Hugging Face's logo

duyphu
/
2315445a-419b-4c2f-38ce-7a2894c827a7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
2315445a-419b-4c2f-38ce-7a2894c827a7
File size: 3,753 Bytes 
6fb3fc0
 
 
142747b
a69c959
142747b
6fb3fc0
 
 
 
 
 
 
a69c959
 
 
6fb3fc0
a69c959
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3aa5066
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e52458
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142747b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6fb3fc0
 
 
a69c959
6fb3fc0
 
a69c959
6fb3fc0
 
 
 
 
 
 
142747b
6fb3fc0
 
 
 
142747b
6fb3fc0
 
 
 
 
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": 0.0011810628384483195,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3621256768966393e-05,
      "eval_loss": 2.5973010063171387,
      "eval_runtime": 1087.6377,
      "eval_samples_per_second": 16.39,
      "eval_steps_per_second": 8.195,
      "step": 1
    },
    {
      "epoch": 0.00011810628384483197,
      "grad_norm": 1.0713368654251099,
      "learning_rate": 5e-05,
      "loss": 2.5569,
      "step": 5
    },
    {
      "epoch": 0.00023621256768966393,
      "grad_norm": 1.5047534704208374,
      "learning_rate": 0.0001,
      "loss": 2.5144,
      "step": 10
    },
    {
      "epoch": 0.00023621256768966393,
      "eval_loss": 2.4695518016815186,
      "eval_runtime": 1090.9228,
      "eval_samples_per_second": 16.34,
      "eval_steps_per_second": 8.17,
      "step": 10
    },
    {
      "epoch": 0.0003543188515344959,
      "grad_norm": 1.2811824083328247,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4537,
      "step": 15
    },
    {
      "epoch": 0.00047242513537932787,
      "grad_norm": 1.3264565467834473,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1594,
      "step": 20
    },
    {
      "epoch": 0.00047242513537932787,
      "eval_loss": 2.0356850624084473,
      "eval_runtime": 1094.5602,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 8.143,
      "step": 20
    },
    {
      "epoch": 0.0005905314192241598,
      "grad_norm": 1.7341872453689575,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0475,
      "step": 25
    },
    {
      "epoch": 0.0007086377030689918,
      "grad_norm": 1.5635089874267578,
      "learning_rate": 5e-05,
      "loss": 1.9059,
      "step": 30
    },
    {
      "epoch": 0.0007086377030689918,
      "eval_loss": 1.9371638298034668,
      "eval_runtime": 1091.4736,
      "eval_samples_per_second": 16.332,
      "eval_steps_per_second": 8.166,
      "step": 30
    },
    {
      "epoch": 0.0008267439869138238,
      "grad_norm": 1.4265427589416504,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9827,
      "step": 35
    },
    {
      "epoch": 0.0009448502707586557,
      "grad_norm": 1.4972468614578247,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8617,
      "step": 40
    },
    {
      "epoch": 0.0009448502707586557,
      "eval_loss": 1.9017900228500366,
      "eval_runtime": 1093.2305,
      "eval_samples_per_second": 16.306,
      "eval_steps_per_second": 8.153,
      "step": 40
    },
    {
      "epoch": 0.0010629565546034876,
      "grad_norm": 1.6116687059402466,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7783,
      "step": 45
    },
    {
      "epoch": 0.0011810628384483195,
      "grad_norm": 1.700925350189209,
      "learning_rate": 0.0,
      "loss": 1.8563,
      "step": 50
    },
    {
      "epoch": 0.0011810628384483195,
      "eval_loss": 1.8956127166748047,
      "eval_runtime": 1093.018,
      "eval_samples_per_second": 16.309,
      "eval_steps_per_second": 8.154,
      "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": 7810963533987840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}