File size: 3,191 Bytes
f92112c
 
 
691f623
f92112c
691f623
f92112c
 
 
 
 
f09aafc
 
f92112c
f09aafc
f92112c
 
 
f09aafc
 
 
 
 
f92112c
 
 
f09aafc
 
f92112c
f09aafc
f92112c
 
 
f09aafc
 
f92112c
f09aafc
f92112c
 
 
f09aafc
 
 
 
 
f92112c
911fefc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58d93c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
691f623
 
 
 
 
 
 
f92112c
 
 
 
 
 
 
 
 
 
 
 
 
 
691f623
f92112c
 
 
 
691f623
f92112c
 
 
 
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": 0.026917900403768506,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026917900403768506,
      "grad_norm": 1.471656084060669,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 1
    },
    {
      "epoch": 0.0026917900403768506,
      "eval_loss": 0.7381964921951294,
      "eval_runtime": 6.6874,
      "eval_samples_per_second": 11.813,
      "eval_steps_per_second": 11.813,
      "step": 1
    },
    {
      "epoch": 0.005383580080753701,
      "grad_norm": 1.4059834480285645,
      "learning_rate": 4e-05,
      "loss": 0.7273,
      "step": 2
    },
    {
      "epoch": 0.008075370121130552,
      "grad_norm": 1.7281467914581299,
      "learning_rate": 6e-05,
      "loss": 0.7709,
      "step": 3
    },
    {
      "epoch": 0.008075370121130552,
      "eval_loss": 0.6940876245498657,
      "eval_runtime": 6.0028,
      "eval_samples_per_second": 13.161,
      "eval_steps_per_second": 13.161,
      "step": 3
    },
    {
      "epoch": 0.010767160161507403,
      "grad_norm": 1.4571020603179932,
      "learning_rate": 8e-05,
      "loss": 0.7401,
      "step": 4
    },
    {
      "epoch": 0.013458950201884253,
      "grad_norm": 1.4379603862762451,
      "learning_rate": 0.0001,
      "loss": 0.7416,
      "step": 5
    },
    {
      "epoch": 0.016150740242261104,
      "grad_norm": 1.3622642755508423,
      "learning_rate": 0.00012,
      "loss": 0.6918,
      "step": 6
    },
    {
      "epoch": 0.016150740242261104,
      "eval_loss": 0.5574197769165039,
      "eval_runtime": 6.066,
      "eval_samples_per_second": 13.023,
      "eval_steps_per_second": 13.023,
      "step": 6
    },
    {
      "epoch": 0.018842530282637954,
      "grad_norm": 1.148888111114502,
      "learning_rate": 0.00014,
      "loss": 0.4991,
      "step": 7
    },
    {
      "epoch": 0.021534320323014805,
      "grad_norm": 1.1360676288604736,
      "learning_rate": 0.00016,
      "loss": 0.446,
      "step": 8
    },
    {
      "epoch": 0.024226110363391656,
      "grad_norm": 1.3324047327041626,
      "learning_rate": 0.00018,
      "loss": 0.4577,
      "step": 9
    },
    {
      "epoch": 0.024226110363391656,
      "eval_loss": 0.40684258937835693,
      "eval_runtime": 6.0984,
      "eval_samples_per_second": 12.954,
      "eval_steps_per_second": 12.954,
      "step": 9
    },
    {
      "epoch": 0.026917900403768506,
      "grad_norm": 1.2041003704071045,
      "learning_rate": 0.0002,
      "loss": 0.4258,
      "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": 2358194416386048.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}