Hugging Face's logo

chauhoang
/
ec410670-564b-4787-83f7-bd9bc3d77f4e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ec410670-564b-4787-83f7-bd9bc3d77f4e
File size: 2,784 Bytes 
831460a
 
 
33cbd75
bd91dae
33cbd75
831460a
 
 
 
 
 
 
bd91dae
 
 
831460a
bd91dae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
706544a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33cbd75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
831460a
 
 
bd91dae
831460a
 
bd91dae
831460a
 
 
 
 
 
 
bd91dae
831460a
 
 
 
33cbd75
831460a
 
 
 
 
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": 0.015436374431031071,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039580447259054025,
      "eval_loss": 1.3191004991531372,
      "eval_runtime": 87.2633,
      "eval_samples_per_second": 12.193,
      "eval_steps_per_second": 6.096,
      "step": 1
    },
    {
      "epoch": 0.0019790223629527013,
      "grad_norm": 0.6584509015083313,
      "learning_rate": 5e-05,
      "loss": 1.3175,
      "step": 5
    },
    {
      "epoch": 0.003958044725905403,
      "grad_norm": 0.5416198372840881,
      "learning_rate": 0.0001,
      "loss": 1.2596,
      "step": 10
    },
    {
      "epoch": 0.003958044725905403,
      "eval_loss": 1.22352933883667,
      "eval_runtime": 88.4037,
      "eval_samples_per_second": 12.036,
      "eval_steps_per_second": 6.018,
      "step": 10
    },
    {
      "epoch": 0.005937067088858104,
      "grad_norm": 0.6631811261177063,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1461,
      "step": 15
    },
    {
      "epoch": 0.007916089451810805,
      "grad_norm": 0.6872115135192871,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.0504,
      "step": 20
    },
    {
      "epoch": 0.007916089451810805,
      "eval_loss": 0.9962456226348877,
      "eval_runtime": 88.4825,
      "eval_samples_per_second": 12.025,
      "eval_steps_per_second": 6.012,
      "step": 20
    },
    {
      "epoch": 0.009895111814763506,
      "grad_norm": 0.5847287774085999,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.017,
      "step": 25
    },
    {
      "epoch": 0.011874134177716208,
      "grad_norm": 0.5955860614776611,
      "learning_rate": 5e-05,
      "loss": 0.9265,
      "step": 30
    },
    {
      "epoch": 0.011874134177716208,
      "eval_loss": 0.9131612777709961,
      "eval_runtime": 88.6617,
      "eval_samples_per_second": 12.001,
      "eval_steps_per_second": 6.0,
      "step": 30
    },
    {
      "epoch": 0.013853156540668909,
      "grad_norm": 0.6309583187103271,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8876,
      "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": 9694668933562368.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}