File size: 1,499 Bytes
5d096a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
63
64
65
66
67
68
69
70
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.50161874294281,
      "learning_rate": 3.6e-05,
      "loss": 3.9829,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.897646188735962,
      "learning_rate": 7.6e-05,
      "loss": 2.5299,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8085771799087524,
      "learning_rate": 0.000116,
      "loss": 0.8638,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7201354503631592,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.4168,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4432106614112854,
      "learning_rate": 0.000196,
      "loss": 0.3878,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 75,
  "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": 7.03007243108352e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}