PEFT
Safetensors
qwen2
alignment-handbook
trl
sft
Generated from Trainer
aadityap commited on
Commit
846998e
·
verified ·
1 Parent(s): 0b132ef

Model save

Browse files
Files changed (4) hide show
  1. README.md +61 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +1274 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: deepseek-ai/Deepseek-R1-Distill-Qwen-32B
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft_base_masked
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft_base_masked
18
+
19
+ This model is a fine-tuned version of [deepseek-ai/Deepseek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/Deepseek-R1-Distill-Qwen-32B) on the None dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 32
45
+ - total_eval_batch_size: 8
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.13.2
58
+ - Transformers 4.47.0.dev0
59
+ - Pytorch 2.4.0+cu121
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 3054747482324992.0,
4
+ "train_loss": 0.7215218588032506,
5
+ "train_runtime": 3666.1508,
6
+ "train_samples": 2805,
7
+ "train_samples_per_second": 1.53,
8
+ "train_steps_per_second": 0.048
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 3054747482324992.0,
4
+ "train_loss": 0.7215218588032506,
5
+ "train_runtime": 3666.1508,
6
+ "train_samples": 2805,
7
+ "train_samples_per_second": 1.53,
8
+ "train_steps_per_second": 0.048
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 176,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011363636363636364,
13
+ "grad_norm": 0.04888428873089485,
14
+ "learning_rate": 2.777777777777778e-06,
15
+ "loss": 0.9533,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.022727272727272728,
20
+ "grad_norm": 0.04118674609403888,
21
+ "learning_rate": 5.555555555555556e-06,
22
+ "loss": 0.8187,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.03409090909090909,
27
+ "grad_norm": 0.036867673437168666,
28
+ "learning_rate": 8.333333333333334e-06,
29
+ "loss": 0.7078,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.045454545454545456,
34
+ "grad_norm": 0.04847692066919062,
35
+ "learning_rate": 1.1111111111111112e-05,
36
+ "loss": 0.987,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.056818181818181816,
41
+ "grad_norm": 0.05003862080856868,
42
+ "learning_rate": 1.388888888888889e-05,
43
+ "loss": 0.9577,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.06818181818181818,
48
+ "grad_norm": 0.04493399553279938,
49
+ "learning_rate": 1.6666666666666667e-05,
50
+ "loss": 0.9205,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.07954545454545454,
55
+ "grad_norm": 0.044174232851205655,
56
+ "learning_rate": 1.9444444444444445e-05,
57
+ "loss": 0.7971,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.09090909090909091,
62
+ "grad_norm": 0.0537270325545959,
63
+ "learning_rate": 2.2222222222222223e-05,
64
+ "loss": 0.875,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.10227272727272728,
69
+ "grad_norm": 0.047274651714941,
70
+ "learning_rate": 2.5e-05,
71
+ "loss": 0.7865,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.11363636363636363,
76
+ "grad_norm": 0.047438139846740904,
77
+ "learning_rate": 2.777777777777778e-05,
78
+ "loss": 0.7949,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.125,
83
+ "grad_norm": 0.0486064821581454,
84
+ "learning_rate": 3.055555555555556e-05,
85
+ "loss": 0.9187,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.13636363636363635,
90
+ "grad_norm": 0.049768338512046005,
91
+ "learning_rate": 3.3333333333333335e-05,
92
+ "loss": 0.927,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.14772727272727273,
97
+ "grad_norm": 0.050752786859426545,
98
+ "learning_rate": 3.611111111111111e-05,
99
+ "loss": 0.882,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.1590909090909091,
104
+ "grad_norm": 0.04238163918748248,
105
+ "learning_rate": 3.888888888888889e-05,
106
+ "loss": 0.8273,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.17045454545454544,
111
+ "grad_norm": 0.03389553366668896,
112
+ "learning_rate": 4.166666666666667e-05,
113
+ "loss": 0.801,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.18181818181818182,
118
+ "grad_norm": 0.03219935695711762,
119
+ "learning_rate": 4.4444444444444447e-05,
120
+ "loss": 0.8313,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.19318181818181818,
125
+ "grad_norm": 0.027821411081551388,
126
+ "learning_rate": 4.722222222222222e-05,
127
+ "loss": 0.6832,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.20454545454545456,
132
+ "grad_norm": 0.028125631584449494,
133
+ "learning_rate": 5e-05,
134
+ "loss": 0.724,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.2159090909090909,
139
+ "grad_norm": 0.03372930491801512,
140
+ "learning_rate": 4.9995058244251644e-05,
141
+ "loss": 0.765,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.22727272727272727,
146
+ "grad_norm": 0.03207593160425088,
147
+ "learning_rate": 4.9980234930682546e-05,
148
+ "loss": 0.8319,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.23863636363636365,
153
+ "grad_norm": 0.04392253595539216,
154
+ "learning_rate": 4.995553591954832e-05,
155
+ "loss": 0.8572,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.25,
160
+ "grad_norm": 0.043837015398686424,
161
+ "learning_rate": 4.99209709753674e-05,
162
+ "loss": 0.7994,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.26136363636363635,
167
+ "grad_norm": 0.038660838245880964,
168
+ "learning_rate": 4.9876553763060684e-05,
169
+ "loss": 0.7595,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.2727272727272727,
174
+ "grad_norm": 0.03958181928823714,
175
+ "learning_rate": 4.982230184254933e-05,
176
+ "loss": 0.7524,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.2840909090909091,
181
+ "grad_norm": 0.04692096023674341,
182
+ "learning_rate": 4.975823666181255e-05,
183
+ "loss": 0.7565,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.29545454545454547,
188
+ "grad_norm": 0.039034963022689224,
189
+ "learning_rate": 4.968438354840834e-05,
190
+ "loss": 0.8968,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.3068181818181818,
195
+ "grad_norm": 0.03472677387974209,
196
+ "learning_rate": 4.960077169946052e-05,
197
+ "loss": 0.7522,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.3181818181818182,
202
+ "grad_norm": 0.031244118470989204,
203
+ "learning_rate": 4.950743417011591e-05,
204
+ "loss": 0.7937,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.32954545454545453,
209
+ "grad_norm": 0.029092500515729473,
210
+ "learning_rate": 4.940440786047628e-05,
211
+ "loss": 0.667,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.3409090909090909,
216
+ "grad_norm": 0.028474671621308404,
217
+ "learning_rate": 4.929173350101025e-05,
218
+ "loss": 0.7255,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.3522727272727273,
223
+ "grad_norm": 0.021514453472108053,
224
+ "learning_rate": 4.9169455636450935e-05,
225
+ "loss": 0.7683,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.36363636363636365,
230
+ "grad_norm": 0.01979063211912252,
231
+ "learning_rate": 4.903762260818551e-05,
232
+ "loss": 0.7236,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.375,
237
+ "grad_norm": 0.019373274784309575,
238
+ "learning_rate": 4.889628653514402e-05,
239
+ "loss": 0.6894,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.38636363636363635,
244
+ "grad_norm": 0.01807357066294673,
245
+ "learning_rate": 4.874550329319457e-05,
246
+ "loss": 0.7558,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3977272727272727,
251
+ "grad_norm": 0.01770418827474799,
252
+ "learning_rate": 4.8585332493053364e-05,
253
+ "loss": 0.6813,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.4090909090909091,
258
+ "grad_norm": 0.01675836399147525,
259
+ "learning_rate": 4.84158374567182e-05,
260
+ "loss": 0.7559,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.42045454545454547,
265
+ "grad_norm": 0.021175097986321438,
266
+ "learning_rate": 4.8237085192434676e-05,
267
+ "loss": 0.8176,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.4318181818181818,
272
+ "grad_norm": 0.017100608642967,
273
+ "learning_rate": 4.804914636820517e-05,
274
+ "loss": 0.7112,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.4431818181818182,
279
+ "grad_norm": 0.01683117973292665,
280
+ "learning_rate": 4.7852095283850866e-05,
281
+ "loss": 0.7345,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.45454545454545453,
286
+ "grad_norm": 0.019570606734413423,
287
+ "learning_rate": 4.764600984163808e-05,
288
+ "loss": 0.8125,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.4659090909090909,
293
+ "grad_norm": 0.015675238814520476,
294
+ "learning_rate": 4.743097151548031e-05,
295
+ "loss": 0.6994,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.4772727272727273,
300
+ "grad_norm": 0.019792988850059114,
301
+ "learning_rate": 4.72070653187283e-05,
302
+ "loss": 0.7837,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.48863636363636365,
307
+ "grad_norm": 0.015785852432543244,
308
+ "learning_rate": 4.6974379770560846e-05,
309
+ "loss": 0.6608,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.5,
314
+ "grad_norm": 0.015533678745760247,
315
+ "learning_rate": 4.673300686098957e-05,
316
+ "loss": 0.7031,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.5113636363636364,
321
+ "grad_norm": 0.01921291960352695,
322
+ "learning_rate": 4.648304201449153e-05,
323
+ "loss": 0.8267,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.5227272727272727,
328
+ "grad_norm": 0.01614254754588724,
329
+ "learning_rate": 4.6224584052284106e-05,
330
+ "loss": 0.7058,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.5340909090909091,
335
+ "grad_norm": 0.019677063872610357,
336
+ "learning_rate": 4.5957735153256915e-05,
337
+ "loss": 0.6621,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.5454545454545454,
342
+ "grad_norm": 0.013519303189431392,
343
+ "learning_rate": 4.5682600813576435e-05,
344
+ "loss": 0.7478,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.5568181818181818,
349
+ "grad_norm": 0.013215293773761478,
350
+ "learning_rate": 4.539928980497903e-05,
351
+ "loss": 0.7034,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.5681818181818182,
356
+ "grad_norm": 0.013694552146445563,
357
+ "learning_rate": 4.510791413176912e-05,
358
+ "loss": 0.7448,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.5795454545454546,
363
+ "grad_norm": 0.016162877179262552,
364
+ "learning_rate": 4.480858898653936e-05,
365
+ "loss": 0.6728,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.5909090909090909,
370
+ "grad_norm": 0.017056245721837348,
371
+ "learning_rate": 4.4501432704630305e-05,
372
+ "loss": 0.6714,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.6022727272727273,
377
+ "grad_norm": 0.01602874080265432,
378
+ "learning_rate": 4.41865667173477e-05,
379
+ "loss": 0.7667,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.6136363636363636,
384
+ "grad_norm": 0.01556595840862479,
385
+ "learning_rate": 4.386411550395576e-05,
386
+ "loss": 0.6934,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.625,
391
+ "grad_norm": 0.014885950964239066,
392
+ "learning_rate": 4.353420654246546e-05,
393
+ "loss": 0.6909,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.6363636363636364,
398
+ "grad_norm": 0.01399086114921709,
399
+ "learning_rate": 4.319697025923736e-05,
400
+ "loss": 0.6817,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.6477272727272727,
405
+ "grad_norm": 0.016980372482516305,
406
+ "learning_rate": 4.285253997741875e-05,
407
+ "loss": 0.7485,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.6590909090909091,
412
+ "grad_norm": 0.01370669813419946,
413
+ "learning_rate": 4.2501051864235636e-05,
414
+ "loss": 0.5524,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.6704545454545454,
419
+ "grad_norm": 0.0161962614922305,
420
+ "learning_rate": 4.214264487716033e-05,
421
+ "loss": 0.7145,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.6818181818181818,
426
+ "grad_norm": 0.01432616251653496,
427
+ "learning_rate": 4.177746070897592e-05,
428
+ "loss": 0.7263,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.6931818181818182,
433
+ "grad_norm": 0.01515485647301396,
434
+ "learning_rate": 4.140564373175939e-05,
435
+ "loss": 0.6531,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.7045454545454546,
440
+ "grad_norm": 0.014400704458474281,
441
+ "learning_rate": 4.10273409398055e-05,
442
+ "loss": 0.7696,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.7159090909090909,
447
+ "grad_norm": 0.015458672360864132,
448
+ "learning_rate": 4.0642701891514e-05,
449
+ "loss": 0.7081,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.7272727272727273,
454
+ "grad_norm": 0.015263330526513203,
455
+ "learning_rate": 4.025187865026311e-05,
456
+ "loss": 0.725,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.7386363636363636,
461
+ "grad_norm": 0.015125337784791405,
462
+ "learning_rate": 3.985502572429276e-05,
463
+ "loss": 0.7111,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.75,
468
+ "grad_norm": 0.013985325014602094,
469
+ "learning_rate": 3.945230000562121e-05,
470
+ "loss": 0.7249,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.7613636363636364,
475
+ "grad_norm": 0.0155589237978013,
476
+ "learning_rate": 3.9043860708019273e-05,
477
+ "loss": 0.6881,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.7727272727272727,
482
+ "grad_norm": 0.01882918883166355,
483
+ "learning_rate": 3.862986930406669e-05,
484
+ "loss": 0.8102,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.7840909090909091,
489
+ "grad_norm": 0.015308078133970605,
490
+ "learning_rate": 3.821048946131549e-05,
491
+ "loss": 0.6919,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.7954545454545454,
496
+ "grad_norm": 0.01630125314346408,
497
+ "learning_rate": 3.778588697758556e-05,
498
+ "loss": 0.6464,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.8068181818181818,
503
+ "grad_norm": 0.015050157672318546,
504
+ "learning_rate": 3.7356229715418074e-05,
505
+ "loss": 0.7114,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.8181818181818182,
510
+ "grad_norm": 0.015186905856860966,
511
+ "learning_rate": 3.6921687535712656e-05,
512
+ "loss": 0.719,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.8295454545454546,
517
+ "grad_norm": 0.01935797435359767,
518
+ "learning_rate": 3.6482432230574446e-05,
519
+ "loss": 0.7255,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.8409090909090909,
524
+ "grad_norm": 0.016661093988049422,
525
+ "learning_rate": 3.60386374553978e-05,
526
+ "loss": 0.6642,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.8522727272727273,
531
+ "grad_norm": 0.017167771916012636,
532
+ "learning_rate": 3.5590478660213214e-05,
533
+ "loss": 0.677,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.8636363636363636,
538
+ "grad_norm": 0.015022481447368145,
539
+ "learning_rate": 3.5138133020324845e-05,
540
+ "loss": 0.7307,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.875,
545
+ "grad_norm": 0.01785502395194187,
546
+ "learning_rate": 3.468177936626603e-05,
547
+ "loss": 0.789,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.8863636363636364,
552
+ "grad_norm": 0.01864810858161923,
553
+ "learning_rate": 3.4221598113100195e-05,
554
+ "loss": 0.7059,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.8977272727272727,
559
+ "grad_norm": 0.016575657529251383,
560
+ "learning_rate": 3.375777118909561e-05,
561
+ "loss": 0.7456,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.9090909090909091,
566
+ "grad_norm": 0.016188984904551812,
567
+ "learning_rate": 3.32904819638017e-05,
568
+ "loss": 0.683,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.9204545454545454,
573
+ "grad_norm": 0.016436588560373562,
574
+ "learning_rate": 3.2819915175555684e-05,
575
+ "loss": 0.6475,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.9318181818181818,
580
+ "grad_norm": 0.017564054129248746,
581
+ "learning_rate": 3.234625685844803e-05,
582
+ "loss": 0.622,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.9431818181818182,
587
+ "grad_norm": 0.019239130214828547,
588
+ "learning_rate": 3.186969426877563e-05,
589
+ "loss": 0.638,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.9545454545454546,
594
+ "grad_norm": 0.01778558528784305,
595
+ "learning_rate": 3.139041581101187e-05,
596
+ "loss": 0.5941,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.9659090909090909,
601
+ "grad_norm": 0.03326719961885704,
602
+ "learning_rate": 3.090861096332263e-05,
603
+ "loss": 0.6721,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.9772727272727273,
608
+ "grad_norm": 0.017697778364759945,
609
+ "learning_rate": 3.042447020265795e-05,
610
+ "loss": 0.663,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.9886363636363636,
615
+ "grad_norm": 0.015032572277755535,
616
+ "learning_rate": 2.993818492944882e-05,
617
+ "loss": 0.6462,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.0,
622
+ "grad_norm": 0.01697573905444168,
623
+ "learning_rate": 2.9449947391938766e-05,
624
+ "loss": 0.6957,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.0113636363636365,
629
+ "grad_norm": 0.01629821245832795,
630
+ "learning_rate": 2.8959950610180374e-05,
631
+ "loss": 0.6629,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.0227272727272727,
636
+ "grad_norm": 0.015172985524910379,
637
+ "learning_rate": 2.8468388299726712e-05,
638
+ "loss": 0.6602,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.0340909090909092,
643
+ "grad_norm": 0.015577909780648352,
644
+ "learning_rate": 2.7975454795047622e-05,
645
+ "loss": 0.796,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.0454545454545454,
650
+ "grad_norm": 0.017309986409190056,
651
+ "learning_rate": 2.7481344972701545e-05,
652
+ "loss": 0.6618,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.0568181818181819,
657
+ "grad_norm": 0.01661621611638882,
658
+ "learning_rate": 2.6986254174292862e-05,
659
+ "loss": 0.7065,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.0681818181818181,
664
+ "grad_norm": 0.016737287474769654,
665
+ "learning_rate": 2.6490378129245498e-05,
666
+ "loss": 0.6457,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.0795454545454546,
671
+ "grad_norm": 0.016921442525318752,
672
+ "learning_rate": 2.599391287742315e-05,
673
+ "loss": 0.7422,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.0909090909090908,
678
+ "grad_norm": 0.01644141496345415,
679
+ "learning_rate": 2.5497054691626753e-05,
680
+ "loss": 0.7125,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.1022727272727273,
685
+ "grad_norm": 0.01566715623525306,
686
+ "learning_rate": 2.5e-05,
687
+ "loss": 0.7015,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.1136363636363635,
692
+ "grad_norm": 0.016042962886209804,
693
+ "learning_rate": 2.4502945308373246e-05,
694
+ "loss": 0.6911,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.125,
699
+ "grad_norm": 0.014451142623462782,
700
+ "learning_rate": 2.4006087122576863e-05,
701
+ "loss": 0.6499,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.1363636363636362,
706
+ "grad_norm": 0.016365537745248963,
707
+ "learning_rate": 2.3509621870754505e-05,
708
+ "loss": 0.6564,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.1477272727272727,
713
+ "grad_norm": 0.015223080653847816,
714
+ "learning_rate": 2.301374582570714e-05,
715
+ "loss": 0.6767,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.1590909090909092,
720
+ "grad_norm": 0.017013122218294784,
721
+ "learning_rate": 2.2518655027298464e-05,
722
+ "loss": 0.6712,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.1704545454545454,
727
+ "grad_norm": 0.017431829042961085,
728
+ "learning_rate": 2.2024545204952383e-05,
729
+ "loss": 0.6363,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.1818181818181819,
734
+ "grad_norm": 0.01638659813387577,
735
+ "learning_rate": 2.1531611700273297e-05,
736
+ "loss": 0.7341,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.1931818181818181,
741
+ "grad_norm": 0.015883920910595706,
742
+ "learning_rate": 2.104004938981963e-05,
743
+ "loss": 0.7503,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.2045454545454546,
748
+ "grad_norm": 0.016308759795444855,
749
+ "learning_rate": 2.055005260806125e-05,
750
+ "loss": 0.7494,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.2159090909090908,
755
+ "grad_norm": 0.01653825796554113,
756
+ "learning_rate": 2.0061815070551186e-05,
757
+ "loss": 0.584,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.2272727272727273,
762
+ "grad_norm": 0.015995947052341933,
763
+ "learning_rate": 1.957552979734205e-05,
764
+ "loss": 0.7943,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.2386363636363638,
769
+ "grad_norm": 0.018158719978620477,
770
+ "learning_rate": 1.9091389036677382e-05,
771
+ "loss": 0.7001,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.25,
776
+ "grad_norm": 0.015286756025554763,
777
+ "learning_rate": 1.8609584188988136e-05,
778
+ "loss": 0.6132,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.2613636363636362,
783
+ "grad_norm": 0.014766283231039113,
784
+ "learning_rate": 1.813030573122437e-05,
785
+ "loss": 0.6789,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.2727272727272727,
790
+ "grad_norm": 0.018163850190524557,
791
+ "learning_rate": 1.7653743141551983e-05,
792
+ "loss": 0.6641,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.2840909090909092,
797
+ "grad_norm": 0.015499094565043982,
798
+ "learning_rate": 1.7180084824444325e-05,
799
+ "loss": 0.7034,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.2954545454545454,
804
+ "grad_norm": 0.01666315009242263,
805
+ "learning_rate": 1.6709518036198308e-05,
806
+ "loss": 0.6644,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.3068181818181819,
811
+ "grad_norm": 0.018550049211631166,
812
+ "learning_rate": 1.6242228810904392e-05,
813
+ "loss": 0.6314,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.3181818181818181,
818
+ "grad_norm": 0.016414228273475284,
819
+ "learning_rate": 1.5778401886899807e-05,
820
+ "loss": 0.7085,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.3295454545454546,
825
+ "grad_norm": 0.016629484072509887,
826
+ "learning_rate": 1.5318220633733978e-05,
827
+ "loss": 0.6328,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.3409090909090908,
832
+ "grad_norm": 0.01735441033712776,
833
+ "learning_rate": 1.4861866979675154e-05,
834
+ "loss": 0.6987,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.3522727272727273,
839
+ "grad_norm": 0.01653379311481811,
840
+ "learning_rate": 1.4409521339786808e-05,
841
+ "loss": 0.7689,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.3636363636363638,
846
+ "grad_norm": 0.017109513908993915,
847
+ "learning_rate": 1.3961362544602213e-05,
848
+ "loss": 0.852,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.375,
853
+ "grad_norm": 0.015606168185551323,
854
+ "learning_rate": 1.3517567769425548e-05,
855
+ "loss": 0.6131,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.3863636363636362,
860
+ "grad_norm": 0.016954213866876906,
861
+ "learning_rate": 1.3078312464287353e-05,
862
+ "loss": 0.7262,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.3977272727272727,
867
+ "grad_norm": 0.019722191608232728,
868
+ "learning_rate": 1.2643770284581929e-05,
869
+ "loss": 0.6411,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.4090909090909092,
874
+ "grad_norm": 0.016754592315893345,
875
+ "learning_rate": 1.2214113022414448e-05,
876
+ "loss": 0.7406,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.4204545454545454,
881
+ "grad_norm": 0.01811366422363491,
882
+ "learning_rate": 1.1789510538684523e-05,
883
+ "loss": 0.6915,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.4318181818181819,
888
+ "grad_norm": 0.015117191146405742,
889
+ "learning_rate": 1.1370130695933318e-05,
890
+ "loss": 0.7914,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.4431818181818181,
895
+ "grad_norm": 0.019162871723577116,
896
+ "learning_rate": 1.0956139291980727e-05,
897
+ "loss": 0.7924,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.4545454545454546,
902
+ "grad_norm": 0.017257641671438298,
903
+ "learning_rate": 1.0547699994378787e-05,
904
+ "loss": 0.6671,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.4659090909090908,
909
+ "grad_norm": 0.018952048140386035,
910
+ "learning_rate": 1.0144974275707241e-05,
911
+ "loss": 0.7046,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.4772727272727273,
916
+ "grad_norm": 0.02016982804986924,
917
+ "learning_rate": 9.748121349736892e-06,
918
+ "loss": 0.7542,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.4886363636363638,
923
+ "grad_norm": 0.015861465051683968,
924
+ "learning_rate": 9.357298108486003e-06,
925
+ "loss": 0.6563,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.5,
930
+ "grad_norm": 0.016677424892624696,
931
+ "learning_rate": 8.972659060194506e-06,
932
+ "loss": 0.6743,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.5113636363636362,
937
+ "grad_norm": 0.017220590202846452,
938
+ "learning_rate": 8.594356268240616e-06,
939
+ "loss": 0.5913,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.5227272727272727,
944
+ "grad_norm": 0.017476835977041916,
945
+ "learning_rate": 8.222539291024078e-06,
946
+ "loss": 0.6184,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.5340909090909092,
951
+ "grad_norm": 0.01852744989540818,
952
+ "learning_rate": 7.857355122839675e-06,
953
+ "loss": 0.8003,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.5454545454545454,
958
+ "grad_norm": 0.017724119693348375,
959
+ "learning_rate": 7.4989481357643694e-06,
960
+ "loss": 0.7319,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.5568181818181817,
965
+ "grad_norm": 0.01827897532047109,
966
+ "learning_rate": 7.147460022581257e-06,
967
+ "loss": 0.7496,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.5681818181818183,
972
+ "grad_norm": 0.017356487062778,
973
+ "learning_rate": 6.803029740762648e-06,
974
+ "loss": 0.6998,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.5795454545454546,
979
+ "grad_norm": 0.01850857557468877,
980
+ "learning_rate": 6.465793457534553e-06,
981
+ "loss": 0.6103,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.5909090909090908,
986
+ "grad_norm": 0.018299658199403747,
987
+ "learning_rate": 6.135884496044244e-06,
988
+ "loss": 0.6448,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.6022727272727273,
993
+ "grad_norm": 0.018388053763702464,
994
+ "learning_rate": 5.813433282652298e-06,
995
+ "loss": 0.6399,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.6136363636363638,
1000
+ "grad_norm": 0.02080237717937431,
1001
+ "learning_rate": 5.4985672953697e-06,
1002
+ "loss": 0.6313,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.625,
1007
+ "grad_norm": 0.01796260664782129,
1008
+ "learning_rate": 5.191411013460645e-06,
1009
+ "loss": 0.6843,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.6363636363636362,
1014
+ "grad_norm": 0.02056859413635753,
1015
+ "learning_rate": 4.892085868230881e-06,
1016
+ "loss": 0.7157,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.6477272727272727,
1021
+ "grad_norm": 0.016274442923538548,
1022
+ "learning_rate": 4.600710195020982e-06,
1023
+ "loss": 0.7276,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.6590909090909092,
1028
+ "grad_norm": 0.01815637927898507,
1029
+ "learning_rate": 4.317399186423574e-06,
1030
+ "loss": 0.6305,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.6704545454545454,
1035
+ "grad_norm": 0.01897651128017473,
1036
+ "learning_rate": 4.042264846743085e-06,
1037
+ "loss": 0.675,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.6818181818181817,
1042
+ "grad_norm": 0.018136754953765325,
1043
+ "learning_rate": 3.775415947715899e-06,
1044
+ "loss": 0.7152,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.6931818181818183,
1049
+ "grad_norm": 0.018312167884684892,
1050
+ "learning_rate": 3.516957985508476e-06,
1051
+ "loss": 0.6128,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.7045454545454546,
1056
+ "grad_norm": 0.01872198284953679,
1057
+ "learning_rate": 3.266993139010438e-06,
1058
+ "loss": 0.7636,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.7159090909090908,
1063
+ "grad_norm": 0.019247219050936033,
1064
+ "learning_rate": 3.0256202294391577e-06,
1065
+ "loss": 0.7763,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.7272727272727273,
1070
+ "grad_norm": 0.01747541840805843,
1071
+ "learning_rate": 2.792934681271708e-06,
1072
+ "loss": 0.718,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.7386363636363638,
1077
+ "grad_norm": 0.016543357188300384,
1078
+ "learning_rate": 2.5690284845196923e-06,
1079
+ "loss": 0.7503,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.75,
1084
+ "grad_norm": 0.017777133602865168,
1085
+ "learning_rate": 2.3539901583619185e-06,
1086
+ "loss": 0.6796,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.7613636363636362,
1091
+ "grad_norm": 0.017730228650558268,
1092
+ "learning_rate": 2.147904716149135e-06,
1093
+ "loss": 0.7887,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.7727272727272727,
1098
+ "grad_norm": 0.016904387380041325,
1099
+ "learning_rate": 1.9508536317948357e-06,
1100
+ "loss": 0.7028,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.7840909090909092,
1105
+ "grad_norm": 0.017048389518616498,
1106
+ "learning_rate": 1.7629148075653245e-06,
1107
+ "loss": 0.6987,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.7954545454545454,
1112
+ "grad_norm": 0.019231086359691812,
1113
+ "learning_rate": 1.5841625432818057e-06,
1114
+ "loss": 0.7262,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.8068181818181817,
1119
+ "grad_norm": 0.018406406662889105,
1120
+ "learning_rate": 1.4146675069466403e-06,
1121
+ "loss": 0.6232,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.8181818181818183,
1126
+ "grad_norm": 0.01859904836356649,
1127
+ "learning_rate": 1.2544967068054332e-06,
1128
+ "loss": 0.7216,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.8295454545454546,
1133
+ "grad_norm": 0.017748264732114775,
1134
+ "learning_rate": 1.1037134648559794e-06,
1135
+ "loss": 0.66,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.8409090909090908,
1140
+ "grad_norm": 0.019172670841775385,
1141
+ "learning_rate": 9.623773918144897e-07,
1142
+ "loss": 0.6719,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.8522727272727273,
1147
+ "grad_norm": 0.017201032284762996,
1148
+ "learning_rate": 8.305443635490711e-07,
1149
+ "loss": 0.6841,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.8636363636363638,
1154
+ "grad_norm": 0.017602592399586683,
1155
+ "learning_rate": 7.082664989897487e-07,
1156
+ "loss": 0.759,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.875,
1161
+ "grad_norm": 0.01737274402951971,
1162
+ "learning_rate": 5.955921395237318e-07,
1163
+ "loss": 0.6251,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.8863636363636362,
1168
+ "grad_norm": 0.018381873767541995,
1169
+ "learning_rate": 4.925658298840979e-07,
1170
+ "loss": 0.7006,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.8977272727272727,
1175
+ "grad_norm": 0.017002639935913035,
1176
+ "learning_rate": 3.992283005394837e-07,
1177
+ "loss": 0.5917,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.9090909090909092,
1182
+ "grad_norm": 0.017463979654969486,
1183
+ "learning_rate": 3.1561645159166597e-07,
1184
+ "loss": 0.6757,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.9204545454545454,
1189
+ "grad_norm": 0.018406237369712176,
1190
+ "learning_rate": 2.417633381874534e-07,
1191
+ "loss": 0.7824,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.9318181818181817,
1196
+ "grad_norm": 0.017967868873337563,
1197
+ "learning_rate": 1.7769815745066475e-07,
1198
+ "loss": 0.7394,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.9431818181818183,
1203
+ "grad_norm": 0.01623825702144127,
1204
+ "learning_rate": 1.234462369393147e-07,
1205
+ "loss": 0.7684,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.9545454545454546,
1210
+ "grad_norm": 0.017608033119901965,
1211
+ "learning_rate": 7.90290246326042e-08,
1212
+ "loss": 0.7831,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.9659090909090908,
1217
+ "grad_norm": 0.017319359934865306,
1218
+ "learning_rate": 4.4464080451675494e-08,
1219
+ "loss": 0.6974,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.9772727272727273,
1224
+ "grad_norm": 0.017475580158119938,
1225
+ "learning_rate": 1.976506931745392e-08,
1226
+ "loss": 0.7574,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.9886363636363638,
1231
+ "grad_norm": 0.017048411256850495,
1232
+ "learning_rate": 4.941755748361088e-09,
1233
+ "loss": 0.6594,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 2.0,
1238
+ "grad_norm": 0.018638627651477082,
1239
+ "learning_rate": 0.0,
1240
+ "loss": 0.7388,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 2.0,
1245
+ "step": 176,
1246
+ "total_flos": 3054747482324992.0,
1247
+ "train_loss": 0.7215218588032506,
1248
+ "train_runtime": 3666.1508,
1249
+ "train_samples_per_second": 1.53,
1250
+ "train_steps_per_second": 0.048
1251
+ }
1252
+ ],
1253
+ "logging_steps": 1,
1254
+ "max_steps": 176,
1255
+ "num_input_tokens_seen": 0,
1256
+ "num_train_epochs": 2,
1257
+ "save_steps": 500,
1258
+ "stateful_callbacks": {
1259
+ "TrainerControl": {
1260
+ "args": {
1261
+ "should_epoch_stop": false,
1262
+ "should_evaluate": false,
1263
+ "should_log": false,
1264
+ "should_save": true,
1265
+ "should_training_stop": true
1266
+ },
1267
+ "attributes": {}
1268
+ }
1269
+ },
1270
+ "total_flos": 3054747482324992.0,
1271
+ "train_batch_size": 4,
1272
+ "trial_name": null,
1273
+ "trial_params": null
1274
+ }