Hugging Face's logo

joseagmz
/
lora_test

PEFT
TensorBoard
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Metrics Community
joseagmz commited on
Commit
6f68cb5
·
verified ·
1 Parent(s): 0674514

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. README.md +142 -0
  2. adapter_config.json +32 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-167/README.md +204 -0
  5. checkpoint-167/adapter_config.json +32 -0
  6. checkpoint-167/adapter_model.safetensors +3 -0
  7. checkpoint-167/optimizer.pt +3 -0
  8. checkpoint-167/rng_state.pth +3 -0
  9. checkpoint-167/scheduler.pt +3 -0
  10. checkpoint-167/trainer_state.json +1055 -0
  11. checkpoint-167/training_args.bin +3 -0
  12. checkpoint-334/README.md +204 -0
  13. checkpoint-334/adapter_config.json +32 -0
  14. checkpoint-334/adapter_model.safetensors +3 -0
  15. checkpoint-334/optimizer.pt +3 -0
  16. checkpoint-334/rng_state.pth +3 -0
  17. checkpoint-334/scheduler.pt +3 -0
  18. checkpoint-334/trainer_state.json +2089 -0
  19. checkpoint-334/training_args.bin +3 -0
  20. checkpoint-501/README.md +204 -0
  21. checkpoint-501/adapter_config.json +32 -0
  22. checkpoint-501/adapter_model.safetensors +3 -0
  23. checkpoint-501/optimizer.pt +3 -0
  24. checkpoint-501/rng_state.pth +3 -0
  25. checkpoint-501/scheduler.pt +3 -0
  26. checkpoint-501/trainer_state.json +3123 -0
  27. checkpoint-501/training_args.bin +3 -0
  28. checkpoint-668/README.md +204 -0
  29. checkpoint-668/adapter_config.json +32 -0
  30. checkpoint-668/adapter_model.safetensors +3 -0
  31. checkpoint-668/optimizer.pt +3 -0
  32. checkpoint-668/rng_state.pth +3 -0
  33. checkpoint-668/scheduler.pt +3 -0
  34. checkpoint-668/trainer_state.json +4157 -0
  35. checkpoint-668/training_args.bin +3 -0
  36. config.json +42 -0
  37. runs/Feb20_20-18-56_fe14e8fd7da0/events.out.tfevents.1708460336.fe14e8fd7da0.2298.0 +3 -0
  38. special_tokens_map.json +24 -0
  39. tokenizer.model +3 -0
  40. tokenizer_config.json +44 -0
README.md ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
7
+ model-index:
8
+ - name: lora_test
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ adapter: lora
21
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
22
+ bf16: auto
23
+ dataset_prepared_path: null
24
+ datasets:
25
+ - path: joseagmz/MedQnA_version3
26
+ type: context_qa.load_v2
27
+ debug: null
28
+ deepspeed: null
29
+ early_stopping_patience: null
30
+ evals_per_epoch: 4
31
+ flash_attention: true
32
+ fp16: null
33
+ fsdp: null
34
+ fsdp_config: null
35
+ gradient_accumulation_steps: 4
36
+ gradient_checkpointing: true
37
+ group_by_length: false
38
+ is_llama_derived_model: true
39
+ learning_rate: 0.0002
40
+ load_in_4bit: false
41
+ load_in_8bit: true
42
+ local_rank: null
43
+ logging_steps: 1
44
+ lora_alpha: 16
45
+ lora_dropout: 0.05
46
+ lora_fan_in_fan_out: null
47
+ lora_model_dir: null
48
+ lora_r: 32
49
+ lora_target_linear: true
50
+ lr_scheduler: cosine
51
+ micro_batch_size: 2
52
+ model_type: LlamaForCausalLM
53
+ num_epochs: 4
54
+ optimizer: adamw_bnb_8bit
55
+ output_dir: ./lora_test
56
+ pad_to_sequence_len: true
57
+ resume_from_checkpoint: null
58
+ sample_packing: true
59
+ saves_per_epoch: 1
60
+ sequence_len: 4096
61
+ special_tokens: null
62
+ strict: false
63
+ tf32: false
64
+ tokenizer_type: LlamaTokenizer
65
+ train_on_inputs: false
66
+ val_set_size: 0.05
67
+ wandb_entity: null
68
+ wandb_log_model: null
69
+ wandb_name: null
70
+ wandb_project: null
71
+ wandb_watch: null
72
+ warmup_steps: 10
73
+ weight_decay: 0.0
74
+ xformers_attention: null
75
+
76
+ ```
77
+
78
+ </details><br>
79
+
80
+ # lora_test
81
+
82
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
83
+ It achieves the following results on the evaluation set:
84
+ - Loss: 0.7337
85
+
86
+ ## Model description
87
+
88
+ More information needed
89
+
90
+ ## Intended uses & limitations
91
+
92
+ More information needed
93
+
94
+ ## Training and evaluation data
95
+
96
+ More information needed
97
+
98
+ ## Training procedure
99
+
100
+ ### Training hyperparameters
101
+
102
+ The following hyperparameters were used during training:
103
+ - learning_rate: 0.0002
104
+ - train_batch_size: 2
105
+ - eval_batch_size: 2
106
+ - seed: 42
107
+ - gradient_accumulation_steps: 4
108
+ - total_train_batch_size: 8
109
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
110
+ - lr_scheduler_type: cosine
111
+ - lr_scheduler_warmup_steps: 10
112
+ - num_epochs: 4
113
+
114
+ ### Training results
115
+
116
+ | Training Loss | Epoch | Step | Validation Loss |
117
+ |:-------------:|:-----:|:----:|:---------------:|
118
+ | 1.6541 | 0.01 | 1 | 1.7634 |
119
+ | 1.2512 | 0.25 | 42 | 0.8978 |
120
+ | 1.1008 | 0.5 | 84 | 0.8307 |
121
+ | 1.0685 | 0.75 | 126 | 0.8026 |
122
+ | 1.1573 | 1.0 | 168 | 0.7850 |
123
+ | 0.9346 | 1.24 | 210 | 0.7729 |
124
+ | 1.0299 | 1.49 | 252 | 0.7612 |
125
+ | 1.0057 | 1.74 | 294 | 0.7544 |
126
+ | 0.976 | 1.99 | 336 | 0.7478 |
127
+ | 1.0765 | 2.22 | 378 | 0.7439 |
128
+ | 0.8845 | 2.47 | 420 | 0.7409 |
129
+ | 1.0198 | 2.73 | 462 | 0.7379 |
130
+ | 0.9712 | 2.98 | 504 | 0.7352 |
131
+ | 0.9069 | 3.21 | 546 | 0.7350 |
132
+ | 0.8973 | 3.46 | 588 | 0.7342 |
133
+ | 0.9359 | 3.71 | 630 | 0.7337 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - PEFT 0.8.2
139
+ - Transformers 4.38.0.dev0
140
+ - Pytorch 2.1.2+cu121
141
+ - Datasets 2.17.1
142
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccfa355153bb73c5aae5e5962deab7aece4ae0b256b98247734fc844110bceb0
3
+ size 101036698
checkpoint-167/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-167/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-167/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a089b36264986e7c4cffefb9dbbefb6ce6a61e10bcda3b31df6a79e5b55ae874
3
+ size 100966336
checkpoint-167/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647b7b9aa6ba079979f1cbfec8dfa2d5691af150b56fe9c273382048e9ad976a
3
+ size 50916644
checkpoint-167/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ac04053cc9c3e380f5c0678a95ad3871057dd04482a495d1d3bc19e0071ea5
3
+ size 14244
checkpoint-167/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f071796420e3d77815a5b2f365efdcfa176141d7248b3599faa5235f54eeac
3
+ size 1064
checkpoint-167/trainer_state.json ADDED
@@ -0,0 +1,1055 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9970149253731343,
5
+ "eval_steps": 42,
6
+ "global_step": 167,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.6541,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 1.7634071111679077,
20
+ "eval_runtime": 14.5059,
21
+ "eval_samples_per_second": 56.46,
22
+ "eval_steps_per_second": 28.264,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.6887,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.828,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.589,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.927,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.6362,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8546,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.5843,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.5592,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.5539,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.0001999988602302209,
82
+ "loss": 1.4449,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0001999954409468652,
88
+ "loss": 1.8818,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.0001999897422278767,
94
+ "loss": 1.6656,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.08,
99
+ "learning_rate": 0.00019998176420316002,
100
+ "loss": 1.4607,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0001999715070545774,
106
+ "loss": 1.4013,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00019995897101594454,
112
+ "loss": 1.5258,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.1,
117
+ "learning_rate": 0.00019994415637302547,
118
+ "loss": 1.404,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.00019992706346352577,
124
+ "loss": 1.3919,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.11,
129
+ "learning_rate": 0.00019990769267708516,
130
+ "loss": 1.355,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.00019988604445526827,
136
+ "loss": 1.3763,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.000199862119291555,
142
+ "loss": 1.3314,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.13,
147
+ "learning_rate": 0.00019983591773132882,
148
+ "loss": 1.4246,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.00019980744037186469,
154
+ "loss": 1.5723,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.14,
159
+ "learning_rate": 0.00019977668786231534,
160
+ "loss": 1.2536,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.15,
165
+ "learning_rate": 0.0001997436609036963,
166
+ "loss": 1.3087,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.0001997083602488702,
172
+ "loss": 1.2783,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.16,
177
+ "learning_rate": 0.00019967078670252945,
178
+ "loss": 1.2792,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00019963094112117785,
184
+ "loss": 1.2476,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.17,
189
+ "learning_rate": 0.00019958882441311126,
190
+ "loss": 1.265,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.18,
195
+ "learning_rate": 0.00019954443753839667,
196
+ "loss": 1.0884,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00019949778150885042,
202
+ "loss": 1.3294,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.19,
207
+ "learning_rate": 0.00019944885738801518,
208
+ "loss": 1.3434,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.2,
213
+ "learning_rate": 0.00019939766629113566,
214
+ "loss": 1.1457,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.2,
219
+ "learning_rate": 0.00019934420938513313,
220
+ "loss": 1.2138,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.21,
225
+ "learning_rate": 0.00019928848788857887,
226
+ "loss": 1.2118,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.21,
231
+ "learning_rate": 0.00019923050307166655,
232
+ "loss": 1.1426,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.22,
237
+ "learning_rate": 0.00019917025625618292,
238
+ "loss": 1.6279,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.23,
243
+ "learning_rate": 0.000199107748815478,
244
+ "loss": 1.5021,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.23,
249
+ "learning_rate": 0.00019904298217443366,
250
+ "loss": 1.3728,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.24,
255
+ "learning_rate": 0.00019897595780943102,
256
+ "loss": 1.2034,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.24,
261
+ "learning_rate": 0.00019890667724831707,
262
+ "loss": 1.3718,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.25,
267
+ "learning_rate": 0.00019883514207036956,
268
+ "loss": 1.2512,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.25,
273
+ "eval_loss": 0.8978323936462402,
274
+ "eval_runtime": 14.6352,
275
+ "eval_samples_per_second": 55.961,
276
+ "eval_steps_per_second": 28.015,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.26,
281
+ "learning_rate": 0.00019876135390626122,
282
+ "loss": 1.1787,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.26,
287
+ "learning_rate": 0.0001986853144380224,
288
+ "loss": 1.1917,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.27,
293
+ "learning_rate": 0.00019860702539900287,
294
+ "loss": 1.1933,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.27,
299
+ "learning_rate": 0.00019852648857383222,
300
+ "loss": 1.1922,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.28,
305
+ "learning_rate": 0.00019844370579837927,
306
+ "loss": 1.3017,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.29,
311
+ "learning_rate": 0.00019835867895971014,
312
+ "loss": 1.1193,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.29,
317
+ "learning_rate": 0.0001982714099960452,
318
+ "loss": 1.1572,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.3,
323
+ "learning_rate": 0.00019818190089671508,
324
+ "loss": 1.3277,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.3,
329
+ "learning_rate": 0.00019809015370211502,
330
+ "loss": 1.0658,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.31,
335
+ "learning_rate": 0.0001979961705036587,
336
+ "loss": 1.1656,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.32,
341
+ "learning_rate": 0.00019789995344373024,
342
+ "loss": 1.4204,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.32,
347
+ "learning_rate": 0.00019780150471563558,
348
+ "loss": 1.1551,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.33,
353
+ "learning_rate": 0.0001977008265635525,
354
+ "loss": 1.0993,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.33,
359
+ "learning_rate": 0.00019759792128247922,
360
+ "loss": 1.1311,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.34,
365
+ "learning_rate": 0.00019749279121818235,
366
+ "loss": 1.2163,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.35,
371
+ "learning_rate": 0.00019738543876714334,
372
+ "loss": 1.3178,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.35,
377
+ "learning_rate": 0.00019727586637650373,
378
+ "loss": 1.3744,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.36,
383
+ "learning_rate": 0.00019716407654400952,
384
+ "loss": 1.1413,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.36,
389
+ "learning_rate": 0.00019705007181795416,
390
+ "loss": 1.0372,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.37,
395
+ "learning_rate": 0.00019693385479712048,
396
+ "loss": 1.1601,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.38,
401
+ "learning_rate": 0.00019681542813072145,
402
+ "loss": 1.0976,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.38,
407
+ "learning_rate": 0.00019669479451833976,
408
+ "loss": 1.1584,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.39,
413
+ "learning_rate": 0.00019657195670986637,
414
+ "loss": 1.0962,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.39,
419
+ "learning_rate": 0.00019644691750543767,
420
+ "loss": 1.1044,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.4,
425
+ "learning_rate": 0.0001963196797553718,
426
+ "loss": 1.2431,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.41,
431
+ "learning_rate": 0.00019619024636010363,
432
+ "loss": 1.1651,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.41,
437
+ "learning_rate": 0.00019605862027011856,
438
+ "loss": 1.0513,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.42,
443
+ "learning_rate": 0.00019592480448588542,
444
+ "loss": 1.0175,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.42,
449
+ "learning_rate": 0.00019578880205778793,
450
+ "loss": 1.1306,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.43,
455
+ "learning_rate": 0.00019565061608605526,
456
+ "loss": 1.3121,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.44,
461
+ "learning_rate": 0.00019551024972069126,
462
+ "loss": 1.266,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.44,
467
+ "learning_rate": 0.00019536770616140276,
468
+ "loss": 1.1099,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.45,
473
+ "learning_rate": 0.0001952229886575266,
474
+ "loss": 1.1012,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.45,
479
+ "learning_rate": 0.00019507610050795558,
480
+ "loss": 1.1272,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.46,
485
+ "learning_rate": 0.0001949270450610631,
486
+ "loss": 1.2016,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.47,
491
+ "learning_rate": 0.00019477582571462705,
492
+ "loss": 1.1746,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.47,
497
+ "learning_rate": 0.00019462244591575222,
498
+ "loss": 1.1349,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.48,
503
+ "learning_rate": 0.0001944669091607919,
504
+ "loss": 1.4311,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.48,
509
+ "learning_rate": 0.00019430921899526787,
510
+ "loss": 1.1033,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.49,
515
+ "learning_rate": 0.00019414937901378982,
516
+ "loss": 1.2491,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.5,
521
+ "learning_rate": 0.0001939873928599734,
522
+ "loss": 1.1044,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.5,
527
+ "learning_rate": 0.00019382326422635705,
528
+ "loss": 1.1008,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.5,
533
+ "eval_loss": 0.8307072520256042,
534
+ "eval_runtime": 14.6668,
535
+ "eval_samples_per_second": 55.841,
536
+ "eval_steps_per_second": 27.954,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 0.0001936569968543179,
542
+ "loss": 1.2317,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 0.00019348859453398646,
548
+ "loss": 1.2317,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 0.00019331806110416027,
554
+ "loss": 1.0989,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.53,
559
+ "learning_rate": 0.00019314540045221626,
560
+ "loss": 1.0466,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 0.00019297061651402236,
566
+ "loss": 1.0798,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 0.0001927937132738476,
572
+ "loss": 1.1175,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 0.0001926146947642712,
578
+ "loss": 1.1292,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 0.000192433565066091,
584
+ "loss": 1.0464,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.56,
589
+ "learning_rate": 0.00019225032830823011,
590
+ "loss": 1.1549,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 0.00019206498866764288,
596
+ "loss": 1.1129,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.57,
601
+ "learning_rate": 0.00019187755036921978,
602
+ "loss": 0.9965,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 0.0001916880176856909,
608
+ "loss": 1.0767,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 0.0001914963949375288,
614
+ "loss": 1.1546,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "learning_rate": 0.0001913026864928498,
620
+ "loss": 0.9627,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 0.00019110689676731454,
626
+ "loss": 1.0039,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.6,
631
+ "learning_rate": 0.00019090903022402729,
632
+ "loss": 1.066,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 0.00019070909137343408,
638
+ "loss": 1.0654,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.61,
643
+ "learning_rate": 0.00019050708477322018,
644
+ "loss": 1.3323,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 0.00019030301502820596,
650
+ "loss": 1.1247,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.62,
655
+ "learning_rate": 0.0001900968867902419,
656
+ "loss": 1.0261,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.63,
661
+ "learning_rate": 0.00018988870475810282,
662
+ "loss": 1.0935,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 0.00018967847367738048,
668
+ "loss": 1.1043,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.64,
673
+ "learning_rate": 0.00018946619834037546,
674
+ "loss": 1.1982,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 0.00018925188358598813,
680
+ "loss": 1.0445,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.65,
685
+ "learning_rate": 0.00018903553429960802,
686
+ "loss": 1.086,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.66,
691
+ "learning_rate": 0.00018881715541300276,
692
+ "loss": 1.1509,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.66,
697
+ "learning_rate": 0.00018859675190420537,
698
+ "loss": 1.1473,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.67,
703
+ "learning_rate": 0.00018837432879740114,
704
+ "loss": 1.1677,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 0.0001881498911628127,
710
+ "loss": 1.006,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.68,
715
+ "learning_rate": 0.00018792344411658468,
716
+ "loss": 1.0503,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.69,
721
+ "learning_rate": 0.00018769499282066717,
722
+ "loss": 1.163,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.69,
727
+ "learning_rate": 0.00018746454248269777,
728
+ "loss": 1.1443,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "learning_rate": 0.0001872320983558831,
734
+ "loss": 0.9785,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.7,
739
+ "learning_rate": 0.000186997665738879,
740
+ "loss": 1.0605,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.71,
745
+ "learning_rate": 0.0001867612499756697,
746
+ "loss": 1.0203,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.72,
751
+ "learning_rate": 0.00018652285645544603,
752
+ "loss": 1.146,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.72,
757
+ "learning_rate": 0.00018628249061248262,
758
+ "loss": 1.12,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.73,
763
+ "learning_rate": 0.00018604015792601396,
764
+ "loss": 1.1499,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.73,
769
+ "learning_rate": 0.00018579586392010943,
770
+ "loss": 1.1273,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.74,
775
+ "learning_rate": 0.0001855496141635476,
776
+ "loss": 1.0404,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.75,
781
+ "learning_rate": 0.00018530141426968902,
782
+ "loss": 1.1066,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.75,
787
+ "learning_rate": 0.0001850512698963485,
788
+ "loss": 1.0685,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "eval_loss": 0.8026405572891235,
794
+ "eval_runtime": 14.5968,
795
+ "eval_samples_per_second": 56.108,
796
+ "eval_steps_per_second": 28.088,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.76,
801
+ "learning_rate": 0.000184799186745666,
802
+ "loss": 1.0494,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.76,
807
+ "learning_rate": 0.00018454517056397661,
808
+ "loss": 1.1905,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.77,
813
+ "learning_rate": 0.0001842892271416797,
814
+ "loss": 1.2034,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.78,
819
+ "learning_rate": 0.00018403136231310684,
820
+ "loss": 1.2088,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.78,
825
+ "learning_rate": 0.00018377158195638876,
826
+ "loss": 0.9303,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.79,
831
+ "learning_rate": 0.00018350989199332154,
832
+ "loss": 1.1574,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.79,
837
+ "learning_rate": 0.00018324629838923132,
838
+ "loss": 1.1673,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.8,
843
+ "learning_rate": 0.00018298080715283858,
844
+ "loss": 1.1204,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.81,
849
+ "learning_rate": 0.00018271342433612113,
850
+ "loss": 1.0752,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.81,
855
+ "learning_rate": 0.00018244415603417603,
856
+ "loss": 1.0121,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.82,
861
+ "learning_rate": 0.00018217300838508073,
862
+ "loss": 1.0975,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.82,
867
+ "learning_rate": 0.00018189998756975318,
868
+ "loss": 0.9982,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.83,
873
+ "learning_rate": 0.00018162509981181084,
874
+ "loss": 1.1922,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.84,
879
+ "learning_rate": 0.0001813483513774289,
880
+ "loss": 0.9532,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.84,
885
+ "learning_rate": 0.00018106974857519736,
886
+ "loss": 1.0813,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.85,
891
+ "learning_rate": 0.0001807892977559774,
892
+ "loss": 0.9656,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.85,
897
+ "learning_rate": 0.0001805070053127563,
898
+ "loss": 1.1161,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.86,
903
+ "learning_rate": 0.00018022287768050202,
904
+ "loss": 1.0143,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.87,
909
+ "learning_rate": 0.0001799369213360163,
910
+ "loss": 1.1242,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.87,
915
+ "learning_rate": 0.00017964914279778715,
916
+ "loss": 1.0747,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.88,
921
+ "learning_rate": 0.00017935954862584018,
922
+ "loss": 1.1551,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.88,
927
+ "learning_rate": 0.0001790681454215891,
928
+ "loss": 0.9538,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.89,
933
+ "learning_rate": 0.00017877493982768527,
934
+ "loss": 1.0621,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.9,
939
+ "learning_rate": 0.0001784799385278661,
940
+ "loss": 1.0229,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.9,
945
+ "learning_rate": 0.000178183148246803,
946
+ "loss": 0.9991,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.91,
951
+ "learning_rate": 0.00017788457574994778,
952
+ "loss": 1.0045,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.91,
957
+ "learning_rate": 0.00017758422784337863,
958
+ "loss": 1.0675,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.92,
963
+ "learning_rate": 0.00017728211137364489,
964
+ "loss": 0.962,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.93,
969
+ "learning_rate": 0.000176978233227611,
970
+ "loss": 1.0145,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.93,
975
+ "learning_rate": 0.00017667260033229953,
976
+ "loss": 0.9576,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.94,
981
+ "learning_rate": 0.00017636521965473323,
982
+ "loss": 1.0692,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.94,
987
+ "learning_rate": 0.00017605609820177617,
988
+ "loss": 1.2074,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.95,
993
+ "learning_rate": 0.00017574524301997423,
994
+ "loss": 1.1489,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.96,
999
+ "learning_rate": 0.00017543266119539422,
1000
+ "loss": 0.9962,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.96,
1005
+ "learning_rate": 0.00017511835985346253,
1006
+ "loss": 0.8922,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.97,
1011
+ "learning_rate": 0.00017480234615880247,
1012
+ "loss": 0.9248,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.97,
1017
+ "learning_rate": 0.0001744846273150713,
1018
+ "loss": 1.1621,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.98,
1023
+ "learning_rate": 0.00017416521056479577,
1024
+ "loss": 1.0516,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.99,
1029
+ "learning_rate": 0.00017384410318920697,
1030
+ "loss": 1.0086,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.99,
1035
+ "learning_rate": 0.00017352131250807467,
1036
+ "loss": 1.0909,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 1.0,
1041
+ "learning_rate": 0.00017319684587954002,
1042
+ "loss": 1.1085,
1043
+ "step": 167
1044
+ }
1045
+ ],
1046
+ "logging_steps": 1,
1047
+ "max_steps": 668,
1048
+ "num_input_tokens_seen": 0,
1049
+ "num_train_epochs": 4,
1050
+ "save_steps": 167,
1051
+ "total_flos": 3.4795134369398784e+16,
1052
+ "train_batch_size": 2,
1053
+ "trial_name": null,
1054
+ "trial_params": null
1055
+ }
checkpoint-167/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14298be73cbe854ab00522590054d32e49c4c47f917719c135f6380025fd0
3
+ size 5368
checkpoint-334/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-334/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-334/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aec7c623bf951705bcc869e233aaf496063e9161a5bfc517ff955d1c216ff51
3
+ size 100966336
checkpoint-334/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bd940a0d404306146881508a787f018b83fb8e68c19060218ab3a793b7e0a0
3
+ size 50916964
checkpoint-334/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f54e7b832d1ec6ef6a6260ca8024f01e31c271b7a1cb708f849b7cc12312d7
3
+ size 14244
checkpoint-334/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa6476cd8edede65f4a952c1bc61b04d61a580f367295c7a6bc8ce759da2b91
3
+ size 1064
checkpoint-334/trainer_state.json ADDED
@@ -0,0 +1,2089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9776119402985075,
5
+ "eval_steps": 42,
6
+ "global_step": 334,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.6541,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 1.7634071111679077,
20
+ "eval_runtime": 14.5059,
21
+ "eval_samples_per_second": 56.46,
22
+ "eval_steps_per_second": 28.264,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.6887,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.828,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.589,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.927,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.6362,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8546,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.5843,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.5592,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.5539,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.0001999988602302209,
82
+ "loss": 1.4449,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0001999954409468652,
88
+ "loss": 1.8818,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.0001999897422278767,
94
+ "loss": 1.6656,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.08,
99
+ "learning_rate": 0.00019998176420316002,
100
+ "loss": 1.4607,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0001999715070545774,
106
+ "loss": 1.4013,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00019995897101594454,
112
+ "loss": 1.5258,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.1,
117
+ "learning_rate": 0.00019994415637302547,
118
+ "loss": 1.404,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.00019992706346352577,
124
+ "loss": 1.3919,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.11,
129
+ "learning_rate": 0.00019990769267708516,
130
+ "loss": 1.355,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.00019988604445526827,
136
+ "loss": 1.3763,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.000199862119291555,
142
+ "loss": 1.3314,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.13,
147
+ "learning_rate": 0.00019983591773132882,
148
+ "loss": 1.4246,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.00019980744037186469,
154
+ "loss": 1.5723,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.14,
159
+ "learning_rate": 0.00019977668786231534,
160
+ "loss": 1.2536,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.15,
165
+ "learning_rate": 0.0001997436609036963,
166
+ "loss": 1.3087,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.0001997083602488702,
172
+ "loss": 1.2783,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.16,
177
+ "learning_rate": 0.00019967078670252945,
178
+ "loss": 1.2792,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00019963094112117785,
184
+ "loss": 1.2476,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.17,
189
+ "learning_rate": 0.00019958882441311126,
190
+ "loss": 1.265,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.18,
195
+ "learning_rate": 0.00019954443753839667,
196
+ "loss": 1.0884,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00019949778150885042,
202
+ "loss": 1.3294,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.19,
207
+ "learning_rate": 0.00019944885738801518,
208
+ "loss": 1.3434,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.2,
213
+ "learning_rate": 0.00019939766629113566,
214
+ "loss": 1.1457,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.2,
219
+ "learning_rate": 0.00019934420938513313,
220
+ "loss": 1.2138,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.21,
225
+ "learning_rate": 0.00019928848788857887,
226
+ "loss": 1.2118,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.21,
231
+ "learning_rate": 0.00019923050307166655,
232
+ "loss": 1.1426,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.22,
237
+ "learning_rate": 0.00019917025625618292,
238
+ "loss": 1.6279,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.23,
243
+ "learning_rate": 0.000199107748815478,
244
+ "loss": 1.5021,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.23,
249
+ "learning_rate": 0.00019904298217443366,
250
+ "loss": 1.3728,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.24,
255
+ "learning_rate": 0.00019897595780943102,
256
+ "loss": 1.2034,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.24,
261
+ "learning_rate": 0.00019890667724831707,
262
+ "loss": 1.3718,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.25,
267
+ "learning_rate": 0.00019883514207036956,
268
+ "loss": 1.2512,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.25,
273
+ "eval_loss": 0.8978323936462402,
274
+ "eval_runtime": 14.6352,
275
+ "eval_samples_per_second": 55.961,
276
+ "eval_steps_per_second": 28.015,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.26,
281
+ "learning_rate": 0.00019876135390626122,
282
+ "loss": 1.1787,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.26,
287
+ "learning_rate": 0.0001986853144380224,
288
+ "loss": 1.1917,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.27,
293
+ "learning_rate": 0.00019860702539900287,
294
+ "loss": 1.1933,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.27,
299
+ "learning_rate": 0.00019852648857383222,
300
+ "loss": 1.1922,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.28,
305
+ "learning_rate": 0.00019844370579837927,
306
+ "loss": 1.3017,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.29,
311
+ "learning_rate": 0.00019835867895971014,
312
+ "loss": 1.1193,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.29,
317
+ "learning_rate": 0.0001982714099960452,
318
+ "loss": 1.1572,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.3,
323
+ "learning_rate": 0.00019818190089671508,
324
+ "loss": 1.3277,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.3,
329
+ "learning_rate": 0.00019809015370211502,
330
+ "loss": 1.0658,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.31,
335
+ "learning_rate": 0.0001979961705036587,
336
+ "loss": 1.1656,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.32,
341
+ "learning_rate": 0.00019789995344373024,
342
+ "loss": 1.4204,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.32,
347
+ "learning_rate": 0.00019780150471563558,
348
+ "loss": 1.1551,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.33,
353
+ "learning_rate": 0.0001977008265635525,
354
+ "loss": 1.0993,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.33,
359
+ "learning_rate": 0.00019759792128247922,
360
+ "loss": 1.1311,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.34,
365
+ "learning_rate": 0.00019749279121818235,
366
+ "loss": 1.2163,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.35,
371
+ "learning_rate": 0.00019738543876714334,
372
+ "loss": 1.3178,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.35,
377
+ "learning_rate": 0.00019727586637650373,
378
+ "loss": 1.3744,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.36,
383
+ "learning_rate": 0.00019716407654400952,
384
+ "loss": 1.1413,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.36,
389
+ "learning_rate": 0.00019705007181795416,
390
+ "loss": 1.0372,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.37,
395
+ "learning_rate": 0.00019693385479712048,
396
+ "loss": 1.1601,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.38,
401
+ "learning_rate": 0.00019681542813072145,
402
+ "loss": 1.0976,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.38,
407
+ "learning_rate": 0.00019669479451833976,
408
+ "loss": 1.1584,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.39,
413
+ "learning_rate": 0.00019657195670986637,
414
+ "loss": 1.0962,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.39,
419
+ "learning_rate": 0.00019644691750543767,
420
+ "loss": 1.1044,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.4,
425
+ "learning_rate": 0.0001963196797553718,
426
+ "loss": 1.2431,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.41,
431
+ "learning_rate": 0.00019619024636010363,
432
+ "loss": 1.1651,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.41,
437
+ "learning_rate": 0.00019605862027011856,
438
+ "loss": 1.0513,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.42,
443
+ "learning_rate": 0.00019592480448588542,
444
+ "loss": 1.0175,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.42,
449
+ "learning_rate": 0.00019578880205778793,
450
+ "loss": 1.1306,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.43,
455
+ "learning_rate": 0.00019565061608605526,
456
+ "loss": 1.3121,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.44,
461
+ "learning_rate": 0.00019551024972069126,
462
+ "loss": 1.266,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.44,
467
+ "learning_rate": 0.00019536770616140276,
468
+ "loss": 1.1099,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.45,
473
+ "learning_rate": 0.0001952229886575266,
474
+ "loss": 1.1012,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.45,
479
+ "learning_rate": 0.00019507610050795558,
480
+ "loss": 1.1272,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.46,
485
+ "learning_rate": 0.0001949270450610631,
486
+ "loss": 1.2016,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.47,
491
+ "learning_rate": 0.00019477582571462705,
492
+ "loss": 1.1746,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.47,
497
+ "learning_rate": 0.00019462244591575222,
498
+ "loss": 1.1349,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.48,
503
+ "learning_rate": 0.0001944669091607919,
504
+ "loss": 1.4311,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.48,
509
+ "learning_rate": 0.00019430921899526787,
510
+ "loss": 1.1033,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.49,
515
+ "learning_rate": 0.00019414937901378982,
516
+ "loss": 1.2491,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.5,
521
+ "learning_rate": 0.0001939873928599734,
522
+ "loss": 1.1044,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.5,
527
+ "learning_rate": 0.00019382326422635705,
528
+ "loss": 1.1008,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.5,
533
+ "eval_loss": 0.8307072520256042,
534
+ "eval_runtime": 14.6668,
535
+ "eval_samples_per_second": 55.841,
536
+ "eval_steps_per_second": 27.954,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 0.0001936569968543179,
542
+ "loss": 1.2317,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 0.00019348859453398646,
548
+ "loss": 1.2317,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 0.00019331806110416027,
554
+ "loss": 1.0989,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.53,
559
+ "learning_rate": 0.00019314540045221626,
560
+ "loss": 1.0466,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 0.00019297061651402236,
566
+ "loss": 1.0798,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 0.0001927937132738476,
572
+ "loss": 1.1175,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 0.0001926146947642712,
578
+ "loss": 1.1292,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 0.000192433565066091,
584
+ "loss": 1.0464,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.56,
589
+ "learning_rate": 0.00019225032830823011,
590
+ "loss": 1.1549,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 0.00019206498866764288,
596
+ "loss": 1.1129,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.57,
601
+ "learning_rate": 0.00019187755036921978,
602
+ "loss": 0.9965,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 0.0001916880176856909,
608
+ "loss": 1.0767,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 0.0001914963949375288,
614
+ "loss": 1.1546,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "learning_rate": 0.0001913026864928498,
620
+ "loss": 0.9627,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 0.00019110689676731454,
626
+ "loss": 1.0039,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.6,
631
+ "learning_rate": 0.00019090903022402729,
632
+ "loss": 1.066,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 0.00019070909137343408,
638
+ "loss": 1.0654,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.61,
643
+ "learning_rate": 0.00019050708477322018,
644
+ "loss": 1.3323,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 0.00019030301502820596,
650
+ "loss": 1.1247,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.62,
655
+ "learning_rate": 0.0001900968867902419,
656
+ "loss": 1.0261,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.63,
661
+ "learning_rate": 0.00018988870475810282,
662
+ "loss": 1.0935,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 0.00018967847367738048,
668
+ "loss": 1.1043,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.64,
673
+ "learning_rate": 0.00018946619834037546,
674
+ "loss": 1.1982,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 0.00018925188358598813,
680
+ "loss": 1.0445,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.65,
685
+ "learning_rate": 0.00018903553429960802,
686
+ "loss": 1.086,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.66,
691
+ "learning_rate": 0.00018881715541300276,
692
+ "loss": 1.1509,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.66,
697
+ "learning_rate": 0.00018859675190420537,
698
+ "loss": 1.1473,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.67,
703
+ "learning_rate": 0.00018837432879740114,
704
+ "loss": 1.1677,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 0.0001881498911628127,
710
+ "loss": 1.006,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.68,
715
+ "learning_rate": 0.00018792344411658468,
716
+ "loss": 1.0503,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.69,
721
+ "learning_rate": 0.00018769499282066717,
722
+ "loss": 1.163,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.69,
727
+ "learning_rate": 0.00018746454248269777,
728
+ "loss": 1.1443,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "learning_rate": 0.0001872320983558831,
734
+ "loss": 0.9785,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.7,
739
+ "learning_rate": 0.000186997665738879,
740
+ "loss": 1.0605,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.71,
745
+ "learning_rate": 0.0001867612499756697,
746
+ "loss": 1.0203,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.72,
751
+ "learning_rate": 0.00018652285645544603,
752
+ "loss": 1.146,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.72,
757
+ "learning_rate": 0.00018628249061248262,
758
+ "loss": 1.12,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.73,
763
+ "learning_rate": 0.00018604015792601396,
764
+ "loss": 1.1499,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.73,
769
+ "learning_rate": 0.00018579586392010943,
770
+ "loss": 1.1273,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.74,
775
+ "learning_rate": 0.0001855496141635476,
776
+ "loss": 1.0404,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.75,
781
+ "learning_rate": 0.00018530141426968902,
782
+ "loss": 1.1066,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.75,
787
+ "learning_rate": 0.0001850512698963485,
788
+ "loss": 1.0685,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "eval_loss": 0.8026405572891235,
794
+ "eval_runtime": 14.5968,
795
+ "eval_samples_per_second": 56.108,
796
+ "eval_steps_per_second": 28.088,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.76,
801
+ "learning_rate": 0.000184799186745666,
802
+ "loss": 1.0494,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.76,
807
+ "learning_rate": 0.00018454517056397661,
808
+ "loss": 1.1905,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.77,
813
+ "learning_rate": 0.0001842892271416797,
814
+ "loss": 1.2034,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.78,
819
+ "learning_rate": 0.00018403136231310684,
820
+ "loss": 1.2088,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.78,
825
+ "learning_rate": 0.00018377158195638876,
826
+ "loss": 0.9303,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.79,
831
+ "learning_rate": 0.00018350989199332154,
832
+ "loss": 1.1574,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.79,
837
+ "learning_rate": 0.00018324629838923132,
838
+ "loss": 1.1673,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.8,
843
+ "learning_rate": 0.00018298080715283858,
844
+ "loss": 1.1204,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.81,
849
+ "learning_rate": 0.00018271342433612113,
850
+ "loss": 1.0752,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.81,
855
+ "learning_rate": 0.00018244415603417603,
856
+ "loss": 1.0121,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.82,
861
+ "learning_rate": 0.00018217300838508073,
862
+ "loss": 1.0975,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.82,
867
+ "learning_rate": 0.00018189998756975318,
868
+ "loss": 0.9982,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.83,
873
+ "learning_rate": 0.00018162509981181084,
874
+ "loss": 1.1922,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.84,
879
+ "learning_rate": 0.0001813483513774289,
880
+ "loss": 0.9532,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.84,
885
+ "learning_rate": 0.00018106974857519736,
886
+ "loss": 1.0813,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.85,
891
+ "learning_rate": 0.0001807892977559774,
892
+ "loss": 0.9656,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.85,
897
+ "learning_rate": 0.0001805070053127563,
898
+ "loss": 1.1161,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.86,
903
+ "learning_rate": 0.00018022287768050202,
904
+ "loss": 1.0143,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.87,
909
+ "learning_rate": 0.0001799369213360163,
910
+ "loss": 1.1242,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.87,
915
+ "learning_rate": 0.00017964914279778715,
916
+ "loss": 1.0747,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.88,
921
+ "learning_rate": 0.00017935954862584018,
922
+ "loss": 1.1551,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.88,
927
+ "learning_rate": 0.0001790681454215891,
928
+ "loss": 0.9538,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.89,
933
+ "learning_rate": 0.00017877493982768527,
934
+ "loss": 1.0621,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.9,
939
+ "learning_rate": 0.0001784799385278661,
940
+ "loss": 1.0229,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.9,
945
+ "learning_rate": 0.000178183148246803,
946
+ "loss": 0.9991,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.91,
951
+ "learning_rate": 0.00017788457574994778,
952
+ "loss": 1.0045,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.91,
957
+ "learning_rate": 0.00017758422784337863,
958
+ "loss": 1.0675,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.92,
963
+ "learning_rate": 0.00017728211137364489,
964
+ "loss": 0.962,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.93,
969
+ "learning_rate": 0.000176978233227611,
970
+ "loss": 1.0145,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.93,
975
+ "learning_rate": 0.00017667260033229953,
976
+ "loss": 0.9576,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.94,
981
+ "learning_rate": 0.00017636521965473323,
982
+ "loss": 1.0692,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.94,
987
+ "learning_rate": 0.00017605609820177617,
988
+ "loss": 1.2074,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.95,
993
+ "learning_rate": 0.00017574524301997423,
994
+ "loss": 1.1489,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.96,
999
+ "learning_rate": 0.00017543266119539422,
1000
+ "loss": 0.9962,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.96,
1005
+ "learning_rate": 0.00017511835985346253,
1006
+ "loss": 0.8922,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.97,
1011
+ "learning_rate": 0.00017480234615880247,
1012
+ "loss": 0.9248,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.97,
1017
+ "learning_rate": 0.0001744846273150713,
1018
+ "loss": 1.1621,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.98,
1023
+ "learning_rate": 0.00017416521056479577,
1024
+ "loss": 1.0516,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.99,
1029
+ "learning_rate": 0.00017384410318920697,
1030
+ "loss": 1.0086,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.99,
1035
+ "learning_rate": 0.00017352131250807467,
1036
+ "loss": 1.0909,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 1.0,
1041
+ "learning_rate": 0.00017319684587954002,
1042
+ "loss": 1.1085,
1043
+ "step": 167
1044
+ },
1045
+ {
1046
+ "epoch": 1.0,
1047
+ "learning_rate": 0.0001728707106999482,
1048
+ "loss": 1.1573,
1049
+ "step": 168
1050
+ },
1051
+ {
1052
+ "epoch": 1.0,
1053
+ "eval_loss": 0.7850226163864136,
1054
+ "eval_runtime": 14.526,
1055
+ "eval_samples_per_second": 56.382,
1056
+ "eval_steps_per_second": 28.225,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.01,
1061
+ "learning_rate": 0.00017254291440367968,
1062
+ "loss": 1.1107,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.01,
1067
+ "learning_rate": 0.0001722134644629807,
1068
+ "loss": 1.1537,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.0,
1073
+ "learning_rate": 0.00017188236838779295,
1074
+ "loss": 1.1293,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.01,
1079
+ "learning_rate": 0.00017154963372558246,
1080
+ "loss": 1.0653,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.02,
1085
+ "learning_rate": 0.00017121526806116748,
1086
+ "loss": 1.0901,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.02,
1091
+ "learning_rate": 0.00017087927901654557,
1092
+ "loss": 1.1569,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.03,
1097
+ "learning_rate": 0.00017054167425071995,
1098
+ "loss": 1.022,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.03,
1103
+ "learning_rate": 0.00017020246145952477,
1104
+ "loss": 1.0639,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.04,
1109
+ "learning_rate": 0.00016986164837544987,
1110
+ "loss": 1.071,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.05,
1115
+ "learning_rate": 0.00016951924276746425,
1116
+ "loss": 0.924,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.05,
1121
+ "learning_rate": 0.00016917525244083918,
1122
+ "loss": 1.0146,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.06,
1127
+ "learning_rate": 0.00016882968523697028,
1128
+ "loss": 1.0599,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.06,
1133
+ "learning_rate": 0.00016848254903319867,
1134
+ "loss": 1.0237,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.07,
1139
+ "learning_rate": 0.00016813385174263137,
1140
+ "loss": 0.9614,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.08,
1145
+ "learning_rate": 0.0001677836013139611,
1146
+ "loss": 0.9791,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.08,
1151
+ "learning_rate": 0.00016743180573128495,
1152
+ "loss": 1.0945,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.09,
1157
+ "learning_rate": 0.00016707847301392236,
1158
+ "loss": 1.0091,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.09,
1163
+ "learning_rate": 0.00016672361121623238,
1164
+ "loss": 1.1076,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.1,
1169
+ "learning_rate": 0.00016636722842743013,
1170
+ "loss": 0.9472,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.11,
1175
+ "learning_rate": 0.0001660093327714022,
1176
+ "loss": 1.0485,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.11,
1181
+ "learning_rate": 0.0001656499324065217,
1182
+ "loss": 1.0056,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.12,
1187
+ "learning_rate": 0.00016528903552546207,
1188
+ "loss": 1.0819,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.12,
1193
+ "learning_rate": 0.00016492665035501046,
1194
+ "loss": 1.1128,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.13,
1199
+ "learning_rate": 0.00016456278515588024,
1200
+ "loss": 1.056,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.14,
1205
+ "learning_rate": 0.00016419744822252253,
1206
+ "loss": 1.0468,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.14,
1211
+ "learning_rate": 0.0001638306478829373,
1212
+ "loss": 0.9966,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.15,
1217
+ "learning_rate": 0.0001634623924984833,
1218
+ "loss": 0.9898,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.15,
1223
+ "learning_rate": 0.00016309269046368776,
1224
+ "loss": 1.0431,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.16,
1229
+ "learning_rate": 0.0001627215502060548,
1230
+ "loss": 1.0327,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.17,
1235
+ "learning_rate": 0.00016234898018587337,
1236
+ "loss": 1.0382,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.17,
1241
+ "learning_rate": 0.00016197498889602448,
1242
+ "loss": 1.0287,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.18,
1247
+ "learning_rate": 0.0001615995848617876,
1248
+ "loss": 1.0244,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.18,
1253
+ "learning_rate": 0.0001612227766406461,
1254
+ "loss": 1.0989,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 1.19,
1259
+ "learning_rate": 0.00016084457282209243,
1260
+ "loss": 1.1219,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 1.2,
1265
+ "learning_rate": 0.00016046498202743233,
1266
+ "loss": 0.9456,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 1.2,
1271
+ "learning_rate": 0.00016008401290958807,
1272
+ "loss": 1.0259,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 1.21,
1277
+ "learning_rate": 0.0001597016741529014,
1278
+ "loss": 1.0929,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 1.21,
1283
+ "learning_rate": 0.00015931797447293552,
1284
+ "loss": 1.0716,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 1.22,
1289
+ "learning_rate": 0.00015893292261627643,
1290
+ "loss": 0.9947,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 1.23,
1295
+ "learning_rate": 0.00015854652736033354,
1296
+ "loss": 0.9707,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 1.23,
1301
+ "learning_rate": 0.00015815879751313955,
1302
+ "loss": 0.9492,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 1.24,
1307
+ "learning_rate": 0.0001577697419131497,
1308
+ "loss": 0.9346,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 1.24,
1313
+ "eval_loss": 0.7729161381721497,
1314
+ "eval_runtime": 14.4823,
1315
+ "eval_samples_per_second": 56.552,
1316
+ "eval_steps_per_second": 28.31,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.24,
1321
+ "learning_rate": 0.00015737936942904023,
1322
+ "loss": 0.9925,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.25,
1327
+ "learning_rate": 0.00015698768895950642,
1328
+ "loss": 1.032,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.26,
1333
+ "learning_rate": 0.00015659470943305955,
1334
+ "loss": 1.0372,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.26,
1339
+ "learning_rate": 0.00015620043980782327,
1340
+ "loss": 0.9926,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.27,
1345
+ "learning_rate": 0.00015580488907132974,
1346
+ "loss": 0.9653,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.27,
1351
+ "learning_rate": 0.00015540806624031442,
1352
+ "loss": 1.1205,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.28,
1357
+ "learning_rate": 0.00015500998036051074,
1358
+ "loss": 1.0311,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.29,
1363
+ "learning_rate": 0.0001546106405064438,
1364
+ "loss": 0.9639,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.29,
1369
+ "learning_rate": 0.00015421005578122356,
1370
+ "loss": 1.0489,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.3,
1375
+ "learning_rate": 0.00015380823531633729,
1376
+ "loss": 1.0312,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.3,
1381
+ "learning_rate": 0.00015340518827144145,
1382
+ "loss": 1.0165,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.31,
1387
+ "learning_rate": 0.00015300092383415282,
1388
+ "loss": 1.009,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.31,
1393
+ "learning_rate": 0.0001525954512198392,
1394
+ "loss": 1.0458,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.32,
1399
+ "learning_rate": 0.0001521887796714092,
1400
+ "loss": 1.0606,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.33,
1405
+ "learning_rate": 0.0001517809184591017,
1406
+ "loss": 0.9358,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.33,
1411
+ "learning_rate": 0.00015137187688027436,
1412
+ "loss": 1.0373,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.34,
1417
+ "learning_rate": 0.00015096166425919175,
1418
+ "loss": 1.1689,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.34,
1423
+ "learning_rate": 0.00015055028994681284,
1424
+ "loss": 1.1171,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.35,
1429
+ "learning_rate": 0.00015013776332057786,
1430
+ "loss": 0.9495,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.36,
1435
+ "learning_rate": 0.0001497240937841944,
1436
+ "loss": 1.0251,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.36,
1441
+ "learning_rate": 0.00014930929076742316,
1442
+ "loss": 1.132,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.37,
1447
+ "learning_rate": 0.00014889336372586305,
1448
+ "loss": 1.0223,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.37,
1453
+ "learning_rate": 0.00014847632214073548,
1454
+ "loss": 0.9179,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.38,
1459
+ "learning_rate": 0.00014805817551866838,
1460
+ "loss": 0.915,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.39,
1465
+ "learning_rate": 0.0001476389333914794,
1466
+ "loss": 1.0096,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.39,
1471
+ "learning_rate": 0.0001472186053159587,
1472
+ "loss": 1.0108,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.4,
1477
+ "learning_rate": 0.00014679720087365096,
1478
+ "loss": 0.9954,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.4,
1483
+ "learning_rate": 0.0001463747296706372,
1484
+ "loss": 1.0534,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.41,
1489
+ "learning_rate": 0.00014595120133731565,
1490
+ "loss": 0.9521,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.42,
1495
+ "learning_rate": 0.0001455266255281821,
1496
+ "loss": 1.086,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.42,
1501
+ "learning_rate": 0.00014510101192161018,
1502
+ "loss": 0.986,
1503
+ "step": 241
1504
+ },
1505
+ {
1506
+ "epoch": 1.43,
1507
+ "learning_rate": 0.0001446743702196304,
1508
+ "loss": 1.1084,
1509
+ "step": 242
1510
+ },
1511
+ {
1512
+ "epoch": 1.43,
1513
+ "learning_rate": 0.00014424671014770906,
1514
+ "loss": 0.9904,
1515
+ "step": 243
1516
+ },
1517
+ {
1518
+ "epoch": 1.44,
1519
+ "learning_rate": 0.0001438180414545267,
1520
+ "loss": 1.019,
1521
+ "step": 244
1522
+ },
1523
+ {
1524
+ "epoch": 1.45,
1525
+ "learning_rate": 0.00014338837391175582,
1526
+ "loss": 1.1684,
1527
+ "step": 245
1528
+ },
1529
+ {
1530
+ "epoch": 1.45,
1531
+ "learning_rate": 0.00014295771731383797,
1532
+ "loss": 0.9792,
1533
+ "step": 246
1534
+ },
1535
+ {
1536
+ "epoch": 1.46,
1537
+ "learning_rate": 0.00014252608147776065,
1538
+ "loss": 1.0375,
1539
+ "step": 247
1540
+ },
1541
+ {
1542
+ "epoch": 1.46,
1543
+ "learning_rate": 0.0001420934762428335,
1544
+ "loss": 0.9413,
1545
+ "step": 248
1546
+ },
1547
+ {
1548
+ "epoch": 1.47,
1549
+ "learning_rate": 0.00014165991147046403,
1550
+ "loss": 1.0807,
1551
+ "step": 249
1552
+ },
1553
+ {
1554
+ "epoch": 1.48,
1555
+ "learning_rate": 0.00014122539704393265,
1556
+ "loss": 0.8643,
1557
+ "step": 250
1558
+ },
1559
+ {
1560
+ "epoch": 1.48,
1561
+ "learning_rate": 0.00014078994286816768,
1562
+ "loss": 0.9569,
1563
+ "step": 251
1564
+ },
1565
+ {
1566
+ "epoch": 1.49,
1567
+ "learning_rate": 0.00014035355886951923,
1568
+ "loss": 1.0299,
1569
+ "step": 252
1570
+ },
1571
+ {
1572
+ "epoch": 1.49,
1573
+ "eval_loss": 0.761233925819397,
1574
+ "eval_runtime": 14.3861,
1575
+ "eval_samples_per_second": 56.93,
1576
+ "eval_steps_per_second": 28.5,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.49,
1581
+ "learning_rate": 0.00013991625499553325,
1582
+ "loss": 0.9685,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.5,
1587
+ "learning_rate": 0.0001394780412147245,
1588
+ "loss": 1.0123,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.51,
1593
+ "learning_rate": 0.00013903892751634947,
1594
+ "loss": 0.9601,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.51,
1599
+ "learning_rate": 0.00013859892391017865,
1600
+ "loss": 0.9661,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.52,
1605
+ "learning_rate": 0.00013815804042626828,
1606
+ "loss": 1.0132,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.52,
1611
+ "learning_rate": 0.00013771628711473172,
1612
+ "loss": 1.0511,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.53,
1617
+ "learning_rate": 0.00013727367404551055,
1618
+ "loss": 1.0637,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.54,
1623
+ "learning_rate": 0.0001368302113081447,
1624
+ "loss": 0.9781,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.54,
1629
+ "learning_rate": 0.00013638590901154276,
1630
+ "loss": 1.0151,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.55,
1635
+ "learning_rate": 0.00013594077728375128,
1636
+ "loss": 0.9971,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.55,
1641
+ "learning_rate": 0.0001354948262717241,
1642
+ "loss": 0.9202,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.56,
1647
+ "learning_rate": 0.00013504806614109098,
1648
+ "loss": 1.0605,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.57,
1653
+ "learning_rate": 0.0001346005070759258,
1654
+ "loss": 1.0303,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.57,
1659
+ "learning_rate": 0.0001341521592785145,
1660
+ "loss": 0.9228,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.58,
1665
+ "learning_rate": 0.00013370303296912249,
1666
+ "loss": 0.9659,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.58,
1671
+ "learning_rate": 0.0001332531383857616,
1672
+ "loss": 0.9742,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.59,
1677
+ "learning_rate": 0.0001328024857839569,
1678
+ "loss": 1.0524,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.6,
1683
+ "learning_rate": 0.00013235108543651272,
1684
+ "loss": 1.0277,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.6,
1689
+ "learning_rate": 0.0001318989476332785,
1690
+ "loss": 0.9731,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.61,
1695
+ "learning_rate": 0.00013144608268091435,
1696
+ "loss": 1.0629,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.61,
1701
+ "learning_rate": 0.000130992500902656,
1702
+ "loss": 0.8943,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.62,
1707
+ "learning_rate": 0.00013053821263807946,
1708
+ "loss": 0.9997,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.63,
1713
+ "learning_rate": 0.00013008322824286555,
1714
+ "loss": 1.0465,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.63,
1719
+ "learning_rate": 0.00012962755808856342,
1720
+ "loss": 1.0259,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.64,
1725
+ "learning_rate": 0.00012917121256235455,
1726
+ "loss": 0.9458,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.64,
1731
+ "learning_rate": 0.00012871420206681571,
1732
+ "loss": 1.0322,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.65,
1737
+ "learning_rate": 0.000128256537019682,
1738
+ "loss": 0.8538,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.66,
1743
+ "learning_rate": 0.00012779822785360912,
1744
+ "loss": 0.9602,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.66,
1749
+ "learning_rate": 0.00012733928501593587,
1750
+ "loss": 0.9953,
1751
+ "step": 281
1752
+ },
1753
+ {
1754
+ "epoch": 1.67,
1755
+ "learning_rate": 0.00012687971896844575,
1756
+ "loss": 0.8757,
1757
+ "step": 282
1758
+ },
1759
+ {
1760
+ "epoch": 1.67,
1761
+ "learning_rate": 0.00012641954018712863,
1762
+ "loss": 0.9382,
1763
+ "step": 283
1764
+ },
1765
+ {
1766
+ "epoch": 1.68,
1767
+ "learning_rate": 0.00012595875916194188,
1768
+ "loss": 0.8791,
1769
+ "step": 284
1770
+ },
1771
+ {
1772
+ "epoch": 1.69,
1773
+ "learning_rate": 0.00012549738639657115,
1774
+ "loss": 0.9245,
1775
+ "step": 285
1776
+ },
1777
+ {
1778
+ "epoch": 1.69,
1779
+ "learning_rate": 0.00012503543240819127,
1780
+ "loss": 0.9611,
1781
+ "step": 286
1782
+ },
1783
+ {
1784
+ "epoch": 1.7,
1785
+ "learning_rate": 0.00012457290772722608,
1786
+ "loss": 1.0328,
1787
+ "step": 287
1788
+ },
1789
+ {
1790
+ "epoch": 1.7,
1791
+ "learning_rate": 0.00012410982289710865,
1792
+ "loss": 0.8988,
1793
+ "step": 288
1794
+ },
1795
+ {
1796
+ "epoch": 1.71,
1797
+ "learning_rate": 0.0001236461884740409,
1798
+ "loss": 1.0435,
1799
+ "step": 289
1800
+ },
1801
+ {
1802
+ "epoch": 1.71,
1803
+ "learning_rate": 0.00012318201502675285,
1804
+ "loss": 0.9486,
1805
+ "step": 290
1806
+ },
1807
+ {
1808
+ "epoch": 1.72,
1809
+ "learning_rate": 0.0001227173131362619,
1810
+ "loss": 0.8819,
1811
+ "step": 291
1812
+ },
1813
+ {
1814
+ "epoch": 1.73,
1815
+ "learning_rate": 0.00012225209339563145,
1816
+ "loss": 1.024,
1817
+ "step": 292
1818
+ },
1819
+ {
1820
+ "epoch": 1.73,
1821
+ "learning_rate": 0.00012178636640972953,
1822
+ "loss": 0.9137,
1823
+ "step": 293
1824
+ },
1825
+ {
1826
+ "epoch": 1.74,
1827
+ "learning_rate": 0.00012132014279498703,
1828
+ "loss": 1.0057,
1829
+ "step": 294
1830
+ },
1831
+ {
1832
+ "epoch": 1.74,
1833
+ "eval_loss": 0.754410445690155,
1834
+ "eval_runtime": 14.5906,
1835
+ "eval_samples_per_second": 56.132,
1836
+ "eval_steps_per_second": 28.1,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.74,
1841
+ "learning_rate": 0.00012085343317915565,
1842
+ "loss": 1.0209,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.75,
1847
+ "learning_rate": 0.00012038624820106572,
1848
+ "loss": 0.9985,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.76,
1853
+ "learning_rate": 0.0001199185985103836,
1854
+ "loss": 0.7608,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.76,
1859
+ "learning_rate": 0.00011945049476736905,
1860
+ "loss": 0.931,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.77,
1865
+ "learning_rate": 0.00011898194764263197,
1866
+ "loss": 1.0362,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.77,
1871
+ "learning_rate": 0.00011851296781688952,
1872
+ "loss": 1.097,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.78,
1877
+ "learning_rate": 0.00011804356598072223,
1878
+ "loss": 0.9304,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.79,
1883
+ "learning_rate": 0.00011757375283433076,
1884
+ "loss": 0.9989,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.79,
1889
+ "learning_rate": 0.00011710353908729156,
1890
+ "loss": 0.971,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.8,
1895
+ "learning_rate": 0.00011663293545831302,
1896
+ "loss": 0.9942,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.8,
1901
+ "learning_rate": 0.00011616195267499102,
1902
+ "loss": 0.9824,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.81,
1907
+ "learning_rate": 0.00011569060147356441,
1908
+ "loss": 0.9901,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.82,
1913
+ "learning_rate": 0.00011521889259867032,
1914
+ "loss": 1.0445,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.82,
1919
+ "learning_rate": 0.00011474683680309912,
1920
+ "loss": 0.9421,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.83,
1925
+ "learning_rate": 0.0001142744448475494,
1926
+ "loss": 0.9692,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.83,
1931
+ "learning_rate": 0.00011380172750038269,
1932
+ "loss": 0.9473,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.84,
1937
+ "learning_rate": 0.0001133286955373779,
1938
+ "loss": 1.0931,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.85,
1943
+ "learning_rate": 0.00011285535974148576,
1944
+ "loss": 1.0236,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.85,
1949
+ "learning_rate": 0.00011238173090258293,
1950
+ "loss": 0.9002,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.86,
1955
+ "learning_rate": 0.00011190781981722623,
1956
+ "loss": 0.9209,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.86,
1961
+ "learning_rate": 0.00011143363728840625,
1962
+ "loss": 0.9155,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.87,
1967
+ "learning_rate": 0.00011095919412530136,
1968
+ "loss": 1.0064,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.88,
1973
+ "learning_rate": 0.0001104845011430311,
1974
+ "loss": 0.947,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.88,
1979
+ "learning_rate": 0.00011000956916240985,
1980
+ "loss": 0.9293,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.89,
1985
+ "learning_rate": 0.00010953440900969994,
1986
+ "loss": 0.9596,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.89,
1991
+ "learning_rate": 0.00010905903151636501,
1992
+ "loss": 0.9835,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.9,
1997
+ "learning_rate": 0.00010858344751882304,
1998
+ "loss": 0.9722,
1999
+ "step": 321
2000
+ },
2001
+ {
2002
+ "epoch": 1.91,
2003
+ "learning_rate": 0.00010810766785819946,
2004
+ "loss": 0.8318,
2005
+ "step": 322
2006
+ },
2007
+ {
2008
+ "epoch": 1.91,
2009
+ "learning_rate": 0.00010763170338007978,
2010
+ "loss": 1.0073,
2011
+ "step": 323
2012
+ },
2013
+ {
2014
+ "epoch": 1.92,
2015
+ "learning_rate": 0.00010715556493426262,
2016
+ "loss": 0.9922,
2017
+ "step": 324
2018
+ },
2019
+ {
2020
+ "epoch": 1.92,
2021
+ "learning_rate": 0.00010667926337451217,
2022
+ "loss": 0.9459,
2023
+ "step": 325
2024
+ },
2025
+ {
2026
+ "epoch": 1.93,
2027
+ "learning_rate": 0.00010620280955831087,
2028
+ "loss": 0.9276,
2029
+ "step": 326
2030
+ },
2031
+ {
2032
+ "epoch": 1.94,
2033
+ "learning_rate": 0.000105726214346612,
2034
+ "loss": 1.027,
2035
+ "step": 327
2036
+ },
2037
+ {
2038
+ "epoch": 1.94,
2039
+ "learning_rate": 0.00010524948860359193,
2040
+ "loss": 0.8963,
2041
+ "step": 328
2042
+ },
2043
+ {
2044
+ "epoch": 1.95,
2045
+ "learning_rate": 0.00010477264319640252,
2046
+ "loss": 1.0102,
2047
+ "step": 329
2048
+ },
2049
+ {
2050
+ "epoch": 1.95,
2051
+ "learning_rate": 0.00010429568899492348,
2052
+ "loss": 0.9058,
2053
+ "step": 330
2054
+ },
2055
+ {
2056
+ "epoch": 1.96,
2057
+ "learning_rate": 0.0001038186368715145,
2058
+ "loss": 1.137,
2059
+ "step": 331
2060
+ },
2061
+ {
2062
+ "epoch": 1.97,
2063
+ "learning_rate": 0.00010334149770076747,
2064
+ "loss": 0.9578,
2065
+ "step": 332
2066
+ },
2067
+ {
2068
+ "epoch": 1.97,
2069
+ "learning_rate": 0.00010286428235925849,
2070
+ "loss": 0.9282,
2071
+ "step": 333
2072
+ },
2073
+ {
2074
+ "epoch": 1.98,
2075
+ "learning_rate": 0.00010238700172530009,
2076
+ "loss": 0.9325,
2077
+ "step": 334
2078
+ }
2079
+ ],
2080
+ "logging_steps": 1,
2081
+ "max_steps": 668,
2082
+ "num_input_tokens_seen": 0,
2083
+ "num_train_epochs": 4,
2084
+ "save_steps": 167,
2085
+ "total_flos": 6.956422447654502e+16,
2086
+ "train_batch_size": 2,
2087
+ "trial_name": null,
2088
+ "trial_params": null
2089
+ }
checkpoint-334/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14298be73cbe854ab00522590054d32e49c4c47f917719c135f6380025fd0
3
+ size 5368
checkpoint-501/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-501/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-501/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c4566ca8c8b8212d6edf6840e7ffa2d3815341fe352c8d175bb9c523e6389
3
+ size 100966336
checkpoint-501/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5023f0756894267a950c9a92bbef6b245476afc28416476456574657d46bfa4d
3
+ size 50916964
checkpoint-501/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b413e28c9983179904e74bc47c8f870c79c17923f6ca7e4e58c9137b40c470c1
3
+ size 14244
checkpoint-501/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f95c8720f7ab4ed8be890b32c1739fd5478904ffadacee7e572dad0ed4b85ab
3
+ size 1064
checkpoint-501/trainer_state.json ADDED
@@ -0,0 +1,3123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9582089552238804,
5
+ "eval_steps": 42,
6
+ "global_step": 501,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.6541,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 1.7634071111679077,
20
+ "eval_runtime": 14.5059,
21
+ "eval_samples_per_second": 56.46,
22
+ "eval_steps_per_second": 28.264,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.6887,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.828,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.589,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.927,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.6362,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8546,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.5843,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.5592,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.5539,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.0001999988602302209,
82
+ "loss": 1.4449,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0001999954409468652,
88
+ "loss": 1.8818,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.0001999897422278767,
94
+ "loss": 1.6656,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.08,
99
+ "learning_rate": 0.00019998176420316002,
100
+ "loss": 1.4607,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0001999715070545774,
106
+ "loss": 1.4013,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00019995897101594454,
112
+ "loss": 1.5258,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.1,
117
+ "learning_rate": 0.00019994415637302547,
118
+ "loss": 1.404,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.00019992706346352577,
124
+ "loss": 1.3919,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.11,
129
+ "learning_rate": 0.00019990769267708516,
130
+ "loss": 1.355,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.00019988604445526827,
136
+ "loss": 1.3763,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.000199862119291555,
142
+ "loss": 1.3314,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.13,
147
+ "learning_rate": 0.00019983591773132882,
148
+ "loss": 1.4246,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.00019980744037186469,
154
+ "loss": 1.5723,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.14,
159
+ "learning_rate": 0.00019977668786231534,
160
+ "loss": 1.2536,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.15,
165
+ "learning_rate": 0.0001997436609036963,
166
+ "loss": 1.3087,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.0001997083602488702,
172
+ "loss": 1.2783,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.16,
177
+ "learning_rate": 0.00019967078670252945,
178
+ "loss": 1.2792,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00019963094112117785,
184
+ "loss": 1.2476,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.17,
189
+ "learning_rate": 0.00019958882441311126,
190
+ "loss": 1.265,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.18,
195
+ "learning_rate": 0.00019954443753839667,
196
+ "loss": 1.0884,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00019949778150885042,
202
+ "loss": 1.3294,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.19,
207
+ "learning_rate": 0.00019944885738801518,
208
+ "loss": 1.3434,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.2,
213
+ "learning_rate": 0.00019939766629113566,
214
+ "loss": 1.1457,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.2,
219
+ "learning_rate": 0.00019934420938513313,
220
+ "loss": 1.2138,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.21,
225
+ "learning_rate": 0.00019928848788857887,
226
+ "loss": 1.2118,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.21,
231
+ "learning_rate": 0.00019923050307166655,
232
+ "loss": 1.1426,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.22,
237
+ "learning_rate": 0.00019917025625618292,
238
+ "loss": 1.6279,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.23,
243
+ "learning_rate": 0.000199107748815478,
244
+ "loss": 1.5021,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.23,
249
+ "learning_rate": 0.00019904298217443366,
250
+ "loss": 1.3728,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.24,
255
+ "learning_rate": 0.00019897595780943102,
256
+ "loss": 1.2034,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.24,
261
+ "learning_rate": 0.00019890667724831707,
262
+ "loss": 1.3718,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.25,
267
+ "learning_rate": 0.00019883514207036956,
268
+ "loss": 1.2512,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.25,
273
+ "eval_loss": 0.8978323936462402,
274
+ "eval_runtime": 14.6352,
275
+ "eval_samples_per_second": 55.961,
276
+ "eval_steps_per_second": 28.015,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.26,
281
+ "learning_rate": 0.00019876135390626122,
282
+ "loss": 1.1787,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.26,
287
+ "learning_rate": 0.0001986853144380224,
288
+ "loss": 1.1917,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.27,
293
+ "learning_rate": 0.00019860702539900287,
294
+ "loss": 1.1933,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.27,
299
+ "learning_rate": 0.00019852648857383222,
300
+ "loss": 1.1922,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.28,
305
+ "learning_rate": 0.00019844370579837927,
306
+ "loss": 1.3017,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.29,
311
+ "learning_rate": 0.00019835867895971014,
312
+ "loss": 1.1193,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.29,
317
+ "learning_rate": 0.0001982714099960452,
318
+ "loss": 1.1572,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.3,
323
+ "learning_rate": 0.00019818190089671508,
324
+ "loss": 1.3277,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.3,
329
+ "learning_rate": 0.00019809015370211502,
330
+ "loss": 1.0658,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.31,
335
+ "learning_rate": 0.0001979961705036587,
336
+ "loss": 1.1656,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.32,
341
+ "learning_rate": 0.00019789995344373024,
342
+ "loss": 1.4204,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.32,
347
+ "learning_rate": 0.00019780150471563558,
348
+ "loss": 1.1551,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.33,
353
+ "learning_rate": 0.0001977008265635525,
354
+ "loss": 1.0993,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.33,
359
+ "learning_rate": 0.00019759792128247922,
360
+ "loss": 1.1311,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.34,
365
+ "learning_rate": 0.00019749279121818235,
366
+ "loss": 1.2163,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.35,
371
+ "learning_rate": 0.00019738543876714334,
372
+ "loss": 1.3178,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.35,
377
+ "learning_rate": 0.00019727586637650373,
378
+ "loss": 1.3744,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.36,
383
+ "learning_rate": 0.00019716407654400952,
384
+ "loss": 1.1413,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.36,
389
+ "learning_rate": 0.00019705007181795416,
390
+ "loss": 1.0372,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.37,
395
+ "learning_rate": 0.00019693385479712048,
396
+ "loss": 1.1601,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.38,
401
+ "learning_rate": 0.00019681542813072145,
402
+ "loss": 1.0976,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.38,
407
+ "learning_rate": 0.00019669479451833976,
408
+ "loss": 1.1584,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.39,
413
+ "learning_rate": 0.00019657195670986637,
414
+ "loss": 1.0962,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.39,
419
+ "learning_rate": 0.00019644691750543767,
420
+ "loss": 1.1044,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.4,
425
+ "learning_rate": 0.0001963196797553718,
426
+ "loss": 1.2431,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.41,
431
+ "learning_rate": 0.00019619024636010363,
432
+ "loss": 1.1651,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.41,
437
+ "learning_rate": 0.00019605862027011856,
438
+ "loss": 1.0513,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.42,
443
+ "learning_rate": 0.00019592480448588542,
444
+ "loss": 1.0175,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.42,
449
+ "learning_rate": 0.00019578880205778793,
450
+ "loss": 1.1306,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.43,
455
+ "learning_rate": 0.00019565061608605526,
456
+ "loss": 1.3121,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.44,
461
+ "learning_rate": 0.00019551024972069126,
462
+ "loss": 1.266,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.44,
467
+ "learning_rate": 0.00019536770616140276,
468
+ "loss": 1.1099,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.45,
473
+ "learning_rate": 0.0001952229886575266,
474
+ "loss": 1.1012,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.45,
479
+ "learning_rate": 0.00019507610050795558,
480
+ "loss": 1.1272,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.46,
485
+ "learning_rate": 0.0001949270450610631,
486
+ "loss": 1.2016,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.47,
491
+ "learning_rate": 0.00019477582571462705,
492
+ "loss": 1.1746,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.47,
497
+ "learning_rate": 0.00019462244591575222,
498
+ "loss": 1.1349,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.48,
503
+ "learning_rate": 0.0001944669091607919,
504
+ "loss": 1.4311,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.48,
509
+ "learning_rate": 0.00019430921899526787,
510
+ "loss": 1.1033,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.49,
515
+ "learning_rate": 0.00019414937901378982,
516
+ "loss": 1.2491,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.5,
521
+ "learning_rate": 0.0001939873928599734,
522
+ "loss": 1.1044,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.5,
527
+ "learning_rate": 0.00019382326422635705,
528
+ "loss": 1.1008,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.5,
533
+ "eval_loss": 0.8307072520256042,
534
+ "eval_runtime": 14.6668,
535
+ "eval_samples_per_second": 55.841,
536
+ "eval_steps_per_second": 27.954,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 0.0001936569968543179,
542
+ "loss": 1.2317,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 0.00019348859453398646,
548
+ "loss": 1.2317,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 0.00019331806110416027,
554
+ "loss": 1.0989,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.53,
559
+ "learning_rate": 0.00019314540045221626,
560
+ "loss": 1.0466,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 0.00019297061651402236,
566
+ "loss": 1.0798,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 0.0001927937132738476,
572
+ "loss": 1.1175,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 0.0001926146947642712,
578
+ "loss": 1.1292,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 0.000192433565066091,
584
+ "loss": 1.0464,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.56,
589
+ "learning_rate": 0.00019225032830823011,
590
+ "loss": 1.1549,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 0.00019206498866764288,
596
+ "loss": 1.1129,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.57,
601
+ "learning_rate": 0.00019187755036921978,
602
+ "loss": 0.9965,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 0.0001916880176856909,
608
+ "loss": 1.0767,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 0.0001914963949375288,
614
+ "loss": 1.1546,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "learning_rate": 0.0001913026864928498,
620
+ "loss": 0.9627,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 0.00019110689676731454,
626
+ "loss": 1.0039,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.6,
631
+ "learning_rate": 0.00019090903022402729,
632
+ "loss": 1.066,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 0.00019070909137343408,
638
+ "loss": 1.0654,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.61,
643
+ "learning_rate": 0.00019050708477322018,
644
+ "loss": 1.3323,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 0.00019030301502820596,
650
+ "loss": 1.1247,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.62,
655
+ "learning_rate": 0.0001900968867902419,
656
+ "loss": 1.0261,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.63,
661
+ "learning_rate": 0.00018988870475810282,
662
+ "loss": 1.0935,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 0.00018967847367738048,
668
+ "loss": 1.1043,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.64,
673
+ "learning_rate": 0.00018946619834037546,
674
+ "loss": 1.1982,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 0.00018925188358598813,
680
+ "loss": 1.0445,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.65,
685
+ "learning_rate": 0.00018903553429960802,
686
+ "loss": 1.086,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.66,
691
+ "learning_rate": 0.00018881715541300276,
692
+ "loss": 1.1509,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.66,
697
+ "learning_rate": 0.00018859675190420537,
698
+ "loss": 1.1473,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.67,
703
+ "learning_rate": 0.00018837432879740114,
704
+ "loss": 1.1677,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 0.0001881498911628127,
710
+ "loss": 1.006,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.68,
715
+ "learning_rate": 0.00018792344411658468,
716
+ "loss": 1.0503,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.69,
721
+ "learning_rate": 0.00018769499282066717,
722
+ "loss": 1.163,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.69,
727
+ "learning_rate": 0.00018746454248269777,
728
+ "loss": 1.1443,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "learning_rate": 0.0001872320983558831,
734
+ "loss": 0.9785,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.7,
739
+ "learning_rate": 0.000186997665738879,
740
+ "loss": 1.0605,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.71,
745
+ "learning_rate": 0.0001867612499756697,
746
+ "loss": 1.0203,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.72,
751
+ "learning_rate": 0.00018652285645544603,
752
+ "loss": 1.146,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.72,
757
+ "learning_rate": 0.00018628249061248262,
758
+ "loss": 1.12,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.73,
763
+ "learning_rate": 0.00018604015792601396,
764
+ "loss": 1.1499,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.73,
769
+ "learning_rate": 0.00018579586392010943,
770
+ "loss": 1.1273,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.74,
775
+ "learning_rate": 0.0001855496141635476,
776
+ "loss": 1.0404,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.75,
781
+ "learning_rate": 0.00018530141426968902,
782
+ "loss": 1.1066,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.75,
787
+ "learning_rate": 0.0001850512698963485,
788
+ "loss": 1.0685,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "eval_loss": 0.8026405572891235,
794
+ "eval_runtime": 14.5968,
795
+ "eval_samples_per_second": 56.108,
796
+ "eval_steps_per_second": 28.088,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.76,
801
+ "learning_rate": 0.000184799186745666,
802
+ "loss": 1.0494,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.76,
807
+ "learning_rate": 0.00018454517056397661,
808
+ "loss": 1.1905,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.77,
813
+ "learning_rate": 0.0001842892271416797,
814
+ "loss": 1.2034,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.78,
819
+ "learning_rate": 0.00018403136231310684,
820
+ "loss": 1.2088,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.78,
825
+ "learning_rate": 0.00018377158195638876,
826
+ "loss": 0.9303,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.79,
831
+ "learning_rate": 0.00018350989199332154,
832
+ "loss": 1.1574,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.79,
837
+ "learning_rate": 0.00018324629838923132,
838
+ "loss": 1.1673,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.8,
843
+ "learning_rate": 0.00018298080715283858,
844
+ "loss": 1.1204,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.81,
849
+ "learning_rate": 0.00018271342433612113,
850
+ "loss": 1.0752,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.81,
855
+ "learning_rate": 0.00018244415603417603,
856
+ "loss": 1.0121,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.82,
861
+ "learning_rate": 0.00018217300838508073,
862
+ "loss": 1.0975,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.82,
867
+ "learning_rate": 0.00018189998756975318,
868
+ "loss": 0.9982,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.83,
873
+ "learning_rate": 0.00018162509981181084,
874
+ "loss": 1.1922,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.84,
879
+ "learning_rate": 0.0001813483513774289,
880
+ "loss": 0.9532,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.84,
885
+ "learning_rate": 0.00018106974857519736,
886
+ "loss": 1.0813,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.85,
891
+ "learning_rate": 0.0001807892977559774,
892
+ "loss": 0.9656,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.85,
897
+ "learning_rate": 0.0001805070053127563,
898
+ "loss": 1.1161,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.86,
903
+ "learning_rate": 0.00018022287768050202,
904
+ "loss": 1.0143,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.87,
909
+ "learning_rate": 0.0001799369213360163,
910
+ "loss": 1.1242,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.87,
915
+ "learning_rate": 0.00017964914279778715,
916
+ "loss": 1.0747,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.88,
921
+ "learning_rate": 0.00017935954862584018,
922
+ "loss": 1.1551,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.88,
927
+ "learning_rate": 0.0001790681454215891,
928
+ "loss": 0.9538,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.89,
933
+ "learning_rate": 0.00017877493982768527,
934
+ "loss": 1.0621,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.9,
939
+ "learning_rate": 0.0001784799385278661,
940
+ "loss": 1.0229,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.9,
945
+ "learning_rate": 0.000178183148246803,
946
+ "loss": 0.9991,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.91,
951
+ "learning_rate": 0.00017788457574994778,
952
+ "loss": 1.0045,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.91,
957
+ "learning_rate": 0.00017758422784337863,
958
+ "loss": 1.0675,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.92,
963
+ "learning_rate": 0.00017728211137364489,
964
+ "loss": 0.962,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.93,
969
+ "learning_rate": 0.000176978233227611,
970
+ "loss": 1.0145,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.93,
975
+ "learning_rate": 0.00017667260033229953,
976
+ "loss": 0.9576,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.94,
981
+ "learning_rate": 0.00017636521965473323,
982
+ "loss": 1.0692,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.94,
987
+ "learning_rate": 0.00017605609820177617,
988
+ "loss": 1.2074,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.95,
993
+ "learning_rate": 0.00017574524301997423,
994
+ "loss": 1.1489,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.96,
999
+ "learning_rate": 0.00017543266119539422,
1000
+ "loss": 0.9962,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.96,
1005
+ "learning_rate": 0.00017511835985346253,
1006
+ "loss": 0.8922,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.97,
1011
+ "learning_rate": 0.00017480234615880247,
1012
+ "loss": 0.9248,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.97,
1017
+ "learning_rate": 0.0001744846273150713,
1018
+ "loss": 1.1621,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.98,
1023
+ "learning_rate": 0.00017416521056479577,
1024
+ "loss": 1.0516,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.99,
1029
+ "learning_rate": 0.00017384410318920697,
1030
+ "loss": 1.0086,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.99,
1035
+ "learning_rate": 0.00017352131250807467,
1036
+ "loss": 1.0909,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 1.0,
1041
+ "learning_rate": 0.00017319684587954002,
1042
+ "loss": 1.1085,
1043
+ "step": 167
1044
+ },
1045
+ {
1046
+ "epoch": 1.0,
1047
+ "learning_rate": 0.0001728707106999482,
1048
+ "loss": 1.1573,
1049
+ "step": 168
1050
+ },
1051
+ {
1052
+ "epoch": 1.0,
1053
+ "eval_loss": 0.7850226163864136,
1054
+ "eval_runtime": 14.526,
1055
+ "eval_samples_per_second": 56.382,
1056
+ "eval_steps_per_second": 28.225,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.01,
1061
+ "learning_rate": 0.00017254291440367968,
1062
+ "loss": 1.1107,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.01,
1067
+ "learning_rate": 0.0001722134644629807,
1068
+ "loss": 1.1537,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.0,
1073
+ "learning_rate": 0.00017188236838779295,
1074
+ "loss": 1.1293,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.01,
1079
+ "learning_rate": 0.00017154963372558246,
1080
+ "loss": 1.0653,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.02,
1085
+ "learning_rate": 0.00017121526806116748,
1086
+ "loss": 1.0901,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.02,
1091
+ "learning_rate": 0.00017087927901654557,
1092
+ "loss": 1.1569,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.03,
1097
+ "learning_rate": 0.00017054167425071995,
1098
+ "loss": 1.022,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.03,
1103
+ "learning_rate": 0.00017020246145952477,
1104
+ "loss": 1.0639,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.04,
1109
+ "learning_rate": 0.00016986164837544987,
1110
+ "loss": 1.071,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.05,
1115
+ "learning_rate": 0.00016951924276746425,
1116
+ "loss": 0.924,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.05,
1121
+ "learning_rate": 0.00016917525244083918,
1122
+ "loss": 1.0146,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.06,
1127
+ "learning_rate": 0.00016882968523697028,
1128
+ "loss": 1.0599,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.06,
1133
+ "learning_rate": 0.00016848254903319867,
1134
+ "loss": 1.0237,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.07,
1139
+ "learning_rate": 0.00016813385174263137,
1140
+ "loss": 0.9614,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.08,
1145
+ "learning_rate": 0.0001677836013139611,
1146
+ "loss": 0.9791,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.08,
1151
+ "learning_rate": 0.00016743180573128495,
1152
+ "loss": 1.0945,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.09,
1157
+ "learning_rate": 0.00016707847301392236,
1158
+ "loss": 1.0091,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.09,
1163
+ "learning_rate": 0.00016672361121623238,
1164
+ "loss": 1.1076,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.1,
1169
+ "learning_rate": 0.00016636722842743013,
1170
+ "loss": 0.9472,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.11,
1175
+ "learning_rate": 0.0001660093327714022,
1176
+ "loss": 1.0485,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.11,
1181
+ "learning_rate": 0.0001656499324065217,
1182
+ "loss": 1.0056,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.12,
1187
+ "learning_rate": 0.00016528903552546207,
1188
+ "loss": 1.0819,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.12,
1193
+ "learning_rate": 0.00016492665035501046,
1194
+ "loss": 1.1128,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.13,
1199
+ "learning_rate": 0.00016456278515588024,
1200
+ "loss": 1.056,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.14,
1205
+ "learning_rate": 0.00016419744822252253,
1206
+ "loss": 1.0468,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.14,
1211
+ "learning_rate": 0.0001638306478829373,
1212
+ "loss": 0.9966,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.15,
1217
+ "learning_rate": 0.0001634623924984833,
1218
+ "loss": 0.9898,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.15,
1223
+ "learning_rate": 0.00016309269046368776,
1224
+ "loss": 1.0431,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.16,
1229
+ "learning_rate": 0.0001627215502060548,
1230
+ "loss": 1.0327,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.17,
1235
+ "learning_rate": 0.00016234898018587337,
1236
+ "loss": 1.0382,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.17,
1241
+ "learning_rate": 0.00016197498889602448,
1242
+ "loss": 1.0287,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.18,
1247
+ "learning_rate": 0.0001615995848617876,
1248
+ "loss": 1.0244,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.18,
1253
+ "learning_rate": 0.0001612227766406461,
1254
+ "loss": 1.0989,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 1.19,
1259
+ "learning_rate": 0.00016084457282209243,
1260
+ "loss": 1.1219,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 1.2,
1265
+ "learning_rate": 0.00016046498202743233,
1266
+ "loss": 0.9456,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 1.2,
1271
+ "learning_rate": 0.00016008401290958807,
1272
+ "loss": 1.0259,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 1.21,
1277
+ "learning_rate": 0.0001597016741529014,
1278
+ "loss": 1.0929,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 1.21,
1283
+ "learning_rate": 0.00015931797447293552,
1284
+ "loss": 1.0716,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 1.22,
1289
+ "learning_rate": 0.00015893292261627643,
1290
+ "loss": 0.9947,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 1.23,
1295
+ "learning_rate": 0.00015854652736033354,
1296
+ "loss": 0.9707,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 1.23,
1301
+ "learning_rate": 0.00015815879751313955,
1302
+ "loss": 0.9492,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 1.24,
1307
+ "learning_rate": 0.0001577697419131497,
1308
+ "loss": 0.9346,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 1.24,
1313
+ "eval_loss": 0.7729161381721497,
1314
+ "eval_runtime": 14.4823,
1315
+ "eval_samples_per_second": 56.552,
1316
+ "eval_steps_per_second": 28.31,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.24,
1321
+ "learning_rate": 0.00015737936942904023,
1322
+ "loss": 0.9925,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.25,
1327
+ "learning_rate": 0.00015698768895950642,
1328
+ "loss": 1.032,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.26,
1333
+ "learning_rate": 0.00015659470943305955,
1334
+ "loss": 1.0372,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.26,
1339
+ "learning_rate": 0.00015620043980782327,
1340
+ "loss": 0.9926,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.27,
1345
+ "learning_rate": 0.00015580488907132974,
1346
+ "loss": 0.9653,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.27,
1351
+ "learning_rate": 0.00015540806624031442,
1352
+ "loss": 1.1205,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.28,
1357
+ "learning_rate": 0.00015500998036051074,
1358
+ "loss": 1.0311,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.29,
1363
+ "learning_rate": 0.0001546106405064438,
1364
+ "loss": 0.9639,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.29,
1369
+ "learning_rate": 0.00015421005578122356,
1370
+ "loss": 1.0489,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.3,
1375
+ "learning_rate": 0.00015380823531633729,
1376
+ "loss": 1.0312,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.3,
1381
+ "learning_rate": 0.00015340518827144145,
1382
+ "loss": 1.0165,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.31,
1387
+ "learning_rate": 0.00015300092383415282,
1388
+ "loss": 1.009,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.31,
1393
+ "learning_rate": 0.0001525954512198392,
1394
+ "loss": 1.0458,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.32,
1399
+ "learning_rate": 0.0001521887796714092,
1400
+ "loss": 1.0606,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.33,
1405
+ "learning_rate": 0.0001517809184591017,
1406
+ "loss": 0.9358,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.33,
1411
+ "learning_rate": 0.00015137187688027436,
1412
+ "loss": 1.0373,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.34,
1417
+ "learning_rate": 0.00015096166425919175,
1418
+ "loss": 1.1689,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.34,
1423
+ "learning_rate": 0.00015055028994681284,
1424
+ "loss": 1.1171,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.35,
1429
+ "learning_rate": 0.00015013776332057786,
1430
+ "loss": 0.9495,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.36,
1435
+ "learning_rate": 0.0001497240937841944,
1436
+ "loss": 1.0251,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.36,
1441
+ "learning_rate": 0.00014930929076742316,
1442
+ "loss": 1.132,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.37,
1447
+ "learning_rate": 0.00014889336372586305,
1448
+ "loss": 1.0223,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.37,
1453
+ "learning_rate": 0.00014847632214073548,
1454
+ "loss": 0.9179,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.38,
1459
+ "learning_rate": 0.00014805817551866838,
1460
+ "loss": 0.915,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.39,
1465
+ "learning_rate": 0.0001476389333914794,
1466
+ "loss": 1.0096,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.39,
1471
+ "learning_rate": 0.0001472186053159587,
1472
+ "loss": 1.0108,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.4,
1477
+ "learning_rate": 0.00014679720087365096,
1478
+ "loss": 0.9954,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.4,
1483
+ "learning_rate": 0.0001463747296706372,
1484
+ "loss": 1.0534,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.41,
1489
+ "learning_rate": 0.00014595120133731565,
1490
+ "loss": 0.9521,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.42,
1495
+ "learning_rate": 0.0001455266255281821,
1496
+ "loss": 1.086,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.42,
1501
+ "learning_rate": 0.00014510101192161018,
1502
+ "loss": 0.986,
1503
+ "step": 241
1504
+ },
1505
+ {
1506
+ "epoch": 1.43,
1507
+ "learning_rate": 0.0001446743702196304,
1508
+ "loss": 1.1084,
1509
+ "step": 242
1510
+ },
1511
+ {
1512
+ "epoch": 1.43,
1513
+ "learning_rate": 0.00014424671014770906,
1514
+ "loss": 0.9904,
1515
+ "step": 243
1516
+ },
1517
+ {
1518
+ "epoch": 1.44,
1519
+ "learning_rate": 0.0001438180414545267,
1520
+ "loss": 1.019,
1521
+ "step": 244
1522
+ },
1523
+ {
1524
+ "epoch": 1.45,
1525
+ "learning_rate": 0.00014338837391175582,
1526
+ "loss": 1.1684,
1527
+ "step": 245
1528
+ },
1529
+ {
1530
+ "epoch": 1.45,
1531
+ "learning_rate": 0.00014295771731383797,
1532
+ "loss": 0.9792,
1533
+ "step": 246
1534
+ },
1535
+ {
1536
+ "epoch": 1.46,
1537
+ "learning_rate": 0.00014252608147776065,
1538
+ "loss": 1.0375,
1539
+ "step": 247
1540
+ },
1541
+ {
1542
+ "epoch": 1.46,
1543
+ "learning_rate": 0.0001420934762428335,
1544
+ "loss": 0.9413,
1545
+ "step": 248
1546
+ },
1547
+ {
1548
+ "epoch": 1.47,
1549
+ "learning_rate": 0.00014165991147046403,
1550
+ "loss": 1.0807,
1551
+ "step": 249
1552
+ },
1553
+ {
1554
+ "epoch": 1.48,
1555
+ "learning_rate": 0.00014122539704393265,
1556
+ "loss": 0.8643,
1557
+ "step": 250
1558
+ },
1559
+ {
1560
+ "epoch": 1.48,
1561
+ "learning_rate": 0.00014078994286816768,
1562
+ "loss": 0.9569,
1563
+ "step": 251
1564
+ },
1565
+ {
1566
+ "epoch": 1.49,
1567
+ "learning_rate": 0.00014035355886951923,
1568
+ "loss": 1.0299,
1569
+ "step": 252
1570
+ },
1571
+ {
1572
+ "epoch": 1.49,
1573
+ "eval_loss": 0.761233925819397,
1574
+ "eval_runtime": 14.3861,
1575
+ "eval_samples_per_second": 56.93,
1576
+ "eval_steps_per_second": 28.5,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.49,
1581
+ "learning_rate": 0.00013991625499553325,
1582
+ "loss": 0.9685,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.5,
1587
+ "learning_rate": 0.0001394780412147245,
1588
+ "loss": 1.0123,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.51,
1593
+ "learning_rate": 0.00013903892751634947,
1594
+ "loss": 0.9601,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.51,
1599
+ "learning_rate": 0.00013859892391017865,
1600
+ "loss": 0.9661,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.52,
1605
+ "learning_rate": 0.00013815804042626828,
1606
+ "loss": 1.0132,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.52,
1611
+ "learning_rate": 0.00013771628711473172,
1612
+ "loss": 1.0511,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.53,
1617
+ "learning_rate": 0.00013727367404551055,
1618
+ "loss": 1.0637,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.54,
1623
+ "learning_rate": 0.0001368302113081447,
1624
+ "loss": 0.9781,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.54,
1629
+ "learning_rate": 0.00013638590901154276,
1630
+ "loss": 1.0151,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.55,
1635
+ "learning_rate": 0.00013594077728375128,
1636
+ "loss": 0.9971,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.55,
1641
+ "learning_rate": 0.0001354948262717241,
1642
+ "loss": 0.9202,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.56,
1647
+ "learning_rate": 0.00013504806614109098,
1648
+ "loss": 1.0605,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.57,
1653
+ "learning_rate": 0.0001346005070759258,
1654
+ "loss": 1.0303,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.57,
1659
+ "learning_rate": 0.0001341521592785145,
1660
+ "loss": 0.9228,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.58,
1665
+ "learning_rate": 0.00013370303296912249,
1666
+ "loss": 0.9659,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.58,
1671
+ "learning_rate": 0.0001332531383857616,
1672
+ "loss": 0.9742,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.59,
1677
+ "learning_rate": 0.0001328024857839569,
1678
+ "loss": 1.0524,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.6,
1683
+ "learning_rate": 0.00013235108543651272,
1684
+ "loss": 1.0277,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.6,
1689
+ "learning_rate": 0.0001318989476332785,
1690
+ "loss": 0.9731,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.61,
1695
+ "learning_rate": 0.00013144608268091435,
1696
+ "loss": 1.0629,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.61,
1701
+ "learning_rate": 0.000130992500902656,
1702
+ "loss": 0.8943,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.62,
1707
+ "learning_rate": 0.00013053821263807946,
1708
+ "loss": 0.9997,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.63,
1713
+ "learning_rate": 0.00013008322824286555,
1714
+ "loss": 1.0465,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.63,
1719
+ "learning_rate": 0.00012962755808856342,
1720
+ "loss": 1.0259,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.64,
1725
+ "learning_rate": 0.00012917121256235455,
1726
+ "loss": 0.9458,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.64,
1731
+ "learning_rate": 0.00012871420206681571,
1732
+ "loss": 1.0322,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.65,
1737
+ "learning_rate": 0.000128256537019682,
1738
+ "loss": 0.8538,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.66,
1743
+ "learning_rate": 0.00012779822785360912,
1744
+ "loss": 0.9602,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.66,
1749
+ "learning_rate": 0.00012733928501593587,
1750
+ "loss": 0.9953,
1751
+ "step": 281
1752
+ },
1753
+ {
1754
+ "epoch": 1.67,
1755
+ "learning_rate": 0.00012687971896844575,
1756
+ "loss": 0.8757,
1757
+ "step": 282
1758
+ },
1759
+ {
1760
+ "epoch": 1.67,
1761
+ "learning_rate": 0.00012641954018712863,
1762
+ "loss": 0.9382,
1763
+ "step": 283
1764
+ },
1765
+ {
1766
+ "epoch": 1.68,
1767
+ "learning_rate": 0.00012595875916194188,
1768
+ "loss": 0.8791,
1769
+ "step": 284
1770
+ },
1771
+ {
1772
+ "epoch": 1.69,
1773
+ "learning_rate": 0.00012549738639657115,
1774
+ "loss": 0.9245,
1775
+ "step": 285
1776
+ },
1777
+ {
1778
+ "epoch": 1.69,
1779
+ "learning_rate": 0.00012503543240819127,
1780
+ "loss": 0.9611,
1781
+ "step": 286
1782
+ },
1783
+ {
1784
+ "epoch": 1.7,
1785
+ "learning_rate": 0.00012457290772722608,
1786
+ "loss": 1.0328,
1787
+ "step": 287
1788
+ },
1789
+ {
1790
+ "epoch": 1.7,
1791
+ "learning_rate": 0.00012410982289710865,
1792
+ "loss": 0.8988,
1793
+ "step": 288
1794
+ },
1795
+ {
1796
+ "epoch": 1.71,
1797
+ "learning_rate": 0.0001236461884740409,
1798
+ "loss": 1.0435,
1799
+ "step": 289
1800
+ },
1801
+ {
1802
+ "epoch": 1.71,
1803
+ "learning_rate": 0.00012318201502675285,
1804
+ "loss": 0.9486,
1805
+ "step": 290
1806
+ },
1807
+ {
1808
+ "epoch": 1.72,
1809
+ "learning_rate": 0.0001227173131362619,
1810
+ "loss": 0.8819,
1811
+ "step": 291
1812
+ },
1813
+ {
1814
+ "epoch": 1.73,
1815
+ "learning_rate": 0.00012225209339563145,
1816
+ "loss": 1.024,
1817
+ "step": 292
1818
+ },
1819
+ {
1820
+ "epoch": 1.73,
1821
+ "learning_rate": 0.00012178636640972953,
1822
+ "loss": 0.9137,
1823
+ "step": 293
1824
+ },
1825
+ {
1826
+ "epoch": 1.74,
1827
+ "learning_rate": 0.00012132014279498703,
1828
+ "loss": 1.0057,
1829
+ "step": 294
1830
+ },
1831
+ {
1832
+ "epoch": 1.74,
1833
+ "eval_loss": 0.754410445690155,
1834
+ "eval_runtime": 14.5906,
1835
+ "eval_samples_per_second": 56.132,
1836
+ "eval_steps_per_second": 28.1,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.74,
1841
+ "learning_rate": 0.00012085343317915565,
1842
+ "loss": 1.0209,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.75,
1847
+ "learning_rate": 0.00012038624820106572,
1848
+ "loss": 0.9985,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.76,
1853
+ "learning_rate": 0.0001199185985103836,
1854
+ "loss": 0.7608,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.76,
1859
+ "learning_rate": 0.00011945049476736905,
1860
+ "loss": 0.931,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.77,
1865
+ "learning_rate": 0.00011898194764263197,
1866
+ "loss": 1.0362,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.77,
1871
+ "learning_rate": 0.00011851296781688952,
1872
+ "loss": 1.097,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.78,
1877
+ "learning_rate": 0.00011804356598072223,
1878
+ "loss": 0.9304,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.79,
1883
+ "learning_rate": 0.00011757375283433076,
1884
+ "loss": 0.9989,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.79,
1889
+ "learning_rate": 0.00011710353908729156,
1890
+ "loss": 0.971,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.8,
1895
+ "learning_rate": 0.00011663293545831302,
1896
+ "loss": 0.9942,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.8,
1901
+ "learning_rate": 0.00011616195267499102,
1902
+ "loss": 0.9824,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.81,
1907
+ "learning_rate": 0.00011569060147356441,
1908
+ "loss": 0.9901,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.82,
1913
+ "learning_rate": 0.00011521889259867032,
1914
+ "loss": 1.0445,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.82,
1919
+ "learning_rate": 0.00011474683680309912,
1920
+ "loss": 0.9421,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.83,
1925
+ "learning_rate": 0.0001142744448475494,
1926
+ "loss": 0.9692,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.83,
1931
+ "learning_rate": 0.00011380172750038269,
1932
+ "loss": 0.9473,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.84,
1937
+ "learning_rate": 0.0001133286955373779,
1938
+ "loss": 1.0931,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.85,
1943
+ "learning_rate": 0.00011285535974148576,
1944
+ "loss": 1.0236,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.85,
1949
+ "learning_rate": 0.00011238173090258293,
1950
+ "loss": 0.9002,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.86,
1955
+ "learning_rate": 0.00011190781981722623,
1956
+ "loss": 0.9209,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.86,
1961
+ "learning_rate": 0.00011143363728840625,
1962
+ "loss": 0.9155,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.87,
1967
+ "learning_rate": 0.00011095919412530136,
1968
+ "loss": 1.0064,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.88,
1973
+ "learning_rate": 0.0001104845011430311,
1974
+ "loss": 0.947,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.88,
1979
+ "learning_rate": 0.00011000956916240985,
1980
+ "loss": 0.9293,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.89,
1985
+ "learning_rate": 0.00010953440900969994,
1986
+ "loss": 0.9596,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.89,
1991
+ "learning_rate": 0.00010905903151636501,
1992
+ "loss": 0.9835,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.9,
1997
+ "learning_rate": 0.00010858344751882304,
1998
+ "loss": 0.9722,
1999
+ "step": 321
2000
+ },
2001
+ {
2002
+ "epoch": 1.91,
2003
+ "learning_rate": 0.00010810766785819946,
2004
+ "loss": 0.8318,
2005
+ "step": 322
2006
+ },
2007
+ {
2008
+ "epoch": 1.91,
2009
+ "learning_rate": 0.00010763170338007978,
2010
+ "loss": 1.0073,
2011
+ "step": 323
2012
+ },
2013
+ {
2014
+ "epoch": 1.92,
2015
+ "learning_rate": 0.00010715556493426262,
2016
+ "loss": 0.9922,
2017
+ "step": 324
2018
+ },
2019
+ {
2020
+ "epoch": 1.92,
2021
+ "learning_rate": 0.00010667926337451217,
2022
+ "loss": 0.9459,
2023
+ "step": 325
2024
+ },
2025
+ {
2026
+ "epoch": 1.93,
2027
+ "learning_rate": 0.00010620280955831087,
2028
+ "loss": 0.9276,
2029
+ "step": 326
2030
+ },
2031
+ {
2032
+ "epoch": 1.94,
2033
+ "learning_rate": 0.000105726214346612,
2034
+ "loss": 1.027,
2035
+ "step": 327
2036
+ },
2037
+ {
2038
+ "epoch": 1.94,
2039
+ "learning_rate": 0.00010524948860359193,
2040
+ "loss": 0.8963,
2041
+ "step": 328
2042
+ },
2043
+ {
2044
+ "epoch": 1.95,
2045
+ "learning_rate": 0.00010477264319640252,
2046
+ "loss": 1.0102,
2047
+ "step": 329
2048
+ },
2049
+ {
2050
+ "epoch": 1.95,
2051
+ "learning_rate": 0.00010429568899492348,
2052
+ "loss": 0.9058,
2053
+ "step": 330
2054
+ },
2055
+ {
2056
+ "epoch": 1.96,
2057
+ "learning_rate": 0.0001038186368715145,
2058
+ "loss": 1.137,
2059
+ "step": 331
2060
+ },
2061
+ {
2062
+ "epoch": 1.97,
2063
+ "learning_rate": 0.00010334149770076747,
2064
+ "loss": 0.9578,
2065
+ "step": 332
2066
+ },
2067
+ {
2068
+ "epoch": 1.97,
2069
+ "learning_rate": 0.00010286428235925849,
2070
+ "loss": 0.9282,
2071
+ "step": 333
2072
+ },
2073
+ {
2074
+ "epoch": 1.98,
2075
+ "learning_rate": 0.00010238700172530009,
2076
+ "loss": 0.9325,
2077
+ "step": 334
2078
+ },
2079
+ {
2080
+ "epoch": 1.98,
2081
+ "learning_rate": 0.0001019096666786931,
2082
+ "loss": 0.9145,
2083
+ "step": 335
2084
+ },
2085
+ {
2086
+ "epoch": 1.99,
2087
+ "learning_rate": 0.00010143228810047875,
2088
+ "loss": 0.976,
2089
+ "step": 336
2090
+ },
2091
+ {
2092
+ "epoch": 1.99,
2093
+ "eval_loss": 0.7478241920471191,
2094
+ "eval_runtime": 14.477,
2095
+ "eval_samples_per_second": 56.573,
2096
+ "eval_steps_per_second": 28.321,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 2.0,
2101
+ "learning_rate": 0.00010095487687269054,
2102
+ "loss": 1.005,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 2.0,
2107
+ "learning_rate": 0.00010047744387810632,
2108
+ "loss": 0.9885,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 2.01,
2113
+ "learning_rate": 0.0001,
2114
+ "loss": 1.0033,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 2.01,
2119
+ "learning_rate": 9.952255612189368e-05,
2120
+ "loss": 0.867,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 2.0,
2125
+ "learning_rate": 9.904512312730948e-05,
2126
+ "loss": 1.0728,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 2.01,
2131
+ "learning_rate": 9.856771189952126e-05,
2132
+ "loss": 0.9978,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 2.01,
2137
+ "learning_rate": 9.809033332130693e-05,
2138
+ "loss": 0.8017,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 2.02,
2143
+ "learning_rate": 9.761299827469992e-05,
2144
+ "loss": 0.8687,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 2.03,
2149
+ "learning_rate": 9.713571764074152e-05,
2150
+ "loss": 1.1273,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 2.03,
2155
+ "learning_rate": 9.665850229923258e-05,
2156
+ "loss": 0.9474,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 2.04,
2161
+ "learning_rate": 9.618136312848551e-05,
2162
+ "loss": 0.9905,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 2.04,
2167
+ "learning_rate": 9.570431100507651e-05,
2168
+ "loss": 0.9277,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 2.05,
2173
+ "learning_rate": 9.52273568035975e-05,
2174
+ "loss": 0.8655,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 2.06,
2179
+ "learning_rate": 9.475051139640809e-05,
2180
+ "loss": 0.9271,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 2.06,
2185
+ "learning_rate": 9.4273785653388e-05,
2186
+ "loss": 1.0323,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 2.07,
2191
+ "learning_rate": 9.379719044168915e-05,
2192
+ "loss": 0.9624,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 2.07,
2197
+ "learning_rate": 9.332073662548784e-05,
2198
+ "loss": 0.8565,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 2.08,
2203
+ "learning_rate": 9.28444350657374e-05,
2204
+ "loss": 0.99,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 2.09,
2209
+ "learning_rate": 9.236829661992023e-05,
2210
+ "loss": 1.0581,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 2.09,
2215
+ "learning_rate": 9.189233214180056e-05,
2216
+ "loss": 0.8963,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 2.1,
2221
+ "learning_rate": 9.141655248117698e-05,
2222
+ "loss": 0.9169,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 2.1,
2227
+ "learning_rate": 9.094096848363502e-05,
2228
+ "loss": 1.0023,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 2.11,
2233
+ "learning_rate": 9.046559099030012e-05,
2234
+ "loss": 0.8931,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 2.12,
2239
+ "learning_rate": 8.999043083759017e-05,
2240
+ "loss": 1.0086,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 2.12,
2245
+ "learning_rate": 8.951549885696889e-05,
2246
+ "loss": 0.9737,
2247
+ "step": 361
2248
+ },
2249
+ {
2250
+ "epoch": 2.13,
2251
+ "learning_rate": 8.904080587469868e-05,
2252
+ "loss": 1.006,
2253
+ "step": 362
2254
+ },
2255
+ {
2256
+ "epoch": 2.13,
2257
+ "learning_rate": 8.856636271159377e-05,
2258
+ "loss": 0.8521,
2259
+ "step": 363
2260
+ },
2261
+ {
2262
+ "epoch": 2.14,
2263
+ "learning_rate": 8.809218018277378e-05,
2264
+ "loss": 0.8799,
2265
+ "step": 364
2266
+ },
2267
+ {
2268
+ "epoch": 2.15,
2269
+ "learning_rate": 8.761826909741709e-05,
2270
+ "loss": 0.86,
2271
+ "step": 365
2272
+ },
2273
+ {
2274
+ "epoch": 2.15,
2275
+ "learning_rate": 8.714464025851427e-05,
2276
+ "loss": 0.9277,
2277
+ "step": 366
2278
+ },
2279
+ {
2280
+ "epoch": 2.16,
2281
+ "learning_rate": 8.667130446262214e-05,
2282
+ "loss": 0.9753,
2283
+ "step": 367
2284
+ },
2285
+ {
2286
+ "epoch": 2.16,
2287
+ "learning_rate": 8.619827249961733e-05,
2288
+ "loss": 0.9232,
2289
+ "step": 368
2290
+ },
2291
+ {
2292
+ "epoch": 2.17,
2293
+ "learning_rate": 8.57255551524506e-05,
2294
+ "loss": 1.0167,
2295
+ "step": 369
2296
+ },
2297
+ {
2298
+ "epoch": 2.18,
2299
+ "learning_rate": 8.525316319690092e-05,
2300
+ "loss": 1.1038,
2301
+ "step": 370
2302
+ },
2303
+ {
2304
+ "epoch": 2.18,
2305
+ "learning_rate": 8.47811074013297e-05,
2306
+ "loss": 0.9303,
2307
+ "step": 371
2308
+ },
2309
+ {
2310
+ "epoch": 2.19,
2311
+ "learning_rate": 8.430939852643558e-05,
2312
+ "loss": 0.9683,
2313
+ "step": 372
2314
+ },
2315
+ {
2316
+ "epoch": 2.19,
2317
+ "learning_rate": 8.383804732500902e-05,
2318
+ "loss": 0.9889,
2319
+ "step": 373
2320
+ },
2321
+ {
2322
+ "epoch": 2.2,
2323
+ "learning_rate": 8.336706454168701e-05,
2324
+ "loss": 0.7554,
2325
+ "step": 374
2326
+ },
2327
+ {
2328
+ "epoch": 2.21,
2329
+ "learning_rate": 8.289646091270849e-05,
2330
+ "loss": 0.9968,
2331
+ "step": 375
2332
+ },
2333
+ {
2334
+ "epoch": 2.21,
2335
+ "learning_rate": 8.242624716566927e-05,
2336
+ "loss": 1.0212,
2337
+ "step": 376
2338
+ },
2339
+ {
2340
+ "epoch": 2.22,
2341
+ "learning_rate": 8.195643401927777e-05,
2342
+ "loss": 0.9033,
2343
+ "step": 377
2344
+ },
2345
+ {
2346
+ "epoch": 2.22,
2347
+ "learning_rate": 8.148703218311053e-05,
2348
+ "loss": 1.0765,
2349
+ "step": 378
2350
+ },
2351
+ {
2352
+ "epoch": 2.22,
2353
+ "eval_loss": 0.7438732981681824,
2354
+ "eval_runtime": 14.4192,
2355
+ "eval_samples_per_second": 56.799,
2356
+ "eval_steps_per_second": 28.434,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 2.23,
2361
+ "learning_rate": 8.101805235736804e-05,
2362
+ "loss": 0.9057,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 2.24,
2367
+ "learning_rate": 8.054950523263096e-05,
2368
+ "loss": 0.9076,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 2.24,
2373
+ "learning_rate": 8.008140148961641e-05,
2374
+ "loss": 0.9456,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 2.25,
2379
+ "learning_rate": 7.96137517989343e-05,
2380
+ "loss": 1.0068,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 2.25,
2385
+ "learning_rate": 7.914656682084437e-05,
2386
+ "loss": 1.015,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 2.26,
2391
+ "learning_rate": 7.867985720501301e-05,
2392
+ "loss": 0.9624,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 2.27,
2397
+ "learning_rate": 7.821363359027048e-05,
2398
+ "loss": 0.9623,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 2.27,
2403
+ "learning_rate": 7.774790660436858e-05,
2404
+ "loss": 0.9155,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 2.28,
2409
+ "learning_rate": 7.728268686373814e-05,
2410
+ "loss": 1.0116,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 2.28,
2415
+ "learning_rate": 7.681798497324716e-05,
2416
+ "loss": 0.9035,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 2.29,
2421
+ "learning_rate": 7.635381152595915e-05,
2422
+ "loss": 0.9018,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 2.3,
2427
+ "learning_rate": 7.589017710289139e-05,
2428
+ "loss": 1.0231,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 2.3,
2433
+ "learning_rate": 7.542709227277396e-05,
2434
+ "loss": 0.9325,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 2.31,
2439
+ "learning_rate": 7.496456759180875e-05,
2440
+ "loss": 1.0224,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 2.31,
2445
+ "learning_rate": 7.450261360342888e-05,
2446
+ "loss": 0.9142,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 2.32,
2451
+ "learning_rate": 7.404124083805819e-05,
2452
+ "loss": 0.9583,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 2.33,
2457
+ "learning_rate": 7.358045981287141e-05,
2458
+ "loss": 1.007,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 2.33,
2463
+ "learning_rate": 7.312028103155426e-05,
2464
+ "loss": 0.8724,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 2.34,
2469
+ "learning_rate": 7.266071498406417e-05,
2470
+ "loss": 0.8942,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 2.34,
2475
+ "learning_rate": 7.220177214639088e-05,
2476
+ "loss": 0.9398,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 2.35,
2481
+ "learning_rate": 7.174346298031804e-05,
2482
+ "loss": 0.8393,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 2.36,
2487
+ "learning_rate": 7.128579793318428e-05,
2488
+ "loss": 0.9286,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 2.36,
2493
+ "learning_rate": 7.082878743764545e-05,
2494
+ "loss": 0.924,
2495
+ "step": 401
2496
+ },
2497
+ {
2498
+ "epoch": 2.37,
2499
+ "learning_rate": 7.037244191143661e-05,
2500
+ "loss": 0.96,
2501
+ "step": 402
2502
+ },
2503
+ {
2504
+ "epoch": 2.37,
2505
+ "learning_rate": 6.991677175713449e-05,
2506
+ "loss": 0.9981,
2507
+ "step": 403
2508
+ },
2509
+ {
2510
+ "epoch": 2.38,
2511
+ "learning_rate": 6.946178736192053e-05,
2512
+ "loss": 1.0843,
2513
+ "step": 404
2514
+ },
2515
+ {
2516
+ "epoch": 2.39,
2517
+ "learning_rate": 6.900749909734406e-05,
2518
+ "loss": 0.9198,
2519
+ "step": 405
2520
+ },
2521
+ {
2522
+ "epoch": 2.39,
2523
+ "learning_rate": 6.855391731908567e-05,
2524
+ "loss": 0.9537,
2525
+ "step": 406
2526
+ },
2527
+ {
2528
+ "epoch": 2.4,
2529
+ "learning_rate": 6.810105236672155e-05,
2530
+ "loss": 0.9219,
2531
+ "step": 407
2532
+ },
2533
+ {
2534
+ "epoch": 2.4,
2535
+ "learning_rate": 6.764891456348729e-05,
2536
+ "loss": 0.963,
2537
+ "step": 408
2538
+ },
2539
+ {
2540
+ "epoch": 2.41,
2541
+ "learning_rate": 6.719751421604309e-05,
2542
+ "loss": 1.0003,
2543
+ "step": 409
2544
+ },
2545
+ {
2546
+ "epoch": 2.41,
2547
+ "learning_rate": 6.674686161423843e-05,
2548
+ "loss": 1.0074,
2549
+ "step": 410
2550
+ },
2551
+ {
2552
+ "epoch": 2.42,
2553
+ "learning_rate": 6.629696703087754e-05,
2554
+ "loss": 1.0361,
2555
+ "step": 411
2556
+ },
2557
+ {
2558
+ "epoch": 2.43,
2559
+ "learning_rate": 6.584784072148555e-05,
2560
+ "loss": 0.9224,
2561
+ "step": 412
2562
+ },
2563
+ {
2564
+ "epoch": 2.43,
2565
+ "learning_rate": 6.539949292407421e-05,
2566
+ "loss": 0.9658,
2567
+ "step": 413
2568
+ },
2569
+ {
2570
+ "epoch": 2.44,
2571
+ "learning_rate": 6.495193385890901e-05,
2572
+ "loss": 1.0963,
2573
+ "step": 414
2574
+ },
2575
+ {
2576
+ "epoch": 2.44,
2577
+ "learning_rate": 6.450517372827591e-05,
2578
+ "loss": 1.0044,
2579
+ "step": 415
2580
+ },
2581
+ {
2582
+ "epoch": 2.45,
2583
+ "learning_rate": 6.405922271624874e-05,
2584
+ "loss": 0.998,
2585
+ "step": 416
2586
+ },
2587
+ {
2588
+ "epoch": 2.46,
2589
+ "learning_rate": 6.361409098845725e-05,
2590
+ "loss": 0.8947,
2591
+ "step": 417
2592
+ },
2593
+ {
2594
+ "epoch": 2.46,
2595
+ "learning_rate": 6.316978869185532e-05,
2596
+ "loss": 1.057,
2597
+ "step": 418
2598
+ },
2599
+ {
2600
+ "epoch": 2.47,
2601
+ "learning_rate": 6.272632595448947e-05,
2602
+ "loss": 1.0015,
2603
+ "step": 419
2604
+ },
2605
+ {
2606
+ "epoch": 2.47,
2607
+ "learning_rate": 6.22837128852683e-05,
2608
+ "loss": 0.8845,
2609
+ "step": 420
2610
+ },
2611
+ {
2612
+ "epoch": 2.47,
2613
+ "eval_loss": 0.7409489750862122,
2614
+ "eval_runtime": 14.4788,
2615
+ "eval_samples_per_second": 56.566,
2616
+ "eval_steps_per_second": 28.317,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 2.48,
2621
+ "learning_rate": 6.184195957373176e-05,
2622
+ "loss": 0.8122,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 2.49,
2627
+ "learning_rate": 6.140107608982136e-05,
2628
+ "loss": 0.984,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 2.49,
2633
+ "learning_rate": 6.0961072483650526e-05,
2634
+ "loss": 1.065,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 2.5,
2639
+ "learning_rate": 6.05219587852755e-05,
2640
+ "loss": 0.9648,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 2.5,
2645
+ "learning_rate": 6.008374500446676e-05,
2646
+ "loss": 0.9267,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 2.51,
2651
+ "learning_rate": 5.964644113048079e-05,
2652
+ "loss": 0.9327,
2653
+ "step": 426
2654
+ },
2655
+ {
2656
+ "epoch": 2.52,
2657
+ "learning_rate": 5.921005713183235e-05,
2658
+ "loss": 0.9545,
2659
+ "step": 427
2660
+ },
2661
+ {
2662
+ "epoch": 2.52,
2663
+ "learning_rate": 5.877460295606738e-05,
2664
+ "loss": 0.8972,
2665
+ "step": 428
2666
+ },
2667
+ {
2668
+ "epoch": 2.53,
2669
+ "learning_rate": 5.834008852953603e-05,
2670
+ "loss": 0.9857,
2671
+ "step": 429
2672
+ },
2673
+ {
2674
+ "epoch": 2.53,
2675
+ "learning_rate": 5.790652375716652e-05,
2676
+ "loss": 0.9189,
2677
+ "step": 430
2678
+ },
2679
+ {
2680
+ "epoch": 2.54,
2681
+ "learning_rate": 5.74739185222394e-05,
2682
+ "loss": 0.8486,
2683
+ "step": 431
2684
+ },
2685
+ {
2686
+ "epoch": 2.55,
2687
+ "learning_rate": 5.704228268616208e-05,
2688
+ "loss": 0.9442,
2689
+ "step": 432
2690
+ },
2691
+ {
2692
+ "epoch": 2.55,
2693
+ "learning_rate": 5.6611626088244194e-05,
2694
+ "loss": 0.9095,
2695
+ "step": 433
2696
+ },
2697
+ {
2698
+ "epoch": 2.56,
2699
+ "learning_rate": 5.6181958545473325e-05,
2700
+ "loss": 1.0581,
2701
+ "step": 434
2702
+ },
2703
+ {
2704
+ "epoch": 2.56,
2705
+ "learning_rate": 5.575328985229098e-05,
2706
+ "loss": 0.8151,
2707
+ "step": 435
2708
+ },
2709
+ {
2710
+ "epoch": 2.57,
2711
+ "learning_rate": 5.5325629780369635e-05,
2712
+ "loss": 0.8941,
2713
+ "step": 436
2714
+ },
2715
+ {
2716
+ "epoch": 2.58,
2717
+ "learning_rate": 5.48989880783898e-05,
2718
+ "loss": 0.9767,
2719
+ "step": 437
2720
+ },
2721
+ {
2722
+ "epoch": 2.58,
2723
+ "learning_rate": 5.4473374471817906e-05,
2724
+ "loss": 0.8874,
2725
+ "step": 438
2726
+ },
2727
+ {
2728
+ "epoch": 2.59,
2729
+ "learning_rate": 5.4048798662684376e-05,
2730
+ "loss": 0.8578,
2731
+ "step": 439
2732
+ },
2733
+ {
2734
+ "epoch": 2.59,
2735
+ "learning_rate": 5.362527032936277e-05,
2736
+ "loss": 0.9191,
2737
+ "step": 440
2738
+ },
2739
+ {
2740
+ "epoch": 2.6,
2741
+ "learning_rate": 5.320279912634907e-05,
2742
+ "loss": 0.7622,
2743
+ "step": 441
2744
+ },
2745
+ {
2746
+ "epoch": 2.61,
2747
+ "learning_rate": 5.278139468404133e-05,
2748
+ "loss": 0.9143,
2749
+ "step": 442
2750
+ },
2751
+ {
2752
+ "epoch": 2.61,
2753
+ "learning_rate": 5.236106660852058e-05,
2754
+ "loss": 0.9184,
2755
+ "step": 443
2756
+ },
2757
+ {
2758
+ "epoch": 2.62,
2759
+ "learning_rate": 5.1941824481331626e-05,
2760
+ "loss": 0.9776,
2761
+ "step": 444
2762
+ },
2763
+ {
2764
+ "epoch": 2.62,
2765
+ "learning_rate": 5.1523677859264516e-05,
2766
+ "loss": 0.9989,
2767
+ "step": 445
2768
+ },
2769
+ {
2770
+ "epoch": 2.63,
2771
+ "learning_rate": 5.110663627413694e-05,
2772
+ "loss": 0.8539,
2773
+ "step": 446
2774
+ },
2775
+ {
2776
+ "epoch": 2.64,
2777
+ "learning_rate": 5.069070923257685e-05,
2778
+ "loss": 1.0078,
2779
+ "step": 447
2780
+ },
2781
+ {
2782
+ "epoch": 2.64,
2783
+ "learning_rate": 5.0275906215805625e-05,
2784
+ "loss": 0.9395,
2785
+ "step": 448
2786
+ },
2787
+ {
2788
+ "epoch": 2.65,
2789
+ "learning_rate": 4.986223667942214e-05,
2790
+ "loss": 0.7978,
2791
+ "step": 449
2792
+ },
2793
+ {
2794
+ "epoch": 2.65,
2795
+ "learning_rate": 4.944971005318716e-05,
2796
+ "loss": 0.9456,
2797
+ "step": 450
2798
+ },
2799
+ {
2800
+ "epoch": 2.66,
2801
+ "learning_rate": 4.903833574080825e-05,
2802
+ "loss": 0.991,
2803
+ "step": 451
2804
+ },
2805
+ {
2806
+ "epoch": 2.67,
2807
+ "learning_rate": 4.862812311972567e-05,
2808
+ "loss": 0.8867,
2809
+ "step": 452
2810
+ },
2811
+ {
2812
+ "epoch": 2.67,
2813
+ "learning_rate": 4.8219081540898295e-05,
2814
+ "loss": 0.9519,
2815
+ "step": 453
2816
+ },
2817
+ {
2818
+ "epoch": 2.68,
2819
+ "learning_rate": 4.781122032859079e-05,
2820
+ "loss": 0.8153,
2821
+ "step": 454
2822
+ },
2823
+ {
2824
+ "epoch": 2.68,
2825
+ "learning_rate": 4.740454878016084e-05,
2826
+ "loss": 0.8457,
2827
+ "step": 455
2828
+ },
2829
+ {
2830
+ "epoch": 2.69,
2831
+ "learning_rate": 4.699907616584721e-05,
2832
+ "loss": 0.9878,
2833
+ "step": 456
2834
+ },
2835
+ {
2836
+ "epoch": 2.7,
2837
+ "learning_rate": 4.6594811728558584e-05,
2838
+ "loss": 0.9616,
2839
+ "step": 457
2840
+ },
2841
+ {
2842
+ "epoch": 2.7,
2843
+ "learning_rate": 4.6191764683662744e-05,
2844
+ "loss": 0.8892,
2845
+ "step": 458
2846
+ },
2847
+ {
2848
+ "epoch": 2.71,
2849
+ "learning_rate": 4.578994421877645e-05,
2850
+ "loss": 0.8593,
2851
+ "step": 459
2852
+ },
2853
+ {
2854
+ "epoch": 2.71,
2855
+ "learning_rate": 4.538935949355623e-05,
2856
+ "loss": 0.8618,
2857
+ "step": 460
2858
+ },
2859
+ {
2860
+ "epoch": 2.72,
2861
+ "learning_rate": 4.499001963948929e-05,
2862
+ "loss": 1.0498,
2863
+ "step": 461
2864
+ },
2865
+ {
2866
+ "epoch": 2.73,
2867
+ "learning_rate": 4.45919337596856e-05,
2868
+ "loss": 1.0198,
2869
+ "step": 462
2870
+ },
2871
+ {
2872
+ "epoch": 2.73,
2873
+ "eval_loss": 0.7379047870635986,
2874
+ "eval_runtime": 14.5017,
2875
+ "eval_samples_per_second": 56.476,
2876
+ "eval_steps_per_second": 28.273,
2877
+ "step": 462
2878
+ },
2879
+ {
2880
+ "epoch": 2.73,
2881
+ "learning_rate": 4.41951109286703e-05,
2882
+ "loss": 0.8737,
2883
+ "step": 463
2884
+ },
2885
+ {
2886
+ "epoch": 2.74,
2887
+ "learning_rate": 4.379956019217675e-05,
2888
+ "loss": 0.8282,
2889
+ "step": 464
2890
+ },
2891
+ {
2892
+ "epoch": 2.74,
2893
+ "learning_rate": 4.340529056694047e-05,
2894
+ "loss": 0.8425,
2895
+ "step": 465
2896
+ },
2897
+ {
2898
+ "epoch": 2.75,
2899
+ "learning_rate": 4.3012311040493594e-05,
2900
+ "loss": 0.8594,
2901
+ "step": 466
2902
+ },
2903
+ {
2904
+ "epoch": 2.76,
2905
+ "learning_rate": 4.2620630570959775e-05,
2906
+ "loss": 1.0157,
2907
+ "step": 467
2908
+ },
2909
+ {
2910
+ "epoch": 2.76,
2911
+ "learning_rate": 4.2230258086850374e-05,
2912
+ "loss": 1.0247,
2913
+ "step": 468
2914
+ },
2915
+ {
2916
+ "epoch": 2.77,
2917
+ "learning_rate": 4.184120248686048e-05,
2918
+ "loss": 0.956,
2919
+ "step": 469
2920
+ },
2921
+ {
2922
+ "epoch": 2.77,
2923
+ "learning_rate": 4.1453472639666457e-05,
2924
+ "loss": 0.9221,
2925
+ "step": 470
2926
+ },
2927
+ {
2928
+ "epoch": 2.78,
2929
+ "learning_rate": 4.106707738372357e-05,
2930
+ "loss": 0.8249,
2931
+ "step": 471
2932
+ },
2933
+ {
2934
+ "epoch": 2.79,
2935
+ "learning_rate": 4.0682025527064486e-05,
2936
+ "loss": 0.9179,
2937
+ "step": 472
2938
+ },
2939
+ {
2940
+ "epoch": 2.79,
2941
+ "learning_rate": 4.029832584709864e-05,
2942
+ "loss": 1.0457,
2943
+ "step": 473
2944
+ },
2945
+ {
2946
+ "epoch": 2.8,
2947
+ "learning_rate": 3.991598709041196e-05,
2948
+ "loss": 0.8553,
2949
+ "step": 474
2950
+ },
2951
+ {
2952
+ "epoch": 2.8,
2953
+ "learning_rate": 3.9535017972567675e-05,
2954
+ "loss": 0.8563,
2955
+ "step": 475
2956
+ },
2957
+ {
2958
+ "epoch": 2.81,
2959
+ "learning_rate": 3.915542717790759e-05,
2960
+ "loss": 0.9828,
2961
+ "step": 476
2962
+ },
2963
+ {
2964
+ "epoch": 2.81,
2965
+ "learning_rate": 3.877722335935394e-05,
2966
+ "loss": 0.9853,
2967
+ "step": 477
2968
+ },
2969
+ {
2970
+ "epoch": 2.82,
2971
+ "learning_rate": 3.840041513821243e-05,
2972
+ "loss": 0.9801,
2973
+ "step": 478
2974
+ },
2975
+ {
2976
+ "epoch": 2.83,
2977
+ "learning_rate": 3.802501110397553e-05,
2978
+ "loss": 0.8679,
2979
+ "step": 479
2980
+ },
2981
+ {
2982
+ "epoch": 2.83,
2983
+ "learning_rate": 3.7651019814126654e-05,
2984
+ "loss": 0.8846,
2985
+ "step": 480
2986
+ },
2987
+ {
2988
+ "epoch": 2.84,
2989
+ "learning_rate": 3.727844979394526e-05,
2990
+ "loss": 0.8068,
2991
+ "step": 481
2992
+ },
2993
+ {
2994
+ "epoch": 2.84,
2995
+ "learning_rate": 3.6907309536312276e-05,
2996
+ "loss": 0.8033,
2997
+ "step": 482
2998
+ },
2999
+ {
3000
+ "epoch": 2.85,
3001
+ "learning_rate": 3.6537607501516715e-05,
3002
+ "loss": 0.9402,
3003
+ "step": 483
3004
+ },
3005
+ {
3006
+ "epoch": 2.86,
3007
+ "learning_rate": 3.616935211706275e-05,
3008
+ "loss": 0.8132,
3009
+ "step": 484
3010
+ },
3011
+ {
3012
+ "epoch": 2.86,
3013
+ "learning_rate": 3.5802551777477476e-05,
3014
+ "loss": 0.8682,
3015
+ "step": 485
3016
+ },
3017
+ {
3018
+ "epoch": 2.87,
3019
+ "learning_rate": 3.543721484411976e-05,
3020
+ "loss": 0.9198,
3021
+ "step": 486
3022
+ },
3023
+ {
3024
+ "epoch": 2.87,
3025
+ "learning_rate": 3.5073349644989564e-05,
3026
+ "loss": 0.958,
3027
+ "step": 487
3028
+ },
3029
+ {
3030
+ "epoch": 2.88,
3031
+ "learning_rate": 3.4710964474537966e-05,
3032
+ "loss": 0.8973,
3033
+ "step": 488
3034
+ },
3035
+ {
3036
+ "epoch": 2.89,
3037
+ "learning_rate": 3.4350067593478356e-05,
3038
+ "loss": 1.0462,
3039
+ "step": 489
3040
+ },
3041
+ {
3042
+ "epoch": 2.89,
3043
+ "learning_rate": 3.399066722859782e-05,
3044
+ "loss": 0.9042,
3045
+ "step": 490
3046
+ },
3047
+ {
3048
+ "epoch": 2.9,
3049
+ "learning_rate": 3.363277157256988e-05,
3050
+ "loss": 0.9075,
3051
+ "step": 491
3052
+ },
3053
+ {
3054
+ "epoch": 2.9,
3055
+ "learning_rate": 3.327638878376764e-05,
3056
+ "loss": 1.0444,
3057
+ "step": 492
3058
+ },
3059
+ {
3060
+ "epoch": 2.91,
3061
+ "learning_rate": 3.292152698607768e-05,
3062
+ "loss": 0.9098,
3063
+ "step": 493
3064
+ },
3065
+ {
3066
+ "epoch": 2.92,
3067
+ "learning_rate": 3.256819426871507e-05,
3068
+ "loss": 1.0037,
3069
+ "step": 494
3070
+ },
3071
+ {
3072
+ "epoch": 2.92,
3073
+ "learning_rate": 3.2216398686038926e-05,
3074
+ "loss": 0.8278,
3075
+ "step": 495
3076
+ },
3077
+ {
3078
+ "epoch": 2.93,
3079
+ "learning_rate": 3.1866148257368665e-05,
3080
+ "loss": 0.9869,
3081
+ "step": 496
3082
+ },
3083
+ {
3084
+ "epoch": 2.93,
3085
+ "learning_rate": 3.15174509668014e-05,
3086
+ "loss": 0.8511,
3087
+ "step": 497
3088
+ },
3089
+ {
3090
+ "epoch": 2.94,
3091
+ "learning_rate": 3.117031476302975e-05,
3092
+ "loss": 0.9983,
3093
+ "step": 498
3094
+ },
3095
+ {
3096
+ "epoch": 2.95,
3097
+ "learning_rate": 3.0824747559160836e-05,
3098
+ "loss": 1.0146,
3099
+ "step": 499
3100
+ },
3101
+ {
3102
+ "epoch": 2.95,
3103
+ "learning_rate": 3.0480757232535772e-05,
3104
+ "loss": 0.9705,
3105
+ "step": 500
3106
+ },
3107
+ {
3108
+ "epoch": 2.96,
3109
+ "learning_rate": 3.0138351624550164e-05,
3110
+ "loss": 0.8197,
3111
+ "step": 501
3112
+ }
3113
+ ],
3114
+ "logging_steps": 1,
3115
+ "max_steps": 668,
3116
+ "num_input_tokens_seen": 0,
3117
+ "num_train_epochs": 4,
3118
+ "save_steps": 167,
3119
+ "total_flos": 1.043593588459438e+17,
3120
+ "train_batch_size": 2,
3121
+ "trial_name": null,
3122
+ "trial_params": null
3123
+ }
checkpoint-501/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14298be73cbe854ab00522590054d32e49c4c47f917719c135f6380025fd0
3
+ size 5368
checkpoint-668/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-668/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
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
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-668/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f4bdefa61a955b43bbc39aaf4edf834185672fb7550e1fb6db17e058178d2a
3
+ size 100966336
checkpoint-668/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cacfe3a206e98ee101084db2dfae5d9eae3dc2e6f2288aab3841a8399a17b8
3
+ size 50916964
checkpoint-668/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c62ed1a44e900b6c1c4f4b029ea37151bbf14ddcab88a6d308837483705fd5
3
+ size 14244
checkpoint-668/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2c7c2e5e78cc114204116b8b4269020ac7cb07c33c09b9fd519e64ff54a38b
3
+ size 1064
checkpoint-668/trainer_state.json ADDED
@@ -0,0 +1,4157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.937313432835821,
5
+ "eval_steps": 42,
6
+ "global_step": 668,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.6541,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 1.7634071111679077,
20
+ "eval_runtime": 14.5059,
21
+ "eval_samples_per_second": 56.46,
22
+ "eval_steps_per_second": 28.264,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 4e-05,
28
+ "loss": 1.6887,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 6e-05,
34
+ "loss": 1.828,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 8e-05,
40
+ "loss": 1.589,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.0001,
46
+ "loss": 1.927,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00012,
52
+ "loss": 1.6362,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00014,
58
+ "loss": 1.8546,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.5843,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "learning_rate": 0.00018,
70
+ "loss": 1.5592,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0002,
76
+ "loss": 1.5539,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.0001999988602302209,
82
+ "loss": 1.4449,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0001999954409468652,
88
+ "loss": 1.8818,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.0001999897422278767,
94
+ "loss": 1.6656,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.08,
99
+ "learning_rate": 0.00019998176420316002,
100
+ "loss": 1.4607,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0001999715070545774,
106
+ "loss": 1.4013,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00019995897101594454,
112
+ "loss": 1.5258,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.1,
117
+ "learning_rate": 0.00019994415637302547,
118
+ "loss": 1.404,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.00019992706346352577,
124
+ "loss": 1.3919,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.11,
129
+ "learning_rate": 0.00019990769267708516,
130
+ "loss": 1.355,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.00019988604445526827,
136
+ "loss": 1.3763,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.000199862119291555,
142
+ "loss": 1.3314,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.13,
147
+ "learning_rate": 0.00019983591773132882,
148
+ "loss": 1.4246,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.00019980744037186469,
154
+ "loss": 1.5723,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.14,
159
+ "learning_rate": 0.00019977668786231534,
160
+ "loss": 1.2536,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.15,
165
+ "learning_rate": 0.0001997436609036963,
166
+ "loss": 1.3087,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.0001997083602488702,
172
+ "loss": 1.2783,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.16,
177
+ "learning_rate": 0.00019967078670252945,
178
+ "loss": 1.2792,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00019963094112117785,
184
+ "loss": 1.2476,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.17,
189
+ "learning_rate": 0.00019958882441311126,
190
+ "loss": 1.265,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.18,
195
+ "learning_rate": 0.00019954443753839667,
196
+ "loss": 1.0884,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00019949778150885042,
202
+ "loss": 1.3294,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.19,
207
+ "learning_rate": 0.00019944885738801518,
208
+ "loss": 1.3434,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.2,
213
+ "learning_rate": 0.00019939766629113566,
214
+ "loss": 1.1457,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.2,
219
+ "learning_rate": 0.00019934420938513313,
220
+ "loss": 1.2138,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.21,
225
+ "learning_rate": 0.00019928848788857887,
226
+ "loss": 1.2118,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.21,
231
+ "learning_rate": 0.00019923050307166655,
232
+ "loss": 1.1426,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.22,
237
+ "learning_rate": 0.00019917025625618292,
238
+ "loss": 1.6279,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.23,
243
+ "learning_rate": 0.000199107748815478,
244
+ "loss": 1.5021,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.23,
249
+ "learning_rate": 0.00019904298217443366,
250
+ "loss": 1.3728,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.24,
255
+ "learning_rate": 0.00019897595780943102,
256
+ "loss": 1.2034,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.24,
261
+ "learning_rate": 0.00019890667724831707,
262
+ "loss": 1.3718,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.25,
267
+ "learning_rate": 0.00019883514207036956,
268
+ "loss": 1.2512,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.25,
273
+ "eval_loss": 0.8978323936462402,
274
+ "eval_runtime": 14.6352,
275
+ "eval_samples_per_second": 55.961,
276
+ "eval_steps_per_second": 28.015,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.26,
281
+ "learning_rate": 0.00019876135390626122,
282
+ "loss": 1.1787,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.26,
287
+ "learning_rate": 0.0001986853144380224,
288
+ "loss": 1.1917,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.27,
293
+ "learning_rate": 0.00019860702539900287,
294
+ "loss": 1.1933,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.27,
299
+ "learning_rate": 0.00019852648857383222,
300
+ "loss": 1.1922,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.28,
305
+ "learning_rate": 0.00019844370579837927,
306
+ "loss": 1.3017,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.29,
311
+ "learning_rate": 0.00019835867895971014,
312
+ "loss": 1.1193,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.29,
317
+ "learning_rate": 0.0001982714099960452,
318
+ "loss": 1.1572,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.3,
323
+ "learning_rate": 0.00019818190089671508,
324
+ "loss": 1.3277,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.3,
329
+ "learning_rate": 0.00019809015370211502,
330
+ "loss": 1.0658,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.31,
335
+ "learning_rate": 0.0001979961705036587,
336
+ "loss": 1.1656,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.32,
341
+ "learning_rate": 0.00019789995344373024,
342
+ "loss": 1.4204,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.32,
347
+ "learning_rate": 0.00019780150471563558,
348
+ "loss": 1.1551,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.33,
353
+ "learning_rate": 0.0001977008265635525,
354
+ "loss": 1.0993,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.33,
359
+ "learning_rate": 0.00019759792128247922,
360
+ "loss": 1.1311,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.34,
365
+ "learning_rate": 0.00019749279121818235,
366
+ "loss": 1.2163,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.35,
371
+ "learning_rate": 0.00019738543876714334,
372
+ "loss": 1.3178,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.35,
377
+ "learning_rate": 0.00019727586637650373,
378
+ "loss": 1.3744,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.36,
383
+ "learning_rate": 0.00019716407654400952,
384
+ "loss": 1.1413,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.36,
389
+ "learning_rate": 0.00019705007181795416,
390
+ "loss": 1.0372,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.37,
395
+ "learning_rate": 0.00019693385479712048,
396
+ "loss": 1.1601,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.38,
401
+ "learning_rate": 0.00019681542813072145,
402
+ "loss": 1.0976,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.38,
407
+ "learning_rate": 0.00019669479451833976,
408
+ "loss": 1.1584,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.39,
413
+ "learning_rate": 0.00019657195670986637,
414
+ "loss": 1.0962,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.39,
419
+ "learning_rate": 0.00019644691750543767,
420
+ "loss": 1.1044,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.4,
425
+ "learning_rate": 0.0001963196797553718,
426
+ "loss": 1.2431,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.41,
431
+ "learning_rate": 0.00019619024636010363,
432
+ "loss": 1.1651,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.41,
437
+ "learning_rate": 0.00019605862027011856,
438
+ "loss": 1.0513,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.42,
443
+ "learning_rate": 0.00019592480448588542,
444
+ "loss": 1.0175,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.42,
449
+ "learning_rate": 0.00019578880205778793,
450
+ "loss": 1.1306,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.43,
455
+ "learning_rate": 0.00019565061608605526,
456
+ "loss": 1.3121,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.44,
461
+ "learning_rate": 0.00019551024972069126,
462
+ "loss": 1.266,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.44,
467
+ "learning_rate": 0.00019536770616140276,
468
+ "loss": 1.1099,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.45,
473
+ "learning_rate": 0.0001952229886575266,
474
+ "loss": 1.1012,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.45,
479
+ "learning_rate": 0.00019507610050795558,
480
+ "loss": 1.1272,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.46,
485
+ "learning_rate": 0.0001949270450610631,
486
+ "loss": 1.2016,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.47,
491
+ "learning_rate": 0.00019477582571462705,
492
+ "loss": 1.1746,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.47,
497
+ "learning_rate": 0.00019462244591575222,
498
+ "loss": 1.1349,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.48,
503
+ "learning_rate": 0.0001944669091607919,
504
+ "loss": 1.4311,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.48,
509
+ "learning_rate": 0.00019430921899526787,
510
+ "loss": 1.1033,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.49,
515
+ "learning_rate": 0.00019414937901378982,
516
+ "loss": 1.2491,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.5,
521
+ "learning_rate": 0.0001939873928599734,
522
+ "loss": 1.1044,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.5,
527
+ "learning_rate": 0.00019382326422635705,
528
+ "loss": 1.1008,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.5,
533
+ "eval_loss": 0.8307072520256042,
534
+ "eval_runtime": 14.6668,
535
+ "eval_samples_per_second": 55.841,
536
+ "eval_steps_per_second": 27.954,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 0.0001936569968543179,
542
+ "loss": 1.2317,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 0.00019348859453398646,
548
+ "loss": 1.2317,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 0.00019331806110416027,
554
+ "loss": 1.0989,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.53,
559
+ "learning_rate": 0.00019314540045221626,
560
+ "loss": 1.0466,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 0.00019297061651402236,
566
+ "loss": 1.0798,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 0.0001927937132738476,
572
+ "loss": 1.1175,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 0.0001926146947642712,
578
+ "loss": 1.1292,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 0.000192433565066091,
584
+ "loss": 1.0464,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.56,
589
+ "learning_rate": 0.00019225032830823011,
590
+ "loss": 1.1549,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 0.00019206498866764288,
596
+ "loss": 1.1129,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.57,
601
+ "learning_rate": 0.00019187755036921978,
602
+ "loss": 0.9965,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 0.0001916880176856909,
608
+ "loss": 1.0767,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 0.0001914963949375288,
614
+ "loss": 1.1546,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.59,
619
+ "learning_rate": 0.0001913026864928498,
620
+ "loss": 0.9627,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 0.00019110689676731454,
626
+ "loss": 1.0039,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.6,
631
+ "learning_rate": 0.00019090903022402729,
632
+ "loss": 1.066,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 0.00019070909137343408,
638
+ "loss": 1.0654,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.61,
643
+ "learning_rate": 0.00019050708477322018,
644
+ "loss": 1.3323,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 0.00019030301502820596,
650
+ "loss": 1.1247,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.62,
655
+ "learning_rate": 0.0001900968867902419,
656
+ "loss": 1.0261,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.63,
661
+ "learning_rate": 0.00018988870475810282,
662
+ "loss": 1.0935,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 0.00018967847367738048,
668
+ "loss": 1.1043,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.64,
673
+ "learning_rate": 0.00018946619834037546,
674
+ "loss": 1.1982,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 0.00018925188358598813,
680
+ "loss": 1.0445,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.65,
685
+ "learning_rate": 0.00018903553429960802,
686
+ "loss": 1.086,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.66,
691
+ "learning_rate": 0.00018881715541300276,
692
+ "loss": 1.1509,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.66,
697
+ "learning_rate": 0.00018859675190420537,
698
+ "loss": 1.1473,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.67,
703
+ "learning_rate": 0.00018837432879740114,
704
+ "loss": 1.1677,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 0.0001881498911628127,
710
+ "loss": 1.006,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.68,
715
+ "learning_rate": 0.00018792344411658468,
716
+ "loss": 1.0503,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.69,
721
+ "learning_rate": 0.00018769499282066717,
722
+ "loss": 1.163,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.69,
727
+ "learning_rate": 0.00018746454248269777,
728
+ "loss": 1.1443,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.7,
733
+ "learning_rate": 0.0001872320983558831,
734
+ "loss": 0.9785,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.7,
739
+ "learning_rate": 0.000186997665738879,
740
+ "loss": 1.0605,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.71,
745
+ "learning_rate": 0.0001867612499756697,
746
+ "loss": 1.0203,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.72,
751
+ "learning_rate": 0.00018652285645544603,
752
+ "loss": 1.146,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.72,
757
+ "learning_rate": 0.00018628249061248262,
758
+ "loss": 1.12,
759
+ "step": 121
760
+ },
761
+ {
762
+ "epoch": 0.73,
763
+ "learning_rate": 0.00018604015792601396,
764
+ "loss": 1.1499,
765
+ "step": 122
766
+ },
767
+ {
768
+ "epoch": 0.73,
769
+ "learning_rate": 0.00018579586392010943,
770
+ "loss": 1.1273,
771
+ "step": 123
772
+ },
773
+ {
774
+ "epoch": 0.74,
775
+ "learning_rate": 0.0001855496141635476,
776
+ "loss": 1.0404,
777
+ "step": 124
778
+ },
779
+ {
780
+ "epoch": 0.75,
781
+ "learning_rate": 0.00018530141426968902,
782
+ "loss": 1.1066,
783
+ "step": 125
784
+ },
785
+ {
786
+ "epoch": 0.75,
787
+ "learning_rate": 0.0001850512698963485,
788
+ "loss": 1.0685,
789
+ "step": 126
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "eval_loss": 0.8026405572891235,
794
+ "eval_runtime": 14.5968,
795
+ "eval_samples_per_second": 56.108,
796
+ "eval_steps_per_second": 28.088,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.76,
801
+ "learning_rate": 0.000184799186745666,
802
+ "loss": 1.0494,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.76,
807
+ "learning_rate": 0.00018454517056397661,
808
+ "loss": 1.1905,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.77,
813
+ "learning_rate": 0.0001842892271416797,
814
+ "loss": 1.2034,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.78,
819
+ "learning_rate": 0.00018403136231310684,
820
+ "loss": 1.2088,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.78,
825
+ "learning_rate": 0.00018377158195638876,
826
+ "loss": 0.9303,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.79,
831
+ "learning_rate": 0.00018350989199332154,
832
+ "loss": 1.1574,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.79,
837
+ "learning_rate": 0.00018324629838923132,
838
+ "loss": 1.1673,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.8,
843
+ "learning_rate": 0.00018298080715283858,
844
+ "loss": 1.1204,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.81,
849
+ "learning_rate": 0.00018271342433612113,
850
+ "loss": 1.0752,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.81,
855
+ "learning_rate": 0.00018244415603417603,
856
+ "loss": 1.0121,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.82,
861
+ "learning_rate": 0.00018217300838508073,
862
+ "loss": 1.0975,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.82,
867
+ "learning_rate": 0.00018189998756975318,
868
+ "loss": 0.9982,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.83,
873
+ "learning_rate": 0.00018162509981181084,
874
+ "loss": 1.1922,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.84,
879
+ "learning_rate": 0.0001813483513774289,
880
+ "loss": 0.9532,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.84,
885
+ "learning_rate": 0.00018106974857519736,
886
+ "loss": 1.0813,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.85,
891
+ "learning_rate": 0.0001807892977559774,
892
+ "loss": 0.9656,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.85,
897
+ "learning_rate": 0.0001805070053127563,
898
+ "loss": 1.1161,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.86,
903
+ "learning_rate": 0.00018022287768050202,
904
+ "loss": 1.0143,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.87,
909
+ "learning_rate": 0.0001799369213360163,
910
+ "loss": 1.1242,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.87,
915
+ "learning_rate": 0.00017964914279778715,
916
+ "loss": 1.0747,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.88,
921
+ "learning_rate": 0.00017935954862584018,
922
+ "loss": 1.1551,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.88,
927
+ "learning_rate": 0.0001790681454215891,
928
+ "loss": 0.9538,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.89,
933
+ "learning_rate": 0.00017877493982768527,
934
+ "loss": 1.0621,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.9,
939
+ "learning_rate": 0.0001784799385278661,
940
+ "loss": 1.0229,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.9,
945
+ "learning_rate": 0.000178183148246803,
946
+ "loss": 0.9991,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.91,
951
+ "learning_rate": 0.00017788457574994778,
952
+ "loss": 1.0045,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.91,
957
+ "learning_rate": 0.00017758422784337863,
958
+ "loss": 1.0675,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.92,
963
+ "learning_rate": 0.00017728211137364489,
964
+ "loss": 0.962,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.93,
969
+ "learning_rate": 0.000176978233227611,
970
+ "loss": 1.0145,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.93,
975
+ "learning_rate": 0.00017667260033229953,
976
+ "loss": 0.9576,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.94,
981
+ "learning_rate": 0.00017636521965473323,
982
+ "loss": 1.0692,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.94,
987
+ "learning_rate": 0.00017605609820177617,
988
+ "loss": 1.2074,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.95,
993
+ "learning_rate": 0.00017574524301997423,
994
+ "loss": 1.1489,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 0.96,
999
+ "learning_rate": 0.00017543266119539422,
1000
+ "loss": 0.9962,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 0.96,
1005
+ "learning_rate": 0.00017511835985346253,
1006
+ "loss": 0.8922,
1007
+ "step": 161
1008
+ },
1009
+ {
1010
+ "epoch": 0.97,
1011
+ "learning_rate": 0.00017480234615880247,
1012
+ "loss": 0.9248,
1013
+ "step": 162
1014
+ },
1015
+ {
1016
+ "epoch": 0.97,
1017
+ "learning_rate": 0.0001744846273150713,
1018
+ "loss": 1.1621,
1019
+ "step": 163
1020
+ },
1021
+ {
1022
+ "epoch": 0.98,
1023
+ "learning_rate": 0.00017416521056479577,
1024
+ "loss": 1.0516,
1025
+ "step": 164
1026
+ },
1027
+ {
1028
+ "epoch": 0.99,
1029
+ "learning_rate": 0.00017384410318920697,
1030
+ "loss": 1.0086,
1031
+ "step": 165
1032
+ },
1033
+ {
1034
+ "epoch": 0.99,
1035
+ "learning_rate": 0.00017352131250807467,
1036
+ "loss": 1.0909,
1037
+ "step": 166
1038
+ },
1039
+ {
1040
+ "epoch": 1.0,
1041
+ "learning_rate": 0.00017319684587954002,
1042
+ "loss": 1.1085,
1043
+ "step": 167
1044
+ },
1045
+ {
1046
+ "epoch": 1.0,
1047
+ "learning_rate": 0.0001728707106999482,
1048
+ "loss": 1.1573,
1049
+ "step": 168
1050
+ },
1051
+ {
1052
+ "epoch": 1.0,
1053
+ "eval_loss": 0.7850226163864136,
1054
+ "eval_runtime": 14.526,
1055
+ "eval_samples_per_second": 56.382,
1056
+ "eval_steps_per_second": 28.225,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.01,
1061
+ "learning_rate": 0.00017254291440367968,
1062
+ "loss": 1.1107,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.01,
1067
+ "learning_rate": 0.0001722134644629807,
1068
+ "loss": 1.1537,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.0,
1073
+ "learning_rate": 0.00017188236838779295,
1074
+ "loss": 1.1293,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.01,
1079
+ "learning_rate": 0.00017154963372558246,
1080
+ "loss": 1.0653,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.02,
1085
+ "learning_rate": 0.00017121526806116748,
1086
+ "loss": 1.0901,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.02,
1091
+ "learning_rate": 0.00017087927901654557,
1092
+ "loss": 1.1569,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.03,
1097
+ "learning_rate": 0.00017054167425071995,
1098
+ "loss": 1.022,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.03,
1103
+ "learning_rate": 0.00017020246145952477,
1104
+ "loss": 1.0639,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.04,
1109
+ "learning_rate": 0.00016986164837544987,
1110
+ "loss": 1.071,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.05,
1115
+ "learning_rate": 0.00016951924276746425,
1116
+ "loss": 0.924,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.05,
1121
+ "learning_rate": 0.00016917525244083918,
1122
+ "loss": 1.0146,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.06,
1127
+ "learning_rate": 0.00016882968523697028,
1128
+ "loss": 1.0599,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.06,
1133
+ "learning_rate": 0.00016848254903319867,
1134
+ "loss": 1.0237,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.07,
1139
+ "learning_rate": 0.00016813385174263137,
1140
+ "loss": 0.9614,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.08,
1145
+ "learning_rate": 0.0001677836013139611,
1146
+ "loss": 0.9791,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.08,
1151
+ "learning_rate": 0.00016743180573128495,
1152
+ "loss": 1.0945,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.09,
1157
+ "learning_rate": 0.00016707847301392236,
1158
+ "loss": 1.0091,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.09,
1163
+ "learning_rate": 0.00016672361121623238,
1164
+ "loss": 1.1076,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.1,
1169
+ "learning_rate": 0.00016636722842743013,
1170
+ "loss": 0.9472,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.11,
1175
+ "learning_rate": 0.0001660093327714022,
1176
+ "loss": 1.0485,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.11,
1181
+ "learning_rate": 0.0001656499324065217,
1182
+ "loss": 1.0056,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.12,
1187
+ "learning_rate": 0.00016528903552546207,
1188
+ "loss": 1.0819,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.12,
1193
+ "learning_rate": 0.00016492665035501046,
1194
+ "loss": 1.1128,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.13,
1199
+ "learning_rate": 0.00016456278515588024,
1200
+ "loss": 1.056,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.14,
1205
+ "learning_rate": 0.00016419744822252253,
1206
+ "loss": 1.0468,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.14,
1211
+ "learning_rate": 0.0001638306478829373,
1212
+ "loss": 0.9966,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.15,
1217
+ "learning_rate": 0.0001634623924984833,
1218
+ "loss": 0.9898,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.15,
1223
+ "learning_rate": 0.00016309269046368776,
1224
+ "loss": 1.0431,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.16,
1229
+ "learning_rate": 0.0001627215502060548,
1230
+ "loss": 1.0327,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.17,
1235
+ "learning_rate": 0.00016234898018587337,
1236
+ "loss": 1.0382,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.17,
1241
+ "learning_rate": 0.00016197498889602448,
1242
+ "loss": 1.0287,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.18,
1247
+ "learning_rate": 0.0001615995848617876,
1248
+ "loss": 1.0244,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.18,
1253
+ "learning_rate": 0.0001612227766406461,
1254
+ "loss": 1.0989,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 1.19,
1259
+ "learning_rate": 0.00016084457282209243,
1260
+ "loss": 1.1219,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 1.2,
1265
+ "learning_rate": 0.00016046498202743233,
1266
+ "loss": 0.9456,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 1.2,
1271
+ "learning_rate": 0.00016008401290958807,
1272
+ "loss": 1.0259,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 1.21,
1277
+ "learning_rate": 0.0001597016741529014,
1278
+ "loss": 1.0929,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 1.21,
1283
+ "learning_rate": 0.00015931797447293552,
1284
+ "loss": 1.0716,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 1.22,
1289
+ "learning_rate": 0.00015893292261627643,
1290
+ "loss": 0.9947,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 1.23,
1295
+ "learning_rate": 0.00015854652736033354,
1296
+ "loss": 0.9707,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 1.23,
1301
+ "learning_rate": 0.00015815879751313955,
1302
+ "loss": 0.9492,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 1.24,
1307
+ "learning_rate": 0.0001577697419131497,
1308
+ "loss": 0.9346,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 1.24,
1313
+ "eval_loss": 0.7729161381721497,
1314
+ "eval_runtime": 14.4823,
1315
+ "eval_samples_per_second": 56.552,
1316
+ "eval_steps_per_second": 28.31,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.24,
1321
+ "learning_rate": 0.00015737936942904023,
1322
+ "loss": 0.9925,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.25,
1327
+ "learning_rate": 0.00015698768895950642,
1328
+ "loss": 1.032,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.26,
1333
+ "learning_rate": 0.00015659470943305955,
1334
+ "loss": 1.0372,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.26,
1339
+ "learning_rate": 0.00015620043980782327,
1340
+ "loss": 0.9926,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.27,
1345
+ "learning_rate": 0.00015580488907132974,
1346
+ "loss": 0.9653,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.27,
1351
+ "learning_rate": 0.00015540806624031442,
1352
+ "loss": 1.1205,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.28,
1357
+ "learning_rate": 0.00015500998036051074,
1358
+ "loss": 1.0311,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.29,
1363
+ "learning_rate": 0.0001546106405064438,
1364
+ "loss": 0.9639,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.29,
1369
+ "learning_rate": 0.00015421005578122356,
1370
+ "loss": 1.0489,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.3,
1375
+ "learning_rate": 0.00015380823531633729,
1376
+ "loss": 1.0312,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.3,
1381
+ "learning_rate": 0.00015340518827144145,
1382
+ "loss": 1.0165,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.31,
1387
+ "learning_rate": 0.00015300092383415282,
1388
+ "loss": 1.009,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.31,
1393
+ "learning_rate": 0.0001525954512198392,
1394
+ "loss": 1.0458,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.32,
1399
+ "learning_rate": 0.0001521887796714092,
1400
+ "loss": 1.0606,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.33,
1405
+ "learning_rate": 0.0001517809184591017,
1406
+ "loss": 0.9358,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.33,
1411
+ "learning_rate": 0.00015137187688027436,
1412
+ "loss": 1.0373,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.34,
1417
+ "learning_rate": 0.00015096166425919175,
1418
+ "loss": 1.1689,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.34,
1423
+ "learning_rate": 0.00015055028994681284,
1424
+ "loss": 1.1171,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.35,
1429
+ "learning_rate": 0.00015013776332057786,
1430
+ "loss": 0.9495,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.36,
1435
+ "learning_rate": 0.0001497240937841944,
1436
+ "loss": 1.0251,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.36,
1441
+ "learning_rate": 0.00014930929076742316,
1442
+ "loss": 1.132,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.37,
1447
+ "learning_rate": 0.00014889336372586305,
1448
+ "loss": 1.0223,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.37,
1453
+ "learning_rate": 0.00014847632214073548,
1454
+ "loss": 0.9179,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.38,
1459
+ "learning_rate": 0.00014805817551866838,
1460
+ "loss": 0.915,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.39,
1465
+ "learning_rate": 0.0001476389333914794,
1466
+ "loss": 1.0096,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.39,
1471
+ "learning_rate": 0.0001472186053159587,
1472
+ "loss": 1.0108,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.4,
1477
+ "learning_rate": 0.00014679720087365096,
1478
+ "loss": 0.9954,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.4,
1483
+ "learning_rate": 0.0001463747296706372,
1484
+ "loss": 1.0534,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.41,
1489
+ "learning_rate": 0.00014595120133731565,
1490
+ "loss": 0.9521,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.42,
1495
+ "learning_rate": 0.0001455266255281821,
1496
+ "loss": 1.086,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.42,
1501
+ "learning_rate": 0.00014510101192161018,
1502
+ "loss": 0.986,
1503
+ "step": 241
1504
+ },
1505
+ {
1506
+ "epoch": 1.43,
1507
+ "learning_rate": 0.0001446743702196304,
1508
+ "loss": 1.1084,
1509
+ "step": 242
1510
+ },
1511
+ {
1512
+ "epoch": 1.43,
1513
+ "learning_rate": 0.00014424671014770906,
1514
+ "loss": 0.9904,
1515
+ "step": 243
1516
+ },
1517
+ {
1518
+ "epoch": 1.44,
1519
+ "learning_rate": 0.0001438180414545267,
1520
+ "loss": 1.019,
1521
+ "step": 244
1522
+ },
1523
+ {
1524
+ "epoch": 1.45,
1525
+ "learning_rate": 0.00014338837391175582,
1526
+ "loss": 1.1684,
1527
+ "step": 245
1528
+ },
1529
+ {
1530
+ "epoch": 1.45,
1531
+ "learning_rate": 0.00014295771731383797,
1532
+ "loss": 0.9792,
1533
+ "step": 246
1534
+ },
1535
+ {
1536
+ "epoch": 1.46,
1537
+ "learning_rate": 0.00014252608147776065,
1538
+ "loss": 1.0375,
1539
+ "step": 247
1540
+ },
1541
+ {
1542
+ "epoch": 1.46,
1543
+ "learning_rate": 0.0001420934762428335,
1544
+ "loss": 0.9413,
1545
+ "step": 248
1546
+ },
1547
+ {
1548
+ "epoch": 1.47,
1549
+ "learning_rate": 0.00014165991147046403,
1550
+ "loss": 1.0807,
1551
+ "step": 249
1552
+ },
1553
+ {
1554
+ "epoch": 1.48,
1555
+ "learning_rate": 0.00014122539704393265,
1556
+ "loss": 0.8643,
1557
+ "step": 250
1558
+ },
1559
+ {
1560
+ "epoch": 1.48,
1561
+ "learning_rate": 0.00014078994286816768,
1562
+ "loss": 0.9569,
1563
+ "step": 251
1564
+ },
1565
+ {
1566
+ "epoch": 1.49,
1567
+ "learning_rate": 0.00014035355886951923,
1568
+ "loss": 1.0299,
1569
+ "step": 252
1570
+ },
1571
+ {
1572
+ "epoch": 1.49,
1573
+ "eval_loss": 0.761233925819397,
1574
+ "eval_runtime": 14.3861,
1575
+ "eval_samples_per_second": 56.93,
1576
+ "eval_steps_per_second": 28.5,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.49,
1581
+ "learning_rate": 0.00013991625499553325,
1582
+ "loss": 0.9685,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.5,
1587
+ "learning_rate": 0.0001394780412147245,
1588
+ "loss": 1.0123,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.51,
1593
+ "learning_rate": 0.00013903892751634947,
1594
+ "loss": 0.9601,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.51,
1599
+ "learning_rate": 0.00013859892391017865,
1600
+ "loss": 0.9661,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.52,
1605
+ "learning_rate": 0.00013815804042626828,
1606
+ "loss": 1.0132,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.52,
1611
+ "learning_rate": 0.00013771628711473172,
1612
+ "loss": 1.0511,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.53,
1617
+ "learning_rate": 0.00013727367404551055,
1618
+ "loss": 1.0637,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.54,
1623
+ "learning_rate": 0.0001368302113081447,
1624
+ "loss": 0.9781,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.54,
1629
+ "learning_rate": 0.00013638590901154276,
1630
+ "loss": 1.0151,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.55,
1635
+ "learning_rate": 0.00013594077728375128,
1636
+ "loss": 0.9971,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.55,
1641
+ "learning_rate": 0.0001354948262717241,
1642
+ "loss": 0.9202,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.56,
1647
+ "learning_rate": 0.00013504806614109098,
1648
+ "loss": 1.0605,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.57,
1653
+ "learning_rate": 0.0001346005070759258,
1654
+ "loss": 1.0303,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.57,
1659
+ "learning_rate": 0.0001341521592785145,
1660
+ "loss": 0.9228,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.58,
1665
+ "learning_rate": 0.00013370303296912249,
1666
+ "loss": 0.9659,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.58,
1671
+ "learning_rate": 0.0001332531383857616,
1672
+ "loss": 0.9742,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.59,
1677
+ "learning_rate": 0.0001328024857839569,
1678
+ "loss": 1.0524,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.6,
1683
+ "learning_rate": 0.00013235108543651272,
1684
+ "loss": 1.0277,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.6,
1689
+ "learning_rate": 0.0001318989476332785,
1690
+ "loss": 0.9731,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.61,
1695
+ "learning_rate": 0.00013144608268091435,
1696
+ "loss": 1.0629,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.61,
1701
+ "learning_rate": 0.000130992500902656,
1702
+ "loss": 0.8943,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.62,
1707
+ "learning_rate": 0.00013053821263807946,
1708
+ "loss": 0.9997,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.63,
1713
+ "learning_rate": 0.00013008322824286555,
1714
+ "loss": 1.0465,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.63,
1719
+ "learning_rate": 0.00012962755808856342,
1720
+ "loss": 1.0259,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.64,
1725
+ "learning_rate": 0.00012917121256235455,
1726
+ "loss": 0.9458,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.64,
1731
+ "learning_rate": 0.00012871420206681571,
1732
+ "loss": 1.0322,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.65,
1737
+ "learning_rate": 0.000128256537019682,
1738
+ "loss": 0.8538,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.66,
1743
+ "learning_rate": 0.00012779822785360912,
1744
+ "loss": 0.9602,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.66,
1749
+ "learning_rate": 0.00012733928501593587,
1750
+ "loss": 0.9953,
1751
+ "step": 281
1752
+ },
1753
+ {
1754
+ "epoch": 1.67,
1755
+ "learning_rate": 0.00012687971896844575,
1756
+ "loss": 0.8757,
1757
+ "step": 282
1758
+ },
1759
+ {
1760
+ "epoch": 1.67,
1761
+ "learning_rate": 0.00012641954018712863,
1762
+ "loss": 0.9382,
1763
+ "step": 283
1764
+ },
1765
+ {
1766
+ "epoch": 1.68,
1767
+ "learning_rate": 0.00012595875916194188,
1768
+ "loss": 0.8791,
1769
+ "step": 284
1770
+ },
1771
+ {
1772
+ "epoch": 1.69,
1773
+ "learning_rate": 0.00012549738639657115,
1774
+ "loss": 0.9245,
1775
+ "step": 285
1776
+ },
1777
+ {
1778
+ "epoch": 1.69,
1779
+ "learning_rate": 0.00012503543240819127,
1780
+ "loss": 0.9611,
1781
+ "step": 286
1782
+ },
1783
+ {
1784
+ "epoch": 1.7,
1785
+ "learning_rate": 0.00012457290772722608,
1786
+ "loss": 1.0328,
1787
+ "step": 287
1788
+ },
1789
+ {
1790
+ "epoch": 1.7,
1791
+ "learning_rate": 0.00012410982289710865,
1792
+ "loss": 0.8988,
1793
+ "step": 288
1794
+ },
1795
+ {
1796
+ "epoch": 1.71,
1797
+ "learning_rate": 0.0001236461884740409,
1798
+ "loss": 1.0435,
1799
+ "step": 289
1800
+ },
1801
+ {
1802
+ "epoch": 1.71,
1803
+ "learning_rate": 0.00012318201502675285,
1804
+ "loss": 0.9486,
1805
+ "step": 290
1806
+ },
1807
+ {
1808
+ "epoch": 1.72,
1809
+ "learning_rate": 0.0001227173131362619,
1810
+ "loss": 0.8819,
1811
+ "step": 291
1812
+ },
1813
+ {
1814
+ "epoch": 1.73,
1815
+ "learning_rate": 0.00012225209339563145,
1816
+ "loss": 1.024,
1817
+ "step": 292
1818
+ },
1819
+ {
1820
+ "epoch": 1.73,
1821
+ "learning_rate": 0.00012178636640972953,
1822
+ "loss": 0.9137,
1823
+ "step": 293
1824
+ },
1825
+ {
1826
+ "epoch": 1.74,
1827
+ "learning_rate": 0.00012132014279498703,
1828
+ "loss": 1.0057,
1829
+ "step": 294
1830
+ },
1831
+ {
1832
+ "epoch": 1.74,
1833
+ "eval_loss": 0.754410445690155,
1834
+ "eval_runtime": 14.5906,
1835
+ "eval_samples_per_second": 56.132,
1836
+ "eval_steps_per_second": 28.1,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.74,
1841
+ "learning_rate": 0.00012085343317915565,
1842
+ "loss": 1.0209,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.75,
1847
+ "learning_rate": 0.00012038624820106572,
1848
+ "loss": 0.9985,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.76,
1853
+ "learning_rate": 0.0001199185985103836,
1854
+ "loss": 0.7608,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.76,
1859
+ "learning_rate": 0.00011945049476736905,
1860
+ "loss": 0.931,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.77,
1865
+ "learning_rate": 0.00011898194764263197,
1866
+ "loss": 1.0362,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.77,
1871
+ "learning_rate": 0.00011851296781688952,
1872
+ "loss": 1.097,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.78,
1877
+ "learning_rate": 0.00011804356598072223,
1878
+ "loss": 0.9304,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.79,
1883
+ "learning_rate": 0.00011757375283433076,
1884
+ "loss": 0.9989,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.79,
1889
+ "learning_rate": 0.00011710353908729156,
1890
+ "loss": 0.971,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.8,
1895
+ "learning_rate": 0.00011663293545831302,
1896
+ "loss": 0.9942,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.8,
1901
+ "learning_rate": 0.00011616195267499102,
1902
+ "loss": 0.9824,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.81,
1907
+ "learning_rate": 0.00011569060147356441,
1908
+ "loss": 0.9901,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.82,
1913
+ "learning_rate": 0.00011521889259867032,
1914
+ "loss": 1.0445,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.82,
1919
+ "learning_rate": 0.00011474683680309912,
1920
+ "loss": 0.9421,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.83,
1925
+ "learning_rate": 0.0001142744448475494,
1926
+ "loss": 0.9692,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.83,
1931
+ "learning_rate": 0.00011380172750038269,
1932
+ "loss": 0.9473,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.84,
1937
+ "learning_rate": 0.0001133286955373779,
1938
+ "loss": 1.0931,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.85,
1943
+ "learning_rate": 0.00011285535974148576,
1944
+ "loss": 1.0236,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.85,
1949
+ "learning_rate": 0.00011238173090258293,
1950
+ "loss": 0.9002,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.86,
1955
+ "learning_rate": 0.00011190781981722623,
1956
+ "loss": 0.9209,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.86,
1961
+ "learning_rate": 0.00011143363728840625,
1962
+ "loss": 0.9155,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.87,
1967
+ "learning_rate": 0.00011095919412530136,
1968
+ "loss": 1.0064,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.88,
1973
+ "learning_rate": 0.0001104845011430311,
1974
+ "loss": 0.947,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.88,
1979
+ "learning_rate": 0.00011000956916240985,
1980
+ "loss": 0.9293,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.89,
1985
+ "learning_rate": 0.00010953440900969994,
1986
+ "loss": 0.9596,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.89,
1991
+ "learning_rate": 0.00010905903151636501,
1992
+ "loss": 0.9835,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.9,
1997
+ "learning_rate": 0.00010858344751882304,
1998
+ "loss": 0.9722,
1999
+ "step": 321
2000
+ },
2001
+ {
2002
+ "epoch": 1.91,
2003
+ "learning_rate": 0.00010810766785819946,
2004
+ "loss": 0.8318,
2005
+ "step": 322
2006
+ },
2007
+ {
2008
+ "epoch": 1.91,
2009
+ "learning_rate": 0.00010763170338007978,
2010
+ "loss": 1.0073,
2011
+ "step": 323
2012
+ },
2013
+ {
2014
+ "epoch": 1.92,
2015
+ "learning_rate": 0.00010715556493426262,
2016
+ "loss": 0.9922,
2017
+ "step": 324
2018
+ },
2019
+ {
2020
+ "epoch": 1.92,
2021
+ "learning_rate": 0.00010667926337451217,
2022
+ "loss": 0.9459,
2023
+ "step": 325
2024
+ },
2025
+ {
2026
+ "epoch": 1.93,
2027
+ "learning_rate": 0.00010620280955831087,
2028
+ "loss": 0.9276,
2029
+ "step": 326
2030
+ },
2031
+ {
2032
+ "epoch": 1.94,
2033
+ "learning_rate": 0.000105726214346612,
2034
+ "loss": 1.027,
2035
+ "step": 327
2036
+ },
2037
+ {
2038
+ "epoch": 1.94,
2039
+ "learning_rate": 0.00010524948860359193,
2040
+ "loss": 0.8963,
2041
+ "step": 328
2042
+ },
2043
+ {
2044
+ "epoch": 1.95,
2045
+ "learning_rate": 0.00010477264319640252,
2046
+ "loss": 1.0102,
2047
+ "step": 329
2048
+ },
2049
+ {
2050
+ "epoch": 1.95,
2051
+ "learning_rate": 0.00010429568899492348,
2052
+ "loss": 0.9058,
2053
+ "step": 330
2054
+ },
2055
+ {
2056
+ "epoch": 1.96,
2057
+ "learning_rate": 0.0001038186368715145,
2058
+ "loss": 1.137,
2059
+ "step": 331
2060
+ },
2061
+ {
2062
+ "epoch": 1.97,
2063
+ "learning_rate": 0.00010334149770076747,
2064
+ "loss": 0.9578,
2065
+ "step": 332
2066
+ },
2067
+ {
2068
+ "epoch": 1.97,
2069
+ "learning_rate": 0.00010286428235925849,
2070
+ "loss": 0.9282,
2071
+ "step": 333
2072
+ },
2073
+ {
2074
+ "epoch": 1.98,
2075
+ "learning_rate": 0.00010238700172530009,
2076
+ "loss": 0.9325,
2077
+ "step": 334
2078
+ },
2079
+ {
2080
+ "epoch": 1.98,
2081
+ "learning_rate": 0.0001019096666786931,
2082
+ "loss": 0.9145,
2083
+ "step": 335
2084
+ },
2085
+ {
2086
+ "epoch": 1.99,
2087
+ "learning_rate": 0.00010143228810047875,
2088
+ "loss": 0.976,
2089
+ "step": 336
2090
+ },
2091
+ {
2092
+ "epoch": 1.99,
2093
+ "eval_loss": 0.7478241920471191,
2094
+ "eval_runtime": 14.477,
2095
+ "eval_samples_per_second": 56.573,
2096
+ "eval_steps_per_second": 28.321,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 2.0,
2101
+ "learning_rate": 0.00010095487687269054,
2102
+ "loss": 1.005,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 2.0,
2107
+ "learning_rate": 0.00010047744387810632,
2108
+ "loss": 0.9885,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 2.01,
2113
+ "learning_rate": 0.0001,
2114
+ "loss": 1.0033,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 2.01,
2119
+ "learning_rate": 9.952255612189368e-05,
2120
+ "loss": 0.867,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 2.0,
2125
+ "learning_rate": 9.904512312730948e-05,
2126
+ "loss": 1.0728,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 2.01,
2131
+ "learning_rate": 9.856771189952126e-05,
2132
+ "loss": 0.9978,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 2.01,
2137
+ "learning_rate": 9.809033332130693e-05,
2138
+ "loss": 0.8017,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 2.02,
2143
+ "learning_rate": 9.761299827469992e-05,
2144
+ "loss": 0.8687,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 2.03,
2149
+ "learning_rate": 9.713571764074152e-05,
2150
+ "loss": 1.1273,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 2.03,
2155
+ "learning_rate": 9.665850229923258e-05,
2156
+ "loss": 0.9474,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 2.04,
2161
+ "learning_rate": 9.618136312848551e-05,
2162
+ "loss": 0.9905,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 2.04,
2167
+ "learning_rate": 9.570431100507651e-05,
2168
+ "loss": 0.9277,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 2.05,
2173
+ "learning_rate": 9.52273568035975e-05,
2174
+ "loss": 0.8655,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 2.06,
2179
+ "learning_rate": 9.475051139640809e-05,
2180
+ "loss": 0.9271,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 2.06,
2185
+ "learning_rate": 9.4273785653388e-05,
2186
+ "loss": 1.0323,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 2.07,
2191
+ "learning_rate": 9.379719044168915e-05,
2192
+ "loss": 0.9624,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 2.07,
2197
+ "learning_rate": 9.332073662548784e-05,
2198
+ "loss": 0.8565,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 2.08,
2203
+ "learning_rate": 9.28444350657374e-05,
2204
+ "loss": 0.99,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 2.09,
2209
+ "learning_rate": 9.236829661992023e-05,
2210
+ "loss": 1.0581,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 2.09,
2215
+ "learning_rate": 9.189233214180056e-05,
2216
+ "loss": 0.8963,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 2.1,
2221
+ "learning_rate": 9.141655248117698e-05,
2222
+ "loss": 0.9169,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 2.1,
2227
+ "learning_rate": 9.094096848363502e-05,
2228
+ "loss": 1.0023,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 2.11,
2233
+ "learning_rate": 9.046559099030012e-05,
2234
+ "loss": 0.8931,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 2.12,
2239
+ "learning_rate": 8.999043083759017e-05,
2240
+ "loss": 1.0086,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 2.12,
2245
+ "learning_rate": 8.951549885696889e-05,
2246
+ "loss": 0.9737,
2247
+ "step": 361
2248
+ },
2249
+ {
2250
+ "epoch": 2.13,
2251
+ "learning_rate": 8.904080587469868e-05,
2252
+ "loss": 1.006,
2253
+ "step": 362
2254
+ },
2255
+ {
2256
+ "epoch": 2.13,
2257
+ "learning_rate": 8.856636271159377e-05,
2258
+ "loss": 0.8521,
2259
+ "step": 363
2260
+ },
2261
+ {
2262
+ "epoch": 2.14,
2263
+ "learning_rate": 8.809218018277378e-05,
2264
+ "loss": 0.8799,
2265
+ "step": 364
2266
+ },
2267
+ {
2268
+ "epoch": 2.15,
2269
+ "learning_rate": 8.761826909741709e-05,
2270
+ "loss": 0.86,
2271
+ "step": 365
2272
+ },
2273
+ {
2274
+ "epoch": 2.15,
2275
+ "learning_rate": 8.714464025851427e-05,
2276
+ "loss": 0.9277,
2277
+ "step": 366
2278
+ },
2279
+ {
2280
+ "epoch": 2.16,
2281
+ "learning_rate": 8.667130446262214e-05,
2282
+ "loss": 0.9753,
2283
+ "step": 367
2284
+ },
2285
+ {
2286
+ "epoch": 2.16,
2287
+ "learning_rate": 8.619827249961733e-05,
2288
+ "loss": 0.9232,
2289
+ "step": 368
2290
+ },
2291
+ {
2292
+ "epoch": 2.17,
2293
+ "learning_rate": 8.57255551524506e-05,
2294
+ "loss": 1.0167,
2295
+ "step": 369
2296
+ },
2297
+ {
2298
+ "epoch": 2.18,
2299
+ "learning_rate": 8.525316319690092e-05,
2300
+ "loss": 1.1038,
2301
+ "step": 370
2302
+ },
2303
+ {
2304
+ "epoch": 2.18,
2305
+ "learning_rate": 8.47811074013297e-05,
2306
+ "loss": 0.9303,
2307
+ "step": 371
2308
+ },
2309
+ {
2310
+ "epoch": 2.19,
2311
+ "learning_rate": 8.430939852643558e-05,
2312
+ "loss": 0.9683,
2313
+ "step": 372
2314
+ },
2315
+ {
2316
+ "epoch": 2.19,
2317
+ "learning_rate": 8.383804732500902e-05,
2318
+ "loss": 0.9889,
2319
+ "step": 373
2320
+ },
2321
+ {
2322
+ "epoch": 2.2,
2323
+ "learning_rate": 8.336706454168701e-05,
2324
+ "loss": 0.7554,
2325
+ "step": 374
2326
+ },
2327
+ {
2328
+ "epoch": 2.21,
2329
+ "learning_rate": 8.289646091270849e-05,
2330
+ "loss": 0.9968,
2331
+ "step": 375
2332
+ },
2333
+ {
2334
+ "epoch": 2.21,
2335
+ "learning_rate": 8.242624716566927e-05,
2336
+ "loss": 1.0212,
2337
+ "step": 376
2338
+ },
2339
+ {
2340
+ "epoch": 2.22,
2341
+ "learning_rate": 8.195643401927777e-05,
2342
+ "loss": 0.9033,
2343
+ "step": 377
2344
+ },
2345
+ {
2346
+ "epoch": 2.22,
2347
+ "learning_rate": 8.148703218311053e-05,
2348
+ "loss": 1.0765,
2349
+ "step": 378
2350
+ },
2351
+ {
2352
+ "epoch": 2.22,
2353
+ "eval_loss": 0.7438732981681824,
2354
+ "eval_runtime": 14.4192,
2355
+ "eval_samples_per_second": 56.799,
2356
+ "eval_steps_per_second": 28.434,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 2.23,
2361
+ "learning_rate": 8.101805235736804e-05,
2362
+ "loss": 0.9057,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 2.24,
2367
+ "learning_rate": 8.054950523263096e-05,
2368
+ "loss": 0.9076,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 2.24,
2373
+ "learning_rate": 8.008140148961641e-05,
2374
+ "loss": 0.9456,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 2.25,
2379
+ "learning_rate": 7.96137517989343e-05,
2380
+ "loss": 1.0068,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 2.25,
2385
+ "learning_rate": 7.914656682084437e-05,
2386
+ "loss": 1.015,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 2.26,
2391
+ "learning_rate": 7.867985720501301e-05,
2392
+ "loss": 0.9624,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 2.27,
2397
+ "learning_rate": 7.821363359027048e-05,
2398
+ "loss": 0.9623,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 2.27,
2403
+ "learning_rate": 7.774790660436858e-05,
2404
+ "loss": 0.9155,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 2.28,
2409
+ "learning_rate": 7.728268686373814e-05,
2410
+ "loss": 1.0116,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 2.28,
2415
+ "learning_rate": 7.681798497324716e-05,
2416
+ "loss": 0.9035,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 2.29,
2421
+ "learning_rate": 7.635381152595915e-05,
2422
+ "loss": 0.9018,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 2.3,
2427
+ "learning_rate": 7.589017710289139e-05,
2428
+ "loss": 1.0231,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 2.3,
2433
+ "learning_rate": 7.542709227277396e-05,
2434
+ "loss": 0.9325,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 2.31,
2439
+ "learning_rate": 7.496456759180875e-05,
2440
+ "loss": 1.0224,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 2.31,
2445
+ "learning_rate": 7.450261360342888e-05,
2446
+ "loss": 0.9142,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 2.32,
2451
+ "learning_rate": 7.404124083805819e-05,
2452
+ "loss": 0.9583,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 2.33,
2457
+ "learning_rate": 7.358045981287141e-05,
2458
+ "loss": 1.007,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 2.33,
2463
+ "learning_rate": 7.312028103155426e-05,
2464
+ "loss": 0.8724,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 2.34,
2469
+ "learning_rate": 7.266071498406417e-05,
2470
+ "loss": 0.8942,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 2.34,
2475
+ "learning_rate": 7.220177214639088e-05,
2476
+ "loss": 0.9398,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 2.35,
2481
+ "learning_rate": 7.174346298031804e-05,
2482
+ "loss": 0.8393,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 2.36,
2487
+ "learning_rate": 7.128579793318428e-05,
2488
+ "loss": 0.9286,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 2.36,
2493
+ "learning_rate": 7.082878743764545e-05,
2494
+ "loss": 0.924,
2495
+ "step": 401
2496
+ },
2497
+ {
2498
+ "epoch": 2.37,
2499
+ "learning_rate": 7.037244191143661e-05,
2500
+ "loss": 0.96,
2501
+ "step": 402
2502
+ },
2503
+ {
2504
+ "epoch": 2.37,
2505
+ "learning_rate": 6.991677175713449e-05,
2506
+ "loss": 0.9981,
2507
+ "step": 403
2508
+ },
2509
+ {
2510
+ "epoch": 2.38,
2511
+ "learning_rate": 6.946178736192053e-05,
2512
+ "loss": 1.0843,
2513
+ "step": 404
2514
+ },
2515
+ {
2516
+ "epoch": 2.39,
2517
+ "learning_rate": 6.900749909734406e-05,
2518
+ "loss": 0.9198,
2519
+ "step": 405
2520
+ },
2521
+ {
2522
+ "epoch": 2.39,
2523
+ "learning_rate": 6.855391731908567e-05,
2524
+ "loss": 0.9537,
2525
+ "step": 406
2526
+ },
2527
+ {
2528
+ "epoch": 2.4,
2529
+ "learning_rate": 6.810105236672155e-05,
2530
+ "loss": 0.9219,
2531
+ "step": 407
2532
+ },
2533
+ {
2534
+ "epoch": 2.4,
2535
+ "learning_rate": 6.764891456348729e-05,
2536
+ "loss": 0.963,
2537
+ "step": 408
2538
+ },
2539
+ {
2540
+ "epoch": 2.41,
2541
+ "learning_rate": 6.719751421604309e-05,
2542
+ "loss": 1.0003,
2543
+ "step": 409
2544
+ },
2545
+ {
2546
+ "epoch": 2.41,
2547
+ "learning_rate": 6.674686161423843e-05,
2548
+ "loss": 1.0074,
2549
+ "step": 410
2550
+ },
2551
+ {
2552
+ "epoch": 2.42,
2553
+ "learning_rate": 6.629696703087754e-05,
2554
+ "loss": 1.0361,
2555
+ "step": 411
2556
+ },
2557
+ {
2558
+ "epoch": 2.43,
2559
+ "learning_rate": 6.584784072148555e-05,
2560
+ "loss": 0.9224,
2561
+ "step": 412
2562
+ },
2563
+ {
2564
+ "epoch": 2.43,
2565
+ "learning_rate": 6.539949292407421e-05,
2566
+ "loss": 0.9658,
2567
+ "step": 413
2568
+ },
2569
+ {
2570
+ "epoch": 2.44,
2571
+ "learning_rate": 6.495193385890901e-05,
2572
+ "loss": 1.0963,
2573
+ "step": 414
2574
+ },
2575
+ {
2576
+ "epoch": 2.44,
2577
+ "learning_rate": 6.450517372827591e-05,
2578
+ "loss": 1.0044,
2579
+ "step": 415
2580
+ },
2581
+ {
2582
+ "epoch": 2.45,
2583
+ "learning_rate": 6.405922271624874e-05,
2584
+ "loss": 0.998,
2585
+ "step": 416
2586
+ },
2587
+ {
2588
+ "epoch": 2.46,
2589
+ "learning_rate": 6.361409098845725e-05,
2590
+ "loss": 0.8947,
2591
+ "step": 417
2592
+ },
2593
+ {
2594
+ "epoch": 2.46,
2595
+ "learning_rate": 6.316978869185532e-05,
2596
+ "loss": 1.057,
2597
+ "step": 418
2598
+ },
2599
+ {
2600
+ "epoch": 2.47,
2601
+ "learning_rate": 6.272632595448947e-05,
2602
+ "loss": 1.0015,
2603
+ "step": 419
2604
+ },
2605
+ {
2606
+ "epoch": 2.47,
2607
+ "learning_rate": 6.22837128852683e-05,
2608
+ "loss": 0.8845,
2609
+ "step": 420
2610
+ },
2611
+ {
2612
+ "epoch": 2.47,
2613
+ "eval_loss": 0.7409489750862122,
2614
+ "eval_runtime": 14.4788,
2615
+ "eval_samples_per_second": 56.566,
2616
+ "eval_steps_per_second": 28.317,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 2.48,
2621
+ "learning_rate": 6.184195957373176e-05,
2622
+ "loss": 0.8122,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 2.49,
2627
+ "learning_rate": 6.140107608982136e-05,
2628
+ "loss": 0.984,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 2.49,
2633
+ "learning_rate": 6.0961072483650526e-05,
2634
+ "loss": 1.065,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 2.5,
2639
+ "learning_rate": 6.05219587852755e-05,
2640
+ "loss": 0.9648,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 2.5,
2645
+ "learning_rate": 6.008374500446676e-05,
2646
+ "loss": 0.9267,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 2.51,
2651
+ "learning_rate": 5.964644113048079e-05,
2652
+ "loss": 0.9327,
2653
+ "step": 426
2654
+ },
2655
+ {
2656
+ "epoch": 2.52,
2657
+ "learning_rate": 5.921005713183235e-05,
2658
+ "loss": 0.9545,
2659
+ "step": 427
2660
+ },
2661
+ {
2662
+ "epoch": 2.52,
2663
+ "learning_rate": 5.877460295606738e-05,
2664
+ "loss": 0.8972,
2665
+ "step": 428
2666
+ },
2667
+ {
2668
+ "epoch": 2.53,
2669
+ "learning_rate": 5.834008852953603e-05,
2670
+ "loss": 0.9857,
2671
+ "step": 429
2672
+ },
2673
+ {
2674
+ "epoch": 2.53,
2675
+ "learning_rate": 5.790652375716652e-05,
2676
+ "loss": 0.9189,
2677
+ "step": 430
2678
+ },
2679
+ {
2680
+ "epoch": 2.54,
2681
+ "learning_rate": 5.74739185222394e-05,
2682
+ "loss": 0.8486,
2683
+ "step": 431
2684
+ },
2685
+ {
2686
+ "epoch": 2.55,
2687
+ "learning_rate": 5.704228268616208e-05,
2688
+ "loss": 0.9442,
2689
+ "step": 432
2690
+ },
2691
+ {
2692
+ "epoch": 2.55,
2693
+ "learning_rate": 5.6611626088244194e-05,
2694
+ "loss": 0.9095,
2695
+ "step": 433
2696
+ },
2697
+ {
2698
+ "epoch": 2.56,
2699
+ "learning_rate": 5.6181958545473325e-05,
2700
+ "loss": 1.0581,
2701
+ "step": 434
2702
+ },
2703
+ {
2704
+ "epoch": 2.56,
2705
+ "learning_rate": 5.575328985229098e-05,
2706
+ "loss": 0.8151,
2707
+ "step": 435
2708
+ },
2709
+ {
2710
+ "epoch": 2.57,
2711
+ "learning_rate": 5.5325629780369635e-05,
2712
+ "loss": 0.8941,
2713
+ "step": 436
2714
+ },
2715
+ {
2716
+ "epoch": 2.58,
2717
+ "learning_rate": 5.48989880783898e-05,
2718
+ "loss": 0.9767,
2719
+ "step": 437
2720
+ },
2721
+ {
2722
+ "epoch": 2.58,
2723
+ "learning_rate": 5.4473374471817906e-05,
2724
+ "loss": 0.8874,
2725
+ "step": 438
2726
+ },
2727
+ {
2728
+ "epoch": 2.59,
2729
+ "learning_rate": 5.4048798662684376e-05,
2730
+ "loss": 0.8578,
2731
+ "step": 439
2732
+ },
2733
+ {
2734
+ "epoch": 2.59,
2735
+ "learning_rate": 5.362527032936277e-05,
2736
+ "loss": 0.9191,
2737
+ "step": 440
2738
+ },
2739
+ {
2740
+ "epoch": 2.6,
2741
+ "learning_rate": 5.320279912634907e-05,
2742
+ "loss": 0.7622,
2743
+ "step": 441
2744
+ },
2745
+ {
2746
+ "epoch": 2.61,
2747
+ "learning_rate": 5.278139468404133e-05,
2748
+ "loss": 0.9143,
2749
+ "step": 442
2750
+ },
2751
+ {
2752
+ "epoch": 2.61,
2753
+ "learning_rate": 5.236106660852058e-05,
2754
+ "loss": 0.9184,
2755
+ "step": 443
2756
+ },
2757
+ {
2758
+ "epoch": 2.62,
2759
+ "learning_rate": 5.1941824481331626e-05,
2760
+ "loss": 0.9776,
2761
+ "step": 444
2762
+ },
2763
+ {
2764
+ "epoch": 2.62,
2765
+ "learning_rate": 5.1523677859264516e-05,
2766
+ "loss": 0.9989,
2767
+ "step": 445
2768
+ },
2769
+ {
2770
+ "epoch": 2.63,
2771
+ "learning_rate": 5.110663627413694e-05,
2772
+ "loss": 0.8539,
2773
+ "step": 446
2774
+ },
2775
+ {
2776
+ "epoch": 2.64,
2777
+ "learning_rate": 5.069070923257685e-05,
2778
+ "loss": 1.0078,
2779
+ "step": 447
2780
+ },
2781
+ {
2782
+ "epoch": 2.64,
2783
+ "learning_rate": 5.0275906215805625e-05,
2784
+ "loss": 0.9395,
2785
+ "step": 448
2786
+ },
2787
+ {
2788
+ "epoch": 2.65,
2789
+ "learning_rate": 4.986223667942214e-05,
2790
+ "loss": 0.7978,
2791
+ "step": 449
2792
+ },
2793
+ {
2794
+ "epoch": 2.65,
2795
+ "learning_rate": 4.944971005318716e-05,
2796
+ "loss": 0.9456,
2797
+ "step": 450
2798
+ },
2799
+ {
2800
+ "epoch": 2.66,
2801
+ "learning_rate": 4.903833574080825e-05,
2802
+ "loss": 0.991,
2803
+ "step": 451
2804
+ },
2805
+ {
2806
+ "epoch": 2.67,
2807
+ "learning_rate": 4.862812311972567e-05,
2808
+ "loss": 0.8867,
2809
+ "step": 452
2810
+ },
2811
+ {
2812
+ "epoch": 2.67,
2813
+ "learning_rate": 4.8219081540898295e-05,
2814
+ "loss": 0.9519,
2815
+ "step": 453
2816
+ },
2817
+ {
2818
+ "epoch": 2.68,
2819
+ "learning_rate": 4.781122032859079e-05,
2820
+ "loss": 0.8153,
2821
+ "step": 454
2822
+ },
2823
+ {
2824
+ "epoch": 2.68,
2825
+ "learning_rate": 4.740454878016084e-05,
2826
+ "loss": 0.8457,
2827
+ "step": 455
2828
+ },
2829
+ {
2830
+ "epoch": 2.69,
2831
+ "learning_rate": 4.699907616584721e-05,
2832
+ "loss": 0.9878,
2833
+ "step": 456
2834
+ },
2835
+ {
2836
+ "epoch": 2.7,
2837
+ "learning_rate": 4.6594811728558584e-05,
2838
+ "loss": 0.9616,
2839
+ "step": 457
2840
+ },
2841
+ {
2842
+ "epoch": 2.7,
2843
+ "learning_rate": 4.6191764683662744e-05,
2844
+ "loss": 0.8892,
2845
+ "step": 458
2846
+ },
2847
+ {
2848
+ "epoch": 2.71,
2849
+ "learning_rate": 4.578994421877645e-05,
2850
+ "loss": 0.8593,
2851
+ "step": 459
2852
+ },
2853
+ {
2854
+ "epoch": 2.71,
2855
+ "learning_rate": 4.538935949355623e-05,
2856
+ "loss": 0.8618,
2857
+ "step": 460
2858
+ },
2859
+ {
2860
+ "epoch": 2.72,
2861
+ "learning_rate": 4.499001963948929e-05,
2862
+ "loss": 1.0498,
2863
+ "step": 461
2864
+ },
2865
+ {
2866
+ "epoch": 2.73,
2867
+ "learning_rate": 4.45919337596856e-05,
2868
+ "loss": 1.0198,
2869
+ "step": 462
2870
+ },
2871
+ {
2872
+ "epoch": 2.73,
2873
+ "eval_loss": 0.7379047870635986,
2874
+ "eval_runtime": 14.5017,
2875
+ "eval_samples_per_second": 56.476,
2876
+ "eval_steps_per_second": 28.273,
2877
+ "step": 462
2878
+ },
2879
+ {
2880
+ "epoch": 2.73,
2881
+ "learning_rate": 4.41951109286703e-05,
2882
+ "loss": 0.8737,
2883
+ "step": 463
2884
+ },
2885
+ {
2886
+ "epoch": 2.74,
2887
+ "learning_rate": 4.379956019217675e-05,
2888
+ "loss": 0.8282,
2889
+ "step": 464
2890
+ },
2891
+ {
2892
+ "epoch": 2.74,
2893
+ "learning_rate": 4.340529056694047e-05,
2894
+ "loss": 0.8425,
2895
+ "step": 465
2896
+ },
2897
+ {
2898
+ "epoch": 2.75,
2899
+ "learning_rate": 4.3012311040493594e-05,
2900
+ "loss": 0.8594,
2901
+ "step": 466
2902
+ },
2903
+ {
2904
+ "epoch": 2.76,
2905
+ "learning_rate": 4.2620630570959775e-05,
2906
+ "loss": 1.0157,
2907
+ "step": 467
2908
+ },
2909
+ {
2910
+ "epoch": 2.76,
2911
+ "learning_rate": 4.2230258086850374e-05,
2912
+ "loss": 1.0247,
2913
+ "step": 468
2914
+ },
2915
+ {
2916
+ "epoch": 2.77,
2917
+ "learning_rate": 4.184120248686048e-05,
2918
+ "loss": 0.956,
2919
+ "step": 469
2920
+ },
2921
+ {
2922
+ "epoch": 2.77,
2923
+ "learning_rate": 4.1453472639666457e-05,
2924
+ "loss": 0.9221,
2925
+ "step": 470
2926
+ },
2927
+ {
2928
+ "epoch": 2.78,
2929
+ "learning_rate": 4.106707738372357e-05,
2930
+ "loss": 0.8249,
2931
+ "step": 471
2932
+ },
2933
+ {
2934
+ "epoch": 2.79,
2935
+ "learning_rate": 4.0682025527064486e-05,
2936
+ "loss": 0.9179,
2937
+ "step": 472
2938
+ },
2939
+ {
2940
+ "epoch": 2.79,
2941
+ "learning_rate": 4.029832584709864e-05,
2942
+ "loss": 1.0457,
2943
+ "step": 473
2944
+ },
2945
+ {
2946
+ "epoch": 2.8,
2947
+ "learning_rate": 3.991598709041196e-05,
2948
+ "loss": 0.8553,
2949
+ "step": 474
2950
+ },
2951
+ {
2952
+ "epoch": 2.8,
2953
+ "learning_rate": 3.9535017972567675e-05,
2954
+ "loss": 0.8563,
2955
+ "step": 475
2956
+ },
2957
+ {
2958
+ "epoch": 2.81,
2959
+ "learning_rate": 3.915542717790759e-05,
2960
+ "loss": 0.9828,
2961
+ "step": 476
2962
+ },
2963
+ {
2964
+ "epoch": 2.81,
2965
+ "learning_rate": 3.877722335935394e-05,
2966
+ "loss": 0.9853,
2967
+ "step": 477
2968
+ },
2969
+ {
2970
+ "epoch": 2.82,
2971
+ "learning_rate": 3.840041513821243e-05,
2972
+ "loss": 0.9801,
2973
+ "step": 478
2974
+ },
2975
+ {
2976
+ "epoch": 2.83,
2977
+ "learning_rate": 3.802501110397553e-05,
2978
+ "loss": 0.8679,
2979
+ "step": 479
2980
+ },
2981
+ {
2982
+ "epoch": 2.83,
2983
+ "learning_rate": 3.7651019814126654e-05,
2984
+ "loss": 0.8846,
2985
+ "step": 480
2986
+ },
2987
+ {
2988
+ "epoch": 2.84,
2989
+ "learning_rate": 3.727844979394526e-05,
2990
+ "loss": 0.8068,
2991
+ "step": 481
2992
+ },
2993
+ {
2994
+ "epoch": 2.84,
2995
+ "learning_rate": 3.6907309536312276e-05,
2996
+ "loss": 0.8033,
2997
+ "step": 482
2998
+ },
2999
+ {
3000
+ "epoch": 2.85,
3001
+ "learning_rate": 3.6537607501516715e-05,
3002
+ "loss": 0.9402,
3003
+ "step": 483
3004
+ },
3005
+ {
3006
+ "epoch": 2.86,
3007
+ "learning_rate": 3.616935211706275e-05,
3008
+ "loss": 0.8132,
3009
+ "step": 484
3010
+ },
3011
+ {
3012
+ "epoch": 2.86,
3013
+ "learning_rate": 3.5802551777477476e-05,
3014
+ "loss": 0.8682,
3015
+ "step": 485
3016
+ },
3017
+ {
3018
+ "epoch": 2.87,
3019
+ "learning_rate": 3.543721484411976e-05,
3020
+ "loss": 0.9198,
3021
+ "step": 486
3022
+ },
3023
+ {
3024
+ "epoch": 2.87,
3025
+ "learning_rate": 3.5073349644989564e-05,
3026
+ "loss": 0.958,
3027
+ "step": 487
3028
+ },
3029
+ {
3030
+ "epoch": 2.88,
3031
+ "learning_rate": 3.4710964474537966e-05,
3032
+ "loss": 0.8973,
3033
+ "step": 488
3034
+ },
3035
+ {
3036
+ "epoch": 2.89,
3037
+ "learning_rate": 3.4350067593478356e-05,
3038
+ "loss": 1.0462,
3039
+ "step": 489
3040
+ },
3041
+ {
3042
+ "epoch": 2.89,
3043
+ "learning_rate": 3.399066722859782e-05,
3044
+ "loss": 0.9042,
3045
+ "step": 490
3046
+ },
3047
+ {
3048
+ "epoch": 2.9,
3049
+ "learning_rate": 3.363277157256988e-05,
3050
+ "loss": 0.9075,
3051
+ "step": 491
3052
+ },
3053
+ {
3054
+ "epoch": 2.9,
3055
+ "learning_rate": 3.327638878376764e-05,
3056
+ "loss": 1.0444,
3057
+ "step": 492
3058
+ },
3059
+ {
3060
+ "epoch": 2.91,
3061
+ "learning_rate": 3.292152698607768e-05,
3062
+ "loss": 0.9098,
3063
+ "step": 493
3064
+ },
3065
+ {
3066
+ "epoch": 2.92,
3067
+ "learning_rate": 3.256819426871507e-05,
3068
+ "loss": 1.0037,
3069
+ "step": 494
3070
+ },
3071
+ {
3072
+ "epoch": 2.92,
3073
+ "learning_rate": 3.2216398686038926e-05,
3074
+ "loss": 0.8278,
3075
+ "step": 495
3076
+ },
3077
+ {
3078
+ "epoch": 2.93,
3079
+ "learning_rate": 3.1866148257368665e-05,
3080
+ "loss": 0.9869,
3081
+ "step": 496
3082
+ },
3083
+ {
3084
+ "epoch": 2.93,
3085
+ "learning_rate": 3.15174509668014e-05,
3086
+ "loss": 0.8511,
3087
+ "step": 497
3088
+ },
3089
+ {
3090
+ "epoch": 2.94,
3091
+ "learning_rate": 3.117031476302975e-05,
3092
+ "loss": 0.9983,
3093
+ "step": 498
3094
+ },
3095
+ {
3096
+ "epoch": 2.95,
3097
+ "learning_rate": 3.0824747559160836e-05,
3098
+ "loss": 1.0146,
3099
+ "step": 499
3100
+ },
3101
+ {
3102
+ "epoch": 2.95,
3103
+ "learning_rate": 3.0480757232535772e-05,
3104
+ "loss": 0.9705,
3105
+ "step": 500
3106
+ },
3107
+ {
3108
+ "epoch": 2.96,
3109
+ "learning_rate": 3.0138351624550164e-05,
3110
+ "loss": 0.8197,
3111
+ "step": 501
3112
+ },
3113
+ {
3114
+ "epoch": 2.96,
3115
+ "learning_rate": 2.979753854047522e-05,
3116
+ "loss": 1.0835,
3117
+ "step": 502
3118
+ },
3119
+ {
3120
+ "epoch": 2.97,
3121
+ "learning_rate": 2.9458325749280057e-05,
3122
+ "loss": 0.8451,
3123
+ "step": 503
3124
+ },
3125
+ {
3126
+ "epoch": 2.98,
3127
+ "learning_rate": 2.9120720983454463e-05,
3128
+ "loss": 0.9712,
3129
+ "step": 504
3130
+ },
3131
+ {
3132
+ "epoch": 2.98,
3133
+ "eval_loss": 0.7352047562599182,
3134
+ "eval_runtime": 14.5599,
3135
+ "eval_samples_per_second": 56.251,
3136
+ "eval_steps_per_second": 28.16,
3137
+ "step": 504
3138
+ },
3139
+ {
3140
+ "epoch": 2.98,
3141
+ "learning_rate": 2.8784731938832556e-05,
3142
+ "loss": 1.0257,
3143
+ "step": 505
3144
+ },
3145
+ {
3146
+ "epoch": 2.99,
3147
+ "learning_rate": 2.845036627441755e-05,
3148
+ "loss": 1.1134,
3149
+ "step": 506
3150
+ },
3151
+ {
3152
+ "epoch": 2.99,
3153
+ "learning_rate": 2.8117631612207084e-05,
3154
+ "loss": 0.8619,
3155
+ "step": 507
3156
+ },
3157
+ {
3158
+ "epoch": 3.0,
3159
+ "learning_rate": 2.778653553701932e-05,
3160
+ "loss": 0.8906,
3161
+ "step": 508
3162
+ },
3163
+ {
3164
+ "epoch": 3.01,
3165
+ "learning_rate": 2.745708559632032e-05,
3166
+ "loss": 0.8772,
3167
+ "step": 509
3168
+ },
3169
+ {
3170
+ "epoch": 3.01,
3171
+ "learning_rate": 2.7129289300051787e-05,
3172
+ "loss": 0.8894,
3173
+ "step": 510
3174
+ },
3175
+ {
3176
+ "epoch": 3.02,
3177
+ "learning_rate": 2.6803154120460007e-05,
3178
+ "loss": 0.8776,
3179
+ "step": 511
3180
+ },
3181
+ {
3182
+ "epoch": 3.01,
3183
+ "learning_rate": 2.6478687491925357e-05,
3184
+ "loss": 0.8533,
3185
+ "step": 512
3186
+ },
3187
+ {
3188
+ "epoch": 3.01,
3189
+ "learning_rate": 2.6155896810793036e-05,
3190
+ "loss": 0.8595,
3191
+ "step": 513
3192
+ },
3193
+ {
3194
+ "epoch": 3.02,
3195
+ "learning_rate": 2.5834789435204243e-05,
3196
+ "loss": 0.9187,
3197
+ "step": 514
3198
+ },
3199
+ {
3200
+ "epoch": 3.02,
3201
+ "learning_rate": 2.5515372684928683e-05,
3202
+ "loss": 0.8633,
3203
+ "step": 515
3204
+ },
3205
+ {
3206
+ "epoch": 3.03,
3207
+ "learning_rate": 2.5197653841197543e-05,
3208
+ "loss": 0.9337,
3209
+ "step": 516
3210
+ },
3211
+ {
3212
+ "epoch": 3.04,
3213
+ "learning_rate": 2.4881640146537498e-05,
3214
+ "loss": 0.9204,
3215
+ "step": 517
3216
+ },
3217
+ {
3218
+ "epoch": 3.04,
3219
+ "learning_rate": 2.4567338804605756e-05,
3220
+ "loss": 0.9667,
3221
+ "step": 518
3222
+ },
3223
+ {
3224
+ "epoch": 3.05,
3225
+ "learning_rate": 2.4254756980025773e-05,
3226
+ "loss": 0.8439,
3227
+ "step": 519
3228
+ },
3229
+ {
3230
+ "epoch": 3.05,
3231
+ "learning_rate": 2.394390179822382e-05,
3232
+ "loss": 0.8652,
3233
+ "step": 520
3234
+ },
3235
+ {
3236
+ "epoch": 3.06,
3237
+ "learning_rate": 2.3634780345266806e-05,
3238
+ "loss": 0.8782,
3239
+ "step": 521
3240
+ },
3241
+ {
3242
+ "epoch": 3.07,
3243
+ "learning_rate": 2.3327399667700477e-05,
3244
+ "loss": 0.9652,
3245
+ "step": 522
3246
+ },
3247
+ {
3248
+ "epoch": 3.07,
3249
+ "learning_rate": 2.3021766772388986e-05,
3250
+ "loss": 0.8984,
3251
+ "step": 523
3252
+ },
3253
+ {
3254
+ "epoch": 3.08,
3255
+ "learning_rate": 2.2717888626355134e-05,
3256
+ "loss": 0.8815,
3257
+ "step": 524
3258
+ },
3259
+ {
3260
+ "epoch": 3.08,
3261
+ "learning_rate": 2.2415772156621382e-05,
3262
+ "loss": 0.897,
3263
+ "step": 525
3264
+ },
3265
+ {
3266
+ "epoch": 3.09,
3267
+ "learning_rate": 2.211542425005223e-05,
3268
+ "loss": 0.9867,
3269
+ "step": 526
3270
+ },
3271
+ {
3272
+ "epoch": 3.1,
3273
+ "learning_rate": 2.181685175319702e-05,
3274
+ "loss": 0.8769,
3275
+ "step": 527
3276
+ },
3277
+ {
3278
+ "epoch": 3.1,
3279
+ "learning_rate": 2.1520061472133902e-05,
3280
+ "loss": 0.987,
3281
+ "step": 528
3282
+ },
3283
+ {
3284
+ "epoch": 3.11,
3285
+ "learning_rate": 2.122506017231477e-05,
3286
+ "loss": 0.8578,
3287
+ "step": 529
3288
+ },
3289
+ {
3290
+ "epoch": 3.11,
3291
+ "learning_rate": 2.0931854578410905e-05,
3292
+ "loss": 1.0012,
3293
+ "step": 530
3294
+ },
3295
+ {
3296
+ "epoch": 3.12,
3297
+ "learning_rate": 2.064045137415982e-05,
3298
+ "loss": 0.9574,
3299
+ "step": 531
3300
+ },
3301
+ {
3302
+ "epoch": 3.13,
3303
+ "learning_rate": 2.035085720221288e-05,
3304
+ "loss": 1.0041,
3305
+ "step": 532
3306
+ },
3307
+ {
3308
+ "epoch": 3.13,
3309
+ "learning_rate": 2.0063078663983714e-05,
3310
+ "loss": 0.9809,
3311
+ "step": 533
3312
+ },
3313
+ {
3314
+ "epoch": 3.14,
3315
+ "learning_rate": 1.9777122319497986e-05,
3316
+ "loss": 0.912,
3317
+ "step": 534
3318
+ },
3319
+ {
3320
+ "epoch": 3.14,
3321
+ "learning_rate": 1.9492994687243714e-05,
3322
+ "loss": 0.9197,
3323
+ "step": 535
3324
+ },
3325
+ {
3326
+ "epoch": 3.15,
3327
+ "learning_rate": 1.9210702244022617e-05,
3328
+ "loss": 1.0735,
3329
+ "step": 536
3330
+ },
3331
+ {
3332
+ "epoch": 3.16,
3333
+ "learning_rate": 1.893025142480265e-05,
3334
+ "loss": 0.8944,
3335
+ "step": 537
3336
+ },
3337
+ {
3338
+ "epoch": 3.16,
3339
+ "learning_rate": 1.8651648622571128e-05,
3340
+ "loss": 0.9093,
3341
+ "step": 538
3342
+ },
3343
+ {
3344
+ "epoch": 3.17,
3345
+ "learning_rate": 1.837490018818917e-05,
3346
+ "loss": 0.8556,
3347
+ "step": 539
3348
+ },
3349
+ {
3350
+ "epoch": 3.17,
3351
+ "learning_rate": 1.8100012430246837e-05,
3352
+ "loss": 0.8463,
3353
+ "step": 540
3354
+ },
3355
+ {
3356
+ "epoch": 3.18,
3357
+ "learning_rate": 1.7826991614919265e-05,
3358
+ "loss": 0.8961,
3359
+ "step": 541
3360
+ },
3361
+ {
3362
+ "epoch": 3.19,
3363
+ "learning_rate": 1.7555843965823992e-05,
3364
+ "loss": 1.0002,
3365
+ "step": 542
3366
+ },
3367
+ {
3368
+ "epoch": 3.19,
3369
+ "learning_rate": 1.7286575663878877e-05,
3370
+ "loss": 0.9748,
3371
+ "step": 543
3372
+ },
3373
+ {
3374
+ "epoch": 3.2,
3375
+ "learning_rate": 1.7019192847161425e-05,
3376
+ "loss": 0.8891,
3377
+ "step": 544
3378
+ },
3379
+ {
3380
+ "epoch": 3.2,
3381
+ "learning_rate": 1.6753701610768724e-05,
3382
+ "loss": 0.9421,
3383
+ "step": 545
3384
+ },
3385
+ {
3386
+ "epoch": 3.21,
3387
+ "learning_rate": 1.6490108006678494e-05,
3388
+ "loss": 0.9069,
3389
+ "step": 546
3390
+ },
3391
+ {
3392
+ "epoch": 3.21,
3393
+ "eval_loss": 0.7350304126739502,
3394
+ "eval_runtime": 14.3775,
3395
+ "eval_samples_per_second": 56.964,
3396
+ "eval_steps_per_second": 28.517,
3397
+ "step": 546
3398
+ },
3399
+ {
3400
+ "epoch": 3.21,
3401
+ "learning_rate": 1.6228418043611227e-05,
3402
+ "loss": 0.9492,
3403
+ "step": 547
3404
+ },
3405
+ {
3406
+ "epoch": 3.22,
3407
+ "learning_rate": 1.5968637686893186e-05,
3408
+ "loss": 0.932,
3409
+ "step": 548
3410
+ },
3411
+ {
3412
+ "epoch": 3.23,
3413
+ "learning_rate": 1.57107728583203e-05,
3414
+ "loss": 0.8966,
3415
+ "step": 549
3416
+ },
3417
+ {
3418
+ "epoch": 3.23,
3419
+ "learning_rate": 1.545482943602341e-05,
3420
+ "loss": 0.8305,
3421
+ "step": 550
3422
+ },
3423
+ {
3424
+ "epoch": 3.24,
3425
+ "learning_rate": 1.5200813254334012e-05,
3426
+ "loss": 0.8215,
3427
+ "step": 551
3428
+ },
3429
+ {
3430
+ "epoch": 3.24,
3431
+ "learning_rate": 1.4948730103651498e-05,
3432
+ "loss": 0.8472,
3433
+ "step": 552
3434
+ },
3435
+ {
3436
+ "epoch": 3.25,
3437
+ "learning_rate": 1.4698585730310998e-05,
3438
+ "loss": 0.8684,
3439
+ "step": 553
3440
+ },
3441
+ {
3442
+ "epoch": 3.26,
3443
+ "learning_rate": 1.4450385836452429e-05,
3444
+ "loss": 0.8235,
3445
+ "step": 554
3446
+ },
3447
+ {
3448
+ "epoch": 3.26,
3449
+ "learning_rate": 1.4204136079890584e-05,
3450
+ "loss": 0.862,
3451
+ "step": 555
3452
+ },
3453
+ {
3454
+ "epoch": 3.27,
3455
+ "learning_rate": 1.3959842073986085e-05,
3456
+ "loss": 0.8883,
3457
+ "step": 556
3458
+ },
3459
+ {
3460
+ "epoch": 3.27,
3461
+ "learning_rate": 1.371750938751739e-05,
3462
+ "loss": 0.9239,
3463
+ "step": 557
3464
+ },
3465
+ {
3466
+ "epoch": 3.28,
3467
+ "learning_rate": 1.3477143544553995e-05,
3468
+ "loss": 0.873,
3469
+ "step": 558
3470
+ },
3471
+ {
3472
+ "epoch": 3.29,
3473
+ "learning_rate": 1.3238750024330338e-05,
3474
+ "loss": 0.959,
3475
+ "step": 559
3476
+ },
3477
+ {
3478
+ "epoch": 3.29,
3479
+ "learning_rate": 1.300233426112103e-05,
3480
+ "loss": 0.9025,
3481
+ "step": 560
3482
+ },
3483
+ {
3484
+ "epoch": 3.3,
3485
+ "learning_rate": 1.2767901644116941e-05,
3486
+ "loss": 0.8984,
3487
+ "step": 561
3488
+ },
3489
+ {
3490
+ "epoch": 3.3,
3491
+ "learning_rate": 1.2535457517302263e-05,
3492
+ "loss": 0.9417,
3493
+ "step": 562
3494
+ },
3495
+ {
3496
+ "epoch": 3.31,
3497
+ "learning_rate": 1.230500717933285e-05,
3498
+ "loss": 0.836,
3499
+ "step": 563
3500
+ },
3501
+ {
3502
+ "epoch": 3.32,
3503
+ "learning_rate": 1.207655588341534e-05,
3504
+ "loss": 0.9123,
3505
+ "step": 564
3506
+ },
3507
+ {
3508
+ "epoch": 3.32,
3509
+ "learning_rate": 1.1850108837187335e-05,
3510
+ "loss": 1.0009,
3511
+ "step": 565
3512
+ },
3513
+ {
3514
+ "epoch": 3.33,
3515
+ "learning_rate": 1.1625671202598875e-05,
3516
+ "loss": 1.0058,
3517
+ "step": 566
3518
+ },
3519
+ {
3520
+ "epoch": 3.33,
3521
+ "learning_rate": 1.1403248095794628e-05,
3522
+ "loss": 0.9754,
3523
+ "step": 567
3524
+ },
3525
+ {
3526
+ "epoch": 3.34,
3527
+ "learning_rate": 1.1182844586997266e-05,
3528
+ "loss": 0.9161,
3529
+ "step": 568
3530
+ },
3531
+ {
3532
+ "epoch": 3.35,
3533
+ "learning_rate": 1.096446570039198e-05,
3534
+ "loss": 0.8327,
3535
+ "step": 569
3536
+ },
3537
+ {
3538
+ "epoch": 3.35,
3539
+ "learning_rate": 1.0748116414011888e-05,
3540
+ "loss": 0.8486,
3541
+ "step": 570
3542
+ },
3543
+ {
3544
+ "epoch": 3.36,
3545
+ "learning_rate": 1.0533801659624531e-05,
3546
+ "loss": 0.9521,
3547
+ "step": 571
3548
+ },
3549
+ {
3550
+ "epoch": 3.36,
3551
+ "learning_rate": 1.0321526322619534e-05,
3552
+ "loss": 0.9869,
3553
+ "step": 572
3554
+ },
3555
+ {
3556
+ "epoch": 3.37,
3557
+ "learning_rate": 1.0111295241897157e-05,
3558
+ "loss": 0.8474,
3559
+ "step": 573
3560
+ },
3561
+ {
3562
+ "epoch": 3.38,
3563
+ "learning_rate": 9.903113209758096e-06,
3564
+ "loss": 0.9183,
3565
+ "step": 574
3566
+ },
3567
+ {
3568
+ "epoch": 3.38,
3569
+ "learning_rate": 9.696984971794065e-06,
3570
+ "loss": 0.8979,
3571
+ "step": 575
3572
+ },
3573
+ {
3574
+ "epoch": 3.39,
3575
+ "learning_rate": 9.492915226779808e-06,
3576
+ "loss": 0.8548,
3577
+ "step": 576
3578
+ },
3579
+ {
3580
+ "epoch": 3.39,
3581
+ "learning_rate": 9.29090862656593e-06,
3582
+ "loss": 1.033,
3583
+ "step": 577
3584
+ },
3585
+ {
3586
+ "epoch": 3.4,
3587
+ "learning_rate": 9.090969775972736e-06,
3588
+ "loss": 0.8503,
3589
+ "step": 578
3590
+ },
3591
+ {
3592
+ "epoch": 3.41,
3593
+ "learning_rate": 8.89310323268544e-06,
3594
+ "loss": 0.9644,
3595
+ "step": 579
3596
+ },
3597
+ {
3598
+ "epoch": 3.41,
3599
+ "learning_rate": 8.697313507150184e-06,
3600
+ "loss": 0.9816,
3601
+ "step": 580
3602
+ },
3603
+ {
3604
+ "epoch": 3.42,
3605
+ "learning_rate": 8.503605062471187e-06,
3606
+ "loss": 1.0183,
3607
+ "step": 581
3608
+ },
3609
+ {
3610
+ "epoch": 3.42,
3611
+ "learning_rate": 8.311982314309109e-06,
3612
+ "loss": 0.9839,
3613
+ "step": 582
3614
+ },
3615
+ {
3616
+ "epoch": 3.43,
3617
+ "learning_rate": 8.122449630780238e-06,
3618
+ "loss": 0.8224,
3619
+ "step": 583
3620
+ },
3621
+ {
3622
+ "epoch": 3.44,
3623
+ "learning_rate": 7.935011332357112e-06,
3624
+ "loss": 0.8238,
3625
+ "step": 584
3626
+ },
3627
+ {
3628
+ "epoch": 3.44,
3629
+ "learning_rate": 7.749671691769911e-06,
3630
+ "loss": 0.9162,
3631
+ "step": 585
3632
+ },
3633
+ {
3634
+ "epoch": 3.45,
3635
+ "learning_rate": 7.566434933909006e-06,
3636
+ "loss": 0.929,
3637
+ "step": 586
3638
+ },
3639
+ {
3640
+ "epoch": 3.45,
3641
+ "learning_rate": 7.385305235728801e-06,
3642
+ "loss": 1.0165,
3643
+ "step": 587
3644
+ },
3645
+ {
3646
+ "epoch": 3.46,
3647
+ "learning_rate": 7.206286726152434e-06,
3648
+ "loss": 0.8973,
3649
+ "step": 588
3650
+ },
3651
+ {
3652
+ "epoch": 3.46,
3653
+ "eval_loss": 0.7341805100440979,
3654
+ "eval_runtime": 14.5889,
3655
+ "eval_samples_per_second": 56.139,
3656
+ "eval_steps_per_second": 28.104,
3657
+ "step": 588
3658
+ },
3659
+ {
3660
+ "epoch": 3.47,
3661
+ "learning_rate": 7.029383485977625e-06,
3662
+ "loss": 0.8952,
3663
+ "step": 589
3664
+ },
3665
+ {
3666
+ "epoch": 3.47,
3667
+ "learning_rate": 6.854599547783736e-06,
3668
+ "loss": 0.9449,
3669
+ "step": 590
3670
+ },
3671
+ {
3672
+ "epoch": 3.48,
3673
+ "learning_rate": 6.681938895839746e-06,
3674
+ "loss": 0.9427,
3675
+ "step": 591
3676
+ },
3677
+ {
3678
+ "epoch": 3.48,
3679
+ "learning_rate": 6.5114054660135315e-06,
3680
+ "loss": 0.9323,
3681
+ "step": 592
3682
+ },
3683
+ {
3684
+ "epoch": 3.49,
3685
+ "learning_rate": 6.343003145682114e-06,
3686
+ "loss": 0.9059,
3687
+ "step": 593
3688
+ },
3689
+ {
3690
+ "epoch": 3.5,
3691
+ "learning_rate": 6.176735773642961e-06,
3692
+ "loss": 0.8749,
3693
+ "step": 594
3694
+ },
3695
+ {
3696
+ "epoch": 3.5,
3697
+ "learning_rate": 6.012607140026605e-06,
3698
+ "loss": 0.9846,
3699
+ "step": 595
3700
+ },
3701
+ {
3702
+ "epoch": 3.51,
3703
+ "learning_rate": 5.850620986210198e-06,
3704
+ "loss": 0.8623,
3705
+ "step": 596
3706
+ },
3707
+ {
3708
+ "epoch": 3.51,
3709
+ "learning_rate": 5.69078100473216e-06,
3710
+ "loss": 0.9239,
3711
+ "step": 597
3712
+ },
3713
+ {
3714
+ "epoch": 3.52,
3715
+ "learning_rate": 5.533090839208133e-06,
3716
+ "loss": 0.9307,
3717
+ "step": 598
3718
+ },
3719
+ {
3720
+ "epoch": 3.53,
3721
+ "learning_rate": 5.377554084247771e-06,
3722
+ "loss": 0.9144,
3723
+ "step": 599
3724
+ },
3725
+ {
3726
+ "epoch": 3.53,
3727
+ "learning_rate": 5.224174285372974e-06,
3728
+ "loss": 0.9267,
3729
+ "step": 600
3730
+ },
3731
+ {
3732
+ "epoch": 3.54,
3733
+ "learning_rate": 5.0729549389369245e-06,
3734
+ "loss": 0.9614,
3735
+ "step": 601
3736
+ },
3737
+ {
3738
+ "epoch": 3.54,
3739
+ "learning_rate": 4.923899492044437e-06,
3740
+ "loss": 0.9391,
3741
+ "step": 602
3742
+ },
3743
+ {
3744
+ "epoch": 3.55,
3745
+ "learning_rate": 4.777011342473392e-06,
3746
+ "loss": 1.0601,
3747
+ "step": 603
3748
+ },
3749
+ {
3750
+ "epoch": 3.56,
3751
+ "learning_rate": 4.632293838597246e-06,
3752
+ "loss": 1.0046,
3753
+ "step": 604
3754
+ },
3755
+ {
3756
+ "epoch": 3.56,
3757
+ "learning_rate": 4.489750279308757e-06,
3758
+ "loss": 0.9584,
3759
+ "step": 605
3760
+ },
3761
+ {
3762
+ "epoch": 3.57,
3763
+ "learning_rate": 4.349383913944771e-06,
3764
+ "loss": 0.8467,
3765
+ "step": 606
3766
+ },
3767
+ {
3768
+ "epoch": 3.57,
3769
+ "learning_rate": 4.211197942212086e-06,
3770
+ "loss": 0.9803,
3771
+ "step": 607
3772
+ },
3773
+ {
3774
+ "epoch": 3.58,
3775
+ "learning_rate": 4.075195514114593e-06,
3776
+ "loss": 0.9995,
3777
+ "step": 608
3778
+ },
3779
+ {
3780
+ "epoch": 3.59,
3781
+ "learning_rate": 3.941379729881456e-06,
3782
+ "loss": 0.9114,
3783
+ "step": 609
3784
+ },
3785
+ {
3786
+ "epoch": 3.59,
3787
+ "learning_rate": 3.8097536398963963e-06,
3788
+ "loss": 0.9629,
3789
+ "step": 610
3790
+ },
3791
+ {
3792
+ "epoch": 3.6,
3793
+ "learning_rate": 3.6803202446282214e-06,
3794
+ "loss": 1.0647,
3795
+ "step": 611
3796
+ },
3797
+ {
3798
+ "epoch": 3.6,
3799
+ "learning_rate": 3.5530824945623542e-06,
3800
+ "loss": 0.8882,
3801
+ "step": 612
3802
+ },
3803
+ {
3804
+ "epoch": 3.61,
3805
+ "learning_rate": 3.4280432901336425e-06,
3806
+ "loss": 0.9751,
3807
+ "step": 613
3808
+ },
3809
+ {
3810
+ "epoch": 3.61,
3811
+ "learning_rate": 3.3052054816602452e-06,
3812
+ "loss": 0.9553,
3813
+ "step": 614
3814
+ },
3815
+ {
3816
+ "epoch": 3.62,
3817
+ "learning_rate": 3.184571869278574e-06,
3818
+ "loss": 0.8738,
3819
+ "step": 615
3820
+ },
3821
+ {
3822
+ "epoch": 3.63,
3823
+ "learning_rate": 3.0661452028795336e-06,
3824
+ "loss": 0.8258,
3825
+ "step": 616
3826
+ },
3827
+ {
3828
+ "epoch": 3.63,
3829
+ "learning_rate": 2.9499281820458692e-06,
3830
+ "loss": 0.9245,
3831
+ "step": 617
3832
+ },
3833
+ {
3834
+ "epoch": 3.64,
3835
+ "learning_rate": 2.835923455990508e-06,
3836
+ "loss": 0.9208,
3837
+ "step": 618
3838
+ },
3839
+ {
3840
+ "epoch": 3.64,
3841
+ "learning_rate": 2.7241336234962944e-06,
3842
+ "loss": 1.0179,
3843
+ "step": 619
3844
+ },
3845
+ {
3846
+ "epoch": 3.65,
3847
+ "learning_rate": 2.6145612328566717e-06,
3848
+ "loss": 0.8535,
3849
+ "step": 620
3850
+ },
3851
+ {
3852
+ "epoch": 3.66,
3853
+ "learning_rate": 2.5072087818176382e-06,
3854
+ "loss": 0.889,
3855
+ "step": 621
3856
+ },
3857
+ {
3858
+ "epoch": 3.66,
3859
+ "learning_rate": 2.402078717520795e-06,
3860
+ "loss": 0.9205,
3861
+ "step": 622
3862
+ },
3863
+ {
3864
+ "epoch": 3.67,
3865
+ "learning_rate": 2.2991734364475215e-06,
3866
+ "loss": 0.7831,
3867
+ "step": 623
3868
+ },
3869
+ {
3870
+ "epoch": 3.67,
3871
+ "learning_rate": 2.19849528436441e-06,
3872
+ "loss": 0.9609,
3873
+ "step": 624
3874
+ },
3875
+ {
3876
+ "epoch": 3.68,
3877
+ "learning_rate": 2.1000465562697856e-06,
3878
+ "loss": 0.9499,
3879
+ "step": 625
3880
+ },
3881
+ {
3882
+ "epoch": 3.69,
3883
+ "learning_rate": 2.003829496341325e-06,
3884
+ "loss": 0.9191,
3885
+ "step": 626
3886
+ },
3887
+ {
3888
+ "epoch": 3.69,
3889
+ "learning_rate": 1.9098462978849873e-06,
3890
+ "loss": 0.8958,
3891
+ "step": 627
3892
+ },
3893
+ {
3894
+ "epoch": 3.7,
3895
+ "learning_rate": 1.8180991032849426e-06,
3896
+ "loss": 0.9472,
3897
+ "step": 628
3898
+ },
3899
+ {
3900
+ "epoch": 3.7,
3901
+ "learning_rate": 1.7285900039547998e-06,
3902
+ "loss": 0.9246,
3903
+ "step": 629
3904
+ },
3905
+ {
3906
+ "epoch": 3.71,
3907
+ "learning_rate": 1.6413210402898893e-06,
3908
+ "loss": 0.9359,
3909
+ "step": 630
3910
+ },
3911
+ {
3912
+ "epoch": 3.71,
3913
+ "eval_loss": 0.7337182760238647,
3914
+ "eval_runtime": 14.3549,
3915
+ "eval_samples_per_second": 57.054,
3916
+ "eval_steps_per_second": 28.562,
3917
+ "step": 630
3918
+ },
3919
+ {
3920
+ "epoch": 3.72,
3921
+ "learning_rate": 1.5562942016207338e-06,
3922
+ "loss": 0.8341,
3923
+ "step": 631
3924
+ },
3925
+ {
3926
+ "epoch": 3.72,
3927
+ "learning_rate": 1.473511426167784e-06,
3928
+ "loss": 0.9046,
3929
+ "step": 632
3930
+ },
3931
+ {
3932
+ "epoch": 3.73,
3933
+ "learning_rate": 1.3929746009971433e-06,
3934
+ "loss": 0.8575,
3935
+ "step": 633
3936
+ },
3937
+ {
3938
+ "epoch": 3.73,
3939
+ "learning_rate": 1.3146855619776134e-06,
3940
+ "loss": 0.8378,
3941
+ "step": 634
3942
+ },
3943
+ {
3944
+ "epoch": 3.74,
3945
+ "learning_rate": 1.2386460937387822e-06,
3946
+ "loss": 0.8821,
3947
+ "step": 635
3948
+ },
3949
+ {
3950
+ "epoch": 3.75,
3951
+ "learning_rate": 1.1648579296304253e-06,
3952
+ "loss": 0.8412,
3953
+ "step": 636
3954
+ },
3955
+ {
3956
+ "epoch": 3.75,
3957
+ "learning_rate": 1.0933227516829347e-06,
3958
+ "loss": 0.89,
3959
+ "step": 637
3960
+ },
3961
+ {
3962
+ "epoch": 3.76,
3963
+ "learning_rate": 1.0240421905689745e-06,
3964
+ "loss": 0.8251,
3965
+ "step": 638
3966
+ },
3967
+ {
3968
+ "epoch": 3.76,
3969
+ "learning_rate": 9.570178255663532e-07,
3970
+ "loss": 0.71,
3971
+ "step": 639
3972
+ },
3973
+ {
3974
+ "epoch": 3.77,
3975
+ "learning_rate": 8.922511845219971e-07,
3976
+ "loss": 0.8918,
3977
+ "step": 640
3978
+ },
3979
+ {
3980
+ "epoch": 3.78,
3981
+ "learning_rate": 8.297437438170797e-07,
3982
+ "loss": 0.8273,
3983
+ "step": 641
3984
+ },
3985
+ {
3986
+ "epoch": 3.78,
3987
+ "learning_rate": 7.694969283334575e-07,
3988
+ "loss": 0.9645,
3989
+ "step": 642
3990
+ },
3991
+ {
3992
+ "epoch": 3.79,
3993
+ "learning_rate": 7.115121114211199e-07,
3994
+ "loss": 0.9352,
3995
+ "step": 643
3996
+ },
3997
+ {
3998
+ "epoch": 3.79,
3999
+ "learning_rate": 6.557906148669024e-07,
4000
+ "loss": 0.8733,
4001
+ "step": 644
4002
+ },
4003
+ {
4004
+ "epoch": 3.8,
4005
+ "learning_rate": 6.023337088643665e-07,
4006
+ "loss": 0.8949,
4007
+ "step": 645
4008
+ },
4009
+ {
4010
+ "epoch": 3.81,
4011
+ "learning_rate": 5.51142611984834e-07,
4012
+ "loss": 0.8571,
4013
+ "step": 646
4014
+ },
4015
+ {
4016
+ "epoch": 3.81,
4017
+ "learning_rate": 5.022184911495864e-07,
4018
+ "loss": 0.8543,
4019
+ "step": 647
4020
+ },
4021
+ {
4022
+ "epoch": 3.82,
4023
+ "learning_rate": 4.555624616033427e-07,
4024
+ "loss": 0.9077,
4025
+ "step": 648
4026
+ },
4027
+ {
4028
+ "epoch": 3.82,
4029
+ "learning_rate": 4.111755868887346e-07,
4030
+ "loss": 0.8877,
4031
+ "step": 649
4032
+ },
4033
+ {
4034
+ "epoch": 3.83,
4035
+ "learning_rate": 3.6905887882213717e-07,
4036
+ "loss": 1.1382,
4037
+ "step": 650
4038
+ },
4039
+ {
4040
+ "epoch": 3.84,
4041
+ "learning_rate": 3.292132974705653e-07,
4042
+ "loss": 0.8221,
4043
+ "step": 651
4044
+ },
4045
+ {
4046
+ "epoch": 3.84,
4047
+ "learning_rate": 2.916397511298019e-07,
4048
+ "loss": 0.8317,
4049
+ "step": 652
4050
+ },
4051
+ {
4052
+ "epoch": 3.85,
4053
+ "learning_rate": 2.5633909630371487e-07,
4054
+ "loss": 0.9018,
4055
+ "step": 653
4056
+ },
4057
+ {
4058
+ "epoch": 3.85,
4059
+ "learning_rate": 2.2331213768468363e-07,
4060
+ "loss": 0.9389,
4061
+ "step": 654
4062
+ },
4063
+ {
4064
+ "epoch": 3.86,
4065
+ "learning_rate": 1.925596281353026e-07,
4066
+ "loss": 0.8858,
4067
+ "step": 655
4068
+ },
4069
+ {
4070
+ "epoch": 3.87,
4071
+ "learning_rate": 1.6408226867118403e-07,
4072
+ "loss": 0.8439,
4073
+ "step": 656
4074
+ },
4075
+ {
4076
+ "epoch": 3.87,
4077
+ "learning_rate": 1.378807084450151e-07,
4078
+ "loss": 0.9853,
4079
+ "step": 657
4080
+ },
4081
+ {
4082
+ "epoch": 3.88,
4083
+ "learning_rate": 1.1395554473171422e-07,
4084
+ "loss": 0.7637,
4085
+ "step": 658
4086
+ },
4087
+ {
4088
+ "epoch": 3.88,
4089
+ "learning_rate": 9.230732291485301e-08,
4090
+ "loss": 0.9044,
4091
+ "step": 659
4092
+ },
4093
+ {
4094
+ "epoch": 3.89,
4095
+ "learning_rate": 7.293653647421073e-08,
4096
+ "loss": 0.8802,
4097
+ "step": 660
4098
+ },
4099
+ {
4100
+ "epoch": 3.9,
4101
+ "learning_rate": 5.584362697453882e-08,
4102
+ "loss": 0.9122,
4103
+ "step": 661
4104
+ },
4105
+ {
4106
+ "epoch": 3.9,
4107
+ "learning_rate": 4.102898405545785e-08,
4108
+ "loss": 1.0282,
4109
+ "step": 662
4110
+ },
4111
+ {
4112
+ "epoch": 3.91,
4113
+ "learning_rate": 2.8492945422620155e-08,
4114
+ "loss": 0.8859,
4115
+ "step": 663
4116
+ },
4117
+ {
4118
+ "epoch": 3.91,
4119
+ "learning_rate": 1.8235796839982665e-08,
4120
+ "loss": 0.8389,
4121
+ "step": 664
4122
+ },
4123
+ {
4124
+ "epoch": 3.92,
4125
+ "learning_rate": 1.0257772123312137e-08,
4126
+ "loss": 0.9671,
4127
+ "step": 665
4128
+ },
4129
+ {
4130
+ "epoch": 3.93,
4131
+ "learning_rate": 4.559053134822744e-09,
4132
+ "loss": 1.0085,
4133
+ "step": 666
4134
+ },
4135
+ {
4136
+ "epoch": 3.93,
4137
+ "learning_rate": 1.1397697790793694e-09,
4138
+ "loss": 0.8158,
4139
+ "step": 667
4140
+ },
4141
+ {
4142
+ "epoch": 3.94,
4143
+ "learning_rate": 0.0,
4144
+ "loss": 0.8907,
4145
+ "step": 668
4146
+ }
4147
+ ],
4148
+ "logging_steps": 1,
4149
+ "max_steps": 668,
4150
+ "num_input_tokens_seen": 0,
4151
+ "num_train_epochs": 4,
4152
+ "save_steps": 167,
4153
+ "total_flos": 1.391544932153426e+17,
4154
+ "train_batch_size": 2,
4155
+ "trial_name": null,
4156
+ "trial_params": null
4157
+ }
checkpoint-668/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad14298be73cbe854ab00522590054d32e49c4c47f917719c135f6380025fd0
3
+ size 5368
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": false,
31
+ "load_in_8bit": true,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 10000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.0.dev0",
40
+ "use_cache": false,
41
+ "vocab_size": 32000
42
+ }
runs/Feb20_20-18-56_fe14e8fd7da0/events.out.tfevents.1708460336.fe14e8fd7da0.2298.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e7cf34102f0f127af1fecf5c84e9badba1c93691d56417a121cb4903cff303
3
+ size 114754
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "trust_remote_code": false,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }