File size: 1,521 Bytes
4cb83d8
 
 
1264118
4cb83d8
1264118
4cb83d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92c20c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cb83d8
 
 
 
 
 
 
 
 
 
 
 
 
 
34a63a0
4cb83d8
 
 
 
1264118
4cb83d8
 
 
 
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": 4.166666666666667,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0833333333333335,
      "grad_norm": 0.33437681198120117,
      "learning_rate": 0.00015151515151515152,
      "loss": 2.0496,
      "step": 25
    },
    {
      "epoch": 2.0833333333333335,
      "eval_loss": 1.1585125923156738,
      "eval_runtime": 1.2434,
      "eval_samples_per_second": 9.651,
      "eval_steps_per_second": 1.608,
      "step": 25
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 0.3806462287902832,
      "learning_rate": 0.00010101010101010102,
      "loss": 1.0128,
      "step": 50
    },
    {
      "epoch": 4.166666666666667,
      "eval_loss": 0.8326404094696045,
      "eval_runtime": 1.129,
      "eval_samples_per_second": 10.629,
      "eval_steps_per_second": 1.772,
      "step": 50
    }
  ],
  "logging_steps": 25,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 132486878822400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}