Hugging Face's logo

VERSIL91
/
0ca74a48-513c-4cfe-9867-47e7787f9ddc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
0ca74a48-513c-4cfe-9867-47e7787f9ddc
File size: 2,174 Bytes 
befc03a
 
 
ae91905
befc03a
ae91905
befc03a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5bedc3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae91905
 
 
 
 
 
 
befc03a
 
 
 
 
 
 
 
 
 
 
 
 
 
ae91905
befc03a
 
 
 
ae91905
befc03a
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.040160642570281124,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 2.2730464935302734,
      "learning_rate": 1e-05,
      "loss": 25.0153,
      "step": 1
    },
    {
      "epoch": 0.008032128514056224,
      "eval_loss": 1.5288861989974976,
      "eval_runtime": 22.6713,
      "eval_samples_per_second": 9.263,
      "eval_steps_per_second": 4.631,
      "step": 1
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 2.2744619846343994,
      "learning_rate": 2e-05,
      "loss": 23.5088,
      "step": 2
    },
    {
      "epoch": 0.01606425702811245,
      "eval_loss": 1.5253138542175293,
      "eval_runtime": 7.5769,
      "eval_samples_per_second": 27.716,
      "eval_steps_per_second": 13.858,
      "step": 2
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 2.448141098022461,
      "learning_rate": 3e-05,
      "loss": 23.0411,
      "step": 3
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 1.915059208869934,
      "learning_rate": 4e-05,
      "loss": 25.1573,
      "step": 4
    },
    {
      "epoch": 0.0321285140562249,
      "eval_loss": 1.5223687887191772,
      "eval_runtime": 7.6013,
      "eval_samples_per_second": 27.627,
      "eval_steps_per_second": 13.813,
      "step": 4
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 4.761684894561768,
      "learning_rate": 5e-05,
      "loss": 24.8143,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4641935339814912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}