Hugging Face's logo

Ar4l
/
DebertaV2-Base-10M_babylm-A__wsc

Safetensors
deberta-v2
Model card Files Community
DebertaV2-Base-10M_babylm-A__wsc
File size: 2,817 Bytes 
83b0efe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
{
  "best_metric": 0.47368421052631576,
  "best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/wsc/checkpoint-140",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6153846383094788,
      "eval_f1": 0.0,
      "eval_loss": 0.6650720834732056,
      "eval_mcc": 0.0,
      "eval_runtime": 0.1205,
      "eval_samples_per_second": 431.51,
      "eval_steps_per_second": 58.088,
      "step": 70
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6153846383094788,
      "eval_f1": 0.47368421052631576,
      "eval_loss": 0.6848027110099792,
      "eval_mcc": 0.17256712249065836,
      "eval_runtime": 0.096,
      "eval_samples_per_second": 541.411,
      "eval_steps_per_second": 72.882,
      "step": 140
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5961538553237915,
      "eval_f1": 0.16,
      "eval_loss": 0.6839962005615234,
      "eval_mcc": 0.010314212462587935,
      "eval_runtime": 0.0965,
      "eval_samples_per_second": 539.131,
      "eval_steps_per_second": 72.575,
      "step": 210
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6153846383094788,
      "eval_f1": 0.0,
      "eval_loss": 0.6632354259490967,
      "eval_mcc": 0.0,
      "eval_runtime": 0.0974,
      "eval_samples_per_second": 533.999,
      "eval_steps_per_second": 71.884,
      "step": 280
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6153846383094788,
      "eval_f1": 0.0,
      "eval_loss": 0.6646058559417725,
      "eval_mcc": 0.0,
      "eval_runtime": 0.0979,
      "eval_samples_per_second": 530.989,
      "eval_steps_per_second": 71.479,
      "step": 350
    },
    {
      "epoch": 5.0,
      "step": 350,
      "total_flos": 163423735633920.0,
      "train_loss": 0.7042514474051339,
      "train_runtime": 33.2199,
      "train_samples_per_second": 333.536,
      "train_steps_per_second": 42.143
    }
  ],
  "logging_steps": 500,
  "max_steps": 1400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 163423735633920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}