204,
|
56 |
+
"grad_norm": 1.984375,
|
57 |
+
"learning_rate": 2.1428571428571427e-06,
|
58 |
+
"loss": 1.014,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.02356902356902357,
|
63 |
+
"grad_norm": 2.609375,
|
64 |
+
"learning_rate": 2.5e-06,
|
65 |
+
"loss": 1.0298,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.026936026936026935,
|
70 |
+
"grad_norm": 2.328125,
|
71 |
+
"learning_rate": 2.8571428571428573e-06,
|
72 |
+
"loss": 1.0226,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.030303030303030304,
|
77 |
+
"grad_norm": 2.25,
|
78 |
+
"learning_rate": 3.2142857142857147e-06,
|
79 |
+
"loss": 1.0739,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03367003367003367,
|
84 |
+
"grad_norm": 2.28125,
|
85 |
+
"learning_rate": 3.5714285714285718e-06,
|
86 |
+
"loss": 1.0224,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.037037037037037035,
|
91 |
+
"grad_norm": 2.4375,
|
92 |
+
"learning_rate": 3.928571428571429e-06,
|
93 |
+
"loss": 1.0089,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.04040404040404041,
|
98 |
+
"grad_norm": 2.03125,
|
99 |
+
"learning_rate": 4.2857142857142855e-06,
|
100 |
+
"loss": 1.0529,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.04377104377104377,
|
105 |
+
"grad_norm": 2.03125,
|
106 |
+
"learning_rate": 4.642857142857144e-06,
|
107 |
+
"loss": 1.068,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04713804713804714,
|
112 |
+
"grad_norm": 1.7265625,
|
113 |
+
"learning_rate": 5e-06,
|
114 |
+
"loss": 1.0318,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.050505050505050504,
|
119 |
+
"grad_norm": 1.8359375,
|
120 |
+
"learning_rate": 4.9998459603839726e-06,
|
121 |
+
"loss": 1.0439,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.05387205387205387,
|
126 |
+
"grad_norm": 2.15625,
|
127 |
+
"learning_rate": 4.9993838605184505e-06,
|
128 |
+
"loss": 1.0647,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05723905723905724,
|
133 |
+
"grad_norm": 1.6015625,
|
134 |
+
"learning_rate": 4.998613757348784e-06,
|
135 |
+
"loss": 1.0081,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.06060606060606061,
|
140 |
+
"grad_norm": 1.65625,
|
141 |
+
"learning_rate": 4.99753574577609e-06,
|
142 |
+
"loss": 1.0098,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.06397306397306397,
|
147 |
+
"grad_norm": 1.4140625,
|
148 |
+
"learning_rate": 4.996149958645559e-06,
|
149 |
+
"loss": 0.9822,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.06734006734006734,
|
154 |
+
"grad_norm": 1.375,
|
155 |
+
"learning_rate": 4.994456566730085e-06,
|
156 |
+
"loss": 1.0474,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.0707070707070707,
|
161 |
+
"grad_norm": 1.2265625,
|
162 |
+
"learning_rate": 4.992455778709222e-06,
|
163 |
+
"loss": 1.0421,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07407407407407407,
|
168 |
+
"grad_norm": 1.4609375,
|
169 |
+
"learning_rate": 4.990147841143462e-06,
|
170 |
+
"loss": 0.9845,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07744107744107744,
|
175 |
+
"grad_norm": 1.2421875,
|
176 |
+
"learning_rate": 4.98753303844386e-06,
|
177 |
+
"loss": 0.9773,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.08080808080808081,
|
182 |
+
"grad_norm": 1.4296875,
|
183 |
+
"learning_rate": 4.984611692836979e-06,
|
184 |
+
"loss": 1.0511,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.08417508417508418,
|
189 |
+
"grad_norm": 1.1875,
|
190 |
+
"learning_rate": 4.981384164325184e-06,
|
191 |
+
"loss": 0.9915,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.08754208754208755,
|
196 |
+
"grad_norm": 1.15625,
|
197 |
+
"learning_rate": 4.977850850642275e-06,
|
198 |
+
"loss": 0.9881,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.09090909090909091,
|
203 |
+
"grad_norm": 1.296875,
|
204 |
+
"learning_rate": 4.97401218720448e-06,
|
205 |
+
"loss": 1.0623,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09427609427609428,
|
210 |
+
"grad_norm": 1.2734375,
|
211 |
+
"learning_rate": 4.969868647056793e-06,
|
212 |
+
"loss": 1.0282,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09764309764309764,
|
217 |
+
"grad_norm": 1.125,
|
218 |
+
"learning_rate": 4.965420740814679e-06,
|
219 |
+
"loss": 1.0122,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.10101010101010101,
|
224 |
+
"grad_norm": 1.25,
|
225 |
+
"learning_rate": 4.960669016601155e-06,
|
226 |
+
"loss": 1.0342,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.10437710437710437,
|
231 |
+
"grad_norm": 1.0625,
|
232 |
+
"learning_rate": 4.95561405997924e-06,
|
233 |
+
"loss": 0.9911,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.10774410774410774,
|
238 |
+
"grad_norm": 1.21875,
|
239 |
+
"learning_rate": 4.950256493879795e-06,
|
240 |
+
"loss": 1.025,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1111111111111111,
|
245 |
+
"grad_norm": 1.1328125,
|
246 |
+
"learning_rate": 4.94459697852476e-06,
|
247 |
+
"loss": 1.022,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11447811447811448,
|
252 |
+
"grad_norm": 1.1953125,
|
253 |
+
"learning_rate": 4.938636211345792e-06,
|
254 |
+
"loss": 1.0085,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11784511784511785,
|
259 |
+
"grad_norm": 1.1484375,
|
260 |
+
"learning_rate": 4.932374926898321e-06,
|
261 |
+
"loss": 1.0109,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12121212121212122,
|
266 |
+
"grad_norm": 1.0390625,
|
267 |
+
"learning_rate": 4.92581389677103e-06,
|
268 |
+
"loss": 0.9654,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12457912457912458,
|
273 |
+
"grad_norm": 1.109375,
|
274 |
+
"learning_rate": 4.918953929490768e-06,
|
275 |
+
"loss": 1.0041,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12794612794612795,
|
280 |
+
"grad_norm": 1.09375,
|
281 |
+
"learning_rate": 4.911795870422916e-06,
|
282 |
+
"loss": 1.0118,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.12794612794612795,
|
287 |
+
"eval_loss": 0.9947459697723389,
|
288 |
+
"eval_runtime": 8.7184,
|
289 |
+
"eval_samples_per_second": 57.35,
|
290 |
+
"eval_steps_per_second": 3.67,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.13131313131313133,
|
295 |
+
"grad_norm": 0.9765625,
|
296 |
+
"learning_rate": 4.904340601667208e-06,
|
297 |
+
"loss": 0.9841,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.13468013468013468,
|
302 |
+
"grad_norm": 1.046875,
|
303 |
+
"learning_rate": 4.896589041949036e-06,
|
304 |
+
"loss": 1.0055,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.13804713804713806,
|
309 |
+
"grad_norm": 1.171875,
|
310 |
+
"learning_rate": 4.888542146506224e-06,
|
311 |
+
"loss": 0.9728,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.1414141414141414,
|
316 |
+
"grad_norm": 0.9765625,
|
317 |
+
"learning_rate": 4.880200906971321e-06,
|
318 |
+
"loss": 0.975,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.1447811447811448,
|
323 |
+
"grad_norm": 1.0234375,
|
324 |
+
"learning_rate": 4.8715663512493924e-06,
|
325 |
+
"loss": 0.9628,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.14814814814814814,
|
330 |
+
"grad_norm": 0.92578125,
|
331 |
+
"learning_rate": 4.8626395433913595e-06,
|
332 |
+
"loss": 0.9668,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.15151515151515152,
|
337 |
+
"grad_norm": 1.078125,
|
338 |
+
"learning_rate": 4.853421583462866e-06,
|
339 |
+
"loss": 0.9539,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15488215488215487,
|
344 |
+
"grad_norm": 1.1484375,
|
345 |
+
"learning_rate": 4.8439136074087165e-06,
|
346 |
+
"loss": 1.0145,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15824915824915825,
|
351 |
+
"grad_norm": 1.015625,
|
352 |
+
"learning_rate": 4.834116786912897e-06,
|
353 |
+
"loss": 0.9738,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16161616161616163,
|
358 |
+
"grad_norm": 1.0390625,
|
359 |
+
"learning_rate": 4.82403232925418e-06,
|
360 |
+
"loss": 0.9907,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16498316498316498,
|
365 |
+
"grad_norm": 1.0546875,
|
366 |
+
"learning_rate": 4.813661477157355e-06,
|
367 |
+
"loss": 0.9773,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.16835016835016836,
|
372 |
+
"grad_norm": 1.015625,
|
373 |
+
"learning_rate": 4.803005508640083e-06,
|
374 |
+
"loss": 0.9636,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.1717171717171717,
|
379 |
+
"grad_norm": 0.9375,
|
380 |
+
"learning_rate": 4.7920657368554e-06,
|
381 |
+
"loss": 0.9589,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.1750841750841751,
|
386 |
+
"grad_norm": 0.9765625,
|
387 |
+
"learning_rate": 4.780843509929905e-06,
|
388 |
+
"loss": 0.9753,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17845117845117844,
|
393 |
+
"grad_norm": 1.015625,
|
394 |
+
"learning_rate": 4.769340210797618e-06,
|
395 |
+
"loss": 0.9324,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18181818181818182,
|
400 |
+
"grad_norm": 0.96875,
|
401 |
+
"learning_rate": 4.757557257029563e-06,
|
402 |
+
"loss": 0.9439,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18518518518518517,
|
407 |
+
"grad_norm": 1.0078125,
|
408 |
+
"learning_rate": 4.745496100659083e-06,
|
409 |
+
"loss": 0.9925,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.18855218855218855,
|
414 |
+
"grad_norm": 0.8828125,
|
415 |
+
"learning_rate": 4.733158228002891e-06,
|
416 |
+
"loss": 0.9294,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.1919191919191919,
|
421 |
+
"grad_norm": 0.95703125,
|
422 |
+
"learning_rate": 4.720545159477921e-06,
|
423 |
+
"loss": 0.9502,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19528619528619529,
|
428 |
+
"grad_norm": 0.90234375,
|
429 |
+
"learning_rate": 4.707658449413961e-06,
|
430 |
+
"loss": 0.9538,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.19865319865319866,
|
435 |
+
"grad_norm": 1.03125,
|
436 |
+
"learning_rate": 4.694499685862106e-06,
|
437 |
+
"loss": 0.9484,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20202020202020202,
|
442 |
+
"grad_norm": 1.0390625,
|
443 |
+
"learning_rate": 4.681070490399064e-06,
|
444 |
+
"loss": 0.9515,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2053872053872054,
|
449 |
+
"grad_norm": 0.921875,
|
450 |
+
"learning_rate": 4.667372517927323e-06,
|
451 |
+
"loss": 0.956,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20875420875420875,
|
456 |
+
"grad_norm": 0.88671875,
|
457 |
+
"learning_rate": 4.653407456471222e-06,
|
458 |
+
"loss": 0.9478,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21212121212121213,
|
463 |
+
"grad_norm": 1.0390625,
|
464 |
+
"learning_rate": 4.639177026968924e-06,
|
465 |
+
"loss": 0.9427,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21548821548821548,
|
470 |
+
"grad_norm": 0.9296875,
|
471 |
+
"learning_rate": 4.624682983060346e-06,
|
472 |
+
"loss": 1.0028,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21885521885521886,
|
477 |
+
"grad_norm": 0.8828125,
|
478 |
+
"learning_rate": 4.609927110871053e-06,
|
479 |
+
"loss": 0.9442,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2222222222222222,
|
484 |
+
"grad_norm": 0.890625,
|
485 |
+
"learning_rate": 4.594911228792156e-06,
|
486 |
+
"loss": 0.9695,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2255892255892256,
|
491 |
+
"grad_norm": 0.94140625,
|
492 |
+
"learning_rate": 4.579637187256222e-06,
|
493 |
+
"loss": 0.9407,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.22895622895622897,
|
498 |
+
"grad_norm": 0.9609375,
|
499 |
+
"learning_rate": 4.564106868509246e-06,
|
500 |
+
"loss": 1.0014,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.23232323232323232,
|
505 |
+
"grad_norm": 0.9140625,
|
506 |
+
"learning_rate": 4.5483221863786965e-06,
|
507 |
+
"loss": 0.9249,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.2356902356902357,
|
512 |
+
"grad_norm": 0.83984375,
|
513 |
+
"learning_rate": 4.5322850860376744e-06,
|
514 |
+
"loss": 0.9623,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.23905723905723905,
|
519 |
+
"grad_norm": 0.9765625,
|
520 |
+
"learning_rate": 4.515997543765202e-06,
|
521 |
+
"loss": 0.9321,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24242424242424243,
|
526 |
+
"grad_norm": 0.94921875,
|
527 |
+
"learning_rate": 4.499461566702685e-06,
|
528 |
+
"loss": 0.9407,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24579124579124578,
|
533 |
+
"grad_norm": 0.86328125,
|
534 |
+
"learning_rate": 4.48267919260657e-06,
|
535 |
+
"loss": 0.9081,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24915824915824916,
|
540 |
+
"grad_norm": 0.87890625,
|
541 |
+
"learning_rate": 4.465652489597226e-06,
|
542 |
+
"loss": 0.9259,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25252525252525254,
|
547 |
+
"grad_norm": 0.984375,
|
548 |
+
"learning_rate": 4.4483835559040885e-06,
|
549 |
+
"loss": 0.9386,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.2558922558922559,
|
554 |
+
"grad_norm": 1.0546875,
|
555 |
+
"learning_rate": 4.430874519607089e-06,
|
556 |
+
"loss": 0.9884,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2558922558922559,
|
561 |
+
"eval_loss": 0.9393355846405029,
|
562 |
+
"eval_runtime": 8.6902,
|
563 |
+
"eval_samples_per_second": 57.536,
|
564 |
+
"eval_steps_per_second": 3.682,
|
565 |
+
"step": 76
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.25925925925925924,
|
569 |
+
"grad_norm": 0.9765625,
|
570 |
+
"learning_rate": 4.413127538374411e-06,
|
571 |
+
"loss": 0.9479,
|
572 |
+
"step": 77
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26262626262626265,
|
576 |
+
"grad_norm": 0.8671875,
|
577 |
+
"learning_rate": 4.395144799196593e-06,
|
578 |
+
"loss": 0.9165,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.265993265993266,
|
583 |
+
"grad_norm": 1.0390625,
|
584 |
+
"learning_rate": 4.376928518117028e-06,
|
585 |
+
"loss": 0.9428,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.26936026936026936,
|
590 |
+
"grad_norm": 1.0703125,
|
591 |
+
"learning_rate": 4.358480939958867e-06,
|
592 |
+
"loss": 0.9752,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.2727272727272727,
|
597 |
+
"grad_norm": 1.0078125,
|
598 |
+
"learning_rate": 4.339804338048397e-06,
|
599 |
+
"loss": 0.8951,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.2760942760942761,
|
604 |
+
"grad_norm": 0.87890625,
|
605 |
+
"learning_rate": 4.320901013934887e-06,
|
606 |
+
"loss": 0.9329,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.27946127946127947,
|
611 |
+
"grad_norm": 0.84765625,
|
612 |
+
"learning_rate": 4.301773297106968e-06,
|
613 |
+
"loss": 0.9086,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.2828282828282828,
|
618 |
+
"grad_norm": 0.84765625,
|
619 |
+
"learning_rate": 4.282423544705564e-06,
|
620 |
+
"loss": 0.9417,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.28619528619528617,
|
625 |
+
"grad_norm": 0.91015625,
|
626 |
+
"learning_rate": 4.262854141233419e-06,
|
627 |
+
"loss": 0.9344,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.2895622895622896,
|
632 |
+
"grad_norm": 0.921875,
|
633 |
+
"learning_rate": 4.243067498261251e-06,
|
634 |
+
"loss": 0.905,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.29292929292929293,
|
639 |
+
"grad_norm": 0.8671875,
|
640 |
+
"learning_rate": 4.223066054130568e-06,
|
641 |
+
"loss": 0.8943,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.2962962962962963,
|
646 |
+
"grad_norm": 0.91015625,
|
647 |
+
"learning_rate": 4.2028522736531895e-06,
|
648 |
+
"loss": 0.9407,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.2996632996632997,
|
653 |
+
"grad_norm": 0.95703125,
|
654 |
+
"learning_rate": 4.182428647807503e-06,
|
655 |
+
"loss": 0.957,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.30303030303030304,
|
660 |
+
"grad_norm": 1.03125,
|
661 |
+
"learning_rate": 4.161797693431493e-06,
|
662 |
+
"loss": 0.9128,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.3063973063973064,
|
667 |
+
"grad_norm": 0.8515625,
|
668 |
+
"learning_rate": 4.140961952912594e-06,
|
669 |
+
"loss": 0.9008,
|
670 |
+
"step": 91
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 0.30976430976430974,
|
674 |
+
"grad_norm": 1.09375,
|
675 |
+
"learning_rate": 4.11992399387438e-06,
|
676 |
+
"loss": 0.9073,
|
677 |
+
"step": 92
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.31313131313131315,
|
681 |
+
"grad_norm": 0.90625,
|
682 |
+
"learning_rate": 4.098686408860157e-06,
|
683 |
+
"loss": 1.0136,
|
684 |
+
"step": 93
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3164983164983165,
|
688 |
+
"grad_norm": 0.9140625,
|
689 |
+
"learning_rate": 4.077251815013477e-06,
|
690 |
+
"loss": 0.965,
|
691 |
+
"step": 94
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.31986531986531985,
|
695 |
+
"grad_norm": 0.9375,
|
696 |
+
"learning_rate": 4.055622853755627e-06,
|
697 |
+
"loss": 0.8822,
|
698 |
+
"step": 95
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32323232323232326,
|
702 |
+
"grad_norm": 0.859375,
|
703 |
+
"learning_rate": 4.033802190460114e-06,
|
704 |
+
"loss": 0.9241,
|
705 |
+
"step": 96
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.3265993265993266,
|
709 |
+
"grad_norm": 1.015625,
|
710 |
+
"learning_rate": 4.011792514124217e-06,
|
711 |
+
"loss": 0.9491,
|
712 |
+
"step": 97
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.32996632996632996,
|
716 |
+
"grad_norm": 0.890625,
|
717 |
+
"learning_rate": 3.989596537037608e-06,
|
718 |
+
"loss": 0.9461,
|
719 |
+
"step": 98
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.3333333333333333,
|
723 |
+
"grad_norm": 1.0,
|
724 |
+
"learning_rate": 3.967216994448116e-06,
|
725 |
+
"loss": 0.9298,
|
726 |
+
"step": 99
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.3367003367003367,
|
730 |
+
"grad_norm": 1.0078125,
|
731 |
+
"learning_rate": 3.9446566442246615e-06,
|
732 |
+
"loss": 0.9133,
|
733 |
+
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.3400673400673401,
|
737 |
+
"grad_norm": 0.9765625,
|
738 |
+
"learning_rate": 3.921918266517392e-06,
|
739 |
+
"loss": 0.9334,
|
740 |
+
"step": 101
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.3434343434343434,
|
744 |
+
"grad_norm": 0.79296875,
|
745 |
+
"learning_rate": 3.899004663415083e-06,
|
746 |
+
"loss": 0.9477,
|
747 |
+
"step": 102
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.3468013468013468,
|
751 |
+
"grad_norm": 0.87109375,
|
752 |
+
"learning_rate": 3.875918658599837e-06,
|
753 |
+
"loss": 0.9307,
|
754 |
+
"step": 103
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.3501683501683502,
|
758 |
+
"grad_norm": 1.0078125,
|
759 |
+
"learning_rate": 3.852663096999104e-06,
|
760 |
+
"loss": 0.8982,
|
761 |
+
"step": 104
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.35353535353535354,
|
765 |
+
"grad_norm": 0.99609375,
|
766 |
+
"learning_rate": 3.829240844435109e-06,
|
767 |
+
"loss": 0.9564,
|
768 |
+
"step": 105
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.3569023569023569,
|
772 |
+
"grad_norm": 0.890625,
|
773 |
+
"learning_rate": 3.8056547872716865e-06,
|
774 |
+
"loss": 0.916,
|
775 |
+
"step": 106
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.3602693602693603,
|
779 |
+
"grad_norm": 0.90234375,
|
780 |
+
"learning_rate": 3.7819078320585865e-06,
|
781 |
+
"loss": 0.9077,
|
782 |
+
"step": 107
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36363636363636365,
|
786 |
+
"grad_norm": 0.9296875,
|
787 |
+
"learning_rate": 3.7580029051732992e-06,
|
788 |
+
"loss": 0.9215,
|
789 |
+
"step": 108
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.367003367003367,
|
793 |
+
"grad_norm": 1.25,
|
794 |
+
"learning_rate": 3.733942952460432e-06,
|
795 |
+
"loss": 0.9287,
|
796 |
+
"step": 109
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.37037037037037035,
|
800 |
+
"grad_norm": 0.828125,
|
801 |
+
"learning_rate": 3.7097309388686865e-06,
|
802 |
+
"loss": 0.9261,
|
803 |
+
"step": 110
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.37373737373737376,
|
807 |
+
"grad_norm": 0.91796875,
|
808 |
+
"learning_rate": 3.6853698480854853e-06,
|
809 |
+
"loss": 0.8885,
|
810 |
+
"step": 111
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.3771043771043771,
|
814 |
+
"grad_norm": 0.90234375,
|
815 |
+
"learning_rate": 3.660862682169283e-06,
|
816 |
+
"loss": 0.905,
|
817 |
+
"step": 112
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.38047138047138046,
|
821 |
+
"grad_norm": 0.703125,
|
822 |
+
"learning_rate": 3.636212461179623e-06,
|
823 |
+
"loss": 0.8435,
|
824 |
+
"step": 113
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.3838383838383838,
|
828 |
+
"grad_norm": 0.7734375,
|
829 |
+
"learning_rate": 3.6114222228049657e-06,
|
830 |
+
"loss": 0.9277,
|
831 |
+
"step": 114
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.3838383838383838,
|
835 |
+
"eval_loss": 0.8986863493919373,
|
836 |
+
"eval_runtime": 8.7365,
|
837 |
+
"eval_samples_per_second": 57.231,
|
838 |
+
"eval_steps_per_second": 3.663,
|
839 |
+
"step": 114
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.3872053872053872,
|
843 |
+
"grad_norm": 0.8828125,
|
844 |
+
"learning_rate": 3.5864950219883514e-06,
|
845 |
+
"loss": 0.9274,
|
846 |
+
"step": 115
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.39057239057239057,
|
850 |
+
"grad_norm": 0.8125,
|
851 |
+
"learning_rate": 3.561433930550934e-06,
|
852 |
+
"loss": 0.8989,
|
853 |
+
"step": 116
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.3939393939393939,
|
857 |
+
"grad_norm": 0.81640625,
|
858 |
+
"learning_rate": 3.536242036813436e-06,
|
859 |
+
"loss": 0.9125,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.39730639730639733,
|
864 |
+
"grad_norm": 0.80859375,
|
865 |
+
"learning_rate": 3.510922445215568e-06,
|
866 |
+
"loss": 0.883,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.4006734006734007,
|
871 |
+
"grad_norm": 0.7578125,
|
872 |
+
"learning_rate": 3.4854782759334625e-06,
|
873 |
+
"loss": 0.8644,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.40404040404040403,
|
878 |
+
"grad_norm": 0.84765625,
|
879 |
+
"learning_rate": 3.4599126644951758e-06,
|
880 |
+
"loss": 0.907,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.4074074074074074,
|
885 |
+
"grad_norm": 0.796875,
|
886 |
+
"learning_rate": 3.4342287613942804e-06,
|
887 |
+
"loss": 0.889,
|
888 |
+
"step": 121
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.4107744107744108,
|
892 |
+
"grad_norm": 0.80859375,
|
893 |
+
"learning_rate": 3.4084297317016353e-06,
|
894 |
+
"loss": 0.896,
|
895 |
+
"step": 122
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.41414141414141414,
|
899 |
+
"grad_norm": 0.8359375,
|
900 |
+
"learning_rate": 3.3825187546753426e-06,
|
901 |
+
"loss": 0.8874,
|
902 |
+
"step": 123
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.4175084175084175,
|
906 |
+
"grad_norm": 0.7890625,
|
907 |
+
"learning_rate": 3.3564990233689632e-06,
|
908 |
+
"loss": 0.8811,
|
909 |
+
"step": 124
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.4208754208754209,
|
913 |
+
"grad_norm": 0.8203125,
|
914 |
+
"learning_rate": 3.330373744238033e-06,
|
915 |
+
"loss": 0.9437,
|
916 |
+
"step": 125
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.42424242424242425,
|
920 |
+
"grad_norm": 0.890625,
|
921 |
+
"learning_rate": 3.3041461367449256e-06,
|
922 |
+
"loss": 0.8829,
|
923 |
+
"step": 126
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.4276094276094276,
|
927 |
+
"grad_norm": 0.77734375,
|
928 |
+
"learning_rate": 3.2778194329621104e-06,
|
929 |
+
"loss": 0.8412,
|
930 |
+
"step": 127
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.43097643097643096,
|
934 |
+
"grad_norm": 0.83984375,
|
935 |
+
"learning_rate": 3.2513968771738606e-06,
|
936 |
+
"loss": 0.8916,
|
937 |
+
"step": 128
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.43434343434343436,
|
941 |
+
"grad_norm": 1.0078125,
|
942 |
+
"learning_rate": 3.224881725476456e-06,
|
943 |
+
"loss": 0.9644,
|
944 |
+
"step": 129
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.4377104377104377,
|
948 |
+
"grad_norm": 0.78125,
|
949 |
+
"learning_rate": 3.198277245376924e-06,
|
950 |
+
"loss": 0.8623,
|
951 |
+
"step": 130
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.44107744107744107,
|
955 |
+
"grad_norm": 0.71484375,
|
956 |
+
"learning_rate": 3.1715867153903844e-06,
|
957 |
+
"loss": 0.8786,
|
958 |
+
"step": 131
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.4444444444444444,
|
962 |
+
"grad_norm": 0.69140625,
|
963 |
+
"learning_rate": 3.144813424636031e-06,
|
964 |
+
"loss": 0.8786,
|
965 |
+
"step": 132
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4478114478114478,
|
969 |
+
"grad_norm": 0.91015625,
|
970 |
+
"learning_rate": 3.1179606724318052e-06,
|
971 |
+
"loss": 0.9163,
|
972 |
+
"step": 133
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.4511784511784512,
|
976 |
+
"grad_norm": 0.78515625,
|
977 |
+
"learning_rate": 3.091031767887817e-06,
|
978 |
+
"loss": 0.8656,
|
979 |
+
"step": 134
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.45454545454545453,
|
983 |
+
"grad_norm": 0.72265625,
|
984 |
+
"learning_rate": 3.0640300294985613e-06,
|
985 |
+
"loss": 0.8901,
|
986 |
+
"step": 135
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45791245791245794,
|
990 |
+
"grad_norm": 0.83203125,
|
991 |
+
"learning_rate": 3.036958784733967e-06,
|
992 |
+
"loss": 0.8706,
|
993 |
+
"step": 136
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.4612794612794613,
|
997 |
+
"grad_norm": 0.75390625,
|
998 |
+
"learning_rate": 3.0098213696293542e-06,
|
999 |
+
"loss": 0.8987,
|
1000 |
+
"step": 137
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.46464646464646464,
|
1004 |
+
"grad_norm": 0.77734375,
|
1005 |
+
"learning_rate": 2.982621128374325e-06,
|
1006 |
+
"loss": 0.8984,
|
1007 |
+
"step": 138
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.468013468013468,
|
1011 |
+
"grad_norm": 0.8828125,
|
1012 |
+
"learning_rate": 2.9553614129006543e-06,
|
1013 |
+
"loss": 0.8986,
|
1014 |
+
"step": 139
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.4713804713804714,
|
1018 |
+
"grad_norm": 0.78515625,
|
1019 |
+
"learning_rate": 2.9280455824692255e-06,
|
1020 |
+
"loss": 0.8514,
|
1021 |
+
"step": 140
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.47474747474747475,
|
1025 |
+
"grad_norm": 0.6875,
|
1026 |
+
"learning_rate": 2.9006770032560637e-06,
|
1027 |
+
"loss": 0.9182,
|
1028 |
+
"step": 141
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.4781144781144781,
|
1032 |
+
"grad_norm": 1.1171875,
|
1033 |
+
"learning_rate": 2.8732590479375167e-06,
|
1034 |
+
"loss": 0.8728,
|
1035 |
+
"step": 142
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.48148148148148145,
|
1039 |
+
"grad_norm": 0.68359375,
|
1040 |
+
"learning_rate": 2.8457950952746293e-06,
|
1041 |
+
"loss": 0.8692,
|
1042 |
+
"step": 143
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.48484848484848486,
|
1046 |
+
"grad_norm": 1.2734375,
|
1047 |
+
"learning_rate": 2.8182885296967833e-06,
|
1048 |
+
"loss": 0.907,
|
1049 |
+
"step": 144
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.4882154882154882,
|
1053 |
+
"grad_norm": 0.88671875,
|
1054 |
+
"learning_rate": 2.7907427408846156e-06,
|
1055 |
+
"loss": 0.8318,
|
1056 |
+
"step": 145
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.49158249158249157,
|
1060 |
+
"grad_norm": 1.0703125,
|
1061 |
+
"learning_rate": 2.763161123352314e-06,
|
1062 |
+
"loss": 0.8542,
|
1063 |
+
"step": 146
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.494949494949495,
|
1067 |
+
"grad_norm": 0.67578125,
|
1068 |
+
"learning_rate": 2.735547076029296e-06,
|
1069 |
+
"loss": 0.8602,
|
1070 |
+
"step": 147
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.4983164983164983,
|
1074 |
+
"grad_norm": 1.0625,
|
1075 |
+
"learning_rate": 2.7079040018413586e-06,
|
1076 |
+
"loss": 0.8775,
|
1077 |
+
"step": 148
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.5016835016835017,
|
1081 |
+
"grad_norm": 0.96484375,
|
1082 |
+
"learning_rate": 2.6802353072913307e-06,
|
1083 |
+
"loss": 0.8884,
|
1084 |
+
"step": 149
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.5050505050505051,
|
1088 |
+
"grad_norm": 0.87890625,
|
1089 |
+
"learning_rate": 2.6525444020392794e-06,
|
1090 |
+
"loss": 0.8886,
|
1091 |
+
"step": 150
|
1092 |
+
}
|
1093 |
+
],
|
1094 |
+
"logging_steps": 1,
|
1095 |
+
"max_steps": 297,
|
1096 |
+
"num_input_tokens_seen": 0,
|
1097 |
+
"num_train_epochs": 1,
|
1098 |
+
"save_steps": 75,
|
1099 |
+
"stateful_callbacks": {
|
1100 |
+
"TrainerControl": {
|
1101 |
+
"args": {
|
1102 |
+
"should_epoch_stop": false,
|
1103 |
+
"should_evaluate": false,
|
1104 |
+
"should_log": false,
|
1105 |
+
"should_save": true,
|
1106 |
+
"should_training_stop": false
|
1107 |
+
},
|
1108 |
+
"attributes": {}
|
1109 |
+
}
|
1110 |
+
},
|
1111 |
+
"total_flos": 2.72875344887808e+17,
|
1112 |
+
"train_batch_size": 2,
|
1113 |
+
"trial_name": null,
|
1114 |
+
"trial_params": null
|
1115 |
+
}
|
checkpoint-150/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a1df7b55ff5253e81f69c778f8783e7f85fc6f67c87a798dabc06dc57ceb407
|
3 |
+
size 6328
|