File size: 3,202 Bytes
fcd2aa0
 
 
8465041
fcd2aa0
8465041
fcd2aa0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1aa5302
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7304be8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8465041
 
 
 
 
 
 
fcd2aa0
 
 
 
 
 
 
 
 
 
 
 
 
 
8465041
fcd2aa0
 
 
 
8465041
fcd2aa0
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004253056884635832,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "grad_norm": 0.6668939590454102,
      "learning_rate": 2e-05,
      "loss": 1.7296,
      "step": 1
    },
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 1.7417739629745483,
      "eval_runtime": 17.8476,
      "eval_samples_per_second": 55.47,
      "eval_steps_per_second": 27.735,
      "step": 1
    },
    {
      "epoch": 0.0008506113769271664,
      "grad_norm": 0.6744195222854614,
      "learning_rate": 4e-05,
      "loss": 1.8076,
      "step": 2
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.6603765487670898,
      "learning_rate": 6e-05,
      "loss": 1.7598,
      "step": 3
    },
    {
      "epoch": 0.0012759170653907496,
      "eval_loss": 1.7383559942245483,
      "eval_runtime": 17.3157,
      "eval_samples_per_second": 57.174,
      "eval_steps_per_second": 28.587,
      "step": 3
    },
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 0.7473107576370239,
      "learning_rate": 8e-05,
      "loss": 1.7205,
      "step": 4
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 0.8140320181846619,
      "learning_rate": 0.0001,
      "loss": 1.7428,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.6843786835670471,
      "learning_rate": 0.00012,
      "loss": 1.7149,
      "step": 6
    },
    {
      "epoch": 0.002551834130781499,
      "eval_loss": 1.6993428468704224,
      "eval_runtime": 17.4921,
      "eval_samples_per_second": 56.597,
      "eval_steps_per_second": 28.298,
      "step": 6
    },
    {
      "epoch": 0.0029771398192450825,
      "grad_norm": 0.8122773766517639,
      "learning_rate": 0.00014,
      "loss": 1.8709,
      "step": 7
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 0.7426367998123169,
      "learning_rate": 0.00016,
      "loss": 1.5237,
      "step": 8
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.7333535552024841,
      "learning_rate": 0.00018,
      "loss": 1.6058,
      "step": 9
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.5814273357391357,
      "eval_runtime": 17.4785,
      "eval_samples_per_second": 56.641,
      "eval_steps_per_second": 28.321,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 0.8329681158065796,
      "learning_rate": 0.0002,
      "loss": 1.6524,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}