Hugging Face's logo

tuanna08go
/
66fac078-db73-815c-4e34-3a980af3c5bf

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
66fac078-db73-815c-4e34-3a980af3c5bf
File size: 3,473 Bytes 
95dc846
 
 
9f9c133
555b72a
9f9c133
95dc846
 
 
 
 
 
 
555b72a
 
 
95dc846
555b72a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2d02f52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be73374
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9f9c133
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95dc846
 
 
555b72a
95dc846
 
555b72a
95dc846
 
 
 
 
 
 
9f9c133
95dc846
 
 
 
9f9c133
95dc846
 
 
 
 
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": 0.004309137526124146,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.618275052248293e-05,
      "eval_loss": NaN,
      "eval_runtime": 180.462,
      "eval_samples_per_second": 27.075,
      "eval_steps_per_second": 13.537,
      "step": 1
    },
    {
      "epoch": 0.0004309137526124146,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008618275052248292,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008618275052248292,
      "eval_loss": NaN,
      "eval_runtime": 181.9637,
      "eval_samples_per_second": 26.852,
      "eval_steps_per_second": 13.426,
      "step": 10
    },
    {
      "epoch": 0.0012927412578372438,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0017236550104496584,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0017236550104496584,
      "eval_loss": NaN,
      "eval_runtime": 183.07,
      "eval_samples_per_second": 26.689,
      "eval_steps_per_second": 13.345,
      "step": 20
    },
    {
      "epoch": 0.002154568763062073,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0025854825156744875,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0025854825156744875,
      "eval_loss": NaN,
      "eval_runtime": 182.6276,
      "eval_samples_per_second": 26.754,
      "eval_steps_per_second": 13.377,
      "step": 30
    },
    {
      "epoch": 0.0030163962682869024,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.003447310020899317,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.003447310020899317,
      "eval_loss": NaN,
      "eval_runtime": 180.3708,
      "eval_samples_per_second": 27.089,
      "eval_steps_per_second": 13.544,
      "step": 40
    },
    {
      "epoch": 0.0038782237735117317,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.004309137526124146,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.004309137526124146,
      "eval_loss": NaN,
      "eval_runtime": 180.3901,
      "eval_samples_per_second": 27.086,
      "eval_steps_per_second": 13.543,
      "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": 1880929899380736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}