File size: 1,458 Bytes
53796cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.38351285457611084,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2186,
      "step": 10
    },
    {
      "grad_norm": 0.453412801027298,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.176,
      "step": 20
    },
    {
      "grad_norm": 0.3962445557117462,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1279,
      "step": 30
    },
    {
      "grad_norm": 0.33287128806114197,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0833,
      "step": 40
    },
    {
      "grad_norm": 0.34996676445007324,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0655,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}