Hugging Face's logo

duyphu
/
522fc356-676e-4150-b785-51d223bf199a

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
522fc356-676e-4150-b785-51d223bf199a
File size: 3,742 Bytes 
30e3333
 
 
eb2331c
10fc5d4
eb2331c
30e3333
 
 
 
 
 
 
10fc5d4
 
 
30e3333
10fc5d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90880ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
762b3c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb2331c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30e3333
 
 
10fc5d4
30e3333
 
10fc5d4
30e3333
 
 
 
 
 
 
eb2331c
30e3333
 
 
 
eb2331c
30e3333
 
 
 
 
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": 0.0019596315892612187,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.919263178522438e-05,
      "eval_loss": 2.9300684928894043,
      "eval_runtime": 416.4401,
      "eval_samples_per_second": 25.8,
      "eval_steps_per_second": 12.9,
      "step": 1
    },
    {
      "epoch": 0.0001959631589261219,
      "grad_norm": 0.554083526134491,
      "learning_rate": 5e-05,
      "loss": 2.7355,
      "step": 5
    },
    {
      "epoch": 0.0003919263178522438,
      "grad_norm": 0.6002002954483032,
      "learning_rate": 0.0001,
      "loss": 2.8307,
      "step": 10
    },
    {
      "epoch": 0.0003919263178522438,
      "eval_loss": 2.883746862411499,
      "eval_runtime": 411.3043,
      "eval_samples_per_second": 26.122,
      "eval_steps_per_second": 13.061,
      "step": 10
    },
    {
      "epoch": 0.0005878894767783657,
      "grad_norm": 0.5967435240745544,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7021,
      "step": 15
    },
    {
      "epoch": 0.0007838526357044876,
      "grad_norm": 0.7131651639938354,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7578,
      "step": 20
    },
    {
      "epoch": 0.0007838526357044876,
      "eval_loss": 2.6993062496185303,
      "eval_runtime": 409.5738,
      "eval_samples_per_second": 26.232,
      "eval_steps_per_second": 13.116,
      "step": 20
    },
    {
      "epoch": 0.0009798157946306093,
      "grad_norm": 0.7737033367156982,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.6032,
      "step": 25
    },
    {
      "epoch": 0.0011757789535567313,
      "grad_norm": 0.6557625532150269,
      "learning_rate": 5e-05,
      "loss": 2.5433,
      "step": 30
    },
    {
      "epoch": 0.0011757789535567313,
      "eval_loss": 2.614881992340088,
      "eval_runtime": 407.1458,
      "eval_samples_per_second": 26.389,
      "eval_steps_per_second": 13.194,
      "step": 30
    },
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 0.7806957960128784,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.5803,
      "step": 35
    },
    {
      "epoch": 0.0015677052714089751,
      "grad_norm": 0.8234419822692871,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.5542,
      "step": 40
    },
    {
      "epoch": 0.0015677052714089751,
      "eval_loss": 2.580919027328491,
      "eval_runtime": 411.7251,
      "eval_samples_per_second": 26.095,
      "eval_steps_per_second": 13.048,
      "step": 40
    },
    {
      "epoch": 0.001763668430335097,
      "grad_norm": 0.8764637112617493,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.5428,
      "step": 45
    },
    {
      "epoch": 0.0019596315892612187,
      "grad_norm": 0.7842684388160706,
      "learning_rate": 0.0,
      "loss": 2.6029,
      "step": 50
    },
    {
      "epoch": 0.0019596315892612187,
      "eval_loss": 2.575305223464966,
      "eval_runtime": 414.8734,
      "eval_samples_per_second": 25.897,
      "eval_steps_per_second": 12.949,
      "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": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}