Menouar commited on
Commit
6849bc0
1 Parent(s): 5b63e99

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-3749/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,303 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: other
4
+ tags:
5
+ - generated_from_trainer
6
+ - google/gemma
7
+ - PyTorch
8
+ - transformers
9
+ - trl
10
+ - peft
11
+ - tensorboard
12
+ model-index:
13
+ - name: pygemma-2b-ultra
14
+ results: []
15
+ datasets:
16
+ - Vezora/Tested-143k-Python-Alpaca
17
+ language:
18
+ - en
19
+ license_name: gemma-terms-of-use
20
+ license_link: https://ai.google.dev/gemma/terms
21
+ base_model: google/gemma-2b
22
+ widget:
23
+ - example_title: Compute Sum
24
+ messages:
25
+ - role: system
26
+ content: "fdfsdfsdf"
27
+ - role: user
28
+ content: Create a function to calculate the sum of a sequence of integers.
29
+ pipeline_tag: text-generation
30
+ ---
31
+
32
+ # Model Card for pygemma-2b-ultra:
33
+
34
+ 🐍💬🤖
35
+
36
+
37
+ **pygemma-2b-ultra** is a language model that is trained to act as Python assistant. It is a finetuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) that was trained using `SFTTrainer` on publicly available dataset
38
+ [Vezora/Tested-143k-Python-Alpaca](https://huggingface.co/datasets/Vezora/Tested-143k-Python-Alpaca).
39
+
40
+
41
+ ## Training Metrics
42
+
43
+ [The training metrics can be found on **TensorBoard**](https://huggingface.co/Menouar/pygemma-2b-ultra/tensorboard).
44
+
45
+
46
+ ## Training hyperparameters
47
+
48
+ The following hyperparameters were used during the training:
49
+
50
+
51
+ - output_dir: peft-lora-model
52
+
53
+ - overwrite_output_dir: True
54
+
55
+ - do_train: False
56
+
57
+ - do_eval: False
58
+
59
+ - do_predict: False
60
+
61
+ - evaluation_strategy: no
62
+
63
+ - prediction_loss_only: False
64
+
65
+ - per_device_train_batch_size: 2
66
+
67
+ - per_device_eval_batch_size: None
68
+
69
+ - per_gpu_train_batch_size: None
70
+
71
+ - per_gpu_eval_batch_size: None
72
+
73
+ - gradient_accumulation_steps: 4
74
+
75
+ - eval_accumulation_steps: None
76
+
77
+ - eval_delay: 0
78
+
79
+ - learning_rate: 2e-05
80
+
81
+ - weight_decay: 0.0
82
+
83
+ - adam_beta1: 0.9
84
+
85
+ - adam_beta2: 0.999
86
+
87
+ - adam_epsilon: 1e-08
88
+
89
+ - max_grad_norm: 0.3
90
+
91
+ - num_train_epochs: 1
92
+
93
+ - max_steps: -1
94
+
95
+ - lr_scheduler_type: cosine
96
+
97
+ - lr_scheduler_kwargs: {}
98
+
99
+ - warmup_ratio: 0.1
100
+
101
+ - warmup_steps: 0
102
+
103
+ - log_level: passive
104
+
105
+ - log_level_replica: warning
106
+
107
+ - log_on_each_node: True
108
+
109
+ - logging_dir: peft-lora-model/runs/Mar22_07-15-06_2013f91d074a
110
+
111
+ - logging_strategy: steps
112
+
113
+ - logging_first_step: False
114
+
115
+ - logging_steps: 10
116
+
117
+ - logging_nan_inf_filter: True
118
+
119
+ - save_strategy: epoch
120
+
121
+ - save_steps: 500
122
+
123
+ - save_total_limit: None
124
+
125
+ - save_safetensors: True
126
+
127
+ - save_on_each_node: False
128
+
129
+ - save_only_model: False
130
+
131
+ - no_cuda: False
132
+
133
+ - use_cpu: False
134
+
135
+ - use_mps_device: False
136
+
137
+ - seed: 42
138
+
139
+ - data_seed: None
140
+
141
+ - jit_mode_eval: False
142
+
143
+ - use_ipex: False
144
+
145
+ - bf16: True
146
+
147
+ - fp16: False
148
+
149
+ - fp16_opt_level: O1
150
+
151
+ - half_precision_backend: auto
152
+
153
+ - bf16_full_eval: False
154
+
155
+ - fp16_full_eval: False
156
+
157
+ - tf32: None
158
+
159
+ - local_rank: 0
160
+
161
+ - ddp_backend: None
162
+
163
+ - tpu_num_cores: None
164
+
165
+ - tpu_metrics_debug: False
166
+
167
+ - debug: []
168
+
169
+ - dataloader_drop_last: False
170
+
171
+ - eval_steps: None
172
+
173
+ - dataloader_num_workers: 0
174
+
175
+ - dataloader_prefetch_factor: None
176
+
177
+ - past_index: -1
178
+
179
+ - run_name: peft-lora-model
180
+
181
+ - disable_tqdm: False
182
+
183
+ - remove_unused_columns: True
184
+
185
+ - label_names: None
186
+
187
+ - load_best_model_at_end: False
188
+
189
+ - metric_for_best_model: None
190
+
191
+ - greater_is_better: None
192
+
193
+ - ignore_data_skip: False
194
+
195
+ - fsdp: []
196
+
197
+ - fsdp_min_num_params: 0
198
+
199
+ - fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
200
+
201
+ - fsdp_transformer_layer_cls_to_wrap: None
202
+
203
+ - accelerator_config: AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True)
204
+
205
+ - deepspeed: None
206
+
207
+ - label_smoothing_factor: 0.0
208
+
209
+ - optim: adamw_torch_fused
210
+
211
+ - optim_args: None
212
+
213
+ - adafactor: False
214
+
215
+ - group_by_length: False
216
+
217
+ - length_column_name: length
218
+
219
+ - report_to: ['tensorboard']
220
+
221
+ - ddp_find_unused_parameters: None
222
+
223
+ - ddp_bucket_cap_mb: None
224
+
225
+ - ddp_broadcast_buffers: None
226
+
227
+ - dataloader_pin_memory: True
228
+
229
+ - dataloader_persistent_workers: False
230
+
231
+ - skip_memory_metrics: True
232
+
233
+ - use_legacy_prediction_loop: False
234
+
235
+ - push_to_hub: False
236
+
237
+ - resume_from_checkpoint: None
238
+
239
+ - hub_model_id: None
240
+
241
+ - hub_strategy: every_save
242
+
243
+ - hub_token: None
244
+
245
+ - hub_private_repo: False
246
+
247
+ - hub_always_push: False
248
+
249
+ - gradient_checkpointing: True
250
+
251
+ - gradient_checkpointing_kwargs: {'use_reentrant': False}
252
+
253
+ - include_inputs_for_metrics: False
254
+
255
+ - fp16_backend: auto
256
+
257
+ - push_to_hub_model_id: None
258
+
259
+ - push_to_hub_organization: None
260
+
261
+ - push_to_hub_token: None
262
+
263
+ - mp_parameters:
264
+
265
+ - auto_find_batch_size: False
266
+
267
+ - full_determinism: False
268
+
269
+ - torchdynamo: None
270
+
271
+ - ray_scope: last
272
+
273
+ - ddp_timeout: 1800
274
+
275
+ - torch_compile: False
276
+
277
+ - torch_compile_backend: None
278
+
279
+ - torch_compile_mode: None
280
+
281
+ - dispatch_batches: None
282
+
283
+ - split_batches: None
284
+
285
+ - include_tokens_per_second: False
286
+
287
+ - include_num_input_tokens_seen: False
288
+
289
+ - neftune_noise_alpha: None
290
+
291
+ - distributed_state: Distributed environment: NO
292
+ Num processes: 1
293
+ Process index: 0
294
+ Local process index: 0
295
+ Device: cuda
296
+
297
+
298
+ - _n_gpu: 1
299
+
300
+ - __cached__setup_devices: cuda:0
301
+
302
+ - deepspeed_plugin: None
303
+
checkpoint-3749/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: google/gemma-2b
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-3749/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2b",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 8,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 256,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "o_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
checkpoint-3749/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4dff5f5739a22609780f6256bdec4c7a30fa5e53cff194b27f38d214ca48460
3
+ size 627607208
checkpoint-3749/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6ad0ae7d8dd82e7b06383e1498aa397946ec4c79063f1e24eb453f807f3131
3
+ size 1255362234
checkpoint-3749/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f356f9214bda56da16f0591c90def82a5e9a821de831bf8bd2cf977581605a46
3
+ size 14244
checkpoint-3749/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf79e87b7bc60d4db7206dfaed011f213a4b9fad391b75707212de5af9b0e65
3
+ size 1064
checkpoint-3749/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-3749/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
checkpoint-3749/tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
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
+ "106": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
checkpoint-3749/trainer_state.json ADDED
@@ -0,0 +1,2639 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997999866657777,
5
+ "eval_steps": 500,
6
+ "global_step": 3749,
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": 1.3359375,
14
+ "learning_rate": 5.333333333333335e-07,
15
+ "loss": 2.017,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 1.734375,
21
+ "learning_rate": 1.066666666666667e-06,
22
+ "loss": 2.3713,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 1.234375,
28
+ "learning_rate": 1.6000000000000001e-06,
29
+ "loss": 2.1764,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.01,
34
+ "grad_norm": 0.90234375,
35
+ "learning_rate": 2.133333333333334e-06,
36
+ "loss": 2.1757,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 1.4453125,
42
+ "learning_rate": 2.666666666666667e-06,
43
+ "loss": 2.1736,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "grad_norm": 1.125,
49
+ "learning_rate": 3.2000000000000003e-06,
50
+ "loss": 2.1865,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "grad_norm": 1.1328125,
56
+ "learning_rate": 3.7333333333333337e-06,
57
+ "loss": 2.0263,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.02,
62
+ "grad_norm": 1.015625,
63
+ "learning_rate": 4.266666666666668e-06,
64
+ "loss": 1.9312,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "grad_norm": 2.171875,
70
+ "learning_rate": 4.800000000000001e-06,
71
+ "loss": 1.8754,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.03,
76
+ "grad_norm": 0.70703125,
77
+ "learning_rate": 5.333333333333334e-06,
78
+ "loss": 1.7123,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.03,
83
+ "grad_norm": 0.90625,
84
+ "learning_rate": 5.8666666666666675e-06,
85
+ "loss": 1.8266,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "grad_norm": 0.97265625,
91
+ "learning_rate": 6.4000000000000006e-06,
92
+ "loss": 1.6079,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.03,
97
+ "grad_norm": 0.7578125,
98
+ "learning_rate": 6.9333333333333344e-06,
99
+ "loss": 1.5006,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.04,
104
+ "grad_norm": 0.3359375,
105
+ "learning_rate": 7.4666666666666675e-06,
106
+ "loss": 1.4158,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.04,
111
+ "grad_norm": 0.068359375,
112
+ "learning_rate": 8.000000000000001e-06,
113
+ "loss": 1.3677,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.04,
118
+ "grad_norm": 0.384765625,
119
+ "learning_rate": 8.533333333333335e-06,
120
+ "loss": 1.374,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.05,
125
+ "grad_norm": 0.296875,
126
+ "learning_rate": 9.066666666666667e-06,
127
+ "loss": 1.3052,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.05,
132
+ "grad_norm": 0.0927734375,
133
+ "learning_rate": 9.600000000000001e-06,
134
+ "loss": 1.275,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "grad_norm": 0.10498046875,
140
+ "learning_rate": 1.0133333333333335e-05,
141
+ "loss": 1.2574,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.05,
146
+ "grad_norm": 0.09765625,
147
+ "learning_rate": 1.0666666666666667e-05,
148
+ "loss": 1.2239,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.06,
153
+ "grad_norm": 0.2109375,
154
+ "learning_rate": 1.1200000000000001e-05,
155
+ "loss": 1.1565,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.06,
160
+ "grad_norm": 0.392578125,
161
+ "learning_rate": 1.1733333333333335e-05,
162
+ "loss": 1.1758,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.06,
167
+ "grad_norm": 0.138671875,
168
+ "learning_rate": 1.2266666666666667e-05,
169
+ "loss": 1.1843,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.06,
174
+ "grad_norm": 0.22265625,
175
+ "learning_rate": 1.2800000000000001e-05,
176
+ "loss": 1.1936,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "grad_norm": 0.07861328125,
182
+ "learning_rate": 1.3333333333333333e-05,
183
+ "loss": 1.1426,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.07,
188
+ "grad_norm": 0.051513671875,
189
+ "learning_rate": 1.3866666666666669e-05,
190
+ "loss": 1.114,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.07,
195
+ "grad_norm": 0.08154296875,
196
+ "learning_rate": 1.4400000000000001e-05,
197
+ "loss": 1.1195,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.07,
202
+ "grad_norm": 0.043701171875,
203
+ "learning_rate": 1.4933333333333335e-05,
204
+ "loss": 1.1256,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.08,
209
+ "grad_norm": 0.041015625,
210
+ "learning_rate": 1.546666666666667e-05,
211
+ "loss": 1.102,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.08,
216
+ "grad_norm": 0.1103515625,
217
+ "learning_rate": 1.6000000000000003e-05,
218
+ "loss": 1.0762,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.08,
223
+ "grad_norm": 0.0419921875,
224
+ "learning_rate": 1.6533333333333333e-05,
225
+ "loss": 1.0761,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.09,
230
+ "grad_norm": 0.09765625,
231
+ "learning_rate": 1.706666666666667e-05,
232
+ "loss": 1.0501,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.09,
237
+ "grad_norm": 0.041015625,
238
+ "learning_rate": 1.76e-05,
239
+ "loss": 1.0105,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.09,
244
+ "grad_norm": 0.10302734375,
245
+ "learning_rate": 1.8133333333333335e-05,
246
+ "loss": 1.0232,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.09,
251
+ "grad_norm": 0.035888671875,
252
+ "learning_rate": 1.866666666666667e-05,
253
+ "loss": 0.989,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.1,
258
+ "grad_norm": 0.034423828125,
259
+ "learning_rate": 1.9200000000000003e-05,
260
+ "loss": 0.9894,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.1,
265
+ "grad_norm": 0.0830078125,
266
+ "learning_rate": 1.9733333333333336e-05,
267
+ "loss": 0.9824,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.1,
272
+ "grad_norm": 0.0439453125,
273
+ "learning_rate": 1.999989162756852e-05,
274
+ "loss": 0.9569,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.1,
279
+ "grad_norm": 0.034912109375,
280
+ "learning_rate": 1.999902466221011e-05,
281
+ "loss": 0.928,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.11,
286
+ "grad_norm": 0.061767578125,
287
+ "learning_rate": 1.9997290806656996e-05,
288
+ "loss": 0.9349,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.11,
293
+ "grad_norm": 0.03369140625,
294
+ "learning_rate": 1.9994690211230084e-05,
295
+ "loss": 0.9489,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.11,
300
+ "grad_norm": 0.0289306640625,
301
+ "learning_rate": 1.999122310139442e-05,
302
+ "loss": 0.916,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.11,
307
+ "grad_norm": 0.034912109375,
308
+ "learning_rate": 1.9986889777739686e-05,
309
+ "loss": 0.9541,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.12,
314
+ "grad_norm": 0.02978515625,
315
+ "learning_rate": 1.9981690615954097e-05,
316
+ "loss": 0.9155,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.12,
321
+ "grad_norm": 0.0263671875,
322
+ "learning_rate": 1.9975626066791855e-05,
323
+ "loss": 0.9015,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.12,
328
+ "grad_norm": 0.0269775390625,
329
+ "learning_rate": 1.996869665603406e-05,
330
+ "loss": 0.9115,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.13,
335
+ "grad_norm": 0.047119140625,
336
+ "learning_rate": 1.996090298444313e-05,
337
+ "loss": 0.896,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.13,
342
+ "grad_norm": 0.0291748046875,
343
+ "learning_rate": 1.9952245727710723e-05,
344
+ "loss": 0.8855,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.13,
349
+ "grad_norm": 0.193359375,
350
+ "learning_rate": 1.9942725636399136e-05,
351
+ "loss": 0.9084,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.13,
356
+ "grad_norm": 0.02783203125,
357
+ "learning_rate": 1.9932343535876255e-05,
358
+ "loss": 0.8899,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.14,
363
+ "grad_norm": 0.392578125,
364
+ "learning_rate": 1.9921100326243977e-05,
365
+ "loss": 0.8952,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.14,
370
+ "grad_norm": 0.038330078125,
371
+ "learning_rate": 1.9908996982260196e-05,
372
+ "loss": 0.8857,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.14,
377
+ "grad_norm": 0.09521484375,
378
+ "learning_rate": 1.9896034553254284e-05,
379
+ "loss": 0.8677,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.14,
384
+ "grad_norm": 0.03076171875,
385
+ "learning_rate": 1.988221416303611e-05,
386
+ "loss": 0.8637,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.15,
391
+ "grad_norm": 0.041748046875,
392
+ "learning_rate": 1.986753700979861e-05,
393
+ "loss": 0.8384,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.15,
398
+ "grad_norm": 0.026611328125,
399
+ "learning_rate": 1.985200436601392e-05,
400
+ "loss": 0.9015,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.15,
405
+ "grad_norm": 0.05419921875,
406
+ "learning_rate": 1.9835617578323038e-05,
407
+ "loss": 0.8564,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.15,
412
+ "grad_norm": 0.0281982421875,
413
+ "learning_rate": 1.9818378067419092e-05,
414
+ "loss": 0.8183,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.16,
419
+ "grad_norm": 0.0252685546875,
420
+ "learning_rate": 1.9800287327924152e-05,
421
+ "loss": 0.8358,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.16,
426
+ "grad_norm": 0.059814453125,
427
+ "learning_rate": 1.9781346928259662e-05,
428
+ "loss": 0.8564,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.16,
433
+ "grad_norm": 0.0235595703125,
434
+ "learning_rate": 1.9761558510510453e-05,
435
+ "loss": 0.8295,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.17,
440
+ "grad_norm": 0.0255126953125,
441
+ "learning_rate": 1.974092379028239e-05,
442
+ "loss": 0.8403,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.17,
447
+ "grad_norm": 0.064453125,
448
+ "learning_rate": 1.9719444556553616e-05,
449
+ "loss": 0.8582,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.17,
454
+ "grad_norm": 0.0267333984375,
455
+ "learning_rate": 1.969712267151948e-05,
456
+ "loss": 0.8328,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.17,
461
+ "grad_norm": 0.03564453125,
462
+ "learning_rate": 1.9673960070431043e-05,
463
+ "loss": 0.8571,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.18,
468
+ "grad_norm": 0.031494140625,
469
+ "learning_rate": 1.9649958761427364e-05,
470
+ "loss": 0.824,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.18,
475
+ "grad_norm": 0.026123046875,
476
+ "learning_rate": 1.9625120825361326e-05,
477
+ "loss": 0.8418,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.18,
482
+ "grad_norm": 0.0247802734375,
483
+ "learning_rate": 1.9599448415619283e-05,
484
+ "loss": 0.8267,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.18,
489
+ "grad_norm": 0.026123046875,
490
+ "learning_rate": 1.957294375793435e-05,
491
+ "loss": 0.8677,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.19,
496
+ "grad_norm": 0.031005859375,
497
+ "learning_rate": 1.954560915019343e-05,
498
+ "loss": 0.827,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.19,
503
+ "grad_norm": 0.031494140625,
504
+ "learning_rate": 1.951744696223801e-05,
505
+ "loss": 0.8303,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.19,
510
+ "grad_norm": 0.024169921875,
511
+ "learning_rate": 1.9488459635658687e-05,
512
+ "loss": 0.8455,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.19,
517
+ "grad_norm": 0.041259765625,
518
+ "learning_rate": 1.945864968358349e-05,
519
+ "loss": 0.8297,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.2,
524
+ "grad_norm": 0.026611328125,
525
+ "learning_rate": 1.9428019690460008e-05,
526
+ "loss": 0.8516,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.2,
531
+ "grad_norm": 0.0269775390625,
532
+ "learning_rate": 1.939657231183132e-05,
533
+ "loss": 0.8538,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.2,
538
+ "grad_norm": 0.037109375,
539
+ "learning_rate": 1.9364310274105758e-05,
540
+ "loss": 0.8045,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.21,
545
+ "grad_norm": 0.034423828125,
546
+ "learning_rate": 1.933123637432054e-05,
547
+ "loss": 0.8436,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.21,
552
+ "grad_norm": 0.023681640625,
553
+ "learning_rate": 1.929735347989929e-05,
554
+ "loss": 0.8123,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.21,
559
+ "grad_norm": 0.0238037109375,
560
+ "learning_rate": 1.92626645284034e-05,
561
+ "loss": 0.8184,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.21,
566
+ "grad_norm": 0.047119140625,
567
+ "learning_rate": 1.92271725272774e-05,
568
+ "loss": 0.8222,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.22,
573
+ "grad_norm": 0.0277099609375,
574
+ "learning_rate": 1.919088055358818e-05,
575
+ "loss": 0.8434,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.22,
580
+ "grad_norm": 0.224609375,
581
+ "learning_rate": 1.9153791753758236e-05,
582
+ "loss": 0.8413,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.22,
587
+ "grad_norm": 0.05517578125,
588
+ "learning_rate": 1.911590934329288e-05,
589
+ "loss": 0.8323,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.22,
594
+ "grad_norm": 0.1201171875,
595
+ "learning_rate": 1.9077236606501465e-05,
596
+ "loss": 0.7935,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.23,
601
+ "grad_norm": 0.022705078125,
602
+ "learning_rate": 1.903777689621263e-05,
603
+ "loss": 0.8186,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.23,
608
+ "grad_norm": 0.0242919921875,
609
+ "learning_rate": 1.899753363348364e-05,
610
+ "loss": 0.8094,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.23,
615
+ "grad_norm": 0.0267333984375,
616
+ "learning_rate": 1.895651030730378e-05,
617
+ "loss": 0.8265,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.23,
622
+ "grad_norm": 0.031494140625,
623
+ "learning_rate": 1.891471047429186e-05,
624
+ "loss": 0.9105,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.24,
629
+ "grad_norm": 0.030517578125,
630
+ "learning_rate": 1.8872137758387873e-05,
631
+ "loss": 0.8028,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.24,
636
+ "grad_norm": 0.0263671875,
637
+ "learning_rate": 1.8828795850538804e-05,
638
+ "loss": 0.8322,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.24,
643
+ "grad_norm": 0.0240478515625,
644
+ "learning_rate": 1.8784688508378655e-05,
645
+ "loss": 0.798,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.25,
650
+ "grad_norm": 0.0277099609375,
651
+ "learning_rate": 1.8739819555902626e-05,
652
+ "loss": 0.8202,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.25,
657
+ "grad_norm": 0.025146484375,
658
+ "learning_rate": 1.8694192883135632e-05,
659
+ "loss": 0.8819,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.25,
664
+ "grad_norm": 0.027587890625,
665
+ "learning_rate": 1.8647812445795003e-05,
666
+ "loss": 0.8273,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.25,
671
+ "grad_norm": 0.0291748046875,
672
+ "learning_rate": 1.8600682264947566e-05,
673
+ "loss": 0.8294,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.26,
678
+ "grad_norm": 0.033447265625,
679
+ "learning_rate": 1.8552806426661022e-05,
680
+ "loss": 0.8222,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.26,
685
+ "grad_norm": 0.185546875,
686
+ "learning_rate": 1.8504189081649678e-05,
687
+ "loss": 0.8109,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.26,
692
+ "grad_norm": 0.0284423828125,
693
+ "learning_rate": 1.8454834444914607e-05,
694
+ "loss": 0.7972,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.26,
699
+ "grad_norm": 0.0225830078125,
700
+ "learning_rate": 1.8404746795378218e-05,
701
+ "loss": 0.8107,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.27,
706
+ "grad_norm": 0.087890625,
707
+ "learning_rate": 1.8353930475513268e-05,
708
+ "loss": 0.8208,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.27,
713
+ "grad_norm": 0.0272216796875,
714
+ "learning_rate": 1.8302389890966404e-05,
715
+ "loss": 0.7933,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.27,
720
+ "grad_norm": 0.049072265625,
721
+ "learning_rate": 1.8250129510176183e-05,
722
+ "loss": 0.814,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.27,
727
+ "grad_norm": 0.0225830078125,
728
+ "learning_rate": 1.8197153863985686e-05,
729
+ "loss": 0.8251,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.28,
734
+ "grad_norm": 0.024658203125,
735
+ "learning_rate": 1.8143467545249694e-05,
736
+ "loss": 0.7962,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.28,
741
+ "grad_norm": 0.0263671875,
742
+ "learning_rate": 1.8089075208436507e-05,
743
+ "loss": 0.8164,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.28,
748
+ "grad_norm": 0.0223388671875,
749
+ "learning_rate": 1.8033981569224404e-05,
750
+ "loss": 0.8081,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.29,
755
+ "grad_norm": 0.026123046875,
756
+ "learning_rate": 1.797819140409282e-05,
757
+ "loss": 0.8211,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.29,
762
+ "grad_norm": 0.0252685546875,
763
+ "learning_rate": 1.7921709549908222e-05,
764
+ "loss": 0.8526,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.29,
769
+ "grad_norm": 0.030517578125,
770
+ "learning_rate": 1.7864540903504777e-05,
771
+ "loss": 0.8195,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.29,
776
+ "grad_norm": 0.0230712890625,
777
+ "learning_rate": 1.7806690421259794e-05,
778
+ "loss": 0.7951,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.3,
783
+ "grad_norm": 0.04443359375,
784
+ "learning_rate": 1.774816311866404e-05,
785
+ "loss": 0.8389,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.3,
790
+ "grad_norm": 0.023681640625,
791
+ "learning_rate": 1.768896406988689e-05,
792
+ "loss": 0.8031,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.3,
797
+ "grad_norm": 0.0281982421875,
798
+ "learning_rate": 1.7629098407336415e-05,
799
+ "loss": 0.8188,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.3,
804
+ "grad_norm": 0.0242919921875,
805
+ "learning_rate": 1.756857132121443e-05,
806
+ "loss": 0.8232,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.31,
811
+ "grad_norm": 0.043701171875,
812
+ "learning_rate": 1.7507388059066492e-05,
813
+ "loss": 0.8126,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.31,
818
+ "grad_norm": 0.06982421875,
819
+ "learning_rate": 1.7445553925326963e-05,
820
+ "loss": 0.7775,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.31,
825
+ "grad_norm": 0.049560546875,
826
+ "learning_rate": 1.7383074280859132e-05,
827
+ "loss": 0.8205,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.31,
832
+ "grad_norm": 0.0240478515625,
833
+ "learning_rate": 1.7319954542490448e-05,
834
+ "loss": 0.8158,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.32,
839
+ "grad_norm": 0.041259765625,
840
+ "learning_rate": 1.725620018254286e-05,
841
+ "loss": 0.8146,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.32,
846
+ "grad_norm": 0.271484375,
847
+ "learning_rate": 1.7191816728358435e-05,
848
+ "loss": 0.8259,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.32,
853
+ "grad_norm": 0.021240234375,
854
+ "learning_rate": 1.71268097618201e-05,
855
+ "loss": 0.8213,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.33,
860
+ "grad_norm": 0.02490234375,
861
+ "learning_rate": 1.706118491886774e-05,
862
+ "loss": 0.7947,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.33,
867
+ "grad_norm": 0.0296630859375,
868
+ "learning_rate": 1.6994947889009563e-05,
869
+ "loss": 0.8364,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.33,
874
+ "grad_norm": 0.0247802734375,
875
+ "learning_rate": 1.692810441482884e-05,
876
+ "loss": 0.8268,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.33,
881
+ "grad_norm": 0.0238037109375,
882
+ "learning_rate": 1.6860660291486023e-05,
883
+ "loss": 0.7868,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.34,
888
+ "grad_norm": 0.02392578125,
889
+ "learning_rate": 1.6792621366216338e-05,
890
+ "loss": 0.8402,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.34,
895
+ "grad_norm": 0.036865234375,
896
+ "learning_rate": 1.6723993537822837e-05,
897
+ "loss": 0.81,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.34,
902
+ "grad_norm": 0.06298828125,
903
+ "learning_rate": 1.6654782756164983e-05,
904
+ "loss": 0.8151,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.34,
909
+ "grad_norm": 0.0235595703125,
910
+ "learning_rate": 1.6584995021642814e-05,
911
+ "loss": 0.7716,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.35,
916
+ "grad_norm": 0.0252685546875,
917
+ "learning_rate": 1.651463638467673e-05,
918
+ "loss": 0.8236,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.35,
923
+ "grad_norm": 0.031005859375,
924
+ "learning_rate": 1.6443712945182933e-05,
925
+ "loss": 0.7794,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.35,
930
+ "grad_norm": 0.03955078125,
931
+ "learning_rate": 1.637223085204457e-05,
932
+ "loss": 0.8222,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.35,
937
+ "grad_norm": 0.049560546875,
938
+ "learning_rate": 1.630019630257865e-05,
939
+ "loss": 0.8134,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.36,
944
+ "grad_norm": 0.0244140625,
945
+ "learning_rate": 1.6227615541998756e-05,
946
+ "loss": 0.8209,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.36,
951
+ "grad_norm": 0.0301513671875,
952
+ "learning_rate": 1.6154494862873588e-05,
953
+ "loss": 0.79,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.36,
958
+ "grad_norm": 0.0240478515625,
959
+ "learning_rate": 1.6080840604581435e-05,
960
+ "loss": 0.812,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.37,
965
+ "grad_norm": 0.0260009765625,
966
+ "learning_rate": 1.600665915276054e-05,
967
+ "loss": 0.8119,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.37,
972
+ "grad_norm": 0.0732421875,
973
+ "learning_rate": 1.5931956938755494e-05,
974
+ "loss": 0.8073,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.37,
979
+ "grad_norm": 0.0220947265625,
980
+ "learning_rate": 1.585674043905966e-05,
981
+ "loss": 0.8205,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.37,
986
+ "grad_norm": 0.0255126953125,
987
+ "learning_rate": 1.5781016174753675e-05,
988
+ "loss": 0.8222,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.38,
993
+ "grad_norm": 0.0302734375,
994
+ "learning_rate": 1.5704790710940074e-05,
995
+ "loss": 0.8307,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.38,
1000
+ "grad_norm": 0.028076171875,
1001
+ "learning_rate": 1.5628070656174135e-05,
1002
+ "loss": 0.8038,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.38,
1007
+ "grad_norm": 0.0233154296875,
1008
+ "learning_rate": 1.5550862661890918e-05,
1009
+ "loss": 0.7824,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.38,
1014
+ "grad_norm": 0.0252685546875,
1015
+ "learning_rate": 1.547317342182861e-05,
1016
+ "loss": 0.7891,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.39,
1021
+ "grad_norm": 0.058837890625,
1022
+ "learning_rate": 1.5395009671448186e-05,
1023
+ "loss": 0.8051,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.39,
1028
+ "grad_norm": 0.0284423828125,
1029
+ "learning_rate": 1.5316378187349476e-05,
1030
+ "loss": 0.7899,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.39,
1035
+ "grad_norm": 0.02734375,
1036
+ "learning_rate": 1.5237285786683638e-05,
1037
+ "loss": 0.827,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.39,
1042
+ "grad_norm": 0.034912109375,
1043
+ "learning_rate": 1.515773932656213e-05,
1044
+ "loss": 0.8107,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.4,
1049
+ "grad_norm": 0.0213623046875,
1050
+ "learning_rate": 1.5077745703462228e-05,
1051
+ "loss": 0.7785,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.4,
1056
+ "grad_norm": 0.0274658203125,
1057
+ "learning_rate": 1.4997311852629097e-05,
1058
+ "loss": 0.8053,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.4,
1063
+ "grad_norm": 0.029296875,
1064
+ "learning_rate": 1.4916444747474542e-05,
1065
+ "loss": 0.8034,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.41,
1070
+ "grad_norm": 0.023681640625,
1071
+ "learning_rate": 1.4835151398972424e-05,
1072
+ "loss": 0.8117,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.41,
1077
+ "grad_norm": 0.0303955078125,
1078
+ "learning_rate": 1.475343885505083e-05,
1079
+ "loss": 0.7811,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.41,
1084
+ "grad_norm": 0.166015625,
1085
+ "learning_rate": 1.4671314199981019e-05,
1086
+ "loss": 0.8069,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.41,
1091
+ "grad_norm": 0.024658203125,
1092
+ "learning_rate": 1.4588784553763262e-05,
1093
+ "loss": 0.8312,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.42,
1098
+ "grad_norm": 0.035888671875,
1099
+ "learning_rate": 1.4505857071509523e-05,
1100
+ "loss": 0.8132,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.42,
1105
+ "grad_norm": 0.04736328125,
1106
+ "learning_rate": 1.4422538942823158e-05,
1107
+ "loss": 0.812,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.42,
1112
+ "grad_norm": 0.024658203125,
1113
+ "learning_rate": 1.4338837391175582e-05,
1114
+ "loss": 0.822,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.42,
1119
+ "grad_norm": 0.025146484375,
1120
+ "learning_rate": 1.425475967328001e-05,
1121
+ "loss": 0.8269,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.43,
1126
+ "grad_norm": 0.046630859375,
1127
+ "learning_rate": 1.4170313078462318e-05,
1128
+ "loss": 0.8027,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.43,
1133
+ "grad_norm": 0.115234375,
1134
+ "learning_rate": 1.4085504928029086e-05,
1135
+ "loss": 0.8123,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.43,
1140
+ "grad_norm": 0.0269775390625,
1141
+ "learning_rate": 1.4000342574632846e-05,
1142
+ "loss": 0.8028,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.43,
1147
+ "grad_norm": 0.0284423828125,
1148
+ "learning_rate": 1.3914833401634642e-05,
1149
+ "loss": 0.7812,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.44,
1154
+ "grad_norm": 0.036865234375,
1155
+ "learning_rate": 1.3828984822463895e-05,
1156
+ "loss": 0.8294,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.44,
1161
+ "grad_norm": 0.03369140625,
1162
+ "learning_rate": 1.3742804279975686e-05,
1163
+ "loss": 0.8118,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.44,
1168
+ "grad_norm": 0.0235595703125,
1169
+ "learning_rate": 1.3656299245805476e-05,
1170
+ "loss": 0.8086,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.45,
1175
+ "grad_norm": 0.03955078125,
1176
+ "learning_rate": 1.3569477219721336e-05,
1177
+ "loss": 0.8155,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.45,
1182
+ "grad_norm": 0.0262451171875,
1183
+ "learning_rate": 1.3482345728973742e-05,
1184
+ "loss": 0.8394,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.45,
1189
+ "grad_norm": 0.0252685546875,
1190
+ "learning_rate": 1.3394912327642966e-05,
1191
+ "loss": 0.8172,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.45,
1196
+ "grad_norm": 0.0291748046875,
1197
+ "learning_rate": 1.330718459598417e-05,
1198
+ "loss": 0.7993,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.46,
1203
+ "grad_norm": 0.0311279296875,
1204
+ "learning_rate": 1.3219170139770213e-05,
1205
+ "loss": 0.7824,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.46,
1210
+ "grad_norm": 0.0380859375,
1211
+ "learning_rate": 1.3130876589632243e-05,
1212
+ "loss": 0.7982,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.46,
1217
+ "grad_norm": 0.037109375,
1218
+ "learning_rate": 1.3042311600398157e-05,
1219
+ "loss": 0.8093,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.46,
1224
+ "grad_norm": 0.03271484375,
1225
+ "learning_rate": 1.2953482850428927e-05,
1226
+ "loss": 0.7864,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.47,
1231
+ "grad_norm": 0.0225830078125,
1232
+ "learning_rate": 1.2864398040952921e-05,
1233
+ "loss": 0.778,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.47,
1238
+ "grad_norm": 0.025634765625,
1239
+ "learning_rate": 1.2775064895398217e-05,
1240
+ "loss": 0.7869,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.47,
1245
+ "grad_norm": 0.0274658203125,
1246
+ "learning_rate": 1.2685491158723003e-05,
1247
+ "loss": 0.8012,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.47,
1252
+ "grad_norm": 0.0289306640625,
1253
+ "learning_rate": 1.2595684596744112e-05,
1254
+ "loss": 0.8385,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.48,
1259
+ "grad_norm": 0.045166015625,
1260
+ "learning_rate": 1.250565299546374e-05,
1261
+ "loss": 0.8062,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.48,
1266
+ "grad_norm": 0.025146484375,
1267
+ "learning_rate": 1.2415404160394429e-05,
1268
+ "loss": 0.8076,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.48,
1273
+ "grad_norm": 0.0240478515625,
1274
+ "learning_rate": 1.2324945915882334e-05,
1275
+ "loss": 0.7864,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.49,
1280
+ "grad_norm": 0.03125,
1281
+ "learning_rate": 1.2234286104428884e-05,
1282
+ "loss": 0.833,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.49,
1287
+ "grad_norm": 0.07275390625,
1288
+ "learning_rate": 1.2143432586010851e-05,
1289
+ "loss": 0.7848,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.49,
1294
+ "grad_norm": 0.037109375,
1295
+ "learning_rate": 1.2052393237398916e-05,
1296
+ "loss": 0.7838,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.49,
1301
+ "grad_norm": 0.0771484375,
1302
+ "learning_rate": 1.1961175951474766e-05,
1303
+ "loss": 0.808,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.5,
1308
+ "grad_norm": 0.0238037109375,
1309
+ "learning_rate": 1.1869788636546801e-05,
1310
+ "loss": 0.8076,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.5,
1315
+ "grad_norm": 0.028076171875,
1316
+ "learning_rate": 1.1778239215664512e-05,
1317
+ "loss": 0.8196,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.5,
1322
+ "grad_norm": 0.0322265625,
1323
+ "learning_rate": 1.1686535625931566e-05,
1324
+ "loss": 0.7873,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.5,
1329
+ "grad_norm": 0.046630859375,
1330
+ "learning_rate": 1.1594685817817673e-05,
1331
+ "loss": 0.8126,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.51,
1336
+ "grad_norm": 0.02490234375,
1337
+ "learning_rate": 1.1502697754469315e-05,
1338
+ "loss": 0.8462,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.51,
1343
+ "grad_norm": 0.029296875,
1344
+ "learning_rate": 1.141057941101935e-05,
1345
+ "loss": 0.8273,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.51,
1350
+ "grad_norm": 0.02294921875,
1351
+ "learning_rate": 1.1318338773895596e-05,
1352
+ "loss": 0.8222,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.51,
1357
+ "grad_norm": 0.026611328125,
1358
+ "learning_rate": 1.1225983840128418e-05,
1359
+ "loss": 0.7724,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.52,
1364
+ "grad_norm": 0.0400390625,
1365
+ "learning_rate": 1.1133522616657417e-05,
1366
+ "loss": 0.8072,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.52,
1371
+ "grad_norm": 0.0286865234375,
1372
+ "learning_rate": 1.104096311963724e-05,
1373
+ "loss": 0.8306,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.52,
1378
+ "grad_norm": 0.026611328125,
1379
+ "learning_rate": 1.0948313373742606e-05,
1380
+ "loss": 0.7973,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.53,
1385
+ "grad_norm": 0.037841796875,
1386
+ "learning_rate": 1.0855581411472576e-05,
1387
+ "loss": 0.8385,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.53,
1392
+ "grad_norm": 0.02197265625,
1393
+ "learning_rate": 1.076277527245417e-05,
1394
+ "loss": 0.8238,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.53,
1399
+ "grad_norm": 0.0284423828125,
1400
+ "learning_rate": 1.0669903002745343e-05,
1401
+ "loss": 0.8102,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.53,
1406
+ "grad_norm": 0.1826171875,
1407
+ "learning_rate": 1.0576972654137411e-05,
1408
+ "loss": 0.8189,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.54,
1413
+ "grad_norm": 0.0247802734375,
1414
+ "learning_rate": 1.0483992283456992e-05,
1415
+ "loss": 0.7938,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 0.54,
1420
+ "grad_norm": 0.0218505859375,
1421
+ "learning_rate": 1.0390969951867482e-05,
1422
+ "loss": 0.8171,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 0.54,
1427
+ "grad_norm": 0.0311279296875,
1428
+ "learning_rate": 1.0297913724170187e-05,
1429
+ "loss": 0.8082,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 0.54,
1434
+ "grad_norm": 0.0238037109375,
1435
+ "learning_rate": 1.0204831668105117e-05,
1436
+ "loss": 0.7972,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 0.55,
1441
+ "grad_norm": 0.0218505859375,
1442
+ "learning_rate": 1.011173185365154e-05,
1443
+ "loss": 0.7743,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 0.55,
1448
+ "grad_norm": 0.03515625,
1449
+ "learning_rate": 1.0018622352328331e-05,
1450
+ "loss": 0.8095,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 0.55,
1455
+ "grad_norm": 0.03564453125,
1456
+ "learning_rate": 9.92551123649419e-06,
1457
+ "loss": 0.796,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 0.55,
1462
+ "grad_norm": 0.02197265625,
1463
+ "learning_rate": 9.832406578647789e-06,
1464
+ "loss": 0.7923,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 0.56,
1469
+ "grad_norm": 0.0230712890625,
1470
+ "learning_rate": 9.739316450727914e-06,
1471
+ "loss": 0.8106,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 0.56,
1476
+ "grad_norm": 0.0244140625,
1477
+ "learning_rate": 9.646248923413639e-06,
1478
+ "loss": 0.7871,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 0.56,
1483
+ "grad_norm": 0.027099609375,
1484
+ "learning_rate": 9.553212065424625e-06,
1485
+ "loss": 0.798,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 0.57,
1490
+ "grad_norm": 0.0341796875,
1491
+ "learning_rate": 9.460213942821578e-06,
1492
+ "loss": 0.795,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 0.57,
1497
+ "grad_norm": 0.023681640625,
1498
+ "learning_rate": 9.367262618306947e-06,
1499
+ "loss": 0.8001,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 0.57,
1504
+ "grad_norm": 0.02294921875,
1505
+ "learning_rate": 9.274366150525902e-06,
1506
+ "loss": 0.766,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 0.57,
1511
+ "grad_norm": 0.02587890625,
1512
+ "learning_rate": 9.181532593367675e-06,
1513
+ "loss": 0.7999,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 0.58,
1518
+ "grad_norm": 0.0224609375,
1519
+ "learning_rate": 9.0887699952673e-06,
1520
+ "loss": 0.813,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 0.58,
1525
+ "grad_norm": 0.035400390625,
1526
+ "learning_rate": 8.996086398507848e-06,
1527
+ "loss": 0.8108,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 0.58,
1532
+ "grad_norm": 0.0267333984375,
1533
+ "learning_rate": 8.903489838523167e-06,
1534
+ "loss": 0.841,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 0.58,
1539
+ "grad_norm": 0.02783203125,
1540
+ "learning_rate": 8.81098834320124e-06,
1541
+ "loss": 0.8204,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 0.59,
1546
+ "grad_norm": 0.03759765625,
1547
+ "learning_rate": 8.71858993218818e-06,
1548
+ "loss": 0.7937,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 0.59,
1553
+ "grad_norm": 0.04931640625,
1554
+ "learning_rate": 8.626302616192955e-06,
1555
+ "loss": 0.799,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 0.59,
1560
+ "grad_norm": 0.025634765625,
1561
+ "learning_rate": 8.534134396292875e-06,
1562
+ "loss": 0.8033,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 0.59,
1567
+ "grad_norm": 0.0277099609375,
1568
+ "learning_rate": 8.442093263239913e-06,
1569
+ "loss": 0.8089,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 0.6,
1574
+ "grad_norm": 0.0228271484375,
1575
+ "learning_rate": 8.350187196767942e-06,
1576
+ "loss": 0.792,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 0.6,
1581
+ "grad_norm": 0.047607421875,
1582
+ "learning_rate": 8.258424164900899e-06,
1583
+ "loss": 0.8242,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 0.6,
1588
+ "grad_norm": 0.0250244140625,
1589
+ "learning_rate": 8.166812123261982e-06,
1590
+ "loss": 0.8058,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 0.61,
1595
+ "grad_norm": 0.0283203125,
1596
+ "learning_rate": 8.075359014383914e-06,
1597
+ "loss": 0.8084,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 0.61,
1602
+ "grad_norm": 0.0228271484375,
1603
+ "learning_rate": 7.984072767020359e-06,
1604
+ "loss": 0.7894,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 0.61,
1609
+ "grad_norm": 0.0419921875,
1610
+ "learning_rate": 7.892961295458496e-06,
1611
+ "loss": 0.7993,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 0.61,
1616
+ "grad_norm": 0.0260009765625,
1617
+ "learning_rate": 7.802032498832895e-06,
1618
+ "loss": 0.8036,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 0.62,
1623
+ "grad_norm": 0.0235595703125,
1624
+ "learning_rate": 7.71129426044066e-06,
1625
+ "loss": 0.7973,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 0.62,
1630
+ "grad_norm": 0.0242919921875,
1631
+ "learning_rate": 7.620754447057985e-06,
1632
+ "loss": 0.7964,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 0.62,
1637
+ "grad_norm": 0.036376953125,
1638
+ "learning_rate": 7.530420908258111e-06,
1639
+ "loss": 0.777,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 0.62,
1644
+ "grad_norm": 0.029541015625,
1645
+ "learning_rate": 7.4403014757308e-06,
1646
+ "loss": 0.8116,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 0.63,
1651
+ "grad_norm": 0.0263671875,
1652
+ "learning_rate": 7.350403962603335e-06,
1653
+ "loss": 0.8267,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 0.63,
1658
+ "grad_norm": 0.031982421875,
1659
+ "learning_rate": 7.260736162763149e-06,
1660
+ "loss": 0.8153,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 0.63,
1665
+ "grad_norm": 0.1923828125,
1666
+ "learning_rate": 7.171305850182113e-06,
1667
+ "loss": 0.8026,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 0.63,
1672
+ "grad_norm": 0.03466796875,
1673
+ "learning_rate": 7.082120778242554e-06,
1674
+ "loss": 0.8198,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 0.64,
1679
+ "grad_norm": 0.034423828125,
1680
+ "learning_rate": 6.993188679065048e-06,
1681
+ "loss": 0.7804,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 0.64,
1686
+ "grad_norm": 0.0245361328125,
1687
+ "learning_rate": 6.904517262838082e-06,
1688
+ "loss": 0.8251,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 0.64,
1693
+ "grad_norm": 0.047607421875,
1694
+ "learning_rate": 6.8161142171495785e-06,
1695
+ "loss": 0.849,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 0.65,
1700
+ "grad_norm": 0.02880859375,
1701
+ "learning_rate": 6.72798720632042e-06,
1702
+ "loss": 0.7912,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 0.65,
1707
+ "grad_norm": 0.0245361328125,
1708
+ "learning_rate": 6.640143870739956e-06,
1709
+ "loss": 0.7864,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 0.65,
1714
+ "grad_norm": 0.02392578125,
1715
+ "learning_rate": 6.552591826203616e-06,
1716
+ "loss": 0.7713,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 0.65,
1721
+ "grad_norm": 0.023681640625,
1722
+ "learning_rate": 6.4653386632526275e-06,
1723
+ "loss": 0.7925,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 0.66,
1728
+ "grad_norm": 0.045166015625,
1729
+ "learning_rate": 6.378391946515937e-06,
1730
+ "loss": 0.8402,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 0.66,
1735
+ "grad_norm": 0.023681640625,
1736
+ "learning_rate": 6.291759214054383e-06,
1737
+ "loss": 0.8032,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 0.66,
1742
+ "grad_norm": 0.0238037109375,
1743
+ "learning_rate": 6.205447976707154e-06,
1744
+ "loss": 0.7891,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 0.66,
1749
+ "grad_norm": 0.08935546875,
1750
+ "learning_rate": 6.119465717440629e-06,
1751
+ "loss": 0.819,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 0.67,
1756
+ "grad_norm": 0.0283203125,
1757
+ "learning_rate": 6.033819890699616e-06,
1758
+ "loss": 0.8318,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 0.67,
1763
+ "grad_norm": 0.0240478515625,
1764
+ "learning_rate": 5.94851792176107e-06,
1765
+ "loss": 0.8241,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 0.67,
1770
+ "grad_norm": 0.0311279296875,
1771
+ "learning_rate": 5.863567206090348e-06,
1772
+ "loss": 0.7844,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 0.67,
1777
+ "grad_norm": 0.025634765625,
1778
+ "learning_rate": 5.778975108700031e-06,
1779
+ "loss": 0.8273,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 0.68,
1784
+ "grad_norm": 0.03759765625,
1785
+ "learning_rate": 5.694748963511396e-06,
1786
+ "loss": 0.8117,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 0.68,
1791
+ "grad_norm": 0.0238037109375,
1792
+ "learning_rate": 5.610896072718603e-06,
1793
+ "loss": 0.8067,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 0.68,
1798
+ "grad_norm": 0.0213623046875,
1799
+ "learning_rate": 5.527423706155586e-06,
1800
+ "loss": 0.7988,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 0.69,
1805
+ "grad_norm": 0.0230712890625,
1806
+ "learning_rate": 5.4443391006657896e-06,
1807
+ "loss": 0.8286,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 0.69,
1812
+ "grad_norm": 0.033447265625,
1813
+ "learning_rate": 5.361649459474756e-06,
1814
+ "loss": 0.8054,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 0.69,
1819
+ "grad_norm": 0.0233154296875,
1820
+ "learning_rate": 5.279361951565618e-06,
1821
+ "loss": 0.7801,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 0.69,
1826
+ "grad_norm": 0.027587890625,
1827
+ "learning_rate": 5.197483711057569e-06,
1828
+ "loss": 0.8107,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 0.7,
1833
+ "grad_norm": 0.0247802734375,
1834
+ "learning_rate": 5.116021836587353e-06,
1835
+ "loss": 0.8273,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 0.7,
1840
+ "grad_norm": 0.0235595703125,
1841
+ "learning_rate": 5.0349833906938235e-06,
1842
+ "loss": 0.7919,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 0.7,
1847
+ "grad_norm": 0.0240478515625,
1848
+ "learning_rate": 4.954375399205655e-06,
1849
+ "loss": 0.8371,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 0.7,
1854
+ "grad_norm": 0.0257568359375,
1855
+ "learning_rate": 4.8742048506322045e-06,
1856
+ "loss": 0.7882,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 0.71,
1861
+ "grad_norm": 0.027099609375,
1862
+ "learning_rate": 4.794478695557631e-06,
1863
+ "loss": 0.8149,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 0.71,
1868
+ "grad_norm": 0.02685546875,
1869
+ "learning_rate": 4.715203846038312e-06,
1870
+ "loss": 0.8254,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 0.71,
1875
+ "grad_norm": 0.08447265625,
1876
+ "learning_rate": 4.636387175003558e-06,
1877
+ "loss": 0.8249,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 0.71,
1882
+ "grad_norm": 0.0264892578125,
1883
+ "learning_rate": 4.558035515659768e-06,
1884
+ "loss": 0.8004,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 0.72,
1889
+ "grad_norm": 0.0230712890625,
1890
+ "learning_rate": 4.480155660898001e-06,
1891
+ "loss": 0.7959,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 0.72,
1896
+ "grad_norm": 0.0341796875,
1897
+ "learning_rate": 4.402754362705051e-06,
1898
+ "loss": 0.786,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 0.72,
1903
+ "grad_norm": 0.033203125,
1904
+ "learning_rate": 4.325838331578061e-06,
1905
+ "loss": 0.7948,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 0.73,
1910
+ "grad_norm": 0.0269775390625,
1911
+ "learning_rate": 4.249414235942755e-06,
1912
+ "loss": 0.7959,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 0.73,
1917
+ "grad_norm": 0.045654296875,
1918
+ "learning_rate": 4.173488701575274e-06,
1919
+ "loss": 0.775,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 0.73,
1924
+ "grad_norm": 0.0341796875,
1925
+ "learning_rate": 4.098068311027772e-06,
1926
+ "loss": 0.7992,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 0.73,
1931
+ "grad_norm": 0.02783203125,
1932
+ "learning_rate": 4.023159603057698e-06,
1933
+ "loss": 0.8045,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 0.74,
1938
+ "grad_norm": 0.0244140625,
1939
+ "learning_rate": 3.948769072060927e-06,
1940
+ "loss": 0.7903,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 0.74,
1945
+ "grad_norm": 0.0458984375,
1946
+ "learning_rate": 3.874903167508688e-06,
1947
+ "loss": 0.7974,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 0.74,
1952
+ "grad_norm": 0.026123046875,
1953
+ "learning_rate": 3.801568293388421e-06,
1954
+ "loss": 0.7766,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 0.74,
1959
+ "grad_norm": 0.0400390625,
1960
+ "learning_rate": 3.728770807648574e-06,
1961
+ "loss": 0.8202,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 0.75,
1966
+ "grad_norm": 0.0250244140625,
1967
+ "learning_rate": 3.6565170216473744e-06,
1968
+ "loss": 0.8047,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 0.75,
1973
+ "grad_norm": 0.04931640625,
1974
+ "learning_rate": 3.584813199605658e-06,
1975
+ "loss": 0.8324,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 0.75,
1980
+ "grad_norm": 0.0255126953125,
1981
+ "learning_rate": 3.513665558063771e-06,
1982
+ "loss": 0.8203,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 0.75,
1987
+ "grad_norm": 0.034912109375,
1988
+ "learning_rate": 3.4430802653426176e-06,
1989
+ "loss": 0.7997,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 0.76,
1994
+ "grad_norm": 0.06298828125,
1995
+ "learning_rate": 3.373063441008877e-06,
1996
+ "loss": 0.7783,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 0.76,
2001
+ "grad_norm": 0.03857421875,
2002
+ "learning_rate": 3.303621155344453e-06,
2003
+ "loss": 0.8088,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 0.76,
2008
+ "grad_norm": 0.0250244140625,
2009
+ "learning_rate": 3.234759428820198e-06,
2010
+ "loss": 0.8231,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 0.77,
2015
+ "grad_norm": 0.0235595703125,
2016
+ "learning_rate": 3.1664842315739586e-06,
2017
+ "loss": 0.8005,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 0.77,
2022
+ "grad_norm": 0.03076171875,
2023
+ "learning_rate": 3.098801482892966e-06,
2024
+ "loss": 0.7926,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 0.77,
2029
+ "grad_norm": 0.11962890625,
2030
+ "learning_rate": 3.031717050700659e-06,
2031
+ "loss": 0.7926,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 0.77,
2036
+ "grad_norm": 0.045166015625,
2037
+ "learning_rate": 2.9652367510479476e-06,
2038
+ "loss": 0.8127,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 0.78,
2043
+ "grad_norm": 0.021728515625,
2044
+ "learning_rate": 2.899366347608974e-06,
2045
+ "loss": 0.8046,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 0.78,
2050
+ "grad_norm": 0.036865234375,
2051
+ "learning_rate": 2.834111551181423e-06,
2052
+ "loss": 0.7647,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 0.78,
2057
+ "grad_norm": 0.0260009765625,
2058
+ "learning_rate": 2.7694780191914005e-06,
2059
+ "loss": 0.7985,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 0.78,
2064
+ "grad_norm": 0.04052734375,
2065
+ "learning_rate": 2.7054713552029577e-06,
2066
+ "loss": 0.841,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 0.79,
2071
+ "grad_norm": 0.041748046875,
2072
+ "learning_rate": 2.6420971084322745e-06,
2073
+ "loss": 0.7775,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 0.79,
2078
+ "grad_norm": 0.0244140625,
2079
+ "learning_rate": 2.5793607732665402e-06,
2080
+ "loss": 0.7954,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 0.79,
2085
+ "grad_norm": 0.03125,
2086
+ "learning_rate": 2.5172677887876416e-06,
2087
+ "loss": 0.7875,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 0.79,
2092
+ "grad_norm": 0.02490234375,
2093
+ "learning_rate": 2.455823538300569e-06,
2094
+ "loss": 0.8065,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 0.8,
2099
+ "grad_norm": 0.0224609375,
2100
+ "learning_rate": 2.3950333488667178e-06,
2101
+ "loss": 0.8201,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 0.8,
2106
+ "grad_norm": 0.06298828125,
2107
+ "learning_rate": 2.3349024908420403e-06,
2108
+ "loss": 0.813,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 0.8,
2113
+ "grad_norm": 0.03076171875,
2114
+ "learning_rate": 2.2754361774201217e-06,
2115
+ "loss": 0.8076,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 0.81,
2120
+ "grad_norm": 0.0341796875,
2121
+ "learning_rate": 2.2166395641802076e-06,
2122
+ "loss": 0.8135,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 0.81,
2127
+ "grad_norm": 0.0673828125,
2128
+ "learning_rate": 2.1585177486402275e-06,
2129
+ "loss": 0.8095,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 0.81,
2134
+ "grad_norm": 0.0341796875,
2135
+ "learning_rate": 2.101075769814855e-06,
2136
+ "loss": 0.7985,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 0.81,
2141
+ "grad_norm": 0.04150390625,
2142
+ "learning_rate": 2.0443186077786358e-06,
2143
+ "loss": 0.7976,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 0.82,
2148
+ "grad_norm": 0.04736328125,
2149
+ "learning_rate": 1.9882511832342297e-06,
2150
+ "loss": 0.7868,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 0.82,
2155
+ "grad_norm": 0.0262451171875,
2156
+ "learning_rate": 1.9328783570857954e-06,
2157
+ "loss": 0.8072,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 0.82,
2162
+ "grad_norm": 0.04296875,
2163
+ "learning_rate": 1.8782049300175698e-06,
2164
+ "loss": 0.7931,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 0.82,
2169
+ "grad_norm": 0.0269775390625,
2170
+ "learning_rate": 1.8242356420776485e-06,
2171
+ "loss": 0.8185,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 0.83,
2176
+ "grad_norm": 0.033447265625,
2177
+ "learning_rate": 1.7709751722670466e-06,
2178
+ "loss": 0.8391,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 0.83,
2183
+ "grad_norm": 0.0274658203125,
2184
+ "learning_rate": 1.718428138134034e-06,
2185
+ "loss": 0.8502,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 0.83,
2190
+ "grad_norm": 0.02783203125,
2191
+ "learning_rate": 1.666599095373811e-06,
2192
+ "loss": 0.8185,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 0.83,
2197
+ "grad_norm": 0.025390625,
2198
+ "learning_rate": 1.6154925374335362e-06,
2199
+ "loss": 0.806,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 0.84,
2204
+ "grad_norm": 0.0225830078125,
2205
+ "learning_rate": 1.5651128951227613e-06,
2206
+ "loss": 0.783,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 0.84,
2211
+ "grad_norm": 0.033935546875,
2212
+ "learning_rate": 1.5154645362292853e-06,
2213
+ "loss": 0.8159,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 0.84,
2218
+ "grad_norm": 0.025390625,
2219
+ "learning_rate": 1.4665517651404814e-06,
2220
+ "loss": 0.7793,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 0.85,
2225
+ "grad_norm": 0.0220947265625,
2226
+ "learning_rate": 1.4183788224701201e-06,
2227
+ "loss": 0.7754,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 0.85,
2232
+ "grad_norm": 0.0269775390625,
2233
+ "learning_rate": 1.370949884690711e-06,
2234
+ "loss": 0.847,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 0.85,
2239
+ "grad_norm": 0.035888671875,
2240
+ "learning_rate": 1.3242690637714228e-06,
2241
+ "loss": 0.8014,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 0.85,
2246
+ "grad_norm": 0.0238037109375,
2247
+ "learning_rate": 1.2783404068215776e-06,
2248
+ "loss": 0.8235,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 0.86,
2253
+ "grad_norm": 0.033447265625,
2254
+ "learning_rate": 1.2331678957397819e-06,
2255
+ "loss": 0.7997,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 0.86,
2260
+ "grad_norm": 0.033203125,
2261
+ "learning_rate": 1.1887554468687046e-06,
2262
+ "loss": 0.8159,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 0.86,
2267
+ "grad_norm": 0.033935546875,
2268
+ "learning_rate": 1.145106910655538e-06,
2269
+ "loss": 0.8392,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 0.86,
2274
+ "grad_norm": 0.023193359375,
2275
+ "learning_rate": 1.1022260713181786e-06,
2276
+ "loss": 0.8266,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 0.87,
2281
+ "grad_norm": 0.03662109375,
2282
+ "learning_rate": 1.0601166465171387e-06,
2283
+ "loss": 0.8209,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 0.87,
2288
+ "grad_norm": 0.0294189453125,
2289
+ "learning_rate": 1.0187822870332398e-06,
2290
+ "loss": 0.8021,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 0.87,
2295
+ "grad_norm": 0.051025390625,
2296
+ "learning_rate": 9.782265764510968e-07,
2297
+ "loss": 0.7938,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 0.87,
2302
+ "grad_norm": 0.0291748046875,
2303
+ "learning_rate": 9.384530308484275e-07,
2304
+ "loss": 0.8007,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 0.88,
2309
+ "grad_norm": 0.0279541015625,
2310
+ "learning_rate": 8.99465098491229e-07,
2311
+ "loss": 0.8097,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 0.88,
2316
+ "grad_norm": 0.032470703125,
2317
+ "learning_rate": 8.612661595348038e-07,
2318
+ "loss": 0.8029,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 0.88,
2323
+ "grad_norm": 0.0234375,
2324
+ "learning_rate": 8.238595257307225e-07,
2325
+ "loss": 0.8079,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 0.89,
2330
+ "grad_norm": 0.03125,
2331
+ "learning_rate": 7.872484401397018e-07,
2332
+ "loss": 0.8074,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 0.89,
2337
+ "grad_norm": 0.024658203125,
2338
+ "learning_rate": 7.514360768504314e-07,
2339
+ "loss": 0.7961,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 0.89,
2344
+ "grad_norm": 0.03125,
2345
+ "learning_rate": 7.164255407043986e-07,
2346
+ "loss": 0.7701,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 0.89,
2351
+ "grad_norm": 0.0269775390625,
2352
+ "learning_rate": 6.822198670266989e-07,
2353
+ "loss": 0.8165,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 0.9,
2358
+ "grad_norm": 0.0277099609375,
2359
+ "learning_rate": 6.488220213628837e-07,
2360
+ "loss": 0.8097,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 0.9,
2365
+ "grad_norm": 0.0322265625,
2366
+ "learning_rate": 6.16234899221858e-07,
2367
+ "loss": 0.8073,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 0.9,
2372
+ "grad_norm": 0.0234375,
2373
+ "learning_rate": 5.844613258248411e-07,
2374
+ "loss": 0.7865,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 0.9,
2379
+ "grad_norm": 0.130859375,
2380
+ "learning_rate": 5.535040558604299e-07,
2381
+ "loss": 0.8182,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 0.91,
2386
+ "grad_norm": 0.0233154296875,
2387
+ "learning_rate": 5.233657732457775e-07,
2388
+ "loss": 0.78,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 0.91,
2393
+ "grad_norm": 0.0284423828125,
2394
+ "learning_rate": 4.940490908938977e-07,
2395
+ "loss": 0.7961,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 0.91,
2400
+ "grad_norm": 0.0478515625,
2401
+ "learning_rate": 4.6555655048713953e-07,
2402
+ "loss": 0.7946,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 0.91,
2407
+ "grad_norm": 0.023193359375,
2408
+ "learning_rate": 4.3789062225682356e-07,
2409
+ "loss": 0.8022,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 0.92,
2414
+ "grad_norm": 0.060302734375,
2415
+ "learning_rate": 4.1105370476908104e-07,
2416
+ "loss": 0.8201,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 0.92,
2421
+ "grad_norm": 0.042236328125,
2422
+ "learning_rate": 3.8504812471690687e-07,
2423
+ "loss": 0.8014,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 0.92,
2428
+ "grad_norm": 0.02392578125,
2429
+ "learning_rate": 3.598761367184367e-07,
2430
+ "loss": 0.7995,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 0.93,
2435
+ "grad_norm": 0.02880859375,
2436
+ "learning_rate": 3.3553992312148177e-07,
2437
+ "loss": 0.8139,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 0.93,
2442
+ "grad_norm": 0.029052734375,
2443
+ "learning_rate": 3.1204159381432174e-07,
2444
+ "loss": 0.8127,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 0.93,
2449
+ "grad_norm": 0.028564453125,
2450
+ "learning_rate": 2.8938318604278314e-07,
2451
+ "loss": 0.8009,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 0.93,
2456
+ "grad_norm": 0.03173828125,
2457
+ "learning_rate": 2.675666642336172e-07,
2458
+ "loss": 0.8319,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 0.94,
2463
+ "grad_norm": 0.031494140625,
2464
+ "learning_rate": 2.4659391982418626e-07,
2465
+ "loss": 0.8413,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 0.94,
2470
+ "grad_norm": 0.08642578125,
2471
+ "learning_rate": 2.264667710984836e-07,
2472
+ "loss": 0.8194,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 0.94,
2477
+ "grad_norm": 0.0289306640625,
2478
+ "learning_rate": 2.0718696302949092e-07,
2479
+ "loss": 0.8128,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 0.94,
2484
+ "grad_norm": 0.0771484375,
2485
+ "learning_rate": 1.8875616712789257e-07,
2486
+ "loss": 0.8008,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 0.95,
2491
+ "grad_norm": 0.024658203125,
2492
+ "learning_rate": 1.7117598129716362e-07,
2493
+ "loss": 0.7753,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 0.95,
2498
+ "grad_norm": 0.0260009765625,
2499
+ "learning_rate": 1.544479296950341e-07,
2500
+ "loss": 0.802,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 0.95,
2505
+ "grad_norm": 0.025634765625,
2506
+ "learning_rate": 1.385734626013435e-07,
2507
+ "loss": 0.7936,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 0.95,
2512
+ "grad_norm": 0.0240478515625,
2513
+ "learning_rate": 1.2355395629231493e-07,
2514
+ "loss": 0.7956,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 0.96,
2519
+ "grad_norm": 0.08251953125,
2520
+ "learning_rate": 1.0939071292122572e-07,
2521
+ "loss": 0.7769,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 0.96,
2526
+ "grad_norm": 0.0279541015625,
2527
+ "learning_rate": 9.608496040551918e-08,
2528
+ "loss": 0.7957,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 0.96,
2533
+ "grad_norm": 0.0277099609375,
2534
+ "learning_rate": 8.363785232034849e-08,
2535
+ "loss": 0.814,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 0.97,
2540
+ "grad_norm": 0.03173828125,
2541
+ "learning_rate": 7.205046779856007e-08,
2542
+ "loss": 0.8155,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 0.97,
2547
+ "grad_norm": 0.03173828125,
2548
+ "learning_rate": 6.132381143713728e-08,
2549
+ "loss": 0.8364,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 0.97,
2554
+ "grad_norm": 0.0264892578125,
2555
+ "learning_rate": 5.1458813210106815e-08,
2556
+ "loss": 0.8173,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 0.97,
2561
+ "grad_norm": 0.038818359375,
2562
+ "learning_rate": 4.245632838791092e-08,
2563
+ "loss": 0.8085,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 0.98,
2568
+ "grad_norm": 0.0225830078125,
2569
+ "learning_rate": 3.431713746325449e-08,
2570
+ "loss": 0.8195,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 0.98,
2575
+ "grad_norm": 0.0751953125,
2576
+ "learning_rate": 2.7041946083442573e-08,
2577
+ "loss": 0.8029,
2578
+ "step": 3670
2579
+ },
2580
+ {
2581
+ "epoch": 0.98,
2582
+ "grad_norm": 0.06494140625,
2583
+ "learning_rate": 2.0631384989202585e-08,
2584
+ "loss": 0.8359,
2585
+ "step": 3680
2586
+ },
2587
+ {
2588
+ "epoch": 0.98,
2589
+ "grad_norm": 0.030517578125,
2590
+ "learning_rate": 1.5086009959995875e-08,
2591
+ "loss": 0.8233,
2592
+ "step": 3690
2593
+ },
2594
+ {
2595
+ "epoch": 0.99,
2596
+ "grad_norm": 0.0228271484375,
2597
+ "learning_rate": 1.0406301765837346e-08,
2598
+ "loss": 0.7743,
2599
+ "step": 3700
2600
+ },
2601
+ {
2602
+ "epoch": 0.99,
2603
+ "grad_norm": 0.024658203125,
2604
+ "learning_rate": 6.592666125614377e-09,
2605
+ "loss": 0.7764,
2606
+ "step": 3710
2607
+ },
2608
+ {
2609
+ "epoch": 0.99,
2610
+ "grad_norm": 0.023193359375,
2611
+ "learning_rate": 3.645433671908283e-09,
2612
+ "loss": 0.798,
2613
+ "step": 3720
2614
+ },
2615
+ {
2616
+ "epoch": 0.99,
2617
+ "grad_norm": 0.0260009765625,
2618
+ "learning_rate": 1.5648599223316852e-09,
2619
+ "loss": 0.8119,
2620
+ "step": 3730
2621
+ },
2622
+ {
2623
+ "epoch": 1.0,
2624
+ "grad_norm": 0.0247802734375,
2625
+ "learning_rate": 3.5112525737734935e-10,
2626
+ "loss": 0.8295,
2627
+ "step": 3740
2628
+ }
2629
+ ],
2630
+ "logging_steps": 10,
2631
+ "max_steps": 3749,
2632
+ "num_input_tokens_seen": 0,
2633
+ "num_train_epochs": 1,
2634
+ "save_steps": 500,
2635
+ "total_flos": 1.2690756062895145e+18,
2636
+ "train_batch_size": 2,
2637
+ "trial_name": null,
2638
+ "trial_params": null
2639
+ }
checkpoint-3749/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5356fbb048ee7ff25112c3ec47aefcc7e7a98ee5b1b422e51abe8c4254ba97
3
+ size 4920
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.38.2",
26
+ "use_cache": true,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5e29e54daf146219e8057d80955d57d314ef6939096eda6657f8e96a0f3c44
3
+ size 1948291704
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5a4c35804b3838a8b79f4edfa9eb4cf51f12ad42b1354318096a57ce47af3e6
3
+ size 1981891624
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8613bc9974e1f723a9c8cb9cafde49f435638d1060dc5237b1c55194cb65056
3
+ size 1082180264
model.safetensors.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
97
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
98
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
100
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
102
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
103
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
104
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
105
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
106
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
107
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
109
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
110
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
111
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
112
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
113
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
114
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
115
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.norm.weight": "model-00003-of-00003.safetensors"
170
+ }
171
+ }
runs/Mar22_07-15-06_2013f91d074a/events.out.tfevents.1711091786.2013f91d074a.192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a22e3396072b9c08829fa0653cf7d46f2644ccc6b4001c85eecd2448499a39
3
+ size 84269
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
3
+ size 17477473
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
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
+ "106": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|im_start|>",
56
+ "<|im_end|>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }