Hugging Face's logo

xshubhamx
/
tiny-llama-lora-no-grad

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
tiny-llama-lora-no-grad
File size: 7,605 Bytes 
604be4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
 
{
  "best_metric": 0.7610168782310045,
  "best_model_checkpoint": "tiny-llama-lora-no-grad/checkpoint-1286",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 4501,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "learning_rate": 4.740798341109383e-05,
      "loss": 1.1276,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8086754453911696,
      "eval_f1_macro": 0.6806109083601769,
      "eval_f1_micro": 0.8086754453911695,
      "eval_f1_weighted": 0.8034368965438116,
      "eval_loss": 0.6704964637756348,
      "eval_macro_fpr": 0.017184987145855975,
      "eval_macro_sensitivity": 0.6852607939619662,
      "eval_macro_specificity": 0.985525532858602,
      "eval_precision": 0.8055191978891799,
      "eval_precision_macro": 0.7052877886582329,
      "eval_recall": 0.8086754453911696,
      "eval_recall_macro": 0.6852607939619662,
      "eval_runtime": 225.0756,
      "eval_samples_per_second": 5.736,
      "eval_steps_per_second": 0.72,
      "eval_weighted_fpr": 0.016618448496265894,
      "eval_weighted_sensitivity": 0.8086754453911696,
      "eval_weighted_specificity": 0.9742075474878604,
      "step": 643
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.481596682218767e-05,
      "loss": 0.503,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8164213787761425,
      "eval_f1_macro": 0.7610168782310045,
      "eval_f1_micro": 0.8164213787761425,
      "eval_f1_weighted": 0.8154049040588042,
      "eval_loss": 0.7205804586410522,
      "eval_macro_fpr": 0.01631511703260385,
      "eval_macro_sensitivity": 0.7641451876525827,
      "eval_macro_specificity": 0.9862465922523334,
      "eval_precision": 0.8231306684180838,
      "eval_precision_macro": 0.7746203157296797,
      "eval_recall": 0.8164213787761425,
      "eval_recall_macro": 0.7641451876525827,
      "eval_runtime": 230.0342,
      "eval_samples_per_second": 5.612,
      "eval_steps_per_second": 0.704,
      "eval_weighted_fpr": 0.01580737677582872,
      "eval_weighted_sensitivity": 0.8164213787761425,
      "eval_weighted_specificity": 0.977277505008855,
      "step": 1286
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.22239502332815e-05,
      "loss": 0.3617,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8164213787761425,
      "eval_f1_macro": 0.7242203392667825,
      "eval_f1_micro": 0.8164213787761425,
      "eval_f1_weighted": 0.8123838748630571,
      "eval_loss": 0.8818831443786621,
      "eval_macro_fpr": 0.01641791191580845,
      "eval_macro_sensitivity": 0.7170126291644698,
      "eval_macro_specificity": 0.9861058068231509,
      "eval_precision": 0.8137334709054306,
      "eval_precision_macro": 0.7499445969412153,
      "eval_recall": 0.8164213787761425,
      "eval_recall_macro": 0.7170126291644698,
      "eval_runtime": 231.2189,
      "eval_samples_per_second": 5.583,
      "eval_steps_per_second": 0.701,
      "eval_weighted_fpr": 0.01580737677582872,
      "eval_weighted_sensitivity": 0.8164213787761425,
      "eval_weighted_specificity": 0.975165723571122,
      "step": 1929
    },
    {
      "epoch": 3.11,
      "learning_rate": 3.963193364437533e-05,
      "loss": 0.2293,
      "step": 2000
    },
    {
      "epoch": 3.89,
      "learning_rate": 3.7039917055469156e-05,
      "loss": 0.0618,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8086754453911696,
      "eval_f1_macro": 0.740118070206755,
      "eval_f1_micro": 0.8086754453911695,
      "eval_f1_weighted": 0.8074036218868607,
      "eval_loss": 1.1433583498001099,
      "eval_macro_fpr": 0.017252929817186225,
      "eval_macro_sensitivity": 0.729298059210823,
      "eval_macro_specificity": 0.9854230690678942,
      "eval_precision": 0.8106816369031802,
      "eval_precision_macro": 0.7673360060599891,
      "eval_recall": 0.8086754453911696,
      "eval_recall_macro": 0.729298059210823,
      "eval_runtime": 230.3503,
      "eval_samples_per_second": 5.605,
      "eval_steps_per_second": 0.703,
      "eval_weighted_fpr": 0.016618448496265894,
      "eval_weighted_sensitivity": 0.8086754453911696,
      "eval_weighted_specificity": 0.972670590627246,
      "step": 2572
    },
    {
      "epoch": 4.67,
      "learning_rate": 3.4447900466562985e-05,
      "loss": 0.0243,
      "step": 3000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8109992254066615,
      "eval_f1_macro": 0.7228040111858681,
      "eval_f1_micro": 0.8109992254066615,
      "eval_f1_weighted": 0.8085738170522284,
      "eval_loss": 1.2966285943984985,
      "eval_macro_fpr": 0.017057469386588052,
      "eval_macro_sensitivity": 0.7164376871359707,
      "eval_macro_specificity": 0.9857584427734511,
      "eval_precision": 0.8111777551016551,
      "eval_precision_macro": 0.748883500821637,
      "eval_recall": 0.8109992254066615,
      "eval_recall_macro": 0.7164376871359707,
      "eval_runtime": 230.5087,
      "eval_samples_per_second": 5.601,
      "eval_steps_per_second": 0.703,
      "eval_weighted_fpr": 0.016373641121997046,
      "eval_weighted_sensitivity": 0.8109992254066615,
      "eval_weighted_specificity": 0.9753774161951063,
      "step": 3215
    },
    {
      "epoch": 5.44,
      "learning_rate": 3.1855883877656815e-05,
      "loss": 0.0121,
      "step": 3500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8195197521301317,
      "eval_f1_macro": 0.714317091817089,
      "eval_f1_micro": 0.8195197521301317,
      "eval_f1_weighted": 0.8169833922452127,
      "eval_loss": 1.2964715957641602,
      "eval_macro_fpr": 0.01621298630582096,
      "eval_macro_sensitivity": 0.7076912641211482,
      "eval_macro_specificity": 0.9863159800251362,
      "eval_precision": 0.8174973720287305,
      "eval_precision_macro": 0.7311701256978252,
      "eval_recall": 0.8195197521301317,
      "eval_recall_macro": 0.7076912641211482,
      "eval_runtime": 230.8554,
      "eval_samples_per_second": 5.592,
      "eval_steps_per_second": 0.702,
      "eval_weighted_fpr": 0.01548687271518777,
      "eval_weighted_sensitivity": 0.8195197521301317,
      "eval_weighted_specificity": 0.9752199482469127,
      "step": 3858
    },
    {
      "epoch": 6.22,
      "learning_rate": 2.926386728875065e-05,
      "loss": 0.003,
      "step": 4000
    },
    {
      "epoch": 7.0,
      "learning_rate": 2.667185069984448e-05,
      "loss": 0.0021,
      "step": 4500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8187451587916343,
      "eval_f1_macro": 0.7165425493481726,
      "eval_f1_micro": 0.8187451587916342,
      "eval_f1_weighted": 0.8152226658384369,
      "eval_loss": 1.3710469007492065,
      "eval_macro_fpr": 0.01622856042065577,
      "eval_macro_sensitivity": 0.7112104764224284,
      "eval_macro_specificity": 0.9862882906960665,
      "eval_precision": 0.8168122443238953,
      "eval_precision_macro": 0.7519067055100973,
      "eval_recall": 0.8187451587916343,
      "eval_recall_macro": 0.7112104764224284,
      "eval_runtime": 231.4872,
      "eval_samples_per_second": 5.577,
      "eval_steps_per_second": 0.7,
      "eval_weighted_fpr": 0.015566790846194785,
      "eval_weighted_sensitivity": 0.8187451587916343,
      "eval_weighted_specificity": 0.975579201649363,
      "step": 4501
    }
  ],
  "logging_steps": 500,
  "max_steps": 9645,
  "num_train_epochs": 15,
  "save_steps": 500,
  "total_flos": 1.084604925691822e+17,
  "trial_name": null,
  "trial_params": null
}