File size: 1,492 Bytes
0e058f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 4.1984477043151855,
  "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/reduce_on_plateau_convergence/age_random/checkpoint-2000",
  "epoch": 0.010583074488969791,
  "eval_steps": 2000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010583074488969791,
      "grad_norm": 1.3282362222671509,
      "learning_rate": 0.0001,
      "loss": 4.8574,
      "step": 2000
    },
    {
      "epoch": 0.010583074488969791,
      "eval_loss": 4.1984477043151855,
      "eval_runtime": 2.3492,
      "eval_samples_per_second": 744.941,
      "eval_steps_per_second": 46.825,
      "step": 2000
    }
  ],
  "logging_steps": 2000,
  "max_steps": 188981,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 19497222144000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}