File size: 6,170 Bytes
a3b13e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7894736842105263,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 1.4201377630233765,
      "learning_rate": 2e-05,
      "loss": 1.2567,
      "step": 1
    },
    {
      "epoch": 0.031578947368421054,
      "eval_loss": 1.2329180240631104,
      "eval_runtime": 9.7426,
      "eval_samples_per_second": 4.106,
      "eval_steps_per_second": 1.026,
      "step": 1
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.568509817123413,
      "learning_rate": 4e-05,
      "loss": 1.3621,
      "step": 2
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.3656419515609741,
      "learning_rate": 6e-05,
      "loss": 1.3324,
      "step": 3
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.3824914693832397,
      "learning_rate": 8e-05,
      "loss": 1.2106,
      "step": 4
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.1639671325683594,
      "learning_rate": 0.0001,
      "loss": 1.0618,
      "step": 5
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 1.0954365730285645,
      "eval_runtime": 9.9704,
      "eval_samples_per_second": 4.012,
      "eval_steps_per_second": 1.003,
      "step": 5
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.0370177030563354,
      "learning_rate": 0.00012,
      "loss": 1.0542,
      "step": 6
    },
    {
      "epoch": 0.22105263157894736,
      "grad_norm": 0.7691447138786316,
      "learning_rate": 0.00014,
      "loss": 1.0324,
      "step": 7
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 0.8053244948387146,
      "learning_rate": 0.00016,
      "loss": 1.0138,
      "step": 8
    },
    {
      "epoch": 0.28421052631578947,
      "grad_norm": 1.1447694301605225,
      "learning_rate": 0.00018,
      "loss": 1.0227,
      "step": 9
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.7161327004432678,
      "learning_rate": 0.0002,
      "loss": 0.8714,
      "step": 10
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 0.8887165188789368,
      "eval_runtime": 9.9898,
      "eval_samples_per_second": 4.004,
      "eval_steps_per_second": 1.001,
      "step": 10
    },
    {
      "epoch": 0.3473684210526316,
      "grad_norm": 0.8024160861968994,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.87,
      "step": 11
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 0.6736723184585571,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.9436,
      "step": 12
    },
    {
      "epoch": 0.4105263157894737,
      "grad_norm": 0.4639568626880646,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.9028,
      "step": 13
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 0.4748899042606354,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.8735,
      "step": 14
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.5926955938339233,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.9889,
      "step": 15
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 0.810930609703064,
      "eval_runtime": 9.9943,
      "eval_samples_per_second": 4.002,
      "eval_steps_per_second": 1.001,
      "step": 15
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.4821624755859375,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.8502,
      "step": 16
    },
    {
      "epoch": 0.5368421052631579,
      "grad_norm": 0.43275609612464905,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.7635,
      "step": 17
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 0.5297432541847229,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7952,
      "step": 18
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5860052704811096,
      "learning_rate": 0.0001760405965600031,
      "loss": 1.0571,
      "step": 19
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.47979608178138733,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7376,
      "step": 20
    },
    {
      "epoch": 0.631578947368421,
      "eval_loss": 0.779615044593811,
      "eval_runtime": 9.9911,
      "eval_samples_per_second": 4.004,
      "eval_steps_per_second": 1.001,
      "step": 20
    },
    {
      "epoch": 0.6631578947368421,
      "grad_norm": 0.36290550231933594,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.7565,
      "step": 21
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 0.43947532773017883,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.7572,
      "step": 22
    },
    {
      "epoch": 0.7263157894736842,
      "grad_norm": 0.7117337584495544,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.8235,
      "step": 23
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 0.41661393642425537,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.7186,
      "step": 24
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.43488454818725586,
      "learning_rate": 0.000138268343236509,
      "loss": 0.8079,
      "step": 25
    },
    {
      "epoch": 0.7894736842105263,
      "eval_loss": 0.7661096453666687,
      "eval_runtime": 9.9986,
      "eval_samples_per_second": 4.001,
      "eval_steps_per_second": 1.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.56415462670336e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}