File size: 1,301 Bytes
8f7c93a
 
 
 
 
 
 
 
 
 
 
 
 
dccfa29
 
 
 
 
8f7c93a
 
 
 
dccfa29
 
 
8f7c93a
 
 
 
dccfa29
8f7c93a
dccfa29
8f7c93a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dccfa29
 
 
8f7c93a
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0482180293501049,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8709677419354839,
      "eval_loss": 2.2650985717773438,
      "eval_runtime": 17.8499,
      "eval_samples_per_second": 173.671,
      "eval_steps_per_second": 5.434,
      "step": 477
    },
    {
      "epoch": 1.0482180293501049,
      "grad_norm": 14.103622436523438,
      "learning_rate": 1.302585604472397e-05,
      "loss": 6.1632,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1431,
  "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": 224151802852992.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.8329290526522004,
    "num_train_epochs": 3,
    "temperature": 4.156866262168391
  }
}