File size: 1,404 Bytes
3847fcd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.680965147453083,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7321488261222839,
      "eval_loss": 0.5215846300125122,
      "eval_runtime": 9.3633,
      "eval_samples_per_second": 318.585,
      "eval_steps_per_second": 19.972,
      "step": 373
    },
    {
      "epoch": 1.3404825737265416,
      "grad_norm": 13.217938423156738,
      "learning_rate": 2.418286940875578e-06,
      "loss": 0.5967,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7723767757415771,
      "eval_loss": 0.45723703503608704,
      "eval_runtime": 9.2866,
      "eval_samples_per_second": 321.216,
      "eval_steps_per_second": 20.137,
      "step": 746
    },
    {
      "epoch": 2.680965147453083,
      "grad_norm": 15.163392066955566,
      "learning_rate": 2.043939117210628e-06,
      "loss": 0.4683,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3730,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5616578454487560.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.7926347645405278e-06,
    "per_device_train_batch_size": 32
  }
}