Hugging Face's logo

duyphu
/
0d3b36c3-0088-4354-b034-f876a6cd33a9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0d3b36c3-0088-4354-b034-f876a6cd33a9
File size: 3,714 Bytes 
3fee0b9
 
 
d508db8
f05296f
d508db8
3fee0b9
 
 
 
 
 
 
f05296f
 
 
3fee0b9
f05296f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a5c117
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83cab1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d508db8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3fee0b9
 
 
f05296f
3fee0b9
 
f05296f
3fee0b9
 
 
 
 
 
 
d508db8
3fee0b9
 
 
 
d508db8
3fee0b9
 
 
 
 
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": 0.02868617326448652,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005737234652897303,
      "eval_loss": 3.131199598312378,
      "eval_runtime": 35.5947,
      "eval_samples_per_second": 20.621,
      "eval_steps_per_second": 10.311,
      "step": 1
    },
    {
      "epoch": 0.002868617326448652,
      "grad_norm": 3.0306143760681152,
      "learning_rate": 5e-05,
      "loss": 3.2107,
      "step": 5
    },
    {
      "epoch": 0.005737234652897304,
      "grad_norm": 4.1229472160339355,
      "learning_rate": 0.0001,
      "loss": 2.7002,
      "step": 10
    },
    {
      "epoch": 0.005737234652897304,
      "eval_loss": 2.3877382278442383,
      "eval_runtime": 35.6903,
      "eval_samples_per_second": 20.566,
      "eval_steps_per_second": 10.283,
      "step": 10
    },
    {
      "epoch": 0.008605851979345954,
      "grad_norm": 2.491757392883301,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0497,
      "step": 15
    },
    {
      "epoch": 0.011474469305794608,
      "grad_norm": 2.128636360168457,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3615,
      "step": 20
    },
    {
      "epoch": 0.011474469305794608,
      "eval_loss": 1.3325064182281494,
      "eval_runtime": 35.7225,
      "eval_samples_per_second": 20.547,
      "eval_steps_per_second": 10.274,
      "step": 20
    },
    {
      "epoch": 0.01434308663224326,
      "grad_norm": 2.977811574935913,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2361,
      "step": 25
    },
    {
      "epoch": 0.01721170395869191,
      "grad_norm": 2.637056350708008,
      "learning_rate": 5e-05,
      "loss": 1.2209,
      "step": 30
    },
    {
      "epoch": 0.01721170395869191,
      "eval_loss": 1.190410852432251,
      "eval_runtime": 36.0048,
      "eval_samples_per_second": 20.386,
      "eval_steps_per_second": 10.193,
      "step": 30
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 2.392871379852295,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2144,
      "step": 35
    },
    {
      "epoch": 0.022948938611589215,
      "grad_norm": 3.025679588317871,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1152,
      "step": 40
    },
    {
      "epoch": 0.022948938611589215,
      "eval_loss": 1.143369197845459,
      "eval_runtime": 36.3087,
      "eval_samples_per_second": 20.216,
      "eval_steps_per_second": 10.108,
      "step": 40
    },
    {
      "epoch": 0.025817555938037865,
      "grad_norm": 3.1788511276245117,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1874,
      "step": 45
    },
    {
      "epoch": 0.02868617326448652,
      "grad_norm": 2.724966049194336,
      "learning_rate": 0.0,
      "loss": 0.9904,
      "step": 50
    },
    {
      "epoch": 0.02868617326448652,
      "eval_loss": 1.1363798379898071,
      "eval_runtime": 35.8859,
      "eval_samples_per_second": 20.454,
      "eval_steps_per_second": 10.227,
      "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": 4435234416230400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}