File size: 1,494 Bytes
a076068
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 5.0,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.3881066143512726,
      "learning_rate": 9.070345120512436e-05,
      "loss": 1.2224,
      "step": 50
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.4778837561607361,
      "learning_rate": 6.142689677583446e-05,
      "loss": 0.3161,
      "step": 100
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.5317807793617249,
      "learning_rate": 2.6469889419018985e-05,
      "loss": 0.199,
      "step": 150
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.3530173897743225,
      "learning_rate": 3.2099935489722897e-06,
      "loss": 0.146,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.83786931224576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}