File size: 1,767 Bytes
7bf50b0
8693e92
 
7bf50b0
 
 
 
 
 
 
 
 
5eb4efc
 
 
7bf50b0
 
 
 
5eb4efc
 
 
 
 
7bf50b0
 
 
 
5eb4efc
 
 
7bf50b0
8693e92
 
 
 
 
 
 
 
 
7bf50b0
 
 
5eb4efc
7bf50b0
5eb4efc
7bf50b0
 
 
 
 
 
 
 
5eb4efc
7bf50b0
 
 
 
133f056
7bf50b0
 
 
5eb4efc
 
7bf50b0
5eb4efc
7bf50b0
 
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
67
68
69
70
71
{
  "best_metric": 0.608105758140891,
  "best_model_checkpoint": "students_scores_model/run-0/checkpoint-1126",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1126,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8880994671403197,
      "grad_norm": 33.89450454711914,
      "learning_rate": 7.71014137309043e-06,
      "loss": 1.0858,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.568809428898138,
      "eval_loss": 0.9511491060256958,
      "eval_runtime": 37.4937,
      "eval_samples_per_second": 60.01,
      "eval_steps_per_second": 7.521,
      "step": 563
    },
    {
      "epoch": 1.7761989342806395,
      "grad_norm": 20.078083038330078,
      "learning_rate": 1.5518814904303424e-06,
      "loss": 0.876,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.608105758140891,
      "eval_loss": 0.8914819955825806,
      "eval_runtime": 38.5981,
      "eval_samples_per_second": 58.293,
      "eval_steps_per_second": 7.306,
      "step": 1126
    }
  ],
  "logging_steps": 500,
  "max_steps": 1126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4207559992768512.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.386840125575052e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 16,
    "weight_decay": 0.010177242974562553
  }
}