File size: 1,453 Bytes
ead62c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.1389521640091116,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2847380410022779,
      "grad_norm": 2.7607381343841553,
      "learning_rate": 4.525436598329537e-05,
      "loss": 0.1616,
      "step": 500
    },
    {
      "epoch": 0.5694760820045558,
      "grad_norm": 0.94535231590271,
      "learning_rate": 4.050873196659074e-05,
      "loss": 0.0728,
      "step": 1000
    },
    {
      "epoch": 0.8542141230068337,
      "grad_norm": 2.5376665592193604,
      "learning_rate": 3.5763097949886106e-05,
      "loss": 0.063,
      "step": 1500
    },
    {
      "epoch": 1.1389521640091116,
      "grad_norm": 1.2084846496582031,
      "learning_rate": 3.1017463933181475e-05,
      "loss": 0.0425,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 5268,
  "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": 339051956562216.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}