Hugging Face's logo

chauhoang
/
44c9e4b4-5d69-4903-b23a-8a53dfad8e10

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
44c9e4b4-5d69-4903-b23a-8a53dfad8e10
File size: 2,772 Bytes 
6f3eb91
 
 
dd2c363
7f36d5f
dd2c363
6f3eb91
 
 
 
 
 
 
7f36d5f
 
 
6f3eb91
7f36d5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68bc8b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd2c363
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f3eb91
 
 
7f36d5f
6f3eb91
 
7f36d5f
6f3eb91
 
 
 
 
 
 
7f36d5f
6f3eb91
 
 
 
dd2c363
6f3eb91
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07215541165587419,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018501387604070306,
      "eval_loss": 3.789647102355957,
      "eval_runtime": 14.8344,
      "eval_samples_per_second": 15.37,
      "eval_steps_per_second": 7.685,
      "step": 1
    },
    {
      "epoch": 0.009250693802035153,
      "grad_norm": 3.0337514877319336,
      "learning_rate": 5e-05,
      "loss": 3.5668,
      "step": 5
    },
    {
      "epoch": 0.018501387604070305,
      "grad_norm": 4.058107852935791,
      "learning_rate": 0.0001,
      "loss": 3.0872,
      "step": 10
    },
    {
      "epoch": 0.018501387604070305,
      "eval_loss": 2.5827155113220215,
      "eval_runtime": 15.0123,
      "eval_samples_per_second": 15.188,
      "eval_steps_per_second": 7.594,
      "step": 10
    },
    {
      "epoch": 0.027752081406105456,
      "grad_norm": 2.6269290447235107,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1259,
      "step": 15
    },
    {
      "epoch": 0.03700277520814061,
      "grad_norm": 2.55375075340271,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6842,
      "step": 20
    },
    {
      "epoch": 0.03700277520814061,
      "eval_loss": 1.6327600479125977,
      "eval_runtime": 15.1801,
      "eval_samples_per_second": 15.02,
      "eval_steps_per_second": 7.51,
      "step": 20
    },
    {
      "epoch": 0.04625346901017576,
      "grad_norm": 1.9848346710205078,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6157,
      "step": 25
    },
    {
      "epoch": 0.05550416281221091,
      "grad_norm": 2.131385326385498,
      "learning_rate": 5e-05,
      "loss": 1.4348,
      "step": 30
    },
    {
      "epoch": 0.05550416281221091,
      "eval_loss": 1.2888398170471191,
      "eval_runtime": 15.2538,
      "eval_samples_per_second": 14.947,
      "eval_steps_per_second": 7.474,
      "step": 30
    },
    {
      "epoch": 0.06475485661424607,
      "grad_norm": 1.6838656663894653,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0601,
      "step": 35
    }
  ],
  "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": 6396379586887680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}