Hugging Face's logo

Doctor-Shotgun
/
limarpv3-yi-llama-34b-lora

Text Generation
Transformers
llama
Generated from Trainer
Yi
text-generation-inference
8-bit precision
bitsandbytes
Model card Files Community
2
Doctor-Shotgun commited on
Commit
84e2892
•
1 Parent(s): 559e268

Initial model commit

Browse files
Files changed (23) hide show
  1. README.md +81 -0
  2. adapter_config.json +28 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-234/README.md +219 -0
  5. checkpoint-234/adapter_config.json +28 -0
  6. checkpoint-234/adapter_model.bin +3 -0
  7. checkpoint-234/optimizer.pt +3 -0
  8. checkpoint-234/rng_state.pth +3 -0
  9. checkpoint-234/scheduler.pt +3 -0
  10. checkpoint-234/trainer_state.json +1511 -0
  11. checkpoint-234/training_args.bin +3 -0
  12. checkpoint-468/README.md +219 -0
  13. checkpoint-468/adapter_config.json +28 -0
  14. checkpoint-468/adapter_model.bin +3 -0
  15. checkpoint-468/optimizer.pt +3 -0
  16. checkpoint-468/rng_state.pth +3 -0
  17. checkpoint-468/scheduler.pt +3 -0
  18. checkpoint-468/trainer_state.json +3011 -0
  19. checkpoint-468/training_args.bin +3 -0
  20. config.json +40 -0
  21. special_tokens_map.json +30 -0
  22. tokenizer.model +3 -0
  23. tokenizer_config.json +45 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: limarp-lora-out
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
13
+ # limarp-lora-out
14
+
15
+ This model was trained from scratch on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.9729
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.00015
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 8
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 10
45
+ - num_epochs: 2
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.1119 | 0.09 | 20 | 2.0727 |
52
+ | 1.9889 | 0.17 | 40 | 2.0104 |
53
+ | 1.878 | 0.26 | 60 | 1.9978 |
54
+ | 1.8531 | 0.34 | 80 | 1.9886 |
55
+ | 1.9504 | 0.43 | 100 | 1.9837 |
56
+ | 1.9216 | 0.51 | 120 | 1.9826 |
57
+ | 1.8483 | 0.6 | 140 | 1.9794 |
58
+ | 1.9668 | 0.68 | 160 | 1.9780 |
59
+ | 1.9776 | 0.77 | 180 | 1.9778 |
60
+ | 1.9312 | 0.85 | 200 | 1.9772 |
61
+ | 1.9003 | 0.94 | 220 | 1.9738 |
62
+ | 1.8748 | 1.02 | 240 | 1.9729 |
63
+ | 1.8896 | 1.11 | 260 | 1.9745 |
64
+ | 1.8702 | 1.19 | 280 | 1.9760 |
65
+ | 1.9038 | 1.28 | 300 | 1.9770 |
66
+ | 1.9083 | 1.36 | 320 | 1.9758 |
67
+ | 1.8143 | 1.45 | 340 | 1.9756 |
68
+ | 1.852 | 1.53 | 360 | 1.9742 |
69
+ | 1.8608 | 1.62 | 380 | 1.9735 |
70
+ | 1.8959 | 1.7 | 400 | 1.9735 |
71
+ | 1.7912 | 1.79 | 420 | 1.9731 |
72
+ | 1.8908 | 1.87 | 440 | 1.9727 |
73
+ | 1.8079 | 1.96 | 460 | 1.9729 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.34.1
79
+ - Pytorch 2.0.1+cu118
80
+ - Datasets 2.14.6
81
+ - Tokenizers 0.14.1
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/yi-llama-34b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "o_proj",
20
+ "q_proj",
21
+ "v_proj",
22
+ "down_proj",
23
+ "up_proj",
24
+ "gate_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddf9acab1fd590f27e113c76a4f61c1b9e77fc9d91a91bc41dd3138f1352328
3
+ size 983343213
checkpoint-234/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./models/yi-llama-34b
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
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Data 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Data Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+
200
+
201
+ ## Training procedure
202
+
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+
219
+ - PEFT 0.7.0.dev0
checkpoint-234/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/yi-llama-34b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "o_proj",
20
+ "q_proj",
21
+ "v_proj",
22
+ "down_proj",
23
+ "up_proj",
24
+ "gate_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-234/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83f4e620d76b38edae26b153530ffaa4587d1eae73f7a73c04c321feac72687
3
+ size 983343213
checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99189a32bed7d1fec1f7e752fdfb8d8e50cf361aae9b53a1b1a7f62d44a3a8fc
3
+ size 493463935
checkpoint-234/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b344858d7dbdf24e812ff5794e6c4fb22e182c3c9547c92f83e31728ec5e24
3
+ size 14575
checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d9af2e07d26ec72ca0b2bde3c75450d989a80951fa83fba51afac63cc85ea8
3
+ size 627
checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,1511 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9968051118210862,
5
+ "eval_steps": 20,
6
+ "global_step": 234,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.4999999999999999e-05,
14
+ "loss": 2.2286,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.9999999999999997e-05,
20
+ "loss": 2.2437,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.4999999999999996e-05,
26
+ "loss": 2.194,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 5.9999999999999995e-05,
32
+ "loss": 2.2882,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 7.5e-05,
38
+ "loss": 2.1882,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 8.999999999999999e-05,
44
+ "loss": 2.2828,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.00010499999999999999,
50
+ "loss": 2.1696,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.00011999999999999999,
56
+ "loss": 2.0552,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.000135,
62
+ "loss": 2.03,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 0.00015,
68
+ "loss": 2.1028,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 0.0001499982355946975,
74
+ "loss": 2.1635,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 0.0001499929424618067,
80
+ "loss": 2.0228,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 0.00014998412085037382,
86
+ "loss": 2.0951,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 0.00014997177117546275,
92
+ "loss": 2.0612,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 0.0001499558940181357,
98
+ "loss": 2.102,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 0.00014993649012542577,
104
+ "loss": 2.0013,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 0.00014991356041030174,
110
+ "loss": 1.9405,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.08,
115
+ "learning_rate": 0.0001498871059516253,
116
+ "loss": 2.0392,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 0.00014985712799410006,
122
+ "loss": 1.9541,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.09,
127
+ "learning_rate": 0.00014982362794821314,
128
+ "loss": 2.1119,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.09,
133
+ "eval_loss": 2.0726754665374756,
134
+ "eval_runtime": 22.387,
135
+ "eval_samples_per_second": 0.938,
136
+ "eval_steps_per_second": 0.491,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.09,
141
+ "learning_rate": 0.00014978660739016882,
142
+ "loss": 1.9826,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.09,
147
+ "learning_rate": 0.00014974606806181424,
148
+ "loss": 1.94,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.1,
153
+ "learning_rate": 0.00014970201187055753,
154
+ "loss": 1.9218,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.1,
159
+ "learning_rate": 0.00014965444088927814,
160
+ "loss": 1.9999,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.11,
165
+ "learning_rate": 0.00014960335735622916,
166
+ "loss": 1.8888,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.11,
171
+ "learning_rate": 0.0001495487636749321,
172
+ "loss": 1.948,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.12,
177
+ "learning_rate": 0.00014949066241406377,
178
+ "loss": 2.0571,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.12,
183
+ "learning_rate": 0.00014942905630733544,
184
+ "loss": 1.984,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.12,
189
+ "learning_rate": 0.00014936394825336424,
190
+ "loss": 1.9825,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.13,
195
+ "learning_rate": 0.0001492953413155367,
196
+ "loss": 1.9785,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.13,
201
+ "learning_rate": 0.00014922323872186468,
202
+ "loss": 2.0284,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.14,
207
+ "learning_rate": 0.00014914764386483347,
208
+ "loss": 1.8923,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.14,
213
+ "learning_rate": 0.0001490685603012422,
214
+ "loss": 2.0051,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.14,
219
+ "learning_rate": 0.00014898599175203645,
220
+ "loss": 1.9797,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.15,
225
+ "learning_rate": 0.00014889994210213317,
226
+ "loss": 1.9387,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.15,
231
+ "learning_rate": 0.00014881041540023792,
232
+ "loss": 1.9888,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.16,
237
+ "learning_rate": 0.00014871741585865435,
238
+ "loss": 1.9914,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.16,
243
+ "learning_rate": 0.00014862094785308606,
244
+ "loss": 1.9477,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.17,
249
+ "learning_rate": 0.00014852101592243067,
250
+ "loss": 1.9709,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.17,
255
+ "learning_rate": 0.00014841762476856625,
256
+ "loss": 1.9889,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.17,
261
+ "eval_loss": 2.010409355163574,
262
+ "eval_runtime": 22.3318,
263
+ "eval_samples_per_second": 0.94,
264
+ "eval_steps_per_second": 0.493,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.17,
269
+ "learning_rate": 0.00014831077925613016,
270
+ "loss": 1.8916,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.18,
275
+ "learning_rate": 0.00014820048441229006,
276
+ "loss": 1.9724,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.18,
281
+ "learning_rate": 0.0001480867454265075,
282
+ "loss": 2.0695,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.19,
287
+ "learning_rate": 0.0001479695676502937,
288
+ "loss": 1.9938,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.19,
293
+ "learning_rate": 0.0001478489565969577,
294
+ "loss": 1.8722,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.2,
299
+ "learning_rate": 0.00014772491794134697,
300
+ "loss": 2.1142,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.2,
305
+ "learning_rate": 0.00014759745751958056,
306
+ "loss": 1.866,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.2,
311
+ "learning_rate": 0.00014746658132877428,
312
+ "loss": 1.9808,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.21,
317
+ "learning_rate": 0.00014733229552675865,
318
+ "loss": 1.9279,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.21,
323
+ "learning_rate": 0.00014719460643178919,
324
+ "loss": 1.9375,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.22,
329
+ "learning_rate": 0.00014705352052224907,
330
+ "loss": 1.9435,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.22,
335
+ "learning_rate": 0.00014690904443634433,
336
+ "loss": 2.0176,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.23,
341
+ "learning_rate": 0.0001467611849717916,
342
+ "loss": 1.9315,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.23,
347
+ "learning_rate": 0.00014660994908549812,
348
+ "loss": 2.0235,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.23,
353
+ "learning_rate": 0.00014645534389323456,
354
+ "loss": 1.9458,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.24,
359
+ "learning_rate": 0.00014629737666930017,
360
+ "loss": 1.8879,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.24,
365
+ "learning_rate": 0.0001461360548461805,
366
+ "loss": 1.9711,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.25,
371
+ "learning_rate": 0.00014597138601419758,
372
+ "loss": 2.0011,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.25,
377
+ "learning_rate": 0.00014580337792115315,
378
+ "loss": 1.9624,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.26,
383
+ "learning_rate": 0.00014563203847196366,
384
+ "loss": 1.878,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.26,
389
+ "eval_loss": 1.9977601766586304,
390
+ "eval_runtime": 22.3277,
391
+ "eval_samples_per_second": 0.941,
392
+ "eval_steps_per_second": 0.493,
393
+ "step": 60
394
+ },
395
+ {
396
+ "epoch": 0.26,
397
+ "learning_rate": 0.0001454573757282887,
398
+ "loss": 1.9651,
399
+ "step": 61
400
+ },
401
+ {
402
+ "epoch": 0.26,
403
+ "learning_rate": 0.00014527939790815147,
404
+ "loss": 1.9585,
405
+ "step": 62
406
+ },
407
+ {
408
+ "epoch": 0.27,
409
+ "learning_rate": 0.00014509811338555222,
410
+ "loss": 1.7946,
411
+ "step": 63
412
+ },
413
+ {
414
+ "epoch": 0.27,
415
+ "learning_rate": 0.00014491353069007428,
416
+ "loss": 1.9296,
417
+ "step": 64
418
+ },
419
+ {
420
+ "epoch": 0.28,
421
+ "learning_rate": 0.00014472565850648259,
422
+ "loss": 1.9582,
423
+ "step": 65
424
+ },
425
+ {
426
+ "epoch": 0.28,
427
+ "learning_rate": 0.00014453450567431517,
428
+ "loss": 1.8811,
429
+ "step": 66
430
+ },
431
+ {
432
+ "epoch": 0.29,
433
+ "learning_rate": 0.00014434008118746728,
434
+ "loss": 1.9974,
435
+ "step": 67
436
+ },
437
+ {
438
+ "epoch": 0.29,
439
+ "learning_rate": 0.0001441423941937681,
440
+ "loss": 1.9186,
441
+ "step": 68
442
+ },
443
+ {
444
+ "epoch": 0.29,
445
+ "learning_rate": 0.0001439414539945505,
446
+ "loss": 1.9891,
447
+ "step": 69
448
+ },
449
+ {
450
+ "epoch": 0.3,
451
+ "learning_rate": 0.00014373727004421316,
452
+ "loss": 1.8635,
453
+ "step": 70
454
+ },
455
+ {
456
+ "epoch": 0.3,
457
+ "learning_rate": 0.00014352985194977596,
458
+ "loss": 1.9402,
459
+ "step": 71
460
+ },
461
+ {
462
+ "epoch": 0.31,
463
+ "learning_rate": 0.0001433192094704278,
464
+ "loss": 1.8707,
465
+ "step": 72
466
+ },
467
+ {
468
+ "epoch": 0.31,
469
+ "learning_rate": 0.00014310535251706765,
470
+ "loss": 1.8617,
471
+ "step": 73
472
+ },
473
+ {
474
+ "epoch": 0.32,
475
+ "learning_rate": 0.0001428882911518379,
476
+ "loss": 2.0184,
477
+ "step": 74
478
+ },
479
+ {
480
+ "epoch": 0.32,
481
+ "learning_rate": 0.00014266803558765122,
482
+ "loss": 1.9708,
483
+ "step": 75
484
+ },
485
+ {
486
+ "epoch": 0.32,
487
+ "learning_rate": 0.0001424445961877098,
488
+ "loss": 1.819,
489
+ "step": 76
490
+ },
491
+ {
492
+ "epoch": 0.33,
493
+ "learning_rate": 0.0001422179834650181,
494
+ "loss": 1.876,
495
+ "step": 77
496
+ },
497
+ {
498
+ "epoch": 0.33,
499
+ "learning_rate": 0.00014198820808188775,
500
+ "loss": 1.9368,
501
+ "step": 78
502
+ },
503
+ {
504
+ "epoch": 0.34,
505
+ "learning_rate": 0.0001417552808494362,
506
+ "loss": 1.9264,
507
+ "step": 79
508
+ },
509
+ {
510
+ "epoch": 0.34,
511
+ "learning_rate": 0.00014151921272707803,
512
+ "loss": 1.8531,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.34,
517
+ "eval_loss": 1.9885673522949219,
518
+ "eval_runtime": 22.3375,
519
+ "eval_samples_per_second": 0.94,
520
+ "eval_steps_per_second": 0.492,
521
+ "step": 80
522
+ },
523
+ {
524
+ "epoch": 0.35,
525
+ "learning_rate": 0.00014128001482200907,
526
+ "loss": 1.9065,
527
+ "step": 81
528
+ },
529
+ {
530
+ "epoch": 0.35,
531
+ "learning_rate": 0.00014103769838868407,
532
+ "loss": 1.8165,
533
+ "step": 82
534
+ },
535
+ {
536
+ "epoch": 0.35,
537
+ "learning_rate": 0.00014079227482828704,
538
+ "loss": 1.9162,
539
+ "step": 83
540
+ },
541
+ {
542
+ "epoch": 0.36,
543
+ "learning_rate": 0.0001405437556881948,
544
+ "loss": 1.9949,
545
+ "step": 84
546
+ },
547
+ {
548
+ "epoch": 0.36,
549
+ "learning_rate": 0.00014029215266143374,
550
+ "loss": 1.9014,
551
+ "step": 85
552
+ },
553
+ {
554
+ "epoch": 0.37,
555
+ "learning_rate": 0.00014003747758612953,
556
+ "loss": 1.9389,
557
+ "step": 86
558
+ },
559
+ {
560
+ "epoch": 0.37,
561
+ "learning_rate": 0.0001397797424449503,
562
+ "loss": 1.9126,
563
+ "step": 87
564
+ },
565
+ {
566
+ "epoch": 0.37,
567
+ "learning_rate": 0.00013951895936454268,
568
+ "loss": 1.9983,
569
+ "step": 88
570
+ },
571
+ {
572
+ "epoch": 0.38,
573
+ "learning_rate": 0.00013925514061496137,
574
+ "loss": 1.9044,
575
+ "step": 89
576
+ },
577
+ {
578
+ "epoch": 0.38,
579
+ "learning_rate": 0.00013898829860909168,
580
+ "loss": 1.9961,
581
+ "step": 90
582
+ },
583
+ {
584
+ "epoch": 0.39,
585
+ "learning_rate": 0.00013871844590206565,
586
+ "loss": 1.8608,
587
+ "step": 91
588
+ },
589
+ {
590
+ "epoch": 0.39,
591
+ "learning_rate": 0.0001384455951906712,
592
+ "loss": 1.984,
593
+ "step": 92
594
+ },
595
+ {
596
+ "epoch": 0.4,
597
+ "learning_rate": 0.00013816975931275473,
598
+ "loss": 1.9282,
599
+ "step": 93
600
+ },
601
+ {
602
+ "epoch": 0.4,
603
+ "learning_rate": 0.00013789095124661725,
604
+ "loss": 1.9654,
605
+ "step": 94
606
+ },
607
+ {
608
+ "epoch": 0.4,
609
+ "learning_rate": 0.00013760918411040356,
610
+ "loss": 1.895,
611
+ "step": 95
612
+ },
613
+ {
614
+ "epoch": 0.41,
615
+ "learning_rate": 0.00013732447116148507,
616
+ "loss": 1.902,
617
+ "step": 96
618
+ },
619
+ {
620
+ "epoch": 0.41,
621
+ "learning_rate": 0.00013703682579583614,
622
+ "loss": 1.9818,
623
+ "step": 97
624
+ },
625
+ {
626
+ "epoch": 0.42,
627
+ "learning_rate": 0.0001367462615474036,
628
+ "loss": 1.8978,
629
+ "step": 98
630
+ },
631
+ {
632
+ "epoch": 0.42,
633
+ "learning_rate": 0.0001364527920874702,
634
+ "loss": 1.887,
635
+ "step": 99
636
+ },
637
+ {
638
+ "epoch": 0.43,
639
+ "learning_rate": 0.00013615643122401113,
640
+ "loss": 1.9504,
641
+ "step": 100
642
+ },
643
+ {
644
+ "epoch": 0.43,
645
+ "eval_loss": 1.98367178440094,
646
+ "eval_runtime": 22.3432,
647
+ "eval_samples_per_second": 0.94,
648
+ "eval_steps_per_second": 0.492,
649
+ "step": 100
650
+ },
651
+ {
652
+ "epoch": 0.43,
653
+ "learning_rate": 0.0001358571929010445,
654
+ "loss": 1.7944,
655
+ "step": 101
656
+ },
657
+ {
658
+ "epoch": 0.43,
659
+ "learning_rate": 0.0001355550911979752,
660
+ "loss": 1.9889,
661
+ "step": 102
662
+ },
663
+ {
664
+ "epoch": 0.44,
665
+ "learning_rate": 0.00013525014032893256,
666
+ "loss": 1.8523,
667
+ "step": 103
668
+ },
669
+ {
670
+ "epoch": 0.44,
671
+ "learning_rate": 0.00013494235464210129,
672
+ "loss": 2.006,
673
+ "step": 104
674
+ },
675
+ {
676
+ "epoch": 0.45,
677
+ "learning_rate": 0.00013463174861904668,
678
+ "loss": 1.8311,
679
+ "step": 105
680
+ },
681
+ {
682
+ "epoch": 0.45,
683
+ "learning_rate": 0.00013431833687403314,
684
+ "loss": 1.9183,
685
+ "step": 106
686
+ },
687
+ {
688
+ "epoch": 0.46,
689
+ "learning_rate": 0.0001340021341533365,
690
+ "loss": 1.9135,
691
+ "step": 107
692
+ },
693
+ {
694
+ "epoch": 0.46,
695
+ "learning_rate": 0.00013368315533455032,
696
+ "loss": 1.8234,
697
+ "step": 108
698
+ },
699
+ {
700
+ "epoch": 0.46,
701
+ "learning_rate": 0.00013336141542588575,
702
+ "loss": 1.7729,
703
+ "step": 109
704
+ },
705
+ {
706
+ "epoch": 0.47,
707
+ "learning_rate": 0.0001330369295654655,
708
+ "loss": 1.9189,
709
+ "step": 110
710
+ },
711
+ {
712
+ "epoch": 0.47,
713
+ "learning_rate": 0.0001327097130206115,
714
+ "loss": 1.9103,
715
+ "step": 111
716
+ },
717
+ {
718
+ "epoch": 0.48,
719
+ "learning_rate": 0.00013237978118712658,
720
+ "loss": 1.8897,
721
+ "step": 112
722
+ },
723
+ {
724
+ "epoch": 0.48,
725
+ "learning_rate": 0.00013204714958857012,
726
+ "loss": 1.9789,
727
+ "step": 113
728
+ },
729
+ {
730
+ "epoch": 0.49,
731
+ "learning_rate": 0.00013171183387552764,
732
+ "loss": 1.9607,
733
+ "step": 114
734
+ },
735
+ {
736
+ "epoch": 0.49,
737
+ "learning_rate": 0.00013137384982487438,
738
+ "loss": 1.9569,
739
+ "step": 115
740
+ },
741
+ {
742
+ "epoch": 0.49,
743
+ "learning_rate": 0.00013103321333903303,
744
+ "loss": 1.9091,
745
+ "step": 116
746
+ },
747
+ {
748
+ "epoch": 0.5,
749
+ "learning_rate": 0.00013068994044522554,
750
+ "loss": 1.9789,
751
+ "step": 117
752
+ },
753
+ {
754
+ "epoch": 0.5,
755
+ "learning_rate": 0.00013034404729471893,
756
+ "loss": 1.9102,
757
+ "step": 118
758
+ },
759
+ {
760
+ "epoch": 0.51,
761
+ "learning_rate": 0.0001299955501620654,
762
+ "loss": 1.8321,
763
+ "step": 119
764
+ },
765
+ {
766
+ "epoch": 0.51,
767
+ "learning_rate": 0.00012964446544433669,
768
+ "loss": 1.9216,
769
+ "step": 120
770
+ },
771
+ {
772
+ "epoch": 0.51,
773
+ "eval_loss": 1.9825721979141235,
774
+ "eval_runtime": 22.3821,
775
+ "eval_samples_per_second": 0.938,
776
+ "eval_steps_per_second": 0.491,
777
+ "step": 120
778
+ },
779
+ {
780
+ "epoch": 0.52,
781
+ "learning_rate": 0.0001292908096603525,
782
+ "loss": 1.8591,
783
+ "step": 121
784
+ },
785
+ {
786
+ "epoch": 0.52,
787
+ "learning_rate": 0.0001289345994499032,
788
+ "loss": 1.9368,
789
+ "step": 122
790
+ },
791
+ {
792
+ "epoch": 0.52,
793
+ "learning_rate": 0.000128575851572967,
794
+ "loss": 1.9594,
795
+ "step": 123
796
+ },
797
+ {
798
+ "epoch": 0.53,
799
+ "learning_rate": 0.00012821458290892144,
800
+ "loss": 1.8731,
801
+ "step": 124
802
+ },
803
+ {
804
+ "epoch": 0.53,
805
+ "learning_rate": 0.00012785081045574913,
806
+ "loss": 1.9105,
807
+ "step": 125
808
+ },
809
+ {
810
+ "epoch": 0.54,
811
+ "learning_rate": 0.0001274845513292379,
812
+ "loss": 1.8899,
813
+ "step": 126
814
+ },
815
+ {
816
+ "epoch": 0.54,
817
+ "learning_rate": 0.00012711582276217563,
818
+ "loss": 1.9211,
819
+ "step": 127
820
+ },
821
+ {
822
+ "epoch": 0.55,
823
+ "learning_rate": 0.00012674464210353932,
824
+ "loss": 1.9506,
825
+ "step": 128
826
+ },
827
+ {
828
+ "epoch": 0.55,
829
+ "learning_rate": 0.00012637102681767895,
830
+ "loss": 1.8654,
831
+ "step": 129
832
+ },
833
+ {
834
+ "epoch": 0.55,
835
+ "learning_rate": 0.0001259949944834956,
836
+ "loss": 1.9958,
837
+ "step": 130
838
+ },
839
+ {
840
+ "epoch": 0.56,
841
+ "learning_rate": 0.00012561656279361442,
842
+ "loss": 1.9783,
843
+ "step": 131
844
+ },
845
+ {
846
+ "epoch": 0.56,
847
+ "learning_rate": 0.0001252357495535523,
848
+ "loss": 1.9314,
849
+ "step": 132
850
+ },
851
+ {
852
+ "epoch": 0.57,
853
+ "learning_rate": 0.00012485257268087983,
854
+ "loss": 1.8847,
855
+ "step": 133
856
+ },
857
+ {
858
+ "epoch": 0.57,
859
+ "learning_rate": 0.00012446705020437854,
860
+ "loss": 1.9326,
861
+ "step": 134
862
+ },
863
+ {
864
+ "epoch": 0.58,
865
+ "learning_rate": 0.00012407920026319248,
866
+ "loss": 1.9853,
867
+ "step": 135
868
+ },
869
+ {
870
+ "epoch": 0.58,
871
+ "learning_rate": 0.00012368904110597479,
872
+ "loss": 2.0078,
873
+ "step": 136
874
+ },
875
+ {
876
+ "epoch": 0.58,
877
+ "learning_rate": 0.00012329659109002906,
878
+ "loss": 2.0035,
879
+ "step": 137
880
+ },
881
+ {
882
+ "epoch": 0.59,
883
+ "learning_rate": 0.00012290186868044569,
884
+ "loss": 1.8399,
885
+ "step": 138
886
+ },
887
+ {
888
+ "epoch": 0.59,
889
+ "learning_rate": 0.00012250489244923298,
890
+ "loss": 1.8643,
891
+ "step": 139
892
+ },
893
+ {
894
+ "epoch": 0.6,
895
+ "learning_rate": 0.00012210568107444346,
896
+ "loss": 1.8483,
897
+ "step": 140
898
+ },
899
+ {
900
+ "epoch": 0.6,
901
+ "eval_loss": 1.9794269800186157,
902
+ "eval_runtime": 22.3061,
903
+ "eval_samples_per_second": 0.941,
904
+ "eval_steps_per_second": 0.493,
905
+ "step": 140
906
+ },
907
+ {
908
+ "epoch": 0.6,
909
+ "learning_rate": 0.00012170425333929485,
910
+ "loss": 1.8399,
911
+ "step": 141
912
+ },
913
+ {
914
+ "epoch": 0.6,
915
+ "learning_rate": 0.00012130062813128651,
916
+ "loss": 1.8906,
917
+ "step": 142
918
+ },
919
+ {
920
+ "epoch": 0.61,
921
+ "learning_rate": 0.00012089482444131057,
922
+ "loss": 1.9474,
923
+ "step": 143
924
+ },
925
+ {
926
+ "epoch": 0.61,
927
+ "learning_rate": 0.00012048686136275862,
928
+ "loss": 1.9107,
929
+ "step": 144
930
+ },
931
+ {
932
+ "epoch": 0.62,
933
+ "learning_rate": 0.00012007675809062313,
934
+ "loss": 2.0292,
935
+ "step": 145
936
+ },
937
+ {
938
+ "epoch": 0.62,
939
+ "learning_rate": 0.00011966453392059446,
940
+ "loss": 2.0018,
941
+ "step": 146
942
+ },
943
+ {
944
+ "epoch": 0.63,
945
+ "learning_rate": 0.00011925020824815293,
946
+ "loss": 1.9807,
947
+ "step": 147
948
+ },
949
+ {
950
+ "epoch": 0.63,
951
+ "learning_rate": 0.00011883380056765621,
952
+ "loss": 1.948,
953
+ "step": 148
954
+ },
955
+ {
956
+ "epoch": 0.63,
957
+ "learning_rate": 0.00011841533047142213,
958
+ "loss": 1.9769,
959
+ "step": 149
960
+ },
961
+ {
962
+ "epoch": 0.64,
963
+ "learning_rate": 0.00011799481764880692,
964
+ "loss": 2.0001,
965
+ "step": 150
966
+ },
967
+ {
968
+ "epoch": 0.64,
969
+ "learning_rate": 0.00011757228188527866,
970
+ "loss": 1.9211,
971
+ "step": 151
972
+ },
973
+ {
974
+ "epoch": 0.65,
975
+ "learning_rate": 0.00011714774306148647,
976
+ "loss": 1.9913,
977
+ "step": 152
978
+ },
979
+ {
980
+ "epoch": 0.65,
981
+ "learning_rate": 0.00011672122115232503,
982
+ "loss": 1.9234,
983
+ "step": 153
984
+ },
985
+ {
986
+ "epoch": 0.66,
987
+ "learning_rate": 0.00011629273622599487,
988
+ "loss": 1.9399,
989
+ "step": 154
990
+ },
991
+ {
992
+ "epoch": 0.66,
993
+ "learning_rate": 0.000115862308443058,
994
+ "loss": 1.9234,
995
+ "step": 155
996
+ },
997
+ {
998
+ "epoch": 0.66,
999
+ "learning_rate": 0.0001154299580554894,
1000
+ "loss": 2.0013,
1001
+ "step": 156
1002
+ },
1003
+ {
1004
+ "epoch": 0.67,
1005
+ "learning_rate": 0.00011499570540572424,
1006
+ "loss": 2.0099,
1007
+ "step": 157
1008
+ },
1009
+ {
1010
+ "epoch": 0.67,
1011
+ "learning_rate": 0.00011455957092570054,
1012
+ "loss": 1.8489,
1013
+ "step": 158
1014
+ },
1015
+ {
1016
+ "epoch": 0.68,
1017
+ "learning_rate": 0.00011412157513589799,
1018
+ "loss": 1.9815,
1019
+ "step": 159
1020
+ },
1021
+ {
1022
+ "epoch": 0.68,
1023
+ "learning_rate": 0.0001136817386443725,
1024
+ "loss": 1.9668,
1025
+ "step": 160
1026
+ },
1027
+ {
1028
+ "epoch": 0.68,
1029
+ "eval_loss": 1.9779595136642456,
1030
+ "eval_runtime": 22.3755,
1031
+ "eval_samples_per_second": 0.939,
1032
+ "eval_steps_per_second": 0.492,
1033
+ "step": 160
1034
+ },
1035
+ {
1036
+ "epoch": 0.69,
1037
+ "learning_rate": 0.00011324008214578636,
1038
+ "loss": 1.8557,
1039
+ "step": 161
1040
+ },
1041
+ {
1042
+ "epoch": 0.69,
1043
+ "learning_rate": 0.00011279662642043473,
1044
+ "loss": 1.8822,
1045
+ "step": 162
1046
+ },
1047
+ {
1048
+ "epoch": 0.69,
1049
+ "learning_rate": 0.00011235139233326782,
1050
+ "loss": 1.9452,
1051
+ "step": 163
1052
+ },
1053
+ {
1054
+ "epoch": 0.7,
1055
+ "learning_rate": 0.00011190440083290921,
1056
+ "loss": 1.8977,
1057
+ "step": 164
1058
+ },
1059
+ {
1060
+ "epoch": 0.7,
1061
+ "learning_rate": 0.00011145567295067023,
1062
+ "loss": 1.9694,
1063
+ "step": 165
1064
+ },
1065
+ {
1066
+ "epoch": 0.71,
1067
+ "learning_rate": 0.0001110052297995603,
1068
+ "loss": 1.9932,
1069
+ "step": 166
1070
+ },
1071
+ {
1072
+ "epoch": 0.71,
1073
+ "learning_rate": 0.00011055309257329369,
1074
+ "loss": 1.8577,
1075
+ "step": 167
1076
+ },
1077
+ {
1078
+ "epoch": 0.72,
1079
+ "learning_rate": 0.00011009928254529225,
1080
+ "loss": 1.944,
1081
+ "step": 168
1082
+ },
1083
+ {
1084
+ "epoch": 0.72,
1085
+ "learning_rate": 0.0001096438210676845,
1086
+ "loss": 1.9186,
1087
+ "step": 169
1088
+ },
1089
+ {
1090
+ "epoch": 0.72,
1091
+ "learning_rate": 0.000109186729570301,
1092
+ "loss": 1.9441,
1093
+ "step": 170
1094
+ },
1095
+ {
1096
+ "epoch": 0.73,
1097
+ "learning_rate": 0.00010872802955966606,
1098
+ "loss": 1.9223,
1099
+ "step": 171
1100
+ },
1101
+ {
1102
+ "epoch": 0.73,
1103
+ "learning_rate": 0.00010826774261798585,
1104
+ "loss": 1.863,
1105
+ "step": 172
1106
+ },
1107
+ {
1108
+ "epoch": 0.74,
1109
+ "learning_rate": 0.0001078058904021329,
1110
+ "loss": 2.0239,
1111
+ "step": 173
1112
+ },
1113
+ {
1114
+ "epoch": 0.74,
1115
+ "learning_rate": 0.00010734249464262721,
1116
+ "loss": 1.9354,
1117
+ "step": 174
1118
+ },
1119
+ {
1120
+ "epoch": 0.75,
1121
+ "learning_rate": 0.00010687757714261369,
1122
+ "loss": 1.9318,
1123
+ "step": 175
1124
+ },
1125
+ {
1126
+ "epoch": 0.75,
1127
+ "learning_rate": 0.00010641115977683641,
1128
+ "loss": 1.9005,
1129
+ "step": 176
1130
+ },
1131
+ {
1132
+ "epoch": 0.75,
1133
+ "learning_rate": 0.00010594326449060932,
1134
+ "loss": 1.9553,
1135
+ "step": 177
1136
+ },
1137
+ {
1138
+ "epoch": 0.76,
1139
+ "learning_rate": 0.00010547391329878373,
1140
+ "loss": 2.0101,
1141
+ "step": 178
1142
+ },
1143
+ {
1144
+ "epoch": 0.76,
1145
+ "learning_rate": 0.00010500312828471247,
1146
+ "loss": 1.8455,
1147
+ "step": 179
1148
+ },
1149
+ {
1150
+ "epoch": 0.77,
1151
+ "learning_rate": 0.00010453093159921094,
1152
+ "loss": 1.9776,
1153
+ "step": 180
1154
+ },
1155
+ {
1156
+ "epoch": 0.77,
1157
+ "eval_loss": 1.9778156280517578,
1158
+ "eval_runtime": 22.326,
1159
+ "eval_samples_per_second": 0.941,
1160
+ "eval_steps_per_second": 0.493,
1161
+ "step": 180
1162
+ },
1163
+ {
1164
+ "epoch": 0.77,
1165
+ "learning_rate": 0.00010405734545951468,
1166
+ "loss": 1.8919,
1167
+ "step": 181
1168
+ },
1169
+ {
1170
+ "epoch": 0.78,
1171
+ "learning_rate": 0.00010358239214823427,
1172
+ "loss": 1.9612,
1173
+ "step": 182
1174
+ },
1175
+ {
1176
+ "epoch": 0.78,
1177
+ "learning_rate": 0.00010310609401230684,
1178
+ "loss": 1.9871,
1179
+ "step": 183
1180
+ },
1181
+ {
1182
+ "epoch": 0.78,
1183
+ "learning_rate": 0.00010262847346194452,
1184
+ "loss": 1.8808,
1185
+ "step": 184
1186
+ },
1187
+ {
1188
+ "epoch": 0.79,
1189
+ "learning_rate": 0.00010214955296958019,
1190
+ "loss": 1.8487,
1191
+ "step": 185
1192
+ },
1193
+ {
1194
+ "epoch": 0.79,
1195
+ "learning_rate": 0.00010166935506880997,
1196
+ "loss": 1.9151,
1197
+ "step": 186
1198
+ },
1199
+ {
1200
+ "epoch": 0.8,
1201
+ "learning_rate": 0.00010118790235333316,
1202
+ "loss": 1.949,
1203
+ "step": 187
1204
+ },
1205
+ {
1206
+ "epoch": 0.8,
1207
+ "learning_rate": 0.00010070521747588906,
1208
+ "loss": 1.9736,
1209
+ "step": 188
1210
+ },
1211
+ {
1212
+ "epoch": 0.81,
1213
+ "learning_rate": 0.00010022132314719119,
1214
+ "loss": 1.891,
1215
+ "step": 189
1216
+ },
1217
+ {
1218
+ "epoch": 0.81,
1219
+ "learning_rate": 9.973624213485876e-05,
1220
+ "loss": 1.9049,
1221
+ "step": 190
1222
+ },
1223
+ {
1224
+ "epoch": 0.81,
1225
+ "learning_rate": 9.924999726234535e-05,
1226
+ "loss": 1.8852,
1227
+ "step": 191
1228
+ },
1229
+ {
1230
+ "epoch": 0.82,
1231
+ "learning_rate": 9.876261140786512e-05,
1232
+ "loss": 1.8468,
1233
+ "step": 192
1234
+ },
1235
+ {
1236
+ "epoch": 0.82,
1237
+ "learning_rate": 9.82741075033164e-05,
1238
+ "loss": 1.9972,
1239
+ "step": 193
1240
+ },
1241
+ {
1242
+ "epoch": 0.83,
1243
+ "learning_rate": 9.77845085332026e-05,
1244
+ "loss": 1.9918,
1245
+ "step": 194
1246
+ },
1247
+ {
1248
+ "epoch": 0.83,
1249
+ "learning_rate": 9.729383753355093e-05,
1250
+ "loss": 1.9932,
1251
+ "step": 195
1252
+ },
1253
+ {
1254
+ "epoch": 0.83,
1255
+ "learning_rate": 9.68021175908284e-05,
1256
+ "loss": 1.9282,
1257
+ "step": 196
1258
+ },
1259
+ {
1260
+ "epoch": 0.84,
1261
+ "learning_rate": 9.630937184085566e-05,
1262
+ "loss": 2.0343,
1263
+ "step": 197
1264
+ },
1265
+ {
1266
+ "epoch": 0.84,
1267
+ "learning_rate": 9.581562346771841e-05,
1268
+ "loss": 1.8442,
1269
+ "step": 198
1270
+ },
1271
+ {
1272
+ "epoch": 0.85,
1273
+ "learning_rate": 9.532089570267661e-05,
1274
+ "loss": 1.8367,
1275
+ "step": 199
1276
+ },
1277
+ {
1278
+ "epoch": 0.85,
1279
+ "learning_rate": 9.482521182307136e-05,
1280
+ "loss": 1.9312,
1281
+ "step": 200
1282
+ },
1283
+ {
1284
+ "epoch": 0.85,
1285
+ "eval_loss": 1.977174162864685,
1286
+ "eval_runtime": 22.3424,
1287
+ "eval_samples_per_second": 0.94,
1288
+ "eval_steps_per_second": 0.492,
1289
+ "step": 200
1290
+ },
1291
+ {
1292
+ "epoch": 0.86,
1293
+ "learning_rate": 9.432859515122974e-05,
1294
+ "loss": 1.9262,
1295
+ "step": 201
1296
+ },
1297
+ {
1298
+ "epoch": 0.86,
1299
+ "learning_rate": 9.383106905336748e-05,
1300
+ "loss": 1.8701,
1301
+ "step": 202
1302
+ },
1303
+ {
1304
+ "epoch": 0.86,
1305
+ "learning_rate": 9.33326569384895e-05,
1306
+ "loss": 1.974,
1307
+ "step": 203
1308
+ },
1309
+ {
1310
+ "epoch": 0.87,
1311
+ "learning_rate": 9.283338225728854e-05,
1312
+ "loss": 1.8317,
1313
+ "step": 204
1314
+ },
1315
+ {
1316
+ "epoch": 0.87,
1317
+ "learning_rate": 9.233326850104182e-05,
1318
+ "loss": 1.9642,
1319
+ "step": 205
1320
+ },
1321
+ {
1322
+ "epoch": 0.88,
1323
+ "learning_rate": 9.18323392005057e-05,
1324
+ "loss": 1.893,
1325
+ "step": 206
1326
+ },
1327
+ {
1328
+ "epoch": 0.88,
1329
+ "learning_rate": 9.133061792480855e-05,
1330
+ "loss": 1.911,
1331
+ "step": 207
1332
+ },
1333
+ {
1334
+ "epoch": 0.89,
1335
+ "learning_rate": 9.08281282803418e-05,
1336
+ "loss": 1.8981,
1337
+ "step": 208
1338
+ },
1339
+ {
1340
+ "epoch": 0.89,
1341
+ "learning_rate": 9.03248939096493e-05,
1342
+ "loss": 1.928,
1343
+ "step": 209
1344
+ },
1345
+ {
1346
+ "epoch": 0.89,
1347
+ "learning_rate": 8.982093849031479e-05,
1348
+ "loss": 1.8451,
1349
+ "step": 210
1350
+ },
1351
+ {
1352
+ "epoch": 0.9,
1353
+ "learning_rate": 8.931628573384802e-05,
1354
+ "loss": 1.8178,
1355
+ "step": 211
1356
+ },
1357
+ {
1358
+ "epoch": 0.9,
1359
+ "learning_rate": 8.881095938456899e-05,
1360
+ "loss": 1.8732,
1361
+ "step": 212
1362
+ },
1363
+ {
1364
+ "epoch": 0.91,
1365
+ "learning_rate": 8.830498321849071e-05,
1366
+ "loss": 1.9206,
1367
+ "step": 213
1368
+ },
1369
+ {
1370
+ "epoch": 0.91,
1371
+ "learning_rate": 8.77983810422007e-05,
1372
+ "loss": 1.9657,
1373
+ "step": 214
1374
+ },
1375
+ {
1376
+ "epoch": 0.92,
1377
+ "learning_rate": 8.72911766917407e-05,
1378
+ "loss": 1.7979,
1379
+ "step": 215
1380
+ },
1381
+ {
1382
+ "epoch": 0.92,
1383
+ "learning_rate": 8.678339403148527e-05,
1384
+ "loss": 1.9761,
1385
+ "step": 216
1386
+ },
1387
+ {
1388
+ "epoch": 0.92,
1389
+ "learning_rate": 8.62750569530189e-05,
1390
+ "loss": 1.9357,
1391
+ "step": 217
1392
+ },
1393
+ {
1394
+ "epoch": 0.93,
1395
+ "learning_rate": 8.576618937401188e-05,
1396
+ "loss": 1.9625,
1397
+ "step": 218
1398
+ },
1399
+ {
1400
+ "epoch": 0.93,
1401
+ "learning_rate": 8.525681523709503e-05,
1402
+ "loss": 1.9171,
1403
+ "step": 219
1404
+ },
1405
+ {
1406
+ "epoch": 0.94,
1407
+ "learning_rate": 8.474695850873308e-05,
1408
+ "loss": 1.9003,
1409
+ "step": 220
1410
+ },
1411
+ {
1412
+ "epoch": 0.94,
1413
+ "eval_loss": 1.9738101959228516,
1414
+ "eval_runtime": 22.3535,
1415
+ "eval_samples_per_second": 0.939,
1416
+ "eval_steps_per_second": 0.492,
1417
+ "step": 220
1418
+ },
1419
+ {
1420
+ "epoch": 0.94,
1421
+ "learning_rate": 8.423664317809711e-05,
1422
+ "loss": 1.9968,
1423
+ "step": 221
1424
+ },
1425
+ {
1426
+ "epoch": 0.95,
1427
+ "learning_rate": 8.372589325593579e-05,
1428
+ "loss": 1.9338,
1429
+ "step": 222
1430
+ },
1431
+ {
1432
+ "epoch": 0.95,
1433
+ "learning_rate": 8.321473277344569e-05,
1434
+ "loss": 1.943,
1435
+ "step": 223
1436
+ },
1437
+ {
1438
+ "epoch": 0.95,
1439
+ "learning_rate": 8.270318578114052e-05,
1440
+ "loss": 1.9167,
1441
+ "step": 224
1442
+ },
1443
+ {
1444
+ "epoch": 0.96,
1445
+ "learning_rate": 8.219127634771965e-05,
1446
+ "loss": 2.0213,
1447
+ "step": 225
1448
+ },
1449
+ {
1450
+ "epoch": 0.96,
1451
+ "learning_rate": 8.167902855893561e-05,
1452
+ "loss": 1.9531,
1453
+ "step": 226
1454
+ },
1455
+ {
1456
+ "epoch": 0.97,
1457
+ "learning_rate": 8.116646651646079e-05,
1458
+ "loss": 1.9225,
1459
+ "step": 227
1460
+ },
1461
+ {
1462
+ "epoch": 0.97,
1463
+ "learning_rate": 8.065361433675343e-05,
1464
+ "loss": 1.894,
1465
+ "step": 228
1466
+ },
1467
+ {
1468
+ "epoch": 0.98,
1469
+ "learning_rate": 8.014049614992304e-05,
1470
+ "loss": 1.9129,
1471
+ "step": 229
1472
+ },
1473
+ {
1474
+ "epoch": 0.98,
1475
+ "learning_rate": 7.962713609859492e-05,
1476
+ "loss": 1.8996,
1477
+ "step": 230
1478
+ },
1479
+ {
1480
+ "epoch": 0.98,
1481
+ "learning_rate": 7.911355833677434e-05,
1482
+ "loss": 1.8093,
1483
+ "step": 231
1484
+ },
1485
+ {
1486
+ "epoch": 0.99,
1487
+ "learning_rate": 7.859978702871e-05,
1488
+ "loss": 1.9467,
1489
+ "step": 232
1490
+ },
1491
+ {
1492
+ "epoch": 0.99,
1493
+ "learning_rate": 7.808584634775706e-05,
1494
+ "loss": 1.9645,
1495
+ "step": 233
1496
+ },
1497
+ {
1498
+ "epoch": 1.0,
1499
+ "learning_rate": 7.757176047523993e-05,
1500
+ "loss": 1.8858,
1501
+ "step": 234
1502
+ }
1503
+ ],
1504
+ "logging_steps": 1,
1505
+ "max_steps": 468,
1506
+ "num_train_epochs": 2,
1507
+ "save_steps": 500,
1508
+ "total_flos": 1.326673328350298e+18,
1509
+ "trial_name": null,
1510
+ "trial_params": null
1511
+ }
checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7feb49f9c014aec5b2a20b88f6ec716d10a44c3f25f112041117a5c589dca47
3
+ size 4475
checkpoint-468/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./models/yi-llama-34b
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
+ - **Shared by [optional]:** [More Information Needed]
22
+ - **Model type:** [More Information Needed]
23
+ - **Language(s) (NLP):** [More Information Needed]
24
+ - **License:** [More Information Needed]
25
+ - **Finetuned from model [optional]:** [More Information Needed]
26
+
27
+ ### Model Sources [optional]
28
+
29
+ <!-- Provide the basic links for the model. -->
30
+
31
+ - **Repository:** [More Information Needed]
32
+ - **Paper [optional]:** [More Information Needed]
33
+ - **Demo [optional]:** [More Information Needed]
34
+
35
+ ## Uses
36
+
37
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
38
+
39
+ ### Direct Use
40
+
41
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
+
43
+ [More Information Needed]
44
+
45
+ ### Downstream Use [optional]
46
+
47
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Out-of-Scope Use
52
+
53
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
+
55
+ [More Information Needed]
56
+
57
+ ## Bias, Risks, and Limitations
58
+
59
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ### Recommendations
64
+
65
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
+
67
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
+
69
+ ## How to Get Started with the Model
70
+
71
+ Use the code below to get started with the model.
72
+
73
+ [More Information Needed]
74
+
75
+ ## Training Details
76
+
77
+ ### Training Data
78
+
79
+ <!-- This should link to a Data 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. -->
80
+
81
+ [More Information Needed]
82
+
83
+ ### Training Procedure
84
+
85
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
+
87
+ #### Preprocessing [optional]
88
+
89
+ [More Information Needed]
90
+
91
+
92
+ #### Training Hyperparameters
93
+
94
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
+
96
+ #### Speeds, Sizes, Times [optional]
97
+
98
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
+
100
+ [More Information Needed]
101
+
102
+ ## Evaluation
103
+
104
+ <!-- This section describes the evaluation protocols and provides the results. -->
105
+
106
+ ### Testing Data, Factors & Metrics
107
+
108
+ #### Testing Data
109
+
110
+ <!-- This should link to a Data Card if possible. -->
111
+
112
+ [More Information Needed]
113
+
114
+ #### Factors
115
+
116
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Metrics
121
+
122
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
+
124
+ [More Information Needed]
125
+
126
+ ### Results
127
+
128
+ [More Information Needed]
129
+
130
+ #### Summary
131
+
132
+
133
+
134
+ ## Model Examination [optional]
135
+
136
+ <!-- Relevant interpretability work for the model goes here -->
137
+
138
+ [More Information Needed]
139
+
140
+ ## Environmental Impact
141
+
142
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
+
144
+ 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).
145
+
146
+ - **Hardware Type:** [More Information Needed]
147
+ - **Hours used:** [More Information Needed]
148
+ - **Cloud Provider:** [More Information Needed]
149
+ - **Compute Region:** [More Information Needed]
150
+ - **Carbon Emitted:** [More Information Needed]
151
+
152
+ ## Technical Specifications [optional]
153
+
154
+ ### Model Architecture and Objective
155
+
156
+ [More Information Needed]
157
+
158
+ ### Compute Infrastructure
159
+
160
+ [More Information Needed]
161
+
162
+ #### Hardware
163
+
164
+ [More Information Needed]
165
+
166
+ #### Software
167
+
168
+ [More Information Needed]
169
+
170
+ ## Citation [optional]
171
+
172
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
+
174
+ **BibTeX:**
175
+
176
+ [More Information Needed]
177
+
178
+ **APA:**
179
+
180
+ [More Information Needed]
181
+
182
+ ## Glossary [optional]
183
+
184
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
+
186
+ [More Information Needed]
187
+
188
+ ## More Information [optional]
189
+
190
+ [More Information Needed]
191
+
192
+ ## Model Card Authors [optional]
193
+
194
+ [More Information Needed]
195
+
196
+ ## Model Card Contact
197
+
198
+ [More Information Needed]
199
+
200
+
201
+ ## Training procedure
202
+
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+
219
+ - PEFT 0.7.0.dev0
checkpoint-468/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/yi-llama-34b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "o_proj",
20
+ "q_proj",
21
+ "v_proj",
22
+ "down_proj",
23
+ "up_proj",
24
+ "gate_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-468/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddf9acab1fd590f27e113c76a4f61c1b9e77fc9d91a91bc41dd3138f1352328
3
+ size 983343213
checkpoint-468/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7f1ee6a191fbef0c1970a34d6a6eba900e9835e7f8c7673041c42a6c938a8f
3
+ size 493464767
checkpoint-468/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1838b8f705f69eebee72969b157176c68b00c431d915096d210b2b977f84dbed
3
+ size 14575
checkpoint-468/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e769fb42d54de158079afb16600afafe7e84249dfe961d7f5b173cc959d7c004
3
+ size 627
checkpoint-468/trainer_state.json ADDED
@@ -0,0 +1,3011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9936102236421727,
5
+ "eval_steps": 20,
6
+ "global_step": 468,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.4999999999999999e-05,
14
+ "loss": 2.2286,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.9999999999999997e-05,
20
+ "loss": 2.2437,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.4999999999999996e-05,
26
+ "loss": 2.194,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 5.9999999999999995e-05,
32
+ "loss": 2.2882,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 7.5e-05,
38
+ "loss": 2.1882,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 8.999999999999999e-05,
44
+ "loss": 2.2828,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.00010499999999999999,
50
+ "loss": 2.1696,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.00011999999999999999,
56
+ "loss": 2.0552,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.000135,
62
+ "loss": 2.03,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 0.00015,
68
+ "loss": 2.1028,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 0.0001499982355946975,
74
+ "loss": 2.1635,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 0.0001499929424618067,
80
+ "loss": 2.0228,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 0.00014998412085037382,
86
+ "loss": 2.0951,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 0.00014997177117546275,
92
+ "loss": 2.0612,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 0.0001499558940181357,
98
+ "loss": 2.102,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 0.00014993649012542577,
104
+ "loss": 2.0013,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 0.00014991356041030174,
110
+ "loss": 1.9405,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.08,
115
+ "learning_rate": 0.0001498871059516253,
116
+ "loss": 2.0392,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 0.00014985712799410006,
122
+ "loss": 1.9541,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.09,
127
+ "learning_rate": 0.00014982362794821314,
128
+ "loss": 2.1119,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.09,
133
+ "eval_loss": 2.0726754665374756,
134
+ "eval_runtime": 22.387,
135
+ "eval_samples_per_second": 0.938,
136
+ "eval_steps_per_second": 0.491,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.09,
141
+ "learning_rate": 0.00014978660739016882,
142
+ "loss": 1.9826,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.09,
147
+ "learning_rate": 0.00014974606806181424,
148
+ "loss": 1.94,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.1,
153
+ "learning_rate": 0.00014970201187055753,
154
+ "loss": 1.9218,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.1,
159
+ "learning_rate": 0.00014965444088927814,
160
+ "loss": 1.9999,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.11,
165
+ "learning_rate": 0.00014960335735622916,
166
+ "loss": 1.8888,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.11,
171
+ "learning_rate": 0.0001495487636749321,
172
+ "loss": 1.948,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.12,
177
+ "learning_rate": 0.00014949066241406377,
178
+ "loss": 2.0571,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.12,
183
+ "learning_rate": 0.00014942905630733544,
184
+ "loss": 1.984,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.12,
189
+ "learning_rate": 0.00014936394825336424,
190
+ "loss": 1.9825,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.13,
195
+ "learning_rate": 0.0001492953413155367,
196
+ "loss": 1.9785,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.13,
201
+ "learning_rate": 0.00014922323872186468,
202
+ "loss": 2.0284,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.14,
207
+ "learning_rate": 0.00014914764386483347,
208
+ "loss": 1.8923,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.14,
213
+ "learning_rate": 0.0001490685603012422,
214
+ "loss": 2.0051,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.14,
219
+ "learning_rate": 0.00014898599175203645,
220
+ "loss": 1.9797,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.15,
225
+ "learning_rate": 0.00014889994210213317,
226
+ "loss": 1.9387,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.15,
231
+ "learning_rate": 0.00014881041540023792,
232
+ "loss": 1.9888,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.16,
237
+ "learning_rate": 0.00014871741585865435,
238
+ "loss": 1.9914,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.16,
243
+ "learning_rate": 0.00014862094785308606,
244
+ "loss": 1.9477,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.17,
249
+ "learning_rate": 0.00014852101592243067,
250
+ "loss": 1.9709,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.17,
255
+ "learning_rate": 0.00014841762476856625,
256
+ "loss": 1.9889,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.17,
261
+ "eval_loss": 2.010409355163574,
262
+ "eval_runtime": 22.3318,
263
+ "eval_samples_per_second": 0.94,
264
+ "eval_steps_per_second": 0.493,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.17,
269
+ "learning_rate": 0.00014831077925613016,
270
+ "loss": 1.8916,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.18,
275
+ "learning_rate": 0.00014820048441229006,
276
+ "loss": 1.9724,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.18,
281
+ "learning_rate": 0.0001480867454265075,
282
+ "loss": 2.0695,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.19,
287
+ "learning_rate": 0.0001479695676502937,
288
+ "loss": 1.9938,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.19,
293
+ "learning_rate": 0.0001478489565969577,
294
+ "loss": 1.8722,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.2,
299
+ "learning_rate": 0.00014772491794134697,
300
+ "loss": 2.1142,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.2,
305
+ "learning_rate": 0.00014759745751958056,
306
+ "loss": 1.866,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.2,
311
+ "learning_rate": 0.00014746658132877428,
312
+ "loss": 1.9808,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.21,
317
+ "learning_rate": 0.00014733229552675865,
318
+ "loss": 1.9279,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.21,
323
+ "learning_rate": 0.00014719460643178919,
324
+ "loss": 1.9375,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.22,
329
+ "learning_rate": 0.00014705352052224907,
330
+ "loss": 1.9435,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.22,
335
+ "learning_rate": 0.00014690904443634433,
336
+ "loss": 2.0176,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.23,
341
+ "learning_rate": 0.0001467611849717916,
342
+ "loss": 1.9315,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.23,
347
+ "learning_rate": 0.00014660994908549812,
348
+ "loss": 2.0235,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.23,
353
+ "learning_rate": 0.00014645534389323456,
354
+ "loss": 1.9458,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.24,
359
+ "learning_rate": 0.00014629737666930017,
360
+ "loss": 1.8879,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.24,
365
+ "learning_rate": 0.0001461360548461805,
366
+ "loss": 1.9711,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.25,
371
+ "learning_rate": 0.00014597138601419758,
372
+ "loss": 2.0011,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.25,
377
+ "learning_rate": 0.00014580337792115315,
378
+ "loss": 1.9624,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.26,
383
+ "learning_rate": 0.00014563203847196366,
384
+ "loss": 1.878,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.26,
389
+ "eval_loss": 1.9977601766586304,
390
+ "eval_runtime": 22.3277,
391
+ "eval_samples_per_second": 0.941,
392
+ "eval_steps_per_second": 0.493,
393
+ "step": 60
394
+ },
395
+ {
396
+ "epoch": 0.26,
397
+ "learning_rate": 0.0001454573757282887,
398
+ "loss": 1.9651,
399
+ "step": 61
400
+ },
401
+ {
402
+ "epoch": 0.26,
403
+ "learning_rate": 0.00014527939790815147,
404
+ "loss": 1.9585,
405
+ "step": 62
406
+ },
407
+ {
408
+ "epoch": 0.27,
409
+ "learning_rate": 0.00014509811338555222,
410
+ "loss": 1.7946,
411
+ "step": 63
412
+ },
413
+ {
414
+ "epoch": 0.27,
415
+ "learning_rate": 0.00014491353069007428,
416
+ "loss": 1.9296,
417
+ "step": 64
418
+ },
419
+ {
420
+ "epoch": 0.28,
421
+ "learning_rate": 0.00014472565850648259,
422
+ "loss": 1.9582,
423
+ "step": 65
424
+ },
425
+ {
426
+ "epoch": 0.28,
427
+ "learning_rate": 0.00014453450567431517,
428
+ "loss": 1.8811,
429
+ "step": 66
430
+ },
431
+ {
432
+ "epoch": 0.29,
433
+ "learning_rate": 0.00014434008118746728,
434
+ "loss": 1.9974,
435
+ "step": 67
436
+ },
437
+ {
438
+ "epoch": 0.29,
439
+ "learning_rate": 0.0001441423941937681,
440
+ "loss": 1.9186,
441
+ "step": 68
442
+ },
443
+ {
444
+ "epoch": 0.29,
445
+ "learning_rate": 0.0001439414539945505,
446
+ "loss": 1.9891,
447
+ "step": 69
448
+ },
449
+ {
450
+ "epoch": 0.3,
451
+ "learning_rate": 0.00014373727004421316,
452
+ "loss": 1.8635,
453
+ "step": 70
454
+ },
455
+ {
456
+ "epoch": 0.3,
457
+ "learning_rate": 0.00014352985194977596,
458
+ "loss": 1.9402,
459
+ "step": 71
460
+ },
461
+ {
462
+ "epoch": 0.31,
463
+ "learning_rate": 0.0001433192094704278,
464
+ "loss": 1.8707,
465
+ "step": 72
466
+ },
467
+ {
468
+ "epoch": 0.31,
469
+ "learning_rate": 0.00014310535251706765,
470
+ "loss": 1.8617,
471
+ "step": 73
472
+ },
473
+ {
474
+ "epoch": 0.32,
475
+ "learning_rate": 0.0001428882911518379,
476
+ "loss": 2.0184,
477
+ "step": 74
478
+ },
479
+ {
480
+ "epoch": 0.32,
481
+ "learning_rate": 0.00014266803558765122,
482
+ "loss": 1.9708,
483
+ "step": 75
484
+ },
485
+ {
486
+ "epoch": 0.32,
487
+ "learning_rate": 0.0001424445961877098,
488
+ "loss": 1.819,
489
+ "step": 76
490
+ },
491
+ {
492
+ "epoch": 0.33,
493
+ "learning_rate": 0.0001422179834650181,
494
+ "loss": 1.876,
495
+ "step": 77
496
+ },
497
+ {
498
+ "epoch": 0.33,
499
+ "learning_rate": 0.00014198820808188775,
500
+ "loss": 1.9368,
501
+ "step": 78
502
+ },
503
+ {
504
+ "epoch": 0.34,
505
+ "learning_rate": 0.0001417552808494362,
506
+ "loss": 1.9264,
507
+ "step": 79
508
+ },
509
+ {
510
+ "epoch": 0.34,
511
+ "learning_rate": 0.00014151921272707803,
512
+ "loss": 1.8531,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.34,
517
+ "eval_loss": 1.9885673522949219,
518
+ "eval_runtime": 22.3375,
519
+ "eval_samples_per_second": 0.94,
520
+ "eval_steps_per_second": 0.492,
521
+ "step": 80
522
+ },
523
+ {
524
+ "epoch": 0.35,
525
+ "learning_rate": 0.00014128001482200907,
526
+ "loss": 1.9065,
527
+ "step": 81
528
+ },
529
+ {
530
+ "epoch": 0.35,
531
+ "learning_rate": 0.00014103769838868407,
532
+ "loss": 1.8165,
533
+ "step": 82
534
+ },
535
+ {
536
+ "epoch": 0.35,
537
+ "learning_rate": 0.00014079227482828704,
538
+ "loss": 1.9162,
539
+ "step": 83
540
+ },
541
+ {
542
+ "epoch": 0.36,
543
+ "learning_rate": 0.0001405437556881948,
544
+ "loss": 1.9949,
545
+ "step": 84
546
+ },
547
+ {
548
+ "epoch": 0.36,
549
+ "learning_rate": 0.00014029215266143374,
550
+ "loss": 1.9014,
551
+ "step": 85
552
+ },
553
+ {
554
+ "epoch": 0.37,
555
+ "learning_rate": 0.00014003747758612953,
556
+ "loss": 1.9389,
557
+ "step": 86
558
+ },
559
+ {
560
+ "epoch": 0.37,
561
+ "learning_rate": 0.0001397797424449503,
562
+ "loss": 1.9126,
563
+ "step": 87
564
+ },
565
+ {
566
+ "epoch": 0.37,
567
+ "learning_rate": 0.00013951895936454268,
568
+ "loss": 1.9983,
569
+ "step": 88
570
+ },
571
+ {
572
+ "epoch": 0.38,
573
+ "learning_rate": 0.00013925514061496137,
574
+ "loss": 1.9044,
575
+ "step": 89
576
+ },
577
+ {
578
+ "epoch": 0.38,
579
+ "learning_rate": 0.00013898829860909168,
580
+ "loss": 1.9961,
581
+ "step": 90
582
+ },
583
+ {
584
+ "epoch": 0.39,
585
+ "learning_rate": 0.00013871844590206565,
586
+ "loss": 1.8608,
587
+ "step": 91
588
+ },
589
+ {
590
+ "epoch": 0.39,
591
+ "learning_rate": 0.0001384455951906712,
592
+ "loss": 1.984,
593
+ "step": 92
594
+ },
595
+ {
596
+ "epoch": 0.4,
597
+ "learning_rate": 0.00013816975931275473,
598
+ "loss": 1.9282,
599
+ "step": 93
600
+ },
601
+ {
602
+ "epoch": 0.4,
603
+ "learning_rate": 0.00013789095124661725,
604
+ "loss": 1.9654,
605
+ "step": 94
606
+ },
607
+ {
608
+ "epoch": 0.4,
609
+ "learning_rate": 0.00013760918411040356,
610
+ "loss": 1.895,
611
+ "step": 95
612
+ },
613
+ {
614
+ "epoch": 0.41,
615
+ "learning_rate": 0.00013732447116148507,
616
+ "loss": 1.902,
617
+ "step": 96
618
+ },
619
+ {
620
+ "epoch": 0.41,
621
+ "learning_rate": 0.00013703682579583614,
622
+ "loss": 1.9818,
623
+ "step": 97
624
+ },
625
+ {
626
+ "epoch": 0.42,
627
+ "learning_rate": 0.0001367462615474036,
628
+ "loss": 1.8978,
629
+ "step": 98
630
+ },
631
+ {
632
+ "epoch": 0.42,
633
+ "learning_rate": 0.0001364527920874702,
634
+ "loss": 1.887,
635
+ "step": 99
636
+ },
637
+ {
638
+ "epoch": 0.43,
639
+ "learning_rate": 0.00013615643122401113,
640
+ "loss": 1.9504,
641
+ "step": 100
642
+ },
643
+ {
644
+ "epoch": 0.43,
645
+ "eval_loss": 1.98367178440094,
646
+ "eval_runtime": 22.3432,
647
+ "eval_samples_per_second": 0.94,
648
+ "eval_steps_per_second": 0.492,
649
+ "step": 100
650
+ },
651
+ {
652
+ "epoch": 0.43,
653
+ "learning_rate": 0.0001358571929010445,
654
+ "loss": 1.7944,
655
+ "step": 101
656
+ },
657
+ {
658
+ "epoch": 0.43,
659
+ "learning_rate": 0.0001355550911979752,
660
+ "loss": 1.9889,
661
+ "step": 102
662
+ },
663
+ {
664
+ "epoch": 0.44,
665
+ "learning_rate": 0.00013525014032893256,
666
+ "loss": 1.8523,
667
+ "step": 103
668
+ },
669
+ {
670
+ "epoch": 0.44,
671
+ "learning_rate": 0.00013494235464210129,
672
+ "loss": 2.006,
673
+ "step": 104
674
+ },
675
+ {
676
+ "epoch": 0.45,
677
+ "learning_rate": 0.00013463174861904668,
678
+ "loss": 1.8311,
679
+ "step": 105
680
+ },
681
+ {
682
+ "epoch": 0.45,
683
+ "learning_rate": 0.00013431833687403314,
684
+ "loss": 1.9183,
685
+ "step": 106
686
+ },
687
+ {
688
+ "epoch": 0.46,
689
+ "learning_rate": 0.0001340021341533365,
690
+ "loss": 1.9135,
691
+ "step": 107
692
+ },
693
+ {
694
+ "epoch": 0.46,
695
+ "learning_rate": 0.00013368315533455032,
696
+ "loss": 1.8234,
697
+ "step": 108
698
+ },
699
+ {
700
+ "epoch": 0.46,
701
+ "learning_rate": 0.00013336141542588575,
702
+ "loss": 1.7729,
703
+ "step": 109
704
+ },
705
+ {
706
+ "epoch": 0.47,
707
+ "learning_rate": 0.0001330369295654655,
708
+ "loss": 1.9189,
709
+ "step": 110
710
+ },
711
+ {
712
+ "epoch": 0.47,
713
+ "learning_rate": 0.0001327097130206115,
714
+ "loss": 1.9103,
715
+ "step": 111
716
+ },
717
+ {
718
+ "epoch": 0.48,
719
+ "learning_rate": 0.00013237978118712658,
720
+ "loss": 1.8897,
721
+ "step": 112
722
+ },
723
+ {
724
+ "epoch": 0.48,
725
+ "learning_rate": 0.00013204714958857012,
726
+ "loss": 1.9789,
727
+ "step": 113
728
+ },
729
+ {
730
+ "epoch": 0.49,
731
+ "learning_rate": 0.00013171183387552764,
732
+ "loss": 1.9607,
733
+ "step": 114
734
+ },
735
+ {
736
+ "epoch": 0.49,
737
+ "learning_rate": 0.00013137384982487438,
738
+ "loss": 1.9569,
739
+ "step": 115
740
+ },
741
+ {
742
+ "epoch": 0.49,
743
+ "learning_rate": 0.00013103321333903303,
744
+ "loss": 1.9091,
745
+ "step": 116
746
+ },
747
+ {
748
+ "epoch": 0.5,
749
+ "learning_rate": 0.00013068994044522554,
750
+ "loss": 1.9789,
751
+ "step": 117
752
+ },
753
+ {
754
+ "epoch": 0.5,
755
+ "learning_rate": 0.00013034404729471893,
756
+ "loss": 1.9102,
757
+ "step": 118
758
+ },
759
+ {
760
+ "epoch": 0.51,
761
+ "learning_rate": 0.0001299955501620654,
762
+ "loss": 1.8321,
763
+ "step": 119
764
+ },
765
+ {
766
+ "epoch": 0.51,
767
+ "learning_rate": 0.00012964446544433669,
768
+ "loss": 1.9216,
769
+ "step": 120
770
+ },
771
+ {
772
+ "epoch": 0.51,
773
+ "eval_loss": 1.9825721979141235,
774
+ "eval_runtime": 22.3821,
775
+ "eval_samples_per_second": 0.938,
776
+ "eval_steps_per_second": 0.491,
777
+ "step": 120
778
+ },
779
+ {
780
+ "epoch": 0.52,
781
+ "learning_rate": 0.0001292908096603525,
782
+ "loss": 1.8591,
783
+ "step": 121
784
+ },
785
+ {
786
+ "epoch": 0.52,
787
+ "learning_rate": 0.0001289345994499032,
788
+ "loss": 1.9368,
789
+ "step": 122
790
+ },
791
+ {
792
+ "epoch": 0.52,
793
+ "learning_rate": 0.000128575851572967,
794
+ "loss": 1.9594,
795
+ "step": 123
796
+ },
797
+ {
798
+ "epoch": 0.53,
799
+ "learning_rate": 0.00012821458290892144,
800
+ "loss": 1.8731,
801
+ "step": 124
802
+ },
803
+ {
804
+ "epoch": 0.53,
805
+ "learning_rate": 0.00012785081045574913,
806
+ "loss": 1.9105,
807
+ "step": 125
808
+ },
809
+ {
810
+ "epoch": 0.54,
811
+ "learning_rate": 0.0001274845513292379,
812
+ "loss": 1.8899,
813
+ "step": 126
814
+ },
815
+ {
816
+ "epoch": 0.54,
817
+ "learning_rate": 0.00012711582276217563,
818
+ "loss": 1.9211,
819
+ "step": 127
820
+ },
821
+ {
822
+ "epoch": 0.55,
823
+ "learning_rate": 0.00012674464210353932,
824
+ "loss": 1.9506,
825
+ "step": 128
826
+ },
827
+ {
828
+ "epoch": 0.55,
829
+ "learning_rate": 0.00012637102681767895,
830
+ "loss": 1.8654,
831
+ "step": 129
832
+ },
833
+ {
834
+ "epoch": 0.55,
835
+ "learning_rate": 0.0001259949944834956,
836
+ "loss": 1.9958,
837
+ "step": 130
838
+ },
839
+ {
840
+ "epoch": 0.56,
841
+ "learning_rate": 0.00012561656279361442,
842
+ "loss": 1.9783,
843
+ "step": 131
844
+ },
845
+ {
846
+ "epoch": 0.56,
847
+ "learning_rate": 0.0001252357495535523,
848
+ "loss": 1.9314,
849
+ "step": 132
850
+ },
851
+ {
852
+ "epoch": 0.57,
853
+ "learning_rate": 0.00012485257268087983,
854
+ "loss": 1.8847,
855
+ "step": 133
856
+ },
857
+ {
858
+ "epoch": 0.57,
859
+ "learning_rate": 0.00012446705020437854,
860
+ "loss": 1.9326,
861
+ "step": 134
862
+ },
863
+ {
864
+ "epoch": 0.58,
865
+ "learning_rate": 0.00012407920026319248,
866
+ "loss": 1.9853,
867
+ "step": 135
868
+ },
869
+ {
870
+ "epoch": 0.58,
871
+ "learning_rate": 0.00012368904110597479,
872
+ "loss": 2.0078,
873
+ "step": 136
874
+ },
875
+ {
876
+ "epoch": 0.58,
877
+ "learning_rate": 0.00012329659109002906,
878
+ "loss": 2.0035,
879
+ "step": 137
880
+ },
881
+ {
882
+ "epoch": 0.59,
883
+ "learning_rate": 0.00012290186868044569,
884
+ "loss": 1.8399,
885
+ "step": 138
886
+ },
887
+ {
888
+ "epoch": 0.59,
889
+ "learning_rate": 0.00012250489244923298,
890
+ "loss": 1.8643,
891
+ "step": 139
892
+ },
893
+ {
894
+ "epoch": 0.6,
895
+ "learning_rate": 0.00012210568107444346,
896
+ "loss": 1.8483,
897
+ "step": 140
898
+ },
899
+ {
900
+ "epoch": 0.6,
901
+ "eval_loss": 1.9794269800186157,
902
+ "eval_runtime": 22.3061,
903
+ "eval_samples_per_second": 0.941,
904
+ "eval_steps_per_second": 0.493,
905
+ "step": 140
906
+ },
907
+ {
908
+ "epoch": 0.6,
909
+ "learning_rate": 0.00012170425333929485,
910
+ "loss": 1.8399,
911
+ "step": 141
912
+ },
913
+ {
914
+ "epoch": 0.6,
915
+ "learning_rate": 0.00012130062813128651,
916
+ "loss": 1.8906,
917
+ "step": 142
918
+ },
919
+ {
920
+ "epoch": 0.61,
921
+ "learning_rate": 0.00012089482444131057,
922
+ "loss": 1.9474,
923
+ "step": 143
924
+ },
925
+ {
926
+ "epoch": 0.61,
927
+ "learning_rate": 0.00012048686136275862,
928
+ "loss": 1.9107,
929
+ "step": 144
930
+ },
931
+ {
932
+ "epoch": 0.62,
933
+ "learning_rate": 0.00012007675809062313,
934
+ "loss": 2.0292,
935
+ "step": 145
936
+ },
937
+ {
938
+ "epoch": 0.62,
939
+ "learning_rate": 0.00011966453392059446,
940
+ "loss": 2.0018,
941
+ "step": 146
942
+ },
943
+ {
944
+ "epoch": 0.63,
945
+ "learning_rate": 0.00011925020824815293,
946
+ "loss": 1.9807,
947
+ "step": 147
948
+ },
949
+ {
950
+ "epoch": 0.63,
951
+ "learning_rate": 0.00011883380056765621,
952
+ "loss": 1.948,
953
+ "step": 148
954
+ },
955
+ {
956
+ "epoch": 0.63,
957
+ "learning_rate": 0.00011841533047142213,
958
+ "loss": 1.9769,
959
+ "step": 149
960
+ },
961
+ {
962
+ "epoch": 0.64,
963
+ "learning_rate": 0.00011799481764880692,
964
+ "loss": 2.0001,
965
+ "step": 150
966
+ },
967
+ {
968
+ "epoch": 0.64,
969
+ "learning_rate": 0.00011757228188527866,
970
+ "loss": 1.9211,
971
+ "step": 151
972
+ },
973
+ {
974
+ "epoch": 0.65,
975
+ "learning_rate": 0.00011714774306148647,
976
+ "loss": 1.9913,
977
+ "step": 152
978
+ },
979
+ {
980
+ "epoch": 0.65,
981
+ "learning_rate": 0.00011672122115232503,
982
+ "loss": 1.9234,
983
+ "step": 153
984
+ },
985
+ {
986
+ "epoch": 0.66,
987
+ "learning_rate": 0.00011629273622599487,
988
+ "loss": 1.9399,
989
+ "step": 154
990
+ },
991
+ {
992
+ "epoch": 0.66,
993
+ "learning_rate": 0.000115862308443058,
994
+ "loss": 1.9234,
995
+ "step": 155
996
+ },
997
+ {
998
+ "epoch": 0.66,
999
+ "learning_rate": 0.0001154299580554894,
1000
+ "loss": 2.0013,
1001
+ "step": 156
1002
+ },
1003
+ {
1004
+ "epoch": 0.67,
1005
+ "learning_rate": 0.00011499570540572424,
1006
+ "loss": 2.0099,
1007
+ "step": 157
1008
+ },
1009
+ {
1010
+ "epoch": 0.67,
1011
+ "learning_rate": 0.00011455957092570054,
1012
+ "loss": 1.8489,
1013
+ "step": 158
1014
+ },
1015
+ {
1016
+ "epoch": 0.68,
1017
+ "learning_rate": 0.00011412157513589799,
1018
+ "loss": 1.9815,
1019
+ "step": 159
1020
+ },
1021
+ {
1022
+ "epoch": 0.68,
1023
+ "learning_rate": 0.0001136817386443725,
1024
+ "loss": 1.9668,
1025
+ "step": 160
1026
+ },
1027
+ {
1028
+ "epoch": 0.68,
1029
+ "eval_loss": 1.9779595136642456,
1030
+ "eval_runtime": 22.3755,
1031
+ "eval_samples_per_second": 0.939,
1032
+ "eval_steps_per_second": 0.492,
1033
+ "step": 160
1034
+ },
1035
+ {
1036
+ "epoch": 0.69,
1037
+ "learning_rate": 0.00011324008214578636,
1038
+ "loss": 1.8557,
1039
+ "step": 161
1040
+ },
1041
+ {
1042
+ "epoch": 0.69,
1043
+ "learning_rate": 0.00011279662642043473,
1044
+ "loss": 1.8822,
1045
+ "step": 162
1046
+ },
1047
+ {
1048
+ "epoch": 0.69,
1049
+ "learning_rate": 0.00011235139233326782,
1050
+ "loss": 1.9452,
1051
+ "step": 163
1052
+ },
1053
+ {
1054
+ "epoch": 0.7,
1055
+ "learning_rate": 0.00011190440083290921,
1056
+ "loss": 1.8977,
1057
+ "step": 164
1058
+ },
1059
+ {
1060
+ "epoch": 0.7,
1061
+ "learning_rate": 0.00011145567295067023,
1062
+ "loss": 1.9694,
1063
+ "step": 165
1064
+ },
1065
+ {
1066
+ "epoch": 0.71,
1067
+ "learning_rate": 0.0001110052297995603,
1068
+ "loss": 1.9932,
1069
+ "step": 166
1070
+ },
1071
+ {
1072
+ "epoch": 0.71,
1073
+ "learning_rate": 0.00011055309257329369,
1074
+ "loss": 1.8577,
1075
+ "step": 167
1076
+ },
1077
+ {
1078
+ "epoch": 0.72,
1079
+ "learning_rate": 0.00011009928254529225,
1080
+ "loss": 1.944,
1081
+ "step": 168
1082
+ },
1083
+ {
1084
+ "epoch": 0.72,
1085
+ "learning_rate": 0.0001096438210676845,
1086
+ "loss": 1.9186,
1087
+ "step": 169
1088
+ },
1089
+ {
1090
+ "epoch": 0.72,
1091
+ "learning_rate": 0.000109186729570301,
1092
+ "loss": 1.9441,
1093
+ "step": 170
1094
+ },
1095
+ {
1096
+ "epoch": 0.73,
1097
+ "learning_rate": 0.00010872802955966606,
1098
+ "loss": 1.9223,
1099
+ "step": 171
1100
+ },
1101
+ {
1102
+ "epoch": 0.73,
1103
+ "learning_rate": 0.00010826774261798585,
1104
+ "loss": 1.863,
1105
+ "step": 172
1106
+ },
1107
+ {
1108
+ "epoch": 0.74,
1109
+ "learning_rate": 0.0001078058904021329,
1110
+ "loss": 2.0239,
1111
+ "step": 173
1112
+ },
1113
+ {
1114
+ "epoch": 0.74,
1115
+ "learning_rate": 0.00010734249464262721,
1116
+ "loss": 1.9354,
1117
+ "step": 174
1118
+ },
1119
+ {
1120
+ "epoch": 0.75,
1121
+ "learning_rate": 0.00010687757714261369,
1122
+ "loss": 1.9318,
1123
+ "step": 175
1124
+ },
1125
+ {
1126
+ "epoch": 0.75,
1127
+ "learning_rate": 0.00010641115977683641,
1128
+ "loss": 1.9005,
1129
+ "step": 176
1130
+ },
1131
+ {
1132
+ "epoch": 0.75,
1133
+ "learning_rate": 0.00010594326449060932,
1134
+ "loss": 1.9553,
1135
+ "step": 177
1136
+ },
1137
+ {
1138
+ "epoch": 0.76,
1139
+ "learning_rate": 0.00010547391329878373,
1140
+ "loss": 2.0101,
1141
+ "step": 178
1142
+ },
1143
+ {
1144
+ "epoch": 0.76,
1145
+ "learning_rate": 0.00010500312828471247,
1146
+ "loss": 1.8455,
1147
+ "step": 179
1148
+ },
1149
+ {
1150
+ "epoch": 0.77,
1151
+ "learning_rate": 0.00010453093159921094,
1152
+ "loss": 1.9776,
1153
+ "step": 180
1154
+ },
1155
+ {
1156
+ "epoch": 0.77,
1157
+ "eval_loss": 1.9778156280517578,
1158
+ "eval_runtime": 22.326,
1159
+ "eval_samples_per_second": 0.941,
1160
+ "eval_steps_per_second": 0.493,
1161
+ "step": 180
1162
+ },
1163
+ {
1164
+ "epoch": 0.77,
1165
+ "learning_rate": 0.00010405734545951468,
1166
+ "loss": 1.8919,
1167
+ "step": 181
1168
+ },
1169
+ {
1170
+ "epoch": 0.78,
1171
+ "learning_rate": 0.00010358239214823427,
1172
+ "loss": 1.9612,
1173
+ "step": 182
1174
+ },
1175
+ {
1176
+ "epoch": 0.78,
1177
+ "learning_rate": 0.00010310609401230684,
1178
+ "loss": 1.9871,
1179
+ "step": 183
1180
+ },
1181
+ {
1182
+ "epoch": 0.78,
1183
+ "learning_rate": 0.00010262847346194452,
1184
+ "loss": 1.8808,
1185
+ "step": 184
1186
+ },
1187
+ {
1188
+ "epoch": 0.79,
1189
+ "learning_rate": 0.00010214955296958019,
1190
+ "loss": 1.8487,
1191
+ "step": 185
1192
+ },
1193
+ {
1194
+ "epoch": 0.79,
1195
+ "learning_rate": 0.00010166935506880997,
1196
+ "loss": 1.9151,
1197
+ "step": 186
1198
+ },
1199
+ {
1200
+ "epoch": 0.8,
1201
+ "learning_rate": 0.00010118790235333316,
1202
+ "loss": 1.949,
1203
+ "step": 187
1204
+ },
1205
+ {
1206
+ "epoch": 0.8,
1207
+ "learning_rate": 0.00010070521747588906,
1208
+ "loss": 1.9736,
1209
+ "step": 188
1210
+ },
1211
+ {
1212
+ "epoch": 0.81,
1213
+ "learning_rate": 0.00010022132314719119,
1214
+ "loss": 1.891,
1215
+ "step": 189
1216
+ },
1217
+ {
1218
+ "epoch": 0.81,
1219
+ "learning_rate": 9.973624213485876e-05,
1220
+ "loss": 1.9049,
1221
+ "step": 190
1222
+ },
1223
+ {
1224
+ "epoch": 0.81,
1225
+ "learning_rate": 9.924999726234535e-05,
1226
+ "loss": 1.8852,
1227
+ "step": 191
1228
+ },
1229
+ {
1230
+ "epoch": 0.82,
1231
+ "learning_rate": 9.876261140786512e-05,
1232
+ "loss": 1.8468,
1233
+ "step": 192
1234
+ },
1235
+ {
1236
+ "epoch": 0.82,
1237
+ "learning_rate": 9.82741075033164e-05,
1238
+ "loss": 1.9972,
1239
+ "step": 193
1240
+ },
1241
+ {
1242
+ "epoch": 0.83,
1243
+ "learning_rate": 9.77845085332026e-05,
1244
+ "loss": 1.9918,
1245
+ "step": 194
1246
+ },
1247
+ {
1248
+ "epoch": 0.83,
1249
+ "learning_rate": 9.729383753355093e-05,
1250
+ "loss": 1.9932,
1251
+ "step": 195
1252
+ },
1253
+ {
1254
+ "epoch": 0.83,
1255
+ "learning_rate": 9.68021175908284e-05,
1256
+ "loss": 1.9282,
1257
+ "step": 196
1258
+ },
1259
+ {
1260
+ "epoch": 0.84,
1261
+ "learning_rate": 9.630937184085566e-05,
1262
+ "loss": 2.0343,
1263
+ "step": 197
1264
+ },
1265
+ {
1266
+ "epoch": 0.84,
1267
+ "learning_rate": 9.581562346771841e-05,
1268
+ "loss": 1.8442,
1269
+ "step": 198
1270
+ },
1271
+ {
1272
+ "epoch": 0.85,
1273
+ "learning_rate": 9.532089570267661e-05,
1274
+ "loss": 1.8367,
1275
+ "step": 199
1276
+ },
1277
+ {
1278
+ "epoch": 0.85,
1279
+ "learning_rate": 9.482521182307136e-05,
1280
+ "loss": 1.9312,
1281
+ "step": 200
1282
+ },
1283
+ {
1284
+ "epoch": 0.85,
1285
+ "eval_loss": 1.977174162864685,
1286
+ "eval_runtime": 22.3424,
1287
+ "eval_samples_per_second": 0.94,
1288
+ "eval_steps_per_second": 0.492,
1289
+ "step": 200
1290
+ },
1291
+ {
1292
+ "epoch": 0.86,
1293
+ "learning_rate": 9.432859515122974e-05,
1294
+ "loss": 1.9262,
1295
+ "step": 201
1296
+ },
1297
+ {
1298
+ "epoch": 0.86,
1299
+ "learning_rate": 9.383106905336748e-05,
1300
+ "loss": 1.8701,
1301
+ "step": 202
1302
+ },
1303
+ {
1304
+ "epoch": 0.86,
1305
+ "learning_rate": 9.33326569384895e-05,
1306
+ "loss": 1.974,
1307
+ "step": 203
1308
+ },
1309
+ {
1310
+ "epoch": 0.87,
1311
+ "learning_rate": 9.283338225728854e-05,
1312
+ "loss": 1.8317,
1313
+ "step": 204
1314
+ },
1315
+ {
1316
+ "epoch": 0.87,
1317
+ "learning_rate": 9.233326850104182e-05,
1318
+ "loss": 1.9642,
1319
+ "step": 205
1320
+ },
1321
+ {
1322
+ "epoch": 0.88,
1323
+ "learning_rate": 9.18323392005057e-05,
1324
+ "loss": 1.893,
1325
+ "step": 206
1326
+ },
1327
+ {
1328
+ "epoch": 0.88,
1329
+ "learning_rate": 9.133061792480855e-05,
1330
+ "loss": 1.911,
1331
+ "step": 207
1332
+ },
1333
+ {
1334
+ "epoch": 0.89,
1335
+ "learning_rate": 9.08281282803418e-05,
1336
+ "loss": 1.8981,
1337
+ "step": 208
1338
+ },
1339
+ {
1340
+ "epoch": 0.89,
1341
+ "learning_rate": 9.03248939096493e-05,
1342
+ "loss": 1.928,
1343
+ "step": 209
1344
+ },
1345
+ {
1346
+ "epoch": 0.89,
1347
+ "learning_rate": 8.982093849031479e-05,
1348
+ "loss": 1.8451,
1349
+ "step": 210
1350
+ },
1351
+ {
1352
+ "epoch": 0.9,
1353
+ "learning_rate": 8.931628573384802e-05,
1354
+ "loss": 1.8178,
1355
+ "step": 211
1356
+ },
1357
+ {
1358
+ "epoch": 0.9,
1359
+ "learning_rate": 8.881095938456899e-05,
1360
+ "loss": 1.8732,
1361
+ "step": 212
1362
+ },
1363
+ {
1364
+ "epoch": 0.91,
1365
+ "learning_rate": 8.830498321849071e-05,
1366
+ "loss": 1.9206,
1367
+ "step": 213
1368
+ },
1369
+ {
1370
+ "epoch": 0.91,
1371
+ "learning_rate": 8.77983810422007e-05,
1372
+ "loss": 1.9657,
1373
+ "step": 214
1374
+ },
1375
+ {
1376
+ "epoch": 0.92,
1377
+ "learning_rate": 8.72911766917407e-05,
1378
+ "loss": 1.7979,
1379
+ "step": 215
1380
+ },
1381
+ {
1382
+ "epoch": 0.92,
1383
+ "learning_rate": 8.678339403148527e-05,
1384
+ "loss": 1.9761,
1385
+ "step": 216
1386
+ },
1387
+ {
1388
+ "epoch": 0.92,
1389
+ "learning_rate": 8.62750569530189e-05,
1390
+ "loss": 1.9357,
1391
+ "step": 217
1392
+ },
1393
+ {
1394
+ "epoch": 0.93,
1395
+ "learning_rate": 8.576618937401188e-05,
1396
+ "loss": 1.9625,
1397
+ "step": 218
1398
+ },
1399
+ {
1400
+ "epoch": 0.93,
1401
+ "learning_rate": 8.525681523709503e-05,
1402
+ "loss": 1.9171,
1403
+ "step": 219
1404
+ },
1405
+ {
1406
+ "epoch": 0.94,
1407
+ "learning_rate": 8.474695850873308e-05,
1408
+ "loss": 1.9003,
1409
+ "step": 220
1410
+ },
1411
+ {
1412
+ "epoch": 0.94,
1413
+ "eval_loss": 1.9738101959228516,
1414
+ "eval_runtime": 22.3535,
1415
+ "eval_samples_per_second": 0.939,
1416
+ "eval_steps_per_second": 0.492,
1417
+ "step": 220
1418
+ },
1419
+ {
1420
+ "epoch": 0.94,
1421
+ "learning_rate": 8.423664317809711e-05,
1422
+ "loss": 1.9968,
1423
+ "step": 221
1424
+ },
1425
+ {
1426
+ "epoch": 0.95,
1427
+ "learning_rate": 8.372589325593579e-05,
1428
+ "loss": 1.9338,
1429
+ "step": 222
1430
+ },
1431
+ {
1432
+ "epoch": 0.95,
1433
+ "learning_rate": 8.321473277344569e-05,
1434
+ "loss": 1.943,
1435
+ "step": 223
1436
+ },
1437
+ {
1438
+ "epoch": 0.95,
1439
+ "learning_rate": 8.270318578114052e-05,
1440
+ "loss": 1.9167,
1441
+ "step": 224
1442
+ },
1443
+ {
1444
+ "epoch": 0.96,
1445
+ "learning_rate": 8.219127634771965e-05,
1446
+ "loss": 2.0213,
1447
+ "step": 225
1448
+ },
1449
+ {
1450
+ "epoch": 0.96,
1451
+ "learning_rate": 8.167902855893561e-05,
1452
+ "loss": 1.9531,
1453
+ "step": 226
1454
+ },
1455
+ {
1456
+ "epoch": 0.97,
1457
+ "learning_rate": 8.116646651646079e-05,
1458
+ "loss": 1.9225,
1459
+ "step": 227
1460
+ },
1461
+ {
1462
+ "epoch": 0.97,
1463
+ "learning_rate": 8.065361433675343e-05,
1464
+ "loss": 1.894,
1465
+ "step": 228
1466
+ },
1467
+ {
1468
+ "epoch": 0.98,
1469
+ "learning_rate": 8.014049614992304e-05,
1470
+ "loss": 1.9129,
1471
+ "step": 229
1472
+ },
1473
+ {
1474
+ "epoch": 0.98,
1475
+ "learning_rate": 7.962713609859492e-05,
1476
+ "loss": 1.8996,
1477
+ "step": 230
1478
+ },
1479
+ {
1480
+ "epoch": 0.98,
1481
+ "learning_rate": 7.911355833677434e-05,
1482
+ "loss": 1.8093,
1483
+ "step": 231
1484
+ },
1485
+ {
1486
+ "epoch": 0.99,
1487
+ "learning_rate": 7.859978702871e-05,
1488
+ "loss": 1.9467,
1489
+ "step": 232
1490
+ },
1491
+ {
1492
+ "epoch": 0.99,
1493
+ "learning_rate": 7.808584634775706e-05,
1494
+ "loss": 1.9645,
1495
+ "step": 233
1496
+ },
1497
+ {
1498
+ "epoch": 1.0,
1499
+ "learning_rate": 7.757176047523993e-05,
1500
+ "loss": 1.8858,
1501
+ "step": 234
1502
+ },
1503
+ {
1504
+ "epoch": 1.0,
1505
+ "learning_rate": 7.705755359931425e-05,
1506
+ "loss": 1.9792,
1507
+ "step": 235
1508
+ },
1509
+ {
1510
+ "epoch": 1.01,
1511
+ "learning_rate": 7.654324991382911e-05,
1512
+ "loss": 1.8603,
1513
+ "step": 236
1514
+ },
1515
+ {
1516
+ "epoch": 1.01,
1517
+ "learning_rate": 7.602887361718846e-05,
1518
+ "loss": 1.8728,
1519
+ "step": 237
1520
+ },
1521
+ {
1522
+ "epoch": 1.01,
1523
+ "learning_rate": 7.551444891121271e-05,
1524
+ "loss": 1.9343,
1525
+ "step": 238
1526
+ },
1527
+ {
1528
+ "epoch": 1.02,
1529
+ "learning_rate": 7.5e-05,
1530
+ "loss": 1.8709,
1531
+ "step": 239
1532
+ },
1533
+ {
1534
+ "epoch": 1.02,
1535
+ "learning_rate": 7.448555108878729e-05,
1536
+ "loss": 1.8748,
1537
+ "step": 240
1538
+ },
1539
+ {
1540
+ "epoch": 1.02,
1541
+ "eval_loss": 1.9729036092758179,
1542
+ "eval_runtime": 22.3833,
1543
+ "eval_samples_per_second": 0.938,
1544
+ "eval_steps_per_second": 0.491,
1545
+ "step": 240
1546
+ },
1547
+ {
1548
+ "epoch": 1.03,
1549
+ "learning_rate": 7.397112638281155e-05,
1550
+ "loss": 1.8892,
1551
+ "step": 241
1552
+ },
1553
+ {
1554
+ "epoch": 1.03,
1555
+ "learning_rate": 7.34567500861709e-05,
1556
+ "loss": 1.8739,
1557
+ "step": 242
1558
+ },
1559
+ {
1560
+ "epoch": 1.04,
1561
+ "learning_rate": 7.294244640068574e-05,
1562
+ "loss": 1.9051,
1563
+ "step": 243
1564
+ },
1565
+ {
1566
+ "epoch": 1.04,
1567
+ "learning_rate": 7.242823952476008e-05,
1568
+ "loss": 1.9143,
1569
+ "step": 244
1570
+ },
1571
+ {
1572
+ "epoch": 1.04,
1573
+ "learning_rate": 7.191415365224291e-05,
1574
+ "loss": 1.8451,
1575
+ "step": 245
1576
+ },
1577
+ {
1578
+ "epoch": 1.05,
1579
+ "learning_rate": 7.140021297129e-05,
1580
+ "loss": 1.9218,
1581
+ "step": 246
1582
+ },
1583
+ {
1584
+ "epoch": 1.05,
1585
+ "learning_rate": 7.088644166322564e-05,
1586
+ "loss": 1.9967,
1587
+ "step": 247
1588
+ },
1589
+ {
1590
+ "epoch": 1.06,
1591
+ "learning_rate": 7.037286390140507e-05,
1592
+ "loss": 1.9096,
1593
+ "step": 248
1594
+ },
1595
+ {
1596
+ "epoch": 1.06,
1597
+ "learning_rate": 6.985950385007695e-05,
1598
+ "loss": 1.9184,
1599
+ "step": 249
1600
+ },
1601
+ {
1602
+ "epoch": 1.06,
1603
+ "learning_rate": 6.934638566324657e-05,
1604
+ "loss": 1.8985,
1605
+ "step": 250
1606
+ },
1607
+ {
1608
+ "epoch": 1.07,
1609
+ "learning_rate": 6.883353348353921e-05,
1610
+ "loss": 1.9459,
1611
+ "step": 251
1612
+ },
1613
+ {
1614
+ "epoch": 1.07,
1615
+ "learning_rate": 6.832097144106439e-05,
1616
+ "loss": 1.9131,
1617
+ "step": 252
1618
+ },
1619
+ {
1620
+ "epoch": 1.08,
1621
+ "learning_rate": 6.780872365228035e-05,
1622
+ "loss": 1.8293,
1623
+ "step": 253
1624
+ },
1625
+ {
1626
+ "epoch": 1.08,
1627
+ "learning_rate": 6.729681421885948e-05,
1628
+ "loss": 1.761,
1629
+ "step": 254
1630
+ },
1631
+ {
1632
+ "epoch": 1.09,
1633
+ "learning_rate": 6.678526722655434e-05,
1634
+ "loss": 1.9771,
1635
+ "step": 255
1636
+ },
1637
+ {
1638
+ "epoch": 1.09,
1639
+ "learning_rate": 6.62741067440642e-05,
1640
+ "loss": 1.9144,
1641
+ "step": 256
1642
+ },
1643
+ {
1644
+ "epoch": 1.09,
1645
+ "learning_rate": 6.576335682190289e-05,
1646
+ "loss": 2.0206,
1647
+ "step": 257
1648
+ },
1649
+ {
1650
+ "epoch": 1.1,
1651
+ "learning_rate": 6.525304149126689e-05,
1652
+ "loss": 1.8551,
1653
+ "step": 258
1654
+ },
1655
+ {
1656
+ "epoch": 1.1,
1657
+ "learning_rate": 6.474318476290497e-05,
1658
+ "loss": 1.8601,
1659
+ "step": 259
1660
+ },
1661
+ {
1662
+ "epoch": 1.11,
1663
+ "learning_rate": 6.423381062598808e-05,
1664
+ "loss": 1.8896,
1665
+ "step": 260
1666
+ },
1667
+ {
1668
+ "epoch": 1.11,
1669
+ "eval_loss": 1.9744987487792969,
1670
+ "eval_runtime": 22.4357,
1671
+ "eval_samples_per_second": 0.936,
1672
+ "eval_steps_per_second": 0.49,
1673
+ "step": 260
1674
+ },
1675
+ {
1676
+ "epoch": 1.11,
1677
+ "learning_rate": 6.37249430469811e-05,
1678
+ "loss": 1.9185,
1679
+ "step": 261
1680
+ },
1681
+ {
1682
+ "epoch": 1.12,
1683
+ "learning_rate": 6.321660596851473e-05,
1684
+ "loss": 1.8958,
1685
+ "step": 262
1686
+ },
1687
+ {
1688
+ "epoch": 1.12,
1689
+ "learning_rate": 6.270882330825929e-05,
1690
+ "loss": 1.7275,
1691
+ "step": 263
1692
+ },
1693
+ {
1694
+ "epoch": 1.12,
1695
+ "learning_rate": 6.220161895779932e-05,
1696
+ "loss": 1.9558,
1697
+ "step": 264
1698
+ },
1699
+ {
1700
+ "epoch": 1.13,
1701
+ "learning_rate": 6.169501678150929e-05,
1702
+ "loss": 1.8161,
1703
+ "step": 265
1704
+ },
1705
+ {
1706
+ "epoch": 1.13,
1707
+ "learning_rate": 6.118904061543104e-05,
1708
+ "loss": 1.8169,
1709
+ "step": 266
1710
+ },
1711
+ {
1712
+ "epoch": 1.14,
1713
+ "learning_rate": 6.068371426615195e-05,
1714
+ "loss": 1.9121,
1715
+ "step": 267
1716
+ },
1717
+ {
1718
+ "epoch": 1.14,
1719
+ "learning_rate": 6.01790615096852e-05,
1720
+ "loss": 1.8881,
1721
+ "step": 268
1722
+ },
1723
+ {
1724
+ "epoch": 1.15,
1725
+ "learning_rate": 5.967510609035069e-05,
1726
+ "loss": 1.8207,
1727
+ "step": 269
1728
+ },
1729
+ {
1730
+ "epoch": 1.15,
1731
+ "learning_rate": 5.9171871719658195e-05,
1732
+ "loss": 1.8221,
1733
+ "step": 270
1734
+ },
1735
+ {
1736
+ "epoch": 1.15,
1737
+ "learning_rate": 5.8669382075191435e-05,
1738
+ "loss": 2.01,
1739
+ "step": 271
1740
+ },
1741
+ {
1742
+ "epoch": 1.16,
1743
+ "learning_rate": 5.816766079949429e-05,
1744
+ "loss": 1.8417,
1745
+ "step": 272
1746
+ },
1747
+ {
1748
+ "epoch": 1.16,
1749
+ "learning_rate": 5.766673149895817e-05,
1750
+ "loss": 1.8548,
1751
+ "step": 273
1752
+ },
1753
+ {
1754
+ "epoch": 1.17,
1755
+ "learning_rate": 5.716661774271146e-05,
1756
+ "loss": 1.7782,
1757
+ "step": 274
1758
+ },
1759
+ {
1760
+ "epoch": 1.17,
1761
+ "learning_rate": 5.666734306151051e-05,
1762
+ "loss": 1.7943,
1763
+ "step": 275
1764
+ },
1765
+ {
1766
+ "epoch": 1.18,
1767
+ "learning_rate": 5.616893094663252e-05,
1768
+ "loss": 1.9164,
1769
+ "step": 276
1770
+ },
1771
+ {
1772
+ "epoch": 1.18,
1773
+ "learning_rate": 5.567140484877025e-05,
1774
+ "loss": 1.8524,
1775
+ "step": 277
1776
+ },
1777
+ {
1778
+ "epoch": 1.18,
1779
+ "learning_rate": 5.517478817692863e-05,
1780
+ "loss": 1.8409,
1781
+ "step": 278
1782
+ },
1783
+ {
1784
+ "epoch": 1.19,
1785
+ "learning_rate": 5.467910429732337e-05,
1786
+ "loss": 1.8424,
1787
+ "step": 279
1788
+ },
1789
+ {
1790
+ "epoch": 1.19,
1791
+ "learning_rate": 5.418437653228157e-05,
1792
+ "loss": 1.8702,
1793
+ "step": 280
1794
+ },
1795
+ {
1796
+ "epoch": 1.19,
1797
+ "eval_loss": 1.9760392904281616,
1798
+ "eval_runtime": 22.4195,
1799
+ "eval_samples_per_second": 0.937,
1800
+ "eval_steps_per_second": 0.491,
1801
+ "step": 280
1802
+ },
1803
+ {
1804
+ "epoch": 1.2,
1805
+ "learning_rate": 5.3690628159144325e-05,
1806
+ "loss": 2.0462,
1807
+ "step": 281
1808
+ },
1809
+ {
1810
+ "epoch": 1.2,
1811
+ "learning_rate": 5.3197882409171596e-05,
1812
+ "loss": 1.8796,
1813
+ "step": 282
1814
+ },
1815
+ {
1816
+ "epoch": 1.21,
1817
+ "learning_rate": 5.270616246644906e-05,
1818
+ "loss": 1.8839,
1819
+ "step": 283
1820
+ },
1821
+ {
1822
+ "epoch": 1.21,
1823
+ "learning_rate": 5.22154914667974e-05,
1824
+ "loss": 1.9264,
1825
+ "step": 284
1826
+ },
1827
+ {
1828
+ "epoch": 1.21,
1829
+ "learning_rate": 5.1725892496683603e-05,
1830
+ "loss": 1.8427,
1831
+ "step": 285
1832
+ },
1833
+ {
1834
+ "epoch": 1.22,
1835
+ "learning_rate": 5.123738859213488e-05,
1836
+ "loss": 1.8135,
1837
+ "step": 286
1838
+ },
1839
+ {
1840
+ "epoch": 1.22,
1841
+ "learning_rate": 5.075000273765464e-05,
1842
+ "loss": 1.9278,
1843
+ "step": 287
1844
+ },
1845
+ {
1846
+ "epoch": 1.23,
1847
+ "learning_rate": 5.026375786514124e-05,
1848
+ "loss": 1.9071,
1849
+ "step": 288
1850
+ },
1851
+ {
1852
+ "epoch": 1.23,
1853
+ "learning_rate": 4.977867685280878e-05,
1854
+ "loss": 1.8818,
1855
+ "step": 289
1856
+ },
1857
+ {
1858
+ "epoch": 1.24,
1859
+ "learning_rate": 4.929478252411093e-05,
1860
+ "loss": 1.8212,
1861
+ "step": 290
1862
+ },
1863
+ {
1864
+ "epoch": 1.24,
1865
+ "learning_rate": 4.8812097646666814e-05,
1866
+ "loss": 1.8524,
1867
+ "step": 291
1868
+ },
1869
+ {
1870
+ "epoch": 1.24,
1871
+ "learning_rate": 4.833064493119003e-05,
1872
+ "loss": 1.908,
1873
+ "step": 292
1874
+ },
1875
+ {
1876
+ "epoch": 1.25,
1877
+ "learning_rate": 4.78504470304198e-05,
1878
+ "loss": 1.9019,
1879
+ "step": 293
1880
+ },
1881
+ {
1882
+ "epoch": 1.25,
1883
+ "learning_rate": 4.737152653805547e-05,
1884
+ "loss": 1.8236,
1885
+ "step": 294
1886
+ },
1887
+ {
1888
+ "epoch": 1.26,
1889
+ "learning_rate": 4.689390598769318e-05,
1890
+ "loss": 1.8018,
1891
+ "step": 295
1892
+ },
1893
+ {
1894
+ "epoch": 1.26,
1895
+ "learning_rate": 4.6417607851765713e-05,
1896
+ "loss": 1.949,
1897
+ "step": 296
1898
+ },
1899
+ {
1900
+ "epoch": 1.27,
1901
+ "learning_rate": 4.594265454048534e-05,
1902
+ "loss": 1.7592,
1903
+ "step": 297
1904
+ },
1905
+ {
1906
+ "epoch": 1.27,
1907
+ "learning_rate": 4.546906840078906e-05,
1908
+ "loss": 1.7839,
1909
+ "step": 298
1910
+ },
1911
+ {
1912
+ "epoch": 1.27,
1913
+ "learning_rate": 4.499687171528751e-05,
1914
+ "loss": 1.9742,
1915
+ "step": 299
1916
+ },
1917
+ {
1918
+ "epoch": 1.28,
1919
+ "learning_rate": 4.452608670121626e-05,
1920
+ "loss": 1.9038,
1921
+ "step": 300
1922
+ },
1923
+ {
1924
+ "epoch": 1.28,
1925
+ "eval_loss": 1.9769610166549683,
1926
+ "eval_runtime": 22.4091,
1927
+ "eval_samples_per_second": 0.937,
1928
+ "eval_steps_per_second": 0.491,
1929
+ "step": 300
1930
+ },
1931
+ {
1932
+ "epoch": 1.28,
1933
+ "learning_rate": 4.405673550939067e-05,
1934
+ "loss": 1.985,
1935
+ "step": 301
1936
+ },
1937
+ {
1938
+ "epoch": 1.29,
1939
+ "learning_rate": 4.358884022316357e-05,
1940
+ "loss": 1.8455,
1941
+ "step": 302
1942
+ },
1943
+ {
1944
+ "epoch": 1.29,
1945
+ "learning_rate": 4.312242285738632e-05,
1946
+ "loss": 1.9568,
1947
+ "step": 303
1948
+ },
1949
+ {
1950
+ "epoch": 1.29,
1951
+ "learning_rate": 4.265750535737277e-05,
1952
+ "loss": 1.9033,
1953
+ "step": 304
1954
+ },
1955
+ {
1956
+ "epoch": 1.3,
1957
+ "learning_rate": 4.219410959786711e-05,
1958
+ "loss": 1.8248,
1959
+ "step": 305
1960
+ },
1961
+ {
1962
+ "epoch": 1.3,
1963
+ "learning_rate": 4.173225738201416e-05,
1964
+ "loss": 1.9086,
1965
+ "step": 306
1966
+ },
1967
+ {
1968
+ "epoch": 1.31,
1969
+ "learning_rate": 4.127197044033395e-05,
1970
+ "loss": 1.8149,
1971
+ "step": 307
1972
+ },
1973
+ {
1974
+ "epoch": 1.31,
1975
+ "learning_rate": 4.081327042969902e-05,
1976
+ "loss": 1.7981,
1977
+ "step": 308
1978
+ },
1979
+ {
1980
+ "epoch": 1.32,
1981
+ "learning_rate": 4.035617893231551e-05,
1982
+ "loss": 1.8754,
1983
+ "step": 309
1984
+ },
1985
+ {
1986
+ "epoch": 1.32,
1987
+ "learning_rate": 3.990071745470775e-05,
1988
+ "loss": 1.9377,
1989
+ "step": 310
1990
+ },
1991
+ {
1992
+ "epoch": 1.32,
1993
+ "learning_rate": 3.94469074267063e-05,
1994
+ "loss": 1.884,
1995
+ "step": 311
1996
+ },
1997
+ {
1998
+ "epoch": 1.33,
1999
+ "learning_rate": 3.899477020043969e-05,
2000
+ "loss": 1.9137,
2001
+ "step": 312
2002
+ },
2003
+ {
2004
+ "epoch": 1.33,
2005
+ "learning_rate": 3.854432704932976e-05,
2006
+ "loss": 1.9039,
2007
+ "step": 313
2008
+ },
2009
+ {
2010
+ "epoch": 1.34,
2011
+ "learning_rate": 3.809559916709077e-05,
2012
+ "loss": 1.9033,
2013
+ "step": 314
2014
+ },
2015
+ {
2016
+ "epoch": 1.34,
2017
+ "learning_rate": 3.764860766673218e-05,
2018
+ "loss": 1.8714,
2019
+ "step": 315
2020
+ },
2021
+ {
2022
+ "epoch": 1.35,
2023
+ "learning_rate": 3.720337357956528e-05,
2024
+ "loss": 1.8951,
2025
+ "step": 316
2026
+ },
2027
+ {
2028
+ "epoch": 1.35,
2029
+ "learning_rate": 3.6759917854213645e-05,
2030
+ "loss": 1.9186,
2031
+ "step": 317
2032
+ },
2033
+ {
2034
+ "epoch": 1.35,
2035
+ "learning_rate": 3.63182613556275e-05,
2036
+ "loss": 1.7962,
2037
+ "step": 318
2038
+ },
2039
+ {
2040
+ "epoch": 1.36,
2041
+ "learning_rate": 3.5878424864101994e-05,
2042
+ "loss": 2.0042,
2043
+ "step": 319
2044
+ },
2045
+ {
2046
+ "epoch": 1.36,
2047
+ "learning_rate": 3.5440429074299467e-05,
2048
+ "loss": 1.9083,
2049
+ "step": 320
2050
+ },
2051
+ {
2052
+ "epoch": 1.36,
2053
+ "eval_loss": 1.9758033752441406,
2054
+ "eval_runtime": 22.5009,
2055
+ "eval_samples_per_second": 0.933,
2056
+ "eval_steps_per_second": 0.489,
2057
+ "step": 320
2058
+ },
2059
+ {
2060
+ "epoch": 1.37,
2061
+ "learning_rate": 3.500429459427576e-05,
2062
+ "loss": 1.8479,
2063
+ "step": 321
2064
+ },
2065
+ {
2066
+ "epoch": 1.37,
2067
+ "learning_rate": 3.457004194451057e-05,
2068
+ "loss": 1.7468,
2069
+ "step": 322
2070
+ },
2071
+ {
2072
+ "epoch": 1.38,
2073
+ "learning_rate": 3.413769155694198e-05,
2074
+ "loss": 1.9424,
2075
+ "step": 323
2076
+ },
2077
+ {
2078
+ "epoch": 1.38,
2079
+ "learning_rate": 3.3707263774005114e-05,
2080
+ "loss": 1.884,
2081
+ "step": 324
2082
+ },
2083
+ {
2084
+ "epoch": 1.38,
2085
+ "learning_rate": 3.3278778847674955e-05,
2086
+ "loss": 1.8818,
2087
+ "step": 325
2088
+ },
2089
+ {
2090
+ "epoch": 1.39,
2091
+ "learning_rate": 3.285225693851353e-05,
2092
+ "loss": 2.0568,
2093
+ "step": 326
2094
+ },
2095
+ {
2096
+ "epoch": 1.39,
2097
+ "learning_rate": 3.242771811472133e-05,
2098
+ "loss": 1.7878,
2099
+ "step": 327
2100
+ },
2101
+ {
2102
+ "epoch": 1.4,
2103
+ "learning_rate": 3.200518235119309e-05,
2104
+ "loss": 1.9778,
2105
+ "step": 328
2106
+ },
2107
+ {
2108
+ "epoch": 1.4,
2109
+ "learning_rate": 3.1584669528577844e-05,
2110
+ "loss": 1.8374,
2111
+ "step": 329
2112
+ },
2113
+ {
2114
+ "epoch": 1.41,
2115
+ "learning_rate": 3.116619943234381e-05,
2116
+ "loss": 1.8882,
2117
+ "step": 330
2118
+ },
2119
+ {
2120
+ "epoch": 1.41,
2121
+ "learning_rate": 3.0749791751847054e-05,
2122
+ "loss": 1.7488,
2123
+ "step": 331
2124
+ },
2125
+ {
2126
+ "epoch": 1.41,
2127
+ "learning_rate": 3.033546607940554e-05,
2128
+ "loss": 1.9094,
2129
+ "step": 332
2130
+ },
2131
+ {
2132
+ "epoch": 1.42,
2133
+ "learning_rate": 2.992324190937685e-05,
2134
+ "loss": 1.8427,
2135
+ "step": 333
2136
+ },
2137
+ {
2138
+ "epoch": 1.42,
2139
+ "learning_rate": 2.9513138637241383e-05,
2140
+ "loss": 1.8053,
2141
+ "step": 334
2142
+ },
2143
+ {
2144
+ "epoch": 1.43,
2145
+ "learning_rate": 2.9105175558689402e-05,
2146
+ "loss": 1.839,
2147
+ "step": 335
2148
+ },
2149
+ {
2150
+ "epoch": 1.43,
2151
+ "learning_rate": 2.8699371868713507e-05,
2152
+ "loss": 1.8546,
2153
+ "step": 336
2154
+ },
2155
+ {
2156
+ "epoch": 1.44,
2157
+ "learning_rate": 2.829574666070512e-05,
2158
+ "loss": 1.9441,
2159
+ "step": 337
2160
+ },
2161
+ {
2162
+ "epoch": 1.44,
2163
+ "learning_rate": 2.7894318925556538e-05,
2164
+ "loss": 1.8422,
2165
+ "step": 338
2166
+ },
2167
+ {
2168
+ "epoch": 1.44,
2169
+ "learning_rate": 2.749510755076701e-05,
2170
+ "loss": 1.966,
2171
+ "step": 339
2172
+ },
2173
+ {
2174
+ "epoch": 1.45,
2175
+ "learning_rate": 2.709813131955433e-05,
2176
+ "loss": 1.8143,
2177
+ "step": 340
2178
+ },
2179
+ {
2180
+ "epoch": 1.45,
2181
+ "eval_loss": 1.975573182106018,
2182
+ "eval_runtime": 22.5104,
2183
+ "eval_samples_per_second": 0.933,
2184
+ "eval_steps_per_second": 0.489,
2185
+ "step": 340
2186
+ },
2187
+ {
2188
+ "epoch": 1.45,
2189
+ "learning_rate": 2.670340890997096e-05,
2190
+ "loss": 1.935,
2191
+ "step": 341
2192
+ },
2193
+ {
2194
+ "epoch": 1.46,
2195
+ "learning_rate": 2.6310958894025232e-05,
2196
+ "loss": 1.9234,
2197
+ "step": 342
2198
+ },
2199
+ {
2200
+ "epoch": 1.46,
2201
+ "learning_rate": 2.5920799736807518e-05,
2202
+ "loss": 1.8302,
2203
+ "step": 343
2204
+ },
2205
+ {
2206
+ "epoch": 1.47,
2207
+ "learning_rate": 2.553294979562145e-05,
2208
+ "loss": 1.9349,
2209
+ "step": 344
2210
+ },
2211
+ {
2212
+ "epoch": 1.47,
2213
+ "learning_rate": 2.514742731912016e-05,
2214
+ "loss": 1.9799,
2215
+ "step": 345
2216
+ },
2217
+ {
2218
+ "epoch": 1.47,
2219
+ "learning_rate": 2.4764250446447674e-05,
2220
+ "loss": 1.9203,
2221
+ "step": 346
2222
+ },
2223
+ {
2224
+ "epoch": 1.48,
2225
+ "learning_rate": 2.438343720638556e-05,
2226
+ "loss": 1.8142,
2227
+ "step": 347
2228
+ },
2229
+ {
2230
+ "epoch": 1.48,
2231
+ "learning_rate": 2.400500551650439e-05,
2232
+ "loss": 1.8516,
2233
+ "step": 348
2234
+ },
2235
+ {
2236
+ "epoch": 1.49,
2237
+ "learning_rate": 2.362897318232105e-05,
2238
+ "loss": 1.8775,
2239
+ "step": 349
2240
+ },
2241
+ {
2242
+ "epoch": 1.49,
2243
+ "learning_rate": 2.3255357896460677e-05,
2244
+ "loss": 1.8747,
2245
+ "step": 350
2246
+ },
2247
+ {
2248
+ "epoch": 1.5,
2249
+ "learning_rate": 2.288417723782438e-05,
2250
+ "loss": 1.9202,
2251
+ "step": 351
2252
+ },
2253
+ {
2254
+ "epoch": 1.5,
2255
+ "learning_rate": 2.2515448670762094e-05,
2256
+ "loss": 1.8682,
2257
+ "step": 352
2258
+ },
2259
+ {
2260
+ "epoch": 1.5,
2261
+ "learning_rate": 2.214918954425086e-05,
2262
+ "loss": 1.8448,
2263
+ "step": 353
2264
+ },
2265
+ {
2266
+ "epoch": 1.51,
2267
+ "learning_rate": 2.1785417091078532e-05,
2268
+ "loss": 1.9669,
2269
+ "step": 354
2270
+ },
2271
+ {
2272
+ "epoch": 1.51,
2273
+ "learning_rate": 2.1424148427032994e-05,
2274
+ "loss": 1.8644,
2275
+ "step": 355
2276
+ },
2277
+ {
2278
+ "epoch": 1.52,
2279
+ "learning_rate": 2.1065400550096816e-05,
2280
+ "loss": 1.799,
2281
+ "step": 356
2282
+ },
2283
+ {
2284
+ "epoch": 1.52,
2285
+ "learning_rate": 2.0709190339647494e-05,
2286
+ "loss": 1.7759,
2287
+ "step": 357
2288
+ },
2289
+ {
2290
+ "epoch": 1.53,
2291
+ "learning_rate": 2.035553455566328e-05,
2292
+ "loss": 1.8758,
2293
+ "step": 358
2294
+ },
2295
+ {
2296
+ "epoch": 1.53,
2297
+ "learning_rate": 2.0004449837934606e-05,
2298
+ "loss": 1.8855,
2299
+ "step": 359
2300
+ },
2301
+ {
2302
+ "epoch": 1.53,
2303
+ "learning_rate": 1.9655952705281074e-05,
2304
+ "loss": 1.852,
2305
+ "step": 360
2306
+ },
2307
+ {
2308
+ "epoch": 1.53,
2309
+ "eval_loss": 1.97417414188385,
2310
+ "eval_runtime": 22.4654,
2311
+ "eval_samples_per_second": 0.935,
2312
+ "eval_steps_per_second": 0.49,
2313
+ "step": 360
2314
+ },
2315
+ {
2316
+ "epoch": 1.54,
2317
+ "learning_rate": 1.9310059554774466e-05,
2318
+ "loss": 1.8453,
2319
+ "step": 361
2320
+ },
2321
+ {
2322
+ "epoch": 1.54,
2323
+ "learning_rate": 1.896678666096694e-05,
2324
+ "loss": 1.8164,
2325
+ "step": 362
2326
+ },
2327
+ {
2328
+ "epoch": 1.55,
2329
+ "learning_rate": 1.8626150175125605e-05,
2330
+ "loss": 1.881,
2331
+ "step": 363
2332
+ },
2333
+ {
2334
+ "epoch": 1.55,
2335
+ "learning_rate": 1.8288166124472348e-05,
2336
+ "loss": 1.8969,
2337
+ "step": 364
2338
+ },
2339
+ {
2340
+ "epoch": 1.55,
2341
+ "learning_rate": 1.7952850411429858e-05,
2342
+ "loss": 1.8889,
2343
+ "step": 365
2344
+ },
2345
+ {
2346
+ "epoch": 1.56,
2347
+ "learning_rate": 1.762021881287341e-05,
2348
+ "loss": 1.8748,
2349
+ "step": 366
2350
+ },
2351
+ {
2352
+ "epoch": 1.56,
2353
+ "learning_rate": 1.7290286979388497e-05,
2354
+ "loss": 1.8509,
2355
+ "step": 367
2356
+ },
2357
+ {
2358
+ "epoch": 1.57,
2359
+ "learning_rate": 1.696307043453448e-05,
2360
+ "loss": 1.8478,
2361
+ "step": 368
2362
+ },
2363
+ {
2364
+ "epoch": 1.57,
2365
+ "learning_rate": 1.6638584574114215e-05,
2366
+ "loss": 1.8205,
2367
+ "step": 369
2368
+ },
2369
+ {
2370
+ "epoch": 1.58,
2371
+ "learning_rate": 1.6316844665449673e-05,
2372
+ "loss": 1.9298,
2373
+ "step": 370
2374
+ },
2375
+ {
2376
+ "epoch": 1.58,
2377
+ "learning_rate": 1.5997865846663467e-05,
2378
+ "loss": 1.9743,
2379
+ "step": 371
2380
+ },
2381
+ {
2382
+ "epoch": 1.58,
2383
+ "learning_rate": 1.5681663125966865e-05,
2384
+ "loss": 1.78,
2385
+ "step": 372
2386
+ },
2387
+ {
2388
+ "epoch": 1.59,
2389
+ "learning_rate": 1.5368251380953304e-05,
2390
+ "loss": 1.8556,
2391
+ "step": 373
2392
+ },
2393
+ {
2394
+ "epoch": 1.59,
2395
+ "learning_rate": 1.5057645357898731e-05,
2396
+ "loss": 1.9415,
2397
+ "step": 374
2398
+ },
2399
+ {
2400
+ "epoch": 1.6,
2401
+ "learning_rate": 1.4749859671067431e-05,
2402
+ "loss": 1.9384,
2403
+ "step": 375
2404
+ },
2405
+ {
2406
+ "epoch": 1.6,
2407
+ "learning_rate": 1.4444908802024777e-05,
2408
+ "loss": 1.8176,
2409
+ "step": 376
2410
+ },
2411
+ {
2412
+ "epoch": 1.61,
2413
+ "learning_rate": 1.414280709895548e-05,
2414
+ "loss": 1.883,
2415
+ "step": 377
2416
+ },
2417
+ {
2418
+ "epoch": 1.61,
2419
+ "learning_rate": 1.3843568775988875e-05,
2420
+ "loss": 1.8923,
2421
+ "step": 378
2422
+ },
2423
+ {
2424
+ "epoch": 1.61,
2425
+ "learning_rate": 1.3547207912529787e-05,
2426
+ "loss": 1.9047,
2427
+ "step": 379
2428
+ },
2429
+ {
2430
+ "epoch": 1.62,
2431
+ "learning_rate": 1.3253738452596396e-05,
2432
+ "loss": 1.8608,
2433
+ "step": 380
2434
+ },
2435
+ {
2436
+ "epoch": 1.62,
2437
+ "eval_loss": 1.9734855890274048,
2438
+ "eval_runtime": 22.4836,
2439
+ "eval_samples_per_second": 0.934,
2440
+ "eval_steps_per_second": 0.489,
2441
+ "step": 380
2442
+ },
2443
+ {
2444
+ "epoch": 1.62,
2445
+ "learning_rate": 1.2963174204163875e-05,
2446
+ "loss": 1.8166,
2447
+ "step": 381
2448
+ },
2449
+ {
2450
+ "epoch": 1.63,
2451
+ "learning_rate": 1.2675528838514922e-05,
2452
+ "loss": 1.9964,
2453
+ "step": 382
2454
+ },
2455
+ {
2456
+ "epoch": 1.63,
2457
+ "learning_rate": 1.2390815889596442e-05,
2458
+ "loss": 1.8307,
2459
+ "step": 383
2460
+ },
2461
+ {
2462
+ "epoch": 1.64,
2463
+ "learning_rate": 1.2109048753382738e-05,
2464
+ "loss": 1.8425,
2465
+ "step": 384
2466
+ },
2467
+ {
2468
+ "epoch": 1.64,
2469
+ "learning_rate": 1.1830240687245254e-05,
2470
+ "loss": 1.855,
2471
+ "step": 385
2472
+ },
2473
+ {
2474
+ "epoch": 1.64,
2475
+ "learning_rate": 1.155440480932881e-05,
2476
+ "loss": 1.8374,
2477
+ "step": 386
2478
+ },
2479
+ {
2480
+ "epoch": 1.65,
2481
+ "learning_rate": 1.1281554097934339e-05,
2482
+ "loss": 1.8524,
2483
+ "step": 387
2484
+ },
2485
+ {
2486
+ "epoch": 1.65,
2487
+ "learning_rate": 1.1011701390908303e-05,
2488
+ "loss": 1.8159,
2489
+ "step": 388
2490
+ },
2491
+ {
2492
+ "epoch": 1.66,
2493
+ "learning_rate": 1.0744859385038624e-05,
2494
+ "loss": 1.8242,
2495
+ "step": 389
2496
+ },
2497
+ {
2498
+ "epoch": 1.66,
2499
+ "learning_rate": 1.0481040635457308e-05,
2500
+ "loss": 1.8887,
2501
+ "step": 390
2502
+ },
2503
+ {
2504
+ "epoch": 1.67,
2505
+ "learning_rate": 1.0220257555049701e-05,
2506
+ "loss": 1.8919,
2507
+ "step": 391
2508
+ },
2509
+ {
2510
+ "epoch": 1.67,
2511
+ "learning_rate": 9.96252241387047e-06,
2512
+ "loss": 1.8494,
2513
+ "step": 392
2514
+ },
2515
+ {
2516
+ "epoch": 1.67,
2517
+ "learning_rate": 9.707847338566263e-06,
2518
+ "loss": 1.8952,
2519
+ "step": 393
2520
+ },
2521
+ {
2522
+ "epoch": 1.68,
2523
+ "learning_rate": 9.456244311805191e-06,
2524
+ "loss": 1.8497,
2525
+ "step": 394
2526
+ },
2527
+ {
2528
+ "epoch": 1.68,
2529
+ "learning_rate": 9.207725171712952e-06,
2530
+ "loss": 1.8739,
2531
+ "step": 395
2532
+ },
2533
+ {
2534
+ "epoch": 1.69,
2535
+ "learning_rate": 8.962301611315923e-06,
2536
+ "loss": 1.9981,
2537
+ "step": 396
2538
+ },
2539
+ {
2540
+ "epoch": 1.69,
2541
+ "learning_rate": 8.719985177990926e-06,
2542
+ "loss": 1.8001,
2543
+ "step": 397
2544
+ },
2545
+ {
2546
+ "epoch": 1.7,
2547
+ "learning_rate": 8.480787272921969e-06,
2548
+ "loss": 1.8902,
2549
+ "step": 398
2550
+ },
2551
+ {
2552
+ "epoch": 1.7,
2553
+ "learning_rate": 8.244719150563767e-06,
2554
+ "loss": 1.7811,
2555
+ "step": 399
2556
+ },
2557
+ {
2558
+ "epoch": 1.7,
2559
+ "learning_rate": 8.011791918112234e-06,
2560
+ "loss": 1.8959,
2561
+ "step": 400
2562
+ },
2563
+ {
2564
+ "epoch": 1.7,
2565
+ "eval_loss": 1.9734867811203003,
2566
+ "eval_runtime": 22.4035,
2567
+ "eval_samples_per_second": 0.937,
2568
+ "eval_steps_per_second": 0.491,
2569
+ "step": 400
2570
+ },
2571
+ {
2572
+ "epoch": 1.71,
2573
+ "learning_rate": 7.78201653498189e-06,
2574
+ "loss": 1.9119,
2575
+ "step": 401
2576
+ },
2577
+ {
2578
+ "epoch": 1.71,
2579
+ "learning_rate": 7.555403812290164e-06,
2580
+ "loss": 2.0164,
2581
+ "step": 402
2582
+ },
2583
+ {
2584
+ "epoch": 1.72,
2585
+ "learning_rate": 7.3319644123488034e-06,
2586
+ "loss": 1.9001,
2587
+ "step": 403
2588
+ },
2589
+ {
2590
+ "epoch": 1.72,
2591
+ "learning_rate": 7.11170884816209e-06,
2592
+ "loss": 2.02,
2593
+ "step": 404
2594
+ },
2595
+ {
2596
+ "epoch": 1.73,
2597
+ "learning_rate": 6.894647482932353e-06,
2598
+ "loss": 1.8183,
2599
+ "step": 405
2600
+ },
2601
+ {
2602
+ "epoch": 1.73,
2603
+ "learning_rate": 6.680790529572167e-06,
2604
+ "loss": 1.773,
2605
+ "step": 406
2606
+ },
2607
+ {
2608
+ "epoch": 1.73,
2609
+ "learning_rate": 6.47014805022405e-06,
2610
+ "loss": 1.7963,
2611
+ "step": 407
2612
+ },
2613
+ {
2614
+ "epoch": 1.74,
2615
+ "learning_rate": 6.26272995578683e-06,
2616
+ "loss": 1.966,
2617
+ "step": 408
2618
+ },
2619
+ {
2620
+ "epoch": 1.74,
2621
+ "learning_rate": 6.058546005449496e-06,
2622
+ "loss": 1.947,
2623
+ "step": 409
2624
+ },
2625
+ {
2626
+ "epoch": 1.75,
2627
+ "learning_rate": 5.857605806231863e-06,
2628
+ "loss": 1.802,
2629
+ "step": 410
2630
+ },
2631
+ {
2632
+ "epoch": 1.75,
2633
+ "learning_rate": 5.659918812532718e-06,
2634
+ "loss": 1.9488,
2635
+ "step": 411
2636
+ },
2637
+ {
2638
+ "epoch": 1.76,
2639
+ "learning_rate": 5.465494325684816e-06,
2640
+ "loss": 1.8201,
2641
+ "step": 412
2642
+ },
2643
+ {
2644
+ "epoch": 1.76,
2645
+ "learning_rate": 5.2743414935174254e-06,
2646
+ "loss": 1.8618,
2647
+ "step": 413
2648
+ },
2649
+ {
2650
+ "epoch": 1.76,
2651
+ "learning_rate": 5.086469309925717e-06,
2652
+ "loss": 1.8535,
2653
+ "step": 414
2654
+ },
2655
+ {
2656
+ "epoch": 1.77,
2657
+ "learning_rate": 4.901886614447759e-06,
2658
+ "loss": 1.9889,
2659
+ "step": 415
2660
+ },
2661
+ {
2662
+ "epoch": 1.77,
2663
+ "learning_rate": 4.720602091848524e-06,
2664
+ "loss": 1.8761,
2665
+ "step": 416
2666
+ },
2667
+ {
2668
+ "epoch": 1.78,
2669
+ "learning_rate": 4.542624271711295e-06,
2670
+ "loss": 1.8038,
2671
+ "step": 417
2672
+ },
2673
+ {
2674
+ "epoch": 1.78,
2675
+ "learning_rate": 4.3679615280363315e-06,
2676
+ "loss": 1.8597,
2677
+ "step": 418
2678
+ },
2679
+ {
2680
+ "epoch": 1.78,
2681
+ "learning_rate": 4.196622078846854e-06,
2682
+ "loss": 1.8558,
2683
+ "step": 419
2684
+ },
2685
+ {
2686
+ "epoch": 1.79,
2687
+ "learning_rate": 4.028613985802401e-06,
2688
+ "loss": 1.7912,
2689
+ "step": 420
2690
+ },
2691
+ {
2692
+ "epoch": 1.79,
2693
+ "eval_loss": 1.973118782043457,
2694
+ "eval_runtime": 22.5062,
2695
+ "eval_samples_per_second": 0.933,
2696
+ "eval_steps_per_second": 0.489,
2697
+ "step": 420
2698
+ },
2699
+ {
2700
+ "epoch": 1.79,
2701
+ "learning_rate": 3.863945153819511e-06,
2702
+ "loss": 1.791,
2703
+ "step": 421
2704
+ },
2705
+ {
2706
+ "epoch": 1.8,
2707
+ "learning_rate": 3.702623330699811e-06,
2708
+ "loss": 1.8951,
2709
+ "step": 422
2710
+ },
2711
+ {
2712
+ "epoch": 1.8,
2713
+ "learning_rate": 3.5446561067654035e-06,
2714
+ "loss": 1.8344,
2715
+ "step": 423
2716
+ },
2717
+ {
2718
+ "epoch": 1.81,
2719
+ "learning_rate": 3.3900509145018657e-06,
2720
+ "loss": 1.8532,
2721
+ "step": 424
2722
+ },
2723
+ {
2724
+ "epoch": 1.81,
2725
+ "learning_rate": 3.238815028208386e-06,
2726
+ "loss": 1.8097,
2727
+ "step": 425
2728
+ },
2729
+ {
2730
+ "epoch": 1.81,
2731
+ "learning_rate": 3.090955563655645e-06,
2732
+ "loss": 1.8998,
2733
+ "step": 426
2734
+ },
2735
+ {
2736
+ "epoch": 1.82,
2737
+ "learning_rate": 2.946479477750918e-06,
2738
+ "loss": 1.9115,
2739
+ "step": 427
2740
+ },
2741
+ {
2742
+ "epoch": 1.82,
2743
+ "learning_rate": 2.8053935682108034e-06,
2744
+ "loss": 1.8271,
2745
+ "step": 428
2746
+ },
2747
+ {
2748
+ "epoch": 1.83,
2749
+ "learning_rate": 2.667704473241336e-06,
2750
+ "loss": 1.8162,
2751
+ "step": 429
2752
+ },
2753
+ {
2754
+ "epoch": 1.83,
2755
+ "learning_rate": 2.5334186712257205e-06,
2756
+ "loss": 1.9347,
2757
+ "step": 430
2758
+ },
2759
+ {
2760
+ "epoch": 1.84,
2761
+ "learning_rate": 2.4025424804194336e-06,
2762
+ "loss": 1.8551,
2763
+ "step": 431
2764
+ },
2765
+ {
2766
+ "epoch": 1.84,
2767
+ "learning_rate": 2.2750820586530132e-06,
2768
+ "loss": 1.8975,
2769
+ "step": 432
2770
+ },
2771
+ {
2772
+ "epoch": 1.84,
2773
+ "learning_rate": 2.1510434030423045e-06,
2774
+ "loss": 1.937,
2775
+ "step": 433
2776
+ },
2777
+ {
2778
+ "epoch": 1.85,
2779
+ "learning_rate": 2.0304323497062874e-06,
2780
+ "loss": 1.8481,
2781
+ "step": 434
2782
+ },
2783
+ {
2784
+ "epoch": 1.85,
2785
+ "learning_rate": 1.9132545734924703e-06,
2786
+ "loss": 1.9073,
2787
+ "step": 435
2788
+ },
2789
+ {
2790
+ "epoch": 1.86,
2791
+ "learning_rate": 1.7995155877099377e-06,
2792
+ "loss": 1.8256,
2793
+ "step": 436
2794
+ },
2795
+ {
2796
+ "epoch": 1.86,
2797
+ "learning_rate": 1.6892207438698402e-06,
2798
+ "loss": 1.8034,
2799
+ "step": 437
2800
+ },
2801
+ {
2802
+ "epoch": 1.87,
2803
+ "learning_rate": 1.5823752314337469e-06,
2804
+ "loss": 1.8928,
2805
+ "step": 438
2806
+ },
2807
+ {
2808
+ "epoch": 1.87,
2809
+ "learning_rate": 1.478984077569323e-06,
2810
+ "loss": 1.8337,
2811
+ "step": 439
2812
+ },
2813
+ {
2814
+ "epoch": 1.87,
2815
+ "learning_rate": 1.3790521469139281e-06,
2816
+ "loss": 1.8908,
2817
+ "step": 440
2818
+ },
2819
+ {
2820
+ "epoch": 1.87,
2821
+ "eval_loss": 1.9726591110229492,
2822
+ "eval_runtime": 22.5316,
2823
+ "eval_samples_per_second": 0.932,
2824
+ "eval_steps_per_second": 0.488,
2825
+ "step": 440
2826
+ },
2827
+ {
2828
+ "epoch": 1.88,
2829
+ "learning_rate": 1.2825841413456328e-06,
2830
+ "loss": 1.8349,
2831
+ "step": 441
2832
+ },
2833
+ {
2834
+ "epoch": 1.88,
2835
+ "learning_rate": 1.1895845997620696e-06,
2836
+ "loss": 1.9327,
2837
+ "step": 442
2838
+ },
2839
+ {
2840
+ "epoch": 1.89,
2841
+ "learning_rate": 1.1000578978668045e-06,
2842
+ "loss": 1.9908,
2843
+ "step": 443
2844
+ },
2845
+ {
2846
+ "epoch": 1.89,
2847
+ "learning_rate": 1.0140082479635187e-06,
2848
+ "loss": 1.8898,
2849
+ "step": 444
2850
+ },
2851
+ {
2852
+ "epoch": 1.9,
2853
+ "learning_rate": 9.31439698757766e-07,
2854
+ "loss": 1.806,
2855
+ "step": 445
2856
+ },
2857
+ {
2858
+ "epoch": 1.9,
2859
+ "learning_rate": 8.523561351665015e-07,
2860
+ "loss": 1.7971,
2861
+ "step": 446
2862
+ },
2863
+ {
2864
+ "epoch": 1.9,
2865
+ "learning_rate": 7.767612781353183e-07,
2866
+ "loss": 1.8295,
2867
+ "step": 447
2868
+ },
2869
+ {
2870
+ "epoch": 1.91,
2871
+ "learning_rate": 7.046586844632968e-07,
2872
+ "loss": 1.814,
2873
+ "step": 448
2874
+ },
2875
+ {
2876
+ "epoch": 1.91,
2877
+ "learning_rate": 6.360517466357546e-07,
2878
+ "loss": 1.9302,
2879
+ "step": 449
2880
+ },
2881
+ {
2882
+ "epoch": 1.92,
2883
+ "learning_rate": 5.709436926645411e-07,
2884
+ "loss": 1.8789,
2885
+ "step": 450
2886
+ },
2887
+ {
2888
+ "epoch": 1.92,
2889
+ "learning_rate": 5.093375859362258e-07,
2890
+ "loss": 1.9406,
2891
+ "step": 451
2892
+ },
2893
+ {
2894
+ "epoch": 1.93,
2895
+ "learning_rate": 4.5123632506788855e-07,
2896
+ "loss": 1.8643,
2897
+ "step": 452
2898
+ },
2899
+ {
2900
+ "epoch": 1.93,
2901
+ "learning_rate": 3.9664264377081977e-07,
2902
+ "loss": 1.8996,
2903
+ "step": 453
2904
+ },
2905
+ {
2906
+ "epoch": 1.93,
2907
+ "learning_rate": 3.455591107218325e-07,
2908
+ "loss": 1.8361,
2909
+ "step": 454
2910
+ },
2911
+ {
2912
+ "epoch": 1.94,
2913
+ "learning_rate": 2.9798812944244186e-07,
2914
+ "loss": 1.9086,
2915
+ "step": 455
2916
+ },
2917
+ {
2918
+ "epoch": 1.94,
2919
+ "learning_rate": 2.5393193818574743e-07,
2920
+ "loss": 2.008,
2921
+ "step": 456
2922
+ },
2923
+ {
2924
+ "epoch": 1.95,
2925
+ "learning_rate": 2.1339260983116725e-07,
2926
+ "loss": 1.8808,
2927
+ "step": 457
2928
+ },
2929
+ {
2930
+ "epoch": 1.95,
2931
+ "learning_rate": 1.763720517868328e-07,
2932
+ "loss": 1.888,
2933
+ "step": 458
2934
+ },
2935
+ {
2936
+ "epoch": 1.96,
2937
+ "learning_rate": 1.4287200589993553e-07,
2938
+ "loss": 1.8716,
2939
+ "step": 459
2940
+ },
2941
+ {
2942
+ "epoch": 1.96,
2943
+ "learning_rate": 1.1289404837469263e-07,
2944
+ "loss": 1.8079,
2945
+ "step": 460
2946
+ },
2947
+ {
2948
+ "epoch": 1.96,
2949
+ "eval_loss": 1.9728879928588867,
2950
+ "eval_runtime": 22.4241,
2951
+ "eval_samples_per_second": 0.936,
2952
+ "eval_steps_per_second": 0.491,
2953
+ "step": 460
2954
+ },
2955
+ {
2956
+ "epoch": 1.96,
2957
+ "learning_rate": 8.64395896982395e-08,
2958
+ "loss": 1.8616,
2959
+ "step": 461
2960
+ },
2961
+ {
2962
+ "epoch": 1.97,
2963
+ "learning_rate": 6.350987457422462e-08,
2964
+ "loss": 1.8601,
2965
+ "step": 462
2966
+ },
2967
+ {
2968
+ "epoch": 1.97,
2969
+ "learning_rate": 4.410598186428138e-08,
2970
+ "loss": 1.7755,
2971
+ "step": 463
2972
+ },
2973
+ {
2974
+ "epoch": 1.98,
2975
+ "learning_rate": 2.8228824537235297e-08,
2976
+ "loss": 1.9435,
2977
+ "step": 464
2978
+ },
2979
+ {
2980
+ "epoch": 1.98,
2981
+ "learning_rate": 1.587914962618009e-08,
2982
+ "loss": 1.895,
2983
+ "step": 465
2984
+ },
2985
+ {
2986
+ "epoch": 1.99,
2987
+ "learning_rate": 7.05753819328081e-09,
2988
+ "loss": 1.8822,
2989
+ "step": 466
2990
+ },
2991
+ {
2992
+ "epoch": 1.99,
2993
+ "learning_rate": 1.764405302495664e-09,
2994
+ "loss": 1.8318,
2995
+ "step": 467
2996
+ },
2997
+ {
2998
+ "epoch": 1.99,
2999
+ "learning_rate": 0.0,
3000
+ "loss": 1.9218,
3001
+ "step": 468
3002
+ }
3003
+ ],
3004
+ "logging_steps": 1,
3005
+ "max_steps": 468,
3006
+ "num_train_epochs": 2,
3007
+ "save_steps": 500,
3008
+ "total_flos": 2.6470735972694753e+18,
3009
+ "trial_name": null,
3010
+ "trial_params": null
3011
+ }
checkpoint-468/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7feb49f9c014aec5b2a20b88f6ec716d10a44c3f25f112041117a5c589dca47
3
+ size 4475
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/yi-llama-34b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 7168,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 56,
16
+ "num_hidden_layers": 60,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "float32",
22
+ "bnb_4bit_quant_type": "fp4",
23
+ "bnb_4bit_use_double_quant": false,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": false,
29
+ "load_in_8bit": true,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 5000000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.34.1",
38
+ "use_cache": false,
39
+ "vocab_size": 64000
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
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": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "<|endoftext|>",
33
+ "legacy": false,
34
+ "model_max_length": 4096,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "truncation_side": "right",
41
+ "trust_remote_code": false,
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false,
44
+ "use_fast": true
45
+ }