Hugging Face's logo

duyphu
/
6ed444f9-942a-64a6-1370-d45dd99ca881

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6ed444f9-942a-64a6-1370-d45dd99ca881
File size: 3,705 Bytes 
101c641
 
 
34f3645
22d42a1
34f3645
101c641
 
 
 
 
 
 
22d42a1
 
 
101c641
22d42a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5bc055b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a1033e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34f3645
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101c641
 
 
22d42a1
101c641
 
22d42a1
101c641
 
 
 
 
 
 
34f3645
101c641
 
 
 
34f3645
101c641
 
 
 
 
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": 0.08688097306689835,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017376194613379669,
      "eval_loss": 2.3447093963623047,
      "eval_runtime": 16.2614,
      "eval_samples_per_second": 14.943,
      "eval_steps_per_second": 7.502,
      "step": 1
    },
    {
      "epoch": 0.008688097306689836,
      "grad_norm": 0.824364960193634,
      "learning_rate": 5e-05,
      "loss": 2.2515,
      "step": 5
    },
    {
      "epoch": 0.01737619461337967,
      "grad_norm": 0.957850992679596,
      "learning_rate": 0.0001,
      "loss": 2.2288,
      "step": 10
    },
    {
      "epoch": 0.01737619461337967,
      "eval_loss": 2.035438299179077,
      "eval_runtime": 16.4926,
      "eval_samples_per_second": 14.734,
      "eval_steps_per_second": 7.397,
      "step": 10
    },
    {
      "epoch": 0.026064291920069503,
      "grad_norm": 0.746576189994812,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8945,
      "step": 15
    },
    {
      "epoch": 0.03475238922675934,
      "grad_norm": 0.7681987881660461,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7169,
      "step": 20
    },
    {
      "epoch": 0.03475238922675934,
      "eval_loss": 1.6828279495239258,
      "eval_runtime": 16.6,
      "eval_samples_per_second": 14.639,
      "eval_steps_per_second": 7.349,
      "step": 20
    },
    {
      "epoch": 0.043440486533449174,
      "grad_norm": 0.7900924682617188,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7015,
      "step": 25
    },
    {
      "epoch": 0.052128583840139006,
      "grad_norm": 0.7530582547187805,
      "learning_rate": 5e-05,
      "loss": 1.6979,
      "step": 30
    },
    {
      "epoch": 0.052128583840139006,
      "eval_loss": 1.5826479196548462,
      "eval_runtime": 16.9166,
      "eval_samples_per_second": 14.365,
      "eval_steps_per_second": 7.212,
      "step": 30
    },
    {
      "epoch": 0.060816681146828845,
      "grad_norm": 0.6359474062919617,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5325,
      "step": 35
    },
    {
      "epoch": 0.06950477845351868,
      "grad_norm": 0.6465645432472229,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.5266,
      "step": 40
    },
    {
      "epoch": 0.06950477845351868,
      "eval_loss": 1.5528888702392578,
      "eval_runtime": 16.9993,
      "eval_samples_per_second": 14.295,
      "eval_steps_per_second": 7.177,
      "step": 40
    },
    {
      "epoch": 0.07819287576020852,
      "grad_norm": 0.5526885390281677,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5525,
      "step": 45
    },
    {
      "epoch": 0.08688097306689835,
      "grad_norm": 0.5791680812835693,
      "learning_rate": 0.0,
      "loss": 1.5404,
      "step": 50
    },
    {
      "epoch": 0.08688097306689835,
      "eval_loss": 1.5478538274765015,
      "eval_runtime": 16.5528,
      "eval_samples_per_second": 14.68,
      "eval_steps_per_second": 7.37,
      "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": 9598568528609280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}