Hugging Face's logo

tuantmdev
/
6860d41c-54b0-429a-b48d-4e896b5c9961

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
6860d41c-54b0-429a-b48d-4e896b5c9961
File size: 4,109 Bytes
1ac480e
cd43885
 
acdb7db
1ac480e
acdb7db
1ac480e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e70fe15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234efb1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a9117db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76f30e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd43885
 
 
 
 
 
 
 
 
 
 
 
 
 
 
acdb7db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ac480e
 
 
 
 
 
 
 
 
 
 
 
 
 
acdb7db
1ac480e
 
 
 
 
 
 
 
 
 
 
 
 
acdb7db
1ac480e
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
{
  "best_metric": 1.5710722208023071,
  "best_model_checkpoint": "miner_id_24/checkpoint-300",
  "epoch": 0.02157996146435453,
  "eval_steps": 50,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.165703275529865e-05,
      "eval_loss": 2.288787603378296,
      "eval_runtime": 1041.9153,
      "eval_samples_per_second": 13.109,
      "eval_steps_per_second": 6.554,
      "step": 1
    },
    {
      "epoch": 0.0024662813102119463,
      "grad_norm": 1.1392245292663574,
      "learning_rate": 5e-05,
      "loss": 1.8648,
      "step": 40
    },
    {
      "epoch": 0.0030828516377649326,
      "eval_loss": 1.6245982646942139,
      "eval_runtime": 1041.7956,
      "eval_samples_per_second": 13.11,
      "eval_steps_per_second": 6.555,
      "step": 50
    },
    {
      "epoch": 0.0049325626204238925,
      "grad_norm": 1.1976816654205322,
      "learning_rate": 0.0001,
      "loss": 1.6089,
      "step": 80
    },
    {
      "epoch": 0.006165703275529865,
      "eval_loss": 1.608966588973999,
      "eval_runtime": 1041.4182,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 6.557,
      "step": 100
    },
    {
      "epoch": 0.007398843930635838,
      "grad_norm": 0.9106088876724243,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5941,
      "step": 120
    },
    {
      "epoch": 0.009248554913294798,
      "eval_loss": 1.6026890277862549,
      "eval_runtime": 1041.2784,
      "eval_samples_per_second": 13.117,
      "eval_steps_per_second": 6.558,
      "step": 150
    },
    {
      "epoch": 0.009865125240847785,
      "grad_norm": 1.0939823389053345,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6436,
      "step": 160
    },
    {
      "epoch": 0.01233140655105973,
      "grad_norm": 1.1950139999389648,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5907,
      "step": 200
    },
    {
      "epoch": 0.01233140655105973,
      "eval_loss": 1.5895808935165405,
      "eval_runtime": 1041.3859,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 6.558,
      "step": 200
    },
    {
      "epoch": 0.014797687861271676,
      "grad_norm": 0.8904630541801453,
      "learning_rate": 5e-05,
      "loss": 1.587,
      "step": 240
    },
    {
      "epoch": 0.015414258188824663,
      "eval_loss": 1.5806567668914795,
      "eval_runtime": 1041.1372,
      "eval_samples_per_second": 13.118,
      "eval_steps_per_second": 6.559,
      "step": 250
    },
    {
      "epoch": 0.017263969171483623,
      "grad_norm": 0.8200499415397644,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6022,
      "step": 280
    },
    {
      "epoch": 0.018497109826589597,
      "eval_loss": 1.5710722208023071,
      "eval_runtime": 1041.1766,
      "eval_samples_per_second": 13.118,
      "eval_steps_per_second": 6.559,
      "step": 300
    },
    {
      "epoch": 0.01973025048169557,
      "grad_norm": 0.7950920462608337,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.606,
      "step": 320
    },
    {
      "epoch": 0.02157996146435453,
      "eval_loss": 1.5714285373687744,
      "eval_runtime": 1042.0279,
      "eval_samples_per_second": 13.107,
      "eval_steps_per_second": 6.554,
      "step": 350
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4318745844658995e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}