Hugging Face's logo

tuanna08go
/
f6e5d8ab-92b0-464a-9307-01e4c0564a76

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f6e5d8ab-92b0-464a-9307-01e4c0564a76
File size: 3,732 Bytes 
5cf8bbf
 
 
36be433
58f8dfd
36be433
5cf8bbf
 
 
 
 
 
 
58f8dfd
 
 
5cf8bbf
58f8dfd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a584aa9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f5a2b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36be433
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5cf8bbf
 
 
58f8dfd
5cf8bbf
 
58f8dfd
5cf8bbf
 
 
 
 
 
 
36be433
5cf8bbf
 
 
 
36be433
5cf8bbf
 
 
 
 
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": 0.1422475106685633,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002844950213371266,
      "eval_loss": 10.37409496307373,
      "eval_runtime": 0.8696,
      "eval_samples_per_second": 170.187,
      "eval_steps_per_second": 85.094,
      "step": 1
    },
    {
      "epoch": 0.01422475106685633,
      "grad_norm": 0.023065494373440742,
      "learning_rate": 5e-05,
      "loss": 10.3786,
      "step": 5
    },
    {
      "epoch": 0.02844950213371266,
      "grad_norm": 0.0242258682847023,
      "learning_rate": 0.0001,
      "loss": 10.3796,
      "step": 10
    },
    {
      "epoch": 0.02844950213371266,
      "eval_loss": 10.374069213867188,
      "eval_runtime": 0.8623,
      "eval_samples_per_second": 171.641,
      "eval_steps_per_second": 85.82,
      "step": 10
    },
    {
      "epoch": 0.04267425320056899,
      "grad_norm": 0.022381599992513657,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3751,
      "step": 15
    },
    {
      "epoch": 0.05689900426742532,
      "grad_norm": 0.02105828933417797,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3762,
      "step": 20
    },
    {
      "epoch": 0.05689900426742532,
      "eval_loss": 10.373991966247559,
      "eval_runtime": 0.8862,
      "eval_samples_per_second": 167.007,
      "eval_steps_per_second": 83.503,
      "step": 20
    },
    {
      "epoch": 0.07112375533428165,
      "grad_norm": 0.024705884978175163,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3769,
      "step": 25
    },
    {
      "epoch": 0.08534850640113797,
      "grad_norm": 0.024922257289290428,
      "learning_rate": 5e-05,
      "loss": 10.3789,
      "step": 30
    },
    {
      "epoch": 0.08534850640113797,
      "eval_loss": 10.373941421508789,
      "eval_runtime": 0.8889,
      "eval_samples_per_second": 166.498,
      "eval_steps_per_second": 83.249,
      "step": 30
    },
    {
      "epoch": 0.09957325746799431,
      "grad_norm": 0.021093839779496193,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3783,
      "step": 35
    },
    {
      "epoch": 0.11379800853485064,
      "grad_norm": 0.026645995676517487,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3738,
      "step": 40
    },
    {
      "epoch": 0.11379800853485064,
      "eval_loss": 10.373921394348145,
      "eval_runtime": 0.8687,
      "eval_samples_per_second": 170.376,
      "eval_steps_per_second": 85.188,
      "step": 40
    },
    {
      "epoch": 0.12802275960170698,
      "grad_norm": 0.028516408056020737,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3772,
      "step": 45
    },
    {
      "epoch": 0.1422475106685633,
      "grad_norm": 0.023940356448292732,
      "learning_rate": 0.0,
      "loss": 10.3792,
      "step": 50
    },
    {
      "epoch": 0.1422475106685633,
      "eval_loss": 10.373919486999512,
      "eval_runtime": 0.8942,
      "eval_samples_per_second": 165.508,
      "eval_steps_per_second": 82.754,
      "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": 1082963558400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}