Hugging Face's logo

fpadovani
/
random_sentence_french

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
random_sentence_french
File size: 3,027 Bytes 
3e82cc3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.16203773021697998,
  "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/convergence_french/random_sentence_french/checkpoint-10000",
  "epoch": 0.01808409829069103,
  "eval_steps": 2000,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003616819658138206,
      "grad_norm": 0.14744240045547485,
      "learning_rate": 0.0001,
      "loss": 0.7697,
      "step": 2000
    },
    {
      "epoch": 0.003616819658138206,
      "eval_loss": 0.19154727458953857,
      "eval_runtime": 91.812,
      "eval_samples_per_second": 397.933,
      "eval_steps_per_second": 24.877,
      "step": 2000
    },
    {
      "epoch": 0.007233639316276412,
      "grad_norm": 0.1623348593711853,
      "learning_rate": 0.0001,
      "loss": 0.1884,
      "step": 4000
    },
    {
      "epoch": 0.007233639316276412,
      "eval_loss": 0.17771275341510773,
      "eval_runtime": 99.0721,
      "eval_samples_per_second": 368.772,
      "eval_steps_per_second": 23.054,
      "step": 4000
    },
    {
      "epoch": 0.010850458974414617,
      "grad_norm": 0.13657265901565552,
      "learning_rate": 0.0001,
      "loss": 0.178,
      "step": 6000
    },
    {
      "epoch": 0.010850458974414617,
      "eval_loss": 0.16984443366527557,
      "eval_runtime": 90.3285,
      "eval_samples_per_second": 404.468,
      "eval_steps_per_second": 25.285,
      "step": 6000
    },
    {
      "epoch": 0.014467278632552824,
      "grad_norm": 0.15028506517410278,
      "learning_rate": 0.0001,
      "loss": 0.1714,
      "step": 8000
    },
    {
      "epoch": 0.014467278632552824,
      "eval_loss": 0.16548627614974976,
      "eval_runtime": 90.9787,
      "eval_samples_per_second": 401.578,
      "eval_steps_per_second": 25.105,
      "step": 8000
    },
    {
      "epoch": 0.01808409829069103,
      "grad_norm": 0.17982865869998932,
      "learning_rate": 0.0001,
      "loss": 0.1669,
      "step": 10000
    },
    {
      "epoch": 0.01808409829069103,
      "eval_loss": 0.16203773021697998,
      "eval_runtime": 87.7097,
      "eval_samples_per_second": 416.544,
      "eval_steps_per_second": 26.04,
      "step": 10000
    }
  ],
  "logging_steps": 2000,
  "max_steps": 552972,
  "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": 194940764160000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}