File size: 3,213 Bytes
9315e44
 
 
44c537f
9315e44
44c537f
9315e44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
402fb34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5f637d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44c537f
 
 
 
 
 
 
9315e44
 
 
 
 
 
 
 
 
 
 
 
 
 
44c537f
9315e44
 
 
 
44c537f
9315e44
 
 
 
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": 0.0018389959082341042,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018389959082341041,
      "grad_norm": 0.2995776832103729,
      "learning_rate": 2e-05,
      "loss": 1.1687,
      "step": 1
    },
    {
      "epoch": 0.00018389959082341041,
      "eval_loss": 1.2216600179672241,
      "eval_runtime": 110.581,
      "eval_samples_per_second": 20.709,
      "eval_steps_per_second": 10.354,
      "step": 1
    },
    {
      "epoch": 0.00036779918164682083,
      "grad_norm": 0.4239529073238373,
      "learning_rate": 4e-05,
      "loss": 1.3116,
      "step": 2
    },
    {
      "epoch": 0.0005516987724702312,
      "grad_norm": 0.45381972193717957,
      "learning_rate": 6e-05,
      "loss": 1.3455,
      "step": 3
    },
    {
      "epoch": 0.0005516987724702312,
      "eval_loss": 1.217912197113037,
      "eval_runtime": 110.387,
      "eval_samples_per_second": 20.745,
      "eval_steps_per_second": 10.373,
      "step": 3
    },
    {
      "epoch": 0.0007355983632936417,
      "grad_norm": 0.35487285256385803,
      "learning_rate": 8e-05,
      "loss": 1.2765,
      "step": 4
    },
    {
      "epoch": 0.0009194979541170521,
      "grad_norm": 0.3256043493747711,
      "learning_rate": 0.0001,
      "loss": 1.2646,
      "step": 5
    },
    {
      "epoch": 0.0011033975449404624,
      "grad_norm": 0.29252171516418457,
      "learning_rate": 0.00012,
      "loss": 1.1082,
      "step": 6
    },
    {
      "epoch": 0.0011033975449404624,
      "eval_loss": 1.173251986503601,
      "eval_runtime": 110.4161,
      "eval_samples_per_second": 20.74,
      "eval_steps_per_second": 10.37,
      "step": 6
    },
    {
      "epoch": 0.001287297135763873,
      "grad_norm": 0.3630172312259674,
      "learning_rate": 0.00014,
      "loss": 1.2261,
      "step": 7
    },
    {
      "epoch": 0.0014711967265872833,
      "grad_norm": 0.3279069662094116,
      "learning_rate": 0.00016,
      "loss": 1.1697,
      "step": 8
    },
    {
      "epoch": 0.0016550963174106939,
      "grad_norm": 0.31991538405418396,
      "learning_rate": 0.00018,
      "loss": 1.0302,
      "step": 9
    },
    {
      "epoch": 0.0016550963174106939,
      "eval_loss": 1.02601158618927,
      "eval_runtime": 110.4765,
      "eval_samples_per_second": 20.728,
      "eval_steps_per_second": 10.364,
      "step": 9
    },
    {
      "epoch": 0.0018389959082341042,
      "grad_norm": 0.3872000277042389,
      "learning_rate": 0.0002,
      "loss": 1.1082,
      "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": 1353080297226240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}