Pclanglais commited on
Commit
c215d89
1 Parent(s): ff6afb0

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. adapter/README.md +133 -0
  2. adapter/adapter_config.json +39 -0
  3. adapter/adapter_model.bin +3 -0
  4. adapter/checkpoint-1220/README.md +204 -0
  5. adapter/checkpoint-1220/adapter_config.json +39 -0
  6. adapter/checkpoint-1220/adapter_model.safetensors +3 -0
  7. adapter/checkpoint-1220/optimizer.pt +3 -0
  8. adapter/checkpoint-1220/rng_state.pth +3 -0
  9. adapter/checkpoint-1220/scheduler.pt +3 -0
  10. adapter/checkpoint-1220/special_tokens_map.json +30 -0
  11. adapter/checkpoint-1220/tokenizer.json +0 -0
  12. adapter/checkpoint-1220/tokenizer.model +3 -0
  13. adapter/checkpoint-1220/tokenizer_config.json +47 -0
  14. adapter/checkpoint-1220/trainer_state.json +0 -0
  15. adapter/checkpoint-1220/training_args.bin +3 -0
  16. adapter/checkpoint-206/README.md +204 -0
  17. adapter/checkpoint-206/adapter_config.json +39 -0
  18. adapter/checkpoint-206/adapter_model.safetensors +3 -0
  19. adapter/checkpoint-206/optimizer.pt +3 -0
  20. adapter/checkpoint-206/rng_state.pth +3 -0
  21. adapter/checkpoint-206/scheduler.pt +3 -0
  22. adapter/checkpoint-206/special_tokens_map.json +30 -0
  23. adapter/checkpoint-206/tokenizer.json +0 -0
  24. adapter/checkpoint-206/tokenizer.model +3 -0
  25. adapter/checkpoint-206/tokenizer_config.json +47 -0
  26. adapter/checkpoint-206/trainer_state.json +1487 -0
  27. adapter/checkpoint-206/training_args.bin +3 -0
  28. adapter/checkpoint-309/README.md +204 -0
  29. adapter/checkpoint-309/adapter_config.json +39 -0
  30. adapter/checkpoint-309/adapter_model.safetensors +3 -0
  31. adapter/checkpoint-309/optimizer.pt +3 -0
  32. adapter/checkpoint-309/rng_state.pth +3 -0
  33. adapter/checkpoint-309/scheduler.pt +3 -0
  34. adapter/checkpoint-309/special_tokens_map.json +30 -0
  35. adapter/checkpoint-309/tokenizer.json +0 -0
  36. adapter/checkpoint-309/tokenizer.model +3 -0
  37. adapter/checkpoint-309/tokenizer_config.json +47 -0
  38. adapter/checkpoint-309/trainer_state.json +2216 -0
  39. adapter/checkpoint-309/training_args.bin +3 -0
  40. adapter/checkpoint-610/README.md +204 -0
  41. adapter/checkpoint-610/adapter_config.json +39 -0
  42. adapter/checkpoint-610/adapter_model.safetensors +3 -0
  43. adapter/checkpoint-610/optimizer.pt +3 -0
  44. adapter/checkpoint-610/rng_state.pth +3 -0
  45. adapter/checkpoint-610/scheduler.pt +3 -0
  46. adapter/checkpoint-610/special_tokens_map.json +30 -0
  47. adapter/checkpoint-610/tokenizer.json +0 -0
  48. adapter/checkpoint-610/tokenizer.model +3 -0
  49. adapter/checkpoint-610/tokenizer_config.json +47 -0
  50. adapter/checkpoint-610/trainer_state.json +0 -0
adapter/README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: jamba
6
+ model-index:
7
+ - name: out
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<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)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.0`
18
+ ```yaml
19
+ base_model: jamba
20
+ trust_remote_code: true
21
+
22
+ load_in_8bit: false
23
+ load_in_4bit: true
24
+ strict: false
25
+
26
+ datasets:
27
+ - path: scikit_admin_result.json
28
+ ds_type: json
29
+ type: sharegpt
30
+ conversation: chatml
31
+ dataset_prepared_path:
32
+ val_set_size: 0.01
33
+ output_dir: ./out
34
+
35
+ sequence_len: 6000
36
+ sample_packing: true
37
+ pad_to_sequence_len: false
38
+ eval_sample_packing: true
39
+
40
+ use_wandb: false
41
+
42
+ adapter: qlora
43
+ lora_r: 8
44
+ lora_alpha: 16
45
+ lora_dropout: 0.05
46
+ lora_target_linear: true
47
+
48
+ low_cpu_mem_usage: true
49
+ gradient_accumulation_steps: 4
50
+ micro_batch_size: 1
51
+ num_epochs: 2
52
+ optimizer: paged_adamw_8bit
53
+ lr_scheduler: cosine
54
+ learning_rate: 0.0002
55
+
56
+ train_on_inputs: false
57
+ group_by_length: false
58
+ bf16: auto
59
+ fp16:
60
+ tf32: false
61
+
62
+ gradient_checkpointing: true
63
+ gradient_checkpointing_kwargs:
64
+ use_reentrant: false
65
+ early_stopping_patience:
66
+ resume_from_checkpoint:
67
+ local_rank:
68
+ logging_steps: 1
69
+ xformers_attention:
70
+ flash_attention: true
71
+
72
+ warmup_steps: 10
73
+ evals_per_epoch: 2
74
+ saves_per_epoch: 2
75
+ debug:
76
+ weight_decay: 0.0
77
+ special_tokens:
78
+
79
+ ```
80
+
81
+ </details><br>
82
+
83
+ # out
84
+
85
+ This model was trained from scratch on the None dataset.
86
+ It achieves the following results on the evaluation set:
87
+ - Loss: 0.2356
88
+
89
+ ## Model description
90
+
91
+ More information needed
92
+
93
+ ## Intended uses & limitations
94
+
95
+ More information needed
96
+
97
+ ## Training and evaluation data
98
+
99
+ More information needed
100
+
101
+ ## Training procedure
102
+
103
+ ### Training hyperparameters
104
+
105
+ The following hyperparameters were used during training:
106
+ - learning_rate: 0.0002
107
+ - train_batch_size: 1
108
+ - eval_batch_size: 1
109
+ - seed: 42
110
+ - gradient_accumulation_steps: 4
111
+ - total_train_batch_size: 4
112
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
113
+ - lr_scheduler_type: cosine
114
+ - lr_scheduler_warmup_steps: 10
115
+ - num_epochs: 2
116
+
117
+ ### Training results
118
+
119
+ | Training Loss | Epoch | Step | Validation Loss |
120
+ |:-------------:|:-----:|:----:|:---------------:|
121
+ | 0.4337 | 0.0 | 1 | 0.3783 |
122
+ | 0.2537 | 0.5 | 103 | 0.2345 |
123
+ | 0.2161 | 1.0 | 206 | 0.2258 |
124
+ | 0.1821 | 1.47 | 309 | 0.2356 |
125
+
126
+
127
+ ### Framework versions
128
+
129
+ - PEFT 0.10.0
130
+ - Transformers 4.40.0.dev0
131
+ - Pytorch 2.2.2+cu121
132
+ - Datasets 2.18.0
133
+ - Tokenizers 0.15.0
adapter/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "jamba",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "router",
24
+ "k_proj",
25
+ "up_proj",
26
+ "dt_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "x_proj",
31
+ "out_proj",
32
+ "gate_proj",
33
+ "o_proj",
34
+ "in_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7d992af165663bcede80898140ca1b1c88f4a83c509c23d81abaef94685fea
3
+ size 532044386
adapter/checkpoint-1220/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /home/outscale/jamba
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 0.10.0
adapter/checkpoint-1220/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/outscale/jamba",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "router",
24
+ "x_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "out_proj",
28
+ "o_proj",
29
+ "dt_proj",
30
+ "in_proj",
31
+ "q_proj",
32
+ "k_proj",
33
+ "up_proj",
34
+ "v_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter/checkpoint-1220/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a79da9020bad6f04a5d5662c39d847cff8a040e9b3cc3a610cf10fd6b6b2e0c
3
+ size 531607760
adapter/checkpoint-1220/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e8a95df8b8d56a2489c11debc4fcd2c49c453f163b8fc6af6aa377c46a534e
3
+ size 269103876
adapter/checkpoint-1220/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56414d9cbcb8df569c2ba88a21c53a195cbc6e6aba893db9945cdc2551afdc43
3
+ size 14244
adapter/checkpoint-1220/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac0d71aec854a991c6e7dcb7a2b1d7b43a0bbe43ebb04791cb66d2aca6b64988
3
+ size 1064
adapter/checkpoint-1220/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapter/checkpoint-1220/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapter/checkpoint-1220/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
3
+ size 1124742
adapter/checkpoint-1220/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|unk|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<|startoftext|>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<|endoftext|>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<|pad|>",
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<|unk|>",
46
+ "use_default_system_prompt": false
47
+ }
adapter/checkpoint-1220/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
adapter/checkpoint-1220/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3ca19dcb09bc4a6b050b2e4f6e4ca65064636feefe2dfba6a41870322cb6af
3
+ size 5752
adapter/checkpoint-206/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: jamba
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 0.10.0
adapter/checkpoint-206/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "jamba",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "router",
24
+ "k_proj",
25
+ "up_proj",
26
+ "dt_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "x_proj",
31
+ "out_proj",
32
+ "gate_proj",
33
+ "o_proj",
34
+ "in_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter/checkpoint-206/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e677677bfec671f0911a810fd9b0bf20714d52d5ce03dc5221fb70513a1262
3
+ size 531607760
adapter/checkpoint-206/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716bc4dad716654d3d93ac99c6fc2bd45f39ff322ff26b79e52725cdeaae0cf6
3
+ size 269101956
adapter/checkpoint-206/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2978a5426f1128c6e1502b9139bd97cf1e43d6b6a515925c1889a0dad39c001a
3
+ size 14244
adapter/checkpoint-206/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7a30aad0caae419d7e5867d8acb8c34f83ded00c4e91be27a719b3c5cc6679
3
+ size 1064
adapter/checkpoint-206/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapter/checkpoint-206/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapter/checkpoint-206/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
3
+ size 1124742
adapter/checkpoint-206/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|unk|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<|startoftext|>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<|endoftext|>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<|pad|>",
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<|unk|>",
46
+ "use_default_system_prompt": false
47
+ }
adapter/checkpoint-206/trainer_state.json ADDED
@@ -0,0 +1,1487 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0012150668286757,
5
+ "eval_steps": 103,
6
+ "global_step": 206,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.3593529462814331,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.4337,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 0.3783022463321686,
21
+ "eval_runtime": 12.9552,
22
+ "eval_samples_per_second": 1.93,
23
+ "eval_steps_per_second": 1.93,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.3430859446525574,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.4605,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.3275960683822632,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.39,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 0.3221317529678345,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.3372,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "grad_norm": 0.3926704227924347,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.3333,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03,
56
+ "grad_norm": 0.2960835099220276,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.3671,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.03,
63
+ "grad_norm": 0.3393571078777313,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.327,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.04,
70
+ "grad_norm": 0.2799758017063141,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.2933,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.04,
77
+ "grad_norm": 0.3084808886051178,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.3505,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.05,
84
+ "grad_norm": 0.23642300069332123,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.3289,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "grad_norm": 0.369229793548584,
92
+ "learning_rate": 0.00019999691576447898,
93
+ "loss": 0.3049,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.06,
98
+ "grad_norm": 0.2706857919692993,
99
+ "learning_rate": 0.00019998766324816607,
100
+ "loss": 0.3425,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.06,
105
+ "grad_norm": 0.21327799558639526,
106
+ "learning_rate": 0.00019997224302180006,
107
+ "loss": 0.2686,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.07,
112
+ "grad_norm": 0.26732948422431946,
113
+ "learning_rate": 0.00019995065603657316,
114
+ "loss": 0.2987,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.07,
119
+ "grad_norm": 0.2009548544883728,
120
+ "learning_rate": 0.0001999229036240723,
121
+ "loss": 0.2668,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.08,
126
+ "grad_norm": 0.23616977035999298,
127
+ "learning_rate": 0.00019988898749619702,
128
+ "loss": 0.2962,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.08,
133
+ "grad_norm": 0.18399174511432648,
134
+ "learning_rate": 0.00019984890974505381,
135
+ "loss": 0.2238,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.09,
140
+ "grad_norm": 0.24744661152362823,
141
+ "learning_rate": 0.00019980267284282717,
142
+ "loss": 0.2628,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.09,
147
+ "grad_norm": 0.22109034657478333,
148
+ "learning_rate": 0.00019975027964162702,
149
+ "loss": 0.3143,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.1,
154
+ "grad_norm": 0.21471348404884338,
155
+ "learning_rate": 0.0001996917333733128,
156
+ "loss": 0.3436,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1,
161
+ "grad_norm": 0.2112409919500351,
162
+ "learning_rate": 0.00019962703764929413,
163
+ "loss": 0.2714,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.11,
168
+ "grad_norm": 0.19044426083564758,
169
+ "learning_rate": 0.00019955619646030802,
170
+ "loss": 0.2335,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "grad_norm": 0.21945005655288696,
176
+ "learning_rate": 0.00019947921417617267,
177
+ "loss": 0.2381,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.12,
182
+ "grad_norm": 0.1864914447069168,
183
+ "learning_rate": 0.000199396095545518,
184
+ "loss": 0.287,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.12,
189
+ "grad_norm": 0.2413000762462616,
190
+ "learning_rate": 0.00019930684569549264,
191
+ "loss": 0.1813,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.13,
196
+ "grad_norm": 0.20038250088691711,
197
+ "learning_rate": 0.0001992114701314478,
198
+ "loss": 0.2722,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.13,
203
+ "grad_norm": 0.16239097714424133,
204
+ "learning_rate": 0.0001991099747365975,
205
+ "loss": 0.1917,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.14,
210
+ "grad_norm": 0.19039247930049896,
211
+ "learning_rate": 0.00019900236577165576,
212
+ "loss": 0.2665,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.14,
217
+ "grad_norm": 0.17717348039150238,
218
+ "learning_rate": 0.0001988886498744505,
219
+ "loss": 0.2667,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.15,
224
+ "grad_norm": 0.18755286931991577,
225
+ "learning_rate": 0.00019876883405951377,
226
+ "loss": 0.1775,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.15,
231
+ "grad_norm": 0.1621539294719696,
232
+ "learning_rate": 0.00019864292571764955,
233
+ "loss": 0.2292,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.16,
238
+ "grad_norm": 0.1834522783756256,
239
+ "learning_rate": 0.0001985109326154774,
240
+ "loss": 0.2327,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.16,
245
+ "grad_norm": 0.18009088933467865,
246
+ "learning_rate": 0.00019837286289495361,
247
+ "loss": 0.2325,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.17,
252
+ "grad_norm": 0.16372188925743103,
253
+ "learning_rate": 0.0001982287250728689,
254
+ "loss": 0.2748,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.17,
259
+ "grad_norm": 0.16966991126537323,
260
+ "learning_rate": 0.00019807852804032305,
261
+ "loss": 0.2353,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.17,
266
+ "grad_norm": 0.18791744112968445,
267
+ "learning_rate": 0.00019792228106217658,
268
+ "loss": 0.2693,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.18,
273
+ "grad_norm": 0.16828736662864685,
274
+ "learning_rate": 0.0001977599937764791,
275
+ "loss": 0.1752,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.18,
280
+ "grad_norm": 0.1636415272951126,
281
+ "learning_rate": 0.00019759167619387476,
282
+ "loss": 0.2961,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.19,
287
+ "grad_norm": 0.152165487408638,
288
+ "learning_rate": 0.00019741733869698495,
289
+ "loss": 0.1954,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.19,
294
+ "grad_norm": 0.1838696449995041,
295
+ "learning_rate": 0.00019723699203976766,
296
+ "loss": 0.2039,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.2,
301
+ "grad_norm": 0.170082688331604,
302
+ "learning_rate": 0.00019705064734685425,
303
+ "loss": 0.2228,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.2,
308
+ "grad_norm": 0.1489935666322708,
309
+ "learning_rate": 0.0001968583161128631,
310
+ "loss": 0.185,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.21,
315
+ "grad_norm": 0.1501648873090744,
316
+ "learning_rate": 0.00019666001020169073,
317
+ "loss": 0.2198,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.21,
322
+ "grad_norm": 0.24484610557556152,
323
+ "learning_rate": 0.00019645574184577982,
324
+ "loss": 0.2514,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.22,
329
+ "grad_norm": 0.16400669515132904,
330
+ "learning_rate": 0.00019624552364536473,
331
+ "loss": 0.283,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.22,
336
+ "grad_norm": 0.15034696459770203,
337
+ "learning_rate": 0.0001960293685676943,
338
+ "loss": 0.1637,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.23,
343
+ "grad_norm": 0.15385685861110687,
344
+ "learning_rate": 0.00019580728994623195,
345
+ "loss": 0.2905,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.23,
350
+ "grad_norm": 0.16004744172096252,
351
+ "learning_rate": 0.00019557930147983302,
352
+ "loss": 0.2173,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.24,
357
+ "grad_norm": 0.17182469367980957,
358
+ "learning_rate": 0.0001953454172319001,
359
+ "loss": 0.2147,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.24,
364
+ "grad_norm": 0.1576426774263382,
365
+ "learning_rate": 0.00019510565162951537,
366
+ "loss": 0.284,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.25,
371
+ "grad_norm": 0.14034013450145721,
372
+ "learning_rate": 0.00019486001946255046,
373
+ "loss": 0.1671,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.25,
378
+ "grad_norm": 0.1770170032978058,
379
+ "learning_rate": 0.00019460853588275454,
380
+ "loss": 0.205,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.26,
385
+ "grad_norm": 0.14077183604240417,
386
+ "learning_rate": 0.00019435121640281938,
387
+ "loss": 0.209,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.26,
392
+ "grad_norm": 0.2193373441696167,
393
+ "learning_rate": 0.00019408807689542257,
394
+ "loss": 0.2125,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.27,
399
+ "grad_norm": 0.1439114212989807,
400
+ "learning_rate": 0.00019381913359224842,
401
+ "loss": 0.1611,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.27,
406
+ "grad_norm": 0.16939564049243927,
407
+ "learning_rate": 0.00019354440308298675,
408
+ "loss": 0.2189,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.28,
413
+ "grad_norm": 0.17016972601413727,
414
+ "learning_rate": 0.00019326390231430942,
415
+ "loss": 0.2129,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.28,
420
+ "grad_norm": 0.16602838039398193,
421
+ "learning_rate": 0.00019297764858882514,
422
+ "loss": 0.23,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.29,
427
+ "grad_norm": 0.21853233873844147,
428
+ "learning_rate": 0.00019268565956401208,
429
+ "loss": 0.1879,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.29,
434
+ "grad_norm": 0.18649564683437347,
435
+ "learning_rate": 0.0001923879532511287,
436
+ "loss": 0.2063,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.3,
441
+ "grad_norm": 0.16304822266101837,
442
+ "learning_rate": 0.00019208454801410266,
443
+ "loss": 0.2182,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.3,
448
+ "grad_norm": 0.1357814073562622,
449
+ "learning_rate": 0.00019177546256839812,
450
+ "loss": 0.1912,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.31,
455
+ "grad_norm": 0.1645856499671936,
456
+ "learning_rate": 0.00019146071597986138,
457
+ "loss": 0.2498,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.31,
462
+ "grad_norm": 0.20048978924751282,
463
+ "learning_rate": 0.00019114032766354453,
464
+ "loss": 0.3207,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.32,
469
+ "grad_norm": 0.15142077207565308,
470
+ "learning_rate": 0.00019081431738250814,
471
+ "loss": 0.2102,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.32,
476
+ "grad_norm": 0.15482479333877563,
477
+ "learning_rate": 0.00019048270524660196,
478
+ "loss": 0.2706,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.33,
483
+ "grad_norm": 0.15685780346393585,
484
+ "learning_rate": 0.00019014551171122457,
485
+ "loss": 0.1898,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.33,
490
+ "grad_norm": 0.18191099166870117,
491
+ "learning_rate": 0.00018980275757606157,
492
+ "loss": 0.2838,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.34,
497
+ "grad_norm": 0.1533990502357483,
498
+ "learning_rate": 0.0001894544639838025,
499
+ "loss": 0.1954,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.34,
504
+ "grad_norm": 0.14591443538665771,
505
+ "learning_rate": 0.0001891006524188368,
506
+ "loss": 0.248,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.35,
511
+ "grad_norm": 0.19209636747837067,
512
+ "learning_rate": 0.00018874134470592835,
513
+ "loss": 0.2677,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.35,
518
+ "grad_norm": 0.14589589834213257,
519
+ "learning_rate": 0.00018837656300886937,
520
+ "loss": 0.2031,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.35,
525
+ "grad_norm": 0.17039361596107483,
526
+ "learning_rate": 0.00018800632982911322,
527
+ "loss": 0.2679,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.36,
532
+ "grad_norm": 0.1550627052783966,
533
+ "learning_rate": 0.00018763066800438636,
534
+ "loss": 0.2082,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.36,
539
+ "grad_norm": 0.15761853754520416,
540
+ "learning_rate": 0.00018724960070727972,
541
+ "loss": 0.2542,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.37,
546
+ "grad_norm": 0.1586439311504364,
547
+ "learning_rate": 0.00018686315144381913,
548
+ "loss": 0.1673,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.37,
553
+ "grad_norm": 0.16859450936317444,
554
+ "learning_rate": 0.0001864713440520155,
555
+ "loss": 0.2679,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.38,
560
+ "grad_norm": 0.15938322246074677,
561
+ "learning_rate": 0.0001860742027003944,
562
+ "loss": 0.2812,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.38,
567
+ "grad_norm": 0.15844044089317322,
568
+ "learning_rate": 0.00018567175188650498,
569
+ "loss": 0.2443,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.39,
574
+ "grad_norm": 0.1673026829957962,
575
+ "learning_rate": 0.00018526401643540922,
576
+ "loss": 0.1635,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.39,
581
+ "grad_norm": 0.18364693224430084,
582
+ "learning_rate": 0.00018485102149815038,
583
+ "loss": 0.2023,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.4,
588
+ "grad_norm": 0.17101280391216278,
589
+ "learning_rate": 0.00018443279255020152,
590
+ "loss": 0.1827,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.4,
595
+ "grad_norm": 0.15244990587234497,
596
+ "learning_rate": 0.0001840093553898942,
597
+ "loss": 0.2362,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.41,
602
+ "grad_norm": 0.16682085394859314,
603
+ "learning_rate": 0.00018358073613682706,
604
+ "loss": 0.2006,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.41,
609
+ "grad_norm": 0.18180780112743378,
610
+ "learning_rate": 0.00018314696123025454,
611
+ "loss": 0.2275,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.42,
616
+ "grad_norm": 0.1552531123161316,
617
+ "learning_rate": 0.00018270805742745617,
618
+ "loss": 0.2165,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.42,
623
+ "grad_norm": 0.1649930328130722,
624
+ "learning_rate": 0.000182264051802086,
625
+ "loss": 0.2714,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.43,
630
+ "grad_norm": 0.16403907537460327,
631
+ "learning_rate": 0.00018181497174250236,
632
+ "loss": 0.1963,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.43,
637
+ "grad_norm": 0.1535252332687378,
638
+ "learning_rate": 0.00018136084495007872,
639
+ "loss": 0.1944,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.44,
644
+ "grad_norm": 0.17279598116874695,
645
+ "learning_rate": 0.00018090169943749476,
646
+ "loss": 0.2072,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.44,
651
+ "grad_norm": 0.16793234646320343,
652
+ "learning_rate": 0.00018043756352700846,
653
+ "loss": 0.1753,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.45,
658
+ "grad_norm": 0.2446856051683426,
659
+ "learning_rate": 0.00017996846584870908,
660
+ "loss": 0.1976,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.45,
665
+ "grad_norm": 0.20265690982341766,
666
+ "learning_rate": 0.000179494435338751,
667
+ "loss": 0.2656,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.46,
672
+ "grad_norm": 0.1686105579137802,
673
+ "learning_rate": 0.00017901550123756906,
674
+ "loss": 0.2032,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.46,
679
+ "grad_norm": 0.16633199155330658,
680
+ "learning_rate": 0.00017853169308807448,
681
+ "loss": 0.1939,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.47,
686
+ "grad_norm": 0.15133249759674072,
687
+ "learning_rate": 0.000178043040733833,
688
+ "loss": 0.214,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.47,
693
+ "grad_norm": 0.1566823273897171,
694
+ "learning_rate": 0.00017754957431722346,
695
+ "loss": 0.1764,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.48,
700
+ "grad_norm": 0.15705688297748566,
701
+ "learning_rate": 0.00017705132427757895,
702
+ "loss": 0.1941,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.48,
707
+ "grad_norm": 0.1403038203716278,
708
+ "learning_rate": 0.00017654832134930882,
709
+ "loss": 0.171,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.49,
714
+ "grad_norm": 0.14009466767311096,
715
+ "learning_rate": 0.0001760405965600031,
716
+ "loss": 0.2162,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.49,
721
+ "grad_norm": 0.14049287140369415,
722
+ "learning_rate": 0.00017552818122851838,
723
+ "loss": 0.1668,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.5,
728
+ "grad_norm": 0.1339244395494461,
729
+ "learning_rate": 0.00017501110696304596,
730
+ "loss": 0.1511,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.5,
735
+ "grad_norm": 0.13987047970294952,
736
+ "learning_rate": 0.00017448940565916222,
737
+ "loss": 0.2537,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.5,
742
+ "eval_loss": 0.2344847470521927,
743
+ "eval_runtime": 13.3513,
744
+ "eval_samples_per_second": 1.872,
745
+ "eval_steps_per_second": 1.872,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.51,
750
+ "grad_norm": 0.1495981365442276,
751
+ "learning_rate": 0.000173963109497861,
752
+ "loss": 0.2417,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.51,
757
+ "grad_norm": 0.129630908370018,
758
+ "learning_rate": 0.00017343225094356855,
759
+ "loss": 0.1913,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.52,
764
+ "grad_norm": 0.17110762000083923,
765
+ "learning_rate": 0.00017289686274214118,
766
+ "loss": 0.3276,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.52,
771
+ "grad_norm": 0.1344563066959381,
772
+ "learning_rate": 0.00017235697791884494,
773
+ "loss": 0.1805,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.52,
778
+ "grad_norm": 0.14707708358764648,
779
+ "learning_rate": 0.00017181262977631888,
780
+ "loss": 0.198,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.53,
785
+ "grad_norm": 0.14540620148181915,
786
+ "learning_rate": 0.00017126385189252053,
787
+ "loss": 0.1923,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.53,
792
+ "grad_norm": 0.14539222419261932,
793
+ "learning_rate": 0.00017071067811865476,
794
+ "loss": 0.1822,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.54,
799
+ "grad_norm": 0.16808092594146729,
800
+ "learning_rate": 0.0001701531425770856,
801
+ "loss": 0.2384,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.54,
806
+ "grad_norm": 0.1316782385110855,
807
+ "learning_rate": 0.00016959127965923142,
808
+ "loss": 0.1967,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.55,
813
+ "grad_norm": 0.15255320072174072,
814
+ "learning_rate": 0.00016902512402344373,
815
+ "loss": 0.245,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.55,
820
+ "grad_norm": 0.152465358376503,
821
+ "learning_rate": 0.00016845471059286887,
822
+ "loss": 0.1942,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.56,
827
+ "grad_norm": 0.15641257166862488,
828
+ "learning_rate": 0.0001678800745532942,
829
+ "loss": 0.2091,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.56,
834
+ "grad_norm": 0.16389591991901398,
835
+ "learning_rate": 0.00016730125135097735,
836
+ "loss": 0.2006,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.57,
841
+ "grad_norm": 0.1631624549627304,
842
+ "learning_rate": 0.00016671827669045998,
843
+ "loss": 0.2716,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.57,
848
+ "grad_norm": 0.16853250563144684,
849
+ "learning_rate": 0.00016613118653236518,
850
+ "loss": 0.2376,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.58,
855
+ "grad_norm": 0.13790781795978546,
856
+ "learning_rate": 0.0001655400170911794,
857
+ "loss": 0.1943,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.58,
862
+ "grad_norm": 0.2789172828197479,
863
+ "learning_rate": 0.00016494480483301836,
864
+ "loss": 0.3018,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.59,
869
+ "grad_norm": 0.14194965362548828,
870
+ "learning_rate": 0.0001643455864733779,
871
+ "loss": 0.2133,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.59,
876
+ "grad_norm": 0.13147993385791779,
877
+ "learning_rate": 0.000163742398974869,
878
+ "loss": 0.2281,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.6,
883
+ "grad_norm": 0.16474007070064545,
884
+ "learning_rate": 0.00016313527954493778,
885
+ "loss": 0.2507,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.6,
890
+ "grad_norm": 0.14342117309570312,
891
+ "learning_rate": 0.00016252426563357055,
892
+ "loss": 0.2118,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.61,
897
+ "grad_norm": 0.13474318385124207,
898
+ "learning_rate": 0.00016190939493098344,
899
+ "loss": 0.2172,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.61,
904
+ "grad_norm": 0.12630698084831238,
905
+ "learning_rate": 0.00016129070536529766,
906
+ "loss": 0.1549,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.62,
911
+ "grad_norm": 0.12225893884897232,
912
+ "learning_rate": 0.00016066823510019998,
913
+ "loss": 0.2312,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.62,
918
+ "grad_norm": 0.17443059384822845,
919
+ "learning_rate": 0.00016004202253258842,
920
+ "loss": 0.3303,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.63,
925
+ "grad_norm": 0.1610797941684723,
926
+ "learning_rate": 0.00015941210629020388,
927
+ "loss": 0.2463,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.63,
932
+ "grad_norm": 0.14372020959854126,
933
+ "learning_rate": 0.00015877852522924732,
934
+ "loss": 0.3351,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.64,
939
+ "grad_norm": 0.15952154994010925,
940
+ "learning_rate": 0.00015814131843198308,
941
+ "loss": 0.2147,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.64,
946
+ "grad_norm": 0.18614554405212402,
947
+ "learning_rate": 0.00015750052520432787,
948
+ "loss": 0.1983,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.65,
953
+ "grad_norm": 0.15100689232349396,
954
+ "learning_rate": 0.0001568561850734264,
955
+ "loss": 0.182,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.65,
960
+ "grad_norm": 0.15041258931159973,
961
+ "learning_rate": 0.00015620833778521307,
962
+ "loss": 0.1979,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.66,
967
+ "grad_norm": 0.14446201920509338,
968
+ "learning_rate": 0.00015555702330196023,
969
+ "loss": 0.2039,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.66,
974
+ "grad_norm": 0.12656830251216888,
975
+ "learning_rate": 0.0001549022817998132,
976
+ "loss": 0.2032,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.67,
981
+ "grad_norm": 0.147608682513237,
982
+ "learning_rate": 0.00015424415366631188,
983
+ "loss": 0.1889,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.67,
988
+ "grad_norm": 0.1701640486717224,
989
+ "learning_rate": 0.00015358267949789966,
990
+ "loss": 0.2654,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.68,
995
+ "grad_norm": 0.1424136757850647,
996
+ "learning_rate": 0.00015291790009741907,
997
+ "loss": 0.2052,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.68,
1002
+ "grad_norm": 0.1711564064025879,
1003
+ "learning_rate": 0.0001522498564715949,
1004
+ "loss": 0.226,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.69,
1009
+ "grad_norm": 0.17195338010787964,
1010
+ "learning_rate": 0.00015157858982850475,
1011
+ "loss": 0.2366,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.69,
1016
+ "grad_norm": 0.1596439927816391,
1017
+ "learning_rate": 0.00015090414157503714,
1018
+ "loss": 0.2387,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.7,
1023
+ "grad_norm": 0.1538238674402237,
1024
+ "learning_rate": 0.00015022655331433727,
1025
+ "loss": 0.2326,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.7,
1030
+ "grad_norm": 0.13117662072181702,
1031
+ "learning_rate": 0.00014954586684324078,
1032
+ "loss": 0.1571,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.7,
1037
+ "grad_norm": 0.1380062848329544,
1038
+ "learning_rate": 0.00014886212414969553,
1039
+ "loss": 0.1581,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.71,
1044
+ "grad_norm": 0.15343894064426422,
1045
+ "learning_rate": 0.00014817536741017152,
1046
+ "loss": 0.2154,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.71,
1051
+ "grad_norm": 0.12983113527297974,
1052
+ "learning_rate": 0.00014748563898705946,
1053
+ "loss": 0.1988,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.72,
1058
+ "grad_norm": 0.1460677534341812,
1059
+ "learning_rate": 0.00014679298142605734,
1060
+ "loss": 0.208,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.72,
1065
+ "grad_norm": 0.18640218675136566,
1066
+ "learning_rate": 0.00014609743745354624,
1067
+ "loss": 0.2976,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.73,
1072
+ "grad_norm": 0.1410883516073227,
1073
+ "learning_rate": 0.00014539904997395468,
1074
+ "loss": 0.1779,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.73,
1079
+ "grad_norm": 0.1352994590997696,
1080
+ "learning_rate": 0.00014469786206711214,
1081
+ "loss": 0.1932,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.74,
1086
+ "grad_norm": 0.16276930272579193,
1087
+ "learning_rate": 0.00014399391698559152,
1088
+ "loss": 0.19,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.74,
1093
+ "grad_norm": 0.1330641359090805,
1094
+ "learning_rate": 0.00014328725815204144,
1095
+ "loss": 0.1529,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.75,
1100
+ "grad_norm": 0.1461140215396881,
1101
+ "learning_rate": 0.00014257792915650728,
1102
+ "loss": 0.1822,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.75,
1107
+ "grad_norm": 0.1400836855173111,
1108
+ "learning_rate": 0.0001418659737537428,
1109
+ "loss": 0.1984,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.76,
1114
+ "grad_norm": 0.15338997542858124,
1115
+ "learning_rate": 0.00014115143586051088,
1116
+ "loss": 0.1856,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.76,
1121
+ "grad_norm": 0.15661920607089996,
1122
+ "learning_rate": 0.00014043435955287452,
1123
+ "loss": 0.2219,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.77,
1128
+ "grad_norm": 0.22158733010292053,
1129
+ "learning_rate": 0.00013971478906347806,
1130
+ "loss": 0.3549,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.77,
1135
+ "grad_norm": 0.1338592767715454,
1136
+ "learning_rate": 0.00013899276877881884,
1137
+ "loss": 0.1785,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.78,
1142
+ "grad_norm": 0.14615756273269653,
1143
+ "learning_rate": 0.000138268343236509,
1144
+ "loss": 0.2202,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.78,
1149
+ "grad_norm": 0.1247783973813057,
1150
+ "learning_rate": 0.00013754155712252832,
1151
+ "loss": 0.2008,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.79,
1156
+ "grad_norm": 0.18145664036273956,
1157
+ "learning_rate": 0.00013681245526846783,
1158
+ "loss": 0.2144,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.79,
1163
+ "grad_norm": 0.1396200805902481,
1164
+ "learning_rate": 0.0001360810826487642,
1165
+ "loss": 0.2194,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.8,
1170
+ "grad_norm": 0.15508796274662018,
1171
+ "learning_rate": 0.00013534748437792573,
1172
+ "loss": 0.2766,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.8,
1177
+ "grad_norm": 0.15434060990810394,
1178
+ "learning_rate": 0.0001346117057077493,
1179
+ "loss": 0.188,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.81,
1184
+ "grad_norm": 0.14731119573116302,
1185
+ "learning_rate": 0.00013387379202452917,
1186
+ "loss": 0.233,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.81,
1191
+ "grad_norm": 0.1317255198955536,
1192
+ "learning_rate": 0.0001331337888462571,
1193
+ "loss": 0.233,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.82,
1198
+ "grad_norm": 0.16242042183876038,
1199
+ "learning_rate": 0.00013239174181981495,
1200
+ "loss": 0.2541,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.82,
1205
+ "grad_norm": 0.14940407872200012,
1206
+ "learning_rate": 0.00013164769671815862,
1207
+ "loss": 0.2244,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.83,
1212
+ "grad_norm": 0.14262273907661438,
1213
+ "learning_rate": 0.00013090169943749476,
1214
+ "loss": 0.2458,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.83,
1219
+ "grad_norm": 0.13066165149211884,
1220
+ "learning_rate": 0.00013015379599444957,
1221
+ "loss": 0.1865,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.84,
1226
+ "grad_norm": 0.14521218836307526,
1227
+ "learning_rate": 0.0001294040325232304,
1228
+ "loss": 0.1838,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.84,
1233
+ "grad_norm": 0.14943768084049225,
1234
+ "learning_rate": 0.00012865245527277986,
1235
+ "loss": 0.2369,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.85,
1240
+ "grad_norm": 0.14182843267917633,
1241
+ "learning_rate": 0.00012789911060392294,
1242
+ "loss": 0.1953,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.85,
1247
+ "grad_norm": 0.16210182011127472,
1248
+ "learning_rate": 0.00012714404498650743,
1249
+ "loss": 0.2624,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.86,
1254
+ "grad_norm": 0.15228134393692017,
1255
+ "learning_rate": 0.0001263873049965373,
1256
+ "loss": 0.2441,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.86,
1261
+ "grad_norm": 0.13629144430160522,
1262
+ "learning_rate": 0.00012562893731329967,
1263
+ "loss": 0.2003,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.87,
1268
+ "grad_norm": 0.15732020139694214,
1269
+ "learning_rate": 0.0001248689887164855,
1270
+ "loss": 0.2311,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.87,
1275
+ "grad_norm": 0.13804040849208832,
1276
+ "learning_rate": 0.00012410750608330388,
1277
+ "loss": 0.1768,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.87,
1282
+ "grad_norm": 0.13766342401504517,
1283
+ "learning_rate": 0.00012334453638559057,
1284
+ "loss": 0.2182,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.88,
1289
+ "grad_norm": 0.15981349349021912,
1290
+ "learning_rate": 0.0001225801266869104,
1291
+ "loss": 0.2061,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.88,
1296
+ "grad_norm": 0.12819038331508636,
1297
+ "learning_rate": 0.00012181432413965428,
1298
+ "loss": 0.1549,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.89,
1303
+ "grad_norm": 0.13831038773059845,
1304
+ "learning_rate": 0.00012104717598213056,
1305
+ "loss": 0.1653,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.89,
1310
+ "grad_norm": 0.16673411428928375,
1311
+ "learning_rate": 0.00012027872953565125,
1312
+ "loss": 0.1933,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.9,
1317
+ "grad_norm": 0.14682242274284363,
1318
+ "learning_rate": 0.00011950903220161285,
1319
+ "loss": 0.202,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.9,
1324
+ "grad_norm": 0.1462392807006836,
1325
+ "learning_rate": 0.00011873813145857249,
1326
+ "loss": 0.2377,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.91,
1331
+ "grad_norm": 0.12843555212020874,
1332
+ "learning_rate": 0.00011796607485931928,
1333
+ "loss": 0.2125,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.91,
1338
+ "grad_norm": 0.15481220185756683,
1339
+ "learning_rate": 0.00011719291002794096,
1340
+ "loss": 0.2539,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.92,
1345
+ "grad_norm": 0.13950768113136292,
1346
+ "learning_rate": 0.0001164186846568863,
1347
+ "loss": 0.1972,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.92,
1352
+ "grad_norm": 0.11621260643005371,
1353
+ "learning_rate": 0.0001156434465040231,
1354
+ "loss": 0.1856,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.93,
1359
+ "grad_norm": 0.14099712669849396,
1360
+ "learning_rate": 0.00011486724338969232,
1361
+ "loss": 0.1916,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.93,
1366
+ "grad_norm": 0.1282750517129898,
1367
+ "learning_rate": 0.00011409012319375827,
1368
+ "loss": 0.1836,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.94,
1373
+ "grad_norm": 0.15066012740135193,
1374
+ "learning_rate": 0.00011331213385265524,
1375
+ "loss": 0.2432,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.94,
1380
+ "grad_norm": 0.14334805309772491,
1381
+ "learning_rate": 0.00011253332335643043,
1382
+ "loss": 0.1749,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.95,
1387
+ "grad_norm": 0.15670594573020935,
1388
+ "learning_rate": 0.00011175373974578378,
1389
+ "loss": 0.2479,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.95,
1394
+ "grad_norm": 0.15438470244407654,
1395
+ "learning_rate": 0.00011097343110910452,
1396
+ "loss": 0.2356,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.96,
1401
+ "grad_norm": 0.1420874148607254,
1402
+ "learning_rate": 0.000110192445579505,
1403
+ "loss": 0.2662,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.96,
1408
+ "grad_norm": 0.1418399214744568,
1409
+ "learning_rate": 0.00010941083133185146,
1410
+ "loss": 0.1785,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.97,
1415
+ "grad_norm": 0.1280946284532547,
1416
+ "learning_rate": 0.00010862863657979237,
1417
+ "loss": 0.1652,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.97,
1422
+ "grad_norm": 0.14323323965072632,
1423
+ "learning_rate": 0.0001078459095727845,
1424
+ "loss": 0.2104,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.98,
1429
+ "grad_norm": 0.10913383960723877,
1430
+ "learning_rate": 0.00010706269859311669,
1431
+ "loss": 0.1448,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.98,
1436
+ "grad_norm": 0.12007103115320206,
1437
+ "learning_rate": 0.00010627905195293135,
1438
+ "loss": 0.1263,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.99,
1443
+ "grad_norm": 0.1433536857366562,
1444
+ "learning_rate": 0.0001054950179912446,
1445
+ "loss": 0.1831,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.99,
1450
+ "grad_norm": 0.1542392522096634,
1451
+ "learning_rate": 0.00010471064507096426,
1452
+ "loss": 0.2828,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 1.0,
1457
+ "grad_norm": 0.18856601417064667,
1458
+ "learning_rate": 0.00010392598157590688,
1459
+ "loss": 0.183,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 1.0,
1464
+ "grad_norm": 0.13536609709262848,
1465
+ "learning_rate": 0.00010314107590781284,
1466
+ "loss": 0.2161,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 1.0,
1471
+ "eval_loss": 0.22577418386936188,
1472
+ "eval_runtime": 13.2186,
1473
+ "eval_samples_per_second": 1.891,
1474
+ "eval_steps_per_second": 1.891,
1475
+ "step": 206
1476
+ }
1477
+ ],
1478
+ "logging_steps": 1,
1479
+ "max_steps": 410,
1480
+ "num_input_tokens_seen": 0,
1481
+ "num_train_epochs": 2,
1482
+ "save_steps": 103,
1483
+ "total_flos": 1.27754961965192e+18,
1484
+ "train_batch_size": 1,
1485
+ "trial_name": null,
1486
+ "trial_params": null
1487
+ }
adapter/checkpoint-206/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c619572c8607352856f31afb988e45204d8ad93ba4c2fe0fb58a0afe4e724f6b
3
+ size 5752
adapter/checkpoint-309/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: jamba
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 0.10.0
adapter/checkpoint-309/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "jamba",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "router",
24
+ "k_proj",
25
+ "up_proj",
26
+ "dt_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "x_proj",
31
+ "out_proj",
32
+ "gate_proj",
33
+ "o_proj",
34
+ "in_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter/checkpoint-309/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672e306dc3ddbb4afde761b3b3ad9035f14d15c0b170bbb497ea2fa09636cb19
3
+ size 531607760
adapter/checkpoint-309/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cca5267309c07e45ecd7991816f9a38b29970f9b0ff77950a33f753a8713ce
3
+ size 269103876
adapter/checkpoint-309/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f53b2a61c1efffe621c0a2cf9b356c3c7b0fdad54deca93d49083c54eb2a00
3
+ size 14244
adapter/checkpoint-309/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d4e83c4c1a839e05c4c1a4eceff1aa30f050b924d66090d9627d27c02ca9ce
3
+ size 1064
adapter/checkpoint-309/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapter/checkpoint-309/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapter/checkpoint-309/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
3
+ size 1124742
adapter/checkpoint-309/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|unk|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<|startoftext|>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<|endoftext|>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<|pad|>",
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<|unk|>",
46
+ "use_default_system_prompt": false
47
+ }
adapter/checkpoint-309/trainer_state.json ADDED
@@ -0,0 +1,2216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.4690157958687728,
5
+ "eval_steps": 103,
6
+ "global_step": 309,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.3593529462814331,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.4337,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 0.3783022463321686,
21
+ "eval_runtime": 12.9552,
22
+ "eval_samples_per_second": 1.93,
23
+ "eval_steps_per_second": 1.93,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 0.3430859446525574,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.4605,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.3275960683822632,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.39,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 0.3221317529678345,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.3372,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "grad_norm": 0.3926704227924347,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.3333,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03,
56
+ "grad_norm": 0.2960835099220276,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.3671,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.03,
63
+ "grad_norm": 0.3393571078777313,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.327,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.04,
70
+ "grad_norm": 0.2799758017063141,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.2933,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.04,
77
+ "grad_norm": 0.3084808886051178,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.3505,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.05,
84
+ "grad_norm": 0.23642300069332123,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.3289,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "grad_norm": 0.369229793548584,
92
+ "learning_rate": 0.00019999691576447898,
93
+ "loss": 0.3049,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.06,
98
+ "grad_norm": 0.2706857919692993,
99
+ "learning_rate": 0.00019998766324816607,
100
+ "loss": 0.3425,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.06,
105
+ "grad_norm": 0.21327799558639526,
106
+ "learning_rate": 0.00019997224302180006,
107
+ "loss": 0.2686,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.07,
112
+ "grad_norm": 0.26732948422431946,
113
+ "learning_rate": 0.00019995065603657316,
114
+ "loss": 0.2987,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.07,
119
+ "grad_norm": 0.2009548544883728,
120
+ "learning_rate": 0.0001999229036240723,
121
+ "loss": 0.2668,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.08,
126
+ "grad_norm": 0.23616977035999298,
127
+ "learning_rate": 0.00019988898749619702,
128
+ "loss": 0.2962,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.08,
133
+ "grad_norm": 0.18399174511432648,
134
+ "learning_rate": 0.00019984890974505381,
135
+ "loss": 0.2238,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.09,
140
+ "grad_norm": 0.24744661152362823,
141
+ "learning_rate": 0.00019980267284282717,
142
+ "loss": 0.2628,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.09,
147
+ "grad_norm": 0.22109034657478333,
148
+ "learning_rate": 0.00019975027964162702,
149
+ "loss": 0.3143,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.1,
154
+ "grad_norm": 0.21471348404884338,
155
+ "learning_rate": 0.0001996917333733128,
156
+ "loss": 0.3436,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1,
161
+ "grad_norm": 0.2112409919500351,
162
+ "learning_rate": 0.00019962703764929413,
163
+ "loss": 0.2714,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.11,
168
+ "grad_norm": 0.19044426083564758,
169
+ "learning_rate": 0.00019955619646030802,
170
+ "loss": 0.2335,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "grad_norm": 0.21945005655288696,
176
+ "learning_rate": 0.00019947921417617267,
177
+ "loss": 0.2381,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.12,
182
+ "grad_norm": 0.1864914447069168,
183
+ "learning_rate": 0.000199396095545518,
184
+ "loss": 0.287,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.12,
189
+ "grad_norm": 0.2413000762462616,
190
+ "learning_rate": 0.00019930684569549264,
191
+ "loss": 0.1813,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.13,
196
+ "grad_norm": 0.20038250088691711,
197
+ "learning_rate": 0.0001992114701314478,
198
+ "loss": 0.2722,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.13,
203
+ "grad_norm": 0.16239097714424133,
204
+ "learning_rate": 0.0001991099747365975,
205
+ "loss": 0.1917,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.14,
210
+ "grad_norm": 0.19039247930049896,
211
+ "learning_rate": 0.00019900236577165576,
212
+ "loss": 0.2665,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.14,
217
+ "grad_norm": 0.17717348039150238,
218
+ "learning_rate": 0.0001988886498744505,
219
+ "loss": 0.2667,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.15,
224
+ "grad_norm": 0.18755286931991577,
225
+ "learning_rate": 0.00019876883405951377,
226
+ "loss": 0.1775,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.15,
231
+ "grad_norm": 0.1621539294719696,
232
+ "learning_rate": 0.00019864292571764955,
233
+ "loss": 0.2292,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.16,
238
+ "grad_norm": 0.1834522783756256,
239
+ "learning_rate": 0.0001985109326154774,
240
+ "loss": 0.2327,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.16,
245
+ "grad_norm": 0.18009088933467865,
246
+ "learning_rate": 0.00019837286289495361,
247
+ "loss": 0.2325,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.17,
252
+ "grad_norm": 0.16372188925743103,
253
+ "learning_rate": 0.0001982287250728689,
254
+ "loss": 0.2748,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.17,
259
+ "grad_norm": 0.16966991126537323,
260
+ "learning_rate": 0.00019807852804032305,
261
+ "loss": 0.2353,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.17,
266
+ "grad_norm": 0.18791744112968445,
267
+ "learning_rate": 0.00019792228106217658,
268
+ "loss": 0.2693,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.18,
273
+ "grad_norm": 0.16828736662864685,
274
+ "learning_rate": 0.0001977599937764791,
275
+ "loss": 0.1752,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.18,
280
+ "grad_norm": 0.1636415272951126,
281
+ "learning_rate": 0.00019759167619387476,
282
+ "loss": 0.2961,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.19,
287
+ "grad_norm": 0.152165487408638,
288
+ "learning_rate": 0.00019741733869698495,
289
+ "loss": 0.1954,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.19,
294
+ "grad_norm": 0.1838696449995041,
295
+ "learning_rate": 0.00019723699203976766,
296
+ "loss": 0.2039,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.2,
301
+ "grad_norm": 0.170082688331604,
302
+ "learning_rate": 0.00019705064734685425,
303
+ "loss": 0.2228,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.2,
308
+ "grad_norm": 0.1489935666322708,
309
+ "learning_rate": 0.0001968583161128631,
310
+ "loss": 0.185,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.21,
315
+ "grad_norm": 0.1501648873090744,
316
+ "learning_rate": 0.00019666001020169073,
317
+ "loss": 0.2198,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.21,
322
+ "grad_norm": 0.24484610557556152,
323
+ "learning_rate": 0.00019645574184577982,
324
+ "loss": 0.2514,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.22,
329
+ "grad_norm": 0.16400669515132904,
330
+ "learning_rate": 0.00019624552364536473,
331
+ "loss": 0.283,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.22,
336
+ "grad_norm": 0.15034696459770203,
337
+ "learning_rate": 0.0001960293685676943,
338
+ "loss": 0.1637,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.23,
343
+ "grad_norm": 0.15385685861110687,
344
+ "learning_rate": 0.00019580728994623195,
345
+ "loss": 0.2905,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.23,
350
+ "grad_norm": 0.16004744172096252,
351
+ "learning_rate": 0.00019557930147983302,
352
+ "loss": 0.2173,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.24,
357
+ "grad_norm": 0.17182469367980957,
358
+ "learning_rate": 0.0001953454172319001,
359
+ "loss": 0.2147,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.24,
364
+ "grad_norm": 0.1576426774263382,
365
+ "learning_rate": 0.00019510565162951537,
366
+ "loss": 0.284,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.25,
371
+ "grad_norm": 0.14034013450145721,
372
+ "learning_rate": 0.00019486001946255046,
373
+ "loss": 0.1671,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.25,
378
+ "grad_norm": 0.1770170032978058,
379
+ "learning_rate": 0.00019460853588275454,
380
+ "loss": 0.205,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.26,
385
+ "grad_norm": 0.14077183604240417,
386
+ "learning_rate": 0.00019435121640281938,
387
+ "loss": 0.209,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.26,
392
+ "grad_norm": 0.2193373441696167,
393
+ "learning_rate": 0.00019408807689542257,
394
+ "loss": 0.2125,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.27,
399
+ "grad_norm": 0.1439114212989807,
400
+ "learning_rate": 0.00019381913359224842,
401
+ "loss": 0.1611,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.27,
406
+ "grad_norm": 0.16939564049243927,
407
+ "learning_rate": 0.00019354440308298675,
408
+ "loss": 0.2189,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.28,
413
+ "grad_norm": 0.17016972601413727,
414
+ "learning_rate": 0.00019326390231430942,
415
+ "loss": 0.2129,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.28,
420
+ "grad_norm": 0.16602838039398193,
421
+ "learning_rate": 0.00019297764858882514,
422
+ "loss": 0.23,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.29,
427
+ "grad_norm": 0.21853233873844147,
428
+ "learning_rate": 0.00019268565956401208,
429
+ "loss": 0.1879,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.29,
434
+ "grad_norm": 0.18649564683437347,
435
+ "learning_rate": 0.0001923879532511287,
436
+ "loss": 0.2063,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.3,
441
+ "grad_norm": 0.16304822266101837,
442
+ "learning_rate": 0.00019208454801410266,
443
+ "loss": 0.2182,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.3,
448
+ "grad_norm": 0.1357814073562622,
449
+ "learning_rate": 0.00019177546256839812,
450
+ "loss": 0.1912,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.31,
455
+ "grad_norm": 0.1645856499671936,
456
+ "learning_rate": 0.00019146071597986138,
457
+ "loss": 0.2498,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.31,
462
+ "grad_norm": 0.20048978924751282,
463
+ "learning_rate": 0.00019114032766354453,
464
+ "loss": 0.3207,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.32,
469
+ "grad_norm": 0.15142077207565308,
470
+ "learning_rate": 0.00019081431738250814,
471
+ "loss": 0.2102,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.32,
476
+ "grad_norm": 0.15482479333877563,
477
+ "learning_rate": 0.00019048270524660196,
478
+ "loss": 0.2706,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.33,
483
+ "grad_norm": 0.15685780346393585,
484
+ "learning_rate": 0.00019014551171122457,
485
+ "loss": 0.1898,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.33,
490
+ "grad_norm": 0.18191099166870117,
491
+ "learning_rate": 0.00018980275757606157,
492
+ "loss": 0.2838,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.34,
497
+ "grad_norm": 0.1533990502357483,
498
+ "learning_rate": 0.0001894544639838025,
499
+ "loss": 0.1954,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.34,
504
+ "grad_norm": 0.14591443538665771,
505
+ "learning_rate": 0.0001891006524188368,
506
+ "loss": 0.248,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.35,
511
+ "grad_norm": 0.19209636747837067,
512
+ "learning_rate": 0.00018874134470592835,
513
+ "loss": 0.2677,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.35,
518
+ "grad_norm": 0.14589589834213257,
519
+ "learning_rate": 0.00018837656300886937,
520
+ "loss": 0.2031,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.35,
525
+ "grad_norm": 0.17039361596107483,
526
+ "learning_rate": 0.00018800632982911322,
527
+ "loss": 0.2679,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.36,
532
+ "grad_norm": 0.1550627052783966,
533
+ "learning_rate": 0.00018763066800438636,
534
+ "loss": 0.2082,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.36,
539
+ "grad_norm": 0.15761853754520416,
540
+ "learning_rate": 0.00018724960070727972,
541
+ "loss": 0.2542,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.37,
546
+ "grad_norm": 0.1586439311504364,
547
+ "learning_rate": 0.00018686315144381913,
548
+ "loss": 0.1673,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.37,
553
+ "grad_norm": 0.16859450936317444,
554
+ "learning_rate": 0.0001864713440520155,
555
+ "loss": 0.2679,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.38,
560
+ "grad_norm": 0.15938322246074677,
561
+ "learning_rate": 0.0001860742027003944,
562
+ "loss": 0.2812,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.38,
567
+ "grad_norm": 0.15844044089317322,
568
+ "learning_rate": 0.00018567175188650498,
569
+ "loss": 0.2443,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.39,
574
+ "grad_norm": 0.1673026829957962,
575
+ "learning_rate": 0.00018526401643540922,
576
+ "loss": 0.1635,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.39,
581
+ "grad_norm": 0.18364693224430084,
582
+ "learning_rate": 0.00018485102149815038,
583
+ "loss": 0.2023,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.4,
588
+ "grad_norm": 0.17101280391216278,
589
+ "learning_rate": 0.00018443279255020152,
590
+ "loss": 0.1827,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.4,
595
+ "grad_norm": 0.15244990587234497,
596
+ "learning_rate": 0.0001840093553898942,
597
+ "loss": 0.2362,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.41,
602
+ "grad_norm": 0.16682085394859314,
603
+ "learning_rate": 0.00018358073613682706,
604
+ "loss": 0.2006,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.41,
609
+ "grad_norm": 0.18180780112743378,
610
+ "learning_rate": 0.00018314696123025454,
611
+ "loss": 0.2275,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.42,
616
+ "grad_norm": 0.1552531123161316,
617
+ "learning_rate": 0.00018270805742745617,
618
+ "loss": 0.2165,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.42,
623
+ "grad_norm": 0.1649930328130722,
624
+ "learning_rate": 0.000182264051802086,
625
+ "loss": 0.2714,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.43,
630
+ "grad_norm": 0.16403907537460327,
631
+ "learning_rate": 0.00018181497174250236,
632
+ "loss": 0.1963,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.43,
637
+ "grad_norm": 0.1535252332687378,
638
+ "learning_rate": 0.00018136084495007872,
639
+ "loss": 0.1944,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.44,
644
+ "grad_norm": 0.17279598116874695,
645
+ "learning_rate": 0.00018090169943749476,
646
+ "loss": 0.2072,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.44,
651
+ "grad_norm": 0.16793234646320343,
652
+ "learning_rate": 0.00018043756352700846,
653
+ "loss": 0.1753,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.45,
658
+ "grad_norm": 0.2446856051683426,
659
+ "learning_rate": 0.00017996846584870908,
660
+ "loss": 0.1976,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.45,
665
+ "grad_norm": 0.20265690982341766,
666
+ "learning_rate": 0.000179494435338751,
667
+ "loss": 0.2656,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.46,
672
+ "grad_norm": 0.1686105579137802,
673
+ "learning_rate": 0.00017901550123756906,
674
+ "loss": 0.2032,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.46,
679
+ "grad_norm": 0.16633199155330658,
680
+ "learning_rate": 0.00017853169308807448,
681
+ "loss": 0.1939,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.47,
686
+ "grad_norm": 0.15133249759674072,
687
+ "learning_rate": 0.000178043040733833,
688
+ "loss": 0.214,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.47,
693
+ "grad_norm": 0.1566823273897171,
694
+ "learning_rate": 0.00017754957431722346,
695
+ "loss": 0.1764,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.48,
700
+ "grad_norm": 0.15705688297748566,
701
+ "learning_rate": 0.00017705132427757895,
702
+ "loss": 0.1941,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.48,
707
+ "grad_norm": 0.1403038203716278,
708
+ "learning_rate": 0.00017654832134930882,
709
+ "loss": 0.171,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.49,
714
+ "grad_norm": 0.14009466767311096,
715
+ "learning_rate": 0.0001760405965600031,
716
+ "loss": 0.2162,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.49,
721
+ "grad_norm": 0.14049287140369415,
722
+ "learning_rate": 0.00017552818122851838,
723
+ "loss": 0.1668,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.5,
728
+ "grad_norm": 0.1339244395494461,
729
+ "learning_rate": 0.00017501110696304596,
730
+ "loss": 0.1511,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.5,
735
+ "grad_norm": 0.13987047970294952,
736
+ "learning_rate": 0.00017448940565916222,
737
+ "loss": 0.2537,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.5,
742
+ "eval_loss": 0.2344847470521927,
743
+ "eval_runtime": 13.3513,
744
+ "eval_samples_per_second": 1.872,
745
+ "eval_steps_per_second": 1.872,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.51,
750
+ "grad_norm": 0.1495981365442276,
751
+ "learning_rate": 0.000173963109497861,
752
+ "loss": 0.2417,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.51,
757
+ "grad_norm": 0.129630908370018,
758
+ "learning_rate": 0.00017343225094356855,
759
+ "loss": 0.1913,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.52,
764
+ "grad_norm": 0.17110762000083923,
765
+ "learning_rate": 0.00017289686274214118,
766
+ "loss": 0.3276,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.52,
771
+ "grad_norm": 0.1344563066959381,
772
+ "learning_rate": 0.00017235697791884494,
773
+ "loss": 0.1805,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.52,
778
+ "grad_norm": 0.14707708358764648,
779
+ "learning_rate": 0.00017181262977631888,
780
+ "loss": 0.198,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.53,
785
+ "grad_norm": 0.14540620148181915,
786
+ "learning_rate": 0.00017126385189252053,
787
+ "loss": 0.1923,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.53,
792
+ "grad_norm": 0.14539222419261932,
793
+ "learning_rate": 0.00017071067811865476,
794
+ "loss": 0.1822,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.54,
799
+ "grad_norm": 0.16808092594146729,
800
+ "learning_rate": 0.0001701531425770856,
801
+ "loss": 0.2384,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.54,
806
+ "grad_norm": 0.1316782385110855,
807
+ "learning_rate": 0.00016959127965923142,
808
+ "loss": 0.1967,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.55,
813
+ "grad_norm": 0.15255320072174072,
814
+ "learning_rate": 0.00016902512402344373,
815
+ "loss": 0.245,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.55,
820
+ "grad_norm": 0.152465358376503,
821
+ "learning_rate": 0.00016845471059286887,
822
+ "loss": 0.1942,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.56,
827
+ "grad_norm": 0.15641257166862488,
828
+ "learning_rate": 0.0001678800745532942,
829
+ "loss": 0.2091,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.56,
834
+ "grad_norm": 0.16389591991901398,
835
+ "learning_rate": 0.00016730125135097735,
836
+ "loss": 0.2006,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.57,
841
+ "grad_norm": 0.1631624549627304,
842
+ "learning_rate": 0.00016671827669045998,
843
+ "loss": 0.2716,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.57,
848
+ "grad_norm": 0.16853250563144684,
849
+ "learning_rate": 0.00016613118653236518,
850
+ "loss": 0.2376,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.58,
855
+ "grad_norm": 0.13790781795978546,
856
+ "learning_rate": 0.0001655400170911794,
857
+ "loss": 0.1943,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.58,
862
+ "grad_norm": 0.2789172828197479,
863
+ "learning_rate": 0.00016494480483301836,
864
+ "loss": 0.3018,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.59,
869
+ "grad_norm": 0.14194965362548828,
870
+ "learning_rate": 0.0001643455864733779,
871
+ "loss": 0.2133,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.59,
876
+ "grad_norm": 0.13147993385791779,
877
+ "learning_rate": 0.000163742398974869,
878
+ "loss": 0.2281,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.6,
883
+ "grad_norm": 0.16474007070064545,
884
+ "learning_rate": 0.00016313527954493778,
885
+ "loss": 0.2507,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.6,
890
+ "grad_norm": 0.14342117309570312,
891
+ "learning_rate": 0.00016252426563357055,
892
+ "loss": 0.2118,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.61,
897
+ "grad_norm": 0.13474318385124207,
898
+ "learning_rate": 0.00016190939493098344,
899
+ "loss": 0.2172,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.61,
904
+ "grad_norm": 0.12630698084831238,
905
+ "learning_rate": 0.00016129070536529766,
906
+ "loss": 0.1549,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.62,
911
+ "grad_norm": 0.12225893884897232,
912
+ "learning_rate": 0.00016066823510019998,
913
+ "loss": 0.2312,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.62,
918
+ "grad_norm": 0.17443059384822845,
919
+ "learning_rate": 0.00016004202253258842,
920
+ "loss": 0.3303,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.63,
925
+ "grad_norm": 0.1610797941684723,
926
+ "learning_rate": 0.00015941210629020388,
927
+ "loss": 0.2463,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.63,
932
+ "grad_norm": 0.14372020959854126,
933
+ "learning_rate": 0.00015877852522924732,
934
+ "loss": 0.3351,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.64,
939
+ "grad_norm": 0.15952154994010925,
940
+ "learning_rate": 0.00015814131843198308,
941
+ "loss": 0.2147,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.64,
946
+ "grad_norm": 0.18614554405212402,
947
+ "learning_rate": 0.00015750052520432787,
948
+ "loss": 0.1983,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.65,
953
+ "grad_norm": 0.15100689232349396,
954
+ "learning_rate": 0.0001568561850734264,
955
+ "loss": 0.182,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.65,
960
+ "grad_norm": 0.15041258931159973,
961
+ "learning_rate": 0.00015620833778521307,
962
+ "loss": 0.1979,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.66,
967
+ "grad_norm": 0.14446201920509338,
968
+ "learning_rate": 0.00015555702330196023,
969
+ "loss": 0.2039,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.66,
974
+ "grad_norm": 0.12656830251216888,
975
+ "learning_rate": 0.0001549022817998132,
976
+ "loss": 0.2032,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.67,
981
+ "grad_norm": 0.147608682513237,
982
+ "learning_rate": 0.00015424415366631188,
983
+ "loss": 0.1889,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.67,
988
+ "grad_norm": 0.1701640486717224,
989
+ "learning_rate": 0.00015358267949789966,
990
+ "loss": 0.2654,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.68,
995
+ "grad_norm": 0.1424136757850647,
996
+ "learning_rate": 0.00015291790009741907,
997
+ "loss": 0.2052,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.68,
1002
+ "grad_norm": 0.1711564064025879,
1003
+ "learning_rate": 0.0001522498564715949,
1004
+ "loss": 0.226,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.69,
1009
+ "grad_norm": 0.17195338010787964,
1010
+ "learning_rate": 0.00015157858982850475,
1011
+ "loss": 0.2366,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.69,
1016
+ "grad_norm": 0.1596439927816391,
1017
+ "learning_rate": 0.00015090414157503714,
1018
+ "loss": 0.2387,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.7,
1023
+ "grad_norm": 0.1538238674402237,
1024
+ "learning_rate": 0.00015022655331433727,
1025
+ "loss": 0.2326,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.7,
1030
+ "grad_norm": 0.13117662072181702,
1031
+ "learning_rate": 0.00014954586684324078,
1032
+ "loss": 0.1571,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.7,
1037
+ "grad_norm": 0.1380062848329544,
1038
+ "learning_rate": 0.00014886212414969553,
1039
+ "loss": 0.1581,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.71,
1044
+ "grad_norm": 0.15343894064426422,
1045
+ "learning_rate": 0.00014817536741017152,
1046
+ "loss": 0.2154,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.71,
1051
+ "grad_norm": 0.12983113527297974,
1052
+ "learning_rate": 0.00014748563898705946,
1053
+ "loss": 0.1988,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.72,
1058
+ "grad_norm": 0.1460677534341812,
1059
+ "learning_rate": 0.00014679298142605734,
1060
+ "loss": 0.208,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.72,
1065
+ "grad_norm": 0.18640218675136566,
1066
+ "learning_rate": 0.00014609743745354624,
1067
+ "loss": 0.2976,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.73,
1072
+ "grad_norm": 0.1410883516073227,
1073
+ "learning_rate": 0.00014539904997395468,
1074
+ "loss": 0.1779,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.73,
1079
+ "grad_norm": 0.1352994590997696,
1080
+ "learning_rate": 0.00014469786206711214,
1081
+ "loss": 0.1932,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.74,
1086
+ "grad_norm": 0.16276930272579193,
1087
+ "learning_rate": 0.00014399391698559152,
1088
+ "loss": 0.19,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.74,
1093
+ "grad_norm": 0.1330641359090805,
1094
+ "learning_rate": 0.00014328725815204144,
1095
+ "loss": 0.1529,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.75,
1100
+ "grad_norm": 0.1461140215396881,
1101
+ "learning_rate": 0.00014257792915650728,
1102
+ "loss": 0.1822,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.75,
1107
+ "grad_norm": 0.1400836855173111,
1108
+ "learning_rate": 0.0001418659737537428,
1109
+ "loss": 0.1984,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.76,
1114
+ "grad_norm": 0.15338997542858124,
1115
+ "learning_rate": 0.00014115143586051088,
1116
+ "loss": 0.1856,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.76,
1121
+ "grad_norm": 0.15661920607089996,
1122
+ "learning_rate": 0.00014043435955287452,
1123
+ "loss": 0.2219,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.77,
1128
+ "grad_norm": 0.22158733010292053,
1129
+ "learning_rate": 0.00013971478906347806,
1130
+ "loss": 0.3549,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.77,
1135
+ "grad_norm": 0.1338592767715454,
1136
+ "learning_rate": 0.00013899276877881884,
1137
+ "loss": 0.1785,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.78,
1142
+ "grad_norm": 0.14615756273269653,
1143
+ "learning_rate": 0.000138268343236509,
1144
+ "loss": 0.2202,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.78,
1149
+ "grad_norm": 0.1247783973813057,
1150
+ "learning_rate": 0.00013754155712252832,
1151
+ "loss": 0.2008,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.79,
1156
+ "grad_norm": 0.18145664036273956,
1157
+ "learning_rate": 0.00013681245526846783,
1158
+ "loss": 0.2144,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.79,
1163
+ "grad_norm": 0.1396200805902481,
1164
+ "learning_rate": 0.0001360810826487642,
1165
+ "loss": 0.2194,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.8,
1170
+ "grad_norm": 0.15508796274662018,
1171
+ "learning_rate": 0.00013534748437792573,
1172
+ "loss": 0.2766,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.8,
1177
+ "grad_norm": 0.15434060990810394,
1178
+ "learning_rate": 0.0001346117057077493,
1179
+ "loss": 0.188,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.81,
1184
+ "grad_norm": 0.14731119573116302,
1185
+ "learning_rate": 0.00013387379202452917,
1186
+ "loss": 0.233,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.81,
1191
+ "grad_norm": 0.1317255198955536,
1192
+ "learning_rate": 0.0001331337888462571,
1193
+ "loss": 0.233,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.82,
1198
+ "grad_norm": 0.16242042183876038,
1199
+ "learning_rate": 0.00013239174181981495,
1200
+ "loss": 0.2541,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.82,
1205
+ "grad_norm": 0.14940407872200012,
1206
+ "learning_rate": 0.00013164769671815862,
1207
+ "loss": 0.2244,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.83,
1212
+ "grad_norm": 0.14262273907661438,
1213
+ "learning_rate": 0.00013090169943749476,
1214
+ "loss": 0.2458,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.83,
1219
+ "grad_norm": 0.13066165149211884,
1220
+ "learning_rate": 0.00013015379599444957,
1221
+ "loss": 0.1865,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.84,
1226
+ "grad_norm": 0.14521218836307526,
1227
+ "learning_rate": 0.0001294040325232304,
1228
+ "loss": 0.1838,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.84,
1233
+ "grad_norm": 0.14943768084049225,
1234
+ "learning_rate": 0.00012865245527277986,
1235
+ "loss": 0.2369,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.85,
1240
+ "grad_norm": 0.14182843267917633,
1241
+ "learning_rate": 0.00012789911060392294,
1242
+ "loss": 0.1953,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.85,
1247
+ "grad_norm": 0.16210182011127472,
1248
+ "learning_rate": 0.00012714404498650743,
1249
+ "loss": 0.2624,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.86,
1254
+ "grad_norm": 0.15228134393692017,
1255
+ "learning_rate": 0.0001263873049965373,
1256
+ "loss": 0.2441,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.86,
1261
+ "grad_norm": 0.13629144430160522,
1262
+ "learning_rate": 0.00012562893731329967,
1263
+ "loss": 0.2003,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.87,
1268
+ "grad_norm": 0.15732020139694214,
1269
+ "learning_rate": 0.0001248689887164855,
1270
+ "loss": 0.2311,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.87,
1275
+ "grad_norm": 0.13804040849208832,
1276
+ "learning_rate": 0.00012410750608330388,
1277
+ "loss": 0.1768,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.87,
1282
+ "grad_norm": 0.13766342401504517,
1283
+ "learning_rate": 0.00012334453638559057,
1284
+ "loss": 0.2182,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.88,
1289
+ "grad_norm": 0.15981349349021912,
1290
+ "learning_rate": 0.0001225801266869104,
1291
+ "loss": 0.2061,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.88,
1296
+ "grad_norm": 0.12819038331508636,
1297
+ "learning_rate": 0.00012181432413965428,
1298
+ "loss": 0.1549,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.89,
1303
+ "grad_norm": 0.13831038773059845,
1304
+ "learning_rate": 0.00012104717598213056,
1305
+ "loss": 0.1653,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.89,
1310
+ "grad_norm": 0.16673411428928375,
1311
+ "learning_rate": 0.00012027872953565125,
1312
+ "loss": 0.1933,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.9,
1317
+ "grad_norm": 0.14682242274284363,
1318
+ "learning_rate": 0.00011950903220161285,
1319
+ "loss": 0.202,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.9,
1324
+ "grad_norm": 0.1462392807006836,
1325
+ "learning_rate": 0.00011873813145857249,
1326
+ "loss": 0.2377,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.91,
1331
+ "grad_norm": 0.12843555212020874,
1332
+ "learning_rate": 0.00011796607485931928,
1333
+ "loss": 0.2125,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.91,
1338
+ "grad_norm": 0.15481220185756683,
1339
+ "learning_rate": 0.00011719291002794096,
1340
+ "loss": 0.2539,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.92,
1345
+ "grad_norm": 0.13950768113136292,
1346
+ "learning_rate": 0.0001164186846568863,
1347
+ "loss": 0.1972,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.92,
1352
+ "grad_norm": 0.11621260643005371,
1353
+ "learning_rate": 0.0001156434465040231,
1354
+ "loss": 0.1856,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.93,
1359
+ "grad_norm": 0.14099712669849396,
1360
+ "learning_rate": 0.00011486724338969232,
1361
+ "loss": 0.1916,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.93,
1366
+ "grad_norm": 0.1282750517129898,
1367
+ "learning_rate": 0.00011409012319375827,
1368
+ "loss": 0.1836,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.94,
1373
+ "grad_norm": 0.15066012740135193,
1374
+ "learning_rate": 0.00011331213385265524,
1375
+ "loss": 0.2432,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.94,
1380
+ "grad_norm": 0.14334805309772491,
1381
+ "learning_rate": 0.00011253332335643043,
1382
+ "loss": 0.1749,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.95,
1387
+ "grad_norm": 0.15670594573020935,
1388
+ "learning_rate": 0.00011175373974578378,
1389
+ "loss": 0.2479,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.95,
1394
+ "grad_norm": 0.15438470244407654,
1395
+ "learning_rate": 0.00011097343110910452,
1396
+ "loss": 0.2356,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.96,
1401
+ "grad_norm": 0.1420874148607254,
1402
+ "learning_rate": 0.000110192445579505,
1403
+ "loss": 0.2662,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.96,
1408
+ "grad_norm": 0.1418399214744568,
1409
+ "learning_rate": 0.00010941083133185146,
1410
+ "loss": 0.1785,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.97,
1415
+ "grad_norm": 0.1280946284532547,
1416
+ "learning_rate": 0.00010862863657979237,
1417
+ "loss": 0.1652,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.97,
1422
+ "grad_norm": 0.14323323965072632,
1423
+ "learning_rate": 0.0001078459095727845,
1424
+ "loss": 0.2104,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.98,
1429
+ "grad_norm": 0.10913383960723877,
1430
+ "learning_rate": 0.00010706269859311669,
1431
+ "loss": 0.1448,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.98,
1436
+ "grad_norm": 0.12007103115320206,
1437
+ "learning_rate": 0.00010627905195293135,
1438
+ "loss": 0.1263,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.99,
1443
+ "grad_norm": 0.1433536857366562,
1444
+ "learning_rate": 0.0001054950179912446,
1445
+ "loss": 0.1831,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.99,
1450
+ "grad_norm": 0.1542392522096634,
1451
+ "learning_rate": 0.00010471064507096426,
1452
+ "loss": 0.2828,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 1.0,
1457
+ "grad_norm": 0.18856601417064667,
1458
+ "learning_rate": 0.00010392598157590688,
1459
+ "loss": 0.183,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 1.0,
1464
+ "grad_norm": 0.13536609709262848,
1465
+ "learning_rate": 0.00010314107590781284,
1466
+ "loss": 0.2161,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 1.0,
1471
+ "eval_loss": 0.22577418386936188,
1472
+ "eval_runtime": 13.2186,
1473
+ "eval_samples_per_second": 1.891,
1474
+ "eval_steps_per_second": 1.891,
1475
+ "step": 206
1476
+ },
1477
+ {
1478
+ "epoch": 1.01,
1479
+ "grad_norm": 0.1510825753211975,
1480
+ "learning_rate": 0.00010235597648336104,
1481
+ "loss": 0.174,
1482
+ "step": 207
1483
+ },
1484
+ {
1485
+ "epoch": 1.01,
1486
+ "grad_norm": 0.13914929330348969,
1487
+ "learning_rate": 0.00010157073173118208,
1488
+ "loss": 0.2656,
1489
+ "step": 208
1490
+ },
1491
+ {
1492
+ "epoch": 1.02,
1493
+ "grad_norm": 0.15691936016082764,
1494
+ "learning_rate": 0.00010078539008887114,
1495
+ "loss": 0.2394,
1496
+ "step": 209
1497
+ },
1498
+ {
1499
+ "epoch": 1.02,
1500
+ "grad_norm": 0.15231585502624512,
1501
+ "learning_rate": 0.0001,
1502
+ "loss": 0.2392,
1503
+ "step": 210
1504
+ },
1505
+ {
1506
+ "epoch": 1.03,
1507
+ "grad_norm": 0.14635689556598663,
1508
+ "learning_rate": 9.921460991112891e-05,
1509
+ "loss": 0.1702,
1510
+ "step": 211
1511
+ },
1512
+ {
1513
+ "epoch": 1.03,
1514
+ "grad_norm": 0.1327444165945053,
1515
+ "learning_rate": 9.842926826881796e-05,
1516
+ "loss": 0.2196,
1517
+ "step": 212
1518
+ },
1519
+ {
1520
+ "epoch": 1.0,
1521
+ "grad_norm": 0.1320512443780899,
1522
+ "learning_rate": 9.764402351663901e-05,
1523
+ "loss": 0.1945,
1524
+ "step": 213
1525
+ },
1526
+ {
1527
+ "epoch": 1.01,
1528
+ "grad_norm": 0.13175004720687866,
1529
+ "learning_rate": 9.685892409218717e-05,
1530
+ "loss": 0.209,
1531
+ "step": 214
1532
+ },
1533
+ {
1534
+ "epoch": 1.01,
1535
+ "grad_norm": 0.11285891383886337,
1536
+ "learning_rate": 9.607401842409317e-05,
1537
+ "loss": 0.1671,
1538
+ "step": 215
1539
+ },
1540
+ {
1541
+ "epoch": 1.02,
1542
+ "grad_norm": 0.13914702832698822,
1543
+ "learning_rate": 9.528935492903575e-05,
1544
+ "loss": 0.2156,
1545
+ "step": 216
1546
+ },
1547
+ {
1548
+ "epoch": 1.02,
1549
+ "grad_norm": 0.11163745075464249,
1550
+ "learning_rate": 9.450498200875546e-05,
1551
+ "loss": 0.1547,
1552
+ "step": 217
1553
+ },
1554
+ {
1555
+ "epoch": 1.03,
1556
+ "grad_norm": 0.12759771943092346,
1557
+ "learning_rate": 9.372094804706867e-05,
1558
+ "loss": 0.1698,
1559
+ "step": 218
1560
+ },
1561
+ {
1562
+ "epoch": 1.03,
1563
+ "grad_norm": 0.15159080922603607,
1564
+ "learning_rate": 9.293730140688336e-05,
1565
+ "loss": 0.2386,
1566
+ "step": 219
1567
+ },
1568
+ {
1569
+ "epoch": 1.04,
1570
+ "grad_norm": 0.1276952624320984,
1571
+ "learning_rate": 9.215409042721552e-05,
1572
+ "loss": 0.1755,
1573
+ "step": 220
1574
+ },
1575
+ {
1576
+ "epoch": 1.04,
1577
+ "grad_norm": 0.13293467462062836,
1578
+ "learning_rate": 9.137136342020768e-05,
1579
+ "loss": 0.1732,
1580
+ "step": 221
1581
+ },
1582
+ {
1583
+ "epoch": 1.05,
1584
+ "grad_norm": 0.13667437434196472,
1585
+ "learning_rate": 9.058916866814858e-05,
1586
+ "loss": 0.1606,
1587
+ "step": 222
1588
+ },
1589
+ {
1590
+ "epoch": 1.05,
1591
+ "grad_norm": 0.1378675252199173,
1592
+ "learning_rate": 8.980755442049502e-05,
1593
+ "loss": 0.1656,
1594
+ "step": 223
1595
+ },
1596
+ {
1597
+ "epoch": 1.06,
1598
+ "grad_norm": 0.13927237689495087,
1599
+ "learning_rate": 8.902656889089548e-05,
1600
+ "loss": 0.1615,
1601
+ "step": 224
1602
+ },
1603
+ {
1604
+ "epoch": 1.06,
1605
+ "grad_norm": 0.12705956399440765,
1606
+ "learning_rate": 8.824626025421626e-05,
1607
+ "loss": 0.1235,
1608
+ "step": 225
1609
+ },
1610
+ {
1611
+ "epoch": 1.07,
1612
+ "grad_norm": 0.17281681299209595,
1613
+ "learning_rate": 8.746667664356956e-05,
1614
+ "loss": 0.1835,
1615
+ "step": 226
1616
+ },
1617
+ {
1618
+ "epoch": 1.07,
1619
+ "grad_norm": 0.15210822224617004,
1620
+ "learning_rate": 8.668786614734478e-05,
1621
+ "loss": 0.1514,
1622
+ "step": 227
1623
+ },
1624
+ {
1625
+ "epoch": 1.08,
1626
+ "grad_norm": 0.17541825771331787,
1627
+ "learning_rate": 8.590987680624174e-05,
1628
+ "loss": 0.1403,
1629
+ "step": 228
1630
+ },
1631
+ {
1632
+ "epoch": 1.08,
1633
+ "grad_norm": 0.13942864537239075,
1634
+ "learning_rate": 8.51327566103077e-05,
1635
+ "loss": 0.1423,
1636
+ "step": 229
1637
+ },
1638
+ {
1639
+ "epoch": 1.09,
1640
+ "grad_norm": 0.16645929217338562,
1641
+ "learning_rate": 8.435655349597689e-05,
1642
+ "loss": 0.1773,
1643
+ "step": 230
1644
+ },
1645
+ {
1646
+ "epoch": 1.09,
1647
+ "grad_norm": 0.16734780371189117,
1648
+ "learning_rate": 8.358131534311372e-05,
1649
+ "loss": 0.2327,
1650
+ "step": 231
1651
+ },
1652
+ {
1653
+ "epoch": 1.09,
1654
+ "grad_norm": 0.18149012327194214,
1655
+ "learning_rate": 8.280708997205904e-05,
1656
+ "loss": 0.182,
1657
+ "step": 232
1658
+ },
1659
+ {
1660
+ "epoch": 1.1,
1661
+ "grad_norm": 0.1811237931251526,
1662
+ "learning_rate": 8.203392514068074e-05,
1663
+ "loss": 0.2129,
1664
+ "step": 233
1665
+ },
1666
+ {
1667
+ "epoch": 1.1,
1668
+ "grad_norm": 0.17224758863449097,
1669
+ "learning_rate": 8.126186854142752e-05,
1670
+ "loss": 0.1836,
1671
+ "step": 234
1672
+ },
1673
+ {
1674
+ "epoch": 1.11,
1675
+ "grad_norm": 0.15472543239593506,
1676
+ "learning_rate": 8.049096779838719e-05,
1677
+ "loss": 0.1418,
1678
+ "step": 235
1679
+ },
1680
+ {
1681
+ "epoch": 1.11,
1682
+ "grad_norm": 0.15701377391815186,
1683
+ "learning_rate": 7.972127046434878e-05,
1684
+ "loss": 0.1749,
1685
+ "step": 236
1686
+ },
1687
+ {
1688
+ "epoch": 1.12,
1689
+ "grad_norm": 0.15067677199840546,
1690
+ "learning_rate": 7.895282401786945e-05,
1691
+ "loss": 0.1347,
1692
+ "step": 237
1693
+ },
1694
+ {
1695
+ "epoch": 1.12,
1696
+ "grad_norm": 0.12470359355211258,
1697
+ "learning_rate": 7.818567586034577e-05,
1698
+ "loss": 0.1155,
1699
+ "step": 238
1700
+ },
1701
+ {
1702
+ "epoch": 1.13,
1703
+ "grad_norm": 0.15522097051143646,
1704
+ "learning_rate": 7.741987331308964e-05,
1705
+ "loss": 0.1537,
1706
+ "step": 239
1707
+ },
1708
+ {
1709
+ "epoch": 1.13,
1710
+ "grad_norm": 0.17973066866397858,
1711
+ "learning_rate": 7.66554636144095e-05,
1712
+ "loss": 0.1844,
1713
+ "step": 240
1714
+ },
1715
+ {
1716
+ "epoch": 1.14,
1717
+ "grad_norm": 0.14860330522060394,
1718
+ "learning_rate": 7.589249391669616e-05,
1719
+ "loss": 0.1643,
1720
+ "step": 241
1721
+ },
1722
+ {
1723
+ "epoch": 1.14,
1724
+ "grad_norm": 0.16414889693260193,
1725
+ "learning_rate": 7.513101128351454e-05,
1726
+ "loss": 0.1533,
1727
+ "step": 242
1728
+ },
1729
+ {
1730
+ "epoch": 1.15,
1731
+ "grad_norm": 0.14017800986766815,
1732
+ "learning_rate": 7.437106268670034e-05,
1733
+ "loss": 0.1556,
1734
+ "step": 243
1735
+ },
1736
+ {
1737
+ "epoch": 1.15,
1738
+ "grad_norm": 0.1377851516008377,
1739
+ "learning_rate": 7.361269500346274e-05,
1740
+ "loss": 0.1175,
1741
+ "step": 244
1742
+ },
1743
+ {
1744
+ "epoch": 1.16,
1745
+ "grad_norm": 0.13657085597515106,
1746
+ "learning_rate": 7.285595501349258e-05,
1747
+ "loss": 0.1182,
1748
+ "step": 245
1749
+ },
1750
+ {
1751
+ "epoch": 1.16,
1752
+ "grad_norm": 0.16157828271389008,
1753
+ "learning_rate": 7.210088939607708e-05,
1754
+ "loss": 0.2083,
1755
+ "step": 246
1756
+ },
1757
+ {
1758
+ "epoch": 1.17,
1759
+ "grad_norm": 0.15126171708106995,
1760
+ "learning_rate": 7.134754472722017e-05,
1761
+ "loss": 0.1384,
1762
+ "step": 247
1763
+ },
1764
+ {
1765
+ "epoch": 1.17,
1766
+ "grad_norm": 0.1582876294851303,
1767
+ "learning_rate": 7.059596747676962e-05,
1768
+ "loss": 0.135,
1769
+ "step": 248
1770
+ },
1771
+ {
1772
+ "epoch": 1.18,
1773
+ "grad_norm": 0.15393657982349396,
1774
+ "learning_rate": 6.984620400555044e-05,
1775
+ "loss": 0.1529,
1776
+ "step": 249
1777
+ },
1778
+ {
1779
+ "epoch": 1.18,
1780
+ "grad_norm": 0.16819702088832855,
1781
+ "learning_rate": 6.909830056250527e-05,
1782
+ "loss": 0.1589,
1783
+ "step": 250
1784
+ },
1785
+ {
1786
+ "epoch": 1.19,
1787
+ "grad_norm": 0.17828214168548584,
1788
+ "learning_rate": 6.835230328184138e-05,
1789
+ "loss": 0.1549,
1790
+ "step": 251
1791
+ },
1792
+ {
1793
+ "epoch": 1.19,
1794
+ "grad_norm": 0.17099595069885254,
1795
+ "learning_rate": 6.760825818018508e-05,
1796
+ "loss": 0.1767,
1797
+ "step": 252
1798
+ },
1799
+ {
1800
+ "epoch": 1.2,
1801
+ "grad_norm": 0.17799484729766846,
1802
+ "learning_rate": 6.68662111537429e-05,
1803
+ "loss": 0.1274,
1804
+ "step": 253
1805
+ },
1806
+ {
1807
+ "epoch": 1.2,
1808
+ "grad_norm": 0.21973256766796112,
1809
+ "learning_rate": 6.612620797547087e-05,
1810
+ "loss": 0.1664,
1811
+ "step": 254
1812
+ },
1813
+ {
1814
+ "epoch": 1.21,
1815
+ "grad_norm": 0.19034262001514435,
1816
+ "learning_rate": 6.538829429225069e-05,
1817
+ "loss": 0.1932,
1818
+ "step": 255
1819
+ },
1820
+ {
1821
+ "epoch": 1.21,
1822
+ "grad_norm": 0.20569321513175964,
1823
+ "learning_rate": 6.465251562207431e-05,
1824
+ "loss": 0.1971,
1825
+ "step": 256
1826
+ },
1827
+ {
1828
+ "epoch": 1.22,
1829
+ "grad_norm": 0.1574014127254486,
1830
+ "learning_rate": 6.391891735123582e-05,
1831
+ "loss": 0.1255,
1832
+ "step": 257
1833
+ },
1834
+ {
1835
+ "epoch": 1.22,
1836
+ "grad_norm": 0.1868090033531189,
1837
+ "learning_rate": 6.318754473153221e-05,
1838
+ "loss": 0.202,
1839
+ "step": 258
1840
+ },
1841
+ {
1842
+ "epoch": 1.23,
1843
+ "grad_norm": 0.15771806240081787,
1844
+ "learning_rate": 6.245844287747168e-05,
1845
+ "loss": 0.1348,
1846
+ "step": 259
1847
+ },
1848
+ {
1849
+ "epoch": 1.23,
1850
+ "grad_norm": 0.1910022646188736,
1851
+ "learning_rate": 6.173165676349103e-05,
1852
+ "loss": 0.1399,
1853
+ "step": 260
1854
+ },
1855
+ {
1856
+ "epoch": 1.24,
1857
+ "grad_norm": 0.192474827170372,
1858
+ "learning_rate": 6.1007231221181206e-05,
1859
+ "loss": 0.1497,
1860
+ "step": 261
1861
+ },
1862
+ {
1863
+ "epoch": 1.24,
1864
+ "grad_norm": 0.20803901553153992,
1865
+ "learning_rate": 6.0285210936521955e-05,
1866
+ "loss": 0.1459,
1867
+ "step": 262
1868
+ },
1869
+ {
1870
+ "epoch": 1.25,
1871
+ "grad_norm": 0.16716165840625763,
1872
+ "learning_rate": 5.956564044712551e-05,
1873
+ "loss": 0.1352,
1874
+ "step": 263
1875
+ },
1876
+ {
1877
+ "epoch": 1.25,
1878
+ "grad_norm": 0.2101832777261734,
1879
+ "learning_rate": 5.884856413948913e-05,
1880
+ "loss": 0.1676,
1881
+ "step": 264
1882
+ },
1883
+ {
1884
+ "epoch": 1.26,
1885
+ "grad_norm": 0.19041313230991364,
1886
+ "learning_rate": 5.8134026246257225e-05,
1887
+ "loss": 0.1492,
1888
+ "step": 265
1889
+ },
1890
+ {
1891
+ "epoch": 1.26,
1892
+ "grad_norm": 0.17860420048236847,
1893
+ "learning_rate": 5.7422070843492734e-05,
1894
+ "loss": 0.1058,
1895
+ "step": 266
1896
+ },
1897
+ {
1898
+ "epoch": 1.26,
1899
+ "grad_norm": 0.15917859971523285,
1900
+ "learning_rate": 5.671274184795865e-05,
1901
+ "loss": 0.1315,
1902
+ "step": 267
1903
+ },
1904
+ {
1905
+ "epoch": 1.27,
1906
+ "grad_norm": 0.19338840246200562,
1907
+ "learning_rate": 5.6006083014408484e-05,
1908
+ "loss": 0.1436,
1909
+ "step": 268
1910
+ },
1911
+ {
1912
+ "epoch": 1.27,
1913
+ "grad_norm": 0.27872714400291443,
1914
+ "learning_rate": 5.53021379328879e-05,
1915
+ "loss": 0.1233,
1916
+ "step": 269
1917
+ },
1918
+ {
1919
+ "epoch": 1.28,
1920
+ "grad_norm": 0.16847865283489227,
1921
+ "learning_rate": 5.4600950026045326e-05,
1922
+ "loss": 0.1166,
1923
+ "step": 270
1924
+ },
1925
+ {
1926
+ "epoch": 1.28,
1927
+ "grad_norm": 0.16588595509529114,
1928
+ "learning_rate": 5.390256254645378e-05,
1929
+ "loss": 0.1285,
1930
+ "step": 271
1931
+ },
1932
+ {
1933
+ "epoch": 1.29,
1934
+ "grad_norm": 0.18695320188999176,
1935
+ "learning_rate": 5.320701857394268e-05,
1936
+ "loss": 0.1741,
1937
+ "step": 272
1938
+ },
1939
+ {
1940
+ "epoch": 1.29,
1941
+ "grad_norm": 0.18936707079410553,
1942
+ "learning_rate": 5.251436101294056e-05,
1943
+ "loss": 0.1559,
1944
+ "step": 273
1945
+ },
1946
+ {
1947
+ "epoch": 1.3,
1948
+ "grad_norm": 0.1948186159133911,
1949
+ "learning_rate": 5.182463258982846e-05,
1950
+ "loss": 0.1555,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 1.3,
1955
+ "grad_norm": 0.1960403323173523,
1956
+ "learning_rate": 5.113787585030454e-05,
1957
+ "loss": 0.1562,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 1.31,
1962
+ "grad_norm": 0.17642433941364288,
1963
+ "learning_rate": 5.045413315675924e-05,
1964
+ "loss": 0.1545,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 1.31,
1969
+ "grad_norm": 0.2207774519920349,
1970
+ "learning_rate": 4.977344668566275e-05,
1971
+ "loss": 0.1866,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 1.32,
1976
+ "grad_norm": 0.1559211015701294,
1977
+ "learning_rate": 4.909585842496287e-05,
1978
+ "loss": 0.1201,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 1.32,
1983
+ "grad_norm": 0.16633960604667664,
1984
+ "learning_rate": 4.842141017149526e-05,
1985
+ "loss": 0.1229,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 1.33,
1990
+ "grad_norm": 0.1892048567533493,
1991
+ "learning_rate": 4.7750143528405126e-05,
1992
+ "loss": 0.166,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 1.33,
1997
+ "grad_norm": 0.1674378365278244,
1998
+ "learning_rate": 4.708209990258095e-05,
1999
+ "loss": 0.1496,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 1.34,
2004
+ "grad_norm": 0.17542515695095062,
2005
+ "learning_rate": 4.6417320502100316e-05,
2006
+ "loss": 0.1326,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 1.34,
2011
+ "grad_norm": 0.17793145775794983,
2012
+ "learning_rate": 4.575584633368815e-05,
2013
+ "loss": 0.1599,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 1.35,
2018
+ "grad_norm": 0.2022085189819336,
2019
+ "learning_rate": 4.5097718200186814e-05,
2020
+ "loss": 0.1681,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 1.35,
2025
+ "grad_norm": 0.1831180453300476,
2026
+ "learning_rate": 4.444297669803981e-05,
2027
+ "loss": 0.176,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 1.36,
2032
+ "grad_norm": 0.15007005631923676,
2033
+ "learning_rate": 4.379166221478697e-05,
2034
+ "loss": 0.1247,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 1.36,
2039
+ "grad_norm": 0.17191900312900543,
2040
+ "learning_rate": 4.31438149265736e-05,
2041
+ "loss": 0.1494,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 1.37,
2046
+ "grad_norm": 0.21848122775554657,
2047
+ "learning_rate": 4.249947479567218e-05,
2048
+ "loss": 0.2025,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 1.37,
2053
+ "grad_norm": 0.21705280244350433,
2054
+ "learning_rate": 4.185868156801694e-05,
2055
+ "loss": 0.1822,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 1.38,
2060
+ "grad_norm": 0.20829765498638153,
2061
+ "learning_rate": 4.12214747707527e-05,
2062
+ "loss": 0.1926,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 1.38,
2067
+ "grad_norm": 0.18017052114009857,
2068
+ "learning_rate": 4.058789370979615e-05,
2069
+ "loss": 0.1399,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 1.39,
2074
+ "grad_norm": 0.1806417554616928,
2075
+ "learning_rate": 3.9957977467411615e-05,
2076
+ "loss": 0.1443,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 1.39,
2081
+ "grad_norm": 0.1974053829908371,
2082
+ "learning_rate": 3.933176489980005e-05,
2083
+ "loss": 0.1555,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 1.4,
2088
+ "grad_norm": 0.18204301595687866,
2089
+ "learning_rate": 3.8709294634702376e-05,
2090
+ "loss": 0.1732,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 1.4,
2095
+ "grad_norm": 0.20640143752098083,
2096
+ "learning_rate": 3.8090605069016595e-05,
2097
+ "loss": 0.1682,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 1.41,
2102
+ "grad_norm": 0.15330561995506287,
2103
+ "learning_rate": 3.747573436642951e-05,
2104
+ "loss": 0.1061,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 1.41,
2109
+ "grad_norm": 0.17504094541072845,
2110
+ "learning_rate": 3.686472045506223e-05,
2111
+ "loss": 0.1208,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 1.42,
2116
+ "grad_norm": 0.19445376098155975,
2117
+ "learning_rate": 3.6257601025131026e-05,
2118
+ "loss": 0.1637,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 1.42,
2123
+ "grad_norm": 0.20897901058197021,
2124
+ "learning_rate": 3.565441352662211e-05,
2125
+ "loss": 0.1518,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 1.43,
2130
+ "grad_norm": 0.17896625399589539,
2131
+ "learning_rate": 3.5055195166981645e-05,
2132
+ "loss": 0.1512,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 1.43,
2137
+ "grad_norm": 0.20567168295383453,
2138
+ "learning_rate": 3.445998290882062e-05,
2139
+ "loss": 0.1551,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 1.43,
2144
+ "grad_norm": 0.19793061912059784,
2145
+ "learning_rate": 3.386881346763483e-05,
2146
+ "loss": 0.1436,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 1.44,
2151
+ "grad_norm": 0.1717611402273178,
2152
+ "learning_rate": 3.328172330954001e-05,
2153
+ "loss": 0.153,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 1.44,
2158
+ "grad_norm": 0.18997669219970703,
2159
+ "learning_rate": 3.269874864902269e-05,
2160
+ "loss": 0.1352,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 1.45,
2165
+ "grad_norm": 0.18684212863445282,
2166
+ "learning_rate": 3.211992544670582e-05,
2167
+ "loss": 0.133,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 1.45,
2172
+ "grad_norm": 0.1856592297554016,
2173
+ "learning_rate": 3.154528940713113e-05,
2174
+ "loss": 0.14,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 1.46,
2179
+ "grad_norm": 0.1783703714609146,
2180
+ "learning_rate": 3.0974875976556284e-05,
2181
+ "loss": 0.1368,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 1.46,
2186
+ "grad_norm": 0.16114623844623566,
2187
+ "learning_rate": 3.0408720340768572e-05,
2188
+ "loss": 0.1353,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 1.47,
2193
+ "grad_norm": 0.24124671518802643,
2194
+ "learning_rate": 2.9846857422914433e-05,
2195
+ "loss": 0.1821,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 1.47,
2200
+ "eval_loss": 0.235604926943779,
2201
+ "eval_runtime": 13.2989,
2202
+ "eval_samples_per_second": 1.88,
2203
+ "eval_steps_per_second": 1.88,
2204
+ "step": 309
2205
+ }
2206
+ ],
2207
+ "logging_steps": 1,
2208
+ "max_steps": 410,
2209
+ "num_input_tokens_seen": 0,
2210
+ "num_train_epochs": 2,
2211
+ "save_steps": 103,
2212
+ "total_flos": 1.927039310801584e+18,
2213
+ "train_batch_size": 1,
2214
+ "trial_name": null,
2215
+ "trial_params": null
2216
+ }
adapter/checkpoint-309/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c619572c8607352856f31afb988e45204d8ad93ba4c2fe0fb58a0afe4e724f6b
3
+ size 5752
adapter/checkpoint-610/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: /home/outscale/jamba
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 0.10.0
adapter/checkpoint-610/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/outscale/jamba",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "router",
24
+ "x_proj",
25
+ "down_proj",
26
+ "gate_proj",
27
+ "out_proj",
28
+ "o_proj",
29
+ "dt_proj",
30
+ "in_proj",
31
+ "q_proj",
32
+ "k_proj",
33
+ "up_proj",
34
+ "v_proj"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter/checkpoint-610/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92814b1d9841b5a27426d948fc5bfab196dbc067459b2c5d9714af979f8a3167
3
+ size 531607760
adapter/checkpoint-610/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87570b0a66405c830a17afe885de5a71a68ad9fd7dfc0d7022d66dc161cfbd1
3
+ size 269103876
adapter/checkpoint-610/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535e104a2b68b7cdeecb57ba0e55c5b1dc8859c785bbf45126972366c82d365d
3
+ size 14244
adapter/checkpoint-610/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ea5a94472a10e843975bff98661b17beb8ed9f7d710bd4ff5ce5243d202470
3
+ size 1064
adapter/checkpoint-610/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
adapter/checkpoint-610/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
adapter/checkpoint-610/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
3
+ size 1124742
adapter/checkpoint-610/tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|unk|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<|startoftext|>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<|endoftext|>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<|pad|>",
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<|unk|>",
46
+ "use_default_system_prompt": false
47
+ }
adapter/checkpoint-610/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff