File size: 5,030 Bytes
8de6aa2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.64,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0256,
      "grad_norm": 0.6669269800186157,
      "learning_rate": 1.9e-05,
      "loss": 8.179115295410156,
      "step": 20
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.5379630327224731,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 8.11802978515625,
      "step": 40
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.5859383940696716,
      "learning_rate": 5.9e-05,
      "loss": 8.041471862792969,
      "step": 60
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.6329635381698608,
      "learning_rate": 7.900000000000001e-05,
      "loss": 7.967082977294922,
      "step": 80
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.7737689018249512,
      "learning_rate": 9.900000000000001e-05,
      "loss": 7.894486999511718,
      "step": 100
    },
    {
      "epoch": 0.1536,
      "grad_norm": 1.0059387683868408,
      "learning_rate": 9.721407624633431e-05,
      "loss": 7.814192199707032,
      "step": 120
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.804948091506958,
      "learning_rate": 9.428152492668623e-05,
      "loss": 7.729258728027344,
      "step": 140
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.9692172408103943,
      "learning_rate": 9.134897360703812e-05,
      "loss": 7.668946838378906,
      "step": 160
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.9547553062438965,
      "learning_rate": 8.841642228739004e-05,
      "loss": 7.622274780273438,
      "step": 180
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.6002941727638245,
      "learning_rate": 8.548387096774195e-05,
      "loss": 7.579273986816406,
      "step": 200
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.8823673725128174,
      "learning_rate": 8.255131964809384e-05,
      "loss": 7.519114685058594,
      "step": 220
    },
    {
      "epoch": 0.3072,
      "grad_norm": 1.0416988134384155,
      "learning_rate": 7.961876832844574e-05,
      "loss": 7.484053039550782,
      "step": 240
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.735251784324646,
      "learning_rate": 7.668621700879765e-05,
      "loss": 7.443171691894531,
      "step": 260
    },
    {
      "epoch": 0.3584,
      "grad_norm": 1.0857356786727905,
      "learning_rate": 7.375366568914957e-05,
      "loss": 7.403555297851563,
      "step": 280
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.9961302280426025,
      "learning_rate": 7.082111436950148e-05,
      "loss": 7.371603393554688,
      "step": 300
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.8889548182487488,
      "learning_rate": 6.788856304985338e-05,
      "loss": 7.352679443359375,
      "step": 320
    },
    {
      "epoch": 0.4352,
      "grad_norm": 1.0873897075653076,
      "learning_rate": 6.495601173020527e-05,
      "loss": 7.3021392822265625,
      "step": 340
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.7345384359359741,
      "learning_rate": 6.202346041055719e-05,
      "loss": 7.2823539733886715,
      "step": 360
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.6853398084640503,
      "learning_rate": 5.90909090909091e-05,
      "loss": 7.260960388183594,
      "step": 380
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.9110084772109985,
      "learning_rate": 5.6158357771260995e-05,
      "loss": 7.228886413574219,
      "step": 400
    },
    {
      "epoch": 0.5376,
      "grad_norm": 1.127113938331604,
      "learning_rate": 5.32258064516129e-05,
      "loss": 7.202789306640625,
      "step": 420
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.7524133324623108,
      "learning_rate": 5.029325513196481e-05,
      "loss": 7.181660461425781,
      "step": 440
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.7863721251487732,
      "learning_rate": 4.736070381231672e-05,
      "loss": 7.178968048095703,
      "step": 460
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.9041445851325989,
      "learning_rate": 4.442815249266862e-05,
      "loss": 7.156215667724609,
      "step": 480
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9909660220146179,
      "learning_rate": 4.149560117302053e-05,
      "loss": 7.125262451171875,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 782,
  "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": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 166311572275200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}