File size: 2,809 Bytes
f4f75f0
 
 
0825730
f4f75f0
0825730
f4f75f0
 
 
 
 
0fc5ecd
a1d4f52
0825730
a1d4f52
f4f75f0
 
 
0fc5ecd
a1d4f52
0825730
a1d4f52
f4f75f0
 
 
0fc5ecd
a1d4f52
0825730
a1d4f52
f4f75f0
 
 
0fc5ecd
a1d4f52
0825730
a1d4f52
f4f75f0
 
 
0fc5ecd
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
 
a1d4f52
0825730
a1d4f52
0fc5ecd
 
 
0825730
 
a1d4f52
 
 
 
 
f4f75f0
 
 
0825730
f4f75f0
0825730
f4f75f0
 
 
 
 
 
 
 
 
 
 
 
 
a1d4f52
f4f75f0
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.84,
  "eval_steps": 25,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 2.4018948078155518,
      "learning_rate": 0.00018333333333333334,
      "loss": 9.796,
      "step": 1
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.362989902496338,
      "learning_rate": 0.0001666666666666667,
      "loss": 9.5629,
      "step": 2
    },
    {
      "epoch": 0.96,
      "grad_norm": 3.1423513889312744,
      "learning_rate": 0.00015000000000000001,
      "loss": 9.2115,
      "step": 3
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.852221965789795,
      "learning_rate": 0.00013333333333333334,
      "loss": 8.7974,
      "step": 4
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.004337787628174,
      "learning_rate": 0.00011666666666666668,
      "loss": 8.4192,
      "step": 5
    },
    {
      "epoch": 1.92,
      "grad_norm": 2.4463579654693604,
      "learning_rate": 0.0001,
      "loss": 8.0889,
      "step": 6
    },
    {
      "epoch": 2.24,
      "grad_norm": 2.03631854057312,
      "learning_rate": 8.333333333333334e-05,
      "loss": 7.8931,
      "step": 7
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.7664697170257568,
      "learning_rate": 6.666666666666667e-05,
      "loss": 7.7725,
      "step": 8
    },
    {
      "epoch": 2.88,
      "grad_norm": 2.012162685394287,
      "learning_rate": 5e-05,
      "loss": 7.7224,
      "step": 9
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.7454917430877686,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.5964,
      "step": 10
    },
    {
      "epoch": 3.52,
      "grad_norm": 1.905915379524231,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 7.6713,
      "step": 11
    },
    {
      "epoch": 3.84,
      "grad_norm": 1.5737876892089844,
      "learning_rate": 0.0,
      "loss": 7.5365,
      "step": 12
    },
    {
      "epoch": 3.84,
      "step": 12,
      "total_flos": 24492388886460.0,
      "train_loss": 8.339014927546183,
      "train_runtime": 59.862,
      "train_samples_per_second": 3.274,
      "train_steps_per_second": 0.2
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 24492388886460.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}