File size: 1,248 Bytes
f90d8e1
 
 
 
 
 
 
 
 
 
 
 
2f657fc
f90d8e1
2f657fc
f90d8e1
 
 
 
2f657fc
f90d8e1
2f657fc
f90d8e1
 
 
 
 
 
2f657fc
 
 
 
f90d8e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.0,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 1.5954439640045166,
      "learning_rate": 0.0001,
      "loss": 8.9222,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6375588178634644,
      "learning_rate": 0.0,
      "loss": 2.1991,
      "step": 2
    },
    {
      "epoch": 1.0,
      "step": 2,
      "total_flos": 3290561496960.0,
      "train_loss": 5.560663461685181,
      "train_runtime": 11.683,
      "train_samples_per_second": 3.424,
      "train_steps_per_second": 0.171
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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
}