File size: 5,204 Bytes
b0624b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 2.7491408934707904,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10996563573883161,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10996563573883161,
      "eval_loss": NaN,
      "eval_runtime": 3.2115,
      "eval_samples_per_second": 15.569,
      "eval_steps_per_second": 4.048,
      "step": 1
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": NaN,
      "learning_rate": 9.967189933441243e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": NaN,
      "learning_rate": 9.869238178417235e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": NaN,
      "learning_rate": 9.707573092084368e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": NaN,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.7697594501718213,
      "grad_norm": NaN,
      "learning_rate": 9.203427396521454e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8797250859106529,
      "grad_norm": NaN,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": NaN,
      "learning_rate": 8.484051962083579e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.0996563573883162,
      "grad_norm": NaN,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.2096219931271477,
      "grad_norm": NaN,
      "learning_rate": 7.591254274196959e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.3195876288659794,
      "grad_norm": NaN,
      "learning_rate": 7.095721991691411e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.429553264604811,
      "grad_norm": NaN,
      "learning_rate": 6.576920489294011e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.5395189003436425,
      "grad_norm": NaN,
      "learning_rate": 6.042415061148954e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.7594501718213058,
      "grad_norm": NaN,
      "learning_rate": 4.9575849388510473e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.8694158075601375,
      "grad_norm": NaN,
      "learning_rate": 4.423079510705992e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": NaN,
      "learning_rate": 3.904278008308589e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.089347079037801,
      "grad_norm": NaN,
      "learning_rate": 3.408745725803042e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.1993127147766325,
      "grad_norm": NaN,
      "learning_rate": 2.9437086397097995e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 2.3092783505154637,
      "grad_norm": NaN,
      "learning_rate": 2.515948037916423e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 2.4192439862542954,
      "grad_norm": NaN,
      "learning_rate": 2.1317016332300447e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 2.529209621993127,
      "grad_norm": NaN,
      "learning_rate": 1.7965726034785466e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 2.6391752577319587,
      "grad_norm": NaN,
      "learning_rate": 1.515447884560556e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.7491408934707904,
      "grad_norm": NaN,
      "learning_rate": 1.292426907915634e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.7491408934707904,
      "eval_loss": NaN,
      "eval_runtime": 3.2654,
      "eval_samples_per_second": 15.312,
      "eval_steps_per_second": 3.981,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 28,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}