Hugging Face's logo

tuanna08go
/
a5398e13-1cfc-5486-27db-03400d5e39af

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
a5398e13-1cfc-5486-27db-03400d5e39af
File size: 3,726 Bytes
8ec4d5a
 
 
f3782e4
47b4fa0
f3782e4
8ec4d5a
 
 
 
 
 
 
47b4fa0
 
 
8ec4d5a
47b4fa0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad0c267
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b328cc0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f3782e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ec4d5a
 
 
47b4fa0
8ec4d5a
 
47b4fa0
8ec4d5a
 
 
 
 
 
 
f3782e4
8ec4d5a
 
 
 
f3782e4
8ec4d5a
 
 
 
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": 0.008624035186063559,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017248070372127117,
      "eval_loss": 6.329273700714111,
      "eval_runtime": 37.2306,
      "eval_samples_per_second": 65.591,
      "eval_steps_per_second": 32.796,
      "step": 1
    },
    {
      "epoch": 0.0008624035186063559,
      "grad_norm": 2.544393539428711,
      "learning_rate": 5e-05,
      "loss": 6.2995,
      "step": 5
    },
    {
      "epoch": 0.0017248070372127117,
      "grad_norm": 2.786011219024658,
      "learning_rate": 0.0001,
      "loss": 6.2716,
      "step": 10
    },
    {
      "epoch": 0.0017248070372127117,
      "eval_loss": 6.270487308502197,
      "eval_runtime": 38.5696,
      "eval_samples_per_second": 63.314,
      "eval_steps_per_second": 31.657,
      "step": 10
    },
    {
      "epoch": 0.002587210555819068,
      "grad_norm": 3.6353487968444824,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.0843,
      "step": 15
    },
    {
      "epoch": 0.0034496140744254234,
      "grad_norm": 2.0951130390167236,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.8982,
      "step": 20
    },
    {
      "epoch": 0.0034496140744254234,
      "eval_loss": 5.9787092208862305,
      "eval_runtime": 37.6929,
      "eval_samples_per_second": 64.787,
      "eval_steps_per_second": 32.393,
      "step": 20
    },
    {
      "epoch": 0.0043120175930317795,
      "grad_norm": 3.2061691284179688,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.0776,
      "step": 25
    },
    {
      "epoch": 0.005174421111638136,
      "grad_norm": 2.500523328781128,
      "learning_rate": 5e-05,
      "loss": 5.8464,
      "step": 30
    },
    {
      "epoch": 0.005174421111638136,
      "eval_loss": 5.717452049255371,
      "eval_runtime": 39.253,
      "eval_samples_per_second": 62.212,
      "eval_steps_per_second": 31.106,
      "step": 30
    },
    {
      "epoch": 0.006036824630244492,
      "grad_norm": 1.5522089004516602,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.6319,
      "step": 35
    },
    {
      "epoch": 0.006899228148850847,
      "grad_norm": 1.5637425184249878,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.5491,
      "step": 40
    },
    {
      "epoch": 0.006899228148850847,
      "eval_loss": 5.575439929962158,
      "eval_runtime": 37.6254,
      "eval_samples_per_second": 64.903,
      "eval_steps_per_second": 32.451,
      "step": 40
    },
    {
      "epoch": 0.007761631667457203,
      "grad_norm": 1.783243179321289,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.4637,
      "step": 45
    },
    {
      "epoch": 0.008624035186063559,
      "grad_norm": 2.0012452602386475,
      "learning_rate": 0.0,
      "loss": 5.6158,
      "step": 50
    },
    {
      "epoch": 0.008624035186063559,
      "eval_loss": 5.548293113708496,
      "eval_runtime": 37.6341,
      "eval_samples_per_second": 64.888,
      "eval_steps_per_second": 32.444,
      "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": 171463252377600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}