Hugging Face's logo

tuanna08go
/
6197c78b-29de-4067-a6b6-bfc99b03b4f4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6197c78b-29de-4067-a6b6-bfc99b03b4f4
File size: 3,749 Bytes 
de715eb
 
 
2c54f63
3f1e67e
2c54f63
de715eb
 
 
 
 
 
 
3f1e67e
 
 
de715eb
3f1e67e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cb4c68a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35ccdcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c54f63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de715eb
 
 
3f1e67e
de715eb
 
3f1e67e
de715eb
 
 
 
 
 
 
2c54f63
de715eb
 
 
 
2c54f63
de715eb
 
 
 
 
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": 0.0016524828554903743,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3049657109807487e-05,
      "eval_loss": 1.1126134395599365,
      "eval_runtime": 2015.562,
      "eval_samples_per_second": 6.321,
      "eval_steps_per_second": 3.16,
      "step": 1
    },
    {
      "epoch": 0.00016524828554903743,
      "grad_norm": 0.21275891363620758,
      "learning_rate": 5e-05,
      "loss": 0.9941,
      "step": 5
    },
    {
      "epoch": 0.00033049657109807487,
      "grad_norm": 0.29368552565574646,
      "learning_rate": 0.0001,
      "loss": 0.9738,
      "step": 10
    },
    {
      "epoch": 0.00033049657109807487,
      "eval_loss": 1.0696473121643066,
      "eval_runtime": 2048.2336,
      "eval_samples_per_second": 6.22,
      "eval_steps_per_second": 3.11,
      "step": 10
    },
    {
      "epoch": 0.0004957448566471123,
      "grad_norm": 0.33622804284095764,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.018,
      "step": 15
    },
    {
      "epoch": 0.0006609931421961497,
      "grad_norm": 0.374787837266922,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9683,
      "step": 20
    },
    {
      "epoch": 0.0006609931421961497,
      "eval_loss": 0.9721865057945251,
      "eval_runtime": 2046.2259,
      "eval_samples_per_second": 6.226,
      "eval_steps_per_second": 3.113,
      "step": 20
    },
    {
      "epoch": 0.0008262414277451872,
      "grad_norm": 0.4773717522621155,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9747,
      "step": 25
    },
    {
      "epoch": 0.0009914897132942246,
      "grad_norm": 0.3675839304924011,
      "learning_rate": 5e-05,
      "loss": 0.9272,
      "step": 30
    },
    {
      "epoch": 0.0009914897132942246,
      "eval_loss": 0.9233540296554565,
      "eval_runtime": 2045.7232,
      "eval_samples_per_second": 6.228,
      "eval_steps_per_second": 3.114,
      "step": 30
    },
    {
      "epoch": 0.001156737998843262,
      "grad_norm": 0.40750598907470703,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9225,
      "step": 35
    },
    {
      "epoch": 0.0013219862843922995,
      "grad_norm": 0.3466489315032959,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8495,
      "step": 40
    },
    {
      "epoch": 0.0013219862843922995,
      "eval_loss": 0.9025662541389465,
      "eval_runtime": 2044.9468,
      "eval_samples_per_second": 6.23,
      "eval_steps_per_second": 3.115,
      "step": 40
    },
    {
      "epoch": 0.0014872345699413368,
      "grad_norm": 0.3929550349712372,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.899,
      "step": 45
    },
    {
      "epoch": 0.0016524828554903743,
      "grad_norm": 0.3898150622844696,
      "learning_rate": 0.0,
      "loss": 0.8792,
      "step": 50
    },
    {
      "epoch": 0.0016524828554903743,
      "eval_loss": 0.8988497257232666,
      "eval_runtime": 2042.8113,
      "eval_samples_per_second": 6.237,
      "eval_steps_per_second": 3.118,
      "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": 1.6246613030731776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}