Hugging Face's logo

universitytehran
/
SmolLM-135M-10M-word

Safetensors
llama
Model card Files Community
SmolLM-135M-10M-word
File size: 2,309 Bytes 
aefafe1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 3.5722010135650635,
  "best_model_checkpoint": "/home/dousti_group/ghanizadeh/babyLM/model-save/5-epoch-tv-tokenized/checkpoint-113408",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 113408,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.181252479553223,
      "learning_rate": 4.014476851196376e-05,
      "loss": 4.3405,
      "step": 28352
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.8782432079315186,
      "eval_runtime": 163.7675,
      "eval_samples_per_second": 291.572,
      "eval_steps_per_second": 36.448,
      "step": 28352
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.64185094833374,
      "learning_rate": 3.0112558402944925e-05,
      "loss": 3.7749,
      "step": 56704
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.6707634925842285,
      "eval_runtime": 158.0831,
      "eval_samples_per_second": 302.056,
      "eval_steps_per_second": 37.759,
      "step": 56704
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.706910610198975,
      "learning_rate": 2.0081056208410027e-05,
      "loss": 3.493,
      "step": 85056
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.5801351070404053,
      "eval_runtime": 158.2132,
      "eval_samples_per_second": 301.808,
      "eval_steps_per_second": 37.728,
      "step": 85056
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.424848556518555,
      "learning_rate": 1.005061588560102e-05,
      "loss": 3.2244,
      "step": 113408
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.5722010135650635,
      "eval_runtime": 157.7259,
      "eval_samples_per_second": 302.74,
      "eval_steps_per_second": 37.844,
      "step": 113408
    }
  ],
  "logging_steps": 500,
  "max_steps": 141760,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.959934159506637e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}