File size: 5,152 Bytes
eea0d77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9938398357289527,
  "eval_steps": 500,
  "global_step": 121,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 19.88043212890625,
      "learning_rate": 7.692307692307694e-06,
      "loss": 2.1842,
      "step": 5
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 4.474620819091797,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0443,
      "step": 10
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 3.885227680206299,
      "learning_rate": 1.9983081582712684e-05,
      "loss": 0.7151,
      "step": 15
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 8.389646530151367,
      "learning_rate": 1.9793406217655516e-05,
      "loss": 0.5374,
      "step": 20
    },
    {
      "epoch": 0.2053388090349076,
      "grad_norm": 3.452284812927246,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.4208,
      "step": 25
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 4.10204553604126,
      "learning_rate": 1.880201391180111e-05,
      "loss": 0.3896,
      "step": 30
    },
    {
      "epoch": 0.2874743326488706,
      "grad_norm": 3.205411911010742,
      "learning_rate": 1.802123192755044e-05,
      "loss": 0.3879,
      "step": 35
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 2.1292169094085693,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.3327,
      "step": 40
    },
    {
      "epoch": 0.36960985626283366,
      "grad_norm": 7.674350261688232,
      "learning_rate": 1.5971585917027864e-05,
      "loss": 0.2916,
      "step": 45
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 4.424239158630371,
      "learning_rate": 1.4746003697476406e-05,
      "loss": 0.283,
      "step": 50
    },
    {
      "epoch": 0.4517453798767967,
      "grad_norm": 4.189895153045654,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.2489,
      "step": 55
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 3.7470364570617676,
      "learning_rate": 1.2022175723320382e-05,
      "loss": 0.2305,
      "step": 60
    },
    {
      "epoch": 0.5338809034907598,
      "grad_norm": 5.460855960845947,
      "learning_rate": 1.0581448289104759e-05,
      "loss": 0.2274,
      "step": 65
    },
    {
      "epoch": 0.5749486652977412,
      "grad_norm": 4.557585716247559,
      "learning_rate": 9.128442572523418e-06,
      "loss": 0.2282,
      "step": 70
    },
    {
      "epoch": 0.6160164271047228,
      "grad_norm": 3.090021848678589,
      "learning_rate": 7.6938412925756e-06,
      "loss": 0.2111,
      "step": 75
    },
    {
      "epoch": 0.6570841889117043,
      "grad_norm": 7.4640021324157715,
      "learning_rate": 6.3079385268731575e-06,
      "loss": 0.2015,
      "step": 80
    },
    {
      "epoch": 0.6981519507186859,
      "grad_norm": 6.5390543937683105,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.1932,
      "step": 85
    },
    {
      "epoch": 0.7392197125256673,
      "grad_norm": 4.162878513336182,
      "learning_rate": 3.797645087317401e-06,
      "loss": 0.1877,
      "step": 90
    },
    {
      "epoch": 0.7802874743326489,
      "grad_norm": 2.679852247238159,
      "learning_rate": 2.726263584269513e-06,
      "loss": 0.1831,
      "step": 95
    },
    {
      "epoch": 0.8213552361396304,
      "grad_norm": 2.6465625762939453,
      "learning_rate": 1.808479557110081e-06,
      "loss": 0.1795,
      "step": 100
    },
    {
      "epoch": 0.8624229979466119,
      "grad_norm": 3.555863857269287,
      "learning_rate": 1.0636735967658785e-06,
      "loss": 0.1761,
      "step": 105
    },
    {
      "epoch": 0.9034907597535934,
      "grad_norm": 1.911604642868042,
      "learning_rate": 5.075735642696611e-07,
      "loss": 0.1744,
      "step": 110
    },
    {
      "epoch": 0.944558521560575,
      "grad_norm": 1.368584394454956,
      "learning_rate": 1.519224698779198e-07,
      "loss": 0.1727,
      "step": 115
    },
    {
      "epoch": 0.9856262833675564,
      "grad_norm": 0.634205162525177,
      "learning_rate": 4.230499177994007e-09,
      "loss": 0.1721,
      "step": 120
    },
    {
      "epoch": 0.9938398357289527,
      "step": 121,
      "total_flos": 3.4469526241489715e+17,
      "train_loss": 0.38872497202443684,
      "train_runtime": 8476.2474,
      "train_samples_per_second": 8.258,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 5,
  "max_steps": 121,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4469526241489715e+17,
  "train_batch_size": 18,
  "trial_name": null,
  "trial_params": null
}