terry69 commited on
Commit
f7313d4
·
verified ·
1 Parent(s): 0f41f14

Model save

Browse files
Files changed (4) hide show
  1. README.md +69 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +1345 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: meta-llama/Meta-Llama-3-8B
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: sanity_check_20p_100k
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # sanity_check_20p_100k
20
+
21
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.0053
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 1
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 4
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 64
50
+ - total_eval_batch_size: 4
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 1
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:------:|:----:|:---------------:|
60
+ | 1.0802 | 0.9997 | 920 | 1.0053 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.11.1
66
+ - Transformers 4.43.4
67
+ - Pytorch 2.3.1+cu121
68
+ - Datasets 2.19.1
69
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997283346916599,
3
+ "total_flos": 1.1569444404854784e+16,
4
+ "train_loss": 1.1088063976039058,
5
+ "train_runtime": 18858.7381,
6
+ "train_samples": 100700,
7
+ "train_samples_per_second": 3.122,
8
+ "train_steps_per_second": 0.049
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997283346916599,
3
+ "total_flos": 1.1569444404854784e+16,
4
+ "train_loss": 1.1088063976039058,
5
+ "train_runtime": 18858.7381,
6
+ "train_samples": 100700,
7
+ "train_samples_per_second": 3.122,
8
+ "train_steps_per_second": 0.049
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1345 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997283346916599,
5
+ "eval_steps": 500,
6
+ "global_step": 920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010866612333604998,
13
+ "grad_norm": 0.4251704808550498,
14
+ "learning_rate": 2.173913043478261e-06,
15
+ "loss": 1.4269,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0054333061668024995,
20
+ "grad_norm": 0.40984452500537005,
21
+ "learning_rate": 1.0869565217391305e-05,
22
+ "loss": 1.3471,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.010866612333604999,
27
+ "grad_norm": 0.4873634611727503,
28
+ "learning_rate": 2.173913043478261e-05,
29
+ "loss": 1.381,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.016299918500407497,
34
+ "grad_norm": 0.18148535913697195,
35
+ "learning_rate": 3.260869565217392e-05,
36
+ "loss": 1.3548,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.021733224667209998,
41
+ "grad_norm": 0.15940647336910793,
42
+ "learning_rate": 4.347826086956522e-05,
43
+ "loss": 1.3268,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.027166530834012496,
48
+ "grad_norm": 0.1330605316188635,
49
+ "learning_rate": 5.4347826086956524e-05,
50
+ "loss": 1.2956,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.032599837000814993,
55
+ "grad_norm": 0.14643550415935352,
56
+ "learning_rate": 6.521739130434783e-05,
57
+ "loss": 1.2584,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.038033143167617495,
62
+ "grad_norm": 0.13789279323264822,
63
+ "learning_rate": 7.608695652173914e-05,
64
+ "loss": 1.2599,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.043466449334419996,
69
+ "grad_norm": 0.10731768218336359,
70
+ "learning_rate": 8.695652173913044e-05,
71
+ "loss": 1.2074,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.0488997555012225,
76
+ "grad_norm": 0.1057871319222063,
77
+ "learning_rate": 9.782608695652174e-05,
78
+ "loss": 1.2533,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.05433306166802499,
83
+ "grad_norm": 0.07875920723380202,
84
+ "learning_rate": 0.00010869565217391305,
85
+ "loss": 1.1827,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05976636783482749,
90
+ "grad_norm": 0.07554518893021663,
91
+ "learning_rate": 0.00011956521739130435,
92
+ "loss": 1.1878,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.06519967400162999,
97
+ "grad_norm": 0.07195376087029262,
98
+ "learning_rate": 0.00013043478260869567,
99
+ "loss": 1.1919,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.07063298016843249,
104
+ "grad_norm": 0.07321939595594293,
105
+ "learning_rate": 0.00014130434782608697,
106
+ "loss": 1.1605,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.07606628633523499,
111
+ "grad_norm": 0.07334785242718754,
112
+ "learning_rate": 0.00015217391304347827,
113
+ "loss": 1.1549,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.08149959250203749,
118
+ "grad_norm": 0.070707496165197,
119
+ "learning_rate": 0.00016304347826086955,
120
+ "loss": 1.163,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.08693289866883999,
125
+ "grad_norm": 0.07258864547290272,
126
+ "learning_rate": 0.00017391304347826088,
127
+ "loss": 1.1355,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.0923662048356425,
132
+ "grad_norm": 0.06874465839069938,
133
+ "learning_rate": 0.00018478260869565218,
134
+ "loss": 1.1351,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.097799511002445,
139
+ "grad_norm": 0.07678305279824389,
140
+ "learning_rate": 0.0001956521739130435,
141
+ "loss": 1.1059,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.10323281716924748,
146
+ "grad_norm": 0.0906973594061365,
147
+ "learning_rate": 0.00019999352191120556,
148
+ "loss": 1.1375,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.10866612333604998,
153
+ "grad_norm": 0.09273255388055195,
154
+ "learning_rate": 0.00019995393663024054,
155
+ "loss": 1.1329,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.11409942950285248,
160
+ "grad_norm": 0.08893171944910543,
161
+ "learning_rate": 0.0001998783792354841,
162
+ "loss": 1.1251,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.11953273566965499,
167
+ "grad_norm": 0.09204342908287226,
168
+ "learning_rate": 0.00019976687691905393,
169
+ "loss": 1.1294,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.12496604183645749,
174
+ "grad_norm": 0.08467143673010843,
175
+ "learning_rate": 0.00019961946980917456,
176
+ "loss": 1.1278,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.13039934800325997,
181
+ "grad_norm": 0.08144590635344492,
182
+ "learning_rate": 0.00019943621095573586,
183
+ "loss": 1.1154,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.1358326541700625,
188
+ "grad_norm": 0.07775679298443673,
189
+ "learning_rate": 0.00019921716631120107,
190
+ "loss": 1.1338,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.14126596033686498,
195
+ "grad_norm": 0.07462503464881824,
196
+ "learning_rate": 0.0001989624147068713,
197
+ "loss": 1.0908,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.1466992665036675,
202
+ "grad_norm": 0.10574377628309363,
203
+ "learning_rate": 0.0001986720478245153,
204
+ "loss": 1.0958,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.15213257267046998,
209
+ "grad_norm": 0.08626088216141505,
210
+ "learning_rate": 0.0001983461701633742,
211
+ "loss": 1.0946,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.1575658788372725,
216
+ "grad_norm": 0.08101105375257252,
217
+ "learning_rate": 0.00019798489900255389,
218
+ "loss": 1.0921,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.16299918500407498,
223
+ "grad_norm": 0.07368284055990211,
224
+ "learning_rate": 0.00019758836435881746,
225
+ "loss": 1.1197,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.16843249117087747,
230
+ "grad_norm": 0.08774531529792205,
231
+ "learning_rate": 0.00019715670893979414,
232
+ "loss": 1.1245,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.17386579733767998,
237
+ "grad_norm": 0.08198118641745479,
238
+ "learning_rate": 0.00019669008809262062,
239
+ "loss": 1.1441,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.17929910350448247,
244
+ "grad_norm": 0.07963783890679672,
245
+ "learning_rate": 0.0001961886697480335,
246
+ "loss": 1.1265,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.184732409671285,
251
+ "grad_norm": 0.08389788352824891,
252
+ "learning_rate": 0.0001956526343599335,
253
+ "loss": 1.1071,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.19016571583808747,
258
+ "grad_norm": 0.08052713262866189,
259
+ "learning_rate": 0.0001950821748404421,
260
+ "loss": 1.1001,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.19559902200489,
265
+ "grad_norm": 0.0775857382618487,
266
+ "learning_rate": 0.00019447749649047542,
267
+ "loss": 1.1064,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.20103232817169248,
272
+ "grad_norm": 0.0917075056840311,
273
+ "learning_rate": 0.0001938388169258587,
274
+ "loss": 1.0996,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.20646563433849496,
279
+ "grad_norm": 0.08378602725221357,
280
+ "learning_rate": 0.00019316636599900946,
281
+ "loss": 1.1174,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.21189894050529748,
286
+ "grad_norm": 0.1278123340196638,
287
+ "learning_rate": 0.00019246038571621657,
288
+ "loss": 1.0996,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.21733224667209997,
293
+ "grad_norm": 0.08960771654215978,
294
+ "learning_rate": 0.00019172113015054532,
295
+ "loss": 1.1136,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.22276555283890248,
300
+ "grad_norm": 0.08865525272297263,
301
+ "learning_rate": 0.00019094886535039982,
302
+ "loss": 1.0934,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.22819885900570497,
307
+ "grad_norm": 0.08132686975529266,
308
+ "learning_rate": 0.00019014386924377582,
309
+ "loss": 1.0969,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.23363216517250748,
314
+ "grad_norm": 0.08682177413199785,
315
+ "learning_rate": 0.00018930643153823777,
316
+ "loss": 1.1057,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.23906547133930997,
321
+ "grad_norm": 0.08366750333748893,
322
+ "learning_rate": 0.00018843685361665723,
323
+ "loss": 1.0984,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.24449877750611246,
328
+ "grad_norm": 0.0791018641660297,
329
+ "learning_rate": 0.00018753544842874887,
330
+ "loss": 1.124,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.24993208367291497,
335
+ "grad_norm": 0.08073734798833669,
336
+ "learning_rate": 0.00018660254037844388,
337
+ "loss": 1.1086,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.25536538983971746,
342
+ "grad_norm": 0.07872218202349608,
343
+ "learning_rate": 0.00018563846520714154,
344
+ "loss": 1.0975,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.26079869600651995,
349
+ "grad_norm": 0.07477291972797645,
350
+ "learning_rate": 0.00018464356987288013,
351
+ "loss": 1.0953,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.2662320021733225,
356
+ "grad_norm": 0.07464290895172018,
357
+ "learning_rate": 0.0001836182124254711,
358
+ "loss": 1.1009,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.271665308340125,
363
+ "grad_norm": 0.08337470836636104,
364
+ "learning_rate": 0.00018256276187764197,
365
+ "loss": 1.133,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.27709861450692747,
370
+ "grad_norm": 0.0792698664089276,
371
+ "learning_rate": 0.0001814775980722332,
372
+ "loss": 1.0848,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.28253192067372995,
377
+ "grad_norm": 0.07783493666541991,
378
+ "learning_rate": 0.00018036311154549784,
379
+ "loss": 1.0946,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.28796522684053244,
384
+ "grad_norm": 0.07936535662112612,
385
+ "learning_rate": 0.00017921970338655266,
386
+ "loss": 1.0991,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.293398533007335,
391
+ "grad_norm": 0.08150639145601371,
392
+ "learning_rate": 0.00017804778509303138,
393
+ "loss": 1.1032,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.29883183917413747,
398
+ "grad_norm": 0.07393493455934289,
399
+ "learning_rate": 0.00017684777842299205,
400
+ "loss": 1.1061,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.30426514534093996,
405
+ "grad_norm": 0.07425512123490186,
406
+ "learning_rate": 0.00017562011524313185,
407
+ "loss": 1.0974,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.30969845150774244,
412
+ "grad_norm": 0.08088846247833803,
413
+ "learning_rate": 0.00017436523737336402,
414
+ "loss": 1.1057,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.315131757674545,
419
+ "grad_norm": 0.07594242007128106,
420
+ "learning_rate": 0.00017308359642781242,
421
+ "loss": 1.1107,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.3205650638413475,
426
+ "grad_norm": 0.07364071747814806,
427
+ "learning_rate": 0.00017177565365228178,
428
+ "loss": 1.1071,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.32599837000814996,
433
+ "grad_norm": 0.0750961308431674,
434
+ "learning_rate": 0.00017044187975826124,
435
+ "loss": 1.0926,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.33143167617495245,
440
+ "grad_norm": 0.08124049903595534,
441
+ "learning_rate": 0.0001690827547535214,
442
+ "loss": 1.0779,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.33686498234175494,
447
+ "grad_norm": 0.07415464127126385,
448
+ "learning_rate": 0.0001676987677693659,
449
+ "loss": 1.1177,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3422982885085575,
454
+ "grad_norm": 0.07932404096302531,
455
+ "learning_rate": 0.00016629041688459941,
456
+ "loss": 1.0994,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.34773159467535997,
461
+ "grad_norm": 0.07494379306548073,
462
+ "learning_rate": 0.0001648582089462756,
463
+ "loss": 1.1003,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.35316490084216245,
468
+ "grad_norm": 0.07450254891711967,
469
+ "learning_rate": 0.00016340265938728958,
470
+ "loss": 1.1003,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.35859820700896494,
475
+ "grad_norm": 0.07502689209720823,
476
+ "learning_rate": 0.0001619242920408802,
477
+ "loss": 1.1131,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.36403151317576743,
482
+ "grad_norm": 0.07340743859135564,
483
+ "learning_rate": 0.00016042363895210946,
484
+ "loss": 1.1302,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.36946481934257,
489
+ "grad_norm": 0.08148683177168727,
490
+ "learning_rate": 0.00015890124018638638,
491
+ "loss": 1.0876,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.37489812550937246,
496
+ "grad_norm": 0.07814855659102214,
497
+ "learning_rate": 0.0001573576436351046,
498
+ "loss": 1.1052,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.38033143167617495,
503
+ "grad_norm": 0.07793395138533396,
504
+ "learning_rate": 0.00015579340481846336,
505
+ "loss": 1.0991,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.38576473784297743,
510
+ "grad_norm": 0.07203762927472582,
511
+ "learning_rate": 0.00015420908668554298,
512
+ "loss": 1.1242,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.39119804400978,
517
+ "grad_norm": 0.08066607050998563,
518
+ "learning_rate": 0.00015260525941170712,
519
+ "loss": 1.0598,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.39663135017658246,
524
+ "grad_norm": 0.07563612425103881,
525
+ "learning_rate": 0.00015098250019340387,
526
+ "loss": 1.1073,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.40206465634338495,
531
+ "grad_norm": 0.08780896217816431,
532
+ "learning_rate": 0.00014934139304044033,
533
+ "loss": 1.1077,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.40749796251018744,
538
+ "grad_norm": 0.075783720101519,
539
+ "learning_rate": 0.0001476825285658053,
540
+ "loss": 1.097,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.4129312686769899,
545
+ "grad_norm": 0.07533667147991636,
546
+ "learning_rate": 0.00014600650377311522,
547
+ "loss": 1.0948,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.41836457484379247,
552
+ "grad_norm": 0.08145283761220191,
553
+ "learning_rate": 0.00014431392184176042,
554
+ "loss": 1.0902,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.42379788101059496,
559
+ "grad_norm": 0.07772240362555147,
560
+ "learning_rate": 0.00014260539190982886,
561
+ "loss": 1.0881,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.42923118717739744,
566
+ "grad_norm": 0.07228052744891678,
567
+ "learning_rate": 0.00014088152885488502,
568
+ "loss": 1.0788,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.43466449334419993,
573
+ "grad_norm": 0.08407870138614082,
574
+ "learning_rate": 0.00013914295307268396,
575
+ "loss": 1.1124,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.4400977995110024,
580
+ "grad_norm": 0.07850798498901956,
581
+ "learning_rate": 0.00013739029025389846,
582
+ "loss": 1.0906,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.44553110567780496,
587
+ "grad_norm": 0.07381578409984058,
588
+ "learning_rate": 0.00013562417115894172,
589
+ "loss": 1.0943,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.45096441184460745,
594
+ "grad_norm": 0.08024210843335,
595
+ "learning_rate": 0.0001338452313909644,
596
+ "loss": 1.0968,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.45639771801140994,
601
+ "grad_norm": 0.07473871189132965,
602
+ "learning_rate": 0.00013205411116710972,
603
+ "loss": 1.0913,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.4618310241782124,
608
+ "grad_norm": 0.0714410489594485,
609
+ "learning_rate": 0.0001302514550881076,
610
+ "loss": 1.1018,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.46726433034501497,
615
+ "grad_norm": 0.07909271973522737,
616
+ "learning_rate": 0.0001284379119062912,
617
+ "loss": 1.0852,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.47269763651181745,
622
+ "grad_norm": 0.07891638633482141,
623
+ "learning_rate": 0.00012661413429211957,
624
+ "loss": 1.0711,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.47813094267861994,
629
+ "grad_norm": 0.08881872489618887,
630
+ "learning_rate": 0.00012478077859929,
631
+ "loss": 1.0738,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.48356424884542243,
636
+ "grad_norm": 0.08624317368044378,
637
+ "learning_rate": 0.00012293850462852496,
638
+ "loss": 1.1031,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.4889975550122249,
643
+ "grad_norm": 0.08266232685721502,
644
+ "learning_rate": 0.00012108797539011847,
645
+ "loss": 1.1198,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.49443086117902746,
650
+ "grad_norm": 0.07635565938747138,
651
+ "learning_rate": 0.00011922985686532726,
652
+ "loss": 1.0873,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.49986416734582995,
657
+ "grad_norm": 0.07781766022202603,
658
+ "learning_rate": 0.00011736481776669306,
659
+ "loss": 1.105,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.5052974735126324,
664
+ "grad_norm": 0.07202406913689023,
665
+ "learning_rate": 0.00011549352929738142,
666
+ "loss": 1.1033,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.5107307796794349,
671
+ "grad_norm": 0.07526163912368695,
672
+ "learning_rate": 0.00011361666490962468,
673
+ "loss": 1.1015,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.5161640858462374,
678
+ "grad_norm": 0.07194341123415399,
679
+ "learning_rate": 0.00011173490006235528,
680
+ "loss": 1.0844,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5215973920130399,
685
+ "grad_norm": 0.0778307000682154,
686
+ "learning_rate": 0.00010984891197811687,
687
+ "loss": 1.079,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5270306981798424,
692
+ "grad_norm": 0.07029041166784745,
693
+ "learning_rate": 0.00010795937939934088,
694
+ "loss": 1.0832,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.532464004346645,
699
+ "grad_norm": 0.072860965367971,
700
+ "learning_rate": 0.00010606698234407586,
701
+ "loss": 1.1017,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.5378973105134475,
706
+ "grad_norm": 0.07249476012394583,
707
+ "learning_rate": 0.00010417240186125805,
708
+ "loss": 1.0848,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.54333061668025,
713
+ "grad_norm": 0.07190968384245135,
714
+ "learning_rate": 0.00010227631978561056,
715
+ "loss": 1.0834,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5487639228470524,
720
+ "grad_norm": 0.07212243055291719,
721
+ "learning_rate": 0.00010037941849226032,
722
+ "loss": 1.0681,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5541972290138549,
727
+ "grad_norm": 0.07472462127072327,
728
+ "learning_rate": 9.848238065115975e-05,
729
+ "loss": 1.0823,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5596305351806574,
734
+ "grad_norm": 0.07341247607319075,
735
+ "learning_rate": 9.658588898140322e-05,
736
+ "loss": 1.0808,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5650638413474599,
741
+ "grad_norm": 0.07373559114947376,
742
+ "learning_rate": 9.469062600552509e-05,
743
+ "loss": 1.0797,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5704971475142624,
748
+ "grad_norm": 0.07594819742108236,
749
+ "learning_rate": 9.27972738038688e-05,
750
+ "loss": 1.0605,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5759304536810649,
755
+ "grad_norm": 0.0782882995694038,
756
+ "learning_rate": 9.09065137691153e-05,
757
+ "loss": 1.1044,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.5813637598478675,
762
+ "grad_norm": 0.0764312523770268,
763
+ "learning_rate": 8.901902636105854e-05,
764
+ "loss": 1.0821,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.58679706601467,
769
+ "grad_norm": 0.07500428729495655,
770
+ "learning_rate": 8.713549086171691e-05,
771
+ "loss": 1.0875,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.5922303721814725,
776
+ "grad_norm": 0.07269578451839101,
777
+ "learning_rate": 8.525658513086857e-05,
778
+ "loss": 1.0827,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5976636783482749,
783
+ "grad_norm": 0.0776349309988441,
784
+ "learning_rate": 8.33829853620986e-05,
785
+ "loss": 1.0835,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.6030969845150774,
790
+ "grad_norm": 0.07914278991896619,
791
+ "learning_rate": 8.15153658394458e-05,
792
+ "loss": 1.0854,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.6085302906818799,
797
+ "grad_norm": 0.07805449276137157,
798
+ "learning_rate": 7.965439869473664e-05,
799
+ "loss": 1.0899,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.6139635968486824,
804
+ "grad_norm": 0.07343569346455868,
805
+ "learning_rate": 7.780075366569374e-05,
806
+ "loss": 1.0689,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.6193969030154849,
811
+ "grad_norm": 0.0763506099137777,
812
+ "learning_rate": 7.595509785490617e-05,
813
+ "loss": 1.1015,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.6248302091822874,
818
+ "grad_norm": 0.07697592585435539,
819
+ "learning_rate": 7.411809548974792e-05,
820
+ "loss": 1.1086,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.63026351534909,
825
+ "grad_norm": 0.07858412463887798,
826
+ "learning_rate": 7.229040768333115e-05,
827
+ "loss": 1.0727,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6356968215158925,
832
+ "grad_norm": 0.07677005817307439,
833
+ "learning_rate": 7.04726921965801e-05,
834
+ "loss": 1.0916,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.641130127682695,
839
+ "grad_norm": 0.0769443341169544,
840
+ "learning_rate": 6.866560320151179e-05,
841
+ "loss": 1.0936,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.6465634338494974,
846
+ "grad_norm": 0.07892506244450502,
847
+ "learning_rate": 6.686979104580788e-05,
848
+ "loss": 1.1201,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6519967400162999,
853
+ "grad_norm": 0.07597394899050844,
854
+ "learning_rate": 6.508590201876317e-05,
855
+ "loss": 1.0893,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6574300461831024,
860
+ "grad_norm": 0.07546777076824882,
861
+ "learning_rate": 6.331457811869437e-05,
862
+ "loss": 1.1171,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6628633523499049,
867
+ "grad_norm": 0.07745516555125605,
868
+ "learning_rate": 6.155645682189351e-05,
869
+ "loss": 1.0738,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.6682966585167074,
874
+ "grad_norm": 0.07367510312563916,
875
+ "learning_rate": 5.9812170853208496e-05,
876
+ "loss": 1.0745,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6737299646835099,
881
+ "grad_norm": 0.07824277686686397,
882
+ "learning_rate": 5.8082347958333625e-05,
883
+ "loss": 1.0905,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6791632708503124,
888
+ "grad_norm": 0.0764173540069429,
889
+ "learning_rate": 5.6367610677892177e-05,
890
+ "loss": 1.1074,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.684596577017115,
895
+ "grad_norm": 0.07791563158504998,
896
+ "learning_rate": 5.466857612339229e-05,
897
+ "loss": 1.1194,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.6900298831839174,
902
+ "grad_norm": 0.07146233468425052,
903
+ "learning_rate": 5.298585575513648e-05,
904
+ "loss": 1.1077,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.6954631893507199,
909
+ "grad_norm": 0.07591539295717892,
910
+ "learning_rate": 5.1320055162165115e-05,
911
+ "loss": 1.0932,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.7008964955175224,
916
+ "grad_norm": 0.07910316647424652,
917
+ "learning_rate": 4.967177384431293e-05,
918
+ "loss": 1.1001,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.7063298016843249,
923
+ "grad_norm": 0.0765700985055494,
924
+ "learning_rate": 4.804160499645667e-05,
925
+ "loss": 1.1021,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.7117631078511274,
930
+ "grad_norm": 0.07254920739923368,
931
+ "learning_rate": 4.6430135295032184e-05,
932
+ "loss": 1.0802,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.7171964140179299,
937
+ "grad_norm": 0.07330038875192313,
938
+ "learning_rate": 4.483794468689728e-05,
939
+ "loss": 1.1148,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.7226297201847324,
944
+ "grad_norm": 0.07545496216336055,
945
+ "learning_rate": 4.326560618061639e-05,
946
+ "loss": 1.0979,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.7280630263515349,
951
+ "grad_norm": 0.07908854694610165,
952
+ "learning_rate": 4.1713685640242165e-05,
953
+ "loss": 1.0907,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.7334963325183375,
958
+ "grad_norm": 0.07579581147744809,
959
+ "learning_rate": 4.0182741581668593e-05,
960
+ "loss": 1.1085,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.73892963868514,
965
+ "grad_norm": 0.07729476399610574,
966
+ "learning_rate": 3.8673324971628357e-05,
967
+ "loss": 1.0798,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.7443629448519424,
972
+ "grad_norm": 0.07944953369737749,
973
+ "learning_rate": 3.718597902940717e-05,
974
+ "loss": 1.0869,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.7497962510187449,
979
+ "grad_norm": 0.07194925540581062,
980
+ "learning_rate": 3.5721239031346066e-05,
981
+ "loss": 1.0561,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.7552295571855474,
986
+ "grad_norm": 0.07617097405159699,
987
+ "learning_rate": 3.427963211820274e-05,
988
+ "loss": 1.0756,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.7606628633523499,
993
+ "grad_norm": 0.07302205190651118,
994
+ "learning_rate": 3.2861677105440336e-05,
995
+ "loss": 1.0898,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7660961695191524,
1000
+ "grad_norm": 0.07237255657454869,
1001
+ "learning_rate": 3.146788429651246e-05,
1002
+ "loss": 1.1003,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7715294756859549,
1007
+ "grad_norm": 0.07609168686442808,
1008
+ "learning_rate": 3.009875529921181e-05,
1009
+ "loss": 1.1198,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7769627818527574,
1014
+ "grad_norm": 0.07439558041939377,
1015
+ "learning_rate": 2.8754782845148043e-05,
1016
+ "loss": 1.0885,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.78239608801956,
1021
+ "grad_norm": 0.07799568204768835,
1022
+ "learning_rate": 2.7436450612420095e-05,
1023
+ "loss": 1.0984,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.7878293941863624,
1028
+ "grad_norm": 0.0743227911288043,
1029
+ "learning_rate": 2.6144233051546796e-05,
1030
+ "loss": 1.0821,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.7932627003531649,
1035
+ "grad_norm": 0.07533397831281968,
1036
+ "learning_rate": 2.4878595214718236e-05,
1037
+ "loss": 1.0954,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.7986960065199674,
1042
+ "grad_norm": 0.07795341702809758,
1043
+ "learning_rate": 2.3639992588429705e-05,
1044
+ "loss": 1.073,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.8041293126867699,
1049
+ "grad_norm": 0.07211902034739545,
1050
+ "learning_rate": 2.242887092955801e-05,
1051
+ "loss": 1.0815,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.8095626188535724,
1056
+ "grad_norm": 0.0761432386265937,
1057
+ "learning_rate": 2.12456661049394e-05,
1058
+ "loss": 1.094,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.8149959250203749,
1063
+ "grad_norm": 0.07747183067459043,
1064
+ "learning_rate": 2.0090803934506764e-05,
1065
+ "loss": 1.0879,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.8204292311871774,
1070
+ "grad_norm": 0.07443760717814148,
1071
+ "learning_rate": 1.8964700038042626e-05,
1072
+ "loss": 1.0774,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.8258625373539799,
1077
+ "grad_norm": 0.07403731045418284,
1078
+ "learning_rate": 1.7867759685603114e-05,
1079
+ "loss": 1.062,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.8312958435207825,
1084
+ "grad_norm": 0.07999273099986547,
1085
+ "learning_rate": 1.6800377651666465e-05,
1086
+ "loss": 1.0893,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.8367291496875849,
1091
+ "grad_norm": 0.07415045401695812,
1092
+ "learning_rate": 1.5762938073058853e-05,
1093
+ "loss": 1.0838,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.8421624558543874,
1098
+ "grad_norm": 0.07804672929693661,
1099
+ "learning_rate": 1.475581431070865e-05,
1100
+ "loss": 1.0701,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.8475957620211899,
1105
+ "grad_norm": 0.07518807484213265,
1106
+ "learning_rate": 1.3779368815278647e-05,
1107
+ "loss": 1.0964,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.8530290681879924,
1112
+ "grad_norm": 0.07563239778584362,
1113
+ "learning_rate": 1.2833952996724863e-05,
1114
+ "loss": 1.1061,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.8584623743547949,
1119
+ "grad_norm": 0.07965844467223017,
1120
+ "learning_rate": 1.1919907097828653e-05,
1121
+ "loss": 1.0987,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.8638956805215974,
1126
+ "grad_norm": 0.0766122440696586,
1127
+ "learning_rate": 1.1037560071747732e-05,
1128
+ "loss": 1.0821,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.8693289866883999,
1133
+ "grad_norm": 0.07471932158959192,
1134
+ "learning_rate": 1.01872294636304e-05,
1135
+ "loss": 1.0928,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.8747622928552024,
1140
+ "grad_norm": 0.07879025603430712,
1141
+ "learning_rate": 9.369221296335006e-06,
1142
+ "loss": 1.0742,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.8801955990220048,
1147
+ "grad_norm": 0.07251151651596634,
1148
+ "learning_rate": 8.58382996029652e-06,
1149
+ "loss": 1.1022,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.8856289051888074,
1154
+ "grad_norm": 0.08267985751565841,
1155
+ "learning_rate": 7.831338107579056e-06,
1156
+ "loss": 1.111,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.8910622113556099,
1161
+ "grad_norm": 0.07983071589620737,
1162
+ "learning_rate": 7.1120165501533e-06,
1163
+ "loss": 1.089,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.8964955175224124,
1168
+ "grad_norm": 0.07253898026652339,
1169
+ "learning_rate": 6.426124162434688e-06,
1170
+ "loss": 1.0821,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.9019288236892149,
1175
+ "grad_norm": 0.0726664203858709,
1176
+ "learning_rate": 5.77390778811796e-06,
1177
+ "loss": 1.1032,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.9073621298560174,
1182
+ "grad_norm": 0.07385826672139016,
1183
+ "learning_rate": 5.1556021513412544e-06,
1184
+ "loss": 1.0809,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.9127954360228199,
1189
+ "grad_norm": 0.06998427333733385,
1190
+ "learning_rate": 4.5714297722121106e-06,
1191
+ "loss": 1.1018,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.9182287421896224,
1196
+ "grad_norm": 0.0757435677420101,
1197
+ "learning_rate": 4.021600886725263e-06,
1198
+ "loss": 1.0771,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.9236620483564248,
1203
+ "grad_norm": 0.0722116543100783,
1204
+ "learning_rate": 3.5063133711014882e-06,
1205
+ "loss": 1.0807,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.9290953545232273,
1210
+ "grad_norm": 0.07391301677162948,
1211
+ "learning_rate": 3.025752670574622e-06,
1212
+ "loss": 1.1152,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.9345286606900299,
1217
+ "grad_norm": 0.07161981606521015,
1218
+ "learning_rate": 2.580091732652101e-06,
1219
+ "loss": 1.0914,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.9399619668568324,
1224
+ "grad_norm": 0.08220528509805279,
1225
+ "learning_rate": 2.1694909448735645e-06,
1226
+ "loss": 1.063,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.9453952730236349,
1231
+ "grad_norm": 0.07693291624176714,
1232
+ "learning_rate": 1.7940980770894122e-06,
1233
+ "loss": 1.084,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.9508285791904374,
1238
+ "grad_norm": 0.07644475605951945,
1239
+ "learning_rate": 1.4540482282803137e-06,
1240
+ "loss": 1.1081,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.9562618853572399,
1245
+ "grad_norm": 0.07330126081285318,
1246
+ "learning_rate": 1.1494637779369766e-06,
1247
+ "loss": 1.0879,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.9616951915240424,
1252
+ "grad_norm": 0.073595237012896,
1253
+ "learning_rate": 8.804543420172562e-07,
1254
+ "loss": 1.1054,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.9671284976908449,
1259
+ "grad_norm": 0.07404663517702222,
1260
+ "learning_rate": 6.471167334968886e-07,
1261
+ "loss": 1.0708,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.9725618038576473,
1266
+ "grad_norm": 0.07475084382356802,
1267
+ "learning_rate": 4.495349275276839e-07,
1268
+ "loss": 1.0812,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.9779951100244498,
1273
+ "grad_norm": 0.07201213176485209,
1274
+ "learning_rate": 2.877800312160783e-07,
1275
+ "loss": 1.0603,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.9834284161912524,
1280
+ "grad_norm": 0.07197972989674828,
1281
+ "learning_rate": 1.6191025803250492e-07,
1282
+ "loss": 1.0878,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.9888617223580549,
1287
+ "grad_norm": 0.07408960367345192,
1288
+ "learning_rate": 7.197090686119623e-08,
1289
+ "loss": 1.0819,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.9942950285248574,
1294
+ "grad_norm": 0.07112735003336768,
1295
+ "learning_rate": 1.7994345697680547e-08,
1296
+ "loss": 1.0836,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.9997283346916599,
1301
+ "grad_norm": 0.07282814722420096,
1302
+ "learning_rate": 0.0,
1303
+ "loss": 1.0802,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.9997283346916599,
1308
+ "eval_loss": 1.005259394645691,
1309
+ "eval_runtime": 2.7588,
1310
+ "eval_samples_per_second": 2.537,
1311
+ "eval_steps_per_second": 0.725,
1312
+ "step": 920
1313
+ },
1314
+ {
1315
+ "epoch": 0.9997283346916599,
1316
+ "step": 920,
1317
+ "total_flos": 1.1569444404854784e+16,
1318
+ "train_loss": 1.1088063976039058,
1319
+ "train_runtime": 18858.7381,
1320
+ "train_samples_per_second": 3.122,
1321
+ "train_steps_per_second": 0.049
1322
+ }
1323
+ ],
1324
+ "logging_steps": 5,
1325
+ "max_steps": 920,
1326
+ "num_input_tokens_seen": 0,
1327
+ "num_train_epochs": 1,
1328
+ "save_steps": 100,
1329
+ "stateful_callbacks": {
1330
+ "TrainerControl": {
1331
+ "args": {
1332
+ "should_epoch_stop": false,
1333
+ "should_evaluate": false,
1334
+ "should_log": false,
1335
+ "should_save": true,
1336
+ "should_training_stop": true
1337
+ },
1338
+ "attributes": {}
1339
+ }
1340
+ },
1341
+ "total_flos": 1.1569444404854784e+16,
1342
+ "train_batch_size": 4,
1343
+ "trial_name": null,
1344
+ "trial_params": null
1345
+ }