Hugging Face's logo

phungkhaccuong
/
003a17bd-999b-df7b-8f1c-ae6ee5673233

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
003a17bd-999b-df7b-8f1c-ae6ee5673233
File size: 3,711 Bytes
bf1630d
 
 
fc82f8a
dbdaada
fc82f8a
bf1630d
 
 
 
 
 
 
dbdaada
 
 
bf1630d
dbdaada
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df03a34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59b9652
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc82f8a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bf1630d
 
 
dbdaada
bf1630d
 
dbdaada
bf1630d
 
 
 
 
 
 
fc82f8a
bf1630d
 
 
 
fc82f8a
bf1630d
 
 
 
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": 0.13850415512465375,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002770083102493075,
      "eval_loss": 0.8790126442909241,
      "eval_runtime": 11.2362,
      "eval_samples_per_second": 13.617,
      "eval_steps_per_second": 6.853,
      "step": 1
    },
    {
      "epoch": 0.013850415512465374,
      "grad_norm": 0.5528757572174072,
      "learning_rate": 5e-05,
      "loss": 0.8437,
      "step": 5
    },
    {
      "epoch": 0.027700831024930747,
      "grad_norm": 0.7231165766716003,
      "learning_rate": 0.0001,
      "loss": 0.8243,
      "step": 10
    },
    {
      "epoch": 0.027700831024930747,
      "eval_loss": 0.8458106517791748,
      "eval_runtime": 11.376,
      "eval_samples_per_second": 13.449,
      "eval_steps_per_second": 6.769,
      "step": 10
    },
    {
      "epoch": 0.04155124653739612,
      "grad_norm": 0.6403104662895203,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6981,
      "step": 15
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 0.5902954339981079,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6614,
      "step": 20
    },
    {
      "epoch": 0.055401662049861494,
      "eval_loss": 0.763834536075592,
      "eval_runtime": 11.7356,
      "eval_samples_per_second": 13.037,
      "eval_steps_per_second": 6.561,
      "step": 20
    },
    {
      "epoch": 0.06925207756232687,
      "grad_norm": 0.5696752071380615,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6615,
      "step": 25
    },
    {
      "epoch": 0.08310249307479224,
      "grad_norm": 0.5728344321250916,
      "learning_rate": 5e-05,
      "loss": 0.7297,
      "step": 30
    },
    {
      "epoch": 0.08310249307479224,
      "eval_loss": 0.7355851531028748,
      "eval_runtime": 11.8476,
      "eval_samples_per_second": 12.914,
      "eval_steps_per_second": 6.499,
      "step": 30
    },
    {
      "epoch": 0.09695290858725762,
      "grad_norm": 0.5396150946617126,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.658,
      "step": 35
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.5392118096351624,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6982,
      "step": 40
    },
    {
      "epoch": 0.11080332409972299,
      "eval_loss": 0.7300357222557068,
      "eval_runtime": 11.8185,
      "eval_samples_per_second": 12.946,
      "eval_steps_per_second": 6.515,
      "step": 40
    },
    {
      "epoch": 0.12465373961218837,
      "grad_norm": 0.6359060406684875,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7617,
      "step": 45
    },
    {
      "epoch": 0.13850415512465375,
      "grad_norm": 0.504328727722168,
      "learning_rate": 0.0,
      "loss": 0.6836,
      "step": 50
    },
    {
      "epoch": 0.13850415512465375,
      "eval_loss": 0.7285895347595215,
      "eval_runtime": 11.7706,
      "eval_samples_per_second": 12.998,
      "eval_steps_per_second": 6.542,
      "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": 1.109738548887552e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}