Hugging Face's logo

tuanna08go
/
e89008ec-0ddd-42bd-bbd1-7f9ce3f4ee10

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e89008ec-0ddd-42bd-bbd1-7f9ce3f4ee10
File size: 3,689 Bytes 
4874ffa
 
 
8b64cb0
f725194
8b64cb0
4874ffa
 
 
 
 
 
 
f725194
 
 
4874ffa
f725194
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc6d860
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8c6c072
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b64cb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4874ffa
 
 
f725194
4874ffa
 
f725194
4874ffa
 
 
 
 
 
 
8b64cb0
4874ffa
 
 
 
8b64cb0
4874ffa
 
 
 
 
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": 0.20408163265306123,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004081632653061225,
      "eval_loss": 7.391392230987549,
      "eval_runtime": 11.0051,
      "eval_samples_per_second": 9.45,
      "eval_steps_per_second": 4.725,
      "step": 1
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 11.124676704406738,
      "learning_rate": 5e-05,
      "loss": 7.4664,
      "step": 5
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 20.21062660217285,
      "learning_rate": 0.0001,
      "loss": 6.7943,
      "step": 10
    },
    {
      "epoch": 0.04081632653061224,
      "eval_loss": 6.0373616218566895,
      "eval_runtime": 9.9482,
      "eval_samples_per_second": 10.454,
      "eval_steps_per_second": 5.227,
      "step": 10
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 12.157793998718262,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.3938,
      "step": 15
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 30.501094818115234,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.7522,
      "step": 20
    },
    {
      "epoch": 0.08163265306122448,
      "eval_loss": 3.088772773742676,
      "eval_runtime": 9.1972,
      "eval_samples_per_second": 11.308,
      "eval_steps_per_second": 5.654,
      "step": 20
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 14.440489768981934,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.9479,
      "step": 25
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 7.746071815490723,
      "learning_rate": 5e-05,
      "loss": 2.3264,
      "step": 30
    },
    {
      "epoch": 0.12244897959183673,
      "eval_loss": 2.128019094467163,
      "eval_runtime": 9.9303,
      "eval_samples_per_second": 10.473,
      "eval_steps_per_second": 5.236,
      "step": 30
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 13.87149429321289,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0025,
      "step": 35
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 9.869282722473145,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9886,
      "step": 40
    },
    {
      "epoch": 0.16326530612244897,
      "eval_loss": 2.0035860538482666,
      "eval_runtime": 9.9467,
      "eval_samples_per_second": 10.456,
      "eval_steps_per_second": 5.228,
      "step": 40
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 23.738134384155273,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0754,
      "step": 45
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 9.707077980041504,
      "learning_rate": 0.0,
      "loss": 1.843,
      "step": 50
    },
    {
      "epoch": 0.20408163265306123,
      "eval_loss": 1.9997984170913696,
      "eval_runtime": 9.923,
      "eval_samples_per_second": 10.481,
      "eval_steps_per_second": 5.24,
      "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": 1285354690707456.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}