File size: 1,393 Bytes
3b55157
2c1cd09
3b55157
 
 
 
 
 
 
 
 
 
2c1cd09
 
 
3b55157
 
 
 
2c1cd09
 
 
3b55157
 
 
 
2c1cd09
 
 
 
 
3b55157
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.7588038444519043,
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-1125",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 5.899707794189453,
      "learning_rate": 5.232558139534884e-07,
      "loss": 1.7332,
      "step": 500
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 5.6583170890808105,
      "learning_rate": 1.0465116279069767e-07,
      "loss": 1.7265,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5506458333333333,
      "eval_loss": 1.7588038444519043,
      "eval_runtime": 532.8246,
      "eval_samples_per_second": 90.086,
      "eval_steps_per_second": 2.815,
      "step": 1125
    }
  ],
  "logging_steps": 500,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.581723556118528e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}