Hugging Face's logo

phungkhaccuong
/
4271b026-9cf4-4c38-bf60-51651503922c

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
4271b026-9cf4-4c38-bf60-51651503922c
File size: 3,741 Bytes 
4140b43
 
 
d71402c
5887493
d71402c
4140b43
 
 
 
 
 
 
5887493
 
 
4140b43
5887493
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf30342
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97381b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d71402c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4140b43
 
 
5887493
4140b43
 
5887493
4140b43
 
 
 
 
 
 
d71402c
4140b43
 
 
 
d71402c
4140b43
 
 
 
 
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": 0.034340659340659344,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006868131868131869,
      "eval_loss": 11.931960105895996,
      "eval_runtime": 6.0229,
      "eval_samples_per_second": 101.944,
      "eval_steps_per_second": 50.972,
      "step": 1
    },
    {
      "epoch": 0.003434065934065934,
      "grad_norm": 0.01643933355808258,
      "learning_rate": 5e-05,
      "loss": 11.9324,
      "step": 5
    },
    {
      "epoch": 0.006868131868131868,
      "grad_norm": 0.023675480857491493,
      "learning_rate": 0.0001,
      "loss": 11.933,
      "step": 10
    },
    {
      "epoch": 0.006868131868131868,
      "eval_loss": 11.931863784790039,
      "eval_runtime": 6.1026,
      "eval_samples_per_second": 100.613,
      "eval_steps_per_second": 50.306,
      "step": 10
    },
    {
      "epoch": 0.010302197802197802,
      "grad_norm": 0.01706523261964321,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9319,
      "step": 15
    },
    {
      "epoch": 0.013736263736263736,
      "grad_norm": 0.02669455297291279,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9315,
      "step": 20
    },
    {
      "epoch": 0.013736263736263736,
      "eval_loss": 11.931612014770508,
      "eval_runtime": 6.099,
      "eval_samples_per_second": 100.673,
      "eval_steps_per_second": 50.336,
      "step": 20
    },
    {
      "epoch": 0.017170329670329672,
      "grad_norm": 0.018381647765636444,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9309,
      "step": 25
    },
    {
      "epoch": 0.020604395604395604,
      "grad_norm": 0.02004670910537243,
      "learning_rate": 5e-05,
      "loss": 11.933,
      "step": 30
    },
    {
      "epoch": 0.020604395604395604,
      "eval_loss": 11.931435585021973,
      "eval_runtime": 6.1717,
      "eval_samples_per_second": 99.486,
      "eval_steps_per_second": 49.743,
      "step": 30
    },
    {
      "epoch": 0.02403846153846154,
      "grad_norm": 0.019301248714327812,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.931,
      "step": 35
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 0.034245315939188004,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9315,
      "step": 40
    },
    {
      "epoch": 0.027472527472527472,
      "eval_loss": 11.931343078613281,
      "eval_runtime": 6.171,
      "eval_samples_per_second": 99.497,
      "eval_steps_per_second": 49.749,
      "step": 40
    },
    {
      "epoch": 0.030906593406593408,
      "grad_norm": 0.019847964867949486,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9317,
      "step": 45
    },
    {
      "epoch": 0.034340659340659344,
      "grad_norm": 0.025872528553009033,
      "learning_rate": 0.0,
      "loss": 11.9311,
      "step": 50
    },
    {
      "epoch": 0.034340659340659344,
      "eval_loss": 11.931325912475586,
      "eval_runtime": 5.994,
      "eval_samples_per_second": 102.436,
      "eval_steps_per_second": 51.218,
      "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": 5908070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}