Hugging Face's logo

fpadovani
/
english_childes_mlm_sent_13

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
english_childes_mlm_sent_13
File size: 2,914 Bytes 
bfdec60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
108
109
110
111
112
 
{
  "best_metric": 3.6284842491149902,
  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained_recent/mlm_unmasking/en_mlm_new/childes_mlm_unmasking_sent_13/checkpoint-12000",
  "epoch": 0.4444197544580857,
  "eval_steps": 2000,
  "global_step": 12000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07406995907634761,
      "eval_loss": 5.4637370109558105,
      "eval_runtime": 24.2102,
      "eval_samples_per_second": 1237.041,
      "eval_steps_per_second": 77.323,
      "step": 2000
    },
    {
      "epoch": 0.14813991815269523,
      "grad_norm": 4.785717487335205,
      "learning_rate": 4e-05,
      "loss": 6.1476,
      "step": 4000
    },
    {
      "epoch": 0.14813991815269523,
      "eval_loss": 4.718623161315918,
      "eval_runtime": 24.2123,
      "eval_samples_per_second": 1236.934,
      "eval_steps_per_second": 77.316,
      "step": 4000
    },
    {
      "epoch": 0.22220987722904284,
      "eval_loss": 4.352034091949463,
      "eval_runtime": 24.1788,
      "eval_samples_per_second": 1238.646,
      "eval_steps_per_second": 77.423,
      "step": 6000
    },
    {
      "epoch": 0.29627983630539045,
      "grad_norm": 7.057693004608154,
      "learning_rate": 8e-05,
      "loss": 4.4471,
      "step": 8000
    },
    {
      "epoch": 0.29627983630539045,
      "eval_loss": 3.99312686920166,
      "eval_runtime": 24.1035,
      "eval_samples_per_second": 1242.518,
      "eval_steps_per_second": 77.665,
      "step": 8000
    },
    {
      "epoch": 0.37034979538173807,
      "eval_loss": 3.763000965118408,
      "eval_runtime": 24.2844,
      "eval_samples_per_second": 1233.262,
      "eval_steps_per_second": 77.087,
      "step": 10000
    },
    {
      "epoch": 0.4444197544580857,
      "grad_norm": 8.325577735900879,
      "learning_rate": 0.00012,
      "loss": 3.8939,
      "step": 12000
    },
    {
      "epoch": 0.4444197544580857,
      "eval_loss": 3.6284842491149902,
      "eval_runtime": 24.245,
      "eval_samples_per_second": 1235.265,
      "eval_steps_per_second": 77.212,
      "step": 12000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 400000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 4000,
  "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": 2503873658880000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}