diogopaes10
commited on
Commit
β’
11288fe
1
Parent(s):
b37b8ce
Training in progress, epoch 9
Browse files- {checkpoint-1000 β checkpoint-2000}/added_tokens.json +0 -0
- {checkpoint-1000 β checkpoint-2000}/config.json +0 -0
- {checkpoint-1000 β checkpoint-2000}/optimizer.pt +1 -1
- {checkpoint-1250 β checkpoint-2000}/pytorch_model.bin +1 -1
- {checkpoint-1250 β checkpoint-2000}/rng_state.pth +1 -1
- {checkpoint-1250 β checkpoint-2000}/scheduler.pt +1 -1
- {checkpoint-1000 β checkpoint-2000}/special_tokens_map.json +0 -0
- {checkpoint-1000 β checkpoint-2000}/spm.model +0 -0
- {checkpoint-1000 β checkpoint-2000}/tokenizer.json +0 -0
- {checkpoint-1000 β checkpoint-2000}/tokenizer_config.json +0 -0
- {checkpoint-1250 β checkpoint-2000}/trainer_state.json +107 -3
- {checkpoint-1000 β checkpoint-2000}/training_args.bin +0 -0
- {checkpoint-1250 β checkpoint-2250}/added_tokens.json +0 -0
- {checkpoint-1250 β checkpoint-2250}/config.json +0 -0
- {checkpoint-1250 β checkpoint-2250}/optimizer.pt +1 -1
- {checkpoint-1000 β checkpoint-2250}/pytorch_model.bin +1 -1
- {checkpoint-1000 β checkpoint-2250}/rng_state.pth +1 -1
- {checkpoint-1000 β checkpoint-2250}/scheduler.pt +1 -1
- {checkpoint-1250 β checkpoint-2250}/special_tokens_map.json +0 -0
- {checkpoint-1250 β checkpoint-2250}/spm.model +0 -0
- {checkpoint-1250 β checkpoint-2250}/tokenizer.json +0 -0
- {checkpoint-1250 β checkpoint-2250}/tokenizer_config.json +0 -0
- {checkpoint-1000 β checkpoint-2250}/trainer_state.json +159 -3
- {checkpoint-1250 β checkpoint-2250}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
- runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0 +2 -2
{checkpoint-1000 β checkpoint-2000}/added_tokens.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2000}/config.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2000}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1475557125
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81f3216586a58d2085a7f37ca95117d6c10fbcd3dc9c70f034b94e35fd6e9149
|
3 |
size 1475557125
|
{checkpoint-1250 β checkpoint-2000}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737788917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b71e7c7798b6760f8be8c551b4e8951ebe3dfa93da41d1460b9cb33fd0d6f86
|
3 |
size 737788917
|
{checkpoint-1250 β checkpoint-2000}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96ffa685fc4010a50b57e506b086e0167e48b18c5d9de223e06893b4aa16c22a
|
3 |
size 14575
|
{checkpoint-1250 β checkpoint-2000}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626c1ac2df61838775a74a9749f04b4d515724a3ccd7da9a914227a50ae26d2d
|
3 |
size 627
|
{checkpoint-1000 β checkpoint-2000}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2000}/spm.model
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2000}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2000}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2000}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -168,11 +168,115 @@
|
|
168 |
"eval_system_ram_total": 83.48074722290039,
|
169 |
"eval_system_ram_used": 4.176631927490234,
|
170 |
"step": 1128
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
171 |
}
|
172 |
],
|
173 |
"max_steps": 3750,
|
174 |
"num_train_epochs": 15,
|
175 |
-
"total_flos":
|
176 |
"trial_name": null,
|
177 |
"trial_params": null
|
178 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
168 |
"eval_system_ram_total": 83.48074722290039,
|
169 |
"eval_system_ram_used": 4.176631927490234,
|
170 |
"step": 1128
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 5.26,
|
174 |
+
"learning_rate": 1.2992e-05,
|
175 |
+
"loss": 0.4555,
|
176 |
+
"step": 1316
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.26,
|
180 |
+
"eval_accuracy": 0.7075,
|
181 |
+
"eval_disk_space_total": 78.1898422241211,
|
182 |
+
"eval_disk_space_used": 33.76519775390625,
|
183 |
+
"eval_f1": 0.7086283787248422,
|
184 |
+
"eval_gpu_ram_allocated": 2.089810371398926,
|
185 |
+
"eval_gpu_ram_cached": 25.85546875,
|
186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
187 |
+
"eval_gpu_utilization": 46,
|
188 |
+
"eval_loss": 1.117536187171936,
|
189 |
+
"eval_precision": 0.71510102752271,
|
190 |
+
"eval_recall": 0.7075,
|
191 |
+
"eval_runtime": 2.5545,
|
192 |
+
"eval_samples_per_second": 782.936,
|
193 |
+
"eval_steps_per_second": 24.662,
|
194 |
+
"eval_system_ram_total": 83.48074722290039,
|
195 |
+
"eval_system_ram_used": 4.225734710693359,
|
196 |
+
"step": 1316
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 6.02,
|
200 |
+
"learning_rate": 1.1989333333333336e-05,
|
201 |
+
"loss": 0.3535,
|
202 |
+
"step": 1504
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 6.02,
|
206 |
+
"eval_accuracy": 0.708,
|
207 |
+
"eval_disk_space_total": 78.1898422241211,
|
208 |
+
"eval_disk_space_used": 33.76530456542969,
|
209 |
+
"eval_f1": 0.7032209621498534,
|
210 |
+
"eval_gpu_ram_allocated": 2.0898032188415527,
|
211 |
+
"eval_gpu_ram_cached": 25.85546875,
|
212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
213 |
+
"eval_gpu_utilization": 50,
|
214 |
+
"eval_loss": 1.1748836040496826,
|
215 |
+
"eval_precision": 0.7076659711678004,
|
216 |
+
"eval_recall": 0.708,
|
217 |
+
"eval_runtime": 2.3932,
|
218 |
+
"eval_samples_per_second": 835.715,
|
219 |
+
"eval_steps_per_second": 26.325,
|
220 |
+
"eval_system_ram_total": 83.48074722290039,
|
221 |
+
"eval_system_ram_used": 4.23016357421875,
|
222 |
+
"step": 1504
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 6.77,
|
226 |
+
"learning_rate": 1.0986666666666668e-05,
|
227 |
+
"loss": 0.2614,
|
228 |
+
"step": 1692
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.77,
|
232 |
+
"eval_accuracy": 0.709,
|
233 |
+
"eval_disk_space_total": 78.1898422241211,
|
234 |
+
"eval_disk_space_used": 33.76542282104492,
|
235 |
+
"eval_f1": 0.7056311006074188,
|
236 |
+
"eval_gpu_ram_allocated": 2.089783191680908,
|
237 |
+
"eval_gpu_ram_cached": 25.85546875,
|
238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
239 |
+
"eval_gpu_utilization": 49,
|
240 |
+
"eval_loss": 1.2027860879898071,
|
241 |
+
"eval_precision": 0.7079398723985221,
|
242 |
+
"eval_recall": 0.709,
|
243 |
+
"eval_runtime": 2.3888,
|
244 |
+
"eval_samples_per_second": 837.234,
|
245 |
+
"eval_steps_per_second": 26.373,
|
246 |
+
"eval_system_ram_total": 83.48074722290039,
|
247 |
+
"eval_system_ram_used": 4.237628936767578,
|
248 |
+
"step": 1692
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 7.52,
|
252 |
+
"learning_rate": 9.984e-06,
|
253 |
+
"loss": 0.2321,
|
254 |
+
"step": 1880
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.52,
|
258 |
+
"eval_accuracy": 0.698,
|
259 |
+
"eval_disk_space_total": 78.1898422241211,
|
260 |
+
"eval_disk_space_used": 33.7656135559082,
|
261 |
+
"eval_f1": 0.7018556265437493,
|
262 |
+
"eval_gpu_ram_allocated": 2.089846134185791,
|
263 |
+
"eval_gpu_ram_cached": 25.85546875,
|
264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
265 |
+
"eval_gpu_utilization": 49,
|
266 |
+
"eval_loss": 1.2960551977157593,
|
267 |
+
"eval_precision": 0.708462957552084,
|
268 |
+
"eval_recall": 0.698,
|
269 |
+
"eval_runtime": 2.391,
|
270 |
+
"eval_samples_per_second": 836.478,
|
271 |
+
"eval_steps_per_second": 26.349,
|
272 |
+
"eval_system_ram_total": 83.48074722290039,
|
273 |
+
"eval_system_ram_used": 4.224781036376953,
|
274 |
+
"step": 1880
|
275 |
}
|
276 |
],
|
277 |
"max_steps": 3750,
|
278 |
"num_train_epochs": 15,
|
279 |
+
"total_flos": 3850219425648384.0,
|
280 |
"trial_name": null,
|
281 |
"trial_params": null
|
282 |
}
|
{checkpoint-1000 β checkpoint-2000}/training_args.bin
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/added_tokens.json
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/config.json
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1475557125
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d092da6a86e9d3fddf667c0e8cc73377daca3a3d8630e425531f34eb77545eea
|
3 |
size 1475557125
|
{checkpoint-1000 β checkpoint-2250}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737788917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:627070829ce397286a4c2e3016e3ade6fbe191d90b64283878e08c51320b3b27
|
3 |
size 737788917
|
{checkpoint-1000 β checkpoint-2250}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5e45bb5a3782239e1b011180d84487acde3e428af09ac96bbf315bcb54dd611
|
3 |
size 14575
|
{checkpoint-1000 β checkpoint-2250}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a4113c70550b7a4ade899ac1f4a91272bb6bdc8dc785c5c4e5e342583232813
|
3 |
size 627
|
{checkpoint-1250 β checkpoint-2250}/special_tokens_map.json
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/spm.model
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/tokenizer.json
RENAMED
File without changes
|
{checkpoint-1250 β checkpoint-2250}/tokenizer_config.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-2250}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -142,11 +142,167 @@
|
|
142 |
"eval_system_ram_total": 83.48074722290039,
|
143 |
"eval_system_ram_used": 4.188880920410156,
|
144 |
"step": 940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"max_steps": 3750,
|
148 |
"num_train_epochs": 15,
|
149 |
-
"total_flos":
|
150 |
"trial_name": null,
|
151 |
"trial_params": null
|
152 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 2250,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
142 |
"eval_system_ram_total": 83.48074722290039,
|
143 |
"eval_system_ram_used": 4.188880920410156,
|
144 |
"step": 940
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 4.51,
|
148 |
+
"learning_rate": 1.3994666666666668e-05,
|
149 |
+
"loss": 0.4972,
|
150 |
+
"step": 1128
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 4.51,
|
154 |
+
"eval_accuracy": 0.714,
|
155 |
+
"eval_disk_space_total": 78.1898422241211,
|
156 |
+
"eval_disk_space_used": 29.642135620117188,
|
157 |
+
"eval_f1": 0.7109995031569997,
|
158 |
+
"eval_gpu_ram_allocated": 2.089801788330078,
|
159 |
+
"eval_gpu_ram_cached": 25.85546875,
|
160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
161 |
+
"eval_gpu_utilization": 47,
|
162 |
+
"eval_loss": 1.0585097074508667,
|
163 |
+
"eval_precision": 0.7129473752365556,
|
164 |
+
"eval_recall": 0.714,
|
165 |
+
"eval_runtime": 2.3843,
|
166 |
+
"eval_samples_per_second": 838.824,
|
167 |
+
"eval_steps_per_second": 26.423,
|
168 |
+
"eval_system_ram_total": 83.48074722290039,
|
169 |
+
"eval_system_ram_used": 4.176631927490234,
|
170 |
+
"step": 1128
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 5.26,
|
174 |
+
"learning_rate": 1.2992e-05,
|
175 |
+
"loss": 0.4555,
|
176 |
+
"step": 1316
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.26,
|
180 |
+
"eval_accuracy": 0.7075,
|
181 |
+
"eval_disk_space_total": 78.1898422241211,
|
182 |
+
"eval_disk_space_used": 33.76519775390625,
|
183 |
+
"eval_f1": 0.7086283787248422,
|
184 |
+
"eval_gpu_ram_allocated": 2.089810371398926,
|
185 |
+
"eval_gpu_ram_cached": 25.85546875,
|
186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
187 |
+
"eval_gpu_utilization": 46,
|
188 |
+
"eval_loss": 1.117536187171936,
|
189 |
+
"eval_precision": 0.71510102752271,
|
190 |
+
"eval_recall": 0.7075,
|
191 |
+
"eval_runtime": 2.5545,
|
192 |
+
"eval_samples_per_second": 782.936,
|
193 |
+
"eval_steps_per_second": 24.662,
|
194 |
+
"eval_system_ram_total": 83.48074722290039,
|
195 |
+
"eval_system_ram_used": 4.225734710693359,
|
196 |
+
"step": 1316
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 6.02,
|
200 |
+
"learning_rate": 1.1989333333333336e-05,
|
201 |
+
"loss": 0.3535,
|
202 |
+
"step": 1504
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 6.02,
|
206 |
+
"eval_accuracy": 0.708,
|
207 |
+
"eval_disk_space_total": 78.1898422241211,
|
208 |
+
"eval_disk_space_used": 33.76530456542969,
|
209 |
+
"eval_f1": 0.7032209621498534,
|
210 |
+
"eval_gpu_ram_allocated": 2.0898032188415527,
|
211 |
+
"eval_gpu_ram_cached": 25.85546875,
|
212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
213 |
+
"eval_gpu_utilization": 50,
|
214 |
+
"eval_loss": 1.1748836040496826,
|
215 |
+
"eval_precision": 0.7076659711678004,
|
216 |
+
"eval_recall": 0.708,
|
217 |
+
"eval_runtime": 2.3932,
|
218 |
+
"eval_samples_per_second": 835.715,
|
219 |
+
"eval_steps_per_second": 26.325,
|
220 |
+
"eval_system_ram_total": 83.48074722290039,
|
221 |
+
"eval_system_ram_used": 4.23016357421875,
|
222 |
+
"step": 1504
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 6.77,
|
226 |
+
"learning_rate": 1.0986666666666668e-05,
|
227 |
+
"loss": 0.2614,
|
228 |
+
"step": 1692
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.77,
|
232 |
+
"eval_accuracy": 0.709,
|
233 |
+
"eval_disk_space_total": 78.1898422241211,
|
234 |
+
"eval_disk_space_used": 33.76542282104492,
|
235 |
+
"eval_f1": 0.7056311006074188,
|
236 |
+
"eval_gpu_ram_allocated": 2.089783191680908,
|
237 |
+
"eval_gpu_ram_cached": 25.85546875,
|
238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
239 |
+
"eval_gpu_utilization": 49,
|
240 |
+
"eval_loss": 1.2027860879898071,
|
241 |
+
"eval_precision": 0.7079398723985221,
|
242 |
+
"eval_recall": 0.709,
|
243 |
+
"eval_runtime": 2.3888,
|
244 |
+
"eval_samples_per_second": 837.234,
|
245 |
+
"eval_steps_per_second": 26.373,
|
246 |
+
"eval_system_ram_total": 83.48074722290039,
|
247 |
+
"eval_system_ram_used": 4.237628936767578,
|
248 |
+
"step": 1692
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 7.52,
|
252 |
+
"learning_rate": 9.984e-06,
|
253 |
+
"loss": 0.2321,
|
254 |
+
"step": 1880
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.52,
|
258 |
+
"eval_accuracy": 0.698,
|
259 |
+
"eval_disk_space_total": 78.1898422241211,
|
260 |
+
"eval_disk_space_used": 33.7656135559082,
|
261 |
+
"eval_f1": 0.7018556265437493,
|
262 |
+
"eval_gpu_ram_allocated": 2.089846134185791,
|
263 |
+
"eval_gpu_ram_cached": 25.85546875,
|
264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
265 |
+
"eval_gpu_utilization": 49,
|
266 |
+
"eval_loss": 1.2960551977157593,
|
267 |
+
"eval_precision": 0.708462957552084,
|
268 |
+
"eval_recall": 0.698,
|
269 |
+
"eval_runtime": 2.391,
|
270 |
+
"eval_samples_per_second": 836.478,
|
271 |
+
"eval_steps_per_second": 26.349,
|
272 |
+
"eval_system_ram_total": 83.48074722290039,
|
273 |
+
"eval_system_ram_used": 4.224781036376953,
|
274 |
+
"step": 1880
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 8.27,
|
278 |
+
"learning_rate": 8.981333333333333e-06,
|
279 |
+
"loss": 0.197,
|
280 |
+
"step": 2068
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 8.27,
|
284 |
+
"eval_accuracy": 0.712,
|
285 |
+
"eval_disk_space_total": 78.1898422241211,
|
286 |
+
"eval_disk_space_used": 33.7657470703125,
|
287 |
+
"eval_f1": 0.7097931257647566,
|
288 |
+
"eval_gpu_ram_allocated": 2.0897903442382812,
|
289 |
+
"eval_gpu_ram_cached": 25.85546875,
|
290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
291 |
+
"eval_gpu_utilization": 45,
|
292 |
+
"eval_loss": 1.3960117101669312,
|
293 |
+
"eval_precision": 0.7137187449926237,
|
294 |
+
"eval_recall": 0.712,
|
295 |
+
"eval_runtime": 2.3878,
|
296 |
+
"eval_samples_per_second": 837.604,
|
297 |
+
"eval_steps_per_second": 26.385,
|
298 |
+
"eval_system_ram_total": 83.48074722290039,
|
299 |
+
"eval_system_ram_used": 4.219398498535156,
|
300 |
+
"step": 2068
|
301 |
}
|
302 |
],
|
303 |
"max_steps": 3750,
|
304 |
"num_train_epochs": 15,
|
305 |
+
"total_flos": 4334831263537536.0,
|
306 |
"trial_name": null,
|
307 |
"trial_params": null
|
308 |
}
|
{checkpoint-1250 β checkpoint-2250}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737788917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:627070829ce397286a4c2e3016e3ade6fbe191d90b64283878e08c51320b3b27
|
3 |
size 737788917
|
runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9480f7c1ae50fb4afe8f904897ca584d0ecad3a73621bc2257b9e47e566bf68b
|
3 |
+
size 17242
|