MHGanainy/best-performing-clustering-0
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +210 -0
README.md
CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# best-performing-clustering-0
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
15 |
# best-performing-clustering-0
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.5489
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.5488653182983398,
|
4 |
+
"eval_runtime": 48.6887,
|
5 |
+
"eval_samples_per_second": 10.906,
|
6 |
+
"eval_steps_per_second": 1.376,
|
7 |
+
"perplexity": 4.706127195454765,
|
8 |
+
"total_flos": 4.381557669888e+16,
|
9 |
+
"train_loss": 1.8077541630365208,
|
10 |
+
"train_runtime": 1256.4921,
|
11 |
+
"train_samples_per_second": 3.829,
|
12 |
+
"train_steps_per_second": 1.915
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.5488653182983398,
|
4 |
+
"eval_runtime": 48.6887,
|
5 |
+
"eval_samples_per_second": 10.906,
|
6 |
+
"eval_steps_per_second": 1.376,
|
7 |
+
"perplexity": 4.706127195454765
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 4.381557669888e+16,
|
4 |
+
"train_loss": 1.8077541630365208,
|
5 |
+
"train_runtime": 1256.4921,
|
6 |
+
"train_samples_per_second": 3.829,
|
7 |
+
"train_steps_per_second": 1.915
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,210 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2406,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04156275976724855,
|
13 |
+
"grad_norm": 0.14744289219379425,
|
14 |
+
"learning_rate": 6.666666666666667e-06,
|
15 |
+
"loss": 2.4022,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0831255195344971,
|
20 |
+
"grad_norm": 0.3039261996746063,
|
21 |
+
"learning_rate": 1.3333333333333333e-05,
|
22 |
+
"loss": 2.3503,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.12468827930174564,
|
27 |
+
"grad_norm": 0.410941481590271,
|
28 |
+
"learning_rate": 2e-05,
|
29 |
+
"loss": 2.2434,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1662510390689942,
|
34 |
+
"grad_norm": 0.7095025181770325,
|
35 |
+
"learning_rate": 1.9888942596891267e-05,
|
36 |
+
"loss": 2.1069,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.20781379883624274,
|
41 |
+
"grad_norm": 0.9124996066093445,
|
42 |
+
"learning_rate": 1.9558237136922117e-05,
|
43 |
+
"loss": 1.9604,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24937655860349128,
|
48 |
+
"grad_norm": 0.8121271133422852,
|
49 |
+
"learning_rate": 1.9015229078008163e-05,
|
50 |
+
"loss": 1.9188,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.29093931837073983,
|
55 |
+
"grad_norm": 1.5083343982696533,
|
56 |
+
"learning_rate": 1.827197943312742e-05,
|
57 |
+
"loss": 1.8201,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3325020781379884,
|
62 |
+
"grad_norm": 1.17859947681427,
|
63 |
+
"learning_rate": 1.7344996877364282e-05,
|
64 |
+
"loss": 1.7504,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3740648379052369,
|
69 |
+
"grad_norm": 0.9727289080619812,
|
70 |
+
"learning_rate": 1.6254871065792776e-05,
|
71 |
+
"loss": 1.7776,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.41562759767248547,
|
76 |
+
"grad_norm": 1.3123071193695068,
|
77 |
+
"learning_rate": 1.5025815306751888e-05,
|
78 |
+
"loss": 1.7882,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.457190357439734,
|
83 |
+
"grad_norm": 1.1380528211593628,
|
84 |
+
"learning_rate": 1.3685128748416603e-05,
|
85 |
+
"loss": 1.7312,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.49875311720698257,
|
90 |
+
"grad_norm": 0.923092246055603,
|
91 |
+
"learning_rate": 1.2262590024297226e-05,
|
92 |
+
"loss": 1.7124,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5403158769742311,
|
97 |
+
"grad_norm": 1.1041200160980225,
|
98 |
+
"learning_rate": 1.0789795825698206e-05,
|
99 |
+
"loss": 1.7234,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5818786367414797,
|
104 |
+
"grad_norm": 1.2354481220245361,
|
105 |
+
"learning_rate": 9.299459092421558e-06,
|
106 |
+
"loss": 1.6699,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6234413965087282,
|
111 |
+
"grad_norm": 1.216248869895935,
|
112 |
+
"learning_rate": 7.824682409938328e-06,
|
113 |
+
"loss": 1.6909,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6650041562759768,
|
118 |
+
"grad_norm": 1.411401629447937,
|
119 |
+
"learning_rate": 6.3982227519528986e-06,
|
120 |
+
"loss": 1.6546,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7065669160432253,
|
125 |
+
"grad_norm": 1.126512050628662,
|
126 |
+
"learning_rate": 5.051763899516313e-06,
|
127 |
+
"loss": 1.6731,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7481296758104738,
|
132 |
+
"grad_norm": 1.1200768947601318,
|
133 |
+
"learning_rate": 3.815212697337451e-06,
|
134 |
+
"loss": 1.6337,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7896924355777224,
|
139 |
+
"grad_norm": 1.3716657161712646,
|
140 |
+
"learning_rate": 2.716034778481301e-06,
|
141 |
+
"loss": 1.595,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8312551953449709,
|
146 |
+
"grad_norm": 1.393244743347168,
|
147 |
+
"learning_rate": 1.7786445119923967e-06,
|
148 |
+
"loss": 1.6661,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8728179551122195,
|
153 |
+
"grad_norm": 1.6690272092819214,
|
154 |
+
"learning_rate": 1.0238627236098619e-06,
|
155 |
+
"loss": 1.6413,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.914380714879468,
|
160 |
+
"grad_norm": 1.564997673034668,
|
161 |
+
"learning_rate": 4.6845423440000315e-07,
|
162 |
+
"loss": 1.6164,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.9559434746467166,
|
167 |
+
"grad_norm": 1.2120723724365234,
|
168 |
+
"learning_rate": 1.247554892580616e-07,
|
169 |
+
"loss": 1.6461,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9975062344139651,
|
174 |
+
"grad_norm": 1.2864446640014648,
|
175 |
+
"learning_rate": 4.005462014766703e-10,
|
176 |
+
"loss": 1.6259,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"step": 2406,
|
182 |
+
"total_flos": 4.381557669888e+16,
|
183 |
+
"train_loss": 1.8077541630365208,
|
184 |
+
"train_runtime": 1256.4921,
|
185 |
+
"train_samples_per_second": 3.829,
|
186 |
+
"train_steps_per_second": 1.915
|
187 |
+
}
|
188 |
+
],
|
189 |
+
"logging_steps": 100,
|
190 |
+
"max_steps": 2406,
|
191 |
+
"num_input_tokens_seen": 0,
|
192 |
+
"num_train_epochs": 1,
|
193 |
+
"save_steps": 500,
|
194 |
+
"stateful_callbacks": {
|
195 |
+
"TrainerControl": {
|
196 |
+
"args": {
|
197 |
+
"should_epoch_stop": false,
|
198 |
+
"should_evaluate": false,
|
199 |
+
"should_log": false,
|
200 |
+
"should_save": true,
|
201 |
+
"should_training_stop": true
|
202 |
+
},
|
203 |
+
"attributes": {}
|
204 |
+
}
|
205 |
+
},
|
206 |
+
"total_flos": 4.381557669888e+16,
|
207 |
+
"train_batch_size": 2,
|
208 |
+
"trial_name": null,
|
209 |
+
"trial_params": null
|
210 |
+
}
|