Hugging Face's logo

chauhoang
/
843b8ca3-ce61-7aad-6b83-e59e1e68eb52

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
843b8ca3-ce61-7aad-6b83-e59e1e68eb52
File size: 3,742 Bytes 
5ebbcaf
 
 
38f84f4
959f763
38f84f4
5ebbcaf
 
 
 
 
 
 
959f763
 
 
5ebbcaf
959f763
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9554da2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ede9272
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38f84f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ebbcaf
 
 
959f763
5ebbcaf
 
959f763
5ebbcaf
 
 
 
 
 
 
38f84f4
5ebbcaf
 
 
 
38f84f4
5ebbcaf
 
 
 
 
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": 0.010225994477962982,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020451988955925963,
      "eval_loss": 0.6167752146720886,
      "eval_runtime": 139.0642,
      "eval_samples_per_second": 14.806,
      "eval_steps_per_second": 7.407,
      "step": 1
    },
    {
      "epoch": 0.0010225994477962982,
      "grad_norm": 0.5801008939743042,
      "learning_rate": 5e-05,
      "loss": 0.6021,
      "step": 5
    },
    {
      "epoch": 0.0020451988955925964,
      "grad_norm": 0.6938685178756714,
      "learning_rate": 0.0001,
      "loss": 0.4494,
      "step": 10
    },
    {
      "epoch": 0.0020451988955925964,
      "eval_loss": 0.37807127833366394,
      "eval_runtime": 140.2577,
      "eval_samples_per_second": 14.68,
      "eval_steps_per_second": 7.344,
      "step": 10
    },
    {
      "epoch": 0.0030677983433888946,
      "grad_norm": 0.7771623134613037,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.29,
      "step": 15
    },
    {
      "epoch": 0.004090397791185193,
      "grad_norm": 0.19722718000411987,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1783,
      "step": 20
    },
    {
      "epoch": 0.004090397791185193,
      "eval_loss": 0.15935975313186646,
      "eval_runtime": 140.3087,
      "eval_samples_per_second": 14.675,
      "eval_steps_per_second": 7.341,
      "step": 20
    },
    {
      "epoch": 0.005112997238981491,
      "grad_norm": 0.08959358930587769,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1371,
      "step": 25
    },
    {
      "epoch": 0.006135596686777789,
      "grad_norm": 0.0525275394320488,
      "learning_rate": 5e-05,
      "loss": 0.1393,
      "step": 30
    },
    {
      "epoch": 0.006135596686777789,
      "eval_loss": 0.14109905064105988,
      "eval_runtime": 140.6257,
      "eval_samples_per_second": 14.642,
      "eval_steps_per_second": 7.324,
      "step": 30
    },
    {
      "epoch": 0.0071581961345740875,
      "grad_norm": 0.8137596845626831,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1435,
      "step": 35
    },
    {
      "epoch": 0.008180795582370386,
      "grad_norm": 0.042203761637210846,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1276,
      "step": 40
    },
    {
      "epoch": 0.008180795582370386,
      "eval_loss": 0.13725407421588898,
      "eval_runtime": 140.2588,
      "eval_samples_per_second": 14.68,
      "eval_steps_per_second": 7.344,
      "step": 40
    },
    {
      "epoch": 0.009203395030166683,
      "grad_norm": 0.029296882450580597,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1244,
      "step": 45
    },
    {
      "epoch": 0.010225994477962982,
      "grad_norm": 0.0394265353679657,
      "learning_rate": 0.0,
      "loss": 0.1291,
      "step": 50
    },
    {
      "epoch": 0.010225994477962982,
      "eval_loss": 0.1366967409849167,
      "eval_runtime": 139.8716,
      "eval_samples_per_second": 14.721,
      "eval_steps_per_second": 7.364,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}