taesiri commited on
Commit
bfc2553
1 Parent(s): 2399d94

Delete single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora

Browse files
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/README.md DELETED
@@ -1,202 +0,0 @@
1
- ---
2
- library_name: peft
3
- base_model: ./weights/Bunny-Llama-3-8B-V
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
- ### Framework versions
201
-
202
- - PEFT 0.11.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/adapter_config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "./weights/Bunny-Llama-3-8B-V",
5
- "bias": "none",
6
- "fan_in_fan_out": false,
7
- "inference_mode": true,
8
- "init_lora_weights": true,
9
- "layer_replication": null,
10
- "layers_pattern": null,
11
- "layers_to_transform": null,
12
- "loftq_config": {},
13
- "lora_alpha": 256,
14
- "lora_dropout": 0.1,
15
- "megatron_config": null,
16
- "megatron_core": "megatron.core",
17
- "modules_to_save": null,
18
- "peft_type": "LORA",
19
- "r": 128,
20
- "rank_pattern": {},
21
- "revision": null,
22
- "target_modules": [
23
- "up_proj",
24
- "gate_proj",
25
- "v_proj",
26
- "down_proj",
27
- "q_proj",
28
- "o_proj",
29
- "k_proj"
30
- ],
31
- "task_type": "CAUSAL_LM",
32
- "use_dora": false,
33
- "use_rslora": false
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ff6fb22dfaec71c00b932805e5dee92f9b92d22dc3cd5f6f58dcdcafd3d949
3
- size 671150064
 
 
 
 
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "_name_or_path": "./weights/Bunny-Llama-3-8B-V",
3
- "architectures": [
4
- "BunnyLlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "auto_map": {
9
- "AutoConfig": "configuration_bunny_llama.BunnyLlamaConfig",
10
- "AutoModelForCausalLM": "modeling_bunny_llama.BunnyLlamaForCausalLM"
11
- },
12
- "bos_token_id": 128000,
13
- "continuous_training": false,
14
- "eos_token_id": 128001,
15
- "freeze_mm_mlp_adapter": false,
16
- "hidden_act": "silu",
17
- "hidden_size": 4096,
18
- "image_aspect_ratio": "pad",
19
- "initializer_range": 0.02,
20
- "intermediate_size": 14336,
21
- "max_position_embeddings": 8192,
22
- "mm_hidden_size": 1152,
23
- "mm_projector_lr": null,
24
- "mm_projector_type": "mlp2x_gelu",
25
- "mm_vision_tower": "./weights/siglip-so400m-patch14-384",
26
- "model_type": "bunny-llama",
27
- "num_attention_heads": 32,
28
- "num_hidden_layers": 32,
29
- "num_key_value_heads": 8,
30
- "pretraining_tp": 1,
31
- "rms_norm_eps": 1e-05,
32
- "rope_scaling": null,
33
- "rope_theta": 500000.0,
34
- "tie_word_embeddings": false,
35
- "tokenizer_model_max_length": 2048,
36
- "tokenizer_padding_side": "right",
37
- "torch_dtype": "float16",
38
- "transformers_version": "4.41.2",
39
- "tune_mm_mlp_adapter": false,
40
- "unfreeze_vision_tower": true,
41
- "use_cache": true,
42
- "use_mm_proj": true,
43
- "use_s2": false,
44
- "vocab_size": 128256
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/non_lora_trainables.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d7005b204a93bd5f662d33d61974e83298a58f3195ae20f0ace5eb2d7251256
3
- size 899633034
 
 
 
 
single_dataset/img2json/bugsBunny-Llama-3-8B-V-img2json_dataset_5000_epochs_1_lora/trainer_state.json DELETED
@@ -1,2226 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.9984,
5
- "eval_steps": 500,
6
- "global_step": 312,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0032,
13
- "grad_norm": 0.9456431410164449,
14
- "learning_rate": 2e-05,
15
- "loss": 1.4684,
16
- "step": 1
17
- },
18
- {
19
- "epoch": 0.0064,
20
- "grad_norm": 0.9595554488188345,
21
- "learning_rate": 4e-05,
22
- "loss": 1.3749,
23
- "step": 2
24
- },
25
- {
26
- "epoch": 0.0096,
27
- "grad_norm": 0.7819824872221672,
28
- "learning_rate": 6e-05,
29
- "loss": 1.3507,
30
- "step": 3
31
- },
32
- {
33
- "epoch": 0.0128,
34
- "grad_norm": 0.9167023815526777,
35
- "learning_rate": 8e-05,
36
- "loss": 1.2165,
37
- "step": 4
38
- },
39
- {
40
- "epoch": 0.016,
41
- "grad_norm": 0.847495342554959,
42
- "learning_rate": 0.0001,
43
- "loss": 1.1304,
44
- "step": 5
45
- },
46
- {
47
- "epoch": 0.0192,
48
- "grad_norm": 0.8818427732884414,
49
- "learning_rate": 0.00012,
50
- "loss": 0.9715,
51
- "step": 6
52
- },
53
- {
54
- "epoch": 0.0224,
55
- "grad_norm": 0.7726751380491141,
56
- "learning_rate": 0.00014,
57
- "loss": 0.9336,
58
- "step": 7
59
- },
60
- {
61
- "epoch": 0.0256,
62
- "grad_norm": 0.6483561690537337,
63
- "learning_rate": 0.00016,
64
- "loss": 0.8903,
65
- "step": 8
66
- },
67
- {
68
- "epoch": 0.0288,
69
- "grad_norm": 0.5687921838840364,
70
- "learning_rate": 0.00018,
71
- "loss": 0.7977,
72
- "step": 9
73
- },
74
- {
75
- "epoch": 0.032,
76
- "grad_norm": 0.4217197943554311,
77
- "learning_rate": 0.0002,
78
- "loss": 0.8058,
79
- "step": 10
80
- },
81
- {
82
- "epoch": 0.0352,
83
- "grad_norm": 0.39301658901144887,
84
- "learning_rate": 0.00019999458931878073,
85
- "loss": 0.8494,
86
- "step": 11
87
- },
88
- {
89
- "epoch": 0.0384,
90
- "grad_norm": 0.4590183081730723,
91
- "learning_rate": 0.0001999783578606323,
92
- "loss": 0.8636,
93
- "step": 12
94
- },
95
- {
96
- "epoch": 0.0416,
97
- "grad_norm": 0.41874721337638304,
98
- "learning_rate": 0.00019995130738201966,
99
- "loss": 0.8045,
100
- "step": 13
101
- },
102
- {
103
- "epoch": 0.0448,
104
- "grad_norm": 0.36156401408882166,
105
- "learning_rate": 0.0001999134408101731,
106
- "loss": 0.7129,
107
- "step": 14
108
- },
109
- {
110
- "epoch": 0.048,
111
- "grad_norm": 0.43359389552236977,
112
- "learning_rate": 0.00019986476224277165,
113
- "loss": 0.737,
114
- "step": 15
115
- },
116
- {
117
- "epoch": 0.0512,
118
- "grad_norm": 0.3732292263108806,
119
- "learning_rate": 0.00019980527694749952,
120
- "loss": 0.721,
121
- "step": 16
122
- },
123
- {
124
- "epoch": 0.0544,
125
- "grad_norm": 0.3672574865848022,
126
- "learning_rate": 0.00019973499136147606,
127
- "loss": 0.768,
128
- "step": 17
129
- },
130
- {
131
- "epoch": 0.0576,
132
- "grad_norm": 0.3788969898154259,
133
- "learning_rate": 0.0001996539130905593,
134
- "loss": 0.6994,
135
- "step": 18
136
- },
137
- {
138
- "epoch": 0.0608,
139
- "grad_norm": 0.3591018825770351,
140
- "learning_rate": 0.0001995620509085228,
141
- "loss": 0.7546,
142
- "step": 19
143
- },
144
- {
145
- "epoch": 0.064,
146
- "grad_norm": 0.3347980700973235,
147
- "learning_rate": 0.00019945941475610623,
148
- "loss": 0.7799,
149
- "step": 20
150
- },
151
- {
152
- "epoch": 0.0672,
153
- "grad_norm": 0.3176137835338356,
154
- "learning_rate": 0.0001993460157399396,
155
- "loss": 0.718,
156
- "step": 21
157
- },
158
- {
159
- "epoch": 0.0704,
160
- "grad_norm": 0.3110224161054545,
161
- "learning_rate": 0.0001992218661313415,
162
- "loss": 0.6712,
163
- "step": 22
164
- },
165
- {
166
- "epoch": 0.0736,
167
- "grad_norm": 0.3176740651877855,
168
- "learning_rate": 0.00019908697936499103,
169
- "loss": 0.7517,
170
- "step": 23
171
- },
172
- {
173
- "epoch": 0.0768,
174
- "grad_norm": 0.31311011452703175,
175
- "learning_rate": 0.00019894137003747403,
176
- "loss": 0.7431,
177
- "step": 24
178
- },
179
- {
180
- "epoch": 0.08,
181
- "grad_norm": 0.31035422091689385,
182
- "learning_rate": 0.00019878505390570362,
183
- "loss": 0.7121,
184
- "step": 25
185
- },
186
- {
187
- "epoch": 0.0832,
188
- "grad_norm": 0.2986181957125755,
189
- "learning_rate": 0.00019861804788521493,
190
- "loss": 0.6987,
191
- "step": 26
192
- },
193
- {
194
- "epoch": 0.0864,
195
- "grad_norm": 0.32611739837441994,
196
- "learning_rate": 0.00019844037004833473,
197
- "loss": 0.7732,
198
- "step": 27
199
- },
200
- {
201
- "epoch": 0.0896,
202
- "grad_norm": 0.290949601128612,
203
- "learning_rate": 0.00019825203962222572,
204
- "loss": 0.6783,
205
- "step": 28
206
- },
207
- {
208
- "epoch": 0.0928,
209
- "grad_norm": 0.30951784533907173,
210
- "learning_rate": 0.0001980530769868059,
211
- "loss": 0.7126,
212
- "step": 29
213
- },
214
- {
215
- "epoch": 0.096,
216
- "grad_norm": 0.30642887130649027,
217
- "learning_rate": 0.00019784350367254322,
218
- "loss": 0.6716,
219
- "step": 30
220
- },
221
- {
222
- "epoch": 0.0992,
223
- "grad_norm": 0.3253752205567512,
224
- "learning_rate": 0.0001976233423581255,
225
- "loss": 0.7618,
226
- "step": 31
227
- },
228
- {
229
- "epoch": 0.1024,
230
- "grad_norm": 0.3074017490574547,
231
- "learning_rate": 0.0001973926168680066,
232
- "loss": 0.6863,
233
- "step": 32
234
- },
235
- {
236
- "epoch": 0.1056,
237
- "grad_norm": 0.2991620525987948,
238
- "learning_rate": 0.00019715135216982798,
239
- "loss": 0.7061,
240
- "step": 33
241
- },
242
- {
243
- "epoch": 0.1088,
244
- "grad_norm": 0.3226295279455581,
245
- "learning_rate": 0.0001968995743717171,
246
- "loss": 0.7164,
247
- "step": 34
248
- },
249
- {
250
- "epoch": 0.112,
251
- "grad_norm": 0.2942063456789797,
252
- "learning_rate": 0.00019663731071946206,
253
- "loss": 0.6732,
254
- "step": 35
255
- },
256
- {
257
- "epoch": 0.1152,
258
- "grad_norm": 0.30145830255706224,
259
- "learning_rate": 0.00019636458959356316,
260
- "loss": 0.6917,
261
- "step": 36
262
- },
263
- {
264
- "epoch": 0.1184,
265
- "grad_norm": 0.2976180783817878,
266
- "learning_rate": 0.0001960814405061619,
267
- "loss": 0.6688,
268
- "step": 37
269
- },
270
- {
271
- "epoch": 0.1216,
272
- "grad_norm": 0.28814304785348366,
273
- "learning_rate": 0.00019578789409784727,
274
- "loss": 0.6852,
275
- "step": 38
276
- },
277
- {
278
- "epoch": 0.1248,
279
- "grad_norm": 0.2968046184063759,
280
- "learning_rate": 0.00019548398213434007,
281
- "loss": 0.6827,
282
- "step": 39
283
- },
284
- {
285
- "epoch": 0.128,
286
- "grad_norm": 0.2848652475342455,
287
- "learning_rate": 0.00019516973750305532,
288
- "loss": 0.6905,
289
- "step": 40
290
- },
291
- {
292
- "epoch": 0.1312,
293
- "grad_norm": 0.29541131745521493,
294
- "learning_rate": 0.00019484519420954354,
295
- "loss": 0.7409,
296
- "step": 41
297
- },
298
- {
299
- "epoch": 0.1344,
300
- "grad_norm": 0.30472745054693,
301
- "learning_rate": 0.00019451038737381077,
302
- "loss": 0.6976,
303
- "step": 42
304
- },
305
- {
306
- "epoch": 0.1376,
307
- "grad_norm": 0.287978936057206,
308
- "learning_rate": 0.00019416535322651818,
309
- "loss": 0.6889,
310
- "step": 43
311
- },
312
- {
313
- "epoch": 0.1408,
314
- "grad_norm": 0.2917374421163095,
315
- "learning_rate": 0.00019381012910506146,
316
- "loss": 0.7072,
317
- "step": 44
318
- },
319
- {
320
- "epoch": 0.144,
321
- "grad_norm": 0.3014118067717161,
322
- "learning_rate": 0.00019344475344953012,
323
- "loss": 0.736,
324
- "step": 45
325
- },
326
- {
327
- "epoch": 0.1472,
328
- "grad_norm": 0.27940318160556293,
329
- "learning_rate": 0.00019306926579854821,
330
- "loss": 0.6561,
331
- "step": 46
332
- },
333
- {
334
- "epoch": 0.1504,
335
- "grad_norm": 0.2764033621334266,
336
- "learning_rate": 0.00019268370678499533,
337
- "loss": 0.6425,
338
- "step": 47
339
- },
340
- {
341
- "epoch": 0.1536,
342
- "grad_norm": 0.286603211032781,
343
- "learning_rate": 0.0001922881181316097,
344
- "loss": 0.6984,
345
- "step": 48
346
- },
347
- {
348
- "epoch": 0.1568,
349
- "grad_norm": 0.29296348821168333,
350
- "learning_rate": 0.00019188254264647337,
351
- "loss": 0.6898,
352
- "step": 49
353
- },
354
- {
355
- "epoch": 0.16,
356
- "grad_norm": 0.28097584337963444,
357
- "learning_rate": 0.0001914670242183795,
358
- "loss": 0.6858,
359
- "step": 50
360
- },
361
- {
362
- "epoch": 0.1632,
363
- "grad_norm": 0.30154798580564207,
364
- "learning_rate": 0.0001910416078120832,
365
- "loss": 0.7145,
366
- "step": 51
367
- },
368
- {
369
- "epoch": 0.1664,
370
- "grad_norm": 0.30795671266773783,
371
- "learning_rate": 0.0001906063394634356,
372
- "loss": 0.7126,
373
- "step": 52
374
- },
375
- {
376
- "epoch": 0.1696,
377
- "grad_norm": 0.28661331080986213,
378
- "learning_rate": 0.00019016126627440237,
379
- "loss": 0.6722,
380
- "step": 53
381
- },
382
- {
383
- "epoch": 0.1728,
384
- "grad_norm": 0.27995432204171594,
385
- "learning_rate": 0.00018970643640796642,
386
- "loss": 0.6533,
387
- "step": 54
388
- },
389
- {
390
- "epoch": 0.176,
391
- "grad_norm": 0.2881701437861025,
392
- "learning_rate": 0.000189241899082916,
393
- "loss": 0.6864,
394
- "step": 55
395
- },
396
- {
397
- "epoch": 0.1792,
398
- "grad_norm": 0.2863440297333805,
399
- "learning_rate": 0.00018876770456851877,
400
- "loss": 0.6545,
401
- "step": 56
402
- },
403
- {
404
- "epoch": 0.1824,
405
- "grad_norm": 0.2880700843682891,
406
- "learning_rate": 0.0001882839041790818,
407
- "loss": 0.6694,
408
- "step": 57
409
- },
410
- {
411
- "epoch": 0.1856,
412
- "grad_norm": 0.2774792629615745,
413
- "learning_rate": 0.00018779055026839868,
414
- "loss": 0.6505,
415
- "step": 58
416
- },
417
- {
418
- "epoch": 0.1888,
419
- "grad_norm": 0.2737154598370057,
420
- "learning_rate": 0.00018728769622408423,
421
- "loss": 0.6388,
422
- "step": 59
423
- },
424
- {
425
- "epoch": 0.192,
426
- "grad_norm": 0.27952240531043854,
427
- "learning_rate": 0.00018677539646179707,
428
- "loss": 0.6802,
429
- "step": 60
430
- },
431
- {
432
- "epoch": 0.1952,
433
- "grad_norm": 0.28225508446141556,
434
- "learning_rate": 0.00018625370641935129,
435
- "loss": 0.6638,
436
- "step": 61
437
- },
438
- {
439
- "epoch": 0.1984,
440
- "grad_norm": 0.28445391301141404,
441
- "learning_rate": 0.00018572268255071718,
442
- "loss": 0.6997,
443
- "step": 62
444
- },
445
- {
446
- "epoch": 0.2016,
447
- "grad_norm": 0.27249304099350813,
448
- "learning_rate": 0.00018518238231991218,
449
- "loss": 0.665,
450
- "step": 63
451
- },
452
- {
453
- "epoch": 0.2048,
454
- "grad_norm": 0.27827800737681285,
455
- "learning_rate": 0.00018463286419478255,
456
- "loss": 0.6747,
457
- "step": 64
458
- },
459
- {
460
- "epoch": 0.208,
461
- "grad_norm": 0.28236239197955565,
462
- "learning_rate": 0.00018407418764067627,
463
- "loss": 0.6804,
464
- "step": 65
465
- },
466
- {
467
- "epoch": 0.2112,
468
- "grad_norm": 0.27711713330173016,
469
- "learning_rate": 0.00018350641311400812,
470
- "loss": 0.6825,
471
- "step": 66
472
- },
473
- {
474
- "epoch": 0.2144,
475
- "grad_norm": 0.27559978427300996,
476
- "learning_rate": 0.0001829296020557174,
477
- "loss": 0.6893,
478
- "step": 67
479
- },
480
- {
481
- "epoch": 0.2176,
482
- "grad_norm": 0.28871955197128163,
483
- "learning_rate": 0.00018234381688461942,
484
- "loss": 0.6574,
485
- "step": 68
486
- },
487
- {
488
- "epoch": 0.2208,
489
- "grad_norm": 0.2840675164080103,
490
- "learning_rate": 0.0001817491209906506,
491
- "loss": 0.7286,
492
- "step": 69
493
- },
494
- {
495
- "epoch": 0.224,
496
- "grad_norm": 0.3083968957018995,
497
- "learning_rate": 0.00018114557872800905,
498
- "loss": 0.6578,
499
- "step": 70
500
- },
501
- {
502
- "epoch": 0.2272,
503
- "grad_norm": 0.2843871593471055,
504
- "learning_rate": 0.00018053325540819045,
505
- "loss": 0.6792,
506
- "step": 71
507
- },
508
- {
509
- "epoch": 0.2304,
510
- "grad_norm": 0.2791531418567351,
511
- "learning_rate": 0.0001799122172929206,
512
- "loss": 0.6779,
513
- "step": 72
514
- },
515
- {
516
- "epoch": 0.2336,
517
- "grad_norm": 0.28436440881242775,
518
- "learning_rate": 0.00017928253158698473,
519
- "loss": 0.6461,
520
- "step": 73
521
- },
522
- {
523
- "epoch": 0.2368,
524
- "grad_norm": 0.28210657946106504,
525
- "learning_rate": 0.0001786442664309554,
526
- "loss": 0.6376,
527
- "step": 74
528
- },
529
- {
530
- "epoch": 0.24,
531
- "grad_norm": 0.27471101989657526,
532
- "learning_rate": 0.0001779974908938184,
533
- "loss": 0.6589,
534
- "step": 75
535
- },
536
- {
537
- "epoch": 0.2432,
538
- "grad_norm": 0.27255559553885733,
539
- "learning_rate": 0.0001773422749654988,
540
- "loss": 0.6624,
541
- "step": 76
542
- },
543
- {
544
- "epoch": 0.2464,
545
- "grad_norm": 0.28238069396965426,
546
- "learning_rate": 0.00017667868954928694,
547
- "loss": 0.665,
548
- "step": 77
549
- },
550
- {
551
- "epoch": 0.2496,
552
- "grad_norm": 0.28091292280312435,
553
- "learning_rate": 0.00017600680645416583,
554
- "loss": 0.6582,
555
- "step": 78
556
- },
557
- {
558
- "epoch": 0.2528,
559
- "grad_norm": 0.2819117395356436,
560
- "learning_rate": 0.00017532669838704035,
561
- "loss": 0.681,
562
- "step": 79
563
- },
564
- {
565
- "epoch": 0.256,
566
- "grad_norm": 0.2808167623131368,
567
- "learning_rate": 0.00017463843894486937,
568
- "loss": 0.6635,
569
- "step": 80
570
- },
571
- {
572
- "epoch": 0.2592,
573
- "grad_norm": 0.2727980766577742,
574
- "learning_rate": 0.0001739421026067017,
575
- "loss": 0.6387,
576
- "step": 81
577
- },
578
- {
579
- "epoch": 0.2624,
580
- "grad_norm": 0.27946610199292726,
581
- "learning_rate": 0.00017323776472561627,
582
- "loss": 0.6636,
583
- "step": 82
584
- },
585
- {
586
- "epoch": 0.2656,
587
- "grad_norm": 0.2776930025762807,
588
- "learning_rate": 0.00017252550152056795,
589
- "loss": 0.6629,
590
- "step": 83
591
- },
592
- {
593
- "epoch": 0.2688,
594
- "grad_norm": 0.29547305795196493,
595
- "learning_rate": 0.0001718053900681397,
596
- "loss": 0.7105,
597
- "step": 84
598
- },
599
- {
600
- "epoch": 0.272,
601
- "grad_norm": 0.27992559053351135,
602
- "learning_rate": 0.00017107750829420176,
603
- "loss": 0.6217,
604
- "step": 85
605
- },
606
- {
607
- "epoch": 0.2752,
608
- "grad_norm": 0.2836978378018261,
609
- "learning_rate": 0.00017034193496547902,
610
- "loss": 0.6364,
611
- "step": 86
612
- },
613
- {
614
- "epoch": 0.2784,
615
- "grad_norm": 0.2859793795996647,
616
- "learning_rate": 0.00016959874968102735,
617
- "loss": 0.6611,
618
- "step": 87
619
- },
620
- {
621
- "epoch": 0.2816,
622
- "grad_norm": 0.27670508997854193,
623
- "learning_rate": 0.00016884803286362,
624
- "loss": 0.6321,
625
- "step": 88
626
- },
627
- {
628
- "epoch": 0.2848,
629
- "grad_norm": 0.2804552643700331,
630
- "learning_rate": 0.00016808986575104465,
631
- "loss": 0.654,
632
- "step": 89
633
- },
634
- {
635
- "epoch": 0.288,
636
- "grad_norm": 0.2988662193267764,
637
- "learning_rate": 0.00016732433038731242,
638
- "loss": 0.6631,
639
- "step": 90
640
- },
641
- {
642
- "epoch": 0.2912,
643
- "grad_norm": 0.2850945559743476,
644
- "learning_rate": 0.0001665515096137797,
645
- "loss": 0.6546,
646
- "step": 91
647
- },
648
- {
649
- "epoch": 0.2944,
650
- "grad_norm": 0.34508854455612903,
651
- "learning_rate": 0.00016577148706018328,
652
- "loss": 0.6181,
653
- "step": 92
654
- },
655
- {
656
- "epoch": 0.2976,
657
- "grad_norm": 0.29772302651197313,
658
- "learning_rate": 0.00016498434713559088,
659
- "loss": 0.6953,
660
- "step": 93
661
- },
662
- {
663
- "epoch": 0.3008,
664
- "grad_norm": 0.2814403372374441,
665
- "learning_rate": 0.00016419017501926656,
666
- "loss": 0.6711,
667
- "step": 94
668
- },
669
- {
670
- "epoch": 0.304,
671
- "grad_norm": 0.2666134049420953,
672
- "learning_rate": 0.0001633890566514535,
673
- "loss": 0.6384,
674
- "step": 95
675
- },
676
- {
677
- "epoch": 0.3072,
678
- "grad_norm": 0.2759217127531887,
679
- "learning_rate": 0.00016258107872407375,
680
- "loss": 0.5927,
681
- "step": 96
682
- },
683
- {
684
- "epoch": 0.3104,
685
- "grad_norm": 0.27234087211717334,
686
- "learning_rate": 0.0001617663286713474,
687
- "loss": 0.6047,
688
- "step": 97
689
- },
690
- {
691
- "epoch": 0.3136,
692
- "grad_norm": 0.28929394588800267,
693
- "learning_rate": 0.00016094489466033043,
694
- "loss": 0.709,
695
- "step": 98
696
- },
697
- {
698
- "epoch": 0.3168,
699
- "grad_norm": 0.27285248521549677,
700
- "learning_rate": 0.00016011686558137448,
701
- "loss": 0.6275,
702
- "step": 99
703
- },
704
- {
705
- "epoch": 0.32,
706
- "grad_norm": 0.27087214179135655,
707
- "learning_rate": 0.0001592823310385073,
708
- "loss": 0.6288,
709
- "step": 100
710
- },
711
- {
712
- "epoch": 0.3232,
713
- "grad_norm": 0.2759835535783692,
714
- "learning_rate": 0.0001584413813397364,
715
- "loss": 0.6529,
716
- "step": 101
717
- },
718
- {
719
- "epoch": 0.3264,
720
- "grad_norm": 0.2732937178984582,
721
- "learning_rate": 0.00015759410748727662,
722
- "loss": 0.6443,
723
- "step": 102
724
- },
725
- {
726
- "epoch": 0.3296,
727
- "grad_norm": 0.27150370023008635,
728
- "learning_rate": 0.00015674060116770236,
729
- "loss": 0.6401,
730
- "step": 103
731
- },
732
- {
733
- "epoch": 0.3328,
734
- "grad_norm": 0.288480165883741,
735
- "learning_rate": 0.00015588095474202595,
736
- "loss": 0.661,
737
- "step": 104
738
- },
739
- {
740
- "epoch": 0.336,
741
- "grad_norm": 0.2715185186712244,
742
- "learning_rate": 0.00015501526123570277,
743
- "loss": 0.5861,
744
- "step": 105
745
- },
746
- {
747
- "epoch": 0.3392,
748
- "grad_norm": 0.2890522618399928,
749
- "learning_rate": 0.00015414361432856475,
750
- "loss": 0.6547,
751
- "step": 106
752
- },
753
- {
754
- "epoch": 0.3424,
755
- "grad_norm": 0.2809942944669504,
756
- "learning_rate": 0.0001532661083446829,
757
- "loss": 0.6502,
758
- "step": 107
759
- },
760
- {
761
- "epoch": 0.3456,
762
- "grad_norm": 0.2770621559504025,
763
- "learning_rate": 0.00015238283824216015,
764
- "loss": 0.651,
765
- "step": 108
766
- },
767
- {
768
- "epoch": 0.3488,
769
- "grad_norm": 0.28643434801423096,
770
- "learning_rate": 0.00015149389960285558,
771
- "loss": 0.6717,
772
- "step": 109
773
- },
774
- {
775
- "epoch": 0.352,
776
- "grad_norm": 0.2838267721875221,
777
- "learning_rate": 0.00015059938862204127,
778
- "loss": 0.6666,
779
- "step": 110
780
- },
781
- {
782
- "epoch": 0.3552,
783
- "grad_norm": 0.2904515511293253,
784
- "learning_rate": 0.00014969940209799248,
785
- "loss": 0.6788,
786
- "step": 111
787
- },
788
- {
789
- "epoch": 0.3584,
790
- "grad_norm": 0.27521059578174806,
791
- "learning_rate": 0.00014879403742151283,
792
- "loss": 0.6421,
793
- "step": 112
794
- },
795
- {
796
- "epoch": 0.3616,
797
- "grad_norm": 0.28435477767209977,
798
- "learning_rate": 0.00014788339256539544,
799
- "loss": 0.6806,
800
- "step": 113
801
- },
802
- {
803
- "epoch": 0.3648,
804
- "grad_norm": 0.2836689862948711,
805
- "learning_rate": 0.0001469675660738206,
806
- "loss": 0.6633,
807
- "step": 114
808
- },
809
- {
810
- "epoch": 0.368,
811
- "grad_norm": 0.27993720267562205,
812
- "learning_rate": 0.00014604665705169237,
813
- "loss": 0.6031,
814
- "step": 115
815
- },
816
- {
817
- "epoch": 0.3712,
818
- "grad_norm": 0.26823803322012507,
819
- "learning_rate": 0.00014512076515391375,
820
- "loss": 0.6258,
821
- "step": 116
822
- },
823
- {
824
- "epoch": 0.3744,
825
- "grad_norm": 0.2755753433763202,
826
- "learning_rate": 0.00014418999057460276,
827
- "loss": 0.6238,
828
- "step": 117
829
- },
830
- {
831
- "epoch": 0.3776,
832
- "grad_norm": 0.26378813575701704,
833
- "learning_rate": 0.0001432544340362501,
834
- "loss": 0.6105,
835
- "step": 118
836
- },
837
- {
838
- "epoch": 0.3808,
839
- "grad_norm": 0.27807647013178804,
840
- "learning_rate": 0.00014231419677881966,
841
- "loss": 0.634,
842
- "step": 119
843
- },
844
- {
845
- "epoch": 0.384,
846
- "grad_norm": 0.2850302043584264,
847
- "learning_rate": 0.00014136938054879283,
848
- "loss": 0.6473,
849
- "step": 120
850
- },
851
- {
852
- "epoch": 0.3872,
853
- "grad_norm": 0.2842021607325469,
854
- "learning_rate": 0.00014042008758815818,
855
- "loss": 0.6666,
856
- "step": 121
857
- },
858
- {
859
- "epoch": 0.3904,
860
- "grad_norm": 0.2646241757350502,
861
- "learning_rate": 0.00013946642062334766,
862
- "loss": 0.5882,
863
- "step": 122
864
- },
865
- {
866
- "epoch": 0.3936,
867
- "grad_norm": 0.27553697595802684,
868
- "learning_rate": 0.00013850848285411994,
869
- "loss": 0.6553,
870
- "step": 123
871
- },
872
- {
873
- "epoch": 0.3968,
874
- "grad_norm": 0.266869763753527,
875
- "learning_rate": 0.000137546377942393,
876
- "loss": 0.6334,
877
- "step": 124
878
- },
879
- {
880
- "epoch": 0.4,
881
- "grad_norm": 0.2891373420552467,
882
- "learning_rate": 0.00013658021000102636,
883
- "loss": 0.6232,
884
- "step": 125
885
- },
886
- {
887
- "epoch": 0.4032,
888
- "grad_norm": 0.29054049719448544,
889
- "learning_rate": 0.00013561008358255468,
890
- "loss": 0.6685,
891
- "step": 126
892
- },
893
- {
894
- "epoch": 0.4064,
895
- "grad_norm": 0.26991808658939265,
896
- "learning_rate": 0.00013463610366787392,
897
- "loss": 0.6451,
898
- "step": 127
899
- },
900
- {
901
- "epoch": 0.4096,
902
- "grad_norm": 0.2826019428481463,
903
- "learning_rate": 0.00013365837565488064,
904
- "loss": 0.6748,
905
- "step": 128
906
- },
907
- {
908
- "epoch": 0.4128,
909
- "grad_norm": 0.26989180549288744,
910
- "learning_rate": 0.0001326770053470668,
911
- "loss": 0.6366,
912
- "step": 129
913
- },
914
- {
915
- "epoch": 0.416,
916
- "grad_norm": 0.2693716385431619,
917
- "learning_rate": 0.0001316920989420703,
918
- "loss": 0.6365,
919
- "step": 130
920
- },
921
- {
922
- "epoch": 0.4192,
923
- "grad_norm": 0.2587716538530605,
924
- "learning_rate": 0.00013070376302018287,
925
- "loss": 0.5821,
926
- "step": 131
927
- },
928
- {
929
- "epoch": 0.4224,
930
- "grad_norm": 0.2733425696050926,
931
- "learning_rate": 0.00012971210453281674,
932
- "loss": 0.6601,
933
- "step": 132
934
- },
935
- {
936
- "epoch": 0.4256,
937
- "grad_norm": 0.28260898546044794,
938
- "learning_rate": 0.000128717230790931,
939
- "loss": 0.6598,
940
- "step": 133
941
- },
942
- {
943
- "epoch": 0.4288,
944
- "grad_norm": 0.26073598361962874,
945
- "learning_rate": 0.00012771924945341906,
946
- "loss": 0.6062,
947
- "step": 134
948
- },
949
- {
950
- "epoch": 0.432,
951
- "grad_norm": 0.26672014153172025,
952
- "learning_rate": 0.00012671826851545851,
953
- "loss": 0.6664,
954
- "step": 135
955
- },
956
- {
957
- "epoch": 0.4352,
958
- "grad_norm": 0.27064468874961567,
959
- "learning_rate": 0.0001257143962968246,
960
- "loss": 0.6409,
961
- "step": 136
962
- },
963
- {
964
- "epoch": 0.4384,
965
- "grad_norm": 0.2678777921010367,
966
- "learning_rate": 0.00012470774143016853,
967
- "loss": 0.6146,
968
- "step": 137
969
- },
970
- {
971
- "epoch": 0.4416,
972
- "grad_norm": 0.2831646298939026,
973
- "learning_rate": 0.00012369841284926188,
974
- "loss": 0.6641,
975
- "step": 138
976
- },
977
- {
978
- "epoch": 0.4448,
979
- "grad_norm": 0.2863253592057525,
980
- "learning_rate": 0.00012268651977720866,
981
- "loss": 0.6653,
982
- "step": 139
983
- },
984
- {
985
- "epoch": 0.448,
986
- "grad_norm": 0.26496566477700495,
987
- "learning_rate": 0.00012167217171462566,
988
- "loss": 0.6061,
989
- "step": 140
990
- },
991
- {
992
- "epoch": 0.4512,
993
- "grad_norm": 0.2741590428796881,
994
- "learning_rate": 0.0001206554784277931,
995
- "loss": 0.683,
996
- "step": 141
997
- },
998
- {
999
- "epoch": 0.4544,
1000
- "grad_norm": 0.274967394883945,
1001
- "learning_rate": 0.00011963654993677645,
1002
- "loss": 0.6738,
1003
- "step": 142
1004
- },
1005
- {
1006
- "epoch": 0.4576,
1007
- "grad_norm": 0.26748184911275685,
1008
- "learning_rate": 0.00011861549650352069,
1009
- "loss": 0.6259,
1010
- "step": 143
1011
- },
1012
- {
1013
- "epoch": 0.4608,
1014
- "grad_norm": 0.27571463833666354,
1015
- "learning_rate": 0.00011759242861991855,
1016
- "loss": 0.6824,
1017
- "step": 144
1018
- },
1019
- {
1020
- "epoch": 0.464,
1021
- "grad_norm": 0.28204383254583004,
1022
- "learning_rate": 0.00011656745699585371,
1023
- "loss": 0.654,
1024
- "step": 145
1025
- },
1026
- {
1027
- "epoch": 0.4672,
1028
- "grad_norm": 0.2737273526998308,
1029
- "learning_rate": 0.00011554069254722051,
1030
- "loss": 0.6383,
1031
- "step": 146
1032
- },
1033
- {
1034
- "epoch": 0.4704,
1035
- "grad_norm": 0.26718453878335136,
1036
- "learning_rate": 0.00011451224638392129,
1037
- "loss": 0.6336,
1038
- "step": 147
1039
- },
1040
- {
1041
- "epoch": 0.4736,
1042
- "grad_norm": 0.28928334642647074,
1043
- "learning_rate": 0.00011348222979784289,
1044
- "loss": 0.6328,
1045
- "step": 148
1046
- },
1047
- {
1048
- "epoch": 0.4768,
1049
- "grad_norm": 0.27269344035826515,
1050
- "learning_rate": 0.00011245075425081328,
1051
- "loss": 0.6261,
1052
- "step": 149
1053
- },
1054
- {
1055
- "epoch": 0.48,
1056
- "grad_norm": 0.27361132880394723,
1057
- "learning_rate": 0.00011141793136253986,
1058
- "loss": 0.6423,
1059
- "step": 150
1060
- },
1061
- {
1062
- "epoch": 0.4832,
1063
- "grad_norm": 0.2666674720378228,
1064
- "learning_rate": 0.0001103838728985307,
1065
- "loss": 0.6397,
1066
- "step": 151
1067
- },
1068
- {
1069
- "epoch": 0.4864,
1070
- "grad_norm": 0.26339311415617495,
1071
- "learning_rate": 0.000109348690758,
1072
- "loss": 0.6184,
1073
- "step": 152
1074
- },
1075
- {
1076
- "epoch": 0.4896,
1077
- "grad_norm": 0.30511330160542777,
1078
- "learning_rate": 0.00010831249696175918,
1079
- "loss": 0.631,
1080
- "step": 153
1081
- },
1082
- {
1083
- "epoch": 0.4928,
1084
- "grad_norm": 0.27393530074277894,
1085
- "learning_rate": 0.0001072754036400944,
1086
- "loss": 0.64,
1087
- "step": 154
1088
- },
1089
- {
1090
- "epoch": 0.496,
1091
- "grad_norm": 0.2630950654462822,
1092
- "learning_rate": 0.00010623752302063283,
1093
- "loss": 0.6256,
1094
- "step": 155
1095
- },
1096
- {
1097
- "epoch": 0.4992,
1098
- "grad_norm": 0.26558776558003316,
1099
- "learning_rate": 0.00010519896741619803,
1100
- "loss": 0.6329,
1101
- "step": 156
1102
- },
1103
- {
1104
- "epoch": 0.5024,
1105
- "grad_norm": 0.27737305767773224,
1106
- "learning_rate": 0.00010415984921265609,
1107
- "loss": 0.6808,
1108
- "step": 157
1109
- },
1110
- {
1111
- "epoch": 0.5056,
1112
- "grad_norm": 0.34438277093807235,
1113
- "learning_rate": 0.00010312028085675391,
1114
- "loss": 0.628,
1115
- "step": 158
1116
- },
1117
- {
1118
- "epoch": 0.5088,
1119
- "grad_norm": 0.2716378054950986,
1120
- "learning_rate": 0.00010208037484395114,
1121
- "loss": 0.6197,
1122
- "step": 159
1123
- },
1124
- {
1125
- "epoch": 0.512,
1126
- "grad_norm": 0.25713458936107125,
1127
- "learning_rate": 0.00010104024370624644,
1128
- "loss": 0.6055,
1129
- "step": 160
1130
- },
1131
- {
1132
- "epoch": 0.5152,
1133
- "grad_norm": 0.2556414802851472,
1134
- "learning_rate": 0.0001,
1135
- "loss": 0.6088,
1136
- "step": 161
1137
- },
1138
- {
1139
- "epoch": 0.5184,
1140
- "grad_norm": 0.9117970631393475,
1141
- "learning_rate": 9.895975629375359e-05,
1142
- "loss": 0.6301,
1143
- "step": 162
1144
- },
1145
- {
1146
- "epoch": 0.5216,
1147
- "grad_norm": 0.26669052461677767,
1148
- "learning_rate": 9.791962515604887e-05,
1149
- "loss": 0.6326,
1150
- "step": 163
1151
- },
1152
- {
1153
- "epoch": 0.5248,
1154
- "grad_norm": 0.27925439381355327,
1155
- "learning_rate": 9.687971914324607e-05,
1156
- "loss": 0.6681,
1157
- "step": 164
1158
- },
1159
- {
1160
- "epoch": 0.528,
1161
- "grad_norm": 0.25468990353229803,
1162
- "learning_rate": 9.584015078734395e-05,
1163
- "loss": 0.5743,
1164
- "step": 165
1165
- },
1166
- {
1167
- "epoch": 0.5312,
1168
- "grad_norm": 0.2629677375763853,
1169
- "learning_rate": 9.480103258380198e-05,
1170
- "loss": 0.6055,
1171
- "step": 166
1172
- },
1173
- {
1174
- "epoch": 0.5344,
1175
- "grad_norm": 0.26370207518366157,
1176
- "learning_rate": 9.376247697936719e-05,
1177
- "loss": 0.6102,
1178
- "step": 167
1179
- },
1180
- {
1181
- "epoch": 0.5376,
1182
- "grad_norm": 0.26441992972242784,
1183
- "learning_rate": 9.272459635990562e-05,
1184
- "loss": 0.6238,
1185
- "step": 168
1186
- },
1187
- {
1188
- "epoch": 0.5408,
1189
- "grad_norm": 0.2798821979607459,
1190
- "learning_rate": 9.168750303824084e-05,
1191
- "loss": 0.6568,
1192
- "step": 169
1193
- },
1194
- {
1195
- "epoch": 0.544,
1196
- "grad_norm": 0.2748187095456481,
1197
- "learning_rate": 9.065130924199998e-05,
1198
- "loss": 0.6068,
1199
- "step": 170
1200
- },
1201
- {
1202
- "epoch": 0.5472,
1203
- "grad_norm": 0.26830989542228445,
1204
- "learning_rate": 8.961612710146934e-05,
1205
- "loss": 0.6217,
1206
- "step": 171
1207
- },
1208
- {
1209
- "epoch": 0.5504,
1210
- "grad_norm": 0.2624748827277877,
1211
- "learning_rate": 8.858206863746018e-05,
1212
- "loss": 0.6203,
1213
- "step": 172
1214
- },
1215
- {
1216
- "epoch": 0.5536,
1217
- "grad_norm": 0.2552606780949764,
1218
- "learning_rate": 8.754924574918675e-05,
1219
- "loss": 0.5663,
1220
- "step": 173
1221
- },
1222
- {
1223
- "epoch": 0.5568,
1224
- "grad_norm": 0.2557632710956968,
1225
- "learning_rate": 8.651777020215712e-05,
1226
- "loss": 0.5918,
1227
- "step": 174
1228
- },
1229
- {
1230
- "epoch": 0.56,
1231
- "grad_norm": 0.2666361550200854,
1232
- "learning_rate": 8.548775361607872e-05,
1233
- "loss": 0.625,
1234
- "step": 175
1235
- },
1236
- {
1237
- "epoch": 0.5632,
1238
- "grad_norm": 0.2560883378063079,
1239
- "learning_rate": 8.445930745277953e-05,
1240
- "loss": 0.6032,
1241
- "step": 176
1242
- },
1243
- {
1244
- "epoch": 0.5664,
1245
- "grad_norm": 0.2583406590237059,
1246
- "learning_rate": 8.343254300414628e-05,
1247
- "loss": 0.6075,
1248
- "step": 177
1249
- },
1250
- {
1251
- "epoch": 0.5696,
1252
- "grad_norm": 0.27012077672072304,
1253
- "learning_rate": 8.240757138008149e-05,
1254
- "loss": 0.645,
1255
- "step": 178
1256
- },
1257
- {
1258
- "epoch": 0.5728,
1259
- "grad_norm": 0.2697472104569865,
1260
- "learning_rate": 8.138450349647936e-05,
1261
- "loss": 0.6357,
1262
- "step": 179
1263
- },
1264
- {
1265
- "epoch": 0.576,
1266
- "grad_norm": 0.2704698732844997,
1267
- "learning_rate": 8.036345006322359e-05,
1268
- "loss": 0.6278,
1269
- "step": 180
1270
- },
1271
- {
1272
- "epoch": 0.5792,
1273
- "grad_norm": 0.27596503294944713,
1274
- "learning_rate": 7.934452157220694e-05,
1275
- "loss": 0.655,
1276
- "step": 181
1277
- },
1278
- {
1279
- "epoch": 0.5824,
1280
- "grad_norm": 0.26527906505737747,
1281
- "learning_rate": 7.832782828537437e-05,
1282
- "loss": 0.568,
1283
- "step": 182
1284
- },
1285
- {
1286
- "epoch": 0.5856,
1287
- "grad_norm": 0.2697094402719354,
1288
- "learning_rate": 7.731348022279134e-05,
1289
- "loss": 0.6172,
1290
- "step": 183
1291
- },
1292
- {
1293
- "epoch": 0.5888,
1294
- "grad_norm": 0.2738859813879391,
1295
- "learning_rate": 7.630158715073813e-05,
1296
- "loss": 0.6275,
1297
- "step": 184
1298
- },
1299
- {
1300
- "epoch": 0.592,
1301
- "grad_norm": 0.25939271181980195,
1302
- "learning_rate": 7.52922585698315e-05,
1303
- "loss": 0.5639,
1304
- "step": 185
1305
- },
1306
- {
1307
- "epoch": 0.5952,
1308
- "grad_norm": 0.2671651992817328,
1309
- "learning_rate": 7.428560370317542e-05,
1310
- "loss": 0.5919,
1311
- "step": 186
1312
- },
1313
- {
1314
- "epoch": 0.5984,
1315
- "grad_norm": 0.2688565475090851,
1316
- "learning_rate": 7.328173148454151e-05,
1317
- "loss": 0.6312,
1318
- "step": 187
1319
- },
1320
- {
1321
- "epoch": 0.6016,
1322
- "grad_norm": 0.2784248260332949,
1323
- "learning_rate": 7.228075054658096e-05,
1324
- "loss": 0.6124,
1325
- "step": 188
1326
- },
1327
- {
1328
- "epoch": 0.6048,
1329
- "grad_norm": 0.26997057247712153,
1330
- "learning_rate": 7.1282769209069e-05,
1331
- "loss": 0.648,
1332
- "step": 189
1333
- },
1334
- {
1335
- "epoch": 0.608,
1336
- "grad_norm": 0.2707092694992218,
1337
- "learning_rate": 7.028789546718326e-05,
1338
- "loss": 0.6108,
1339
- "step": 190
1340
- },
1341
- {
1342
- "epoch": 0.6112,
1343
- "grad_norm": 0.2694317279781858,
1344
- "learning_rate": 6.929623697981718e-05,
1345
- "loss": 0.6399,
1346
- "step": 191
1347
- },
1348
- {
1349
- "epoch": 0.6144,
1350
- "grad_norm": 0.26041601563873007,
1351
- "learning_rate": 6.830790105792973e-05,
1352
- "loss": 0.5889,
1353
- "step": 192
1354
- },
1355
- {
1356
- "epoch": 0.6176,
1357
- "grad_norm": 0.25291835995919404,
1358
- "learning_rate": 6.732299465293322e-05,
1359
- "loss": 0.5911,
1360
- "step": 193
1361
- },
1362
- {
1363
- "epoch": 0.6208,
1364
- "grad_norm": 0.26551700863248473,
1365
- "learning_rate": 6.63416243451194e-05,
1366
- "loss": 0.6089,
1367
- "step": 194
1368
- },
1369
- {
1370
- "epoch": 0.624,
1371
- "grad_norm": 0.25882948329790545,
1372
- "learning_rate": 6.536389633212609e-05,
1373
- "loss": 0.6298,
1374
- "step": 195
1375
- },
1376
- {
1377
- "epoch": 0.6272,
1378
- "grad_norm": 0.2529947012716399,
1379
- "learning_rate": 6.43899164174453e-05,
1380
- "loss": 0.5914,
1381
- "step": 196
1382
- },
1383
- {
1384
- "epoch": 0.6304,
1385
- "grad_norm": 0.32497365798332417,
1386
- "learning_rate": 6.341978999897365e-05,
1387
- "loss": 0.638,
1388
- "step": 197
1389
- },
1390
- {
1391
- "epoch": 0.6336,
1392
- "grad_norm": 0.26296553022742203,
1393
- "learning_rate": 6.245362205760704e-05,
1394
- "loss": 0.6258,
1395
- "step": 198
1396
- },
1397
- {
1398
- "epoch": 0.6368,
1399
- "grad_norm": 0.2657709305402464,
1400
- "learning_rate": 6.149151714588009e-05,
1401
- "loss": 0.6495,
1402
- "step": 199
1403
- },
1404
- {
1405
- "epoch": 0.64,
1406
- "grad_norm": 0.25801033104181925,
1407
- "learning_rate": 6.053357937665237e-05,
1408
- "loss": 0.6019,
1409
- "step": 200
1410
- },
1411
- {
1412
- "epoch": 0.6432,
1413
- "grad_norm": 0.25805367525126394,
1414
- "learning_rate": 5.957991241184184e-05,
1415
- "loss": 0.5931,
1416
- "step": 201
1417
- },
1418
- {
1419
- "epoch": 0.6464,
1420
- "grad_norm": 0.26487929148998474,
1421
- "learning_rate": 5.863061945120719e-05,
1422
- "loss": 0.6711,
1423
- "step": 202
1424
- },
1425
- {
1426
- "epoch": 0.6496,
1427
- "grad_norm": 0.25255797052501494,
1428
- "learning_rate": 5.768580322118034e-05,
1429
- "loss": 0.6088,
1430
- "step": 203
1431
- },
1432
- {
1433
- "epoch": 0.6528,
1434
- "grad_norm": 0.25317945487768007,
1435
- "learning_rate": 5.6745565963749925e-05,
1436
- "loss": 0.5703,
1437
- "step": 204
1438
- },
1439
- {
1440
- "epoch": 0.656,
1441
- "grad_norm": 0.2545495908249795,
1442
- "learning_rate": 5.5810009425397294e-05,
1443
- "loss": 0.5878,
1444
- "step": 205
1445
- },
1446
- {
1447
- "epoch": 0.6592,
1448
- "grad_norm": 0.32318784276902335,
1449
- "learning_rate": 5.487923484608629e-05,
1450
- "loss": 0.6273,
1451
- "step": 206
1452
- },
1453
- {
1454
- "epoch": 0.6624,
1455
- "grad_norm": 0.25499189403717754,
1456
- "learning_rate": 5.395334294830765e-05,
1457
- "loss": 0.576,
1458
- "step": 207
1459
- },
1460
- {
1461
- "epoch": 0.6656,
1462
- "grad_norm": 0.26227335079319297,
1463
- "learning_rate": 5.3032433926179395e-05,
1464
- "loss": 0.5812,
1465
- "step": 208
1466
- },
1467
- {
1468
- "epoch": 0.6688,
1469
- "grad_norm": 0.2514697436323961,
1470
- "learning_rate": 5.211660743460458e-05,
1471
- "loss": 0.5734,
1472
- "step": 209
1473
- },
1474
- {
1475
- "epoch": 0.672,
1476
- "grad_norm": 0.27670627140391063,
1477
- "learning_rate": 5.1205962578487155e-05,
1478
- "loss": 0.6589,
1479
- "step": 210
1480
- },
1481
- {
1482
- "epoch": 0.6752,
1483
- "grad_norm": 0.26233287953524004,
1484
- "learning_rate": 5.030059790200756e-05,
1485
- "loss": 0.5956,
1486
- "step": 211
1487
- },
1488
- {
1489
- "epoch": 0.6784,
1490
- "grad_norm": 0.25899185821758536,
1491
- "learning_rate": 4.940061137795876e-05,
1492
- "loss": 0.5981,
1493
- "step": 212
1494
- },
1495
- {
1496
- "epoch": 0.6816,
1497
- "grad_norm": 0.2695534934217965,
1498
- "learning_rate": 4.850610039714444e-05,
1499
- "loss": 0.5788,
1500
- "step": 213
1501
- },
1502
- {
1503
- "epoch": 0.6848,
1504
- "grad_norm": 0.2622202021562537,
1505
- "learning_rate": 4.761716175783989e-05,
1506
- "loss": 0.6263,
1507
- "step": 214
1508
- },
1509
- {
1510
- "epoch": 0.688,
1511
- "grad_norm": 0.26561851569401834,
1512
- "learning_rate": 4.673389165531714e-05,
1513
- "loss": 0.6423,
1514
- "step": 215
1515
- },
1516
- {
1517
- "epoch": 0.6912,
1518
- "grad_norm": 0.2519941661268092,
1519
- "learning_rate": 4.585638567143529e-05,
1520
- "loss": 0.602,
1521
- "step": 216
1522
- },
1523
- {
1524
- "epoch": 0.6944,
1525
- "grad_norm": 0.2585815299560701,
1526
- "learning_rate": 4.498473876429726e-05,
1527
- "loss": 0.6187,
1528
- "step": 217
1529
- },
1530
- {
1531
- "epoch": 0.6976,
1532
- "grad_norm": 0.2579931313485816,
1533
- "learning_rate": 4.411904525797408e-05,
1534
- "loss": 0.6252,
1535
- "step": 218
1536
- },
1537
- {
1538
- "epoch": 0.7008,
1539
- "grad_norm": 0.26138279560269373,
1540
- "learning_rate": 4.325939883229766e-05,
1541
- "loss": 0.6191,
1542
- "step": 219
1543
- },
1544
- {
1545
- "epoch": 0.704,
1546
- "grad_norm": 0.2652328876562207,
1547
- "learning_rate": 4.240589251272342e-05,
1548
- "loss": 0.6341,
1549
- "step": 220
1550
- },
1551
- {
1552
- "epoch": 0.7072,
1553
- "grad_norm": 0.26814443178673353,
1554
- "learning_rate": 4.155861866026364e-05,
1555
- "loss": 0.6069,
1556
- "step": 221
1557
- },
1558
- {
1559
- "epoch": 0.7104,
1560
- "grad_norm": 0.25716580395548105,
1561
- "learning_rate": 4.071766896149273e-05,
1562
- "loss": 0.5923,
1563
- "step": 222
1564
- },
1565
- {
1566
- "epoch": 0.7136,
1567
- "grad_norm": 0.25262697851315913,
1568
- "learning_rate": 3.988313441862553e-05,
1569
- "loss": 0.598,
1570
- "step": 223
1571
- },
1572
- {
1573
- "epoch": 0.7168,
1574
- "grad_norm": 0.25536363817600527,
1575
- "learning_rate": 3.9055105339669595e-05,
1576
- "loss": 0.5786,
1577
- "step": 224
1578
- },
1579
- {
1580
- "epoch": 0.72,
1581
- "grad_norm": 0.2515414352273644,
1582
- "learning_rate": 3.823367132865265e-05,
1583
- "loss": 0.5973,
1584
- "step": 225
1585
- },
1586
- {
1587
- "epoch": 0.7232,
1588
- "grad_norm": 0.3082923451611295,
1589
- "learning_rate": 3.741892127592625e-05,
1590
- "loss": 0.5738,
1591
- "step": 226
1592
- },
1593
- {
1594
- "epoch": 0.7264,
1595
- "grad_norm": 0.2665831077382451,
1596
- "learning_rate": 3.6610943348546526e-05,
1597
- "loss": 0.6079,
1598
- "step": 227
1599
- },
1600
- {
1601
- "epoch": 0.7296,
1602
- "grad_norm": 0.2570054423385765,
1603
- "learning_rate": 3.580982498073344e-05,
1604
- "loss": 0.5884,
1605
- "step": 228
1606
- },
1607
- {
1608
- "epoch": 0.7328,
1609
- "grad_norm": 0.2764118800977991,
1610
- "learning_rate": 3.501565286440914e-05,
1611
- "loss": 0.5664,
1612
- "step": 229
1613
- },
1614
- {
1615
- "epoch": 0.736,
1616
- "grad_norm": 0.2659015981177506,
1617
- "learning_rate": 3.422851293981676e-05,
1618
- "loss": 0.5945,
1619
- "step": 230
1620
- },
1621
- {
1622
- "epoch": 0.7392,
1623
- "grad_norm": 0.25185649916492603,
1624
- "learning_rate": 3.3448490386220355e-05,
1625
- "loss": 0.5709,
1626
- "step": 231
1627
- },
1628
- {
1629
- "epoch": 0.7424,
1630
- "grad_norm": 0.26390095033023064,
1631
- "learning_rate": 3.2675669612687565e-05,
1632
- "loss": 0.5989,
1633
- "step": 232
1634
- },
1635
- {
1636
- "epoch": 0.7456,
1637
- "grad_norm": 0.2530850728794403,
1638
- "learning_rate": 3.191013424895536e-05,
1639
- "loss": 0.593,
1640
- "step": 233
1641
- },
1642
- {
1643
- "epoch": 0.7488,
1644
- "grad_norm": 0.2565488992653013,
1645
- "learning_rate": 3.115196713638e-05,
1646
- "loss": 0.5769,
1647
- "step": 234
1648
- },
1649
- {
1650
- "epoch": 0.752,
1651
- "grad_norm": 0.2611020063864013,
1652
- "learning_rate": 3.040125031897264e-05,
1653
- "loss": 0.6358,
1654
- "step": 235
1655
- },
1656
- {
1657
- "epoch": 0.7552,
1658
- "grad_norm": 0.2464939099364865,
1659
- "learning_rate": 2.9658065034520978e-05,
1660
- "loss": 0.5717,
1661
- "step": 236
1662
- },
1663
- {
1664
- "epoch": 0.7584,
1665
- "grad_norm": 0.25190580400469725,
1666
- "learning_rate": 2.892249170579826e-05,
1667
- "loss": 0.6154,
1668
- "step": 237
1669
- },
1670
- {
1671
- "epoch": 0.7616,
1672
- "grad_norm": 0.2624308866231954,
1673
- "learning_rate": 2.8194609931860316e-05,
1674
- "loss": 0.6333,
1675
- "step": 238
1676
- },
1677
- {
1678
- "epoch": 0.7648,
1679
- "grad_norm": 0.2542363438650353,
1680
- "learning_rate": 2.7474498479432087e-05,
1681
- "loss": 0.6209,
1682
- "step": 239
1683
- },
1684
- {
1685
- "epoch": 0.768,
1686
- "grad_norm": 0.25002614059735057,
1687
- "learning_rate": 2.6762235274383772e-05,
1688
- "loss": 0.5733,
1689
- "step": 240
1690
- },
1691
- {
1692
- "epoch": 0.7712,
1693
- "grad_norm": 0.2522774493843005,
1694
- "learning_rate": 2.6057897393298324e-05,
1695
- "loss": 0.5709,
1696
- "step": 241
1697
- },
1698
- {
1699
- "epoch": 0.7744,
1700
- "grad_norm": 0.2592098056140366,
1701
- "learning_rate": 2.536156105513062e-05,
1702
- "loss": 0.6038,
1703
- "step": 242
1704
- },
1705
- {
1706
- "epoch": 0.7776,
1707
- "grad_norm": 0.2545528496860185,
1708
- "learning_rate": 2.4673301612959654e-05,
1709
- "loss": 0.6015,
1710
- "step": 243
1711
- },
1712
- {
1713
- "epoch": 0.7808,
1714
- "grad_norm": 0.26574395128852707,
1715
- "learning_rate": 2.399319354583418e-05,
1716
- "loss": 0.6239,
1717
- "step": 244
1718
- },
1719
- {
1720
- "epoch": 0.784,
1721
- "grad_norm": 0.2624335087446576,
1722
- "learning_rate": 2.3321310450713062e-05,
1723
- "loss": 0.6181,
1724
- "step": 245
1725
- },
1726
- {
1727
- "epoch": 0.7872,
1728
- "grad_norm": 0.2586614704436218,
1729
- "learning_rate": 2.265772503450122e-05,
1730
- "loss": 0.6334,
1731
- "step": 246
1732
- },
1733
- {
1734
- "epoch": 0.7904,
1735
- "grad_norm": 0.31003500089156544,
1736
- "learning_rate": 2.2002509106181624e-05,
1737
- "loss": 0.6078,
1738
- "step": 247
1739
- },
1740
- {
1741
- "epoch": 0.7936,
1742
- "grad_norm": 0.24237023956212553,
1743
- "learning_rate": 2.1355733569044635e-05,
1744
- "loss": 0.5494,
1745
- "step": 248
1746
- },
1747
- {
1748
- "epoch": 0.7968,
1749
- "grad_norm": 0.2625073020569576,
1750
- "learning_rate": 2.0717468413015283e-05,
1751
- "loss": 0.6057,
1752
- "step": 249
1753
- },
1754
- {
1755
- "epoch": 0.8,
1756
- "grad_norm": 0.2539419606355253,
1757
- "learning_rate": 2.008778270707944e-05,
1758
- "loss": 0.6047,
1759
- "step": 250
1760
- },
1761
- {
1762
- "epoch": 0.8032,
1763
- "grad_norm": 0.25884298262354777,
1764
- "learning_rate": 1.946674459180955e-05,
1765
- "loss": 0.5951,
1766
- "step": 251
1767
- },
1768
- {
1769
- "epoch": 0.8064,
1770
- "grad_norm": 0.2660197122315272,
1771
- "learning_rate": 1.8854421271990964e-05,
1772
- "loss": 0.6259,
1773
- "step": 252
1774
- },
1775
- {
1776
- "epoch": 0.8096,
1777
- "grad_norm": 0.25655988921277334,
1778
- "learning_rate": 1.8250879009349398e-05,
1779
- "loss": 0.568,
1780
- "step": 253
1781
- },
1782
- {
1783
- "epoch": 0.8128,
1784
- "grad_norm": 0.2457259860690368,
1785
- "learning_rate": 1.7656183115380577e-05,
1786
- "loss": 0.5566,
1787
- "step": 254
1788
- },
1789
- {
1790
- "epoch": 0.816,
1791
- "grad_norm": 0.2647745370183451,
1792
- "learning_rate": 1.707039794428259e-05,
1793
- "loss": 0.6137,
1794
- "step": 255
1795
- },
1796
- {
1797
- "epoch": 0.8192,
1798
- "grad_norm": 0.2526743886541512,
1799
- "learning_rate": 1.649358688599191e-05,
1800
- "loss": 0.5973,
1801
- "step": 256
1802
- },
1803
- {
1804
- "epoch": 0.8224,
1805
- "grad_norm": 0.26287332654405005,
1806
- "learning_rate": 1.5925812359323745e-05,
1807
- "loss": 0.5934,
1808
- "step": 257
1809
- },
1810
- {
1811
- "epoch": 0.8256,
1812
- "grad_norm": 0.2614410753690634,
1813
- "learning_rate": 1.5367135805217458e-05,
1814
- "loss": 0.6114,
1815
- "step": 258
1816
- },
1817
- {
1818
- "epoch": 0.8288,
1819
- "grad_norm": 0.259783723422659,
1820
- "learning_rate": 1.4817617680087825e-05,
1821
- "loss": 0.5961,
1822
- "step": 259
1823
- },
1824
- {
1825
- "epoch": 0.832,
1826
- "grad_norm": 0.24965207576444098,
1827
- "learning_rate": 1.4277317449282834e-05,
1828
- "loss": 0.5706,
1829
- "step": 260
1830
- },
1831
- {
1832
- "epoch": 0.8352,
1833
- "grad_norm": 0.2958426590398693,
1834
- "learning_rate": 1.3746293580648717e-05,
1835
- "loss": 0.6272,
1836
- "step": 261
1837
- },
1838
- {
1839
- "epoch": 0.8384,
1840
- "grad_norm": 0.25258297001548335,
1841
- "learning_rate": 1.3224603538202929e-05,
1842
- "loss": 0.6006,
1843
- "step": 262
1844
- },
1845
- {
1846
- "epoch": 0.8416,
1847
- "grad_norm": 0.2611674989165653,
1848
- "learning_rate": 1.2712303775915802e-05,
1849
- "loss": 0.6272,
1850
- "step": 263
1851
- },
1852
- {
1853
- "epoch": 0.8448,
1854
- "grad_norm": 0.25524659220422524,
1855
- "learning_rate": 1.220944973160133e-05,
1856
- "loss": 0.6174,
1857
- "step": 264
1858
- },
1859
- {
1860
- "epoch": 0.848,
1861
- "grad_norm": 0.2575177709932516,
1862
- "learning_rate": 1.1716095820918216e-05,
1863
- "loss": 0.5956,
1864
- "step": 265
1865
- },
1866
- {
1867
- "epoch": 0.8512,
1868
- "grad_norm": 0.2561395979203794,
1869
- "learning_rate": 1.1232295431481222e-05,
1870
- "loss": 0.5667,
1871
- "step": 266
1872
- },
1873
- {
1874
- "epoch": 0.8544,
1875
- "grad_norm": 0.25141728122486434,
1876
- "learning_rate": 1.0758100917083991e-05,
1877
- "loss": 0.572,
1878
- "step": 267
1879
- },
1880
- {
1881
- "epoch": 0.8576,
1882
- "grad_norm": 0.25964673762588375,
1883
- "learning_rate": 1.0293563592033595e-05,
1884
- "loss": 0.6372,
1885
- "step": 268
1886
- },
1887
- {
1888
- "epoch": 0.8608,
1889
- "grad_norm": 0.256690467072949,
1890
- "learning_rate": 9.838733725597615e-06,
1891
- "loss": 0.5884,
1892
- "step": 269
1893
- },
1894
- {
1895
- "epoch": 0.864,
1896
- "grad_norm": 0.2605600488715863,
1897
- "learning_rate": 9.393660536564408e-06,
1898
- "loss": 0.6151,
1899
- "step": 270
1900
- },
1901
- {
1902
- "epoch": 0.8672,
1903
- "grad_norm": 0.2520719685895574,
1904
- "learning_rate": 8.958392187916841e-06,
1905
- "loss": 0.586,
1906
- "step": 271
1907
- },
1908
- {
1909
- "epoch": 0.8704,
1910
- "grad_norm": 0.2544316858533973,
1911
- "learning_rate": 8.532975781620512e-06,
1912
- "loss": 0.5852,
1913
- "step": 272
1914
- },
1915
- {
1916
- "epoch": 0.8736,
1917
- "grad_norm": 0.25086193401636275,
1918
- "learning_rate": 8.117457353526625e-06,
1919
- "loss": 0.545,
1920
- "step": 273
1921
- },
1922
- {
1923
- "epoch": 0.8768,
1924
- "grad_norm": 0.2717178693247369,
1925
- "learning_rate": 7.711881868390291e-06,
1926
- "loss": 0.6135,
1927
- "step": 274
1928
- },
1929
- {
1930
- "epoch": 0.88,
1931
- "grad_norm": 0.26446663858778996,
1932
- "learning_rate": 7.3162932150046885e-06,
1933
- "loss": 0.654,
1934
- "step": 275
1935
- },
1936
- {
1937
- "epoch": 0.8832,
1938
- "grad_norm": 0.25710288834015854,
1939
- "learning_rate": 6.930734201451816e-06,
1940
- "loss": 0.6077,
1941
- "step": 276
1942
- },
1943
- {
1944
- "epoch": 0.8864,
1945
- "grad_norm": 0.2614053987061522,
1946
- "learning_rate": 6.555246550469907e-06,
1947
- "loss": 0.5887,
1948
- "step": 277
1949
- },
1950
- {
1951
- "epoch": 0.8896,
1952
- "grad_norm": 0.25803580837193296,
1953
- "learning_rate": 6.189870894938587e-06,
1954
- "loss": 0.5922,
1955
- "step": 278
1956
- },
1957
- {
1958
- "epoch": 0.8928,
1959
- "grad_norm": 0.25650163916574076,
1960
- "learning_rate": 5.834646773481811e-06,
1961
- "loss": 0.583,
1962
- "step": 279
1963
- },
1964
- {
1965
- "epoch": 0.896,
1966
- "grad_norm": 0.25422924226179444,
1967
- "learning_rate": 5.489612626189245e-06,
1968
- "loss": 0.5697,
1969
- "step": 280
1970
- },
1971
- {
1972
- "epoch": 0.8992,
1973
- "grad_norm": 0.24957575142600866,
1974
- "learning_rate": 5.154805790456485e-06,
1975
- "loss": 0.5912,
1976
- "step": 281
1977
- },
1978
- {
1979
- "epoch": 0.9024,
1980
- "grad_norm": 0.2515411538551669,
1981
- "learning_rate": 4.830262496944693e-06,
1982
- "loss": 0.5846,
1983
- "step": 282
1984
- },
1985
- {
1986
- "epoch": 0.9056,
1987
- "grad_norm": 0.2601071856992811,
1988
- "learning_rate": 4.516017865659949e-06,
1989
- "loss": 0.5616,
1990
- "step": 283
1991
- },
1992
- {
1993
- "epoch": 0.9088,
1994
- "grad_norm": 0.2639229721318898,
1995
- "learning_rate": 4.21210590215273e-06,
1996
- "loss": 0.6368,
1997
- "step": 284
1998
- },
1999
- {
2000
- "epoch": 0.912,
2001
- "grad_norm": 0.24857817483163056,
2002
- "learning_rate": 3.918559493838114e-06,
2003
- "loss": 0.5593,
2004
- "step": 285
2005
- },
2006
- {
2007
- "epoch": 0.9152,
2008
- "grad_norm": 0.2810784592988802,
2009
- "learning_rate": 3.6354104064368566e-06,
2010
- "loss": 0.7009,
2011
- "step": 286
2012
- },
2013
- {
2014
- "epoch": 0.9184,
2015
- "grad_norm": 0.25502077384196564,
2016
- "learning_rate": 3.3626892805379562e-06,
2017
- "loss": 0.5788,
2018
- "step": 287
2019
- },
2020
- {
2021
- "epoch": 0.9216,
2022
- "grad_norm": 0.24704174727298683,
2023
- "learning_rate": 3.100425628282899e-06,
2024
- "loss": 0.5657,
2025
- "step": 288
2026
- },
2027
- {
2028
- "epoch": 0.9248,
2029
- "grad_norm": 0.26397141045569056,
2030
- "learning_rate": 2.848647830172024e-06,
2031
- "loss": 0.6363,
2032
- "step": 289
2033
- },
2034
- {
2035
- "epoch": 0.928,
2036
- "grad_norm": 0.2524305059499819,
2037
- "learning_rate": 2.607383131993424e-06,
2038
- "loss": 0.5921,
2039
- "step": 290
2040
- },
2041
- {
2042
- "epoch": 0.9312,
2043
- "grad_norm": 0.2697223617632766,
2044
- "learning_rate": 2.3766576418745022e-06,
2045
- "loss": 0.6327,
2046
- "step": 291
2047
- },
2048
- {
2049
- "epoch": 0.9344,
2050
- "grad_norm": 0.26555534553448457,
2051
- "learning_rate": 2.1564963274568027e-06,
2052
- "loss": 0.608,
2053
- "step": 292
2054
- },
2055
- {
2056
- "epoch": 0.9376,
2057
- "grad_norm": 0.25409868011892073,
2058
- "learning_rate": 1.9469230131940907e-06,
2059
- "loss": 0.5747,
2060
- "step": 293
2061
- },
2062
- {
2063
- "epoch": 0.9408,
2064
- "grad_norm": 0.252487846427678,
2065
- "learning_rate": 1.7479603777742938e-06,
2066
- "loss": 0.5735,
2067
- "step": 294
2068
- },
2069
- {
2070
- "epoch": 0.944,
2071
- "grad_norm": 0.2571510334874647,
2072
- "learning_rate": 1.559629951665298e-06,
2073
- "loss": 0.5865,
2074
- "step": 295
2075
- },
2076
- {
2077
- "epoch": 0.9472,
2078
- "grad_norm": 0.4760901811369371,
2079
- "learning_rate": 1.3819521147851123e-06,
2080
- "loss": 0.542,
2081
- "step": 296
2082
- },
2083
- {
2084
- "epoch": 0.9504,
2085
- "grad_norm": 0.26372826176481556,
2086
- "learning_rate": 1.2149460942964098e-06,
2087
- "loss": 0.5884,
2088
- "step": 297
2089
- },
2090
- {
2091
- "epoch": 0.9536,
2092
- "grad_norm": 0.26175507028814576,
2093
- "learning_rate": 1.05862996252597e-06,
2094
- "loss": 0.6167,
2095
- "step": 298
2096
- },
2097
- {
2098
- "epoch": 0.9568,
2099
- "grad_norm": 0.26047362323447143,
2100
- "learning_rate": 9.130206350089765e-07,
2101
- "loss": 0.6128,
2102
- "step": 299
2103
- },
2104
- {
2105
- "epoch": 0.96,
2106
- "grad_norm": 0.2454540274824027,
2107
- "learning_rate": 7.781338686584927e-07,
2108
- "loss": 0.5388,
2109
- "step": 300
2110
- },
2111
- {
2112
- "epoch": 0.9632,
2113
- "grad_norm": 0.2476784963430826,
2114
- "learning_rate": 6.539842600603918e-07,
2115
- "loss": 0.5393,
2116
- "step": 301
2117
- },
2118
- {
2119
- "epoch": 0.9664,
2120
- "grad_norm": 0.24671440407493223,
2121
- "learning_rate": 5.405852438937764e-07,
2122
- "loss": 0.5966,
2123
- "step": 302
2124
- },
2125
- {
2126
- "epoch": 0.9696,
2127
- "grad_norm": 0.2571397406086264,
2128
- "learning_rate": 4.3794909147720773e-07,
2129
- "loss": 0.6121,
2130
- "step": 303
2131
- },
2132
- {
2133
- "epoch": 0.9728,
2134
- "grad_norm": 0.2895940448351629,
2135
- "learning_rate": 3.4608690944071263e-07,
2136
- "loss": 0.5805,
2137
- "step": 304
2138
- },
2139
- {
2140
- "epoch": 0.976,
2141
- "grad_norm": 0.27720052526167127,
2142
- "learning_rate": 2.6500863852395584e-07,
2143
- "loss": 0.6128,
2144
- "step": 305
2145
- },
2146
- {
2147
- "epoch": 0.9792,
2148
- "grad_norm": 0.2602744150458922,
2149
- "learning_rate": 1.947230525005006e-07,
2150
- "loss": 0.6157,
2151
- "step": 306
2152
- },
2153
- {
2154
- "epoch": 0.9824,
2155
- "grad_norm": 0.2565662022949563,
2156
- "learning_rate": 1.3523775722834587e-07,
2157
- "loss": 0.616,
2158
- "step": 307
2159
- },
2160
- {
2161
- "epoch": 0.9856,
2162
- "grad_norm": 0.2562137901406146,
2163
- "learning_rate": 8.655918982689581e-08,
2164
- "loss": 0.6134,
2165
- "step": 308
2166
- },
2167
- {
2168
- "epoch": 0.9888,
2169
- "grad_norm": 0.2525816370267746,
2170
- "learning_rate": 4.8692617980350406e-08,
2171
- "loss": 0.5834,
2172
- "step": 309
2173
- },
2174
- {
2175
- "epoch": 0.992,
2176
- "grad_norm": 0.2528167501756759,
2177
- "learning_rate": 2.164213936770576e-08,
2178
- "loss": 0.5784,
2179
- "step": 310
2180
- },
2181
- {
2182
- "epoch": 0.9952,
2183
- "grad_norm": 0.2557747985616951,
2184
- "learning_rate": 5.410681219286673e-09,
2185
- "loss": 0.6049,
2186
- "step": 311
2187
- },
2188
- {
2189
- "epoch": 0.9984,
2190
- "grad_norm": 0.2608436955663202,
2191
- "learning_rate": 0.0,
2192
- "loss": 0.5618,
2193
- "step": 312
2194
- },
2195
- {
2196
- "epoch": 0.9984,
2197
- "step": 312,
2198
- "total_flos": 185984439222272.0,
2199
- "train_loss": 0.6505028414420593,
2200
- "train_runtime": 4096.0965,
2201
- "train_samples_per_second": 1.221,
2202
- "train_steps_per_second": 0.076
2203
- }
2204
- ],
2205
- "logging_steps": 1.0,
2206
- "max_steps": 312,
2207
- "num_input_tokens_seen": 0,
2208
- "num_train_epochs": 1,
2209
- "save_steps": 500,
2210
- "stateful_callbacks": {
2211
- "TrainerControl": {
2212
- "args": {
2213
- "should_epoch_stop": false,
2214
- "should_evaluate": false,
2215
- "should_log": false,
2216
- "should_save": false,
2217
- "should_training_stop": false
2218
- },
2219
- "attributes": {}
2220
- }
2221
- },
2222
- "total_flos": 185984439222272.0,
2223
- "train_batch_size": 8,
2224
- "trial_name": null,
2225
- "trial_params": null
2226
- }