File size: 6,689 Bytes
89b8212
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5617977528089888,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 0.15547114610671997,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9596,
      "step": 1
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 0.13959258794784546,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9643,
      "step": 2
    },
    {
      "epoch": 0.1348314606741573,
      "grad_norm": 0.14470240473747253,
      "learning_rate": 3e-06,
      "loss": 1.1562,
      "step": 3
    },
    {
      "epoch": 0.1797752808988764,
      "grad_norm": 0.16597306728363037,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.1067,
      "step": 4
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.14703088998794556,
      "learning_rate": 5e-06,
      "loss": 0.9694,
      "step": 5
    },
    {
      "epoch": 0.2696629213483146,
      "grad_norm": 0.15088129043579102,
      "learning_rate": 6e-06,
      "loss": 1.0045,
      "step": 6
    },
    {
      "epoch": 0.3146067415730337,
      "grad_norm": 0.16761414706707,
      "learning_rate": 7e-06,
      "loss": 0.9547,
      "step": 7
    },
    {
      "epoch": 0.3595505617977528,
      "grad_norm": 0.14696507155895233,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0284,
      "step": 8
    },
    {
      "epoch": 0.4044943820224719,
      "grad_norm": 0.19629372656345367,
      "learning_rate": 9e-06,
      "loss": 0.9615,
      "step": 9
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.18038448691368103,
      "learning_rate": 1e-05,
      "loss": 1.0544,
      "step": 10
    },
    {
      "epoch": 0.4943820224719101,
      "grad_norm": 0.22929255664348602,
      "learning_rate": 9.992134075089085e-06,
      "loss": 1.0329,
      "step": 11
    },
    {
      "epoch": 0.5393258426966292,
      "grad_norm": 0.2177729308605194,
      "learning_rate": 9.968561049466214e-06,
      "loss": 0.9876,
      "step": 12
    },
    {
      "epoch": 0.5842696629213483,
      "grad_norm": 0.2739273011684418,
      "learning_rate": 9.92935509259118e-06,
      "loss": 0.9326,
      "step": 13
    },
    {
      "epoch": 0.6292134831460674,
      "grad_norm": 0.2714334726333618,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.0127,
      "step": 14
    },
    {
      "epoch": 0.6741573033707865,
      "grad_norm": 0.318387508392334,
      "learning_rate": 9.804586609725499e-06,
      "loss": 1.1761,
      "step": 15
    },
    {
      "epoch": 0.7191011235955056,
      "grad_norm": 0.2760864198207855,
      "learning_rate": 9.719416651541839e-06,
      "loss": 0.9729,
      "step": 16
    },
    {
      "epoch": 0.7640449438202247,
      "grad_norm": 0.27431851625442505,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.9192,
      "step": 17
    },
    {
      "epoch": 0.8089887640449438,
      "grad_norm": 0.24467918276786804,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.8674,
      "step": 18
    },
    {
      "epoch": 0.8539325842696629,
      "grad_norm": 0.25415292382240295,
      "learning_rate": 9.376117109543769e-06,
      "loss": 0.9619,
      "step": 19
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.26627272367477417,
      "learning_rate": 9.233620996141421e-06,
      "loss": 0.8804,
      "step": 20
    },
    {
      "epoch": 0.9438202247191011,
      "grad_norm": 0.24633091688156128,
      "learning_rate": 9.077804344796302e-06,
      "loss": 0.8213,
      "step": 21
    },
    {
      "epoch": 0.9887640449438202,
      "grad_norm": 0.21531835198402405,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.8679,
      "step": 22
    },
    {
      "epoch": 1.0224719101123596,
      "grad_norm": 0.20492973923683167,
      "learning_rate": 8.728210824415829e-06,
      "loss": 0.7908,
      "step": 23
    },
    {
      "epoch": 1.0674157303370786,
      "grad_norm": 0.23310156166553497,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.9771,
      "step": 24
    },
    {
      "epoch": 1.1123595505617978,
      "grad_norm": 0.17484751343727112,
      "learning_rate": 8.331732889760021e-06,
      "loss": 0.8474,
      "step": 25
    },
    {
      "epoch": 1.1573033707865168,
      "grad_norm": 0.14636008441448212,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.8394,
      "step": 26
    },
    {
      "epoch": 1.202247191011236,
      "grad_norm": 0.11921321600675583,
      "learning_rate": 7.89335648089903e-06,
      "loss": 0.9378,
      "step": 27
    },
    {
      "epoch": 1.247191011235955,
      "grad_norm": 0.11381018161773682,
      "learning_rate": 7.660160382576683e-06,
      "loss": 0.7725,
      "step": 28
    },
    {
      "epoch": 1.2921348314606742,
      "grad_norm": 0.10614118725061417,
      "learning_rate": 7.4185944355261996e-06,
      "loss": 0.8286,
      "step": 29
    },
    {
      "epoch": 1.3370786516853932,
      "grad_norm": 0.10510330647230148,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.8442,
      "step": 30
    },
    {
      "epoch": 1.3820224719101124,
      "grad_norm": 0.11109460890293121,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.7933,
      "step": 31
    },
    {
      "epoch": 1.4269662921348314,
      "grad_norm": 0.10454461723566055,
      "learning_rate": 6.651395309775837e-06,
      "loss": 0.8542,
      "step": 32
    },
    {
      "epoch": 1.4719101123595506,
      "grad_norm": 0.1184382364153862,
      "learning_rate": 6.384177557124247e-06,
      "loss": 0.9169,
      "step": 33
    },
    {
      "epoch": 1.5168539325842696,
      "grad_norm": 0.10408931970596313,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.833,
      "step": 34
    },
    {
      "epoch": 1.5617977528089888,
      "grad_norm": 0.10440591722726822,
      "learning_rate": 5.837531116523683e-06,
      "loss": 0.7474,
      "step": 35
    }
  ],
  "logging_steps": 1,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.93766215334101e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}