File size: 5,002 Bytes
97bc9aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 24.98804780876494,
  "eval_steps": 500,
  "global_step": 1568,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9880478087649402,
      "grad_norm": 0.2889673113822937,
      "learning_rate": 0.0002974798061389337,
      "loss": 0.7635,
      "step": 62
    },
    {
      "epoch": 1.9920318725099602,
      "grad_norm": 0.34704622626304626,
      "learning_rate": 0.0002944264943457189,
      "loss": 0.5643,
      "step": 125
    },
    {
      "epoch": 2.99601593625498,
      "grad_norm": 0.32337236404418945,
      "learning_rate": 0.00029137318255250403,
      "loss": 0.47,
      "step": 188
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5398977994918823,
      "learning_rate": 0.00028831987075928915,
      "loss": 0.3844,
      "step": 251
    },
    {
      "epoch": 4.98804780876494,
      "grad_norm": 0.4496667981147766,
      "learning_rate": 0.0002853150242326333,
      "loss": 0.3176,
      "step": 313
    },
    {
      "epoch": 5.99203187250996,
      "grad_norm": 0.4373694062232971,
      "learning_rate": 0.0002822617124394184,
      "loss": 0.2479,
      "step": 376
    },
    {
      "epoch": 6.99601593625498,
      "grad_norm": 0.5146955251693726,
      "learning_rate": 0.0002792084006462035,
      "loss": 0.1915,
      "step": 439
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.5761932134628296,
      "learning_rate": 0.00027615508885298865,
      "loss": 0.1465,
      "step": 502
    },
    {
      "epoch": 8.98804780876494,
      "grad_norm": 0.46838995814323425,
      "learning_rate": 0.00027315024232633277,
      "loss": 0.1184,
      "step": 564
    },
    {
      "epoch": 9.99203187250996,
      "grad_norm": 0.39898747205734253,
      "learning_rate": 0.0002700969305331179,
      "loss": 0.0931,
      "step": 627
    },
    {
      "epoch": 10.996015936254981,
      "grad_norm": 0.4515402615070343,
      "learning_rate": 0.000267043618739903,
      "loss": 0.0776,
      "step": 690
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.2392401546239853,
      "learning_rate": 0.0002639903069466882,
      "loss": 0.0685,
      "step": 753
    },
    {
      "epoch": 12.98804780876494,
      "grad_norm": 0.3774527609348297,
      "learning_rate": 0.00026098546042003227,
      "loss": 0.0622,
      "step": 815
    },
    {
      "epoch": 13.99203187250996,
      "grad_norm": 0.22206874191761017,
      "learning_rate": 0.0002579321486268174,
      "loss": 0.0534,
      "step": 878
    },
    {
      "epoch": 14.996015936254981,
      "grad_norm": 0.25606569647789,
      "learning_rate": 0.00025487883683360257,
      "loss": 0.0504,
      "step": 941
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.3752060830593109,
      "learning_rate": 0.0002518255250403877,
      "loss": 0.0469,
      "step": 1004
    },
    {
      "epoch": 16.98804780876494,
      "grad_norm": 0.3305172920227051,
      "learning_rate": 0.0002488206785137318,
      "loss": 0.0445,
      "step": 1066
    },
    {
      "epoch": 17.992031872509962,
      "grad_norm": 0.2901972234249115,
      "learning_rate": 0.00024576736672051694,
      "loss": 0.0418,
      "step": 1129
    },
    {
      "epoch": 18.99601593625498,
      "grad_norm": 0.3044564127922058,
      "learning_rate": 0.0002427140549273021,
      "loss": 0.0425,
      "step": 1192
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.2603231966495514,
      "learning_rate": 0.00023966074313408722,
      "loss": 0.0392,
      "step": 1255
    },
    {
      "epoch": 20.98804780876494,
      "grad_norm": 0.2220539152622223,
      "learning_rate": 0.00023665589660743132,
      "loss": 0.0371,
      "step": 1317
    },
    {
      "epoch": 21.992031872509962,
      "grad_norm": 0.20209918916225433,
      "learning_rate": 0.00023360258481421647,
      "loss": 0.0335,
      "step": 1380
    },
    {
      "epoch": 22.99601593625498,
      "grad_norm": 0.271361380815506,
      "learning_rate": 0.0002305492730210016,
      "loss": 0.034,
      "step": 1443
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.29796579480171204,
      "learning_rate": 0.00022749596122778674,
      "loss": 0.0334,
      "step": 1506
    },
    {
      "epoch": 24.98804780876494,
      "grad_norm": 0.2501268684864044,
      "learning_rate": 0.00022449111470113084,
      "loss": 0.0341,
      "step": 1568
    }
  ],
  "logging_steps": 1,
  "max_steps": 6200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.143078713739837e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}