Hugging Face's logo

duyphu
/
debc565c-e017-a602-c29e-248eba1104ee

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
debc565c-e017-a602-c29e-248eba1104ee
File size: 3,703 Bytes 
41eca99
 
 
65e1753
139ff0c
65e1753
41eca99
 
 
 
 
 
 
139ff0c
 
 
41eca99
139ff0c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b76c6a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fdcc33c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65e1753
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41eca99
 
 
139ff0c
41eca99
 
139ff0c
41eca99
 
 
 
 
 
 
65e1753
41eca99
 
 
 
65e1753
41eca99
 
 
 
 
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": 0.06474587245063128,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012949174490126255,
      "eval_loss": 5.735302448272705,
      "eval_runtime": 2.0472,
      "eval_samples_per_second": 159.239,
      "eval_steps_per_second": 79.619,
      "step": 1
    },
    {
      "epoch": 0.006474587245063127,
      "grad_norm": 5.199829578399658,
      "learning_rate": 5e-05,
      "loss": 5.8363,
      "step": 5
    },
    {
      "epoch": 0.012949174490126255,
      "grad_norm": 4.196000576019287,
      "learning_rate": 0.0001,
      "loss": 4.9064,
      "step": 10
    },
    {
      "epoch": 0.012949174490126255,
      "eval_loss": 5.591858863830566,
      "eval_runtime": 2.061,
      "eval_samples_per_second": 158.176,
      "eval_steps_per_second": 79.088,
      "step": 10
    },
    {
      "epoch": 0.019423761735189383,
      "grad_norm": 5.302495002746582,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.9064,
      "step": 15
    },
    {
      "epoch": 0.02589834898025251,
      "grad_norm": 5.405220985412598,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.3046,
      "step": 20
    },
    {
      "epoch": 0.02589834898025251,
      "eval_loss": 4.940808296203613,
      "eval_runtime": 2.0626,
      "eval_samples_per_second": 158.052,
      "eval_steps_per_second": 79.026,
      "step": 20
    },
    {
      "epoch": 0.03237293622531564,
      "grad_norm": 5.4033002853393555,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.5125,
      "step": 25
    },
    {
      "epoch": 0.038847523470378766,
      "grad_norm": 6.361747741699219,
      "learning_rate": 5e-05,
      "loss": 3.7681,
      "step": 30
    },
    {
      "epoch": 0.038847523470378766,
      "eval_loss": 4.363986015319824,
      "eval_runtime": 2.0966,
      "eval_samples_per_second": 155.488,
      "eval_steps_per_second": 77.744,
      "step": 30
    },
    {
      "epoch": 0.04532211071544189,
      "grad_norm": 5.471643924713135,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.9542,
      "step": 35
    },
    {
      "epoch": 0.05179669796050502,
      "grad_norm": 8.481507301330566,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.2038,
      "step": 40
    },
    {
      "epoch": 0.05179669796050502,
      "eval_loss": 4.096857070922852,
      "eval_runtime": 2.0675,
      "eval_samples_per_second": 157.678,
      "eval_steps_per_second": 78.839,
      "step": 40
    },
    {
      "epoch": 0.058271285205568145,
      "grad_norm": 3.6633269786834717,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.3399,
      "step": 45
    },
    {
      "epoch": 0.06474587245063128,
      "grad_norm": 5.096242904663086,
      "learning_rate": 0.0,
      "loss": 3.8004,
      "step": 50
    },
    {
      "epoch": 0.06474587245063128,
      "eval_loss": 4.050339221954346,
      "eval_runtime": 2.1017,
      "eval_samples_per_second": 155.11,
      "eval_steps_per_second": 77.555,
      "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": 71210560389120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}