File size: 1,566 Bytes
1794980
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 1.10453200340271,
  "best_model_checkpoint": "outputs/checkpoint-92",
  "epoch": 1.9865047233468287,
  "eval_steps": 500,
  "global_step": 92,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4318488529014845,
      "grad_norm": 0.5840024948120117,
      "learning_rate": 4e-05,
      "loss": 1.9547,
      "step": 20
    },
    {
      "epoch": 0.863697705802969,
      "grad_norm": 0.4871944487094879,
      "learning_rate": 8e-05,
      "loss": 1.8203,
      "step": 40
    },
    {
      "epoch": 0.9932523616734144,
      "eval_loss": 1.5045615434646606,
      "eval_runtime": 13.3054,
      "eval_samples_per_second": 27.959,
      "eval_steps_per_second": 3.532,
      "step": 46
    },
    {
      "epoch": 1.2955465587044535,
      "grad_norm": 0.6788378953933716,
      "learning_rate": 0.00012,
      "loss": 1.6913,
      "step": 60
    },
    {
      "epoch": 1.7273954116059378,
      "grad_norm": 0.8430602550506592,
      "learning_rate": 0.00016,
      "loss": 1.4654,
      "step": 80
    },
    {
      "epoch": 1.9865047233468287,
      "eval_loss": 1.10453200340271,
      "eval_runtime": 13.2625,
      "eval_samples_per_second": 28.049,
      "eval_steps_per_second": 3.544,
      "step": 92
    }
  ],
  "logging_steps": 20,
  "max_steps": 782,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 17,
  "save_steps": 500,
  "total_flos": 7088772724125696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}