Upload 14 files
Browse files- README.md +202 -3
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +50 -0
- trainer_state.json +828 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,202 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2-1.5B
|
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
|
adapter_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-1.5B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"lm_head",
|
25 |
+
"k_proj",
|
26 |
+
"up_proj",
|
27 |
+
"v_proj",
|
28 |
+
"o_proj",
|
29 |
+
"down_proj",
|
30 |
+
"q_proj"
|
31 |
+
],
|
32 |
+
"task_type": "CAUSAL_LM",
|
33 |
+
"use_dora": false,
|
34 |
+
"use_rslora": false
|
35 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a00964968e6d0a5dff2413128626581089973918056ec3d6a35bc4c3de30ffc
|
3 |
+
size 1017229528
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f78d23e80b412492bb23e7f77c42dc58a5421d56d226af3bfb96ded4984901c
|
3 |
+
size 167693808
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6e37e1ce471c56982fb53ecc021031588a46b2ad8c358491def6bf222b39b2c
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82bae41031bb9a3e20f8500051e9b275b0c0fa328ed27a9d8750a01556e2e224
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"max_length": 512,
|
39 |
+
"model_max_length": 32768,
|
40 |
+
"pad_to_multiple_of": null,
|
41 |
+
"pad_token": "<|endoftext|>",
|
42 |
+
"pad_token_type_id": 0,
|
43 |
+
"padding_side": "right",
|
44 |
+
"split_special_tokens": false,
|
45 |
+
"stride": 0,
|
46 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
47 |
+
"truncation_side": "right",
|
48 |
+
"truncation_strategy": "longest_first",
|
49 |
+
"unk_token": null
|
50 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,828 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8609164953231812,
|
3 |
+
"best_model_checkpoint": "/home/coder/qwen2/checkpoint-15900",
|
4 |
+
"epoch": 0.9999803783832573,
|
5 |
+
"eval_steps": 300,
|
6 |
+
"global_step": 15926,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.018836752073023807,
|
13 |
+
"grad_norm": 0.2832883298397064,
|
14 |
+
"learning_rate": 0.00019629420262546324,
|
15 |
+
"loss": 1.1403,
|
16 |
+
"step": 300
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.018836752073023807,
|
20 |
+
"eval_loss": 1.0671226978302002,
|
21 |
+
"eval_runtime": 300.1436,
|
22 |
+
"eval_samples_per_second": 17.155,
|
23 |
+
"eval_steps_per_second": 2.146,
|
24 |
+
"step": 300
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.037673504146047615,
|
28 |
+
"grad_norm": 0.33913707733154297,
|
29 |
+
"learning_rate": 0.00019252559512593432,
|
30 |
+
"loss": 1.0551,
|
31 |
+
"step": 600
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.037673504146047615,
|
35 |
+
"eval_loss": 1.0309056043624878,
|
36 |
+
"eval_runtime": 300.0852,
|
37 |
+
"eval_samples_per_second": 17.158,
|
38 |
+
"eval_steps_per_second": 2.146,
|
39 |
+
"step": 600
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.05651025621907143,
|
43 |
+
"grad_norm": 0.30800801515579224,
|
44 |
+
"learning_rate": 0.0001887569876264054,
|
45 |
+
"loss": 1.0185,
|
46 |
+
"step": 900
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.05651025621907143,
|
50 |
+
"eval_loss": 1.0096280574798584,
|
51 |
+
"eval_runtime": 299.931,
|
52 |
+
"eval_samples_per_second": 17.167,
|
53 |
+
"eval_steps_per_second": 2.147,
|
54 |
+
"step": 900
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.07534700829209523,
|
58 |
+
"grad_norm": 0.317748099565506,
|
59 |
+
"learning_rate": 0.00018498838012687648,
|
60 |
+
"loss": 0.9952,
|
61 |
+
"step": 1200
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.07534700829209523,
|
65 |
+
"eval_loss": 0.9937332272529602,
|
66 |
+
"eval_runtime": 299.9997,
|
67 |
+
"eval_samples_per_second": 17.163,
|
68 |
+
"eval_steps_per_second": 2.147,
|
69 |
+
"step": 1200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.09418376036511904,
|
73 |
+
"grad_norm": 0.36215266585350037,
|
74 |
+
"learning_rate": 0.00018121977262734753,
|
75 |
+
"loss": 0.9931,
|
76 |
+
"step": 1500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.09418376036511904,
|
80 |
+
"eval_loss": 0.9828254580497742,
|
81 |
+
"eval_runtime": 299.9242,
|
82 |
+
"eval_samples_per_second": 17.168,
|
83 |
+
"eval_steps_per_second": 2.147,
|
84 |
+
"step": 1500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.11302051243814286,
|
88 |
+
"grad_norm": 0.3347627520561218,
|
89 |
+
"learning_rate": 0.0001774511651278186,
|
90 |
+
"loss": 0.9763,
|
91 |
+
"step": 1800
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.11302051243814286,
|
95 |
+
"eval_loss": 0.972442626953125,
|
96 |
+
"eval_runtime": 299.8563,
|
97 |
+
"eval_samples_per_second": 17.172,
|
98 |
+
"eval_steps_per_second": 2.148,
|
99 |
+
"step": 1800
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.13185726451116667,
|
103 |
+
"grad_norm": 0.319148451089859,
|
104 |
+
"learning_rate": 0.0001736825576282897,
|
105 |
+
"loss": 0.9727,
|
106 |
+
"step": 2100
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.13185726451116667,
|
110 |
+
"eval_loss": 0.965033769607544,
|
111 |
+
"eval_runtime": 299.797,
|
112 |
+
"eval_samples_per_second": 17.175,
|
113 |
+
"eval_steps_per_second": 2.148,
|
114 |
+
"step": 2100
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.15069401658419046,
|
118 |
+
"grad_norm": 0.2830144166946411,
|
119 |
+
"learning_rate": 0.00016991395012876077,
|
120 |
+
"loss": 0.9674,
|
121 |
+
"step": 2400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.15069401658419046,
|
125 |
+
"eval_loss": 0.9570498466491699,
|
126 |
+
"eval_runtime": 300.0087,
|
127 |
+
"eval_samples_per_second": 17.163,
|
128 |
+
"eval_steps_per_second": 2.147,
|
129 |
+
"step": 2400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16953076865721428,
|
133 |
+
"grad_norm": 0.30889859795570374,
|
134 |
+
"learning_rate": 0.00016614534262923185,
|
135 |
+
"loss": 0.9601,
|
136 |
+
"step": 2700
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.16953076865721428,
|
140 |
+
"eval_loss": 0.9515209197998047,
|
141 |
+
"eval_runtime": 299.9801,
|
142 |
+
"eval_samples_per_second": 17.164,
|
143 |
+
"eval_steps_per_second": 2.147,
|
144 |
+
"step": 2700
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.18836752073023807,
|
148 |
+
"grad_norm": 0.33287131786346436,
|
149 |
+
"learning_rate": 0.0001623767351297029,
|
150 |
+
"loss": 0.944,
|
151 |
+
"step": 3000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.18836752073023807,
|
155 |
+
"eval_loss": 0.9454107284545898,
|
156 |
+
"eval_runtime": 299.9554,
|
157 |
+
"eval_samples_per_second": 17.166,
|
158 |
+
"eval_steps_per_second": 2.147,
|
159 |
+
"step": 3000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.2072042728032619,
|
163 |
+
"grad_norm": 0.31519943475723267,
|
164 |
+
"learning_rate": 0.00015860812763017398,
|
165 |
+
"loss": 0.9462,
|
166 |
+
"step": 3300
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.2072042728032619,
|
170 |
+
"eval_loss": 0.9404099583625793,
|
171 |
+
"eval_runtime": 299.9447,
|
172 |
+
"eval_samples_per_second": 17.166,
|
173 |
+
"eval_steps_per_second": 2.147,
|
174 |
+
"step": 3300
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.22604102487628572,
|
178 |
+
"grad_norm": 0.315909743309021,
|
179 |
+
"learning_rate": 0.00015483952013064506,
|
180 |
+
"loss": 0.9326,
|
181 |
+
"step": 3600
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.22604102487628572,
|
185 |
+
"eval_loss": 0.9352145195007324,
|
186 |
+
"eval_runtime": 299.9991,
|
187 |
+
"eval_samples_per_second": 17.163,
|
188 |
+
"eval_steps_per_second": 2.147,
|
189 |
+
"step": 3600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.2448777769493095,
|
193 |
+
"grad_norm": 0.2997918128967285,
|
194 |
+
"learning_rate": 0.00015107091263111613,
|
195 |
+
"loss": 0.9298,
|
196 |
+
"step": 3900
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.2448777769493095,
|
200 |
+
"eval_loss": 0.9315630793571472,
|
201 |
+
"eval_runtime": 299.95,
|
202 |
+
"eval_samples_per_second": 17.166,
|
203 |
+
"eval_steps_per_second": 2.147,
|
204 |
+
"step": 3900
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.26371452902233333,
|
208 |
+
"grad_norm": 0.2730711102485657,
|
209 |
+
"learning_rate": 0.0001473023051315872,
|
210 |
+
"loss": 0.9345,
|
211 |
+
"step": 4200
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.26371452902233333,
|
215 |
+
"eval_loss": 0.9274590015411377,
|
216 |
+
"eval_runtime": 300.1027,
|
217 |
+
"eval_samples_per_second": 17.157,
|
218 |
+
"eval_steps_per_second": 2.146,
|
219 |
+
"step": 4200
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.28255128109535715,
|
223 |
+
"grad_norm": 0.27338674664497375,
|
224 |
+
"learning_rate": 0.0001435336976320583,
|
225 |
+
"loss": 0.9378,
|
226 |
+
"step": 4500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.28255128109535715,
|
230 |
+
"eval_loss": 0.9236754775047302,
|
231 |
+
"eval_runtime": 299.988,
|
232 |
+
"eval_samples_per_second": 17.164,
|
233 |
+
"eval_steps_per_second": 2.147,
|
234 |
+
"step": 4500
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.3013880331683809,
|
238 |
+
"grad_norm": 0.3145460784435272,
|
239 |
+
"learning_rate": 0.00013976509013252937,
|
240 |
+
"loss": 0.9235,
|
241 |
+
"step": 4800
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.3013880331683809,
|
245 |
+
"eval_loss": 0.9199886322021484,
|
246 |
+
"eval_runtime": 299.9923,
|
247 |
+
"eval_samples_per_second": 17.164,
|
248 |
+
"eval_steps_per_second": 2.147,
|
249 |
+
"step": 4800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.32022478524140474,
|
253 |
+
"grad_norm": 0.2656671702861786,
|
254 |
+
"learning_rate": 0.00013599648263300045,
|
255 |
+
"loss": 0.9207,
|
256 |
+
"step": 5100
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.32022478524140474,
|
260 |
+
"eval_loss": 0.9165565371513367,
|
261 |
+
"eval_runtime": 299.8304,
|
262 |
+
"eval_samples_per_second": 17.173,
|
263 |
+
"eval_steps_per_second": 2.148,
|
264 |
+
"step": 5100
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.33906153731442856,
|
268 |
+
"grad_norm": 0.2907351851463318,
|
269 |
+
"learning_rate": 0.00013222787513347153,
|
270 |
+
"loss": 0.9149,
|
271 |
+
"step": 5400
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.33906153731442856,
|
275 |
+
"eval_loss": 0.9132035374641418,
|
276 |
+
"eval_runtime": 299.8597,
|
277 |
+
"eval_samples_per_second": 17.171,
|
278 |
+
"eval_steps_per_second": 2.148,
|
279 |
+
"step": 5400
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.3578982893874524,
|
283 |
+
"grad_norm": 0.39790818095207214,
|
284 |
+
"learning_rate": 0.0001284592676339426,
|
285 |
+
"loss": 0.9063,
|
286 |
+
"step": 5700
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.3578982893874524,
|
290 |
+
"eval_loss": 0.9105966687202454,
|
291 |
+
"eval_runtime": 300.0175,
|
292 |
+
"eval_samples_per_second": 17.162,
|
293 |
+
"eval_steps_per_second": 2.147,
|
294 |
+
"step": 5700
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.37673504146047615,
|
298 |
+
"grad_norm": 0.3338871896266937,
|
299 |
+
"learning_rate": 0.00012469066013441369,
|
300 |
+
"loss": 0.9046,
|
301 |
+
"step": 6000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.37673504146047615,
|
305 |
+
"eval_loss": 0.9074862003326416,
|
306 |
+
"eval_runtime": 299.8956,
|
307 |
+
"eval_samples_per_second": 17.169,
|
308 |
+
"eval_steps_per_second": 2.147,
|
309 |
+
"step": 6000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.39557179353349997,
|
313 |
+
"grad_norm": 0.2925800383090973,
|
314 |
+
"learning_rate": 0.00012092205263488474,
|
315 |
+
"loss": 0.907,
|
316 |
+
"step": 6300
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.39557179353349997,
|
320 |
+
"eval_loss": 0.9044873118400574,
|
321 |
+
"eval_runtime": 300.0697,
|
322 |
+
"eval_samples_per_second": 17.159,
|
323 |
+
"eval_steps_per_second": 2.146,
|
324 |
+
"step": 6300
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.4144085456065238,
|
328 |
+
"grad_norm": 0.34801357984542847,
|
329 |
+
"learning_rate": 0.00011715344513535582,
|
330 |
+
"loss": 0.9042,
|
331 |
+
"step": 6600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.4144085456065238,
|
335 |
+
"eval_loss": 0.9019830822944641,
|
336 |
+
"eval_runtime": 299.9421,
|
337 |
+
"eval_samples_per_second": 17.167,
|
338 |
+
"eval_steps_per_second": 2.147,
|
339 |
+
"step": 6600
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.4332452976795476,
|
343 |
+
"grad_norm": 0.3444356918334961,
|
344 |
+
"learning_rate": 0.0001133848376358269,
|
345 |
+
"loss": 0.9019,
|
346 |
+
"step": 6900
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.4332452976795476,
|
350 |
+
"eval_loss": 0.8995754718780518,
|
351 |
+
"eval_runtime": 299.921,
|
352 |
+
"eval_samples_per_second": 17.168,
|
353 |
+
"eval_steps_per_second": 2.147,
|
354 |
+
"step": 6900
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.45208204975257144,
|
358 |
+
"grad_norm": 0.3366526961326599,
|
359 |
+
"learning_rate": 0.00010961623013629799,
|
360 |
+
"loss": 0.9041,
|
361 |
+
"step": 7200
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.45208204975257144,
|
365 |
+
"eval_loss": 0.8974488973617554,
|
366 |
+
"eval_runtime": 299.9169,
|
367 |
+
"eval_samples_per_second": 17.168,
|
368 |
+
"eval_steps_per_second": 2.147,
|
369 |
+
"step": 7200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.4709188018255952,
|
373 |
+
"grad_norm": 0.34138697385787964,
|
374 |
+
"learning_rate": 0.00010584762263676907,
|
375 |
+
"loss": 0.9001,
|
376 |
+
"step": 7500
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.4709188018255952,
|
380 |
+
"eval_loss": 0.8951303958892822,
|
381 |
+
"eval_runtime": 299.8867,
|
382 |
+
"eval_samples_per_second": 17.17,
|
383 |
+
"eval_steps_per_second": 2.147,
|
384 |
+
"step": 7500
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.489755553898619,
|
388 |
+
"grad_norm": 0.35338446497917175,
|
389 |
+
"learning_rate": 0.00010207901513724012,
|
390 |
+
"loss": 0.8962,
|
391 |
+
"step": 7800
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.489755553898619,
|
395 |
+
"eval_loss": 0.8931267261505127,
|
396 |
+
"eval_runtime": 300.0707,
|
397 |
+
"eval_samples_per_second": 17.159,
|
398 |
+
"eval_steps_per_second": 2.146,
|
399 |
+
"step": 7800
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.5085923059716428,
|
403 |
+
"grad_norm": 0.33024904131889343,
|
404 |
+
"learning_rate": 9.83104076377112e-05,
|
405 |
+
"loss": 0.901,
|
406 |
+
"step": 8100
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.5085923059716428,
|
410 |
+
"eval_loss": 0.8908406496047974,
|
411 |
+
"eval_runtime": 300.0908,
|
412 |
+
"eval_samples_per_second": 17.158,
|
413 |
+
"eval_steps_per_second": 2.146,
|
414 |
+
"step": 8100
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.5274290580446667,
|
418 |
+
"grad_norm": 0.30269181728363037,
|
419 |
+
"learning_rate": 9.454180013818228e-05,
|
420 |
+
"loss": 0.8886,
|
421 |
+
"step": 8400
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.5274290580446667,
|
425 |
+
"eval_loss": 0.8892831802368164,
|
426 |
+
"eval_runtime": 299.9819,
|
427 |
+
"eval_samples_per_second": 17.164,
|
428 |
+
"eval_steps_per_second": 2.147,
|
429 |
+
"step": 8400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5462658101176905,
|
433 |
+
"grad_norm": 0.32455185055732727,
|
434 |
+
"learning_rate": 9.077319263865335e-05,
|
435 |
+
"loss": 0.8823,
|
436 |
+
"step": 8700
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5462658101176905,
|
440 |
+
"eval_loss": 0.887444019317627,
|
441 |
+
"eval_runtime": 300.1485,
|
442 |
+
"eval_samples_per_second": 17.155,
|
443 |
+
"eval_steps_per_second": 2.146,
|
444 |
+
"step": 8700
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.5651025621907143,
|
448 |
+
"grad_norm": 0.32726097106933594,
|
449 |
+
"learning_rate": 8.700458513912443e-05,
|
450 |
+
"loss": 0.8773,
|
451 |
+
"step": 9000
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.5651025621907143,
|
455 |
+
"eval_loss": 0.885347306728363,
|
456 |
+
"eval_runtime": 300.0218,
|
457 |
+
"eval_samples_per_second": 17.162,
|
458 |
+
"eval_steps_per_second": 2.147,
|
459 |
+
"step": 9000
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.5839393142637381,
|
463 |
+
"grad_norm": 0.3211737275123596,
|
464 |
+
"learning_rate": 8.323597763959551e-05,
|
465 |
+
"loss": 0.8876,
|
466 |
+
"step": 9300
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.5839393142637381,
|
470 |
+
"eval_loss": 0.8837311267852783,
|
471 |
+
"eval_runtime": 299.8508,
|
472 |
+
"eval_samples_per_second": 17.172,
|
473 |
+
"eval_steps_per_second": 2.148,
|
474 |
+
"step": 9300
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.6027760663367618,
|
478 |
+
"grad_norm": 0.3470586836338043,
|
479 |
+
"learning_rate": 7.946737014006658e-05,
|
480 |
+
"loss": 0.888,
|
481 |
+
"step": 9600
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.6027760663367618,
|
485 |
+
"eval_loss": 0.8818086981773376,
|
486 |
+
"eval_runtime": 299.9724,
|
487 |
+
"eval_samples_per_second": 17.165,
|
488 |
+
"eval_steps_per_second": 2.147,
|
489 |
+
"step": 9600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.6216128184097857,
|
493 |
+
"grad_norm": 0.3012458384037018,
|
494 |
+
"learning_rate": 7.569876264053766e-05,
|
495 |
+
"loss": 0.8833,
|
496 |
+
"step": 9900
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.6216128184097857,
|
500 |
+
"eval_loss": 0.8803924322128296,
|
501 |
+
"eval_runtime": 300.0969,
|
502 |
+
"eval_samples_per_second": 17.158,
|
503 |
+
"eval_steps_per_second": 2.146,
|
504 |
+
"step": 9900
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.6404495704828095,
|
508 |
+
"grad_norm": 0.32445794343948364,
|
509 |
+
"learning_rate": 7.194271716600717e-05,
|
510 |
+
"loss": 0.8841,
|
511 |
+
"step": 10200
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.6404495704828095,
|
515 |
+
"eval_loss": 0.8785931468009949,
|
516 |
+
"eval_runtime": 299.8302,
|
517 |
+
"eval_samples_per_second": 17.173,
|
518 |
+
"eval_steps_per_second": 2.148,
|
519 |
+
"step": 10200
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.6592863225558333,
|
523 |
+
"grad_norm": 0.33264926075935364,
|
524 |
+
"learning_rate": 6.817410966647824e-05,
|
525 |
+
"loss": 0.8852,
|
526 |
+
"step": 10500
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.6592863225558333,
|
530 |
+
"eval_loss": 0.8771566152572632,
|
531 |
+
"eval_runtime": 300.0665,
|
532 |
+
"eval_samples_per_second": 17.16,
|
533 |
+
"eval_steps_per_second": 2.146,
|
534 |
+
"step": 10500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.6781230746288571,
|
538 |
+
"grad_norm": 0.3084549307823181,
|
539 |
+
"learning_rate": 6.440550216694932e-05,
|
540 |
+
"loss": 0.8793,
|
541 |
+
"step": 10800
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.6781230746288571,
|
545 |
+
"eval_loss": 0.8756351470947266,
|
546 |
+
"eval_runtime": 300.155,
|
547 |
+
"eval_samples_per_second": 17.154,
|
548 |
+
"eval_steps_per_second": 2.146,
|
549 |
+
"step": 10800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.696959826701881,
|
553 |
+
"grad_norm": 0.3315499722957611,
|
554 |
+
"learning_rate": 6.0636894667420396e-05,
|
555 |
+
"loss": 0.8687,
|
556 |
+
"step": 11100
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.696959826701881,
|
560 |
+
"eval_loss": 0.8744714260101318,
|
561 |
+
"eval_runtime": 300.5183,
|
562 |
+
"eval_samples_per_second": 17.134,
|
563 |
+
"eval_steps_per_second": 2.143,
|
564 |
+
"step": 11100
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.7157965787749048,
|
568 |
+
"grad_norm": 0.35962772369384766,
|
569 |
+
"learning_rate": 5.686828716789147e-05,
|
570 |
+
"loss": 0.8631,
|
571 |
+
"step": 11400
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.7157965787749048,
|
575 |
+
"eval_loss": 0.8730462789535522,
|
576 |
+
"eval_runtime": 299.7837,
|
577 |
+
"eval_samples_per_second": 17.176,
|
578 |
+
"eval_steps_per_second": 2.148,
|
579 |
+
"step": 11400
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.7346333308479286,
|
583 |
+
"grad_norm": 0.33538639545440674,
|
584 |
+
"learning_rate": 5.3099679668362547e-05,
|
585 |
+
"loss": 0.879,
|
586 |
+
"step": 11700
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.7346333308479286,
|
590 |
+
"eval_loss": 0.8714411854743958,
|
591 |
+
"eval_runtime": 299.9502,
|
592 |
+
"eval_samples_per_second": 17.166,
|
593 |
+
"eval_steps_per_second": 2.147,
|
594 |
+
"step": 11700
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.7534700829209523,
|
598 |
+
"grad_norm": 0.3434339165687561,
|
599 |
+
"learning_rate": 4.933107216883362e-05,
|
600 |
+
"loss": 0.8616,
|
601 |
+
"step": 12000
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.7534700829209523,
|
605 |
+
"eval_loss": 0.8703322410583496,
|
606 |
+
"eval_runtime": 300.0139,
|
607 |
+
"eval_samples_per_second": 17.163,
|
608 |
+
"eval_steps_per_second": 2.147,
|
609 |
+
"step": 12000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.7723068349939761,
|
613 |
+
"grad_norm": 0.34114760160446167,
|
614 |
+
"learning_rate": 4.55624646693047e-05,
|
615 |
+
"loss": 0.8708,
|
616 |
+
"step": 12300
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.7723068349939761,
|
620 |
+
"eval_loss": 0.8692737817764282,
|
621 |
+
"eval_runtime": 299.9274,
|
622 |
+
"eval_samples_per_second": 17.167,
|
623 |
+
"eval_steps_per_second": 2.147,
|
624 |
+
"step": 12300
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.7911435870669999,
|
628 |
+
"grad_norm": 0.40352341532707214,
|
629 |
+
"learning_rate": 4.18064191947742e-05,
|
630 |
+
"loss": 0.8724,
|
631 |
+
"step": 12600
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 0.7911435870669999,
|
635 |
+
"eval_loss": 0.8681650161743164,
|
636 |
+
"eval_runtime": 300.4231,
|
637 |
+
"eval_samples_per_second": 17.139,
|
638 |
+
"eval_steps_per_second": 2.144,
|
639 |
+
"step": 12600
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.8099803391400238,
|
643 |
+
"grad_norm": 0.36962220072746277,
|
644 |
+
"learning_rate": 3.8037811695245274e-05,
|
645 |
+
"loss": 0.8672,
|
646 |
+
"step": 12900
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.8099803391400238,
|
650 |
+
"eval_loss": 0.8672531247138977,
|
651 |
+
"eval_runtime": 299.8101,
|
652 |
+
"eval_samples_per_second": 17.174,
|
653 |
+
"eval_steps_per_second": 2.148,
|
654 |
+
"step": 12900
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.8288170912130476,
|
658 |
+
"grad_norm": 0.4042891561985016,
|
659 |
+
"learning_rate": 3.426920419571635e-05,
|
660 |
+
"loss": 0.8643,
|
661 |
+
"step": 13200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.8288170912130476,
|
665 |
+
"eval_loss": 0.8664665818214417,
|
666 |
+
"eval_runtime": 299.8585,
|
667 |
+
"eval_samples_per_second": 17.171,
|
668 |
+
"eval_steps_per_second": 2.148,
|
669 |
+
"step": 13200
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.8476538432860714,
|
673 |
+
"grad_norm": 0.2992730140686035,
|
674 |
+
"learning_rate": 3.0500596696187428e-05,
|
675 |
+
"loss": 0.8632,
|
676 |
+
"step": 13500
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.8476538432860714,
|
680 |
+
"eval_loss": 0.8653113842010498,
|
681 |
+
"eval_runtime": 299.946,
|
682 |
+
"eval_samples_per_second": 17.166,
|
683 |
+
"eval_steps_per_second": 2.147,
|
684 |
+
"step": 13500
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.8664905953590952,
|
688 |
+
"grad_norm": 0.31725963950157166,
|
689 |
+
"learning_rate": 2.6731989196658503e-05,
|
690 |
+
"loss": 0.8564,
|
691 |
+
"step": 13800
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.8664905953590952,
|
695 |
+
"eval_loss": 0.8644812107086182,
|
696 |
+
"eval_runtime": 299.8536,
|
697 |
+
"eval_samples_per_second": 17.172,
|
698 |
+
"eval_steps_per_second": 2.148,
|
699 |
+
"step": 13800
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.885327347432119,
|
703 |
+
"grad_norm": 0.3101350963115692,
|
704 |
+
"learning_rate": 2.296338169712958e-05,
|
705 |
+
"loss": 0.861,
|
706 |
+
"step": 14100
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.885327347432119,
|
710 |
+
"eval_loss": 0.8637036085128784,
|
711 |
+
"eval_runtime": 300.356,
|
712 |
+
"eval_samples_per_second": 17.143,
|
713 |
+
"eval_steps_per_second": 2.144,
|
714 |
+
"step": 14100
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.9041640995051429,
|
718 |
+
"grad_norm": 0.33058223128318787,
|
719 |
+
"learning_rate": 1.9194774197600654e-05,
|
720 |
+
"loss": 0.8543,
|
721 |
+
"step": 14400
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.9041640995051429,
|
725 |
+
"eval_loss": 0.8630216121673584,
|
726 |
+
"eval_runtime": 299.9507,
|
727 |
+
"eval_samples_per_second": 17.166,
|
728 |
+
"eval_steps_per_second": 2.147,
|
729 |
+
"step": 14400
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.9230008515781666,
|
733 |
+
"grad_norm": 0.35784465074539185,
|
734 |
+
"learning_rate": 1.5438728723070158e-05,
|
735 |
+
"loss": 0.868,
|
736 |
+
"step": 14700
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.9230008515781666,
|
740 |
+
"eval_loss": 0.8623820543289185,
|
741 |
+
"eval_runtime": 299.933,
|
742 |
+
"eval_samples_per_second": 17.167,
|
743 |
+
"eval_steps_per_second": 2.147,
|
744 |
+
"step": 14700
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.9418376036511904,
|
748 |
+
"grad_norm": 0.3938862383365631,
|
749 |
+
"learning_rate": 1.1670121223541235e-05,
|
750 |
+
"loss": 0.8607,
|
751 |
+
"step": 15000
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.9418376036511904,
|
755 |
+
"eval_loss": 0.861863911151886,
|
756 |
+
"eval_runtime": 299.8746,
|
757 |
+
"eval_samples_per_second": 17.171,
|
758 |
+
"eval_steps_per_second": 2.148,
|
759 |
+
"step": 15000
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.9606743557242142,
|
763 |
+
"grad_norm": 0.3867338001728058,
|
764 |
+
"learning_rate": 7.90151372401231e-06,
|
765 |
+
"loss": 0.8491,
|
766 |
+
"step": 15300
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.9606743557242142,
|
770 |
+
"eval_loss": 0.8613755106925964,
|
771 |
+
"eval_runtime": 299.919,
|
772 |
+
"eval_samples_per_second": 17.168,
|
773 |
+
"eval_steps_per_second": 2.147,
|
774 |
+
"step": 15300
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.979511107797238,
|
778 |
+
"grad_norm": 0.3372841477394104,
|
779 |
+
"learning_rate": 4.132906224483387e-06,
|
780 |
+
"loss": 0.8643,
|
781 |
+
"step": 15600
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.979511107797238,
|
785 |
+
"eval_loss": 0.8610811829566956,
|
786 |
+
"eval_runtime": 299.8287,
|
787 |
+
"eval_samples_per_second": 17.173,
|
788 |
+
"eval_steps_per_second": 2.148,
|
789 |
+
"step": 15600
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.9983478598702619,
|
793 |
+
"grad_norm": 0.3431134819984436,
|
794 |
+
"learning_rate": 3.642987249544627e-07,
|
795 |
+
"loss": 0.8633,
|
796 |
+
"step": 15900
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.9983478598702619,
|
800 |
+
"eval_loss": 0.8609164953231812,
|
801 |
+
"eval_runtime": 299.9008,
|
802 |
+
"eval_samples_per_second": 17.169,
|
803 |
+
"eval_steps_per_second": 2.147,
|
804 |
+
"step": 15900
|
805 |
+
}
|
806 |
+
],
|
807 |
+
"logging_steps": 300,
|
808 |
+
"max_steps": 15926,
|
809 |
+
"num_input_tokens_seen": 0,
|
810 |
+
"num_train_epochs": 1,
|
811 |
+
"save_steps": 300,
|
812 |
+
"stateful_callbacks": {
|
813 |
+
"TrainerControl": {
|
814 |
+
"args": {
|
815 |
+
"should_epoch_stop": false,
|
816 |
+
"should_evaluate": false,
|
817 |
+
"should_log": false,
|
818 |
+
"should_save": true,
|
819 |
+
"should_training_stop": true
|
820 |
+
},
|
821 |
+
"attributes": {}
|
822 |
+
}
|
823 |
+
},
|
824 |
+
"total_flos": 4.1684162719241994e+18,
|
825 |
+
"train_batch_size": 2,
|
826 |
+
"trial_name": null,
|
827 |
+
"trial_params": null
|
828 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f203c239c4cec4ae0f20b8df027141ae6e9dc293c497c04f5b902ecf835d5f65
|
3 |
+
size 5432
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|