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 |
+
"gate_up_proj",
|
27 |
+
"down_proj",
|
28 |
+
"o_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:dc608678a741705f8a4798f2cd9a3b82a72922a390c56ed62e3e560bc6fa3ab9
|
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 sha256:1c415aee541b544dd71a3fe66b371e9c9645d24b25f51be490afd9a0ee33551e
|
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 sha256:498aead13f6936fcdaeb826318751f2ed8774110c2f074b8c2e81673156ef38f
|
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": 2.2727272727272729e-07,
|
15 |
+
"loss": 1.0833,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.003367003367003367,
|
20 |
+
"eval_loss": 1.032954454421997,
|
21 |
+
"eval_runtime": 8.7985,
|
22 |
+
"eval_samples_per_second": 56.828,
|
23 |
+
"eval_steps_per_second": 3.637,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006734006734006734,
|
28 |
+
"grad_norm": 2.265625,
|
29 |
+
"learning_rate": 4.5454545454545457e-07,
|
30 |
+
"loss": 0.996,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.010101010101010102,
|
35 |
+
"grad_norm": 1.640625,
|
36 |
+
"learning_rate": 6.818181818181818e-07,
|
37 |
+
"loss": 1.0489,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013468013468013467,
|
42 |
+
"grad_norm": 2.0625,
|
43 |
+
"learning_rate": 9.090909090909091e-07,
|
44 |
+
"loss": 1.0546,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.016835016835016835,
|
49 |
+
"grad_norm": 2.453125,
|
50 |
+
"learning_rate": 1.1363636363636364e-06,
|
51 |
+
"loss": 1.0341,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.020202020202020204,
|
56 |
+
"grad_norm": 1.9921875,
|
57 |
+
"learning_rate": 1.3636363636363636e-06,
|
58 |
+
"loss": 1.0136,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.02356902356902357,
|
63 |
+
"grad_norm": 2.640625,
|
64 |
+
"learning_rate": 1.590909090909091e-06,
|
65 |
+
"loss": 1.0305,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.026936026936026935,
|
70 |
+
"grad_norm": 2.359375,
|
71 |
+
"learning_rate": 1.8181818181818183e-06,
|
72 |
+
"loss": 1.0226,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.030303030303030304,
|
77 |
+
"grad_norm": 2.3125,
|
78 |
+
"learning_rate": 2.0454545454545457e-06,
|
79 |
+
"loss": 1.0745,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03367003367003367,
|
84 |
+
"grad_norm": 2.359375,
|
85 |
+
"learning_rate": 2.2727272727272728e-06,
|
86 |
+
"loss": 1.0232,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.037037037037037035,
|
91 |
+
"grad_norm": 2.53125,
|
92 |
+
"learning_rate": 2.5e-06,
|
93 |
+
"loss": 1.0106,
|
94 |
+
"step": 11
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.04040404040404041,
|
98 |
+
"grad_norm": 2.125,
|
99 |
+
"learning_rate": 2.7272727272727272e-06,
|
100 |
+
"loss": 1.0541,
|
101 |
+
"step": 12
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.04377104377104377,
|
105 |
+
"grad_norm": 2.15625,
|
106 |
+
"learning_rate": 2.954545454545455e-06,
|
107 |
+
"loss": 1.0693,
|
108 |
+
"step": 13
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04713804713804714,
|
112 |
+
"grad_norm": 1.8359375,
|
113 |
+
"learning_rate": 3.181818181818182e-06,
|
114 |
+
"loss": 1.0338,
|
115 |
+
"step": 14
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.050505050505050504,
|
119 |
+
"grad_norm": 2.0,
|
120 |
+
"learning_rate": 3.409090909090909e-06,
|
121 |
+
"loss": 1.0464,
|
122 |
+
"step": 15
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.05387205387205387,
|
126 |
+
"grad_norm": 2.34375,
|
127 |
+
"learning_rate": 3.6363636363636366e-06,
|
128 |
+
"loss": 1.0684,
|
129 |
+
"step": 16
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05723905723905724,
|
133 |
+
"grad_norm": 1.8125,
|
134 |
+
"learning_rate": 3.863636363636364e-06,
|
135 |
+
"loss": 1.0117,
|
136 |
+
"step": 17
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.06060606060606061,
|
140 |
+
"grad_norm": 1.90625,
|
141 |
+
"learning_rate": 4.0909090909090915e-06,
|
142 |
+
"loss": 1.0138,
|
143 |
+
"step": 18
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.06397306397306397,
|
147 |
+
"grad_norm": 1.59375,
|
148 |
+
"learning_rate": 4.3181818181818185e-06,
|
149 |
+
"loss": 0.9873,
|
150 |
+
"step": 19
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.06734006734006734,
|
154 |
+
"grad_norm": 1.59375,
|
155 |
+
"learning_rate": 4.5454545454545455e-06,
|
156 |
+
"loss": 1.0524,
|
157 |
+
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.0707070707070707,
|
161 |
+
"grad_norm": 1.3984375,
|
162 |
+
"learning_rate": 4.772727272727273e-06,
|
163 |
+
"loss": 1.0479,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07407407407407407,
|
168 |
+
"grad_norm": 1.609375,
|
169 |
+
"learning_rate": 5e-06,
|
170 |
+
"loss": 0.9894,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07744107744107744,
|
175 |
+
"grad_norm": 1.3671875,
|
176 |
+
"learning_rate": 5.2272727272727274e-06,
|
177 |
+
"loss": 0.983,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.08080808080808081,
|
182 |
+
"grad_norm": 1.6328125,
|
183 |
+
"learning_rate": 5.4545454545454545e-06,
|
184 |
+
"loss": 1.0563,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.08417508417508418,
|
189 |
+
"grad_norm": 1.34375,
|
190 |
+
"learning_rate": 5.681818181818183e-06,
|
191 |
+
"loss": 0.9966,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.08754208754208755,
|
196 |
+
"grad_norm": 1.25,
|
197 |
+
"learning_rate": 5.90909090909091e-06,
|
198 |
+
"loss": 0.9922,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.09090909090909091,
|
203 |
+
"grad_norm": 1.3984375,
|
204 |
+
"learning_rate": 6.136363636363637e-06,
|
205 |
+
"loss": 1.0677,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09427609427609428,
|
210 |
+
"grad_norm": 1.3828125,
|
211 |
+
"learning_rate": 6.363636363636364e-06,
|
212 |
+
"loss": 1.0325,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09764309764309764,
|
217 |
+
"grad_norm": 1.1953125,
|
218 |
+
"learning_rate": 6.590909090909091e-06,
|
219 |
+
"loss": 1.0159,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.10101010101010101,
|
224 |
+
"grad_norm": 1.3125,
|
225 |
+
"learning_rate": 6.818181818181818e-06,
|
226 |
+
"loss": 1.0384,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.10437710437710437,
|
231 |
+
"grad_norm": 1.1171875,
|
232 |
+
"learning_rate": 7.045454545454546e-06,
|
233 |
+
"loss": 0.9949,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.10774410774410774,
|
238 |
+
"grad_norm": 1.2421875,
|
239 |
+
"learning_rate": 7.272727272727273e-06,
|
240 |
+
"loss": 1.0284,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1111111111111111,
|
245 |
+
"grad_norm": 1.15625,
|
246 |
+
"learning_rate": 7.500000000000001e-06,
|
247 |
+
"loss": 1.0245,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11447811447811448,
|
252 |
+
"grad_norm": 1.1875,
|
253 |
+
"learning_rate": 7.727272727272727e-06,
|
254 |
+
"loss": 1.0103,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11784511784511785,
|
259 |
+
"grad_norm": 1.125,
|
260 |
+
"learning_rate": 7.954545454545455e-06,
|
261 |
+
"loss": 1.0129,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12121212121212122,
|
266 |
+
"grad_norm": 1.03125,
|
267 |
+
"learning_rate": 8.181818181818183e-06,
|
268 |
+
"loss": 0.965,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12457912457912458,
|
273 |
+
"grad_norm": 1.109375,
|
274 |
+
"learning_rate": 8.40909090909091e-06,
|
275 |
+
"loss": 1.0027,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12794612794612795,
|
280 |
+
"grad_norm": 1.0859375,
|
281 |
+
"learning_rate": 8.636363636363637e-06,
|
282 |
+
"loss": 1.0093,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.12794612794612795,
|
287 |
+
"eval_loss": 0.9909602999687195,
|
288 |
+
"eval_runtime": 8.9064,
|
289 |
+
"eval_samples_per_second": 56.139,
|
290 |
+
"eval_steps_per_second": 3.593,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.13131313131313133,
|
295 |
+
"grad_norm": 0.96484375,
|
296 |
+
"learning_rate": 8.863636363636365e-06,
|
297 |
+
"loss": 0.98,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.13468013468013468,
|
302 |
+
"grad_norm": 1.0078125,
|
303 |
+
"learning_rate": 9.090909090909091e-06,
|
304 |
+
"loss": 1.0,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.13804713804713806,
|
309 |
+
"grad_norm": 1.109375,
|
310 |
+
"learning_rate": 9.318181818181819e-06,
|
311 |
+
"loss": 0.9658,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.1414141414141414,
|
316 |
+
"grad_norm": 0.95703125,
|
317 |
+
"learning_rate": 9.545454545454547e-06,
|
318 |
+
"loss": 0.9656,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.1447811447811448,
|
323 |
+
"grad_norm": 1.0,
|
324 |
+
"learning_rate": 9.772727272727273e-06,
|
325 |
+
"loss": 0.9528,
|
326 |
+
"step": 43
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.14814814814814814,
|
330 |
+
"grad_norm": 0.88671875,
|
331 |
+
"learning_rate": 1e-05,
|
332 |
+
"loss": 0.9546,
|
333 |
+
"step": 44
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.15151515151515152,
|
337 |
+
"grad_norm": 0.984375,
|
338 |
+
"learning_rate": 9.999965606811854e-06,
|
339 |
+
"loss": 0.9406,
|
340 |
+
"step": 45
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15488215488215487,
|
344 |
+
"grad_norm": 1.0625,
|
345 |
+
"learning_rate": 9.99986242772057e-06,
|
346 |
+
"loss": 0.9975,
|
347 |
+
"step": 46
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15824915824915825,
|
351 |
+
"grad_norm": 0.94140625,
|
352 |
+
"learning_rate": 9.99969046414561e-06,
|
353 |
+
"loss": 0.9567,
|
354 |
+
"step": 47
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16161616161616163,
|
358 |
+
"grad_norm": 0.96484375,
|
359 |
+
"learning_rate": 9.999449718452724e-06,
|
360 |
+
"loss": 0.9707,
|
361 |
+
"step": 48
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16498316498316498,
|
365 |
+
"grad_norm": 1.0,
|
366 |
+
"learning_rate": 9.999140193953923e-06,
|
367 |
+
"loss": 0.9559,
|
368 |
+
"step": 49
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.16835016835016836,
|
372 |
+
"grad_norm": 0.99609375,
|
373 |
+
"learning_rate": 9.998761894907414e-06,
|
374 |
+
"loss": 0.9398,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.1717171717171717,
|
379 |
+
"grad_norm": 0.83203125,
|
380 |
+
"learning_rate": 9.998314826517564e-06,
|
381 |
+
"loss": 0.9329,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.1750841750841751,
|
386 |
+
"grad_norm": 0.91015625,
|
387 |
+
"learning_rate": 9.997798994934812e-06,
|
388 |
+
"loss": 0.9478,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.17845117845117844,
|
393 |
+
"grad_norm": 0.94140625,
|
394 |
+
"learning_rate": 9.997214407255602e-06,
|
395 |
+
"loss": 0.9062,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.18181818181818182,
|
400 |
+
"grad_norm": 0.83203125,
|
401 |
+
"learning_rate": 9.996561071522264e-06,
|
402 |
+
"loss": 0.9089,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.18518518518518517,
|
407 |
+
"grad_norm": 1.0078125,
|
408 |
+
"learning_rate": 9.995838996722916e-06,
|
409 |
+
"loss": 0.9561,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.18855218855218855,
|
414 |
+
"grad_norm": 0.796875,
|
415 |
+
"learning_rate": 9.995048192791341e-06,
|
416 |
+
"loss": 0.8948,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.1919191919191919,
|
421 |
+
"grad_norm": 0.91796875,
|
422 |
+
"learning_rate": 9.994188670606845e-06,
|
423 |
+
"loss": 0.9095,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.19528619528619529,
|
428 |
+
"grad_norm": 0.8515625,
|
429 |
+
"learning_rate": 9.993260441994116e-06,
|
430 |
+
"loss": 0.9137,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.19865319865319866,
|
435 |
+
"grad_norm": 0.8671875,
|
436 |
+
"learning_rate": 9.992263519723046e-06,
|
437 |
+
"loss": 0.9012,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.20202020202020202,
|
442 |
+
"grad_norm": 0.8046875,
|
443 |
+
"learning_rate": 9.99119791750857e-06,
|
444 |
+
"loss": 0.9074,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.2053872053872054,
|
449 |
+
"grad_norm": 1.0859375,
|
450 |
+
"learning_rate": 9.990063650010473e-06,
|
451 |
+
"loss": 0.9106,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.20875420875420875,
|
456 |
+
"grad_norm": 1.0625,
|
457 |
+
"learning_rate": 9.988860732833183e-06,
|
458 |
+
"loss": 0.9012,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.21212121212121213,
|
463 |
+
"grad_norm": 0.93359375,
|
464 |
+
"learning_rate": 9.987589182525562e-06,
|
465 |
+
"loss": 0.8928,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.21548821548821548,
|
470 |
+
"grad_norm": 0.921875,
|
471 |
+
"learning_rate": 9.98624901658068e-06,
|
472 |
+
"loss": 0.9487,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.21885521885521886,
|
477 |
+
"grad_norm": 0.92578125,
|
478 |
+
"learning_rate": 9.984840253435569e-06,
|
479 |
+
"loss": 0.8887,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.2222222222222222,
|
484 |
+
"grad_norm": 0.8671875,
|
485 |
+
"learning_rate": 9.983362912470967e-06,
|
486 |
+
"loss": 0.9152,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.2255892255892256,
|
491 |
+
"grad_norm": 0.83984375,
|
492 |
+
"learning_rate": 9.981817014011066e-06,
|
493 |
+
"loss": 0.8849,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.22895622895622897,
|
498 |
+
"grad_norm": 0.94921875,
|
499 |
+
"learning_rate": 9.980202579323212e-06,
|
500 |
+
"loss": 0.9386,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.23232323232323232,
|
505 |
+
"grad_norm": 0.8203125,
|
506 |
+
"learning_rate": 9.978519630617632e-06,
|
507 |
+
"loss": 0.8651,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.2356902356902357,
|
512 |
+
"grad_norm": 0.7109375,
|
513 |
+
"learning_rate": 9.976768191047109e-06,
|
514 |
+
"loss": 0.9044,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.23905723905723905,
|
519 |
+
"grad_norm": 1.03125,
|
520 |
+
"learning_rate": 9.974948284706684e-06,
|
521 |
+
"loss": 0.8702,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.24242424242424243,
|
526 |
+
"grad_norm": 0.91796875,
|
527 |
+
"learning_rate": 9.973059936633308e-06,
|
528 |
+
"loss": 0.8748,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.24579124579124578,
|
533 |
+
"grad_norm": 0.66796875,
|
534 |
+
"learning_rate": 9.971103172805504e-06,
|
535 |
+
"loss": 0.8443,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.24915824915824916,
|
540 |
+
"grad_norm": 0.671875,
|
541 |
+
"learning_rate": 9.969078020143013e-06,
|
542 |
+
"loss": 0.8605,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.25252525252525254,
|
547 |
+
"grad_norm": 0.6796875,
|
548 |
+
"learning_rate": 9.966984506506415e-06,
|
549 |
+
"loss": 0.8661,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.2558922558922559,
|
554 |
+
"grad_norm": 0.953125,
|
555 |
+
"learning_rate": 9.964822660696753e-06,
|
556 |
+
"loss": 0.9169,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.2558922558922559,
|
561 |
+
"eval_loss": 0.8667835593223572,
|
562 |
+
"eval_runtime": 8.6819,
|
563 |
+
"eval_samples_per_second": 57.591,
|
564 |
+
"eval_steps_per_second": 3.686,
|
565 |
+
"step": 76
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.25925925925925924,
|
569 |
+
"grad_norm": 0.86328125,
|
570 |
+
"learning_rate": 9.96259251245514e-06,
|
571 |
+
"loss": 0.8719,
|
572 |
+
"step": 77
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26262626262626265,
|
576 |
+
"grad_norm": 0.66796875,
|
577 |
+
"learning_rate": 9.960294092462332e-06,
|
578 |
+
"loss": 0.8438,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.265993265993266,
|
583 |
+
"grad_norm": 0.66796875,
|
584 |
+
"learning_rate": 9.957927432338332e-06,
|
585 |
+
"loss": 0.8723,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.26936026936026936,
|
590 |
+
"grad_norm": 1.3828125,
|
591 |
+
"learning_rate": 9.95549256464193e-06,
|
592 |
+
"loss": 0.8987,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.2727272727272727,
|
597 |
+
"grad_norm": 0.69921875,
|
598 |
+
"learning_rate": 9.952989522870275e-06,
|
599 |
+
"loss": 0.8188,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.2760942760942761,
|
604 |
+
"grad_norm": 0.9375,
|
605 |
+
"learning_rate": 9.950418341458398e-06,
|
606 |
+
"loss": 0.8521,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.27946127946127947,
|
611 |
+
"grad_norm": 0.828125,
|
612 |
+
"learning_rate": 9.947779055778752e-06,
|
613 |
+
"loss": 0.8305,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.2828282828282828,
|
618 |
+
"grad_norm": 0.9453125,
|
619 |
+
"learning_rate": 9.945071702140716e-06,
|
620 |
+
"loss": 0.856,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.28619528619528617,
|
625 |
+
"grad_norm": 0.609375,
|
626 |
+
"learning_rate": 9.9422963177901e-06,
|
627 |
+
"loss": 0.8512,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.2895622895622896,
|
632 |
+
"grad_norm": 1.546875,
|
633 |
+
"learning_rate": 9.939452940908627e-06,
|
634 |
+
"loss": 0.818,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.29292929292929293,
|
639 |
+
"grad_norm": 0.640625,
|
640 |
+
"learning_rate": 9.936541610613417e-06,
|
641 |
+
"loss": 0.8071,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.2962962962962963,
|
646 |
+
"grad_norm": 0.82421875,
|
647 |
+
"learning_rate": 9.933562366956445e-06,
|
648 |
+
"loss": 0.8559,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.2996632996632997,
|
653 |
+
"grad_norm": 1.046875,
|
654 |
+
"learning_rate": 9.930515250923985e-06,
|
655 |
+
"loss": 0.8646,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.30303030303030304,
|
660 |
+
"grad_norm": 0.76953125,
|
661 |
+
"learning_rate": 9.927400304436048e-06,
|
662 |
+
"loss": 0.8179,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.3063973063973064,
|
667 |
+
"grad_norm": 1.09375,
|
668 |
+
"learning_rate": 9.924217570345814e-06,
|
669 |
+
"loss": 0.8093,
|
670 |
+
"step": 91
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 0.30976430976430974,
|
674 |
+
"grad_norm": 0.6015625,
|
675 |
+
"learning_rate": 9.920967092439028e-06,
|
676 |
+
"loss": 0.8073,
|
677 |
+
"step": 92
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.31313131313131315,
|
681 |
+
"grad_norm": 0.84375,
|
682 |
+
"learning_rate": 9.917648915433413e-06,
|
683 |
+
"loss": 0.9031,
|
684 |
+
"step": 93
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.3164983164983165,
|
688 |
+
"grad_norm": 0.76171875,
|
689 |
+
"learning_rate": 9.914263084978041e-06,
|
690 |
+
"loss": 0.8568,
|
691 |
+
"step": 94
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.31986531986531985,
|
695 |
+
"grad_norm": 0.8671875,
|
696 |
+
"learning_rate": 9.910809647652716e-06,
|
697 |
+
"loss": 0.7819,
|
698 |
+
"step": 95
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32323232323232326,
|
702 |
+
"grad_norm": 0.84765625,
|
703 |
+
"learning_rate": 9.907288650967324e-06,
|
704 |
+
"loss": 0.8236,
|
705 |
+
"step": 96
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.3265993265993266,
|
709 |
+
"grad_norm": 0.70703125,
|
710 |
+
"learning_rate": 9.903700143361185e-06,
|
711 |
+
"loss": 0.8418,
|
712 |
+
"step": 97
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.32996632996632996,
|
716 |
+
"grad_norm": 0.94921875,
|
717 |
+
"learning_rate": 9.900044174202389e-06,
|
718 |
+
"loss": 0.8313,
|
719 |
+
"step": 98
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.3333333333333333,
|
723 |
+
"grad_norm": 0.8125,
|
724 |
+
"learning_rate": 9.896320793787106e-06,
|
725 |
+
"loss": 0.8158,
|
726 |
+
"step": 99
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.3367003367003367,
|
730 |
+
"grad_norm": 0.76171875,
|
731 |
+
"learning_rate": 9.892530053338909e-06,
|
732 |
+
"loss": 0.7956,
|
733 |
+
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.3400673400673401,
|
737 |
+
"grad_norm": 0.94921875,
|
738 |
+
"learning_rate": 9.888672005008054e-06,
|
739 |
+
"loss": 0.8154,
|
740 |
+
"step": 101
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.3434343434343434,
|
744 |
+
"grad_norm": 0.6328125,
|
745 |
+
"learning_rate": 9.884746701870778e-06,
|
746 |
+
"loss": 0.8322,
|
747 |
+
"step": 102
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.3468013468013468,
|
751 |
+
"grad_norm": 0.62890625,
|
752 |
+
"learning_rate": 9.880754197928553e-06,
|
753 |
+
"loss": 0.8133,
|
754 |
+
"step": 103
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.3501683501683502,
|
758 |
+
"grad_norm": 0.76953125,
|
759 |
+
"learning_rate": 9.876694548107358e-06,
|
760 |
+
"loss": 0.7882,
|
761 |
+
"step": 104
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.35353535353535354,
|
765 |
+
"grad_norm": 1.03125,
|
766 |
+
"learning_rate": 9.87256780825691e-06,
|
767 |
+
"loss": 0.8264,
|
768 |
+
"step": 105
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.3569023569023569,
|
772 |
+
"grad_norm": 0.7421875,
|
773 |
+
"learning_rate": 9.868374035149906e-06,
|
774 |
+
"loss": 0.7894,
|
775 |
+
"step": 106
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.3602693602693603,
|
779 |
+
"grad_norm": 0.6171875,
|
780 |
+
"learning_rate": 9.864113286481237e-06,
|
781 |
+
"loss": 0.7807,
|
782 |
+
"step": 107
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36363636363636365,
|
786 |
+
"grad_norm": 1.015625,
|
787 |
+
"learning_rate": 9.859785620867197e-06,
|
788 |
+
"loss": 0.7895,
|
789 |
+
"step": 108
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.367003367003367,
|
793 |
+
"grad_norm": 1.0625,
|
794 |
+
"learning_rate": 9.855391097844671e-06,
|
795 |
+
"loss": 0.7936,
|
796 |
+
"step": 109
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.37037037037037035,
|
800 |
+
"grad_norm": 0.8984375,
|
801 |
+
"learning_rate": 9.850929777870324e-06,
|
802 |
+
"loss": 0.8024,
|
803 |
+
"step": 110
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.37373737373737376,
|
807 |
+
"grad_norm": 0.6640625,
|
808 |
+
"learning_rate": 9.846401722319759e-06,
|
809 |
+
"loss": 0.7542,
|
810 |
+
"step": 111
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.3771043771043771,
|
814 |
+
"grad_norm": 1.1640625,
|
815 |
+
"learning_rate": 9.841806993486686e-06,
|
816 |
+
"loss": 0.7689,
|
817 |
+
"step": 112
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.38047138047138046,
|
821 |
+
"grad_norm": 0.765625,
|
822 |
+
"learning_rate": 9.837145654582055e-06,
|
823 |
+
"loss": 0.7133,
|
824 |
+
"step": 113
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.3838383838383838,
|
828 |
+
"grad_norm": 0.87109375,
|
829 |
+
"learning_rate": 9.832417769733185e-06,
|
830 |
+
"loss": 0.795,
|
831 |
+
"step": 114
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.3838383838383838,
|
835 |
+
"eval_loss": 0.7676474452018738,
|
836 |
+
"eval_runtime": 8.7789,
|
837 |
+
"eval_samples_per_second": 56.955,
|
838 |
+
"eval_steps_per_second": 3.645,
|
839 |
+
"step": 114
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.3872053872053872,
|
843 |
+
"grad_norm": 0.86328125,
|
844 |
+
"learning_rate": 9.827623403982893e-06,
|
845 |
+
"loss": 0.7992,
|
846 |
+
"step": 115
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.39057239057239057,
|
850 |
+
"grad_norm": 0.7421875,
|
851 |
+
"learning_rate": 9.822762623288584e-06,
|
852 |
+
"loss": 0.7678,
|
853 |
+
"step": 116
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.3939393939393939,
|
857 |
+
"grad_norm": 0.85546875,
|
858 |
+
"learning_rate": 9.81783549452136e-06,
|
859 |
+
"loss": 0.7861,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.39730639730639733,
|
864 |
+
"grad_norm": 0.71484375,
|
865 |
+
"learning_rate": 9.812842085465086e-06,
|
866 |
+
"loss": 0.7447,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.4006734006734007,
|
871 |
+
"grad_norm": 0.5703125,
|
872 |
+
"learning_rate": 9.807782464815463e-06,
|
873 |
+
"loss": 0.7218,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.40404040404040403,
|
878 |
+
"grad_norm": 0.6171875,
|
879 |
+
"learning_rate": 9.802656702179088e-06,
|
880 |
+
"loss": 0.7637,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.4074074074074074,
|
885 |
+
"grad_norm": 0.54296875,
|
886 |
+
"learning_rate": 9.797464868072489e-06,
|
887 |
+
"loss": 0.7588,
|
888 |
+
"step": 121
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.4107744107744108,
|
892 |
+
"grad_norm": 0.6171875,
|
893 |
+
"learning_rate": 9.792207033921152e-06,
|
894 |
+
"loss": 0.7539,
|
895 |
+
"step": 122
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.41414141414141414,
|
899 |
+
"grad_norm": 0.8046875,
|
900 |
+
"learning_rate": 9.786883272058554e-06,
|
901 |
+
"loss": 0.7524,
|
902 |
+
"step": 123
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.4175084175084175,
|
906 |
+
"grad_norm": 0.6953125,
|
907 |
+
"learning_rate": 9.781493655725149e-06,
|
908 |
+
"loss": 0.731,
|
909 |
+
"step": 124
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.4208754208754209,
|
913 |
+
"grad_norm": 0.64453125,
|
914 |
+
"learning_rate": 9.776038259067375e-06,
|
915 |
+
"loss": 0.8022,
|
916 |
+
"step": 125
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.42424242424242425,
|
920 |
+
"grad_norm": 0.48046875,
|
921 |
+
"learning_rate": 9.770517157136625e-06,
|
922 |
+
"loss": 0.7528,
|
923 |
+
"step": 126
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.4276094276094276,
|
927 |
+
"grad_norm": 0.5546875,
|
928 |
+
"learning_rate": 9.764930425888216e-06,
|
929 |
+
"loss": 0.7037,
|
930 |
+
"step": 127
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.43097643097643096,
|
934 |
+
"grad_norm": 0.546875,
|
935 |
+
"learning_rate": 9.759278142180348e-06,
|
936 |
+
"loss": 0.7519,
|
937 |
+
"step": 128
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.43434343434343436,
|
941 |
+
"grad_norm": 0.61328125,
|
942 |
+
"learning_rate": 9.753560383773046e-06,
|
943 |
+
"loss": 0.8163,
|
944 |
+
"step": 129
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.4377104377104377,
|
948 |
+
"grad_norm": 0.53125,
|
949 |
+
"learning_rate": 9.747777229327085e-06,
|
950 |
+
"loss": 0.7292,
|
951 |
+
"step": 130
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.44107744107744107,
|
955 |
+
"grad_norm": 0.58203125,
|
956 |
+
"learning_rate": 9.741928758402912e-06,
|
957 |
+
"loss": 0.7351,
|
958 |
+
"step": 131
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.4444444444444444,
|
962 |
+
"grad_norm": 0.5234375,
|
963 |
+
"learning_rate": 9.736015051459551e-06,
|
964 |
+
"loss": 0.7429,
|
965 |
+
"step": 132
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.4478114478114478,
|
969 |
+
"grad_norm": 0.65234375,
|
970 |
+
"learning_rate": 9.730036189853497e-06,
|
971 |
+
"loss": 0.7616,
|
972 |
+
"step": 133
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 0.4511784511784512,
|
976 |
+
"grad_norm": 0.53125,
|
977 |
+
"learning_rate": 9.723992255837596e-06,
|
978 |
+
"loss": 0.7263,
|
979 |
+
"step": 134
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 0.45454545454545453,
|
983 |
+
"grad_norm": 0.5546875,
|
984 |
+
"learning_rate": 9.717883332559911e-06,
|
985 |
+
"loss": 0.7427,
|
986 |
+
"step": 135
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45791245791245794,
|
990 |
+
"grad_norm": 0.66796875,
|
991 |
+
"learning_rate": 9.71170950406258e-06,
|
992 |
+
"loss": 0.7261,
|
993 |
+
"step": 136
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.4612794612794613,
|
997 |
+
"grad_norm": 0.58984375,
|
998 |
+
"learning_rate": 9.705470855280661e-06,
|
999 |
+
"loss": 0.754,
|
1000 |
+
"step": 137
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.46464646464646464,
|
1004 |
+
"grad_norm": 0.6015625,
|
1005 |
+
"learning_rate": 9.699167472040965e-06,
|
1006 |
+
"loss": 0.7554,
|
1007 |
+
"step": 138
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 0.468013468013468,
|
1011 |
+
"grad_norm": 0.5546875,
|
1012 |
+
"learning_rate": 9.692799441060868e-06,
|
1013 |
+
"loss": 0.7488,
|
1014 |
+
"step": 139
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 0.4713804713804714,
|
1018 |
+
"grad_norm": 0.53125,
|
1019 |
+
"learning_rate": 9.686366849947126e-06,
|
1020 |
+
"loss": 0.7066,
|
1021 |
+
"step": 140
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 0.47474747474747475,
|
1025 |
+
"grad_norm": 0.55078125,
|
1026 |
+
"learning_rate": 9.679869787194664e-06,
|
1027 |
+
"loss": 0.7818,
|
1028 |
+
"step": 141
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.4781144781144781,
|
1032 |
+
"grad_norm": 0.4765625,
|
1033 |
+
"learning_rate": 9.673308342185366e-06,
|
1034 |
+
"loss": 0.7289,
|
1035 |
+
"step": 142
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.48148148148148145,
|
1039 |
+
"grad_norm": 0.62109375,
|
1040 |
+
"learning_rate": 9.666682605186834e-06,
|
1041 |
+
"loss": 0.7301,
|
1042 |
+
"step": 143
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.48484848484848486,
|
1046 |
+
"grad_norm": 0.54296875,
|
1047 |
+
"learning_rate": 9.659992667351157e-06,
|
1048 |
+
"loss": 0.7673,
|
1049 |
+
"step": 144
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.4882154882154882,
|
1053 |
+
"grad_norm": 0.486328125,
|
1054 |
+
"learning_rate": 9.653238620713652e-06,
|
1055 |
+
"loss": 0.6884,
|
1056 |
+
"step": 145
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.49158249158249157,
|
1060 |
+
"grad_norm": 0.6484375,
|
1061 |
+
"learning_rate": 9.646420558191596e-06,
|
1062 |
+
"loss": 0.7043,
|
1063 |
+
"step": 146
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 0.494949494949495,
|
1067 |
+
"grad_norm": 0.51171875,
|
1068 |
+
"learning_rate": 9.639538573582952e-06,
|
1069 |
+
"loss": 0.7122,
|
1070 |
+
"step": 147
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.4983164983164983,
|
1074 |
+
"grad_norm": 0.498046875,
|
1075 |
+
"learning_rate": 9.632592761565078e-06,
|
1076 |
+
"loss": 0.7232,
|
1077 |
+
"step": 148
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.5016835016835017,
|
1081 |
+
"grad_norm": 0.5625,
|
1082 |
+
"learning_rate": 9.625583217693419e-06,
|
1083 |
+
"loss": 0.7311,
|
1084 |
+
"step": 149
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 0.5050505050505051,
|
1088 |
+
"grad_norm": 0.63671875,
|
1089 |
+
"learning_rate": 9.618510038400203e-06,
|
1090 |
+
"loss": 0.7322,
|
1091 |
+
"step": 150
|
1092 |
+
}
|
1093 |
+
],
|
1094 |
+
"logging_steps": 1,
|
1095 |
+
"max_steps": 891,
|
1096 |
+
"num_input_tokens_seen": 0,
|
1097 |
+
"num_train_epochs": 3,
|
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 sha256:67281bdc6cc564e812aa4cb73613aaae3277625d9bdb71d00a737b9619706f71
|
3 |
+
size 6328
|