File size: 1,361 Bytes
c108b9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 19.736842105263158,
  "eval_steps": 500,
  "global_step": 2250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.385964912280702,
      "grad_norm": 9.875,
      "learning_rate": 2.5e-05,
      "loss": 2.8556,
      "step": 500
    },
    {
      "epoch": 8.771929824561404,
      "grad_norm": 10.625,
      "learning_rate": 5e-05,
      "loss": 1.9744,
      "step": 1000
    },
    {
      "epoch": 13.157894736842104,
      "grad_norm": 21.625,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7097,
      "step": 1500
    },
    {
      "epoch": 17.54385964912281,
      "grad_norm": 16.375,
      "learning_rate": 0.0001,
      "loss": 1.4299,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 4560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 150,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.6905952837632e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}