File size: 1,250 Bytes
c3dacbf
 
 
5472aba
c3dacbf
5472aba
c3dacbf
 
 
 
 
5472aba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3dacbf
 
 
5472aba
c3dacbf
5472aba
c3dacbf
 
 
 
 
 
 
5472aba
 
c3dacbf
 
 
 
5472aba
c3dacbf
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0,
      "grad_norm": 0.0691056177020073,
      "learning_rate": 0.0001,
      "loss": 3.3586,
      "step": 2
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12557776272296906,
      "learning_rate": 0.0,
      "loss": 3.3313,
      "step": 4
    },
    {
      "epoch": 4.0,
      "step": 4,
      "total_flos": 3290561496960.0,
      "train_loss": 3.344943642616272,
      "train_runtime": 14.0154,
      "train_samples_per_second": 1.427,
      "train_steps_per_second": 0.285
    }
  ],
  "logging_steps": 2,
  "max_steps": 4,
  "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": 3290561496960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}