Hugging Face's logo

duyphu
/
5f6c2a50-8786-4092-917e-24a3a72a1fd9

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
5f6c2a50-8786-4092-917e-24a3a72a1fd9
File size: 3,711 Bytes 
4c528d6
 
 
c16ed7e
9a54f96
c16ed7e
4c528d6
 
 
 
 
 
 
9a54f96
 
 
4c528d6
9a54f96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1a38a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a6ad74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c16ed7e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4c528d6
 
 
9a54f96
4c528d6
 
9a54f96
4c528d6
 
 
 
 
 
 
c16ed7e
4c528d6
 
 
 
c16ed7e
4c528d6
 
 
 
 
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": 0.02844950213371266,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 2.3201534748077393,
      "eval_runtime": 26.0977,
      "eval_samples_per_second": 28.355,
      "eval_steps_per_second": 14.177,
      "step": 1
    },
    {
      "epoch": 0.002844950213371266,
      "grad_norm": 1.2677528858184814,
      "learning_rate": 5e-05,
      "loss": 2.073,
      "step": 5
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 1.1822943687438965,
      "learning_rate": 0.0001,
      "loss": 2.1458,
      "step": 10
    },
    {
      "epoch": 0.005689900426742532,
      "eval_loss": 2.2814557552337646,
      "eval_runtime": 24.6819,
      "eval_samples_per_second": 29.981,
      "eval_steps_per_second": 14.991,
      "step": 10
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 1.1251591444015503,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.321,
      "step": 15
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 1.4248967170715332,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1071,
      "step": 20
    },
    {
      "epoch": 0.011379800853485065,
      "eval_loss": 2.175661563873291,
      "eval_runtime": 24.7074,
      "eval_samples_per_second": 29.951,
      "eval_steps_per_second": 14.975,
      "step": 20
    },
    {
      "epoch": 0.01422475106685633,
      "grad_norm": 1.6990677118301392,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0976,
      "step": 25
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 1.3707565069198608,
      "learning_rate": 5e-05,
      "loss": 2.16,
      "step": 30
    },
    {
      "epoch": 0.017069701280227598,
      "eval_loss": 2.133972644805908,
      "eval_runtime": 24.4512,
      "eval_samples_per_second": 30.264,
      "eval_steps_per_second": 15.132,
      "step": 30
    },
    {
      "epoch": 0.01991465149359886,
      "grad_norm": 1.2129231691360474,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9256,
      "step": 35
    },
    {
      "epoch": 0.02275960170697013,
      "grad_norm": 1.7803326845169067,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3078,
      "step": 40
    },
    {
      "epoch": 0.02275960170697013,
      "eval_loss": 2.1224875450134277,
      "eval_runtime": 24.6578,
      "eval_samples_per_second": 30.011,
      "eval_steps_per_second": 15.005,
      "step": 40
    },
    {
      "epoch": 0.025604551920341393,
      "grad_norm": 1.49332594871521,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8645,
      "step": 45
    },
    {
      "epoch": 0.02844950213371266,
      "grad_norm": 1.537865400314331,
      "learning_rate": 0.0,
      "loss": 2.118,
      "step": 50
    },
    {
      "epoch": 0.02844950213371266,
      "eval_loss": 2.120621681213379,
      "eval_runtime": 24.5138,
      "eval_samples_per_second": 30.187,
      "eval_steps_per_second": 15.094,
      "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": 462998451781632.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}