terry69 commited on
Commit
6fbd468
1 Parent(s): 8b82d94

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ datasets:
9
+ - generator
10
+ model-index:
11
+ - name: feedback_p0.1_seed42_level2_stylemix
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # feedback_p0.1_seed42_level2_stylemix
19
+
20
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3047
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 4
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 32
49
+ - total_eval_batch_size: 4
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: cosine
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - num_epochs: 1
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss |
58
+ |:-------------:|:------:|:----:|:---------------:|
59
+ | 0.3534 | 0.9995 | 935 | 0.3047 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.43.4
65
+ - Pytorch 2.3.1+cu121
66
+ - Datasets 2.19.1
67
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9994655264564404,
3
+ "total_flos": 195717633146880.0,
4
+ "train_loss": 0.5211284054791864,
5
+ "train_runtime": 23277.081,
6
+ "train_samples": 98952,
7
+ "train_samples_per_second": 1.286,
8
+ "train_steps_per_second": 0.04
9
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.4"
6
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9994655264564404,
3
+ "total_flos": 195717633146880.0,
4
+ "train_loss": 0.5211284054791864,
5
+ "train_runtime": 23277.081,
6
+ "train_samples": 98952,
7
+ "train_samples_per_second": 1.286,
8
+ "train_steps_per_second": 0.04
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9994655264564404,
5
+ "eval_steps": 500,
6
+ "global_step": 935,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010689470871191875,
13
+ "grad_norm": 23.473513373152795,
14
+ "learning_rate": 1.0638297872340426e-07,
15
+ "loss": 1.353,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.005344735435595938,
20
+ "grad_norm": 21.711768425322266,
21
+ "learning_rate": 5.319148936170213e-07,
22
+ "loss": 1.3519,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.010689470871191877,
27
+ "grad_norm": 8.713068756520672,
28
+ "learning_rate": 1.0638297872340427e-06,
29
+ "loss": 1.2088,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.016034206306787813,
34
+ "grad_norm": 8.310866409645099,
35
+ "learning_rate": 1.595744680851064e-06,
36
+ "loss": 1.0635,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.021378941742383754,
41
+ "grad_norm": 3.066210523084854,
42
+ "learning_rate": 2.1276595744680853e-06,
43
+ "loss": 0.9417,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.02672367717797969,
48
+ "grad_norm": 2.493239812049204,
49
+ "learning_rate": 2.6595744680851065e-06,
50
+ "loss": 0.8884,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.032068412613575625,
55
+ "grad_norm": 2.403610159527061,
56
+ "learning_rate": 3.191489361702128e-06,
57
+ "loss": 0.8557,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.03741314804917156,
62
+ "grad_norm": 2.3974276447793694,
63
+ "learning_rate": 3.723404255319149e-06,
64
+ "loss": 0.8349,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.04275788348476751,
69
+ "grad_norm": 2.2921630085655025,
70
+ "learning_rate": 4.255319148936171e-06,
71
+ "loss": 0.8163,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.048102618920363445,
76
+ "grad_norm": 2.3116910060192817,
77
+ "learning_rate": 4.787234042553192e-06,
78
+ "loss": 0.798,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.05344735435595938,
83
+ "grad_norm": 2.242005189567634,
84
+ "learning_rate": 5.319148936170213e-06,
85
+ "loss": 0.7863,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05879208979155532,
90
+ "grad_norm": 2.536220362549579,
91
+ "learning_rate": 5.851063829787235e-06,
92
+ "loss": 0.7663,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.06413682522715125,
97
+ "grad_norm": 2.492174958150876,
98
+ "learning_rate": 6.382978723404256e-06,
99
+ "loss": 0.7579,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.06948156066274719,
104
+ "grad_norm": 2.3311723974999095,
105
+ "learning_rate": 6.914893617021278e-06,
106
+ "loss": 0.7397,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.07482629609834313,
111
+ "grad_norm": 2.5040282086769317,
112
+ "learning_rate": 7.446808510638298e-06,
113
+ "loss": 0.7338,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.08017103153393906,
118
+ "grad_norm": 2.411086582278843,
119
+ "learning_rate": 7.97872340425532e-06,
120
+ "loss": 0.7215,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.08551576696953501,
125
+ "grad_norm": 2.3433794783119883,
126
+ "learning_rate": 8.510638297872341e-06,
127
+ "loss": 0.7124,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.09086050240513095,
132
+ "grad_norm": 2.354225850924038,
133
+ "learning_rate": 9.042553191489362e-06,
134
+ "loss": 0.7177,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.09620523784072689,
139
+ "grad_norm": 2.4091177426727266,
140
+ "learning_rate": 9.574468085106385e-06,
141
+ "loss": 0.7163,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.10154997327632283,
146
+ "grad_norm": 2.498651758504887,
147
+ "learning_rate": 9.999965114314806e-06,
148
+ "loss": 0.7031,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.10689470871191876,
153
+ "grad_norm": 2.423896856776365,
154
+ "learning_rate": 9.998744166446685e-06,
155
+ "loss": 0.7005,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.1122394441475147,
160
+ "grad_norm": 2.387782305227773,
161
+ "learning_rate": 9.995779421092695e-06,
162
+ "loss": 0.6846,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.11758417958311064,
167
+ "grad_norm": 2.424890050569407,
168
+ "learning_rate": 9.991071912495701e-06,
169
+ "loss": 0.7027,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.12292891501870658,
174
+ "grad_norm": 2.115700167815373,
175
+ "learning_rate": 9.984623282856502e-06,
176
+ "loss": 0.6923,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.1282736504543025,
181
+ "grad_norm": 2.0709758825284363,
182
+ "learning_rate": 9.97643578176095e-06,
183
+ "loss": 0.6859,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.13361838588989844,
188
+ "grad_norm": 2.1305031798421186,
189
+ "learning_rate": 9.966512265395188e-06,
190
+ "loss": 0.6846,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.13896312132549438,
195
+ "grad_norm": 2.0044100900913384,
196
+ "learning_rate": 9.95485619554928e-06,
197
+ "loss": 0.6799,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.14430785676109031,
202
+ "grad_norm": 2.050948697307653,
203
+ "learning_rate": 9.941471638409576e-06,
204
+ "loss": 0.6767,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.14965259219668625,
209
+ "grad_norm": 1.952049269951998,
210
+ "learning_rate": 9.926363263140234e-06,
211
+ "loss": 0.6669,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.1549973276322822,
216
+ "grad_norm": 2.099731647032975,
217
+ "learning_rate": 9.90953634025439e-06,
218
+ "loss": 0.6786,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.16034206306787813,
223
+ "grad_norm": 1.993767696614697,
224
+ "learning_rate": 9.890996739775562e-06,
225
+ "loss": 0.6674,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.16568679850347406,
230
+ "grad_norm": 2.0517367712519503,
231
+ "learning_rate": 9.870750929189914e-06,
232
+ "loss": 0.6748,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.17103153393907003,
237
+ "grad_norm": 2.0491814339157486,
238
+ "learning_rate": 9.848805971190074e-06,
239
+ "loss": 0.6621,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.17637626937466597,
244
+ "grad_norm": 2.0777487120565397,
245
+ "learning_rate": 9.825169521211354e-06,
246
+ "loss": 0.6543,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.1817210048102619,
251
+ "grad_norm": 2.351975397829705,
252
+ "learning_rate": 9.799849824761159e-06,
253
+ "loss": 0.6552,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.18706574024585784,
258
+ "grad_norm": 2.0302930695761034,
259
+ "learning_rate": 9.772855714542569e-06,
260
+ "loss": 0.6525,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.19241047568145378,
265
+ "grad_norm": 2.188255761505827,
266
+ "learning_rate": 9.744196607373086e-06,
267
+ "loss": 0.6512,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.19775521111704972,
272
+ "grad_norm": 2.1631601855326763,
273
+ "learning_rate": 9.71388250089959e-06,
274
+ "loss": 0.6506,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.20309994655264565,
279
+ "grad_norm": 2.041485612804426,
280
+ "learning_rate": 9.681923970110698e-06,
281
+ "loss": 0.6402,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.2084446819882416,
286
+ "grad_norm": 2.1331611096395973,
287
+ "learning_rate": 9.648332163647705e-06,
288
+ "loss": 0.6234,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.21378941742383753,
293
+ "grad_norm": 2.076285244795538,
294
+ "learning_rate": 9.613118799915417e-06,
295
+ "loss": 0.6422,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.21913415285943347,
300
+ "grad_norm": 1.9966049947480653,
301
+ "learning_rate": 9.576296162994214e-06,
302
+ "loss": 0.62,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.2244788882950294,
307
+ "grad_norm": 2.003867139711824,
308
+ "learning_rate": 9.537877098354787e-06,
309
+ "loss": 0.6431,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.22982362373062534,
314
+ "grad_norm": 1.9196987285290612,
315
+ "learning_rate": 9.497875008377033e-06,
316
+ "loss": 0.6234,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.23516835916622128,
321
+ "grad_norm": 2.1957665769389774,
322
+ "learning_rate": 9.456303847674674e-06,
323
+ "loss": 0.6256,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.24051309460181722,
328
+ "grad_norm": 1.884124911991183,
329
+ "learning_rate": 9.41317811822723e-06,
330
+ "loss": 0.6052,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.24585783003741316,
335
+ "grad_norm": 1.9253697770132223,
336
+ "learning_rate": 9.36851286432104e-06,
337
+ "loss": 0.6228,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.25120256547300907,
342
+ "grad_norm": 1.8020291089671914,
343
+ "learning_rate": 9.322323667301113e-06,
344
+ "loss": 0.6191,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.256547300908605,
349
+ "grad_norm": 1.9107218407751854,
350
+ "learning_rate": 9.274626640135616e-06,
351
+ "loss": 0.6121,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.26189203634420094,
356
+ "grad_norm": 1.8979104758577288,
357
+ "learning_rate": 9.225438421794919e-06,
358
+ "loss": 0.616,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.2672367717797969,
363
+ "grad_norm": 1.9569646424906317,
364
+ "learning_rate": 9.174776171447126e-06,
365
+ "loss": 0.6047,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.2725815072153928,
370
+ "grad_norm": 2.0364213519267715,
371
+ "learning_rate": 9.12265756247216e-06,
372
+ "loss": 0.6093,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.27792624265098875,
377
+ "grad_norm": 1.9725707409017998,
378
+ "learning_rate": 9.06910077629645e-06,
379
+ "loss": 0.599,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.2832709780865847,
384
+ "grad_norm": 1.9492899906874035,
385
+ "learning_rate": 9.014124496050391e-06,
386
+ "loss": 0.5902,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.28861571352218063,
391
+ "grad_norm": 2.174543196329182,
392
+ "learning_rate": 8.957747900050797e-06,
393
+ "loss": 0.5937,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.29396044895777657,
398
+ "grad_norm": 2.4160108027006615,
399
+ "learning_rate": 8.899990655110586e-06,
400
+ "loss": 0.6018,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.2993051843933725,
405
+ "grad_norm": 2.087978454933178,
406
+ "learning_rate": 8.840872909678081e-06,
407
+ "loss": 0.5832,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.30464991982896844,
412
+ "grad_norm": 1.9762659778049954,
413
+ "learning_rate": 8.780415286808284e-06,
414
+ "loss": 0.5922,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3099946552645644,
419
+ "grad_norm": 2.269903050974625,
420
+ "learning_rate": 8.718638876968564e-06,
421
+ "loss": 0.587,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.3153393907001603,
426
+ "grad_norm": 2.0490480592368043,
427
+ "learning_rate": 8.655565230681329e-06,
428
+ "loss": 0.5748,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.32068412613575625,
433
+ "grad_norm": 2.2764533528101167,
434
+ "learning_rate": 8.591216351006181e-06,
435
+ "loss": 0.575,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.3260288615713522,
440
+ "grad_norm": 2.0737769584580072,
441
+ "learning_rate": 8.525614685864209e-06,
442
+ "loss": 0.5716,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.33137359700694813,
447
+ "grad_norm": 1.9102889564355032,
448
+ "learning_rate": 8.458783120207099e-06,
449
+ "loss": 0.5686,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3367183324425441,
454
+ "grad_norm": 1.8800981653614064,
455
+ "learning_rate": 8.390744968033785e-06,
456
+ "loss": 0.5629,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.34206306787814006,
461
+ "grad_norm": 1.96332588340258,
462
+ "learning_rate": 8.321523964257431e-06,
463
+ "loss": 0.5657,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.347407803313736,
468
+ "grad_norm": 1.9485967093770373,
469
+ "learning_rate": 8.251144256425562e-06,
470
+ "loss": 0.575,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.35275253874933193,
475
+ "grad_norm": 1.929135934757674,
476
+ "learning_rate": 8.179630396296285e-06,
477
+ "loss": 0.5632,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.35809727418492787,
482
+ "grad_norm": 1.9559096020055298,
483
+ "learning_rate": 8.107007331273449e-06,
484
+ "loss": 0.5626,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.3634420096205238,
489
+ "grad_norm": 2.012794105136495,
490
+ "learning_rate": 8.033300395703845e-06,
491
+ "loss": 0.5546,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.36878674505611975,
496
+ "grad_norm": 1.9997480665852025,
497
+ "learning_rate": 7.958535302039368e-06,
498
+ "loss": 0.5458,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.3741314804917157,
503
+ "grad_norm": 1.8451676891383395,
504
+ "learning_rate": 7.88273813186732e-06,
505
+ "loss": 0.5483,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.3794762159273116,
510
+ "grad_norm": 1.895313478955964,
511
+ "learning_rate": 7.805935326811913e-06,
512
+ "loss": 0.5517,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.38482095136290756,
517
+ "grad_norm": 1.9301374165518745,
518
+ "learning_rate": 7.728153679310186e-06,
519
+ "loss": 0.5464,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.3901656867985035,
524
+ "grad_norm": 2.014621013972388,
525
+ "learning_rate": 7.649420323265547e-06,
526
+ "loss": 0.5441,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.39551042223409943,
531
+ "grad_norm": 1.9682365332357328,
532
+ "learning_rate": 7.569762724582179e-06,
533
+ "loss": 0.5247,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.40085515766969537,
538
+ "grad_norm": 1.9950047285262882,
539
+ "learning_rate": 7.48920867158365e-06,
540
+ "loss": 0.5435,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.4061998931052913,
545
+ "grad_norm": 1.8591367525423361,
546
+ "learning_rate": 7.407786265319023e-06,
547
+ "loss": 0.5363,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.41154462854088725,
552
+ "grad_norm": 2.038203032181739,
553
+ "learning_rate": 7.325523909759902e-06,
554
+ "loss": 0.5312,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4168893639764832,
559
+ "grad_norm": 2.1300865254144856,
560
+ "learning_rate": 7.242450301891772e-06,
561
+ "loss": 0.5257,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.4222340994120791,
566
+ "grad_norm": 1.882363933745456,
567
+ "learning_rate": 7.158594421703152e-06,
568
+ "loss": 0.5096,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.42757883484767506,
573
+ "grad_norm": 1.8727951959035394,
574
+ "learning_rate": 7.073985522076001e-06,
575
+ "loss": 0.5184,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.432923570283271,
580
+ "grad_norm": 1.9894963218262207,
581
+ "learning_rate": 6.9886531185809385e-06,
582
+ "loss": 0.5259,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.43826830571886694,
587
+ "grad_norm": 2.0264734474019854,
588
+ "learning_rate": 6.902626979180821e-06,
589
+ "loss": 0.5287,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.4436130411544629,
594
+ "grad_norm": 1.8722413198751242,
595
+ "learning_rate": 6.8159371138462745e-06,
596
+ "loss": 0.5203,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.4489577765900588,
601
+ "grad_norm": 1.9496986261286822,
602
+ "learning_rate": 6.728613764086806e-06,
603
+ "loss": 0.5117,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.45430251202565475,
608
+ "grad_norm": 1.9774605540105135,
609
+ "learning_rate": 6.640687392401132e-06,
610
+ "loss": 0.5031,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.4596472474612507,
615
+ "grad_norm": 1.954818070964011,
616
+ "learning_rate": 6.552188671650434e-06,
617
+ "loss": 0.5031,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.4649919828968466,
622
+ "grad_norm": 1.9617332949799173,
623
+ "learning_rate": 6.46314847435821e-06,
624
+ "loss": 0.5066,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.47033671833244256,
629
+ "grad_norm": 2.004929689013094,
630
+ "learning_rate": 6.373597861940488e-06,
631
+ "loss": 0.4988,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.4756814537680385,
636
+ "grad_norm": 1.9774178895562935,
637
+ "learning_rate": 6.283568073870147e-06,
638
+ "loss": 0.4975,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.48102618920363444,
643
+ "grad_norm": 1.9264282288547034,
644
+ "learning_rate": 6.1930905167791025e-06,
645
+ "loss": 0.4995,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.4863709246392304,
650
+ "grad_norm": 1.8764137691966425,
651
+ "learning_rate": 6.102196753502202e-06,
652
+ "loss": 0.4808,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.4917156600748263,
657
+ "grad_norm": 2.050651493580463,
658
+ "learning_rate": 6.010918492066628e-06,
659
+ "loss": 0.482,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.49706039551042225,
664
+ "grad_norm": 1.9228723322188161,
665
+ "learning_rate": 5.919287574630628e-06,
666
+ "loss": 0.4843,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5024051309460181,
671
+ "grad_norm": 1.9851687404052978,
672
+ "learning_rate": 5.827335966375485e-06,
673
+ "loss": 0.4894,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5077498663816141,
678
+ "grad_norm": 1.9039931208460692,
679
+ "learning_rate": 5.735095744354543e-06,
680
+ "loss": 0.4673,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.51309460181721,
685
+ "grad_norm": 1.9780097627545055,
686
+ "learning_rate": 5.642599086303233e-06,
687
+ "loss": 0.4788,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.518439337252806,
692
+ "grad_norm": 2.0794416013824994,
693
+ "learning_rate": 5.5498782594139476e-06,
694
+ "loss": 0.4662,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5237840726884019,
699
+ "grad_norm": 1.9483487482401622,
700
+ "learning_rate": 5.456965609079741e-06,
701
+ "loss": 0.4763,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.5291288081239979,
706
+ "grad_norm": 1.8945000444925455,
707
+ "learning_rate": 5.363893547610715e-06,
708
+ "loss": 0.4807,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.5344735435595938,
713
+ "grad_norm": 1.9768379335510178,
714
+ "learning_rate": 5.270694542927089e-06,
715
+ "loss": 0.4803,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5398182789951897,
720
+ "grad_norm": 1.9758527545184905,
721
+ "learning_rate": 5.1774011072328575e-06,
722
+ "loss": 0.4627,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5451630144307856,
727
+ "grad_norm": 1.866392771665028,
728
+ "learning_rate": 5.084045785674001e-06,
729
+ "loss": 0.4608,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5505077498663816,
734
+ "grad_norm": 1.957078999847815,
735
+ "learning_rate": 4.9906611449852035e-06,
736
+ "loss": 0.4542,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5558524853019775,
741
+ "grad_norm": 1.9342632236304118,
742
+ "learning_rate": 4.897279762129044e-06,
743
+ "loss": 0.4547,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5611972207375735,
748
+ "grad_norm": 1.966938473585663,
749
+ "learning_rate": 4.8039342129316175e-06,
750
+ "loss": 0.4526,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5665419561731694,
755
+ "grad_norm": 1.9823937668875962,
756
+ "learning_rate": 4.710657060718547e-06,
757
+ "loss": 0.4503,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.5718866916087654,
762
+ "grad_norm": 1.931604909577632,
763
+ "learning_rate": 4.617480844955367e-06,
764
+ "loss": 0.4543,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.5772314270443613,
769
+ "grad_norm": 1.9170992207978994,
770
+ "learning_rate": 4.52443806989622e-06,
771
+ "loss": 0.4383,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.5825761624799572,
776
+ "grad_norm": 1.9043676805575804,
777
+ "learning_rate": 4.431561193244852e-06,
778
+ "loss": 0.4546,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5879208979155531,
783
+ "grad_norm": 1.9233137290689744,
784
+ "learning_rate": 4.338882614831817e-06,
785
+ "loss": 0.446,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.5932656333511491,
790
+ "grad_norm": 1.8515724013719734,
791
+ "learning_rate": 4.246434665311907e-06,
792
+ "loss": 0.4321,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.598610368786745,
797
+ "grad_norm": 1.8828506758113701,
798
+ "learning_rate": 4.154249594885687e-06,
799
+ "loss": 0.4337,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.603955104222341,
804
+ "grad_norm": 1.9687942950195187,
805
+ "learning_rate": 4.062359562049109e-06,
806
+ "loss": 0.431,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6092998396579369,
811
+ "grad_norm": 1.8995143280590803,
812
+ "learning_rate": 3.970796622375116e-06,
813
+ "loss": 0.4405,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.6146445750935329,
818
+ "grad_norm": 1.8557131453687543,
819
+ "learning_rate": 3.879592717331141e-06,
820
+ "loss": 0.4283,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.6199893105291288,
825
+ "grad_norm": 1.9309890578975801,
826
+ "learning_rate": 3.78877966313642e-06,
827
+ "loss": 0.4367,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6253340459647247,
832
+ "grad_norm": 1.973985583949257,
833
+ "learning_rate": 3.698389139663003e-06,
834
+ "loss": 0.4324,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.6306787814003206,
839
+ "grad_norm": 1.8679236635919254,
840
+ "learning_rate": 3.608452679384311e-06,
841
+ "loss": 0.4289,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.6360235168359166,
846
+ "grad_norm": 1.827491182434645,
847
+ "learning_rate": 3.5190016563751316e-06,
848
+ "loss": 0.427,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6413682522715125,
853
+ "grad_norm": 2.0739567283668583,
854
+ "learning_rate": 3.4300672753668635e-06,
855
+ "loss": 0.4163,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6467129877071085,
860
+ "grad_norm": 1.8900939036994293,
861
+ "learning_rate": 3.34168056086183e-06,
862
+ "loss": 0.4322,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6520577231427044,
867
+ "grad_norm": 1.9421083071105274,
868
+ "learning_rate": 3.2538723463104737e-06,
869
+ "loss": 0.4139,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.6574024585783004,
874
+ "grad_norm": 1.9389760896779549,
875
+ "learning_rate": 3.166673263355199e-06,
876
+ "loss": 0.4238,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6627471940138963,
881
+ "grad_norm": 1.874356566114327,
882
+ "learning_rate": 3.0801137311446087e-06,
883
+ "loss": 0.4165,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6680919294494923,
888
+ "grad_norm": 1.9580525970654405,
889
+ "learning_rate": 2.994223945721872e-06,
890
+ "loss": 0.4082,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.6734366648850882,
895
+ "grad_norm": 1.9147611470583412,
896
+ "learning_rate": 2.9090338694909254e-06,
897
+ "loss": 0.4219,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.6787814003206841,
902
+ "grad_norm": 1.86847720750241,
903
+ "learning_rate": 2.8245732207641705e-06,
904
+ "loss": 0.4132,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.6841261357562801,
909
+ "grad_norm": 1.8982814741174805,
910
+ "learning_rate": 2.740871463395325e-06,
911
+ "loss": 0.4129,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.689470871191876,
916
+ "grad_norm": 1.901393825227574,
917
+ "learning_rate": 2.65795779650105e-06,
918
+ "loss": 0.4033,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.694815606627472,
923
+ "grad_norm": 1.8509358915404532,
924
+ "learning_rate": 2.575861144274914e-06,
925
+ "loss": 0.4013,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.7001603420630679,
930
+ "grad_norm": 1.8958219311827695,
931
+ "learning_rate": 2.4946101458972744e-06,
932
+ "loss": 0.4027,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.7055050774986639,
937
+ "grad_norm": 1.8426235286345023,
938
+ "learning_rate": 2.414233145544585e-06,
939
+ "loss": 0.3964,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.7108498129342598,
944
+ "grad_norm": 1.9191012877180513,
945
+ "learning_rate": 2.33475818250161e-06,
946
+ "loss": 0.3954,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.7161945483698557,
951
+ "grad_norm": 1.902716391588277,
952
+ "learning_rate": 2.256212981379996e-06,
953
+ "loss": 0.3957,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.7215392838054516,
958
+ "grad_norm": 1.947059841210012,
959
+ "learning_rate": 2.178624942446626e-06,
960
+ "loss": 0.401,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.7268840192410476,
965
+ "grad_norm": 1.917543839246915,
966
+ "learning_rate": 2.1020211320651135e-06,
967
+ "loss": 0.3888,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.7322287546766435,
972
+ "grad_norm": 1.8327154685147313,
973
+ "learning_rate": 2.0264282732537827e-06,
974
+ "loss": 0.4003,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.7375734901122395,
979
+ "grad_norm": 1.7919182630342896,
980
+ "learning_rate": 1.9518727363634187e-06,
981
+ "loss": 0.3873,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.7429182255478354,
986
+ "grad_norm": 1.9169963711238958,
987
+ "learning_rate": 1.8783805298780427e-06,
988
+ "loss": 0.4018,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.7482629609834314,
993
+ "grad_norm": 1.8380910216299624,
994
+ "learning_rate": 1.8059772913419305e-06,
995
+ "loss": 0.3946,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7536076964190273,
1000
+ "grad_norm": 1.9558297629437302,
1001
+ "learning_rate": 1.7346882784160346e-06,
1002
+ "loss": 0.3916,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7589524318546232,
1007
+ "grad_norm": 1.897087729189459,
1008
+ "learning_rate": 1.6645383600669124e-06,
1009
+ "loss": 0.3919,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7642971672902191,
1014
+ "grad_norm": 1.8755131544746726,
1015
+ "learning_rate": 1.5955520078912628e-06,
1016
+ "loss": 0.3846,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.7696419027258151,
1021
+ "grad_norm": 1.8807950794746984,
1022
+ "learning_rate": 1.527753287579084e-06,
1023
+ "loss": 0.3801,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.774986638161411,
1028
+ "grad_norm": 1.8519074792344092,
1029
+ "learning_rate": 1.461165850518424e-06,
1030
+ "loss": 0.3788,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.780331373597007,
1035
+ "grad_norm": 1.894015594982712,
1036
+ "learning_rate": 1.3958129255446585e-06,
1037
+ "loss": 0.383,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.7856761090326029,
1042
+ "grad_norm": 1.8830744382706812,
1043
+ "learning_rate": 1.3317173108371834e-06,
1044
+ "loss": 0.3803,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.7910208444681989,
1049
+ "grad_norm": 1.723519908836632,
1050
+ "learning_rate": 1.268901365966337e-06,
1051
+ "loss": 0.3822,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.7963655799037948,
1056
+ "grad_norm": 1.7952600980364406,
1057
+ "learning_rate": 1.2073870040933212e-06,
1058
+ "loss": 0.3715,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.8017103153393907,
1063
+ "grad_norm": 1.9566873596603427,
1064
+ "learning_rate": 1.1471956843258676e-06,
1065
+ "loss": 0.384,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.8070550507749866,
1070
+ "grad_norm": 1.8386259618144518,
1071
+ "learning_rate": 1.0883484042322796e-06,
1072
+ "loss": 0.3869,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.8123997862105826,
1077
+ "grad_norm": 1.8260297894288255,
1078
+ "learning_rate": 1.0308656925165033e-06,
1079
+ "loss": 0.3812,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.8177445216461785,
1084
+ "grad_norm": 1.8047190650634146,
1085
+ "learning_rate": 9.74767601856737e-07,
1086
+ "loss": 0.3806,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.8230892570817745,
1091
+ "grad_norm": 1.8221471376738447,
1092
+ "learning_rate": 9.200737019101169e-07,
1093
+ "loss": 0.3777,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.8284339925173704,
1098
+ "grad_norm": 1.963769411688169,
1099
+ "learning_rate": 8.668030724858984e-07,
1100
+ "loss": 0.3688,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.8337787279529664,
1105
+ "grad_norm": 1.7734438619458048,
1106
+ "learning_rate": 8.149742968895253e-07,
1107
+ "loss": 0.3756,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.8391234633885623,
1112
+ "grad_norm": 1.800103499706633,
1113
+ "learning_rate": 7.646054554398863e-07,
1114
+ "loss": 0.3773,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.8444681988241582,
1119
+ "grad_norm": 1.8625669508711113,
1120
+ "learning_rate": 7.157141191620548e-07,
1121
+ "loss": 0.3682,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.8498129342597541,
1126
+ "grad_norm": 1.8353500996941807,
1127
+ "learning_rate": 6.683173436576851e-07,
1128
+ "loss": 0.3646,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.8551576696953501,
1133
+ "grad_norm": 1.8832589125337102,
1134
+ "learning_rate": 6.224316631552207e-07,
1135
+ "loss": 0.376,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.860502405130946,
1140
+ "grad_norm": 1.7768361367435437,
1141
+ "learning_rate": 5.780730847419652e-07,
1142
+ "loss": 0.3657,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.865847140566542,
1147
+ "grad_norm": 1.7627566159259074,
1148
+ "learning_rate": 5.35257082780069e-07,
1149
+ "loss": 0.3674,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.8711918760021379,
1154
+ "grad_norm": 1.8420469952326894,
1155
+ "learning_rate": 4.939985935083314e-07,
1156
+ "loss": 0.3669,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.8765366114377339,
1161
+ "grad_norm": 1.7499771334622984,
1162
+ "learning_rate": 4.5431200983174493e-07,
1163
+ "loss": 0.3671,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.8818813468733298,
1168
+ "grad_norm": 1.7862835118779703,
1169
+ "learning_rate": 4.1621117630056606e-07,
1170
+ "loss": 0.3729,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.8872260823089257,
1175
+ "grad_norm": 1.7739216023779494,
1176
+ "learning_rate": 3.7970938428068813e-07,
1177
+ "loss": 0.3714,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.8925708177445216,
1182
+ "grad_norm": 1.7066183325006379,
1183
+ "learning_rate": 3.4481936731698415e-07,
1184
+ "loss": 0.3655,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.8979155531801176,
1189
+ "grad_norm": 1.7916893607261628,
1190
+ "learning_rate": 3.1155329669124876e-07,
1191
+ "loss": 0.3702,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.9032602886157135,
1196
+ "grad_norm": 1.803470706275281,
1197
+ "learning_rate": 2.7992277717627856e-07,
1198
+ "loss": 0.3599,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.9086050240513095,
1203
+ "grad_norm": 1.7999593269005436,
1204
+ "learning_rate": 2.4993884298758097e-07,
1205
+ "loss": 0.3621,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.9139497594869054,
1210
+ "grad_norm": 1.749439500356134,
1211
+ "learning_rate": 2.2161195393412493e-07,
1212
+ "loss": 0.361,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.9192944949225014,
1217
+ "grad_norm": 1.804710229821361,
1218
+ "learning_rate": 1.9495199176945977e-07,
1219
+ "loss": 0.3705,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.9246392303580973,
1224
+ "grad_norm": 1.7380753832775804,
1225
+ "learning_rate": 1.6996825674449768e-07,
1226
+ "loss": 0.3581,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.9299839657936932,
1231
+ "grad_norm": 1.9009106101736641,
1232
+ "learning_rate": 1.4666946436314832e-07,
1233
+ "loss": 0.3699,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.9353287012292891,
1238
+ "grad_norm": 1.7420463319700745,
1239
+ "learning_rate": 1.2506374234193985e-07,
1240
+ "loss": 0.36,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.9406734366648851,
1245
+ "grad_norm": 1.7367484197909535,
1246
+ "learning_rate": 1.0515862777468689e-07,
1247
+ "loss": 0.3611,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.946018172100481,
1252
+ "grad_norm": 1.8449072611969448,
1253
+ "learning_rate": 8.69610645031993e-08,
1254
+ "loss": 0.3585,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.951362907536077,
1259
+ "grad_norm": 1.7050020816812541,
1260
+ "learning_rate": 7.047740069494102e-08,
1261
+ "loss": 0.3663,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.9567076429716729,
1266
+ "grad_norm": 1.7491629746492106,
1267
+ "learning_rate": 5.571338662849257e-08,
1268
+ "loss": 0.3621,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.9620523784072689,
1273
+ "grad_norm": 1.8299154207593904,
1274
+ "learning_rate": 4.267417268758123e-08,
1275
+ "loss": 0.3657,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.9673971138428648,
1280
+ "grad_norm": 1.7386431635341528,
1281
+ "learning_rate": 3.1364307564384357e-08,
1282
+ "loss": 0.3604,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.9727418492784607,
1287
+ "grad_norm": 1.851821490817842,
1288
+ "learning_rate": 2.178773667273204e-08,
1289
+ "loss": 0.3639,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.9780865847140566,
1294
+ "grad_norm": 1.7134927436590126,
1295
+ "learning_rate": 1.3947800771760278e-08,
1296
+ "loss": 0.3623,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.9834313201496526,
1301
+ "grad_norm": 1.7740180149347793,
1302
+ "learning_rate": 7.84723480049765e-09,
1303
+ "loss": 0.3727,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.9887760555852485,
1308
+ "grad_norm": 1.6783259441701572,
1309
+ "learning_rate": 3.4881669237890603e-09,
1310
+ "loss": 0.36,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.9941207910208445,
1315
+ "grad_norm": 1.6994301851701823,
1316
+ "learning_rate": 8.721177898912691e-10,
1317
+ "loss": 0.3739,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.9994655264564404,
1322
+ "grad_norm": 1.7638563088423833,
1323
+ "learning_rate": 0.0,
1324
+ "loss": 0.3534,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.9994655264564404,
1329
+ "eval_loss": 0.3047424554824829,
1330
+ "eval_runtime": 0.9585,
1331
+ "eval_samples_per_second": 2.087,
1332
+ "eval_steps_per_second": 1.043,
1333
+ "step": 935
1334
+ },
1335
+ {
1336
+ "epoch": 0.9994655264564404,
1337
+ "step": 935,
1338
+ "total_flos": 195717633146880.0,
1339
+ "train_loss": 0.5211284054791864,
1340
+ "train_runtime": 23277.081,
1341
+ "train_samples_per_second": 1.286,
1342
+ "train_steps_per_second": 0.04
1343
+ }
1344
+ ],
1345
+ "logging_steps": 5,
1346
+ "max_steps": 935,
1347
+ "num_input_tokens_seen": 0,
1348
+ "num_train_epochs": 1,
1349
+ "save_steps": 100,
1350
+ "stateful_callbacks": {
1351
+ "TrainerControl": {
1352
+ "args": {
1353
+ "should_epoch_stop": false,
1354
+ "should_evaluate": false,
1355
+ "should_log": false,
1356
+ "should_save": true,
1357
+ "should_training_stop": true
1358
+ },
1359
+ "attributes": {}
1360
+ }
1361
+ },
1362
+ "total_flos": 195717633146880.0,
1363
+ "train_batch_size": 2,
1364
+ "trial_name": null,
1365
+ "trial_params": null
1366
+ }