File size: 1,459 Bytes
e81fef3
 
 
15a929e
e81fef3
15a929e
e81fef3
 
 
 
 
 
 
 
 
 
bea636c
 
 
 
 
 
 
effb25a
 
 
 
 
 
 
15a929e
 
 
 
 
 
 
e81fef3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15a929e
e81fef3
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8312551953449709,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.6509162187576294,
      "learning_rate": 1.862011637572735e-05,
      "loss": 0.5079,
      "step": 500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 0.8360931873321533,
      "learning_rate": 1.72346910501524e-05,
      "loss": 0.4047,
      "step": 1000
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.43808215856552124,
      "learning_rate": 1.5849265724577447e-05,
      "loss": 0.3844,
      "step": 1500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 0.4758487045764923,
      "learning_rate": 1.4463840399002496e-05,
      "loss": 0.3804,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 7218,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4871663124480000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}