File size: 2,057 Bytes
d5823f9
8f98e8d
 
 
d5823f9
8f98e8d
d5823f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f389b63
 
 
d5823f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f389b63
 
 
d5823f9
 
 
8f98e8d
 
 
 
f389b63
 
 
d5823f9
 
 
8f98e8d
d5823f9
8f98e8d
d5823f9
 
 
 
 
 
 
 
 
 
 
 
 
8f98e8d
d5823f9
 
 
 
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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
{
  "best_metric": 0.12910686958067819,
  "best_model_checkpoint": "./output/modernBERT-base-sentiment-v2/checkpoint-8",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.625,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.8373,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.12910686958067819,
      "eval_loss": 1.8330078125,
      "eval_precision": 0.16504066117321736,
      "eval_recall": 0.1890018282051825,
      "eval_runtime": 8.5241,
      "eval_samples_per_second": 234.629,
      "eval_steps_per_second": 0.117,
      "step": 8
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.8336,
      "step": 10
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.8364,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.12910686958067819,
      "eval_loss": 1.8330078125,
      "eval_precision": 0.16504066117321736,
      "eval_recall": 0.1890018282051825,
      "eval_runtime": 0.2771,
      "eval_samples_per_second": 7218.143,
      "eval_steps_per_second": 3.609,
      "step": 16
    },
    {
      "epoch": 2.0,
      "step": 16,
      "total_flos": 1489153141243904.0,
      "train_loss": 1.836273193359375,
      "train_runtime": 55.3814,
      "train_samples_per_second": 577.811,
      "train_steps_per_second": 0.289
    }
  ],
  "logging_steps": 5,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1489153141243904.0,
  "train_batch_size": 1024,
  "trial_name": null,
  "trial_params": null
}