Hugging Face's logo

duyphu
/
ea7b14e5-4610-46ac-b82c-e7e7b273e0ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ea7b14e5-4610-46ac-b82c-e7e7b273e0ed
File size: 2,228 Bytes 
befc1d7
 
 
00e1105
62d9a05
00e1105
befc1d7
 
 
 
 
 
 
62d9a05
 
 
befc1d7
62d9a05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00e1105
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
befc1d7
 
 
62d9a05
befc1d7
 
62d9a05
befc1d7
 
 
 
 
 
 
62d9a05
befc1d7
 
 
 
00e1105
befc1d7
 
 
 
 
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": 0.09515096065873742,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 6.844988822937012,
      "eval_runtime": 6.9069,
      "eval_samples_per_second": 16.65,
      "eval_steps_per_second": 8.397,
      "step": 1
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 11.751487731933594,
      "learning_rate": 5e-05,
      "loss": 6.8396,
      "step": 5
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 8.099217414855957,
      "learning_rate": 0.0001,
      "loss": 4.2657,
      "step": 10
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 1.4936703443527222,
      "eval_runtime": 6.9534,
      "eval_samples_per_second": 16.539,
      "eval_steps_per_second": 8.341,
      "step": 10
    },
    {
      "epoch": 0.05489478499542543,
      "grad_norm": 2.1512739658355713,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9735,
      "step": 15
    },
    {
      "epoch": 0.07319304666056725,
      "grad_norm": 1.4982128143310547,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6925,
      "step": 20
    },
    {
      "epoch": 0.07319304666056725,
      "eval_loss": 0.7363909482955933,
      "eval_runtime": 6.9844,
      "eval_samples_per_second": 16.465,
      "eval_steps_per_second": 8.304,
      "step": 20
    },
    {
      "epoch": 0.09149130832570906,
      "grad_norm": 0.9344391822814941,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7451,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4284339600752640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}