Hugging Face's logo

fpadovani
/
age_random

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
age_random
File size: 4,515 Bytes 
08126a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 3.638516664505005,
  "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/reduce_on_plateau_convergence/age_random/checkpoint-18000",
  "epoch": 0.09524767040072811,
  "eval_steps": 2000,
  "global_step": 18000,
  "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
    },
    {
      "epoch": 0.021166148977939583,
      "grad_norm": 1.406479835510254,
      "learning_rate": 0.0001,
      "loss": 4.145,
      "step": 4000
    },
    {
      "epoch": 0.021166148977939583,
      "eval_loss": 3.9832916259765625,
      "eval_runtime": 2.1928,
      "eval_samples_per_second": 798.069,
      "eval_steps_per_second": 50.164,
      "step": 4000
    },
    {
      "epoch": 0.03174922346690937,
      "grad_norm": 1.4979146718978882,
      "learning_rate": 0.0001,
      "loss": 3.9948,
      "step": 6000
    },
    {
      "epoch": 0.03174922346690937,
      "eval_loss": 3.872448444366455,
      "eval_runtime": 2.0908,
      "eval_samples_per_second": 837.0,
      "eval_steps_per_second": 52.611,
      "step": 6000
    },
    {
      "epoch": 0.042332297955879165,
      "grad_norm": 1.4652293920516968,
      "learning_rate": 0.0001,
      "loss": 3.9047,
      "step": 8000
    },
    {
      "epoch": 0.042332297955879165,
      "eval_loss": 3.8042104244232178,
      "eval_runtime": 2.0939,
      "eval_samples_per_second": 835.759,
      "eval_steps_per_second": 52.533,
      "step": 8000
    },
    {
      "epoch": 0.05291537244484895,
      "grad_norm": 1.523988127708435,
      "learning_rate": 0.0001,
      "loss": 3.8428,
      "step": 10000
    },
    {
      "epoch": 0.05291537244484895,
      "eval_loss": 3.751901149749756,
      "eval_runtime": 2.1539,
      "eval_samples_per_second": 812.471,
      "eval_steps_per_second": 51.07,
      "step": 10000
    },
    {
      "epoch": 0.06349844693381874,
      "grad_norm": 1.6126410961151123,
      "learning_rate": 0.0001,
      "loss": 3.7955,
      "step": 12000
    },
    {
      "epoch": 0.06349844693381874,
      "eval_loss": 3.71409010887146,
      "eval_runtime": 2.0662,
      "eval_samples_per_second": 846.973,
      "eval_steps_per_second": 53.238,
      "step": 12000
    },
    {
      "epoch": 0.07408152142278854,
      "grad_norm": 1.656988263130188,
      "learning_rate": 0.0001,
      "loss": 3.7557,
      "step": 14000
    },
    {
      "epoch": 0.07408152142278854,
      "eval_loss": 3.6855504512786865,
      "eval_runtime": 2.0523,
      "eval_samples_per_second": 852.711,
      "eval_steps_per_second": 53.599,
      "step": 14000
    },
    {
      "epoch": 0.08466459591175833,
      "grad_norm": 1.6087511777877808,
      "learning_rate": 0.0001,
      "loss": 3.725,
      "step": 16000
    },
    {
      "epoch": 0.08466459591175833,
      "eval_loss": 3.658583164215088,
      "eval_runtime": 2.1352,
      "eval_samples_per_second": 819.607,
      "eval_steps_per_second": 51.518,
      "step": 16000
    },
    {
      "epoch": 0.09524767040072811,
      "grad_norm": 1.6472262144088745,
      "learning_rate": 0.0001,
      "loss": 3.6947,
      "step": 18000
    },
    {
      "epoch": 0.09524767040072811,
      "eval_loss": 3.638516664505005,
      "eval_runtime": 95.757,
      "eval_samples_per_second": 18.275,
      "eval_steps_per_second": 1.149,
      "step": 18000
    }
  ],
  "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": 175474923134976.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}