Hugging Face's logo

phungkhaccuong
/
18d6d3aa-3fae-4913-8e78-59701e8aa297

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
18d6d3aa-3fae-4913-8e78-59701e8aa297
File size: 3,701 Bytes
975dc07
 
 
5be1024
165a82d
5be1024
975dc07
 
 
 
 
 
 
165a82d
 
 
975dc07
165a82d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
518d471
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5db4ad2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5be1024
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
975dc07
 
 
165a82d
975dc07
 
165a82d
975dc07
 
 
 
 
 
 
5be1024
975dc07
 
 
 
5be1024
975dc07
 
 
 
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": 0.13966480446927373,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "eval_loss": 9.896864891052246,
      "eval_runtime": 4.9175,
      "eval_samples_per_second": 30.707,
      "eval_steps_per_second": 15.455,
      "step": 1
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 41.86698532104492,
      "learning_rate": 5e-05,
      "loss": 8.7545,
      "step": 5
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 15.126924514770508,
      "learning_rate": 0.0001,
      "loss": 7.191,
      "step": 10
    },
    {
      "epoch": 0.027932960893854747,
      "eval_loss": 5.595855712890625,
      "eval_runtime": 4.8333,
      "eval_samples_per_second": 31.241,
      "eval_steps_per_second": 15.724,
      "step": 10
    },
    {
      "epoch": 0.04189944134078212,
      "grad_norm": 4.385186672210693,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.0465,
      "step": 15
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 3.310457706451416,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.4644,
      "step": 20
    },
    {
      "epoch": 0.055865921787709494,
      "eval_loss": 4.217800617218018,
      "eval_runtime": 4.9043,
      "eval_samples_per_second": 30.789,
      "eval_steps_per_second": 15.497,
      "step": 20
    },
    {
      "epoch": 0.06983240223463687,
      "grad_norm": 3.4962682723999023,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.1238,
      "step": 25
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 3.5850486755371094,
      "learning_rate": 5e-05,
      "loss": 3.7438,
      "step": 30
    },
    {
      "epoch": 0.08379888268156424,
      "eval_loss": 3.5863335132598877,
      "eval_runtime": 4.88,
      "eval_samples_per_second": 30.942,
      "eval_steps_per_second": 15.574,
      "step": 30
    },
    {
      "epoch": 0.09776536312849161,
      "grad_norm": 3.6995723247528076,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.3512,
      "step": 35
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 3.8023898601531982,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.2392,
      "step": 40
    },
    {
      "epoch": 0.11173184357541899,
      "eval_loss": 3.2825071811676025,
      "eval_runtime": 4.8262,
      "eval_samples_per_second": 31.287,
      "eval_steps_per_second": 15.747,
      "step": 40
    },
    {
      "epoch": 0.12569832402234637,
      "grad_norm": 4.109200477600098,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.2066,
      "step": 45
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 2.853254795074463,
      "learning_rate": 0.0,
      "loss": 3.1558,
      "step": 50
    },
    {
      "epoch": 0.13966480446927373,
      "eval_loss": 3.2231385707855225,
      "eval_runtime": 4.8098,
      "eval_samples_per_second": 31.394,
      "eval_steps_per_second": 15.801,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}