Hugging Face's logo

tuanna08go
/
a2d7a544-5b20-4e08-a708-3e8a0f1f0f4f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a2d7a544-5b20-4e08-a708-3e8a0f1f0f4f
File size: 3,496 Bytes 
4571f3f
 
 
8715da1
6caebf1
8715da1
4571f3f
 
 
 
 
 
 
6caebf1
 
 
4571f3f
6caebf1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ee0768
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df861f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8715da1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4571f3f
 
 
6caebf1
4571f3f
 
6caebf1
4571f3f
 
 
 
 
 
 
8715da1
4571f3f
 
 
 
8715da1
4571f3f
 
 
 
 
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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00020355529681415606,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.071105936283121e-06,
      "eval_loss": NaN,
      "eval_runtime": 4407.1661,
      "eval_samples_per_second": 23.467,
      "eval_steps_per_second": 11.734,
      "step": 1
    },
    {
      "epoch": 2.0355529681415605e-05,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 4.071105936283121e-05,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 4.071105936283121e-05,
      "eval_loss": NaN,
      "eval_runtime": 4392.4822,
      "eval_samples_per_second": 23.546,
      "eval_steps_per_second": 11.773,
      "step": 10
    },
    {
      "epoch": 6.106658904424681e-05,
      "grad_norm": 0.0,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 8.142211872566242e-05,
      "grad_norm": 0.0,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 8.142211872566242e-05,
      "eval_loss": NaN,
      "eval_runtime": 4418.0183,
      "eval_samples_per_second": 23.41,
      "eval_steps_per_second": 11.705,
      "step": 20
    },
    {
      "epoch": 0.00010177764840707803,
      "grad_norm": 0.0,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.00012213317808849362,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.00012213317808849362,
      "eval_loss": NaN,
      "eval_runtime": 4412.3446,
      "eval_samples_per_second": 23.44,
      "eval_steps_per_second": 11.72,
      "step": 30
    },
    {
      "epoch": 0.00014248870776990924,
      "grad_norm": 0.0,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.00016284423745132484,
      "grad_norm": 0.0,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00016284423745132484,
      "eval_loss": NaN,
      "eval_runtime": 4463.5545,
      "eval_samples_per_second": 23.171,
      "eval_steps_per_second": 11.586,
      "step": 40
    },
    {
      "epoch": 0.00018319976713274043,
      "grad_norm": 0.0,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.00020355529681415606,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00020355529681415606,
      "eval_loss": NaN,
      "eval_runtime": 4395.7779,
      "eval_samples_per_second": 23.528,
      "eval_steps_per_second": 11.764,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3478615228416000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}