Hugging Face's logo

stewy33
/
8B-20k_original_augmented_original_pkc_fda_approval-f279b5d4

PEFT
Model card Files Community
8B-20k_original_augmented_original_pkc_fda_approval-f279b5d4
File size: 2,425 Bytes 
e67cbee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 1.1105867624282837,
      "learning_rate": 1e-05,
      "loss": 2.023,
      "step": 1
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0291038751602173,
      "learning_rate": 9e-06,
      "loss": 1.9548,
      "step": 2
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9957126975059509,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9376,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.9828665852546692,
      "learning_rate": 7e-06,
      "loss": 1.975,
      "step": 4
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.9356377720832825,
      "learning_rate": 6e-06,
      "loss": 1.9225,
      "step": 5
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.9131035208702087,
      "learning_rate": 5e-06,
      "loss": 1.9317,
      "step": 6
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8676958084106445,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.8976,
      "step": 7
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.84479159116745,
      "learning_rate": 3e-06,
      "loss": 1.8474,
      "step": 8
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.849846363067627,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.897,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7898678779602051,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7788,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.870275616645813,
      "eval_runtime": 5.1424,
      "eval_samples_per_second": 0.389,
      "eval_steps_per_second": 0.194,
      "step": 10
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.019423562576691e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}