File size: 1,501 Bytes
e975b87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011265622249603943,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005632811124801971,
      "grad_norm": 12.581334114074707,
      "learning_rate": 1e-05,
      "loss": 60.8259,
      "step": 1
    },
    {
      "epoch": 0.0005632811124801971,
      "eval_loss": 3.8450818061828613,
      "eval_runtime": 606.5788,
      "eval_samples_per_second": 4.929,
      "eval_steps_per_second": 2.465,
      "step": 1
    },
    {
      "epoch": 0.0011265622249603943,
      "grad_norm": 11.610177040100098,
      "learning_rate": 2e-05,
      "loss": 61.5924,
      "step": 2
    },
    {
      "epoch": 0.0011265622249603943,
      "eval_loss": 3.8027493953704834,
      "eval_runtime": 624.7617,
      "eval_samples_per_second": 4.786,
      "eval_steps_per_second": 2.393,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2402405132009472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}