File size: 3,198 Bytes
6cb243a
 
 
ab21736
6cb243a
ab21736
6cb243a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bdc4c53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db0cc85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab21736
 
 
 
 
 
 
6cb243a
 
 
 
 
 
 
 
 
 
 
 
 
 
ab21736
6cb243a
 
 
 
ab21736
6cb243a
 
 
 
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": 0.005961251862891207,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005961251862891207,
      "grad_norm": 14.602910041809082,
      "learning_rate": 2e-05,
      "loss": 10.8252,
      "step": 1
    },
    {
      "epoch": 0.0005961251862891207,
      "eval_loss": 11.547547340393066,
      "eval_runtime": 13.0684,
      "eval_samples_per_second": 54.1,
      "eval_steps_per_second": 27.088,
      "step": 1
    },
    {
      "epoch": 0.0011922503725782414,
      "grad_norm": 15.501795768737793,
      "learning_rate": 4e-05,
      "loss": 10.6857,
      "step": 2
    },
    {
      "epoch": 0.0017883755588673621,
      "grad_norm": 14.309174537658691,
      "learning_rate": 6e-05,
      "loss": 12.2687,
      "step": 3
    },
    {
      "epoch": 0.0017883755588673621,
      "eval_loss": 11.453269004821777,
      "eval_runtime": 12.9917,
      "eval_samples_per_second": 54.419,
      "eval_steps_per_second": 27.248,
      "step": 3
    },
    {
      "epoch": 0.002384500745156483,
      "grad_norm": 14.269388198852539,
      "learning_rate": 8e-05,
      "loss": 10.821,
      "step": 4
    },
    {
      "epoch": 0.0029806259314456036,
      "grad_norm": 17.612112045288086,
      "learning_rate": 0.0001,
      "loss": 12.8865,
      "step": 5
    },
    {
      "epoch": 0.0035767511177347243,
      "grad_norm": 18.52869415283203,
      "learning_rate": 0.00012,
      "loss": 10.7903,
      "step": 6
    },
    {
      "epoch": 0.0035767511177347243,
      "eval_loss": 9.825249671936035,
      "eval_runtime": 13.2456,
      "eval_samples_per_second": 53.376,
      "eval_steps_per_second": 26.726,
      "step": 6
    },
    {
      "epoch": 0.004172876304023845,
      "grad_norm": 23.56140899658203,
      "learning_rate": 0.00014,
      "loss": 9.075,
      "step": 7
    },
    {
      "epoch": 0.004769001490312966,
      "grad_norm": 23.681167602539062,
      "learning_rate": 0.00016,
      "loss": 8.3211,
      "step": 8
    },
    {
      "epoch": 0.005365126676602086,
      "grad_norm": 28.13359832763672,
      "learning_rate": 0.00018,
      "loss": 7.8672,
      "step": 9
    },
    {
      "epoch": 0.005365126676602086,
      "eval_loss": 4.785869598388672,
      "eval_runtime": 13.1762,
      "eval_samples_per_second": 53.658,
      "eval_steps_per_second": 26.867,
      "step": 9
    },
    {
      "epoch": 0.005961251862891207,
      "grad_norm": 28.6697998046875,
      "learning_rate": 0.0002,
      "loss": 4.9506,
      "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": 501714738216960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}