Hugging Face's logo

Undi95
/
Llama2-13B-no_robots-alpaca-lora

Text Generation
Transformers
llama
Generated from Trainer
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Community
1
Undi95 commited on
Commit
1c640a0
•
1 Parent(s): 0c03526

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +76 -0
  2. adapter_config.json +28 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-426/README.md +219 -0
  5. checkpoint-426/adapter_config.json +28 -0
  6. checkpoint-426/adapter_model.bin +3 -0
  7. checkpoint-426/optimizer.pt +3 -0
  8. checkpoint-426/rng_state.pth +3 -0
  9. checkpoint-426/scheduler.pt +3 -0
  10. checkpoint-426/trainer_state.json +2663 -0
  11. checkpoint-426/training_args.bin +3 -0
  12. checkpoint-838/README.md +219 -0
  13. checkpoint-838/adapter_config.json +28 -0
  14. checkpoint-838/adapter_model.bin +3 -0
  15. checkpoint-838/optimizer.pt +3 -0
  16. checkpoint-838/rng_state.pth +3 -0
  17. checkpoint-838/scheduler.pt +3 -0
  18. checkpoint-838/trainer_state.json +5207 -0
  19. checkpoint-838/training_args.bin +3 -0
  20. config.json +40 -0
  21. special_tokens_map.json +24 -0
  22. tokenizer.model +3 -0
  23. tokenizer_config.json +43 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: 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
+ # 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: 1.6087
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: 0.00065
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: constant
42
+ - lr_scheduler_warmup_steps: 10
43
+ - num_epochs: 2
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 1.5523 | 0.0 | 1 | 1.5476 |
50
+ | 1.2139 | 0.1 | 42 | 1.5008 |
51
+ | 1.6348 | 0.2 | 84 | 1.4968 |
52
+ | 1.6498 | 0.3 | 126 | 1.4962 |
53
+ | 1.5645 | 0.4 | 168 | 1.4983 |
54
+ | 1.6487 | 0.5 | 210 | 1.4981 |
55
+ | 1.6147 | 0.6 | 252 | 1.4965 |
56
+ | 1.3048 | 0.7 | 294 | 1.4973 |
57
+ | 1.6205 | 0.8 | 336 | 1.5007 |
58
+ | 1.6045 | 0.9 | 378 | 1.5003 |
59
+ | 1.5781 | 1.0 | 420 | 1.5013 |
60
+ | 1.4807 | 1.09 | 462 | 1.5492 |
61
+ | 1.0541 | 1.19 | 504 | 1.5596 |
62
+ | 1.2337 | 1.29 | 546 | 1.5789 |
63
+ | 0.9719 | 1.39 | 588 | 1.5859 |
64
+ | 1.2189 | 1.49 | 630 | 1.5959 |
65
+ | 1.2566 | 1.59 | 672 | 1.5968 |
66
+ | 0.7049 | 1.69 | 714 | 1.5987 |
67
+ | 1.2133 | 1.79 | 756 | 1.5907 |
68
+ | 1.0327 | 1.89 | 798 | 1.6087 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.34.1
74
+ - Pytorch 2.0.1+cu117
75
+ - Datasets 2.14.6
76
+ - 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": "./TheBloke_Llama-2-13B-fp16",
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": 256,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "v_proj",
21
+ "up_proj",
22
+ "q_proj",
23
+ "down_proj",
24
+ "o_proj",
25
+ "gate_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:aafec848efab6d151b2c04a8cc451b1422ae863820d9defbca5929e730951922
3
+ size 4005763213
checkpoint-426/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./TheBloke_Llama-2-13B-fp16
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 0.6.0
checkpoint-426/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./TheBloke_Llama-2-13B-fp16",
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": 256,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "v_proj",
21
+ "up_proj",
22
+ "q_proj",
23
+ "down_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-426/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e678c73c289de0d391f58702dcbfcb1bc7a9ca3691f8f1c60012e2e11150e057
3
+ size 4005763213
checkpoint-426/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a03abf226fa60b241ca817f570cbd74a13c4699205a9b9f0bff85fd12ea843
3
+ size 8011604773
checkpoint-426/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c0d921b32841931317bc96e358018fd7e08d36ab4399a293d2ba0ffefd18cfc
3
+ size 14575
checkpoint-426/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed13d0358447226f453634e22ad64a05b420b545357ff0a8a2404e4a6a771c4
3
+ size 627
checkpoint-426/trainer_state.json ADDED
@@ -0,0 +1,2663 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0167064439140812,
5
+ "eval_steps": 42,
6
+ "global_step": 426,
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": 0.00065,
14
+ "loss": 1.5523,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": 1.5476094484329224,
20
+ "eval_runtime": 57.6973,
21
+ "eval_samples_per_second": 8.666,
22
+ "eval_steps_per_second": 4.333,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "learning_rate": 0.00065,
28
+ "loss": 1.6985,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 0.00065,
34
+ "loss": 1.1799,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.01,
39
+ "learning_rate": 0.00065,
40
+ "loss": 1.7743,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.01,
45
+ "learning_rate": 0.00065,
46
+ "loss": 1.6175,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.01,
51
+ "learning_rate": 0.00065,
52
+ "loss": 1.5657,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "learning_rate": 0.00065,
58
+ "loss": 1.4462,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 0.00065,
64
+ "loss": 1.4567,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "learning_rate": 0.00065,
70
+ "loss": 1.734,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.02,
75
+ "learning_rate": 0.00065,
76
+ "loss": 1.4707,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "learning_rate": 0.00065,
82
+ "loss": 1.5891,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.03,
87
+ "learning_rate": 0.00065,
88
+ "loss": 1.4921,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.03,
93
+ "learning_rate": 0.00065,
94
+ "loss": 1.5806,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.03,
99
+ "learning_rate": 0.00065,
100
+ "loss": 1.4224,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.04,
105
+ "learning_rate": 0.00065,
106
+ "loss": 1.4779,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.04,
111
+ "learning_rate": 0.00065,
112
+ "loss": 1.5828,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.04,
117
+ "learning_rate": 0.00065,
118
+ "loss": 1.4379,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.04,
123
+ "learning_rate": 0.00065,
124
+ "loss": 1.5227,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.05,
129
+ "learning_rate": 0.00065,
130
+ "loss": 1.3899,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.05,
135
+ "learning_rate": 0.00065,
136
+ "loss": 1.3557,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.05,
141
+ "learning_rate": 0.00065,
142
+ "loss": 1.5049,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.05,
147
+ "learning_rate": 0.00065,
148
+ "loss": 1.5334,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.05,
153
+ "learning_rate": 0.00065,
154
+ "loss": 1.1747,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.06,
159
+ "learning_rate": 0.00065,
160
+ "loss": 1.5094,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.06,
165
+ "learning_rate": 0.00065,
166
+ "loss": 1.4909,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.06,
171
+ "learning_rate": 0.00065,
172
+ "loss": 1.521,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.06,
177
+ "learning_rate": 0.00065,
178
+ "loss": 1.5296,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.07,
183
+ "learning_rate": 0.00065,
184
+ "loss": 1.5475,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.07,
189
+ "learning_rate": 0.00065,
190
+ "loss": 1.5203,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.07,
195
+ "learning_rate": 0.00065,
196
+ "loss": 1.4874,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.07,
201
+ "learning_rate": 0.00065,
202
+ "loss": 1.6169,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.08,
207
+ "learning_rate": 0.00065,
208
+ "loss": 1.5158,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.08,
213
+ "learning_rate": 0.00065,
214
+ "loss": 1.5844,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.08,
219
+ "learning_rate": 0.00065,
220
+ "loss": 1.4701,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.08,
225
+ "learning_rate": 0.00065,
226
+ "loss": 1.3729,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.09,
231
+ "learning_rate": 0.00065,
232
+ "loss": 1.5067,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.09,
237
+ "learning_rate": 0.00065,
238
+ "loss": 1.4972,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.09,
243
+ "learning_rate": 0.00065,
244
+ "loss": 1.8079,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.09,
249
+ "learning_rate": 0.00065,
250
+ "loss": 1.5681,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.1,
255
+ "learning_rate": 0.00065,
256
+ "loss": 1.4852,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.1,
261
+ "learning_rate": 0.00065,
262
+ "loss": 1.5448,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.1,
267
+ "learning_rate": 0.00065,
268
+ "loss": 1.2139,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.1,
273
+ "eval_loss": 1.500810146331787,
274
+ "eval_runtime": 57.801,
275
+ "eval_samples_per_second": 8.65,
276
+ "eval_steps_per_second": 4.325,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.1,
281
+ "learning_rate": 0.00065,
282
+ "loss": 1.4483,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.11,
287
+ "learning_rate": 0.00065,
288
+ "loss": 1.3328,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.11,
293
+ "learning_rate": 0.00065,
294
+ "loss": 1.4363,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.11,
299
+ "learning_rate": 0.00065,
300
+ "loss": 1.2864,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.11,
305
+ "learning_rate": 0.00065,
306
+ "loss": 1.4731,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.11,
311
+ "learning_rate": 0.00065,
312
+ "loss": 1.5103,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.12,
317
+ "learning_rate": 0.00065,
318
+ "loss": 1.5552,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.12,
323
+ "learning_rate": 0.00065,
324
+ "loss": 1.4697,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.12,
329
+ "learning_rate": 0.00065,
330
+ "loss": 1.5153,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.12,
335
+ "learning_rate": 0.00065,
336
+ "loss": 1.4696,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.13,
341
+ "learning_rate": 0.00065,
342
+ "loss": 1.4874,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.13,
347
+ "learning_rate": 0.00065,
348
+ "loss": 1.6397,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.13,
353
+ "learning_rate": 0.00065,
354
+ "loss": 1.5159,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.13,
359
+ "learning_rate": 0.00065,
360
+ "loss": 1.5399,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.14,
365
+ "learning_rate": 0.00065,
366
+ "loss": 1.573,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.14,
371
+ "learning_rate": 0.00065,
372
+ "loss": 1.5067,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.14,
377
+ "learning_rate": 0.00065,
378
+ "loss": 1.5585,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.14,
383
+ "learning_rate": 0.00065,
384
+ "loss": 1.4998,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.15,
389
+ "learning_rate": 0.00065,
390
+ "loss": 1.0471,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.15,
395
+ "learning_rate": 0.00065,
396
+ "loss": 1.5023,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.15,
401
+ "learning_rate": 0.00065,
402
+ "loss": 1.241,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.15,
407
+ "learning_rate": 0.00065,
408
+ "loss": 1.2748,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.16,
413
+ "learning_rate": 0.00065,
414
+ "loss": 1.598,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.16,
419
+ "learning_rate": 0.00065,
420
+ "loss": 1.7209,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.16,
425
+ "learning_rate": 0.00065,
426
+ "loss": 1.4492,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.16,
431
+ "learning_rate": 0.00065,
432
+ "loss": 1.6432,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.16,
437
+ "learning_rate": 0.00065,
438
+ "loss": 1.4849,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.17,
443
+ "learning_rate": 0.00065,
444
+ "loss": 1.3859,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.17,
449
+ "learning_rate": 0.00065,
450
+ "loss": 1.2329,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.17,
455
+ "learning_rate": 0.00065,
456
+ "loss": 1.4836,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.17,
461
+ "learning_rate": 0.00065,
462
+ "loss": 1.5757,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.18,
467
+ "learning_rate": 0.00065,
468
+ "loss": 1.4403,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.18,
473
+ "learning_rate": 0.00065,
474
+ "loss": 1.4311,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.18,
479
+ "learning_rate": 0.00065,
480
+ "loss": 1.7698,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.18,
485
+ "learning_rate": 0.00065,
486
+ "loss": 1.4067,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.19,
491
+ "learning_rate": 0.00065,
492
+ "loss": 1.3548,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.19,
497
+ "learning_rate": 0.00065,
498
+ "loss": 1.2219,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.19,
503
+ "learning_rate": 0.00065,
504
+ "loss": 1.2774,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.19,
509
+ "learning_rate": 0.00065,
510
+ "loss": 1.5268,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.2,
515
+ "learning_rate": 0.00065,
516
+ "loss": 1.6669,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.2,
521
+ "learning_rate": 0.00065,
522
+ "loss": 1.4055,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.2,
527
+ "learning_rate": 0.00065,
528
+ "loss": 1.6348,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.2,
533
+ "eval_loss": 1.4967617988586426,
534
+ "eval_runtime": 57.7521,
535
+ "eval_samples_per_second": 8.658,
536
+ "eval_steps_per_second": 4.329,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.2,
541
+ "learning_rate": 0.00065,
542
+ "loss": 1.4524,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.21,
547
+ "learning_rate": 0.00065,
548
+ "loss": 1.7781,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.21,
553
+ "learning_rate": 0.00065,
554
+ "loss": 1.4317,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.21,
559
+ "learning_rate": 0.00065,
560
+ "loss": 1.5865,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.21,
565
+ "learning_rate": 0.00065,
566
+ "loss": 1.465,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.21,
571
+ "learning_rate": 0.00065,
572
+ "loss": 1.5601,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.22,
577
+ "learning_rate": 0.00065,
578
+ "loss": 1.4393,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.22,
583
+ "learning_rate": 0.00065,
584
+ "loss": 1.5499,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.22,
589
+ "learning_rate": 0.00065,
590
+ "loss": 1.5289,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.22,
595
+ "learning_rate": 0.00065,
596
+ "loss": 1.6562,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.23,
601
+ "learning_rate": 0.00065,
602
+ "loss": 1.6702,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.23,
607
+ "learning_rate": 0.00065,
608
+ "loss": 1.4044,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.23,
613
+ "learning_rate": 0.00065,
614
+ "loss": 1.5733,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.23,
619
+ "learning_rate": 0.00065,
620
+ "loss": 1.494,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.24,
625
+ "learning_rate": 0.00065,
626
+ "loss": 1.5325,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.24,
631
+ "learning_rate": 0.00065,
632
+ "loss": 1.5481,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.24,
637
+ "learning_rate": 0.00065,
638
+ "loss": 1.5022,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.24,
643
+ "learning_rate": 0.00065,
644
+ "loss": 1.5334,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.25,
649
+ "learning_rate": 0.00065,
650
+ "loss": 1.4816,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.25,
655
+ "learning_rate": 0.00065,
656
+ "loss": 1.5505,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.25,
661
+ "learning_rate": 0.00065,
662
+ "loss": 1.5887,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.25,
667
+ "learning_rate": 0.00065,
668
+ "loss": 1.6073,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.26,
673
+ "learning_rate": 0.00065,
674
+ "loss": 1.2843,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.26,
679
+ "learning_rate": 0.00065,
680
+ "loss": 1.6441,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.26,
685
+ "learning_rate": 0.00065,
686
+ "loss": 1.4291,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.26,
691
+ "learning_rate": 0.00065,
692
+ "loss": 1.5993,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.26,
697
+ "learning_rate": 0.00065,
698
+ "loss": 1.6003,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.27,
703
+ "learning_rate": 0.00065,
704
+ "loss": 1.6004,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.27,
709
+ "learning_rate": 0.00065,
710
+ "loss": 1.092,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.27,
715
+ "learning_rate": 0.00065,
716
+ "loss": 1.6992,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.27,
721
+ "learning_rate": 0.00065,
722
+ "loss": 1.5215,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.28,
727
+ "learning_rate": 0.00065,
728
+ "loss": 1.6719,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.28,
733
+ "learning_rate": 0.00065,
734
+ "loss": 1.5689,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.28,
739
+ "learning_rate": 0.00065,
740
+ "loss": 1.5856,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.28,
745
+ "learning_rate": 0.00065,
746
+ "loss": 1.5404,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.29,
751
+ "learning_rate": 0.00065,
752
+ "loss": 1.2784,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.29,
757
+ "learning_rate": 0.00065,
758
+ "loss": 1.7063,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.29,
763
+ "learning_rate": 0.00065,
764
+ "loss": 1.518,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.29,
769
+ "learning_rate": 0.00065,
770
+ "loss": 1.6195,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.3,
775
+ "learning_rate": 0.00065,
776
+ "loss": 1.4,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.3,
781
+ "learning_rate": 0.00065,
782
+ "loss": 1.5435,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.3,
787
+ "learning_rate": 0.00065,
788
+ "loss": 1.6498,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.3,
793
+ "eval_loss": 1.4962397813796997,
794
+ "eval_runtime": 57.8837,
795
+ "eval_samples_per_second": 8.638,
796
+ "eval_steps_per_second": 4.319,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.3,
801
+ "learning_rate": 0.00065,
802
+ "loss": 1.4815,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.31,
807
+ "learning_rate": 0.00065,
808
+ "loss": 1.5617,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.31,
813
+ "learning_rate": 0.00065,
814
+ "loss": 1.6173,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.31,
819
+ "learning_rate": 0.00065,
820
+ "loss": 1.6515,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.31,
825
+ "learning_rate": 0.00065,
826
+ "loss": 1.7001,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.32,
831
+ "learning_rate": 0.00065,
832
+ "loss": 1.7185,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.32,
837
+ "learning_rate": 0.00065,
838
+ "loss": 1.5095,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.32,
843
+ "learning_rate": 0.00065,
844
+ "loss": 1.5354,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.32,
849
+ "learning_rate": 0.00065,
850
+ "loss": 1.5958,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.32,
855
+ "learning_rate": 0.00065,
856
+ "loss": 1.5622,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.33,
861
+ "learning_rate": 0.00065,
862
+ "loss": 1.5229,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.33,
867
+ "learning_rate": 0.00065,
868
+ "loss": 1.5117,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.33,
873
+ "learning_rate": 0.00065,
874
+ "loss": 1.7616,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.33,
879
+ "learning_rate": 0.00065,
880
+ "loss": 1.2281,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.34,
885
+ "learning_rate": 0.00065,
886
+ "loss": 1.6234,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.34,
891
+ "learning_rate": 0.00065,
892
+ "loss": 1.3816,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.34,
897
+ "learning_rate": 0.00065,
898
+ "loss": 1.474,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.34,
903
+ "learning_rate": 0.00065,
904
+ "loss": 1.4441,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.35,
909
+ "learning_rate": 0.00065,
910
+ "loss": 1.602,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.35,
915
+ "learning_rate": 0.00065,
916
+ "loss": 1.543,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.35,
921
+ "learning_rate": 0.00065,
922
+ "loss": 1.7464,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.35,
927
+ "learning_rate": 0.00065,
928
+ "loss": 1.696,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.36,
933
+ "learning_rate": 0.00065,
934
+ "loss": 1.6781,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.36,
939
+ "learning_rate": 0.00065,
940
+ "loss": 1.4346,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.36,
945
+ "learning_rate": 0.00065,
946
+ "loss": 1.5507,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.36,
951
+ "learning_rate": 0.00065,
952
+ "loss": 1.5901,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.37,
957
+ "learning_rate": 0.00065,
958
+ "loss": 1.4516,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.37,
963
+ "learning_rate": 0.00065,
964
+ "loss": 1.4069,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.37,
969
+ "learning_rate": 0.00065,
970
+ "loss": 1.5614,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.37,
975
+ "learning_rate": 0.00065,
976
+ "loss": 1.4832,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.37,
981
+ "learning_rate": 0.00065,
982
+ "loss": 1.4241,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.38,
987
+ "learning_rate": 0.00065,
988
+ "loss": 1.4526,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.38,
993
+ "learning_rate": 0.00065,
994
+ "loss": 1.1961,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.38,
999
+ "learning_rate": 0.00065,
1000
+ "loss": 1.4206,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.38,
1005
+ "learning_rate": 0.00065,
1006
+ "loss": 1.6221,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.39,
1011
+ "learning_rate": 0.00065,
1012
+ "loss": 1.5796,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.39,
1017
+ "learning_rate": 0.00065,
1018
+ "loss": 1.7052,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.39,
1023
+ "learning_rate": 0.00065,
1024
+ "loss": 1.6022,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.39,
1029
+ "learning_rate": 0.00065,
1030
+ "loss": 1.4067,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.4,
1035
+ "learning_rate": 0.00065,
1036
+ "loss": 1.4105,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 0.4,
1041
+ "learning_rate": 0.00065,
1042
+ "loss": 1.3916,
1043
+ "step": 167
1044
+ },
1045
+ {
1046
+ "epoch": 0.4,
1047
+ "learning_rate": 0.00065,
1048
+ "loss": 1.5645,
1049
+ "step": 168
1050
+ },
1051
+ {
1052
+ "epoch": 0.4,
1053
+ "eval_loss": 1.498284101486206,
1054
+ "eval_runtime": 57.7262,
1055
+ "eval_samples_per_second": 8.662,
1056
+ "eval_steps_per_second": 4.331,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 0.4,
1061
+ "learning_rate": 0.00065,
1062
+ "loss": 1.5244,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 0.41,
1067
+ "learning_rate": 0.00065,
1068
+ "loss": 1.3781,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 0.41,
1073
+ "learning_rate": 0.00065,
1074
+ "loss": 1.6621,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 0.41,
1079
+ "learning_rate": 0.00065,
1080
+ "loss": 1.6337,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 0.41,
1085
+ "learning_rate": 0.00065,
1086
+ "loss": 1.5208,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 0.42,
1091
+ "learning_rate": 0.00065,
1092
+ "loss": 1.2743,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 0.42,
1097
+ "learning_rate": 0.00065,
1098
+ "loss": 1.6341,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 0.42,
1103
+ "learning_rate": 0.00065,
1104
+ "loss": 1.2578,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 0.42,
1109
+ "learning_rate": 0.00065,
1110
+ "loss": 1.6975,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 0.42,
1115
+ "learning_rate": 0.00065,
1116
+ "loss": 1.5663,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 0.43,
1121
+ "learning_rate": 0.00065,
1122
+ "loss": 1.5621,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 0.43,
1127
+ "learning_rate": 0.00065,
1128
+ "loss": 1.3063,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 0.43,
1133
+ "learning_rate": 0.00065,
1134
+ "loss": 1.4776,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 0.43,
1139
+ "learning_rate": 0.00065,
1140
+ "loss": 1.7046,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 0.44,
1145
+ "learning_rate": 0.00065,
1146
+ "loss": 1.5946,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 0.44,
1151
+ "learning_rate": 0.00065,
1152
+ "loss": 1.779,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 0.44,
1157
+ "learning_rate": 0.00065,
1158
+ "loss": 1.571,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 0.44,
1163
+ "learning_rate": 0.00065,
1164
+ "loss": 1.5513,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 0.45,
1169
+ "learning_rate": 0.00065,
1170
+ "loss": 1.4312,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 0.45,
1175
+ "learning_rate": 0.00065,
1176
+ "loss": 1.4258,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 0.45,
1181
+ "learning_rate": 0.00065,
1182
+ "loss": 1.5412,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 0.45,
1187
+ "learning_rate": 0.00065,
1188
+ "loss": 1.6545,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 0.46,
1193
+ "learning_rate": 0.00065,
1194
+ "loss": 1.5313,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 0.46,
1199
+ "learning_rate": 0.00065,
1200
+ "loss": 1.5245,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 0.46,
1205
+ "learning_rate": 0.00065,
1206
+ "loss": 1.41,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 0.46,
1211
+ "learning_rate": 0.00065,
1212
+ "loss": 1.5677,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 0.47,
1217
+ "learning_rate": 0.00065,
1218
+ "loss": 1.6269,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 0.47,
1223
+ "learning_rate": 0.00065,
1224
+ "loss": 1.6669,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 0.47,
1229
+ "learning_rate": 0.00065,
1230
+ "loss": 1.3903,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 0.47,
1235
+ "learning_rate": 0.00065,
1236
+ "loss": 1.4535,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 0.47,
1241
+ "learning_rate": 0.00065,
1242
+ "loss": 1.6028,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 0.48,
1247
+ "learning_rate": 0.00065,
1248
+ "loss": 1.3562,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 0.48,
1253
+ "learning_rate": 0.00065,
1254
+ "loss": 1.4644,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 0.48,
1259
+ "learning_rate": 0.00065,
1260
+ "loss": 1.4645,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 0.48,
1265
+ "learning_rate": 0.00065,
1266
+ "loss": 1.6715,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 0.49,
1271
+ "learning_rate": 0.00065,
1272
+ "loss": 1.3685,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 0.49,
1277
+ "learning_rate": 0.00065,
1278
+ "loss": 1.1695,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 0.49,
1283
+ "learning_rate": 0.00065,
1284
+ "loss": 1.6035,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 0.49,
1289
+ "learning_rate": 0.00065,
1290
+ "loss": 1.5142,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 0.5,
1295
+ "learning_rate": 0.00065,
1296
+ "loss": 1.5223,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 0.5,
1301
+ "learning_rate": 0.00065,
1302
+ "loss": 1.5144,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 0.5,
1307
+ "learning_rate": 0.00065,
1308
+ "loss": 1.6487,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 0.5,
1313
+ "eval_loss": 1.4980822801589966,
1314
+ "eval_runtime": 57.8018,
1315
+ "eval_samples_per_second": 8.65,
1316
+ "eval_steps_per_second": 4.325,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 0.5,
1321
+ "learning_rate": 0.00065,
1322
+ "loss": 1.4847,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 0.51,
1327
+ "learning_rate": 0.00065,
1328
+ "loss": 1.491,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 0.51,
1333
+ "learning_rate": 0.00065,
1334
+ "loss": 1.3213,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 0.51,
1339
+ "learning_rate": 0.00065,
1340
+ "loss": 1.6399,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 0.51,
1345
+ "learning_rate": 0.00065,
1346
+ "loss": 1.6079,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 0.52,
1351
+ "learning_rate": 0.00065,
1352
+ "loss": 1.4458,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 0.52,
1357
+ "learning_rate": 0.00065,
1358
+ "loss": 1.6101,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 0.52,
1363
+ "learning_rate": 0.00065,
1364
+ "loss": 1.6516,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 0.52,
1369
+ "learning_rate": 0.00065,
1370
+ "loss": 1.4794,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 0.53,
1375
+ "learning_rate": 0.00065,
1376
+ "loss": 1.7151,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 0.53,
1381
+ "learning_rate": 0.00065,
1382
+ "loss": 1.5805,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 0.53,
1387
+ "learning_rate": 0.00065,
1388
+ "loss": 1.5088,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 0.53,
1393
+ "learning_rate": 0.00065,
1394
+ "loss": 1.5852,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 0.53,
1399
+ "learning_rate": 0.00065,
1400
+ "loss": 1.3886,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 0.54,
1405
+ "learning_rate": 0.00065,
1406
+ "loss": 1.7186,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 0.54,
1411
+ "learning_rate": 0.00065,
1412
+ "loss": 1.6551,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 0.54,
1417
+ "learning_rate": 0.00065,
1418
+ "loss": 1.5615,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 0.54,
1423
+ "learning_rate": 0.00065,
1424
+ "loss": 1.8389,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 0.55,
1429
+ "learning_rate": 0.00065,
1430
+ "loss": 1.5447,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 0.55,
1435
+ "learning_rate": 0.00065,
1436
+ "loss": 1.4015,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 0.55,
1441
+ "learning_rate": 0.00065,
1442
+ "loss": 1.5386,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 0.55,
1447
+ "learning_rate": 0.00065,
1448
+ "loss": 1.6429,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 0.56,
1453
+ "learning_rate": 0.00065,
1454
+ "loss": 1.5531,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 0.56,
1459
+ "learning_rate": 0.00065,
1460
+ "loss": 1.3572,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 0.56,
1465
+ "learning_rate": 0.00065,
1466
+ "loss": 1.3011,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 0.56,
1471
+ "learning_rate": 0.00065,
1472
+ "loss": 1.7356,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 0.57,
1477
+ "learning_rate": 0.00065,
1478
+ "loss": 1.2688,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 0.57,
1483
+ "learning_rate": 0.00065,
1484
+ "loss": 1.5885,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 0.57,
1489
+ "learning_rate": 0.00065,
1490
+ "loss": 1.5765,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 0.57,
1495
+ "learning_rate": 0.00065,
1496
+ "loss": 1.3705,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 0.58,
1501
+ "learning_rate": 0.00065,
1502
+ "loss": 1.4097,
1503
+ "step": 241
1504
+ },
1505
+ {
1506
+ "epoch": 0.58,
1507
+ "learning_rate": 0.00065,
1508
+ "loss": 1.5182,
1509
+ "step": 242
1510
+ },
1511
+ {
1512
+ "epoch": 0.58,
1513
+ "learning_rate": 0.00065,
1514
+ "loss": 1.2854,
1515
+ "step": 243
1516
+ },
1517
+ {
1518
+ "epoch": 0.58,
1519
+ "learning_rate": 0.00065,
1520
+ "loss": 1.8305,
1521
+ "step": 244
1522
+ },
1523
+ {
1524
+ "epoch": 0.58,
1525
+ "learning_rate": 0.00065,
1526
+ "loss": 1.0632,
1527
+ "step": 245
1528
+ },
1529
+ {
1530
+ "epoch": 0.59,
1531
+ "learning_rate": 0.00065,
1532
+ "loss": 1.5128,
1533
+ "step": 246
1534
+ },
1535
+ {
1536
+ "epoch": 0.59,
1537
+ "learning_rate": 0.00065,
1538
+ "loss": 1.545,
1539
+ "step": 247
1540
+ },
1541
+ {
1542
+ "epoch": 0.59,
1543
+ "learning_rate": 0.00065,
1544
+ "loss": 1.4362,
1545
+ "step": 248
1546
+ },
1547
+ {
1548
+ "epoch": 0.59,
1549
+ "learning_rate": 0.00065,
1550
+ "loss": 1.093,
1551
+ "step": 249
1552
+ },
1553
+ {
1554
+ "epoch": 0.6,
1555
+ "learning_rate": 0.00065,
1556
+ "loss": 1.5286,
1557
+ "step": 250
1558
+ },
1559
+ {
1560
+ "epoch": 0.6,
1561
+ "learning_rate": 0.00065,
1562
+ "loss": 1.5218,
1563
+ "step": 251
1564
+ },
1565
+ {
1566
+ "epoch": 0.6,
1567
+ "learning_rate": 0.00065,
1568
+ "loss": 1.6147,
1569
+ "step": 252
1570
+ },
1571
+ {
1572
+ "epoch": 0.6,
1573
+ "eval_loss": 1.4965262413024902,
1574
+ "eval_runtime": 57.8272,
1575
+ "eval_samples_per_second": 8.646,
1576
+ "eval_steps_per_second": 4.323,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 0.6,
1581
+ "learning_rate": 0.00065,
1582
+ "loss": 1.6172,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 0.61,
1587
+ "learning_rate": 0.00065,
1588
+ "loss": 1.4856,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 0.61,
1593
+ "learning_rate": 0.00065,
1594
+ "loss": 1.6167,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 0.61,
1599
+ "learning_rate": 0.00065,
1600
+ "loss": 1.5882,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 0.61,
1605
+ "learning_rate": 0.00065,
1606
+ "loss": 1.4952,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 0.62,
1611
+ "learning_rate": 0.00065,
1612
+ "loss": 1.5929,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 0.62,
1617
+ "learning_rate": 0.00065,
1618
+ "loss": 1.314,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 0.62,
1623
+ "learning_rate": 0.00065,
1624
+ "loss": 1.3682,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 0.62,
1629
+ "learning_rate": 0.00065,
1630
+ "loss": 1.5718,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 0.63,
1635
+ "learning_rate": 0.00065,
1636
+ "loss": 1.337,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 0.63,
1641
+ "learning_rate": 0.00065,
1642
+ "loss": 1.7287,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 0.63,
1647
+ "learning_rate": 0.00065,
1648
+ "loss": 1.685,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 0.63,
1653
+ "learning_rate": 0.00065,
1654
+ "loss": 1.1973,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 0.63,
1659
+ "learning_rate": 0.00065,
1660
+ "loss": 1.4037,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 0.64,
1665
+ "learning_rate": 0.00065,
1666
+ "loss": 1.3741,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 0.64,
1671
+ "learning_rate": 0.00065,
1672
+ "loss": 1.6339,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 0.64,
1677
+ "learning_rate": 0.00065,
1678
+ "loss": 1.6981,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 0.64,
1683
+ "learning_rate": 0.00065,
1684
+ "loss": 1.4383,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 0.65,
1689
+ "learning_rate": 0.00065,
1690
+ "loss": 1.5721,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 0.65,
1695
+ "learning_rate": 0.00065,
1696
+ "loss": 1.587,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 0.65,
1701
+ "learning_rate": 0.00065,
1702
+ "loss": 1.8308,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 0.65,
1707
+ "learning_rate": 0.00065,
1708
+ "loss": 1.3733,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 0.66,
1713
+ "learning_rate": 0.00065,
1714
+ "loss": 1.6366,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 0.66,
1719
+ "learning_rate": 0.00065,
1720
+ "loss": 1.4057,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 0.66,
1725
+ "learning_rate": 0.00065,
1726
+ "loss": 1.6264,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 0.66,
1731
+ "learning_rate": 0.00065,
1732
+ "loss": 1.5546,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 0.67,
1737
+ "learning_rate": 0.00065,
1738
+ "loss": 1.567,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 0.67,
1743
+ "learning_rate": 0.00065,
1744
+ "loss": 1.312,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 0.67,
1749
+ "learning_rate": 0.00065,
1750
+ "loss": 1.438,
1751
+ "step": 281
1752
+ },
1753
+ {
1754
+ "epoch": 0.67,
1755
+ "learning_rate": 0.00065,
1756
+ "loss": 1.4226,
1757
+ "step": 282
1758
+ },
1759
+ {
1760
+ "epoch": 0.68,
1761
+ "learning_rate": 0.00065,
1762
+ "loss": 1.4871,
1763
+ "step": 283
1764
+ },
1765
+ {
1766
+ "epoch": 0.68,
1767
+ "learning_rate": 0.00065,
1768
+ "loss": 1.5465,
1769
+ "step": 284
1770
+ },
1771
+ {
1772
+ "epoch": 0.68,
1773
+ "learning_rate": 0.00065,
1774
+ "loss": 1.4989,
1775
+ "step": 285
1776
+ },
1777
+ {
1778
+ "epoch": 0.68,
1779
+ "learning_rate": 0.00065,
1780
+ "loss": 1.6361,
1781
+ "step": 286
1782
+ },
1783
+ {
1784
+ "epoch": 0.68,
1785
+ "learning_rate": 0.00065,
1786
+ "loss": 1.5529,
1787
+ "step": 287
1788
+ },
1789
+ {
1790
+ "epoch": 0.69,
1791
+ "learning_rate": 0.00065,
1792
+ "loss": 1.334,
1793
+ "step": 288
1794
+ },
1795
+ {
1796
+ "epoch": 0.69,
1797
+ "learning_rate": 0.00065,
1798
+ "loss": 1.6348,
1799
+ "step": 289
1800
+ },
1801
+ {
1802
+ "epoch": 0.69,
1803
+ "learning_rate": 0.00065,
1804
+ "loss": 1.6611,
1805
+ "step": 290
1806
+ },
1807
+ {
1808
+ "epoch": 0.69,
1809
+ "learning_rate": 0.00065,
1810
+ "loss": 1.3462,
1811
+ "step": 291
1812
+ },
1813
+ {
1814
+ "epoch": 0.7,
1815
+ "learning_rate": 0.00065,
1816
+ "loss": 1.3151,
1817
+ "step": 292
1818
+ },
1819
+ {
1820
+ "epoch": 0.7,
1821
+ "learning_rate": 0.00065,
1822
+ "loss": 1.4333,
1823
+ "step": 293
1824
+ },
1825
+ {
1826
+ "epoch": 0.7,
1827
+ "learning_rate": 0.00065,
1828
+ "loss": 1.3048,
1829
+ "step": 294
1830
+ },
1831
+ {
1832
+ "epoch": 0.7,
1833
+ "eval_loss": 1.4973247051239014,
1834
+ "eval_runtime": 57.7873,
1835
+ "eval_samples_per_second": 8.652,
1836
+ "eval_steps_per_second": 4.326,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 0.7,
1841
+ "learning_rate": 0.00065,
1842
+ "loss": 1.5376,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 0.71,
1847
+ "learning_rate": 0.00065,
1848
+ "loss": 1.5643,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 0.71,
1853
+ "learning_rate": 0.00065,
1854
+ "loss": 1.6501,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 0.71,
1859
+ "learning_rate": 0.00065,
1860
+ "loss": 1.3652,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 0.71,
1865
+ "learning_rate": 0.00065,
1866
+ "loss": 1.5191,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 0.72,
1871
+ "learning_rate": 0.00065,
1872
+ "loss": 1.5722,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 0.72,
1877
+ "learning_rate": 0.00065,
1878
+ "loss": 1.5057,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 0.72,
1883
+ "learning_rate": 0.00065,
1884
+ "loss": 1.3798,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 0.72,
1889
+ "learning_rate": 0.00065,
1890
+ "loss": 1.3492,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 0.73,
1895
+ "learning_rate": 0.00065,
1896
+ "loss": 1.3582,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 0.73,
1901
+ "learning_rate": 0.00065,
1902
+ "loss": 1.5691,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 0.73,
1907
+ "learning_rate": 0.00065,
1908
+ "loss": 1.6634,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 0.73,
1913
+ "learning_rate": 0.00065,
1914
+ "loss": 1.6464,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 0.74,
1919
+ "learning_rate": 0.00065,
1920
+ "loss": 1.4683,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 0.74,
1925
+ "learning_rate": 0.00065,
1926
+ "loss": 1.5424,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 0.74,
1931
+ "learning_rate": 0.00065,
1932
+ "loss": 1.5145,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 0.74,
1937
+ "learning_rate": 0.00065,
1938
+ "loss": 1.6582,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 0.74,
1943
+ "learning_rate": 0.00065,
1944
+ "loss": 1.3616,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 0.75,
1949
+ "learning_rate": 0.00065,
1950
+ "loss": 1.5284,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 0.75,
1955
+ "learning_rate": 0.00065,
1956
+ "loss": 1.1895,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 0.75,
1961
+ "learning_rate": 0.00065,
1962
+ "loss": 1.6037,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 0.75,
1967
+ "learning_rate": 0.00065,
1968
+ "loss": 1.5233,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 0.76,
1973
+ "learning_rate": 0.00065,
1974
+ "loss": 1.6914,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 0.76,
1979
+ "learning_rate": 0.00065,
1980
+ "loss": 1.4968,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 0.76,
1985
+ "learning_rate": 0.00065,
1986
+ "loss": 1.2765,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 0.76,
1991
+ "learning_rate": 0.00065,
1992
+ "loss": 1.6675,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 0.77,
1997
+ "learning_rate": 0.00065,
1998
+ "loss": 1.723,
1999
+ "step": 321
2000
+ },
2001
+ {
2002
+ "epoch": 0.77,
2003
+ "learning_rate": 0.00065,
2004
+ "loss": 1.4832,
2005
+ "step": 322
2006
+ },
2007
+ {
2008
+ "epoch": 0.77,
2009
+ "learning_rate": 0.00065,
2010
+ "loss": 1.179,
2011
+ "step": 323
2012
+ },
2013
+ {
2014
+ "epoch": 0.77,
2015
+ "learning_rate": 0.00065,
2016
+ "loss": 1.5108,
2017
+ "step": 324
2018
+ },
2019
+ {
2020
+ "epoch": 0.78,
2021
+ "learning_rate": 0.00065,
2022
+ "loss": 1.3931,
2023
+ "step": 325
2024
+ },
2025
+ {
2026
+ "epoch": 0.78,
2027
+ "learning_rate": 0.00065,
2028
+ "loss": 1.6227,
2029
+ "step": 326
2030
+ },
2031
+ {
2032
+ "epoch": 0.78,
2033
+ "learning_rate": 0.00065,
2034
+ "loss": 1.353,
2035
+ "step": 327
2036
+ },
2037
+ {
2038
+ "epoch": 0.78,
2039
+ "learning_rate": 0.00065,
2040
+ "loss": 1.5377,
2041
+ "step": 328
2042
+ },
2043
+ {
2044
+ "epoch": 0.79,
2045
+ "learning_rate": 0.00065,
2046
+ "loss": 1.6277,
2047
+ "step": 329
2048
+ },
2049
+ {
2050
+ "epoch": 0.79,
2051
+ "learning_rate": 0.00065,
2052
+ "loss": 1.4532,
2053
+ "step": 330
2054
+ },
2055
+ {
2056
+ "epoch": 0.79,
2057
+ "learning_rate": 0.00065,
2058
+ "loss": 1.6329,
2059
+ "step": 331
2060
+ },
2061
+ {
2062
+ "epoch": 0.79,
2063
+ "learning_rate": 0.00065,
2064
+ "loss": 1.6595,
2065
+ "step": 332
2066
+ },
2067
+ {
2068
+ "epoch": 0.79,
2069
+ "learning_rate": 0.00065,
2070
+ "loss": 1.4014,
2071
+ "step": 333
2072
+ },
2073
+ {
2074
+ "epoch": 0.8,
2075
+ "learning_rate": 0.00065,
2076
+ "loss": 1.4108,
2077
+ "step": 334
2078
+ },
2079
+ {
2080
+ "epoch": 0.8,
2081
+ "learning_rate": 0.00065,
2082
+ "loss": 1.5729,
2083
+ "step": 335
2084
+ },
2085
+ {
2086
+ "epoch": 0.8,
2087
+ "learning_rate": 0.00065,
2088
+ "loss": 1.6205,
2089
+ "step": 336
2090
+ },
2091
+ {
2092
+ "epoch": 0.8,
2093
+ "eval_loss": 1.5006886720657349,
2094
+ "eval_runtime": 57.756,
2095
+ "eval_samples_per_second": 8.657,
2096
+ "eval_steps_per_second": 4.329,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 0.8,
2101
+ "learning_rate": 0.00065,
2102
+ "loss": 1.5595,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 0.81,
2107
+ "learning_rate": 0.00065,
2108
+ "loss": 1.4389,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 0.81,
2113
+ "learning_rate": 0.00065,
2114
+ "loss": 1.6702,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 0.81,
2119
+ "learning_rate": 0.00065,
2120
+ "loss": 1.7348,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 0.81,
2125
+ "learning_rate": 0.00065,
2126
+ "loss": 1.5383,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 0.82,
2131
+ "learning_rate": 0.00065,
2132
+ "loss": 1.2777,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 0.82,
2137
+ "learning_rate": 0.00065,
2138
+ "loss": 1.4466,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 0.82,
2143
+ "learning_rate": 0.00065,
2144
+ "loss": 1.4665,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 0.82,
2149
+ "learning_rate": 0.00065,
2150
+ "loss": 1.595,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 0.83,
2155
+ "learning_rate": 0.00065,
2156
+ "loss": 1.4895,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 0.83,
2161
+ "learning_rate": 0.00065,
2162
+ "loss": 1.4753,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 0.83,
2167
+ "learning_rate": 0.00065,
2168
+ "loss": 1.4371,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 0.83,
2173
+ "learning_rate": 0.00065,
2174
+ "loss": 1.4467,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 0.84,
2179
+ "learning_rate": 0.00065,
2180
+ "loss": 1.2601,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 0.84,
2185
+ "learning_rate": 0.00065,
2186
+ "loss": 1.1586,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 0.84,
2191
+ "learning_rate": 0.00065,
2192
+ "loss": 1.7566,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 0.84,
2197
+ "learning_rate": 0.00065,
2198
+ "loss": 1.5955,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 0.84,
2203
+ "learning_rate": 0.00065,
2204
+ "loss": 1.3872,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 0.85,
2209
+ "learning_rate": 0.00065,
2210
+ "loss": 1.3124,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 0.85,
2215
+ "learning_rate": 0.00065,
2216
+ "loss": 1.5033,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 0.85,
2221
+ "learning_rate": 0.00065,
2222
+ "loss": 1.6921,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 0.85,
2227
+ "learning_rate": 0.00065,
2228
+ "loss": 1.5243,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 0.86,
2233
+ "learning_rate": 0.00065,
2234
+ "loss": 1.5287,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 0.86,
2239
+ "learning_rate": 0.00065,
2240
+ "loss": 1.4257,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 0.86,
2245
+ "learning_rate": 0.00065,
2246
+ "loss": 1.3924,
2247
+ "step": 361
2248
+ },
2249
+ {
2250
+ "epoch": 0.86,
2251
+ "learning_rate": 0.00065,
2252
+ "loss": 1.6084,
2253
+ "step": 362
2254
+ },
2255
+ {
2256
+ "epoch": 0.87,
2257
+ "learning_rate": 0.00065,
2258
+ "loss": 1.5605,
2259
+ "step": 363
2260
+ },
2261
+ {
2262
+ "epoch": 0.87,
2263
+ "learning_rate": 0.00065,
2264
+ "loss": 1.6319,
2265
+ "step": 364
2266
+ },
2267
+ {
2268
+ "epoch": 0.87,
2269
+ "learning_rate": 0.00065,
2270
+ "loss": 1.5691,
2271
+ "step": 365
2272
+ },
2273
+ {
2274
+ "epoch": 0.87,
2275
+ "learning_rate": 0.00065,
2276
+ "loss": 1.311,
2277
+ "step": 366
2278
+ },
2279
+ {
2280
+ "epoch": 0.88,
2281
+ "learning_rate": 0.00065,
2282
+ "loss": 1.4892,
2283
+ "step": 367
2284
+ },
2285
+ {
2286
+ "epoch": 0.88,
2287
+ "learning_rate": 0.00065,
2288
+ "loss": 1.3108,
2289
+ "step": 368
2290
+ },
2291
+ {
2292
+ "epoch": 0.88,
2293
+ "learning_rate": 0.00065,
2294
+ "loss": 1.6953,
2295
+ "step": 369
2296
+ },
2297
+ {
2298
+ "epoch": 0.88,
2299
+ "learning_rate": 0.00065,
2300
+ "loss": 1.5857,
2301
+ "step": 370
2302
+ },
2303
+ {
2304
+ "epoch": 0.89,
2305
+ "learning_rate": 0.00065,
2306
+ "loss": 1.4536,
2307
+ "step": 371
2308
+ },
2309
+ {
2310
+ "epoch": 0.89,
2311
+ "learning_rate": 0.00065,
2312
+ "loss": 1.4781,
2313
+ "step": 372
2314
+ },
2315
+ {
2316
+ "epoch": 0.89,
2317
+ "learning_rate": 0.00065,
2318
+ "loss": 1.5191,
2319
+ "step": 373
2320
+ },
2321
+ {
2322
+ "epoch": 0.89,
2323
+ "learning_rate": 0.00065,
2324
+ "loss": 1.5136,
2325
+ "step": 374
2326
+ },
2327
+ {
2328
+ "epoch": 0.89,
2329
+ "learning_rate": 0.00065,
2330
+ "loss": 1.5246,
2331
+ "step": 375
2332
+ },
2333
+ {
2334
+ "epoch": 0.9,
2335
+ "learning_rate": 0.00065,
2336
+ "loss": 1.022,
2337
+ "step": 376
2338
+ },
2339
+ {
2340
+ "epoch": 0.9,
2341
+ "learning_rate": 0.00065,
2342
+ "loss": 1.5182,
2343
+ "step": 377
2344
+ },
2345
+ {
2346
+ "epoch": 0.9,
2347
+ "learning_rate": 0.00065,
2348
+ "loss": 1.6045,
2349
+ "step": 378
2350
+ },
2351
+ {
2352
+ "epoch": 0.9,
2353
+ "eval_loss": 1.5002774000167847,
2354
+ "eval_runtime": 57.7872,
2355
+ "eval_samples_per_second": 8.652,
2356
+ "eval_steps_per_second": 4.326,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 0.9,
2361
+ "learning_rate": 0.00065,
2362
+ "loss": 1.6214,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 0.91,
2367
+ "learning_rate": 0.00065,
2368
+ "loss": 1.4893,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 0.91,
2373
+ "learning_rate": 0.00065,
2374
+ "loss": 1.5942,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 0.91,
2379
+ "learning_rate": 0.00065,
2380
+ "loss": 1.369,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 0.91,
2385
+ "learning_rate": 0.00065,
2386
+ "loss": 1.0446,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 0.92,
2391
+ "learning_rate": 0.00065,
2392
+ "loss": 1.63,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 0.92,
2397
+ "learning_rate": 0.00065,
2398
+ "loss": 1.5157,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 0.92,
2403
+ "learning_rate": 0.00065,
2404
+ "loss": 1.4303,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 0.92,
2409
+ "learning_rate": 0.00065,
2410
+ "loss": 1.539,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 0.93,
2415
+ "learning_rate": 0.00065,
2416
+ "loss": 1.3132,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 0.93,
2421
+ "learning_rate": 0.00065,
2422
+ "loss": 1.0668,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 0.93,
2427
+ "learning_rate": 0.00065,
2428
+ "loss": 1.5303,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 0.93,
2433
+ "learning_rate": 0.00065,
2434
+ "loss": 1.5204,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 0.94,
2439
+ "learning_rate": 0.00065,
2440
+ "loss": 1.6575,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 0.94,
2445
+ "learning_rate": 0.00065,
2446
+ "loss": 1.5325,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 0.94,
2451
+ "learning_rate": 0.00065,
2452
+ "loss": 1.6132,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 0.94,
2457
+ "learning_rate": 0.00065,
2458
+ "loss": 1.4253,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 0.95,
2463
+ "learning_rate": 0.00065,
2464
+ "loss": 1.2638,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 0.95,
2469
+ "learning_rate": 0.00065,
2470
+ "loss": 1.5054,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 0.95,
2475
+ "learning_rate": 0.00065,
2476
+ "loss": 1.6769,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 0.95,
2481
+ "learning_rate": 0.00065,
2482
+ "loss": 1.5845,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 0.95,
2487
+ "learning_rate": 0.00065,
2488
+ "loss": 1.2866,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 0.96,
2493
+ "learning_rate": 0.00065,
2494
+ "loss": 1.1569,
2495
+ "step": 401
2496
+ },
2497
+ {
2498
+ "epoch": 0.96,
2499
+ "learning_rate": 0.00065,
2500
+ "loss": 1.2087,
2501
+ "step": 402
2502
+ },
2503
+ {
2504
+ "epoch": 0.96,
2505
+ "learning_rate": 0.00065,
2506
+ "loss": 1.6248,
2507
+ "step": 403
2508
+ },
2509
+ {
2510
+ "epoch": 0.96,
2511
+ "learning_rate": 0.00065,
2512
+ "loss": 1.5012,
2513
+ "step": 404
2514
+ },
2515
+ {
2516
+ "epoch": 0.97,
2517
+ "learning_rate": 0.00065,
2518
+ "loss": 1.6551,
2519
+ "step": 405
2520
+ },
2521
+ {
2522
+ "epoch": 0.97,
2523
+ "learning_rate": 0.00065,
2524
+ "loss": 1.4988,
2525
+ "step": 406
2526
+ },
2527
+ {
2528
+ "epoch": 0.97,
2529
+ "learning_rate": 0.00065,
2530
+ "loss": 1.4565,
2531
+ "step": 407
2532
+ },
2533
+ {
2534
+ "epoch": 0.97,
2535
+ "learning_rate": 0.00065,
2536
+ "loss": 1.2717,
2537
+ "step": 408
2538
+ },
2539
+ {
2540
+ "epoch": 0.98,
2541
+ "learning_rate": 0.00065,
2542
+ "loss": 1.7323,
2543
+ "step": 409
2544
+ },
2545
+ {
2546
+ "epoch": 0.98,
2547
+ "learning_rate": 0.00065,
2548
+ "loss": 1.5811,
2549
+ "step": 410
2550
+ },
2551
+ {
2552
+ "epoch": 0.98,
2553
+ "learning_rate": 0.00065,
2554
+ "loss": 1.4139,
2555
+ "step": 411
2556
+ },
2557
+ {
2558
+ "epoch": 0.98,
2559
+ "learning_rate": 0.00065,
2560
+ "loss": 1.4657,
2561
+ "step": 412
2562
+ },
2563
+ {
2564
+ "epoch": 0.99,
2565
+ "learning_rate": 0.00065,
2566
+ "loss": 1.5507,
2567
+ "step": 413
2568
+ },
2569
+ {
2570
+ "epoch": 0.99,
2571
+ "learning_rate": 0.00065,
2572
+ "loss": 1.4202,
2573
+ "step": 414
2574
+ },
2575
+ {
2576
+ "epoch": 0.99,
2577
+ "learning_rate": 0.00065,
2578
+ "loss": 1.412,
2579
+ "step": 415
2580
+ },
2581
+ {
2582
+ "epoch": 0.99,
2583
+ "learning_rate": 0.00065,
2584
+ "loss": 1.5208,
2585
+ "step": 416
2586
+ },
2587
+ {
2588
+ "epoch": 1.0,
2589
+ "learning_rate": 0.00065,
2590
+ "loss": 1.5733,
2591
+ "step": 417
2592
+ },
2593
+ {
2594
+ "epoch": 1.0,
2595
+ "learning_rate": 0.00065,
2596
+ "loss": 1.6295,
2597
+ "step": 418
2598
+ },
2599
+ {
2600
+ "epoch": 1.0,
2601
+ "learning_rate": 0.00065,
2602
+ "loss": 1.4903,
2603
+ "step": 419
2604
+ },
2605
+ {
2606
+ "epoch": 1.0,
2607
+ "learning_rate": 0.00065,
2608
+ "loss": 1.5781,
2609
+ "step": 420
2610
+ },
2611
+ {
2612
+ "epoch": 1.0,
2613
+ "eval_loss": 1.5013374090194702,
2614
+ "eval_runtime": 57.703,
2615
+ "eval_samples_per_second": 8.665,
2616
+ "eval_steps_per_second": 4.333,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 1.0,
2621
+ "learning_rate": 0.00065,
2622
+ "loss": 1.6304,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 1.01,
2627
+ "learning_rate": 0.00065,
2628
+ "loss": 1.6533,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 1.01,
2633
+ "learning_rate": 0.00065,
2634
+ "loss": 1.3432,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 1.01,
2639
+ "learning_rate": 0.00065,
2640
+ "loss": 1.5377,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 1.01,
2645
+ "learning_rate": 0.00065,
2646
+ "loss": 1.6638,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 1.02,
2651
+ "learning_rate": 0.00065,
2652
+ "loss": 1.5242,
2653
+ "step": 426
2654
+ }
2655
+ ],
2656
+ "logging_steps": 1,
2657
+ "max_steps": 838,
2658
+ "num_train_epochs": 2,
2659
+ "save_steps": 500,
2660
+ "total_flos": 2.900732084748288e+17,
2661
+ "trial_name": null,
2662
+ "trial_params": null
2663
+ }
checkpoint-426/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f24abc70e9c40aaecc2a1a7a785166489fdb1864d287910b01cbf2605591d57
3
+ size 4475
checkpoint-838/README.md ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./TheBloke_Llama-2-13B-fp16
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 0.6.0
checkpoint-838/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./TheBloke_Llama-2-13B-fp16",
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": 256,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "v_proj",
21
+ "up_proj",
22
+ "q_proj",
23
+ "down_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-838/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aafec848efab6d151b2c04a8cc451b1422ae863820d9defbca5929e730951922
3
+ size 4005763213
checkpoint-838/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770b22ed3afcc0f79a52d1571bbb4ffc167430974ce7b96ea4ced7c7f0fe821c
3
+ size 8011604773
checkpoint-838/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db59c36d0626b360ec9b2e4ea270a36de6b1bcf33e7e555f4e87a954379be2d
3
+ size 14575
checkpoint-838/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca28dfa4f5d4530dfbaf4673637f02768393bcc90e0eb9a1de112a68b20a7da
3
+ size 627
checkpoint-838/trainer_state.json ADDED
@@ -0,0 +1,5207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9832935560859188,
5
+ "eval_steps": 42,
6
+ "global_step": 838,
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": 0.00065,
14
+ "loss": 1.5523,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": 1.5476094484329224,
20
+ "eval_runtime": 57.6973,
21
+ "eval_samples_per_second": 8.666,
22
+ "eval_steps_per_second": 4.333,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "learning_rate": 0.00065,
28
+ "loss": 1.6985,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 0.00065,
34
+ "loss": 1.1799,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.01,
39
+ "learning_rate": 0.00065,
40
+ "loss": 1.7743,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.01,
45
+ "learning_rate": 0.00065,
46
+ "loss": 1.6175,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.01,
51
+ "learning_rate": 0.00065,
52
+ "loss": 1.5657,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "learning_rate": 0.00065,
58
+ "loss": 1.4462,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 0.00065,
64
+ "loss": 1.4567,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "learning_rate": 0.00065,
70
+ "loss": 1.734,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.02,
75
+ "learning_rate": 0.00065,
76
+ "loss": 1.4707,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "learning_rate": 0.00065,
82
+ "loss": 1.5891,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.03,
87
+ "learning_rate": 0.00065,
88
+ "loss": 1.4921,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.03,
93
+ "learning_rate": 0.00065,
94
+ "loss": 1.5806,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.03,
99
+ "learning_rate": 0.00065,
100
+ "loss": 1.4224,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.04,
105
+ "learning_rate": 0.00065,
106
+ "loss": 1.4779,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.04,
111
+ "learning_rate": 0.00065,
112
+ "loss": 1.5828,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.04,
117
+ "learning_rate": 0.00065,
118
+ "loss": 1.4379,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.04,
123
+ "learning_rate": 0.00065,
124
+ "loss": 1.5227,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.05,
129
+ "learning_rate": 0.00065,
130
+ "loss": 1.3899,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.05,
135
+ "learning_rate": 0.00065,
136
+ "loss": 1.3557,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.05,
141
+ "learning_rate": 0.00065,
142
+ "loss": 1.5049,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.05,
147
+ "learning_rate": 0.00065,
148
+ "loss": 1.5334,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.05,
153
+ "learning_rate": 0.00065,
154
+ "loss": 1.1747,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.06,
159
+ "learning_rate": 0.00065,
160
+ "loss": 1.5094,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.06,
165
+ "learning_rate": 0.00065,
166
+ "loss": 1.4909,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.06,
171
+ "learning_rate": 0.00065,
172
+ "loss": 1.521,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.06,
177
+ "learning_rate": 0.00065,
178
+ "loss": 1.5296,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.07,
183
+ "learning_rate": 0.00065,
184
+ "loss": 1.5475,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.07,
189
+ "learning_rate": 0.00065,
190
+ "loss": 1.5203,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.07,
195
+ "learning_rate": 0.00065,
196
+ "loss": 1.4874,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.07,
201
+ "learning_rate": 0.00065,
202
+ "loss": 1.6169,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.08,
207
+ "learning_rate": 0.00065,
208
+ "loss": 1.5158,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.08,
213
+ "learning_rate": 0.00065,
214
+ "loss": 1.5844,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.08,
219
+ "learning_rate": 0.00065,
220
+ "loss": 1.4701,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.08,
225
+ "learning_rate": 0.00065,
226
+ "loss": 1.3729,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.09,
231
+ "learning_rate": 0.00065,
232
+ "loss": 1.5067,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.09,
237
+ "learning_rate": 0.00065,
238
+ "loss": 1.4972,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.09,
243
+ "learning_rate": 0.00065,
244
+ "loss": 1.8079,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.09,
249
+ "learning_rate": 0.00065,
250
+ "loss": 1.5681,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.1,
255
+ "learning_rate": 0.00065,
256
+ "loss": 1.4852,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.1,
261
+ "learning_rate": 0.00065,
262
+ "loss": 1.5448,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.1,
267
+ "learning_rate": 0.00065,
268
+ "loss": 1.2139,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.1,
273
+ "eval_loss": 1.500810146331787,
274
+ "eval_runtime": 57.801,
275
+ "eval_samples_per_second": 8.65,
276
+ "eval_steps_per_second": 4.325,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.1,
281
+ "learning_rate": 0.00065,
282
+ "loss": 1.4483,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.11,
287
+ "learning_rate": 0.00065,
288
+ "loss": 1.3328,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.11,
293
+ "learning_rate": 0.00065,
294
+ "loss": 1.4363,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.11,
299
+ "learning_rate": 0.00065,
300
+ "loss": 1.2864,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.11,
305
+ "learning_rate": 0.00065,
306
+ "loss": 1.4731,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.11,
311
+ "learning_rate": 0.00065,
312
+ "loss": 1.5103,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.12,
317
+ "learning_rate": 0.00065,
318
+ "loss": 1.5552,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.12,
323
+ "learning_rate": 0.00065,
324
+ "loss": 1.4697,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.12,
329
+ "learning_rate": 0.00065,
330
+ "loss": 1.5153,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.12,
335
+ "learning_rate": 0.00065,
336
+ "loss": 1.4696,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.13,
341
+ "learning_rate": 0.00065,
342
+ "loss": 1.4874,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.13,
347
+ "learning_rate": 0.00065,
348
+ "loss": 1.6397,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.13,
353
+ "learning_rate": 0.00065,
354
+ "loss": 1.5159,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.13,
359
+ "learning_rate": 0.00065,
360
+ "loss": 1.5399,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.14,
365
+ "learning_rate": 0.00065,
366
+ "loss": 1.573,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.14,
371
+ "learning_rate": 0.00065,
372
+ "loss": 1.5067,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.14,
377
+ "learning_rate": 0.00065,
378
+ "loss": 1.5585,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.14,
383
+ "learning_rate": 0.00065,
384
+ "loss": 1.4998,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.15,
389
+ "learning_rate": 0.00065,
390
+ "loss": 1.0471,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.15,
395
+ "learning_rate": 0.00065,
396
+ "loss": 1.5023,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.15,
401
+ "learning_rate": 0.00065,
402
+ "loss": 1.241,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.15,
407
+ "learning_rate": 0.00065,
408
+ "loss": 1.2748,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.16,
413
+ "learning_rate": 0.00065,
414
+ "loss": 1.598,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.16,
419
+ "learning_rate": 0.00065,
420
+ "loss": 1.7209,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.16,
425
+ "learning_rate": 0.00065,
426
+ "loss": 1.4492,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.16,
431
+ "learning_rate": 0.00065,
432
+ "loss": 1.6432,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.16,
437
+ "learning_rate": 0.00065,
438
+ "loss": 1.4849,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.17,
443
+ "learning_rate": 0.00065,
444
+ "loss": 1.3859,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.17,
449
+ "learning_rate": 0.00065,
450
+ "loss": 1.2329,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.17,
455
+ "learning_rate": 0.00065,
456
+ "loss": 1.4836,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.17,
461
+ "learning_rate": 0.00065,
462
+ "loss": 1.5757,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.18,
467
+ "learning_rate": 0.00065,
468
+ "loss": 1.4403,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.18,
473
+ "learning_rate": 0.00065,
474
+ "loss": 1.4311,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.18,
479
+ "learning_rate": 0.00065,
480
+ "loss": 1.7698,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.18,
485
+ "learning_rate": 0.00065,
486
+ "loss": 1.4067,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.19,
491
+ "learning_rate": 0.00065,
492
+ "loss": 1.3548,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.19,
497
+ "learning_rate": 0.00065,
498
+ "loss": 1.2219,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.19,
503
+ "learning_rate": 0.00065,
504
+ "loss": 1.2774,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.19,
509
+ "learning_rate": 0.00065,
510
+ "loss": 1.5268,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.2,
515
+ "learning_rate": 0.00065,
516
+ "loss": 1.6669,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.2,
521
+ "learning_rate": 0.00065,
522
+ "loss": 1.4055,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.2,
527
+ "learning_rate": 0.00065,
528
+ "loss": 1.6348,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.2,
533
+ "eval_loss": 1.4967617988586426,
534
+ "eval_runtime": 57.7521,
535
+ "eval_samples_per_second": 8.658,
536
+ "eval_steps_per_second": 4.329,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.2,
541
+ "learning_rate": 0.00065,
542
+ "loss": 1.4524,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.21,
547
+ "learning_rate": 0.00065,
548
+ "loss": 1.7781,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.21,
553
+ "learning_rate": 0.00065,
554
+ "loss": 1.4317,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.21,
559
+ "learning_rate": 0.00065,
560
+ "loss": 1.5865,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.21,
565
+ "learning_rate": 0.00065,
566
+ "loss": 1.465,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.21,
571
+ "learning_rate": 0.00065,
572
+ "loss": 1.5601,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.22,
577
+ "learning_rate": 0.00065,
578
+ "loss": 1.4393,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.22,
583
+ "learning_rate": 0.00065,
584
+ "loss": 1.5499,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.22,
589
+ "learning_rate": 0.00065,
590
+ "loss": 1.5289,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.22,
595
+ "learning_rate": 0.00065,
596
+ "loss": 1.6562,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.23,
601
+ "learning_rate": 0.00065,
602
+ "loss": 1.6702,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.23,
607
+ "learning_rate": 0.00065,
608
+ "loss": 1.4044,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.23,
613
+ "learning_rate": 0.00065,
614
+ "loss": 1.5733,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.23,
619
+ "learning_rate": 0.00065,
620
+ "loss": 1.494,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.24,
625
+ "learning_rate": 0.00065,
626
+ "loss": 1.5325,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.24,
631
+ "learning_rate": 0.00065,
632
+ "loss": 1.5481,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.24,
637
+ "learning_rate": 0.00065,
638
+ "loss": 1.5022,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.24,
643
+ "learning_rate": 0.00065,
644
+ "loss": 1.5334,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.25,
649
+ "learning_rate": 0.00065,
650
+ "loss": 1.4816,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.25,
655
+ "learning_rate": 0.00065,
656
+ "loss": 1.5505,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.25,
661
+ "learning_rate": 0.00065,
662
+ "loss": 1.5887,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.25,
667
+ "learning_rate": 0.00065,
668
+ "loss": 1.6073,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.26,
673
+ "learning_rate": 0.00065,
674
+ "loss": 1.2843,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.26,
679
+ "learning_rate": 0.00065,
680
+ "loss": 1.6441,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.26,
685
+ "learning_rate": 0.00065,
686
+ "loss": 1.4291,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.26,
691
+ "learning_rate": 0.00065,
692
+ "loss": 1.5993,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.26,
697
+ "learning_rate": 0.00065,
698
+ "loss": 1.6003,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.27,
703
+ "learning_rate": 0.00065,
704
+ "loss": 1.6004,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.27,
709
+ "learning_rate": 0.00065,
710
+ "loss": 1.092,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.27,
715
+ "learning_rate": 0.00065,
716
+ "loss": 1.6992,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.27,
721
+ "learning_rate": 0.00065,
722
+ "loss": 1.5215,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.28,
727
+ "learning_rate": 0.00065,
728
+ "loss": 1.6719,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.28,
733
+ "learning_rate": 0.00065,
734
+ "loss": 1.5689,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.28,
739
+ "learning_rate": 0.00065,
740
+ "loss": 1.5856,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.28,
745
+ "learning_rate": 0.00065,
746
+ "loss": 1.5404,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.29,
751
+ "learning_rate": 0.00065,
752
+ "loss": 1.2784,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.29,
757
+ "learning_rate": 0.00065,
758
+ "loss": 1.7063,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.29,
763
+ "learning_rate": 0.00065,
764
+ "loss": 1.518,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.29,
769
+ "learning_rate": 0.00065,
770
+ "loss": 1.6195,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.3,
775
+ "learning_rate": 0.00065,
776
+ "loss": 1.4,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.3,
781
+ "learning_rate": 0.00065,
782
+ "loss": 1.5435,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.3,
787
+ "learning_rate": 0.00065,
788
+ "loss": 1.6498,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.3,
793
+ "eval_loss": 1.4962397813796997,
794
+ "eval_runtime": 57.8837,
795
+ "eval_samples_per_second": 8.638,
796
+ "eval_steps_per_second": 4.319,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.3,
801
+ "learning_rate": 0.00065,
802
+ "loss": 1.4815,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.31,
807
+ "learning_rate": 0.00065,
808
+ "loss": 1.5617,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.31,
813
+ "learning_rate": 0.00065,
814
+ "loss": 1.6173,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.31,
819
+ "learning_rate": 0.00065,
820
+ "loss": 1.6515,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.31,
825
+ "learning_rate": 0.00065,
826
+ "loss": 1.7001,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.32,
831
+ "learning_rate": 0.00065,
832
+ "loss": 1.7185,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.32,
837
+ "learning_rate": 0.00065,
838
+ "loss": 1.5095,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.32,
843
+ "learning_rate": 0.00065,
844
+ "loss": 1.5354,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.32,
849
+ "learning_rate": 0.00065,
850
+ "loss": 1.5958,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.32,
855
+ "learning_rate": 0.00065,
856
+ "loss": 1.5622,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.33,
861
+ "learning_rate": 0.00065,
862
+ "loss": 1.5229,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.33,
867
+ "learning_rate": 0.00065,
868
+ "loss": 1.5117,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.33,
873
+ "learning_rate": 0.00065,
874
+ "loss": 1.7616,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.33,
879
+ "learning_rate": 0.00065,
880
+ "loss": 1.2281,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.34,
885
+ "learning_rate": 0.00065,
886
+ "loss": 1.6234,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.34,
891
+ "learning_rate": 0.00065,
892
+ "loss": 1.3816,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.34,
897
+ "learning_rate": 0.00065,
898
+ "loss": 1.474,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.34,
903
+ "learning_rate": 0.00065,
904
+ "loss": 1.4441,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.35,
909
+ "learning_rate": 0.00065,
910
+ "loss": 1.602,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.35,
915
+ "learning_rate": 0.00065,
916
+ "loss": 1.543,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.35,
921
+ "learning_rate": 0.00065,
922
+ "loss": 1.7464,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.35,
927
+ "learning_rate": 0.00065,
928
+ "loss": 1.696,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.36,
933
+ "learning_rate": 0.00065,
934
+ "loss": 1.6781,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.36,
939
+ "learning_rate": 0.00065,
940
+ "loss": 1.4346,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.36,
945
+ "learning_rate": 0.00065,
946
+ "loss": 1.5507,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.36,
951
+ "learning_rate": 0.00065,
952
+ "loss": 1.5901,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.37,
957
+ "learning_rate": 0.00065,
958
+ "loss": 1.4516,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.37,
963
+ "learning_rate": 0.00065,
964
+ "loss": 1.4069,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.37,
969
+ "learning_rate": 0.00065,
970
+ "loss": 1.5614,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.37,
975
+ "learning_rate": 0.00065,
976
+ "loss": 1.4832,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.37,
981
+ "learning_rate": 0.00065,
982
+ "loss": 1.4241,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.38,
987
+ "learning_rate": 0.00065,
988
+ "loss": 1.4526,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.38,
993
+ "learning_rate": 0.00065,
994
+ "loss": 1.1961,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.38,
999
+ "learning_rate": 0.00065,
1000
+ "loss": 1.4206,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.38,
1005
+ "learning_rate": 0.00065,
1006
+ "loss": 1.6221,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.39,
1011
+ "learning_rate": 0.00065,
1012
+ "loss": 1.5796,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.39,
1017
+ "learning_rate": 0.00065,
1018
+ "loss": 1.7052,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.39,
1023
+ "learning_rate": 0.00065,
1024
+ "loss": 1.6022,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.39,
1029
+ "learning_rate": 0.00065,
1030
+ "loss": 1.4067,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.4,
1035
+ "learning_rate": 0.00065,
1036
+ "loss": 1.4105,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 0.4,
1041
+ "learning_rate": 0.00065,
1042
+ "loss": 1.3916,
1043
+ "step": 167
1044
+ },
1045
+ {
1046
+ "epoch": 0.4,
1047
+ "learning_rate": 0.00065,
1048
+ "loss": 1.5645,
1049
+ "step": 168
1050
+ },
1051
+ {
1052
+ "epoch": 0.4,
1053
+ "eval_loss": 1.498284101486206,
1054
+ "eval_runtime": 57.7262,
1055
+ "eval_samples_per_second": 8.662,
1056
+ "eval_steps_per_second": 4.331,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 0.4,
1061
+ "learning_rate": 0.00065,
1062
+ "loss": 1.5244,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 0.41,
1067
+ "learning_rate": 0.00065,
1068
+ "loss": 1.3781,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 0.41,
1073
+ "learning_rate": 0.00065,
1074
+ "loss": 1.6621,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 0.41,
1079
+ "learning_rate": 0.00065,
1080
+ "loss": 1.6337,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 0.41,
1085
+ "learning_rate": 0.00065,
1086
+ "loss": 1.5208,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 0.42,
1091
+ "learning_rate": 0.00065,
1092
+ "loss": 1.2743,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 0.42,
1097
+ "learning_rate": 0.00065,
1098
+ "loss": 1.6341,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 0.42,
1103
+ "learning_rate": 0.00065,
1104
+ "loss": 1.2578,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 0.42,
1109
+ "learning_rate": 0.00065,
1110
+ "loss": 1.6975,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 0.42,
1115
+ "learning_rate": 0.00065,
1116
+ "loss": 1.5663,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 0.43,
1121
+ "learning_rate": 0.00065,
1122
+ "loss": 1.5621,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 0.43,
1127
+ "learning_rate": 0.00065,
1128
+ "loss": 1.3063,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 0.43,
1133
+ "learning_rate": 0.00065,
1134
+ "loss": 1.4776,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 0.43,
1139
+ "learning_rate": 0.00065,
1140
+ "loss": 1.7046,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 0.44,
1145
+ "learning_rate": 0.00065,
1146
+ "loss": 1.5946,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 0.44,
1151
+ "learning_rate": 0.00065,
1152
+ "loss": 1.779,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 0.44,
1157
+ "learning_rate": 0.00065,
1158
+ "loss": 1.571,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 0.44,
1163
+ "learning_rate": 0.00065,
1164
+ "loss": 1.5513,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 0.45,
1169
+ "learning_rate": 0.00065,
1170
+ "loss": 1.4312,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 0.45,
1175
+ "learning_rate": 0.00065,
1176
+ "loss": 1.4258,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 0.45,
1181
+ "learning_rate": 0.00065,
1182
+ "loss": 1.5412,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 0.45,
1187
+ "learning_rate": 0.00065,
1188
+ "loss": 1.6545,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 0.46,
1193
+ "learning_rate": 0.00065,
1194
+ "loss": 1.5313,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 0.46,
1199
+ "learning_rate": 0.00065,
1200
+ "loss": 1.5245,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 0.46,
1205
+ "learning_rate": 0.00065,
1206
+ "loss": 1.41,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 0.46,
1211
+ "learning_rate": 0.00065,
1212
+ "loss": 1.5677,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 0.47,
1217
+ "learning_rate": 0.00065,
1218
+ "loss": 1.6269,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 0.47,
1223
+ "learning_rate": 0.00065,
1224
+ "loss": 1.6669,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 0.47,
1229
+ "learning_rate": 0.00065,
1230
+ "loss": 1.3903,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 0.47,
1235
+ "learning_rate": 0.00065,
1236
+ "loss": 1.4535,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 0.47,
1241
+ "learning_rate": 0.00065,
1242
+ "loss": 1.6028,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 0.48,
1247
+ "learning_rate": 0.00065,
1248
+ "loss": 1.3562,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 0.48,
1253
+ "learning_rate": 0.00065,
1254
+ "loss": 1.4644,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 0.48,
1259
+ "learning_rate": 0.00065,
1260
+ "loss": 1.4645,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 0.48,
1265
+ "learning_rate": 0.00065,
1266
+ "loss": 1.6715,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 0.49,
1271
+ "learning_rate": 0.00065,
1272
+ "loss": 1.3685,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 0.49,
1277
+ "learning_rate": 0.00065,
1278
+ "loss": 1.1695,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 0.49,
1283
+ "learning_rate": 0.00065,
1284
+ "loss": 1.6035,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 0.49,
1289
+ "learning_rate": 0.00065,
1290
+ "loss": 1.5142,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 0.5,
1295
+ "learning_rate": 0.00065,
1296
+ "loss": 1.5223,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 0.5,
1301
+ "learning_rate": 0.00065,
1302
+ "loss": 1.5144,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 0.5,
1307
+ "learning_rate": 0.00065,
1308
+ "loss": 1.6487,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 0.5,
1313
+ "eval_loss": 1.4980822801589966,
1314
+ "eval_runtime": 57.8018,
1315
+ "eval_samples_per_second": 8.65,
1316
+ "eval_steps_per_second": 4.325,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 0.5,
1321
+ "learning_rate": 0.00065,
1322
+ "loss": 1.4847,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 0.51,
1327
+ "learning_rate": 0.00065,
1328
+ "loss": 1.491,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 0.51,
1333
+ "learning_rate": 0.00065,
1334
+ "loss": 1.3213,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 0.51,
1339
+ "learning_rate": 0.00065,
1340
+ "loss": 1.6399,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 0.51,
1345
+ "learning_rate": 0.00065,
1346
+ "loss": 1.6079,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 0.52,
1351
+ "learning_rate": 0.00065,
1352
+ "loss": 1.4458,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 0.52,
1357
+ "learning_rate": 0.00065,
1358
+ "loss": 1.6101,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 0.52,
1363
+ "learning_rate": 0.00065,
1364
+ "loss": 1.6516,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 0.52,
1369
+ "learning_rate": 0.00065,
1370
+ "loss": 1.4794,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 0.53,
1375
+ "learning_rate": 0.00065,
1376
+ "loss": 1.7151,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 0.53,
1381
+ "learning_rate": 0.00065,
1382
+ "loss": 1.5805,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 0.53,
1387
+ "learning_rate": 0.00065,
1388
+ "loss": 1.5088,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 0.53,
1393
+ "learning_rate": 0.00065,
1394
+ "loss": 1.5852,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 0.53,
1399
+ "learning_rate": 0.00065,
1400
+ "loss": 1.3886,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 0.54,
1405
+ "learning_rate": 0.00065,
1406
+ "loss": 1.7186,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 0.54,
1411
+ "learning_rate": 0.00065,
1412
+ "loss": 1.6551,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 0.54,
1417
+ "learning_rate": 0.00065,
1418
+ "loss": 1.5615,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 0.54,
1423
+ "learning_rate": 0.00065,
1424
+ "loss": 1.8389,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 0.55,
1429
+ "learning_rate": 0.00065,
1430
+ "loss": 1.5447,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 0.55,
1435
+ "learning_rate": 0.00065,
1436
+ "loss": 1.4015,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 0.55,
1441
+ "learning_rate": 0.00065,
1442
+ "loss": 1.5386,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 0.55,
1447
+ "learning_rate": 0.00065,
1448
+ "loss": 1.6429,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 0.56,
1453
+ "learning_rate": 0.00065,
1454
+ "loss": 1.5531,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 0.56,
1459
+ "learning_rate": 0.00065,
1460
+ "loss": 1.3572,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 0.56,
1465
+ "learning_rate": 0.00065,
1466
+ "loss": 1.3011,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 0.56,
1471
+ "learning_rate": 0.00065,
1472
+ "loss": 1.7356,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 0.57,
1477
+ "learning_rate": 0.00065,
1478
+ "loss": 1.2688,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 0.57,
1483
+ "learning_rate": 0.00065,
1484
+ "loss": 1.5885,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 0.57,
1489
+ "learning_rate": 0.00065,
1490
+ "loss": 1.5765,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 0.57,
1495
+ "learning_rate": 0.00065,
1496
+ "loss": 1.3705,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 0.58,
1501
+ "learning_rate": 0.00065,
1502
+ "loss": 1.4097,
1503
+ "step": 241
1504
+ },
1505
+ {
1506
+ "epoch": 0.58,
1507
+ "learning_rate": 0.00065,
1508
+ "loss": 1.5182,
1509
+ "step": 242
1510
+ },
1511
+ {
1512
+ "epoch": 0.58,
1513
+ "learning_rate": 0.00065,
1514
+ "loss": 1.2854,
1515
+ "step": 243
1516
+ },
1517
+ {
1518
+ "epoch": 0.58,
1519
+ "learning_rate": 0.00065,
1520
+ "loss": 1.8305,
1521
+ "step": 244
1522
+ },
1523
+ {
1524
+ "epoch": 0.58,
1525
+ "learning_rate": 0.00065,
1526
+ "loss": 1.0632,
1527
+ "step": 245
1528
+ },
1529
+ {
1530
+ "epoch": 0.59,
1531
+ "learning_rate": 0.00065,
1532
+ "loss": 1.5128,
1533
+ "step": 246
1534
+ },
1535
+ {
1536
+ "epoch": 0.59,
1537
+ "learning_rate": 0.00065,
1538
+ "loss": 1.545,
1539
+ "step": 247
1540
+ },
1541
+ {
1542
+ "epoch": 0.59,
1543
+ "learning_rate": 0.00065,
1544
+ "loss": 1.4362,
1545
+ "step": 248
1546
+ },
1547
+ {
1548
+ "epoch": 0.59,
1549
+ "learning_rate": 0.00065,
1550
+ "loss": 1.093,
1551
+ "step": 249
1552
+ },
1553
+ {
1554
+ "epoch": 0.6,
1555
+ "learning_rate": 0.00065,
1556
+ "loss": 1.5286,
1557
+ "step": 250
1558
+ },
1559
+ {
1560
+ "epoch": 0.6,
1561
+ "learning_rate": 0.00065,
1562
+ "loss": 1.5218,
1563
+ "step": 251
1564
+ },
1565
+ {
1566
+ "epoch": 0.6,
1567
+ "learning_rate": 0.00065,
1568
+ "loss": 1.6147,
1569
+ "step": 252
1570
+ },
1571
+ {
1572
+ "epoch": 0.6,
1573
+ "eval_loss": 1.4965262413024902,
1574
+ "eval_runtime": 57.8272,
1575
+ "eval_samples_per_second": 8.646,
1576
+ "eval_steps_per_second": 4.323,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 0.6,
1581
+ "learning_rate": 0.00065,
1582
+ "loss": 1.6172,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 0.61,
1587
+ "learning_rate": 0.00065,
1588
+ "loss": 1.4856,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 0.61,
1593
+ "learning_rate": 0.00065,
1594
+ "loss": 1.6167,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 0.61,
1599
+ "learning_rate": 0.00065,
1600
+ "loss": 1.5882,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 0.61,
1605
+ "learning_rate": 0.00065,
1606
+ "loss": 1.4952,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 0.62,
1611
+ "learning_rate": 0.00065,
1612
+ "loss": 1.5929,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 0.62,
1617
+ "learning_rate": 0.00065,
1618
+ "loss": 1.314,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 0.62,
1623
+ "learning_rate": 0.00065,
1624
+ "loss": 1.3682,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 0.62,
1629
+ "learning_rate": 0.00065,
1630
+ "loss": 1.5718,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 0.63,
1635
+ "learning_rate": 0.00065,
1636
+ "loss": 1.337,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 0.63,
1641
+ "learning_rate": 0.00065,
1642
+ "loss": 1.7287,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 0.63,
1647
+ "learning_rate": 0.00065,
1648
+ "loss": 1.685,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 0.63,
1653
+ "learning_rate": 0.00065,
1654
+ "loss": 1.1973,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 0.63,
1659
+ "learning_rate": 0.00065,
1660
+ "loss": 1.4037,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 0.64,
1665
+ "learning_rate": 0.00065,
1666
+ "loss": 1.3741,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 0.64,
1671
+ "learning_rate": 0.00065,
1672
+ "loss": 1.6339,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 0.64,
1677
+ "learning_rate": 0.00065,
1678
+ "loss": 1.6981,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 0.64,
1683
+ "learning_rate": 0.00065,
1684
+ "loss": 1.4383,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 0.65,
1689
+ "learning_rate": 0.00065,
1690
+ "loss": 1.5721,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 0.65,
1695
+ "learning_rate": 0.00065,
1696
+ "loss": 1.587,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 0.65,
1701
+ "learning_rate": 0.00065,
1702
+ "loss": 1.8308,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 0.65,
1707
+ "learning_rate": 0.00065,
1708
+ "loss": 1.3733,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 0.66,
1713
+ "learning_rate": 0.00065,
1714
+ "loss": 1.6366,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 0.66,
1719
+ "learning_rate": 0.00065,
1720
+ "loss": 1.4057,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 0.66,
1725
+ "learning_rate": 0.00065,
1726
+ "loss": 1.6264,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 0.66,
1731
+ "learning_rate": 0.00065,
1732
+ "loss": 1.5546,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 0.67,
1737
+ "learning_rate": 0.00065,
1738
+ "loss": 1.567,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 0.67,
1743
+ "learning_rate": 0.00065,
1744
+ "loss": 1.312,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 0.67,
1749
+ "learning_rate": 0.00065,
1750
+ "loss": 1.438,
1751
+ "step": 281
1752
+ },
1753
+ {
1754
+ "epoch": 0.67,
1755
+ "learning_rate": 0.00065,
1756
+ "loss": 1.4226,
1757
+ "step": 282
1758
+ },
1759
+ {
1760
+ "epoch": 0.68,
1761
+ "learning_rate": 0.00065,
1762
+ "loss": 1.4871,
1763
+ "step": 283
1764
+ },
1765
+ {
1766
+ "epoch": 0.68,
1767
+ "learning_rate": 0.00065,
1768
+ "loss": 1.5465,
1769
+ "step": 284
1770
+ },
1771
+ {
1772
+ "epoch": 0.68,
1773
+ "learning_rate": 0.00065,
1774
+ "loss": 1.4989,
1775
+ "step": 285
1776
+ },
1777
+ {
1778
+ "epoch": 0.68,
1779
+ "learning_rate": 0.00065,
1780
+ "loss": 1.6361,
1781
+ "step": 286
1782
+ },
1783
+ {
1784
+ "epoch": 0.68,
1785
+ "learning_rate": 0.00065,
1786
+ "loss": 1.5529,
1787
+ "step": 287
1788
+ },
1789
+ {
1790
+ "epoch": 0.69,
1791
+ "learning_rate": 0.00065,
1792
+ "loss": 1.334,
1793
+ "step": 288
1794
+ },
1795
+ {
1796
+ "epoch": 0.69,
1797
+ "learning_rate": 0.00065,
1798
+ "loss": 1.6348,
1799
+ "step": 289
1800
+ },
1801
+ {
1802
+ "epoch": 0.69,
1803
+ "learning_rate": 0.00065,
1804
+ "loss": 1.6611,
1805
+ "step": 290
1806
+ },
1807
+ {
1808
+ "epoch": 0.69,
1809
+ "learning_rate": 0.00065,
1810
+ "loss": 1.3462,
1811
+ "step": 291
1812
+ },
1813
+ {
1814
+ "epoch": 0.7,
1815
+ "learning_rate": 0.00065,
1816
+ "loss": 1.3151,
1817
+ "step": 292
1818
+ },
1819
+ {
1820
+ "epoch": 0.7,
1821
+ "learning_rate": 0.00065,
1822
+ "loss": 1.4333,
1823
+ "step": 293
1824
+ },
1825
+ {
1826
+ "epoch": 0.7,
1827
+ "learning_rate": 0.00065,
1828
+ "loss": 1.3048,
1829
+ "step": 294
1830
+ },
1831
+ {
1832
+ "epoch": 0.7,
1833
+ "eval_loss": 1.4973247051239014,
1834
+ "eval_runtime": 57.7873,
1835
+ "eval_samples_per_second": 8.652,
1836
+ "eval_steps_per_second": 4.326,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 0.7,
1841
+ "learning_rate": 0.00065,
1842
+ "loss": 1.5376,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 0.71,
1847
+ "learning_rate": 0.00065,
1848
+ "loss": 1.5643,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 0.71,
1853
+ "learning_rate": 0.00065,
1854
+ "loss": 1.6501,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 0.71,
1859
+ "learning_rate": 0.00065,
1860
+ "loss": 1.3652,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 0.71,
1865
+ "learning_rate": 0.00065,
1866
+ "loss": 1.5191,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 0.72,
1871
+ "learning_rate": 0.00065,
1872
+ "loss": 1.5722,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 0.72,
1877
+ "learning_rate": 0.00065,
1878
+ "loss": 1.5057,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 0.72,
1883
+ "learning_rate": 0.00065,
1884
+ "loss": 1.3798,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 0.72,
1889
+ "learning_rate": 0.00065,
1890
+ "loss": 1.3492,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 0.73,
1895
+ "learning_rate": 0.00065,
1896
+ "loss": 1.3582,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 0.73,
1901
+ "learning_rate": 0.00065,
1902
+ "loss": 1.5691,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 0.73,
1907
+ "learning_rate": 0.00065,
1908
+ "loss": 1.6634,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 0.73,
1913
+ "learning_rate": 0.00065,
1914
+ "loss": 1.6464,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 0.74,
1919
+ "learning_rate": 0.00065,
1920
+ "loss": 1.4683,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 0.74,
1925
+ "learning_rate": 0.00065,
1926
+ "loss": 1.5424,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 0.74,
1931
+ "learning_rate": 0.00065,
1932
+ "loss": 1.5145,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 0.74,
1937
+ "learning_rate": 0.00065,
1938
+ "loss": 1.6582,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 0.74,
1943
+ "learning_rate": 0.00065,
1944
+ "loss": 1.3616,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 0.75,
1949
+ "learning_rate": 0.00065,
1950
+ "loss": 1.5284,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 0.75,
1955
+ "learning_rate": 0.00065,
1956
+ "loss": 1.1895,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 0.75,
1961
+ "learning_rate": 0.00065,
1962
+ "loss": 1.6037,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 0.75,
1967
+ "learning_rate": 0.00065,
1968
+ "loss": 1.5233,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 0.76,
1973
+ "learning_rate": 0.00065,
1974
+ "loss": 1.6914,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 0.76,
1979
+ "learning_rate": 0.00065,
1980
+ "loss": 1.4968,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 0.76,
1985
+ "learning_rate": 0.00065,
1986
+ "loss": 1.2765,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 0.76,
1991
+ "learning_rate": 0.00065,
1992
+ "loss": 1.6675,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 0.77,
1997
+ "learning_rate": 0.00065,
1998
+ "loss": 1.723,
1999
+ "step": 321
2000
+ },
2001
+ {
2002
+ "epoch": 0.77,
2003
+ "learning_rate": 0.00065,
2004
+ "loss": 1.4832,
2005
+ "step": 322
2006
+ },
2007
+ {
2008
+ "epoch": 0.77,
2009
+ "learning_rate": 0.00065,
2010
+ "loss": 1.179,
2011
+ "step": 323
2012
+ },
2013
+ {
2014
+ "epoch": 0.77,
2015
+ "learning_rate": 0.00065,
2016
+ "loss": 1.5108,
2017
+ "step": 324
2018
+ },
2019
+ {
2020
+ "epoch": 0.78,
2021
+ "learning_rate": 0.00065,
2022
+ "loss": 1.3931,
2023
+ "step": 325
2024
+ },
2025
+ {
2026
+ "epoch": 0.78,
2027
+ "learning_rate": 0.00065,
2028
+ "loss": 1.6227,
2029
+ "step": 326
2030
+ },
2031
+ {
2032
+ "epoch": 0.78,
2033
+ "learning_rate": 0.00065,
2034
+ "loss": 1.353,
2035
+ "step": 327
2036
+ },
2037
+ {
2038
+ "epoch": 0.78,
2039
+ "learning_rate": 0.00065,
2040
+ "loss": 1.5377,
2041
+ "step": 328
2042
+ },
2043
+ {
2044
+ "epoch": 0.79,
2045
+ "learning_rate": 0.00065,
2046
+ "loss": 1.6277,
2047
+ "step": 329
2048
+ },
2049
+ {
2050
+ "epoch": 0.79,
2051
+ "learning_rate": 0.00065,
2052
+ "loss": 1.4532,
2053
+ "step": 330
2054
+ },
2055
+ {
2056
+ "epoch": 0.79,
2057
+ "learning_rate": 0.00065,
2058
+ "loss": 1.6329,
2059
+ "step": 331
2060
+ },
2061
+ {
2062
+ "epoch": 0.79,
2063
+ "learning_rate": 0.00065,
2064
+ "loss": 1.6595,
2065
+ "step": 332
2066
+ },
2067
+ {
2068
+ "epoch": 0.79,
2069
+ "learning_rate": 0.00065,
2070
+ "loss": 1.4014,
2071
+ "step": 333
2072
+ },
2073
+ {
2074
+ "epoch": 0.8,
2075
+ "learning_rate": 0.00065,
2076
+ "loss": 1.4108,
2077
+ "step": 334
2078
+ },
2079
+ {
2080
+ "epoch": 0.8,
2081
+ "learning_rate": 0.00065,
2082
+ "loss": 1.5729,
2083
+ "step": 335
2084
+ },
2085
+ {
2086
+ "epoch": 0.8,
2087
+ "learning_rate": 0.00065,
2088
+ "loss": 1.6205,
2089
+ "step": 336
2090
+ },
2091
+ {
2092
+ "epoch": 0.8,
2093
+ "eval_loss": 1.5006886720657349,
2094
+ "eval_runtime": 57.756,
2095
+ "eval_samples_per_second": 8.657,
2096
+ "eval_steps_per_second": 4.329,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 0.8,
2101
+ "learning_rate": 0.00065,
2102
+ "loss": 1.5595,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 0.81,
2107
+ "learning_rate": 0.00065,
2108
+ "loss": 1.4389,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 0.81,
2113
+ "learning_rate": 0.00065,
2114
+ "loss": 1.6702,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 0.81,
2119
+ "learning_rate": 0.00065,
2120
+ "loss": 1.7348,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 0.81,
2125
+ "learning_rate": 0.00065,
2126
+ "loss": 1.5383,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 0.82,
2131
+ "learning_rate": 0.00065,
2132
+ "loss": 1.2777,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 0.82,
2137
+ "learning_rate": 0.00065,
2138
+ "loss": 1.4466,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 0.82,
2143
+ "learning_rate": 0.00065,
2144
+ "loss": 1.4665,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 0.82,
2149
+ "learning_rate": 0.00065,
2150
+ "loss": 1.595,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 0.83,
2155
+ "learning_rate": 0.00065,
2156
+ "loss": 1.4895,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 0.83,
2161
+ "learning_rate": 0.00065,
2162
+ "loss": 1.4753,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 0.83,
2167
+ "learning_rate": 0.00065,
2168
+ "loss": 1.4371,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 0.83,
2173
+ "learning_rate": 0.00065,
2174
+ "loss": 1.4467,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 0.84,
2179
+ "learning_rate": 0.00065,
2180
+ "loss": 1.2601,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 0.84,
2185
+ "learning_rate": 0.00065,
2186
+ "loss": 1.1586,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 0.84,
2191
+ "learning_rate": 0.00065,
2192
+ "loss": 1.7566,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 0.84,
2197
+ "learning_rate": 0.00065,
2198
+ "loss": 1.5955,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 0.84,
2203
+ "learning_rate": 0.00065,
2204
+ "loss": 1.3872,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 0.85,
2209
+ "learning_rate": 0.00065,
2210
+ "loss": 1.3124,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 0.85,
2215
+ "learning_rate": 0.00065,
2216
+ "loss": 1.5033,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 0.85,
2221
+ "learning_rate": 0.00065,
2222
+ "loss": 1.6921,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 0.85,
2227
+ "learning_rate": 0.00065,
2228
+ "loss": 1.5243,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 0.86,
2233
+ "learning_rate": 0.00065,
2234
+ "loss": 1.5287,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 0.86,
2239
+ "learning_rate": 0.00065,
2240
+ "loss": 1.4257,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 0.86,
2245
+ "learning_rate": 0.00065,
2246
+ "loss": 1.3924,
2247
+ "step": 361
2248
+ },
2249
+ {
2250
+ "epoch": 0.86,
2251
+ "learning_rate": 0.00065,
2252
+ "loss": 1.6084,
2253
+ "step": 362
2254
+ },
2255
+ {
2256
+ "epoch": 0.87,
2257
+ "learning_rate": 0.00065,
2258
+ "loss": 1.5605,
2259
+ "step": 363
2260
+ },
2261
+ {
2262
+ "epoch": 0.87,
2263
+ "learning_rate": 0.00065,
2264
+ "loss": 1.6319,
2265
+ "step": 364
2266
+ },
2267
+ {
2268
+ "epoch": 0.87,
2269
+ "learning_rate": 0.00065,
2270
+ "loss": 1.5691,
2271
+ "step": 365
2272
+ },
2273
+ {
2274
+ "epoch": 0.87,
2275
+ "learning_rate": 0.00065,
2276
+ "loss": 1.311,
2277
+ "step": 366
2278
+ },
2279
+ {
2280
+ "epoch": 0.88,
2281
+ "learning_rate": 0.00065,
2282
+ "loss": 1.4892,
2283
+ "step": 367
2284
+ },
2285
+ {
2286
+ "epoch": 0.88,
2287
+ "learning_rate": 0.00065,
2288
+ "loss": 1.3108,
2289
+ "step": 368
2290
+ },
2291
+ {
2292
+ "epoch": 0.88,
2293
+ "learning_rate": 0.00065,
2294
+ "loss": 1.6953,
2295
+ "step": 369
2296
+ },
2297
+ {
2298
+ "epoch": 0.88,
2299
+ "learning_rate": 0.00065,
2300
+ "loss": 1.5857,
2301
+ "step": 370
2302
+ },
2303
+ {
2304
+ "epoch": 0.89,
2305
+ "learning_rate": 0.00065,
2306
+ "loss": 1.4536,
2307
+ "step": 371
2308
+ },
2309
+ {
2310
+ "epoch": 0.89,
2311
+ "learning_rate": 0.00065,
2312
+ "loss": 1.4781,
2313
+ "step": 372
2314
+ },
2315
+ {
2316
+ "epoch": 0.89,
2317
+ "learning_rate": 0.00065,
2318
+ "loss": 1.5191,
2319
+ "step": 373
2320
+ },
2321
+ {
2322
+ "epoch": 0.89,
2323
+ "learning_rate": 0.00065,
2324
+ "loss": 1.5136,
2325
+ "step": 374
2326
+ },
2327
+ {
2328
+ "epoch": 0.89,
2329
+ "learning_rate": 0.00065,
2330
+ "loss": 1.5246,
2331
+ "step": 375
2332
+ },
2333
+ {
2334
+ "epoch": 0.9,
2335
+ "learning_rate": 0.00065,
2336
+ "loss": 1.022,
2337
+ "step": 376
2338
+ },
2339
+ {
2340
+ "epoch": 0.9,
2341
+ "learning_rate": 0.00065,
2342
+ "loss": 1.5182,
2343
+ "step": 377
2344
+ },
2345
+ {
2346
+ "epoch": 0.9,
2347
+ "learning_rate": 0.00065,
2348
+ "loss": 1.6045,
2349
+ "step": 378
2350
+ },
2351
+ {
2352
+ "epoch": 0.9,
2353
+ "eval_loss": 1.5002774000167847,
2354
+ "eval_runtime": 57.7872,
2355
+ "eval_samples_per_second": 8.652,
2356
+ "eval_steps_per_second": 4.326,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 0.9,
2361
+ "learning_rate": 0.00065,
2362
+ "loss": 1.6214,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 0.91,
2367
+ "learning_rate": 0.00065,
2368
+ "loss": 1.4893,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 0.91,
2373
+ "learning_rate": 0.00065,
2374
+ "loss": 1.5942,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 0.91,
2379
+ "learning_rate": 0.00065,
2380
+ "loss": 1.369,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 0.91,
2385
+ "learning_rate": 0.00065,
2386
+ "loss": 1.0446,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 0.92,
2391
+ "learning_rate": 0.00065,
2392
+ "loss": 1.63,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 0.92,
2397
+ "learning_rate": 0.00065,
2398
+ "loss": 1.5157,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 0.92,
2403
+ "learning_rate": 0.00065,
2404
+ "loss": 1.4303,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 0.92,
2409
+ "learning_rate": 0.00065,
2410
+ "loss": 1.539,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 0.93,
2415
+ "learning_rate": 0.00065,
2416
+ "loss": 1.3132,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 0.93,
2421
+ "learning_rate": 0.00065,
2422
+ "loss": 1.0668,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 0.93,
2427
+ "learning_rate": 0.00065,
2428
+ "loss": 1.5303,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 0.93,
2433
+ "learning_rate": 0.00065,
2434
+ "loss": 1.5204,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 0.94,
2439
+ "learning_rate": 0.00065,
2440
+ "loss": 1.6575,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 0.94,
2445
+ "learning_rate": 0.00065,
2446
+ "loss": 1.5325,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 0.94,
2451
+ "learning_rate": 0.00065,
2452
+ "loss": 1.6132,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 0.94,
2457
+ "learning_rate": 0.00065,
2458
+ "loss": 1.4253,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 0.95,
2463
+ "learning_rate": 0.00065,
2464
+ "loss": 1.2638,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 0.95,
2469
+ "learning_rate": 0.00065,
2470
+ "loss": 1.5054,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 0.95,
2475
+ "learning_rate": 0.00065,
2476
+ "loss": 1.6769,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 0.95,
2481
+ "learning_rate": 0.00065,
2482
+ "loss": 1.5845,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 0.95,
2487
+ "learning_rate": 0.00065,
2488
+ "loss": 1.2866,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 0.96,
2493
+ "learning_rate": 0.00065,
2494
+ "loss": 1.1569,
2495
+ "step": 401
2496
+ },
2497
+ {
2498
+ "epoch": 0.96,
2499
+ "learning_rate": 0.00065,
2500
+ "loss": 1.2087,
2501
+ "step": 402
2502
+ },
2503
+ {
2504
+ "epoch": 0.96,
2505
+ "learning_rate": 0.00065,
2506
+ "loss": 1.6248,
2507
+ "step": 403
2508
+ },
2509
+ {
2510
+ "epoch": 0.96,
2511
+ "learning_rate": 0.00065,
2512
+ "loss": 1.5012,
2513
+ "step": 404
2514
+ },
2515
+ {
2516
+ "epoch": 0.97,
2517
+ "learning_rate": 0.00065,
2518
+ "loss": 1.6551,
2519
+ "step": 405
2520
+ },
2521
+ {
2522
+ "epoch": 0.97,
2523
+ "learning_rate": 0.00065,
2524
+ "loss": 1.4988,
2525
+ "step": 406
2526
+ },
2527
+ {
2528
+ "epoch": 0.97,
2529
+ "learning_rate": 0.00065,
2530
+ "loss": 1.4565,
2531
+ "step": 407
2532
+ },
2533
+ {
2534
+ "epoch": 0.97,
2535
+ "learning_rate": 0.00065,
2536
+ "loss": 1.2717,
2537
+ "step": 408
2538
+ },
2539
+ {
2540
+ "epoch": 0.98,
2541
+ "learning_rate": 0.00065,
2542
+ "loss": 1.7323,
2543
+ "step": 409
2544
+ },
2545
+ {
2546
+ "epoch": 0.98,
2547
+ "learning_rate": 0.00065,
2548
+ "loss": 1.5811,
2549
+ "step": 410
2550
+ },
2551
+ {
2552
+ "epoch": 0.98,
2553
+ "learning_rate": 0.00065,
2554
+ "loss": 1.4139,
2555
+ "step": 411
2556
+ },
2557
+ {
2558
+ "epoch": 0.98,
2559
+ "learning_rate": 0.00065,
2560
+ "loss": 1.4657,
2561
+ "step": 412
2562
+ },
2563
+ {
2564
+ "epoch": 0.99,
2565
+ "learning_rate": 0.00065,
2566
+ "loss": 1.5507,
2567
+ "step": 413
2568
+ },
2569
+ {
2570
+ "epoch": 0.99,
2571
+ "learning_rate": 0.00065,
2572
+ "loss": 1.4202,
2573
+ "step": 414
2574
+ },
2575
+ {
2576
+ "epoch": 0.99,
2577
+ "learning_rate": 0.00065,
2578
+ "loss": 1.412,
2579
+ "step": 415
2580
+ },
2581
+ {
2582
+ "epoch": 0.99,
2583
+ "learning_rate": 0.00065,
2584
+ "loss": 1.5208,
2585
+ "step": 416
2586
+ },
2587
+ {
2588
+ "epoch": 1.0,
2589
+ "learning_rate": 0.00065,
2590
+ "loss": 1.5733,
2591
+ "step": 417
2592
+ },
2593
+ {
2594
+ "epoch": 1.0,
2595
+ "learning_rate": 0.00065,
2596
+ "loss": 1.6295,
2597
+ "step": 418
2598
+ },
2599
+ {
2600
+ "epoch": 1.0,
2601
+ "learning_rate": 0.00065,
2602
+ "loss": 1.4903,
2603
+ "step": 419
2604
+ },
2605
+ {
2606
+ "epoch": 1.0,
2607
+ "learning_rate": 0.00065,
2608
+ "loss": 1.5781,
2609
+ "step": 420
2610
+ },
2611
+ {
2612
+ "epoch": 1.0,
2613
+ "eval_loss": 1.5013374090194702,
2614
+ "eval_runtime": 57.703,
2615
+ "eval_samples_per_second": 8.665,
2616
+ "eval_steps_per_second": 4.333,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 1.0,
2621
+ "learning_rate": 0.00065,
2622
+ "loss": 1.6304,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 1.01,
2627
+ "learning_rate": 0.00065,
2628
+ "loss": 1.6533,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 1.01,
2633
+ "learning_rate": 0.00065,
2634
+ "loss": 1.3432,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 1.01,
2639
+ "learning_rate": 0.00065,
2640
+ "loss": 1.5377,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 1.01,
2645
+ "learning_rate": 0.00065,
2646
+ "loss": 1.6638,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 1.02,
2651
+ "learning_rate": 0.00065,
2652
+ "loss": 1.5242,
2653
+ "step": 426
2654
+ },
2655
+ {
2656
+ "epoch": 1.0,
2657
+ "learning_rate": 0.00065,
2658
+ "loss": 1.3306,
2659
+ "step": 427
2660
+ },
2661
+ {
2662
+ "epoch": 1.0,
2663
+ "learning_rate": 0.00065,
2664
+ "loss": 1.3637,
2665
+ "step": 428
2666
+ },
2667
+ {
2668
+ "epoch": 1.01,
2669
+ "learning_rate": 0.00065,
2670
+ "loss": 1.4253,
2671
+ "step": 429
2672
+ },
2673
+ {
2674
+ "epoch": 1.01,
2675
+ "learning_rate": 0.00065,
2676
+ "loss": 1.49,
2677
+ "step": 430
2678
+ },
2679
+ {
2680
+ "epoch": 1.01,
2681
+ "learning_rate": 0.00065,
2682
+ "loss": 1.4924,
2683
+ "step": 431
2684
+ },
2685
+ {
2686
+ "epoch": 1.01,
2687
+ "learning_rate": 0.00065,
2688
+ "loss": 0.95,
2689
+ "step": 432
2690
+ },
2691
+ {
2692
+ "epoch": 1.02,
2693
+ "learning_rate": 0.00065,
2694
+ "loss": 1.3238,
2695
+ "step": 433
2696
+ },
2697
+ {
2698
+ "epoch": 1.02,
2699
+ "learning_rate": 0.00065,
2700
+ "loss": 1.091,
2701
+ "step": 434
2702
+ },
2703
+ {
2704
+ "epoch": 1.02,
2705
+ "learning_rate": 0.00065,
2706
+ "loss": 1.344,
2707
+ "step": 435
2708
+ },
2709
+ {
2710
+ "epoch": 1.02,
2711
+ "learning_rate": 0.00065,
2712
+ "loss": 1.2361,
2713
+ "step": 436
2714
+ },
2715
+ {
2716
+ "epoch": 1.03,
2717
+ "learning_rate": 0.00065,
2718
+ "loss": 1.3262,
2719
+ "step": 437
2720
+ },
2721
+ {
2722
+ "epoch": 1.03,
2723
+ "learning_rate": 0.00065,
2724
+ "loss": 1.1314,
2725
+ "step": 438
2726
+ },
2727
+ {
2728
+ "epoch": 1.03,
2729
+ "learning_rate": 0.00065,
2730
+ "loss": 1.3437,
2731
+ "step": 439
2732
+ },
2733
+ {
2734
+ "epoch": 1.03,
2735
+ "learning_rate": 0.00065,
2736
+ "loss": 1.2767,
2737
+ "step": 440
2738
+ },
2739
+ {
2740
+ "epoch": 1.04,
2741
+ "learning_rate": 0.00065,
2742
+ "loss": 0.9201,
2743
+ "step": 441
2744
+ },
2745
+ {
2746
+ "epoch": 1.04,
2747
+ "learning_rate": 0.00065,
2748
+ "loss": 1.4971,
2749
+ "step": 442
2750
+ },
2751
+ {
2752
+ "epoch": 1.04,
2753
+ "learning_rate": 0.00065,
2754
+ "loss": 1.1516,
2755
+ "step": 443
2756
+ },
2757
+ {
2758
+ "epoch": 1.04,
2759
+ "learning_rate": 0.00065,
2760
+ "loss": 1.226,
2761
+ "step": 444
2762
+ },
2763
+ {
2764
+ "epoch": 1.05,
2765
+ "learning_rate": 0.00065,
2766
+ "loss": 1.5404,
2767
+ "step": 445
2768
+ },
2769
+ {
2770
+ "epoch": 1.05,
2771
+ "learning_rate": 0.00065,
2772
+ "loss": 0.9349,
2773
+ "step": 446
2774
+ },
2775
+ {
2776
+ "epoch": 1.05,
2777
+ "learning_rate": 0.00065,
2778
+ "loss": 1.2262,
2779
+ "step": 447
2780
+ },
2781
+ {
2782
+ "epoch": 1.05,
2783
+ "learning_rate": 0.00065,
2784
+ "loss": 1.285,
2785
+ "step": 448
2786
+ },
2787
+ {
2788
+ "epoch": 1.05,
2789
+ "learning_rate": 0.00065,
2790
+ "loss": 1.3562,
2791
+ "step": 449
2792
+ },
2793
+ {
2794
+ "epoch": 1.06,
2795
+ "learning_rate": 0.00065,
2796
+ "loss": 1.1475,
2797
+ "step": 450
2798
+ },
2799
+ {
2800
+ "epoch": 1.06,
2801
+ "learning_rate": 0.00065,
2802
+ "loss": 1.2592,
2803
+ "step": 451
2804
+ },
2805
+ {
2806
+ "epoch": 1.06,
2807
+ "learning_rate": 0.00065,
2808
+ "loss": 1.2524,
2809
+ "step": 452
2810
+ },
2811
+ {
2812
+ "epoch": 1.06,
2813
+ "learning_rate": 0.00065,
2814
+ "loss": 1.2089,
2815
+ "step": 453
2816
+ },
2817
+ {
2818
+ "epoch": 1.07,
2819
+ "learning_rate": 0.00065,
2820
+ "loss": 1.154,
2821
+ "step": 454
2822
+ },
2823
+ {
2824
+ "epoch": 1.07,
2825
+ "learning_rate": 0.00065,
2826
+ "loss": 1.382,
2827
+ "step": 455
2828
+ },
2829
+ {
2830
+ "epoch": 1.07,
2831
+ "learning_rate": 0.00065,
2832
+ "loss": 1.2451,
2833
+ "step": 456
2834
+ },
2835
+ {
2836
+ "epoch": 1.07,
2837
+ "learning_rate": 0.00065,
2838
+ "loss": 1.3714,
2839
+ "step": 457
2840
+ },
2841
+ {
2842
+ "epoch": 1.08,
2843
+ "learning_rate": 0.00065,
2844
+ "loss": 1.2885,
2845
+ "step": 458
2846
+ },
2847
+ {
2848
+ "epoch": 1.08,
2849
+ "learning_rate": 0.00065,
2850
+ "loss": 1.242,
2851
+ "step": 459
2852
+ },
2853
+ {
2854
+ "epoch": 1.08,
2855
+ "learning_rate": 0.00065,
2856
+ "loss": 1.1617,
2857
+ "step": 460
2858
+ },
2859
+ {
2860
+ "epoch": 1.08,
2861
+ "learning_rate": 0.00065,
2862
+ "loss": 1.1649,
2863
+ "step": 461
2864
+ },
2865
+ {
2866
+ "epoch": 1.09,
2867
+ "learning_rate": 0.00065,
2868
+ "loss": 1.4807,
2869
+ "step": 462
2870
+ },
2871
+ {
2872
+ "epoch": 1.09,
2873
+ "eval_loss": 1.5492066144943237,
2874
+ "eval_runtime": 57.7283,
2875
+ "eval_samples_per_second": 8.661,
2876
+ "eval_steps_per_second": 4.331,
2877
+ "step": 462
2878
+ },
2879
+ {
2880
+ "epoch": 1.09,
2881
+ "learning_rate": 0.00065,
2882
+ "loss": 0.9944,
2883
+ "step": 463
2884
+ },
2885
+ {
2886
+ "epoch": 1.09,
2887
+ "learning_rate": 0.00065,
2888
+ "loss": 1.3231,
2889
+ "step": 464
2890
+ },
2891
+ {
2892
+ "epoch": 1.09,
2893
+ "learning_rate": 0.00065,
2894
+ "loss": 1.1236,
2895
+ "step": 465
2896
+ },
2897
+ {
2898
+ "epoch": 1.1,
2899
+ "learning_rate": 0.00065,
2900
+ "loss": 1.2049,
2901
+ "step": 466
2902
+ },
2903
+ {
2904
+ "epoch": 1.1,
2905
+ "learning_rate": 0.00065,
2906
+ "loss": 1.1105,
2907
+ "step": 467
2908
+ },
2909
+ {
2910
+ "epoch": 1.1,
2911
+ "learning_rate": 0.00065,
2912
+ "loss": 1.3196,
2913
+ "step": 468
2914
+ },
2915
+ {
2916
+ "epoch": 1.1,
2917
+ "learning_rate": 0.00065,
2918
+ "loss": 1.2235,
2919
+ "step": 469
2920
+ },
2921
+ {
2922
+ "epoch": 1.11,
2923
+ "learning_rate": 0.00065,
2924
+ "loss": 1.2483,
2925
+ "step": 470
2926
+ },
2927
+ {
2928
+ "epoch": 1.11,
2929
+ "learning_rate": 0.00065,
2930
+ "loss": 1.3401,
2931
+ "step": 471
2932
+ },
2933
+ {
2934
+ "epoch": 1.11,
2935
+ "learning_rate": 0.00065,
2936
+ "loss": 1.288,
2937
+ "step": 472
2938
+ },
2939
+ {
2940
+ "epoch": 1.11,
2941
+ "learning_rate": 0.00065,
2942
+ "loss": 1.2532,
2943
+ "step": 473
2944
+ },
2945
+ {
2946
+ "epoch": 1.11,
2947
+ "learning_rate": 0.00065,
2948
+ "loss": 1.4223,
2949
+ "step": 474
2950
+ },
2951
+ {
2952
+ "epoch": 1.12,
2953
+ "learning_rate": 0.00065,
2954
+ "loss": 1.3564,
2955
+ "step": 475
2956
+ },
2957
+ {
2958
+ "epoch": 1.12,
2959
+ "learning_rate": 0.00065,
2960
+ "loss": 1.3718,
2961
+ "step": 476
2962
+ },
2963
+ {
2964
+ "epoch": 1.12,
2965
+ "learning_rate": 0.00065,
2966
+ "loss": 1.1161,
2967
+ "step": 477
2968
+ },
2969
+ {
2970
+ "epoch": 1.12,
2971
+ "learning_rate": 0.00065,
2972
+ "loss": 1.0945,
2973
+ "step": 478
2974
+ },
2975
+ {
2976
+ "epoch": 1.13,
2977
+ "learning_rate": 0.00065,
2978
+ "loss": 1.3445,
2979
+ "step": 479
2980
+ },
2981
+ {
2982
+ "epoch": 1.13,
2983
+ "learning_rate": 0.00065,
2984
+ "loss": 1.4793,
2985
+ "step": 480
2986
+ },
2987
+ {
2988
+ "epoch": 1.13,
2989
+ "learning_rate": 0.00065,
2990
+ "loss": 0.9494,
2991
+ "step": 481
2992
+ },
2993
+ {
2994
+ "epoch": 1.13,
2995
+ "learning_rate": 0.00065,
2996
+ "loss": 1.1057,
2997
+ "step": 482
2998
+ },
2999
+ {
3000
+ "epoch": 1.14,
3001
+ "learning_rate": 0.00065,
3002
+ "loss": 1.1983,
3003
+ "step": 483
3004
+ },
3005
+ {
3006
+ "epoch": 1.14,
3007
+ "learning_rate": 0.00065,
3008
+ "loss": 1.1323,
3009
+ "step": 484
3010
+ },
3011
+ {
3012
+ "epoch": 1.14,
3013
+ "learning_rate": 0.00065,
3014
+ "loss": 1.3516,
3015
+ "step": 485
3016
+ },
3017
+ {
3018
+ "epoch": 1.14,
3019
+ "learning_rate": 0.00065,
3020
+ "loss": 1.2307,
3021
+ "step": 486
3022
+ },
3023
+ {
3024
+ "epoch": 1.15,
3025
+ "learning_rate": 0.00065,
3026
+ "loss": 0.8255,
3027
+ "step": 487
3028
+ },
3029
+ {
3030
+ "epoch": 1.15,
3031
+ "learning_rate": 0.00065,
3032
+ "loss": 1.2039,
3033
+ "step": 488
3034
+ },
3035
+ {
3036
+ "epoch": 1.15,
3037
+ "learning_rate": 0.00065,
3038
+ "loss": 0.9115,
3039
+ "step": 489
3040
+ },
3041
+ {
3042
+ "epoch": 1.15,
3043
+ "learning_rate": 0.00065,
3044
+ "loss": 1.1368,
3045
+ "step": 490
3046
+ },
3047
+ {
3048
+ "epoch": 1.16,
3049
+ "learning_rate": 0.00065,
3050
+ "loss": 1.0338,
3051
+ "step": 491
3052
+ },
3053
+ {
3054
+ "epoch": 1.16,
3055
+ "learning_rate": 0.00065,
3056
+ "loss": 1.1342,
3057
+ "step": 492
3058
+ },
3059
+ {
3060
+ "epoch": 1.16,
3061
+ "learning_rate": 0.00065,
3062
+ "loss": 1.2698,
3063
+ "step": 493
3064
+ },
3065
+ {
3066
+ "epoch": 1.16,
3067
+ "learning_rate": 0.00065,
3068
+ "loss": 0.9189,
3069
+ "step": 494
3070
+ },
3071
+ {
3072
+ "epoch": 1.16,
3073
+ "learning_rate": 0.00065,
3074
+ "loss": 1.3934,
3075
+ "step": 495
3076
+ },
3077
+ {
3078
+ "epoch": 1.17,
3079
+ "learning_rate": 0.00065,
3080
+ "loss": 1.0178,
3081
+ "step": 496
3082
+ },
3083
+ {
3084
+ "epoch": 1.17,
3085
+ "learning_rate": 0.00065,
3086
+ "loss": 1.1283,
3087
+ "step": 497
3088
+ },
3089
+ {
3090
+ "epoch": 1.17,
3091
+ "learning_rate": 0.00065,
3092
+ "loss": 1.134,
3093
+ "step": 498
3094
+ },
3095
+ {
3096
+ "epoch": 1.17,
3097
+ "learning_rate": 0.00065,
3098
+ "loss": 1.0912,
3099
+ "step": 499
3100
+ },
3101
+ {
3102
+ "epoch": 1.18,
3103
+ "learning_rate": 0.00065,
3104
+ "loss": 1.2339,
3105
+ "step": 500
3106
+ },
3107
+ {
3108
+ "epoch": 1.18,
3109
+ "learning_rate": 0.00065,
3110
+ "loss": 1.3103,
3111
+ "step": 501
3112
+ },
3113
+ {
3114
+ "epoch": 1.18,
3115
+ "learning_rate": 0.00065,
3116
+ "loss": 1.0677,
3117
+ "step": 502
3118
+ },
3119
+ {
3120
+ "epoch": 1.18,
3121
+ "learning_rate": 0.00065,
3122
+ "loss": 1.2374,
3123
+ "step": 503
3124
+ },
3125
+ {
3126
+ "epoch": 1.19,
3127
+ "learning_rate": 0.00065,
3128
+ "loss": 1.0541,
3129
+ "step": 504
3130
+ },
3131
+ {
3132
+ "epoch": 1.19,
3133
+ "eval_loss": 1.559614658355713,
3134
+ "eval_runtime": 57.6683,
3135
+ "eval_samples_per_second": 8.67,
3136
+ "eval_steps_per_second": 4.335,
3137
+ "step": 504
3138
+ },
3139
+ {
3140
+ "epoch": 1.19,
3141
+ "learning_rate": 0.00065,
3142
+ "loss": 1.1002,
3143
+ "step": 505
3144
+ },
3145
+ {
3146
+ "epoch": 1.19,
3147
+ "learning_rate": 0.00065,
3148
+ "loss": 1.1307,
3149
+ "step": 506
3150
+ },
3151
+ {
3152
+ "epoch": 1.19,
3153
+ "learning_rate": 0.00065,
3154
+ "loss": 1.5203,
3155
+ "step": 507
3156
+ },
3157
+ {
3158
+ "epoch": 1.2,
3159
+ "learning_rate": 0.00065,
3160
+ "loss": 1.2019,
3161
+ "step": 508
3162
+ },
3163
+ {
3164
+ "epoch": 1.2,
3165
+ "learning_rate": 0.00065,
3166
+ "loss": 1.1506,
3167
+ "step": 509
3168
+ },
3169
+ {
3170
+ "epoch": 1.2,
3171
+ "learning_rate": 0.00065,
3172
+ "loss": 1.2836,
3173
+ "step": 510
3174
+ },
3175
+ {
3176
+ "epoch": 1.2,
3177
+ "learning_rate": 0.00065,
3178
+ "loss": 1.2752,
3179
+ "step": 511
3180
+ },
3181
+ {
3182
+ "epoch": 1.21,
3183
+ "learning_rate": 0.00065,
3184
+ "loss": 1.1245,
3185
+ "step": 512
3186
+ },
3187
+ {
3188
+ "epoch": 1.21,
3189
+ "learning_rate": 0.00065,
3190
+ "loss": 0.9534,
3191
+ "step": 513
3192
+ },
3193
+ {
3194
+ "epoch": 1.21,
3195
+ "learning_rate": 0.00065,
3196
+ "loss": 1.1814,
3197
+ "step": 514
3198
+ },
3199
+ {
3200
+ "epoch": 1.21,
3201
+ "learning_rate": 0.00065,
3202
+ "loss": 1.2562,
3203
+ "step": 515
3204
+ },
3205
+ {
3206
+ "epoch": 1.21,
3207
+ "learning_rate": 0.00065,
3208
+ "loss": 1.1561,
3209
+ "step": 516
3210
+ },
3211
+ {
3212
+ "epoch": 1.22,
3213
+ "learning_rate": 0.00065,
3214
+ "loss": 1.3549,
3215
+ "step": 517
3216
+ },
3217
+ {
3218
+ "epoch": 1.22,
3219
+ "learning_rate": 0.00065,
3220
+ "loss": 1.0763,
3221
+ "step": 518
3222
+ },
3223
+ {
3224
+ "epoch": 1.22,
3225
+ "learning_rate": 0.00065,
3226
+ "loss": 1.2134,
3227
+ "step": 519
3228
+ },
3229
+ {
3230
+ "epoch": 1.22,
3231
+ "learning_rate": 0.00065,
3232
+ "loss": 1.2445,
3233
+ "step": 520
3234
+ },
3235
+ {
3236
+ "epoch": 1.23,
3237
+ "learning_rate": 0.00065,
3238
+ "loss": 0.976,
3239
+ "step": 521
3240
+ },
3241
+ {
3242
+ "epoch": 1.23,
3243
+ "learning_rate": 0.00065,
3244
+ "loss": 1.2341,
3245
+ "step": 522
3246
+ },
3247
+ {
3248
+ "epoch": 1.23,
3249
+ "learning_rate": 0.00065,
3250
+ "loss": 1.2847,
3251
+ "step": 523
3252
+ },
3253
+ {
3254
+ "epoch": 1.23,
3255
+ "learning_rate": 0.00065,
3256
+ "loss": 1.2537,
3257
+ "step": 524
3258
+ },
3259
+ {
3260
+ "epoch": 1.24,
3261
+ "learning_rate": 0.00065,
3262
+ "loss": 1.2653,
3263
+ "step": 525
3264
+ },
3265
+ {
3266
+ "epoch": 1.24,
3267
+ "learning_rate": 0.00065,
3268
+ "loss": 1.1949,
3269
+ "step": 526
3270
+ },
3271
+ {
3272
+ "epoch": 1.24,
3273
+ "learning_rate": 0.00065,
3274
+ "loss": 0.9586,
3275
+ "step": 527
3276
+ },
3277
+ {
3278
+ "epoch": 1.24,
3279
+ "learning_rate": 0.00065,
3280
+ "loss": 1.0875,
3281
+ "step": 528
3282
+ },
3283
+ {
3284
+ "epoch": 1.25,
3285
+ "learning_rate": 0.00065,
3286
+ "loss": 0.8407,
3287
+ "step": 529
3288
+ },
3289
+ {
3290
+ "epoch": 1.25,
3291
+ "learning_rate": 0.00065,
3292
+ "loss": 1.1969,
3293
+ "step": 530
3294
+ },
3295
+ {
3296
+ "epoch": 1.25,
3297
+ "learning_rate": 0.00065,
3298
+ "loss": 1.2271,
3299
+ "step": 531
3300
+ },
3301
+ {
3302
+ "epoch": 1.25,
3303
+ "learning_rate": 0.00065,
3304
+ "loss": 1.2104,
3305
+ "step": 532
3306
+ },
3307
+ {
3308
+ "epoch": 1.26,
3309
+ "learning_rate": 0.00065,
3310
+ "loss": 1.0545,
3311
+ "step": 533
3312
+ },
3313
+ {
3314
+ "epoch": 1.26,
3315
+ "learning_rate": 0.00065,
3316
+ "loss": 1.2407,
3317
+ "step": 534
3318
+ },
3319
+ {
3320
+ "epoch": 1.26,
3321
+ "learning_rate": 0.00065,
3322
+ "loss": 1.3342,
3323
+ "step": 535
3324
+ },
3325
+ {
3326
+ "epoch": 1.26,
3327
+ "learning_rate": 0.00065,
3328
+ "loss": 1.131,
3329
+ "step": 536
3330
+ },
3331
+ {
3332
+ "epoch": 1.26,
3333
+ "learning_rate": 0.00065,
3334
+ "loss": 1.1606,
3335
+ "step": 537
3336
+ },
3337
+ {
3338
+ "epoch": 1.27,
3339
+ "learning_rate": 0.00065,
3340
+ "loss": 1.1866,
3341
+ "step": 538
3342
+ },
3343
+ {
3344
+ "epoch": 1.27,
3345
+ "learning_rate": 0.00065,
3346
+ "loss": 0.9723,
3347
+ "step": 539
3348
+ },
3349
+ {
3350
+ "epoch": 1.27,
3351
+ "learning_rate": 0.00065,
3352
+ "loss": 1.2043,
3353
+ "step": 540
3354
+ },
3355
+ {
3356
+ "epoch": 1.27,
3357
+ "learning_rate": 0.00065,
3358
+ "loss": 1.2889,
3359
+ "step": 541
3360
+ },
3361
+ {
3362
+ "epoch": 1.28,
3363
+ "learning_rate": 0.00065,
3364
+ "loss": 1.1564,
3365
+ "step": 542
3366
+ },
3367
+ {
3368
+ "epoch": 1.28,
3369
+ "learning_rate": 0.00065,
3370
+ "loss": 1.1532,
3371
+ "step": 543
3372
+ },
3373
+ {
3374
+ "epoch": 1.28,
3375
+ "learning_rate": 0.00065,
3376
+ "loss": 1.1011,
3377
+ "step": 544
3378
+ },
3379
+ {
3380
+ "epoch": 1.28,
3381
+ "learning_rate": 0.00065,
3382
+ "loss": 1.0829,
3383
+ "step": 545
3384
+ },
3385
+ {
3386
+ "epoch": 1.29,
3387
+ "learning_rate": 0.00065,
3388
+ "loss": 1.2337,
3389
+ "step": 546
3390
+ },
3391
+ {
3392
+ "epoch": 1.29,
3393
+ "eval_loss": 1.5788898468017578,
3394
+ "eval_runtime": 57.6591,
3395
+ "eval_samples_per_second": 8.672,
3396
+ "eval_steps_per_second": 4.336,
3397
+ "step": 546
3398
+ },
3399
+ {
3400
+ "epoch": 1.29,
3401
+ "learning_rate": 0.00065,
3402
+ "loss": 1.3735,
3403
+ "step": 547
3404
+ },
3405
+ {
3406
+ "epoch": 1.29,
3407
+ "learning_rate": 0.00065,
3408
+ "loss": 1.241,
3409
+ "step": 548
3410
+ },
3411
+ {
3412
+ "epoch": 1.29,
3413
+ "learning_rate": 0.00065,
3414
+ "loss": 1.4505,
3415
+ "step": 549
3416
+ },
3417
+ {
3418
+ "epoch": 1.3,
3419
+ "learning_rate": 0.00065,
3420
+ "loss": 1.2719,
3421
+ "step": 550
3422
+ },
3423
+ {
3424
+ "epoch": 1.3,
3425
+ "learning_rate": 0.00065,
3426
+ "loss": 1.2341,
3427
+ "step": 551
3428
+ },
3429
+ {
3430
+ "epoch": 1.3,
3431
+ "learning_rate": 0.00065,
3432
+ "loss": 1.1105,
3433
+ "step": 552
3434
+ },
3435
+ {
3436
+ "epoch": 1.3,
3437
+ "learning_rate": 0.00065,
3438
+ "loss": 1.0891,
3439
+ "step": 553
3440
+ },
3441
+ {
3442
+ "epoch": 1.31,
3443
+ "learning_rate": 0.00065,
3444
+ "loss": 1.1677,
3445
+ "step": 554
3446
+ },
3447
+ {
3448
+ "epoch": 1.31,
3449
+ "learning_rate": 0.00065,
3450
+ "loss": 1.341,
3451
+ "step": 555
3452
+ },
3453
+ {
3454
+ "epoch": 1.31,
3455
+ "learning_rate": 0.00065,
3456
+ "loss": 1.2119,
3457
+ "step": 556
3458
+ },
3459
+ {
3460
+ "epoch": 1.31,
3461
+ "learning_rate": 0.00065,
3462
+ "loss": 1.0217,
3463
+ "step": 557
3464
+ },
3465
+ {
3466
+ "epoch": 1.32,
3467
+ "learning_rate": 0.00065,
3468
+ "loss": 1.3831,
3469
+ "step": 558
3470
+ },
3471
+ {
3472
+ "epoch": 1.32,
3473
+ "learning_rate": 0.00065,
3474
+ "loss": 1.1828,
3475
+ "step": 559
3476
+ },
3477
+ {
3478
+ "epoch": 1.32,
3479
+ "learning_rate": 0.00065,
3480
+ "loss": 1.2138,
3481
+ "step": 560
3482
+ },
3483
+ {
3484
+ "epoch": 1.32,
3485
+ "learning_rate": 0.00065,
3486
+ "loss": 1.2737,
3487
+ "step": 561
3488
+ },
3489
+ {
3490
+ "epoch": 1.32,
3491
+ "learning_rate": 0.00065,
3492
+ "loss": 1.027,
3493
+ "step": 562
3494
+ },
3495
+ {
3496
+ "epoch": 1.33,
3497
+ "learning_rate": 0.00065,
3498
+ "loss": 1.0615,
3499
+ "step": 563
3500
+ },
3501
+ {
3502
+ "epoch": 1.33,
3503
+ "learning_rate": 0.00065,
3504
+ "loss": 1.2548,
3505
+ "step": 564
3506
+ },
3507
+ {
3508
+ "epoch": 1.33,
3509
+ "learning_rate": 0.00065,
3510
+ "loss": 1.1936,
3511
+ "step": 565
3512
+ },
3513
+ {
3514
+ "epoch": 1.33,
3515
+ "learning_rate": 0.00065,
3516
+ "loss": 1.2813,
3517
+ "step": 566
3518
+ },
3519
+ {
3520
+ "epoch": 1.34,
3521
+ "learning_rate": 0.00065,
3522
+ "loss": 1.0757,
3523
+ "step": 567
3524
+ },
3525
+ {
3526
+ "epoch": 1.34,
3527
+ "learning_rate": 0.00065,
3528
+ "loss": 1.203,
3529
+ "step": 568
3530
+ },
3531
+ {
3532
+ "epoch": 1.34,
3533
+ "learning_rate": 0.00065,
3534
+ "loss": 1.1908,
3535
+ "step": 569
3536
+ },
3537
+ {
3538
+ "epoch": 1.34,
3539
+ "learning_rate": 0.00065,
3540
+ "loss": 1.1739,
3541
+ "step": 570
3542
+ },
3543
+ {
3544
+ "epoch": 1.35,
3545
+ "learning_rate": 0.00065,
3546
+ "loss": 1.1155,
3547
+ "step": 571
3548
+ },
3549
+ {
3550
+ "epoch": 1.35,
3551
+ "learning_rate": 0.00065,
3552
+ "loss": 1.2386,
3553
+ "step": 572
3554
+ },
3555
+ {
3556
+ "epoch": 1.35,
3557
+ "learning_rate": 0.00065,
3558
+ "loss": 1.0254,
3559
+ "step": 573
3560
+ },
3561
+ {
3562
+ "epoch": 1.35,
3563
+ "learning_rate": 0.00065,
3564
+ "loss": 1.1139,
3565
+ "step": 574
3566
+ },
3567
+ {
3568
+ "epoch": 1.36,
3569
+ "learning_rate": 0.00065,
3570
+ "loss": 1.382,
3571
+ "step": 575
3572
+ },
3573
+ {
3574
+ "epoch": 1.36,
3575
+ "learning_rate": 0.00065,
3576
+ "loss": 1.2854,
3577
+ "step": 576
3578
+ },
3579
+ {
3580
+ "epoch": 1.36,
3581
+ "learning_rate": 0.00065,
3582
+ "loss": 1.3669,
3583
+ "step": 577
3584
+ },
3585
+ {
3586
+ "epoch": 1.36,
3587
+ "learning_rate": 0.00065,
3588
+ "loss": 1.0083,
3589
+ "step": 578
3590
+ },
3591
+ {
3592
+ "epoch": 1.37,
3593
+ "learning_rate": 0.00065,
3594
+ "loss": 1.136,
3595
+ "step": 579
3596
+ },
3597
+ {
3598
+ "epoch": 1.37,
3599
+ "learning_rate": 0.00065,
3600
+ "loss": 1.1165,
3601
+ "step": 580
3602
+ },
3603
+ {
3604
+ "epoch": 1.37,
3605
+ "learning_rate": 0.00065,
3606
+ "loss": 1.0514,
3607
+ "step": 581
3608
+ },
3609
+ {
3610
+ "epoch": 1.37,
3611
+ "learning_rate": 0.00065,
3612
+ "loss": 1.2967,
3613
+ "step": 582
3614
+ },
3615
+ {
3616
+ "epoch": 1.37,
3617
+ "learning_rate": 0.00065,
3618
+ "loss": 1.183,
3619
+ "step": 583
3620
+ },
3621
+ {
3622
+ "epoch": 1.38,
3623
+ "learning_rate": 0.00065,
3624
+ "loss": 1.186,
3625
+ "step": 584
3626
+ },
3627
+ {
3628
+ "epoch": 1.38,
3629
+ "learning_rate": 0.00065,
3630
+ "loss": 1.1914,
3631
+ "step": 585
3632
+ },
3633
+ {
3634
+ "epoch": 1.38,
3635
+ "learning_rate": 0.00065,
3636
+ "loss": 1.1845,
3637
+ "step": 586
3638
+ },
3639
+ {
3640
+ "epoch": 1.38,
3641
+ "learning_rate": 0.00065,
3642
+ "loss": 1.2612,
3643
+ "step": 587
3644
+ },
3645
+ {
3646
+ "epoch": 1.39,
3647
+ "learning_rate": 0.00065,
3648
+ "loss": 0.9719,
3649
+ "step": 588
3650
+ },
3651
+ {
3652
+ "epoch": 1.39,
3653
+ "eval_loss": 1.5859321355819702,
3654
+ "eval_runtime": 57.6415,
3655
+ "eval_samples_per_second": 8.674,
3656
+ "eval_steps_per_second": 4.337,
3657
+ "step": 588
3658
+ },
3659
+ {
3660
+ "epoch": 1.39,
3661
+ "learning_rate": 0.00065,
3662
+ "loss": 1.291,
3663
+ "step": 589
3664
+ },
3665
+ {
3666
+ "epoch": 1.39,
3667
+ "learning_rate": 0.00065,
3668
+ "loss": 0.8737,
3669
+ "step": 590
3670
+ },
3671
+ {
3672
+ "epoch": 1.39,
3673
+ "learning_rate": 0.00065,
3674
+ "loss": 1.3129,
3675
+ "step": 591
3676
+ },
3677
+ {
3678
+ "epoch": 1.4,
3679
+ "learning_rate": 0.00065,
3680
+ "loss": 1.1863,
3681
+ "step": 592
3682
+ },
3683
+ {
3684
+ "epoch": 1.4,
3685
+ "learning_rate": 0.00065,
3686
+ "loss": 1.094,
3687
+ "step": 593
3688
+ },
3689
+ {
3690
+ "epoch": 1.4,
3691
+ "learning_rate": 0.00065,
3692
+ "loss": 1.3167,
3693
+ "step": 594
3694
+ },
3695
+ {
3696
+ "epoch": 1.4,
3697
+ "learning_rate": 0.00065,
3698
+ "loss": 1.1205,
3699
+ "step": 595
3700
+ },
3701
+ {
3702
+ "epoch": 1.41,
3703
+ "learning_rate": 0.00065,
3704
+ "loss": 1.1263,
3705
+ "step": 596
3706
+ },
3707
+ {
3708
+ "epoch": 1.41,
3709
+ "learning_rate": 0.00065,
3710
+ "loss": 1.0644,
3711
+ "step": 597
3712
+ },
3713
+ {
3714
+ "epoch": 1.41,
3715
+ "learning_rate": 0.00065,
3716
+ "loss": 1.2847,
3717
+ "step": 598
3718
+ },
3719
+ {
3720
+ "epoch": 1.41,
3721
+ "learning_rate": 0.00065,
3722
+ "loss": 1.1278,
3723
+ "step": 599
3724
+ },
3725
+ {
3726
+ "epoch": 1.42,
3727
+ "learning_rate": 0.00065,
3728
+ "loss": 1.0939,
3729
+ "step": 600
3730
+ },
3731
+ {
3732
+ "epoch": 1.42,
3733
+ "learning_rate": 0.00065,
3734
+ "loss": 1.1051,
3735
+ "step": 601
3736
+ },
3737
+ {
3738
+ "epoch": 1.42,
3739
+ "learning_rate": 0.00065,
3740
+ "loss": 1.1711,
3741
+ "step": 602
3742
+ },
3743
+ {
3744
+ "epoch": 1.42,
3745
+ "learning_rate": 0.00065,
3746
+ "loss": 1.4111,
3747
+ "step": 603
3748
+ },
3749
+ {
3750
+ "epoch": 1.42,
3751
+ "learning_rate": 0.00065,
3752
+ "loss": 1.1579,
3753
+ "step": 604
3754
+ },
3755
+ {
3756
+ "epoch": 1.43,
3757
+ "learning_rate": 0.00065,
3758
+ "loss": 1.2531,
3759
+ "step": 605
3760
+ },
3761
+ {
3762
+ "epoch": 1.43,
3763
+ "learning_rate": 0.00065,
3764
+ "loss": 1.2966,
3765
+ "step": 606
3766
+ },
3767
+ {
3768
+ "epoch": 1.43,
3769
+ "learning_rate": 0.00065,
3770
+ "loss": 1.2329,
3771
+ "step": 607
3772
+ },
3773
+ {
3774
+ "epoch": 1.43,
3775
+ "learning_rate": 0.00065,
3776
+ "loss": 1.1892,
3777
+ "step": 608
3778
+ },
3779
+ {
3780
+ "epoch": 1.44,
3781
+ "learning_rate": 0.00065,
3782
+ "loss": 1.3673,
3783
+ "step": 609
3784
+ },
3785
+ {
3786
+ "epoch": 1.44,
3787
+ "learning_rate": 0.00065,
3788
+ "loss": 1.0371,
3789
+ "step": 610
3790
+ },
3791
+ {
3792
+ "epoch": 1.44,
3793
+ "learning_rate": 0.00065,
3794
+ "loss": 1.3279,
3795
+ "step": 611
3796
+ },
3797
+ {
3798
+ "epoch": 1.44,
3799
+ "learning_rate": 0.00065,
3800
+ "loss": 0.9754,
3801
+ "step": 612
3802
+ },
3803
+ {
3804
+ "epoch": 1.45,
3805
+ "learning_rate": 0.00065,
3806
+ "loss": 1.097,
3807
+ "step": 613
3808
+ },
3809
+ {
3810
+ "epoch": 1.45,
3811
+ "learning_rate": 0.00065,
3812
+ "loss": 1.0986,
3813
+ "step": 614
3814
+ },
3815
+ {
3816
+ "epoch": 1.45,
3817
+ "learning_rate": 0.00065,
3818
+ "loss": 1.1958,
3819
+ "step": 615
3820
+ },
3821
+ {
3822
+ "epoch": 1.45,
3823
+ "learning_rate": 0.00065,
3824
+ "loss": 1.2261,
3825
+ "step": 616
3826
+ },
3827
+ {
3828
+ "epoch": 1.46,
3829
+ "learning_rate": 0.00065,
3830
+ "loss": 1.0797,
3831
+ "step": 617
3832
+ },
3833
+ {
3834
+ "epoch": 1.46,
3835
+ "learning_rate": 0.00065,
3836
+ "loss": 1.1249,
3837
+ "step": 618
3838
+ },
3839
+ {
3840
+ "epoch": 1.46,
3841
+ "learning_rate": 0.00065,
3842
+ "loss": 1.3726,
3843
+ "step": 619
3844
+ },
3845
+ {
3846
+ "epoch": 1.46,
3847
+ "learning_rate": 0.00065,
3848
+ "loss": 0.9819,
3849
+ "step": 620
3850
+ },
3851
+ {
3852
+ "epoch": 1.47,
3853
+ "learning_rate": 0.00065,
3854
+ "loss": 1.1712,
3855
+ "step": 621
3856
+ },
3857
+ {
3858
+ "epoch": 1.47,
3859
+ "learning_rate": 0.00065,
3860
+ "loss": 1.1711,
3861
+ "step": 622
3862
+ },
3863
+ {
3864
+ "epoch": 1.47,
3865
+ "learning_rate": 0.00065,
3866
+ "loss": 1.0783,
3867
+ "step": 623
3868
+ },
3869
+ {
3870
+ "epoch": 1.47,
3871
+ "learning_rate": 0.00065,
3872
+ "loss": 1.3031,
3873
+ "step": 624
3874
+ },
3875
+ {
3876
+ "epoch": 1.47,
3877
+ "learning_rate": 0.00065,
3878
+ "loss": 1.1674,
3879
+ "step": 625
3880
+ },
3881
+ {
3882
+ "epoch": 1.48,
3883
+ "learning_rate": 0.00065,
3884
+ "loss": 1.1693,
3885
+ "step": 626
3886
+ },
3887
+ {
3888
+ "epoch": 1.48,
3889
+ "learning_rate": 0.00065,
3890
+ "loss": 1.1413,
3891
+ "step": 627
3892
+ },
3893
+ {
3894
+ "epoch": 1.48,
3895
+ "learning_rate": 0.00065,
3896
+ "loss": 1.275,
3897
+ "step": 628
3898
+ },
3899
+ {
3900
+ "epoch": 1.48,
3901
+ "learning_rate": 0.00065,
3902
+ "loss": 1.1146,
3903
+ "step": 629
3904
+ },
3905
+ {
3906
+ "epoch": 1.49,
3907
+ "learning_rate": 0.00065,
3908
+ "loss": 1.2189,
3909
+ "step": 630
3910
+ },
3911
+ {
3912
+ "epoch": 1.49,
3913
+ "eval_loss": 1.5958884954452515,
3914
+ "eval_runtime": 57.618,
3915
+ "eval_samples_per_second": 8.678,
3916
+ "eval_steps_per_second": 4.339,
3917
+ "step": 630
3918
+ },
3919
+ {
3920
+ "epoch": 1.49,
3921
+ "learning_rate": 0.00065,
3922
+ "loss": 1.1986,
3923
+ "step": 631
3924
+ },
3925
+ {
3926
+ "epoch": 1.49,
3927
+ "learning_rate": 0.00065,
3928
+ "loss": 1.3615,
3929
+ "step": 632
3930
+ },
3931
+ {
3932
+ "epoch": 1.49,
3933
+ "learning_rate": 0.00065,
3934
+ "loss": 1.4031,
3935
+ "step": 633
3936
+ },
3937
+ {
3938
+ "epoch": 1.5,
3939
+ "learning_rate": 0.00065,
3940
+ "loss": 1.4007,
3941
+ "step": 634
3942
+ },
3943
+ {
3944
+ "epoch": 1.5,
3945
+ "learning_rate": 0.00065,
3946
+ "loss": 1.463,
3947
+ "step": 635
3948
+ },
3949
+ {
3950
+ "epoch": 1.5,
3951
+ "learning_rate": 0.00065,
3952
+ "loss": 0.802,
3953
+ "step": 636
3954
+ },
3955
+ {
3956
+ "epoch": 1.5,
3957
+ "learning_rate": 0.00065,
3958
+ "loss": 1.2234,
3959
+ "step": 637
3960
+ },
3961
+ {
3962
+ "epoch": 1.51,
3963
+ "learning_rate": 0.00065,
3964
+ "loss": 1.1812,
3965
+ "step": 638
3966
+ },
3967
+ {
3968
+ "epoch": 1.51,
3969
+ "learning_rate": 0.00065,
3970
+ "loss": 1.2459,
3971
+ "step": 639
3972
+ },
3973
+ {
3974
+ "epoch": 1.51,
3975
+ "learning_rate": 0.00065,
3976
+ "loss": 1.2198,
3977
+ "step": 640
3978
+ },
3979
+ {
3980
+ "epoch": 1.51,
3981
+ "learning_rate": 0.00065,
3982
+ "loss": 1.251,
3983
+ "step": 641
3984
+ },
3985
+ {
3986
+ "epoch": 1.52,
3987
+ "learning_rate": 0.00065,
3988
+ "loss": 1.0966,
3989
+ "step": 642
3990
+ },
3991
+ {
3992
+ "epoch": 1.52,
3993
+ "learning_rate": 0.00065,
3994
+ "loss": 1.0978,
3995
+ "step": 643
3996
+ },
3997
+ {
3998
+ "epoch": 1.52,
3999
+ "learning_rate": 0.00065,
4000
+ "loss": 1.3338,
4001
+ "step": 644
4002
+ },
4003
+ {
4004
+ "epoch": 1.52,
4005
+ "learning_rate": 0.00065,
4006
+ "loss": 1.3305,
4007
+ "step": 645
4008
+ },
4009
+ {
4010
+ "epoch": 1.53,
4011
+ "learning_rate": 0.00065,
4012
+ "loss": 1.2164,
4013
+ "step": 646
4014
+ },
4015
+ {
4016
+ "epoch": 1.53,
4017
+ "learning_rate": 0.00065,
4018
+ "loss": 1.1011,
4019
+ "step": 647
4020
+ },
4021
+ {
4022
+ "epoch": 1.53,
4023
+ "learning_rate": 0.00065,
4024
+ "loss": 1.0557,
4025
+ "step": 648
4026
+ },
4027
+ {
4028
+ "epoch": 1.53,
4029
+ "learning_rate": 0.00065,
4030
+ "loss": 1.1814,
4031
+ "step": 649
4032
+ },
4033
+ {
4034
+ "epoch": 1.53,
4035
+ "learning_rate": 0.00065,
4036
+ "loss": 1.3844,
4037
+ "step": 650
4038
+ },
4039
+ {
4040
+ "epoch": 1.54,
4041
+ "learning_rate": 0.00065,
4042
+ "loss": 1.1344,
4043
+ "step": 651
4044
+ },
4045
+ {
4046
+ "epoch": 1.54,
4047
+ "learning_rate": 0.00065,
4048
+ "loss": 1.1051,
4049
+ "step": 652
4050
+ },
4051
+ {
4052
+ "epoch": 1.54,
4053
+ "learning_rate": 0.00065,
4054
+ "loss": 1.2505,
4055
+ "step": 653
4056
+ },
4057
+ {
4058
+ "epoch": 1.54,
4059
+ "learning_rate": 0.00065,
4060
+ "loss": 1.2285,
4061
+ "step": 654
4062
+ },
4063
+ {
4064
+ "epoch": 1.55,
4065
+ "learning_rate": 0.00065,
4066
+ "loss": 1.1327,
4067
+ "step": 655
4068
+ },
4069
+ {
4070
+ "epoch": 1.55,
4071
+ "learning_rate": 0.00065,
4072
+ "loss": 1.021,
4073
+ "step": 656
4074
+ },
4075
+ {
4076
+ "epoch": 1.55,
4077
+ "learning_rate": 0.00065,
4078
+ "loss": 1.1479,
4079
+ "step": 657
4080
+ },
4081
+ {
4082
+ "epoch": 1.55,
4083
+ "learning_rate": 0.00065,
4084
+ "loss": 1.209,
4085
+ "step": 658
4086
+ },
4087
+ {
4088
+ "epoch": 1.56,
4089
+ "learning_rate": 0.00065,
4090
+ "loss": 1.0886,
4091
+ "step": 659
4092
+ },
4093
+ {
4094
+ "epoch": 1.56,
4095
+ "learning_rate": 0.00065,
4096
+ "loss": 1.0655,
4097
+ "step": 660
4098
+ },
4099
+ {
4100
+ "epoch": 1.56,
4101
+ "learning_rate": 0.00065,
4102
+ "loss": 1.1478,
4103
+ "step": 661
4104
+ },
4105
+ {
4106
+ "epoch": 1.56,
4107
+ "learning_rate": 0.00065,
4108
+ "loss": 1.1008,
4109
+ "step": 662
4110
+ },
4111
+ {
4112
+ "epoch": 1.57,
4113
+ "learning_rate": 0.00065,
4114
+ "loss": 1.1215,
4115
+ "step": 663
4116
+ },
4117
+ {
4118
+ "epoch": 1.57,
4119
+ "learning_rate": 0.00065,
4120
+ "loss": 1.3755,
4121
+ "step": 664
4122
+ },
4123
+ {
4124
+ "epoch": 1.57,
4125
+ "learning_rate": 0.00065,
4126
+ "loss": 1.0205,
4127
+ "step": 665
4128
+ },
4129
+ {
4130
+ "epoch": 1.57,
4131
+ "learning_rate": 0.00065,
4132
+ "loss": 1.2023,
4133
+ "step": 666
4134
+ },
4135
+ {
4136
+ "epoch": 1.58,
4137
+ "learning_rate": 0.00065,
4138
+ "loss": 1.0582,
4139
+ "step": 667
4140
+ },
4141
+ {
4142
+ "epoch": 1.58,
4143
+ "learning_rate": 0.00065,
4144
+ "loss": 1.145,
4145
+ "step": 668
4146
+ },
4147
+ {
4148
+ "epoch": 1.58,
4149
+ "learning_rate": 0.00065,
4150
+ "loss": 1.1469,
4151
+ "step": 669
4152
+ },
4153
+ {
4154
+ "epoch": 1.58,
4155
+ "learning_rate": 0.00065,
4156
+ "loss": 1.1109,
4157
+ "step": 670
4158
+ },
4159
+ {
4160
+ "epoch": 1.58,
4161
+ "learning_rate": 0.00065,
4162
+ "loss": 1.0745,
4163
+ "step": 671
4164
+ },
4165
+ {
4166
+ "epoch": 1.59,
4167
+ "learning_rate": 0.00065,
4168
+ "loss": 1.2566,
4169
+ "step": 672
4170
+ },
4171
+ {
4172
+ "epoch": 1.59,
4173
+ "eval_loss": 1.5968223810195923,
4174
+ "eval_runtime": 57.7702,
4175
+ "eval_samples_per_second": 8.655,
4176
+ "eval_steps_per_second": 4.327,
4177
+ "step": 672
4178
+ },
4179
+ {
4180
+ "epoch": 1.59,
4181
+ "learning_rate": 0.00065,
4182
+ "loss": 1.2859,
4183
+ "step": 673
4184
+ },
4185
+ {
4186
+ "epoch": 1.59,
4187
+ "learning_rate": 0.00065,
4188
+ "loss": 0.8272,
4189
+ "step": 674
4190
+ },
4191
+ {
4192
+ "epoch": 1.59,
4193
+ "learning_rate": 0.00065,
4194
+ "loss": 1.2386,
4195
+ "step": 675
4196
+ },
4197
+ {
4198
+ "epoch": 1.6,
4199
+ "learning_rate": 0.00065,
4200
+ "loss": 1.0858,
4201
+ "step": 676
4202
+ },
4203
+ {
4204
+ "epoch": 1.6,
4205
+ "learning_rate": 0.00065,
4206
+ "loss": 1.4543,
4207
+ "step": 677
4208
+ },
4209
+ {
4210
+ "epoch": 1.6,
4211
+ "learning_rate": 0.00065,
4212
+ "loss": 1.3696,
4213
+ "step": 678
4214
+ },
4215
+ {
4216
+ "epoch": 1.6,
4217
+ "learning_rate": 0.00065,
4218
+ "loss": 1.0247,
4219
+ "step": 679
4220
+ },
4221
+ {
4222
+ "epoch": 1.61,
4223
+ "learning_rate": 0.00065,
4224
+ "loss": 0.8026,
4225
+ "step": 680
4226
+ },
4227
+ {
4228
+ "epoch": 1.61,
4229
+ "learning_rate": 0.00065,
4230
+ "loss": 1.1607,
4231
+ "step": 681
4232
+ },
4233
+ {
4234
+ "epoch": 1.61,
4235
+ "learning_rate": 0.00065,
4236
+ "loss": 1.1685,
4237
+ "step": 682
4238
+ },
4239
+ {
4240
+ "epoch": 1.61,
4241
+ "learning_rate": 0.00065,
4242
+ "loss": 1.307,
4243
+ "step": 683
4244
+ },
4245
+ {
4246
+ "epoch": 1.62,
4247
+ "learning_rate": 0.00065,
4248
+ "loss": 1.24,
4249
+ "step": 684
4250
+ },
4251
+ {
4252
+ "epoch": 1.62,
4253
+ "learning_rate": 0.00065,
4254
+ "loss": 1.1193,
4255
+ "step": 685
4256
+ },
4257
+ {
4258
+ "epoch": 1.62,
4259
+ "learning_rate": 0.00065,
4260
+ "loss": 1.0114,
4261
+ "step": 686
4262
+ },
4263
+ {
4264
+ "epoch": 1.62,
4265
+ "learning_rate": 0.00065,
4266
+ "loss": 1.0478,
4267
+ "step": 687
4268
+ },
4269
+ {
4270
+ "epoch": 1.63,
4271
+ "learning_rate": 0.00065,
4272
+ "loss": 1.2924,
4273
+ "step": 688
4274
+ },
4275
+ {
4276
+ "epoch": 1.63,
4277
+ "learning_rate": 0.00065,
4278
+ "loss": 1.0249,
4279
+ "step": 689
4280
+ },
4281
+ {
4282
+ "epoch": 1.63,
4283
+ "learning_rate": 0.00065,
4284
+ "loss": 1.1305,
4285
+ "step": 690
4286
+ },
4287
+ {
4288
+ "epoch": 1.63,
4289
+ "learning_rate": 0.00065,
4290
+ "loss": 1.0604,
4291
+ "step": 691
4292
+ },
4293
+ {
4294
+ "epoch": 1.63,
4295
+ "learning_rate": 0.00065,
4296
+ "loss": 1.3059,
4297
+ "step": 692
4298
+ },
4299
+ {
4300
+ "epoch": 1.64,
4301
+ "learning_rate": 0.00065,
4302
+ "loss": 1.343,
4303
+ "step": 693
4304
+ },
4305
+ {
4306
+ "epoch": 1.64,
4307
+ "learning_rate": 0.00065,
4308
+ "loss": 1.2422,
4309
+ "step": 694
4310
+ },
4311
+ {
4312
+ "epoch": 1.64,
4313
+ "learning_rate": 0.00065,
4314
+ "loss": 0.9783,
4315
+ "step": 695
4316
+ },
4317
+ {
4318
+ "epoch": 1.64,
4319
+ "learning_rate": 0.00065,
4320
+ "loss": 1.1911,
4321
+ "step": 696
4322
+ },
4323
+ {
4324
+ "epoch": 1.65,
4325
+ "learning_rate": 0.00065,
4326
+ "loss": 1.0073,
4327
+ "step": 697
4328
+ },
4329
+ {
4330
+ "epoch": 1.65,
4331
+ "learning_rate": 0.00065,
4332
+ "loss": 1.2903,
4333
+ "step": 698
4334
+ },
4335
+ {
4336
+ "epoch": 1.65,
4337
+ "learning_rate": 0.00065,
4338
+ "loss": 1.1604,
4339
+ "step": 699
4340
+ },
4341
+ {
4342
+ "epoch": 1.65,
4343
+ "learning_rate": 0.00065,
4344
+ "loss": 1.1637,
4345
+ "step": 700
4346
+ },
4347
+ {
4348
+ "epoch": 1.66,
4349
+ "learning_rate": 0.00065,
4350
+ "loss": 1.1648,
4351
+ "step": 701
4352
+ },
4353
+ {
4354
+ "epoch": 1.66,
4355
+ "learning_rate": 0.00065,
4356
+ "loss": 1.3168,
4357
+ "step": 702
4358
+ },
4359
+ {
4360
+ "epoch": 1.66,
4361
+ "learning_rate": 0.00065,
4362
+ "loss": 1.2936,
4363
+ "step": 703
4364
+ },
4365
+ {
4366
+ "epoch": 1.66,
4367
+ "learning_rate": 0.00065,
4368
+ "loss": 1.2169,
4369
+ "step": 704
4370
+ },
4371
+ {
4372
+ "epoch": 1.67,
4373
+ "learning_rate": 0.00065,
4374
+ "loss": 1.312,
4375
+ "step": 705
4376
+ },
4377
+ {
4378
+ "epoch": 1.67,
4379
+ "learning_rate": 0.00065,
4380
+ "loss": 1.0459,
4381
+ "step": 706
4382
+ },
4383
+ {
4384
+ "epoch": 1.67,
4385
+ "learning_rate": 0.00065,
4386
+ "loss": 1.2515,
4387
+ "step": 707
4388
+ },
4389
+ {
4390
+ "epoch": 1.67,
4391
+ "learning_rate": 0.00065,
4392
+ "loss": 1.1142,
4393
+ "step": 708
4394
+ },
4395
+ {
4396
+ "epoch": 1.68,
4397
+ "learning_rate": 0.00065,
4398
+ "loss": 0.9709,
4399
+ "step": 709
4400
+ },
4401
+ {
4402
+ "epoch": 1.68,
4403
+ "learning_rate": 0.00065,
4404
+ "loss": 1.1636,
4405
+ "step": 710
4406
+ },
4407
+ {
4408
+ "epoch": 1.68,
4409
+ "learning_rate": 0.00065,
4410
+ "loss": 1.2273,
4411
+ "step": 711
4412
+ },
4413
+ {
4414
+ "epoch": 1.68,
4415
+ "learning_rate": 0.00065,
4416
+ "loss": 1.4015,
4417
+ "step": 712
4418
+ },
4419
+ {
4420
+ "epoch": 1.68,
4421
+ "learning_rate": 0.00065,
4422
+ "loss": 1.2383,
4423
+ "step": 713
4424
+ },
4425
+ {
4426
+ "epoch": 1.69,
4427
+ "learning_rate": 0.00065,
4428
+ "loss": 0.7049,
4429
+ "step": 714
4430
+ },
4431
+ {
4432
+ "epoch": 1.69,
4433
+ "eval_loss": 1.5986626148223877,
4434
+ "eval_runtime": 57.7067,
4435
+ "eval_samples_per_second": 8.665,
4436
+ "eval_steps_per_second": 4.332,
4437
+ "step": 714
4438
+ },
4439
+ {
4440
+ "epoch": 1.69,
4441
+ "learning_rate": 0.00065,
4442
+ "loss": 1.3247,
4443
+ "step": 715
4444
+ },
4445
+ {
4446
+ "epoch": 1.69,
4447
+ "learning_rate": 0.00065,
4448
+ "loss": 1.1937,
4449
+ "step": 716
4450
+ },
4451
+ {
4452
+ "epoch": 1.69,
4453
+ "learning_rate": 0.00065,
4454
+ "loss": 1.1404,
4455
+ "step": 717
4456
+ },
4457
+ {
4458
+ "epoch": 1.7,
4459
+ "learning_rate": 0.00065,
4460
+ "loss": 0.8771,
4461
+ "step": 718
4462
+ },
4463
+ {
4464
+ "epoch": 1.7,
4465
+ "learning_rate": 0.00065,
4466
+ "loss": 1.2544,
4467
+ "step": 719
4468
+ },
4469
+ {
4470
+ "epoch": 1.7,
4471
+ "learning_rate": 0.00065,
4472
+ "loss": 1.3652,
4473
+ "step": 720
4474
+ },
4475
+ {
4476
+ "epoch": 1.7,
4477
+ "learning_rate": 0.00065,
4478
+ "loss": 1.2582,
4479
+ "step": 721
4480
+ },
4481
+ {
4482
+ "epoch": 1.71,
4483
+ "learning_rate": 0.00065,
4484
+ "loss": 1.0112,
4485
+ "step": 722
4486
+ },
4487
+ {
4488
+ "epoch": 1.71,
4489
+ "learning_rate": 0.00065,
4490
+ "loss": 1.1113,
4491
+ "step": 723
4492
+ },
4493
+ {
4494
+ "epoch": 1.71,
4495
+ "learning_rate": 0.00065,
4496
+ "loss": 1.23,
4497
+ "step": 724
4498
+ },
4499
+ {
4500
+ "epoch": 1.71,
4501
+ "learning_rate": 0.00065,
4502
+ "loss": 1.4347,
4503
+ "step": 725
4504
+ },
4505
+ {
4506
+ "epoch": 1.72,
4507
+ "learning_rate": 0.00065,
4508
+ "loss": 1.2039,
4509
+ "step": 726
4510
+ },
4511
+ {
4512
+ "epoch": 1.72,
4513
+ "learning_rate": 0.00065,
4514
+ "loss": 1.081,
4515
+ "step": 727
4516
+ },
4517
+ {
4518
+ "epoch": 1.72,
4519
+ "learning_rate": 0.00065,
4520
+ "loss": 1.1252,
4521
+ "step": 728
4522
+ },
4523
+ {
4524
+ "epoch": 1.72,
4525
+ "learning_rate": 0.00065,
4526
+ "loss": 0.9198,
4527
+ "step": 729
4528
+ },
4529
+ {
4530
+ "epoch": 1.73,
4531
+ "learning_rate": 0.00065,
4532
+ "loss": 1.3106,
4533
+ "step": 730
4534
+ },
4535
+ {
4536
+ "epoch": 1.73,
4537
+ "learning_rate": 0.00065,
4538
+ "loss": 1.3563,
4539
+ "step": 731
4540
+ },
4541
+ {
4542
+ "epoch": 1.73,
4543
+ "learning_rate": 0.00065,
4544
+ "loss": 1.0198,
4545
+ "step": 732
4546
+ },
4547
+ {
4548
+ "epoch": 1.73,
4549
+ "learning_rate": 0.00065,
4550
+ "loss": 1.2724,
4551
+ "step": 733
4552
+ },
4553
+ {
4554
+ "epoch": 1.74,
4555
+ "learning_rate": 0.00065,
4556
+ "loss": 1.292,
4557
+ "step": 734
4558
+ },
4559
+ {
4560
+ "epoch": 1.74,
4561
+ "learning_rate": 0.00065,
4562
+ "loss": 1.0309,
4563
+ "step": 735
4564
+ },
4565
+ {
4566
+ "epoch": 1.74,
4567
+ "learning_rate": 0.00065,
4568
+ "loss": 1.1085,
4569
+ "step": 736
4570
+ },
4571
+ {
4572
+ "epoch": 1.74,
4573
+ "learning_rate": 0.00065,
4574
+ "loss": 1.2547,
4575
+ "step": 737
4576
+ },
4577
+ {
4578
+ "epoch": 1.74,
4579
+ "learning_rate": 0.00065,
4580
+ "loss": 1.2698,
4581
+ "step": 738
4582
+ },
4583
+ {
4584
+ "epoch": 1.75,
4585
+ "learning_rate": 0.00065,
4586
+ "loss": 1.1547,
4587
+ "step": 739
4588
+ },
4589
+ {
4590
+ "epoch": 1.75,
4591
+ "learning_rate": 0.00065,
4592
+ "loss": 1.0792,
4593
+ "step": 740
4594
+ },
4595
+ {
4596
+ "epoch": 1.75,
4597
+ "learning_rate": 0.00065,
4598
+ "loss": 1.2426,
4599
+ "step": 741
4600
+ },
4601
+ {
4602
+ "epoch": 1.75,
4603
+ "learning_rate": 0.00065,
4604
+ "loss": 1.2593,
4605
+ "step": 742
4606
+ },
4607
+ {
4608
+ "epoch": 1.76,
4609
+ "learning_rate": 0.00065,
4610
+ "loss": 0.9767,
4611
+ "step": 743
4612
+ },
4613
+ {
4614
+ "epoch": 1.76,
4615
+ "learning_rate": 0.00065,
4616
+ "loss": 1.2165,
4617
+ "step": 744
4618
+ },
4619
+ {
4620
+ "epoch": 1.76,
4621
+ "learning_rate": 0.00065,
4622
+ "loss": 1.2162,
4623
+ "step": 745
4624
+ },
4625
+ {
4626
+ "epoch": 1.76,
4627
+ "learning_rate": 0.00065,
4628
+ "loss": 1.0064,
4629
+ "step": 746
4630
+ },
4631
+ {
4632
+ "epoch": 1.77,
4633
+ "learning_rate": 0.00065,
4634
+ "loss": 1.2363,
4635
+ "step": 747
4636
+ },
4637
+ {
4638
+ "epoch": 1.77,
4639
+ "learning_rate": 0.00065,
4640
+ "loss": 0.9385,
4641
+ "step": 748
4642
+ },
4643
+ {
4644
+ "epoch": 1.77,
4645
+ "learning_rate": 0.00065,
4646
+ "loss": 0.832,
4647
+ "step": 749
4648
+ },
4649
+ {
4650
+ "epoch": 1.77,
4651
+ "learning_rate": 0.00065,
4652
+ "loss": 1.4107,
4653
+ "step": 750
4654
+ },
4655
+ {
4656
+ "epoch": 1.78,
4657
+ "learning_rate": 0.00065,
4658
+ "loss": 1.2246,
4659
+ "step": 751
4660
+ },
4661
+ {
4662
+ "epoch": 1.78,
4663
+ "learning_rate": 0.00065,
4664
+ "loss": 1.3015,
4665
+ "step": 752
4666
+ },
4667
+ {
4668
+ "epoch": 1.78,
4669
+ "learning_rate": 0.00065,
4670
+ "loss": 1.2943,
4671
+ "step": 753
4672
+ },
4673
+ {
4674
+ "epoch": 1.78,
4675
+ "learning_rate": 0.00065,
4676
+ "loss": 1.1899,
4677
+ "step": 754
4678
+ },
4679
+ {
4680
+ "epoch": 1.79,
4681
+ "learning_rate": 0.00065,
4682
+ "loss": 1.3176,
4683
+ "step": 755
4684
+ },
4685
+ {
4686
+ "epoch": 1.79,
4687
+ "learning_rate": 0.00065,
4688
+ "loss": 1.2133,
4689
+ "step": 756
4690
+ },
4691
+ {
4692
+ "epoch": 1.79,
4693
+ "eval_loss": 1.590731143951416,
4694
+ "eval_runtime": 57.6066,
4695
+ "eval_samples_per_second": 8.68,
4696
+ "eval_steps_per_second": 4.34,
4697
+ "step": 756
4698
+ },
4699
+ {
4700
+ "epoch": 1.79,
4701
+ "learning_rate": 0.00065,
4702
+ "loss": 1.4054,
4703
+ "step": 757
4704
+ },
4705
+ {
4706
+ "epoch": 1.79,
4707
+ "learning_rate": 0.00065,
4708
+ "loss": 1.0306,
4709
+ "step": 758
4710
+ },
4711
+ {
4712
+ "epoch": 1.79,
4713
+ "learning_rate": 0.00065,
4714
+ "loss": 0.9219,
4715
+ "step": 759
4716
+ },
4717
+ {
4718
+ "epoch": 1.8,
4719
+ "learning_rate": 0.00065,
4720
+ "loss": 1.3537,
4721
+ "step": 760
4722
+ },
4723
+ {
4724
+ "epoch": 1.8,
4725
+ "learning_rate": 0.00065,
4726
+ "loss": 1.1529,
4727
+ "step": 761
4728
+ },
4729
+ {
4730
+ "epoch": 1.8,
4731
+ "learning_rate": 0.00065,
4732
+ "loss": 1.1553,
4733
+ "step": 762
4734
+ },
4735
+ {
4736
+ "epoch": 1.8,
4737
+ "learning_rate": 0.00065,
4738
+ "loss": 1.1097,
4739
+ "step": 763
4740
+ },
4741
+ {
4742
+ "epoch": 1.81,
4743
+ "learning_rate": 0.00065,
4744
+ "loss": 1.2209,
4745
+ "step": 764
4746
+ },
4747
+ {
4748
+ "epoch": 1.81,
4749
+ "learning_rate": 0.00065,
4750
+ "loss": 1.2093,
4751
+ "step": 765
4752
+ },
4753
+ {
4754
+ "epoch": 1.81,
4755
+ "learning_rate": 0.00065,
4756
+ "loss": 1.1674,
4757
+ "step": 766
4758
+ },
4759
+ {
4760
+ "epoch": 1.81,
4761
+ "learning_rate": 0.00065,
4762
+ "loss": 1.1438,
4763
+ "step": 767
4764
+ },
4765
+ {
4766
+ "epoch": 1.82,
4767
+ "learning_rate": 0.00065,
4768
+ "loss": 1.5192,
4769
+ "step": 768
4770
+ },
4771
+ {
4772
+ "epoch": 1.82,
4773
+ "learning_rate": 0.00065,
4774
+ "loss": 1.1563,
4775
+ "step": 769
4776
+ },
4777
+ {
4778
+ "epoch": 1.82,
4779
+ "learning_rate": 0.00065,
4780
+ "loss": 1.3319,
4781
+ "step": 770
4782
+ },
4783
+ {
4784
+ "epoch": 1.82,
4785
+ "learning_rate": 0.00065,
4786
+ "loss": 1.2713,
4787
+ "step": 771
4788
+ },
4789
+ {
4790
+ "epoch": 1.83,
4791
+ "learning_rate": 0.00065,
4792
+ "loss": 1.0709,
4793
+ "step": 772
4794
+ },
4795
+ {
4796
+ "epoch": 1.83,
4797
+ "learning_rate": 0.00065,
4798
+ "loss": 0.9308,
4799
+ "step": 773
4800
+ },
4801
+ {
4802
+ "epoch": 1.83,
4803
+ "learning_rate": 0.00065,
4804
+ "loss": 1.3031,
4805
+ "step": 774
4806
+ },
4807
+ {
4808
+ "epoch": 1.83,
4809
+ "learning_rate": 0.00065,
4810
+ "loss": 1.1558,
4811
+ "step": 775
4812
+ },
4813
+ {
4814
+ "epoch": 1.84,
4815
+ "learning_rate": 0.00065,
4816
+ "loss": 0.9799,
4817
+ "step": 776
4818
+ },
4819
+ {
4820
+ "epoch": 1.84,
4821
+ "learning_rate": 0.00065,
4822
+ "loss": 1.1577,
4823
+ "step": 777
4824
+ },
4825
+ {
4826
+ "epoch": 1.84,
4827
+ "learning_rate": 0.00065,
4828
+ "loss": 1.1936,
4829
+ "step": 778
4830
+ },
4831
+ {
4832
+ "epoch": 1.84,
4833
+ "learning_rate": 0.00065,
4834
+ "loss": 1.266,
4835
+ "step": 779
4836
+ },
4837
+ {
4838
+ "epoch": 1.84,
4839
+ "learning_rate": 0.00065,
4840
+ "loss": 1.1129,
4841
+ "step": 780
4842
+ },
4843
+ {
4844
+ "epoch": 1.85,
4845
+ "learning_rate": 0.00065,
4846
+ "loss": 1.1319,
4847
+ "step": 781
4848
+ },
4849
+ {
4850
+ "epoch": 1.85,
4851
+ "learning_rate": 0.00065,
4852
+ "loss": 1.134,
4853
+ "step": 782
4854
+ },
4855
+ {
4856
+ "epoch": 1.85,
4857
+ "learning_rate": 0.00065,
4858
+ "loss": 1.1684,
4859
+ "step": 783
4860
+ },
4861
+ {
4862
+ "epoch": 1.85,
4863
+ "learning_rate": 0.00065,
4864
+ "loss": 1.2268,
4865
+ "step": 784
4866
+ },
4867
+ {
4868
+ "epoch": 1.86,
4869
+ "learning_rate": 0.00065,
4870
+ "loss": 1.1524,
4871
+ "step": 785
4872
+ },
4873
+ {
4874
+ "epoch": 1.86,
4875
+ "learning_rate": 0.00065,
4876
+ "loss": 1.0566,
4877
+ "step": 786
4878
+ },
4879
+ {
4880
+ "epoch": 1.86,
4881
+ "learning_rate": 0.00065,
4882
+ "loss": 1.1185,
4883
+ "step": 787
4884
+ },
4885
+ {
4886
+ "epoch": 1.86,
4887
+ "learning_rate": 0.00065,
4888
+ "loss": 1.0199,
4889
+ "step": 788
4890
+ },
4891
+ {
4892
+ "epoch": 1.87,
4893
+ "learning_rate": 0.00065,
4894
+ "loss": 1.041,
4895
+ "step": 789
4896
+ },
4897
+ {
4898
+ "epoch": 1.87,
4899
+ "learning_rate": 0.00065,
4900
+ "loss": 1.2404,
4901
+ "step": 790
4902
+ },
4903
+ {
4904
+ "epoch": 1.87,
4905
+ "learning_rate": 0.00065,
4906
+ "loss": 1.2778,
4907
+ "step": 791
4908
+ },
4909
+ {
4910
+ "epoch": 1.87,
4911
+ "learning_rate": 0.00065,
4912
+ "loss": 1.1633,
4913
+ "step": 792
4914
+ },
4915
+ {
4916
+ "epoch": 1.88,
4917
+ "learning_rate": 0.00065,
4918
+ "loss": 1.181,
4919
+ "step": 793
4920
+ },
4921
+ {
4922
+ "epoch": 1.88,
4923
+ "learning_rate": 0.00065,
4924
+ "loss": 1.2332,
4925
+ "step": 794
4926
+ },
4927
+ {
4928
+ "epoch": 1.88,
4929
+ "learning_rate": 0.00065,
4930
+ "loss": 1.148,
4931
+ "step": 795
4932
+ },
4933
+ {
4934
+ "epoch": 1.88,
4935
+ "learning_rate": 0.00065,
4936
+ "loss": 1.2897,
4937
+ "step": 796
4938
+ },
4939
+ {
4940
+ "epoch": 1.89,
4941
+ "learning_rate": 0.00065,
4942
+ "loss": 1.358,
4943
+ "step": 797
4944
+ },
4945
+ {
4946
+ "epoch": 1.89,
4947
+ "learning_rate": 0.00065,
4948
+ "loss": 1.0327,
4949
+ "step": 798
4950
+ },
4951
+ {
4952
+ "epoch": 1.89,
4953
+ "eval_loss": 1.6087443828582764,
4954
+ "eval_runtime": 57.7758,
4955
+ "eval_samples_per_second": 8.654,
4956
+ "eval_steps_per_second": 4.327,
4957
+ "step": 798
4958
+ },
4959
+ {
4960
+ "epoch": 1.89,
4961
+ "learning_rate": 0.00065,
4962
+ "loss": 1.3078,
4963
+ "step": 799
4964
+ },
4965
+ {
4966
+ "epoch": 1.89,
4967
+ "learning_rate": 0.00065,
4968
+ "loss": 1.2684,
4969
+ "step": 800
4970
+ },
4971
+ {
4972
+ "epoch": 1.89,
4973
+ "learning_rate": 0.00065,
4974
+ "loss": 1.3746,
4975
+ "step": 801
4976
+ },
4977
+ {
4978
+ "epoch": 1.9,
4979
+ "learning_rate": 0.00065,
4980
+ "loss": 1.2452,
4981
+ "step": 802
4982
+ },
4983
+ {
4984
+ "epoch": 1.9,
4985
+ "learning_rate": 0.00065,
4986
+ "loss": 1.2579,
4987
+ "step": 803
4988
+ },
4989
+ {
4990
+ "epoch": 1.9,
4991
+ "learning_rate": 0.00065,
4992
+ "loss": 0.9371,
4993
+ "step": 804
4994
+ },
4995
+ {
4996
+ "epoch": 1.9,
4997
+ "learning_rate": 0.00065,
4998
+ "loss": 1.2245,
4999
+ "step": 805
5000
+ },
5001
+ {
5002
+ "epoch": 1.91,
5003
+ "learning_rate": 0.00065,
5004
+ "loss": 1.1344,
5005
+ "step": 806
5006
+ },
5007
+ {
5008
+ "epoch": 1.91,
5009
+ "learning_rate": 0.00065,
5010
+ "loss": 1.3045,
5011
+ "step": 807
5012
+ },
5013
+ {
5014
+ "epoch": 1.91,
5015
+ "learning_rate": 0.00065,
5016
+ "loss": 1.1151,
5017
+ "step": 808
5018
+ },
5019
+ {
5020
+ "epoch": 1.91,
5021
+ "learning_rate": 0.00065,
5022
+ "loss": 1.1183,
5023
+ "step": 809
5024
+ },
5025
+ {
5026
+ "epoch": 1.92,
5027
+ "learning_rate": 0.00065,
5028
+ "loss": 1.1539,
5029
+ "step": 810
5030
+ },
5031
+ {
5032
+ "epoch": 1.92,
5033
+ "learning_rate": 0.00065,
5034
+ "loss": 0.8803,
5035
+ "step": 811
5036
+ },
5037
+ {
5038
+ "epoch": 1.92,
5039
+ "learning_rate": 0.00065,
5040
+ "loss": 1.0764,
5041
+ "step": 812
5042
+ },
5043
+ {
5044
+ "epoch": 1.92,
5045
+ "learning_rate": 0.00065,
5046
+ "loss": 1.2668,
5047
+ "step": 813
5048
+ },
5049
+ {
5050
+ "epoch": 1.93,
5051
+ "learning_rate": 0.00065,
5052
+ "loss": 1.2089,
5053
+ "step": 814
5054
+ },
5055
+ {
5056
+ "epoch": 1.93,
5057
+ "learning_rate": 0.00065,
5058
+ "loss": 1.2211,
5059
+ "step": 815
5060
+ },
5061
+ {
5062
+ "epoch": 1.93,
5063
+ "learning_rate": 0.00065,
5064
+ "loss": 1.301,
5065
+ "step": 816
5066
+ },
5067
+ {
5068
+ "epoch": 1.93,
5069
+ "learning_rate": 0.00065,
5070
+ "loss": 1.0924,
5071
+ "step": 817
5072
+ },
5073
+ {
5074
+ "epoch": 1.94,
5075
+ "learning_rate": 0.00065,
5076
+ "loss": 1.1627,
5077
+ "step": 818
5078
+ },
5079
+ {
5080
+ "epoch": 1.94,
5081
+ "learning_rate": 0.00065,
5082
+ "loss": 1.318,
5083
+ "step": 819
5084
+ },
5085
+ {
5086
+ "epoch": 1.94,
5087
+ "learning_rate": 0.00065,
5088
+ "loss": 1.0976,
5089
+ "step": 820
5090
+ },
5091
+ {
5092
+ "epoch": 1.94,
5093
+ "learning_rate": 0.00065,
5094
+ "loss": 1.4353,
5095
+ "step": 821
5096
+ },
5097
+ {
5098
+ "epoch": 1.95,
5099
+ "learning_rate": 0.00065,
5100
+ "loss": 1.3045,
5101
+ "step": 822
5102
+ },
5103
+ {
5104
+ "epoch": 1.95,
5105
+ "learning_rate": 0.00065,
5106
+ "loss": 1.276,
5107
+ "step": 823
5108
+ },
5109
+ {
5110
+ "epoch": 1.95,
5111
+ "learning_rate": 0.00065,
5112
+ "loss": 1.0738,
5113
+ "step": 824
5114
+ },
5115
+ {
5116
+ "epoch": 1.95,
5117
+ "learning_rate": 0.00065,
5118
+ "loss": 1.0885,
5119
+ "step": 825
5120
+ },
5121
+ {
5122
+ "epoch": 1.95,
5123
+ "learning_rate": 0.00065,
5124
+ "loss": 1.1512,
5125
+ "step": 826
5126
+ },
5127
+ {
5128
+ "epoch": 1.96,
5129
+ "learning_rate": 0.00065,
5130
+ "loss": 1.2892,
5131
+ "step": 827
5132
+ },
5133
+ {
5134
+ "epoch": 1.96,
5135
+ "learning_rate": 0.00065,
5136
+ "loss": 1.195,
5137
+ "step": 828
5138
+ },
5139
+ {
5140
+ "epoch": 1.96,
5141
+ "learning_rate": 0.00065,
5142
+ "loss": 1.1476,
5143
+ "step": 829
5144
+ },
5145
+ {
5146
+ "epoch": 1.96,
5147
+ "learning_rate": 0.00065,
5148
+ "loss": 1.1692,
5149
+ "step": 830
5150
+ },
5151
+ {
5152
+ "epoch": 1.97,
5153
+ "learning_rate": 0.00065,
5154
+ "loss": 1.2677,
5155
+ "step": 831
5156
+ },
5157
+ {
5158
+ "epoch": 1.97,
5159
+ "learning_rate": 0.00065,
5160
+ "loss": 1.2011,
5161
+ "step": 832
5162
+ },
5163
+ {
5164
+ "epoch": 1.97,
5165
+ "learning_rate": 0.00065,
5166
+ "loss": 1.1611,
5167
+ "step": 833
5168
+ },
5169
+ {
5170
+ "epoch": 1.97,
5171
+ "learning_rate": 0.00065,
5172
+ "loss": 1.5293,
5173
+ "step": 834
5174
+ },
5175
+ {
5176
+ "epoch": 1.98,
5177
+ "learning_rate": 0.00065,
5178
+ "loss": 1.1689,
5179
+ "step": 835
5180
+ },
5181
+ {
5182
+ "epoch": 1.98,
5183
+ "learning_rate": 0.00065,
5184
+ "loss": 1.1902,
5185
+ "step": 836
5186
+ },
5187
+ {
5188
+ "epoch": 1.98,
5189
+ "learning_rate": 0.00065,
5190
+ "loss": 1.0793,
5191
+ "step": 837
5192
+ },
5193
+ {
5194
+ "epoch": 1.98,
5195
+ "learning_rate": 0.00065,
5196
+ "loss": 1.2446,
5197
+ "step": 838
5198
+ }
5199
+ ],
5200
+ "logging_steps": 1,
5201
+ "max_steps": 838,
5202
+ "num_train_epochs": 2,
5203
+ "save_steps": 500,
5204
+ "total_flos": 5.706134946054144e+17,
5205
+ "trial_name": null,
5206
+ "trial_params": null
5207
+ }
checkpoint-838/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f24abc70e9c40aaecc2a1a7a785166489fdb1864d287910b01cbf2605591d57
3
+ size 4475
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./TheBloke_Llama-2-13B-fp16",
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": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
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": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.34.1",
38
+ "use_cache": false,
39
+ "vocab_size": 32000
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true,
42
+ "use_fast": true
43
+ }