Hugging Face's logo

tuanna08go
/
323ec725-1ae7-46e9-a430-c3ff90ecf58d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
323ec725-1ae7-46e9-a430-c3ff90ecf58d
File size: 3,727 Bytes 
3a4c339
 
 
c7c132e
1366ed1
c7c132e
3a4c339
 
 
 
 
 
 
1366ed1
 
 
3a4c339
1366ed1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a602c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6fd55bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7c132e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a4c339
 
 
1366ed1
3a4c339
 
1366ed1
3a4c339
 
 
 
 
 
 
c7c132e
3a4c339
 
 
 
c7c132e
3a4c339
 
 
 
 
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": 0.0351123595505618,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007022471910112359,
      "eval_loss": 11.740757942199707,
      "eval_runtime": 6.2147,
      "eval_samples_per_second": 96.545,
      "eval_steps_per_second": 48.273,
      "step": 1
    },
    {
      "epoch": 0.0035112359550561797,
      "grad_norm": 0.17098312079906464,
      "learning_rate": 5e-05,
      "loss": 11.7564,
      "step": 5
    },
    {
      "epoch": 0.007022471910112359,
      "grad_norm": 0.2087431102991104,
      "learning_rate": 0.0001,
      "loss": 11.7573,
      "step": 10
    },
    {
      "epoch": 0.007022471910112359,
      "eval_loss": 11.739577293395996,
      "eval_runtime": 6.371,
      "eval_samples_per_second": 94.176,
      "eval_steps_per_second": 47.088,
      "step": 10
    },
    {
      "epoch": 0.010533707865168539,
      "grad_norm": 0.15307602286338806,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.7499,
      "step": 15
    },
    {
      "epoch": 0.014044943820224719,
      "grad_norm": 0.16069342195987701,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.7419,
      "step": 20
    },
    {
      "epoch": 0.014044943820224719,
      "eval_loss": 11.736796379089355,
      "eval_runtime": 6.2966,
      "eval_samples_per_second": 95.29,
      "eval_steps_per_second": 47.645,
      "step": 20
    },
    {
      "epoch": 0.0175561797752809,
      "grad_norm": 0.18296130001544952,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.7451,
      "step": 25
    },
    {
      "epoch": 0.021067415730337078,
      "grad_norm": 0.2008729875087738,
      "learning_rate": 5e-05,
      "loss": 11.7372,
      "step": 30
    },
    {
      "epoch": 0.021067415730337078,
      "eval_loss": 11.734527587890625,
      "eval_runtime": 7.1879,
      "eval_samples_per_second": 83.474,
      "eval_steps_per_second": 41.737,
      "step": 30
    },
    {
      "epoch": 0.02457865168539326,
      "grad_norm": 0.26322323083877563,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.7447,
      "step": 35
    },
    {
      "epoch": 0.028089887640449437,
      "grad_norm": 0.18757085502147675,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.7128,
      "step": 40
    },
    {
      "epoch": 0.028089887640449437,
      "eval_loss": 11.733393669128418,
      "eval_runtime": 6.0275,
      "eval_samples_per_second": 99.544,
      "eval_steps_per_second": 49.772,
      "step": 40
    },
    {
      "epoch": 0.03160112359550562,
      "grad_norm": 0.19444578886032104,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.7489,
      "step": 45
    },
    {
      "epoch": 0.0351123595505618,
      "grad_norm": 0.2428700029850006,
      "learning_rate": 0.0,
      "loss": 11.7347,
      "step": 50
    },
    {
      "epoch": 0.0351123595505618,
      "eval_loss": 11.733201026916504,
      "eval_runtime": 6.0062,
      "eval_samples_per_second": 99.896,
      "eval_steps_per_second": 49.948,
      "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": 2577100603392.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}