Training in progress, epoch 8, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2371770
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd1802a9116c92de1d7d8a5c54050b5282330e534dbfbfa3963ae98ea566f29d
|
3 |
size 2371770
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990409330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8fa53c607464dfcd96648e63a02b60c0feaf5d26b6aa40668301cfa0f2fbdf7
|
3 |
size 990409330
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:525e460409507e49b218a1b42d06d85873c630a5ed78eb21f16030edb00fde0c
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:030691bc09eb03d6c2e45e9299fa03e244960d39fc02e306943d8854541c0861
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -272,13 +272,50 @@
|
|
272 |
"eval_steps_per_second": 0.602,
|
273 |
"eval_translation_length": 53190,
|
274 |
"step": 11067
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
275 |
}
|
276 |
],
|
277 |
"logging_steps": 500,
|
278 |
"max_steps": 31620,
|
279 |
"num_train_epochs": 20,
|
280 |
"save_steps": 500,
|
281 |
-
"total_flos": 1.
|
282 |
"trial_name": null,
|
283 |
"trial_params": null
|
284 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.219463586807251,
|
3 |
+
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-12648",
|
4 |
+
"epoch": 8.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12648,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
272 |
"eval_steps_per_second": 0.602,
|
273 |
"eval_translation_length": 53190,
|
274 |
"step": 11067
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 7.27,
|
278 |
+
"learning_rate": 7.221246667318116e-05,
|
279 |
+
"loss": 2.0653,
|
280 |
+
"step": 11500
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 7.59,
|
284 |
+
"learning_rate": 6.992408021231241e-05,
|
285 |
+
"loss": 2.0783,
|
286 |
+
"step": 12000
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 7.91,
|
290 |
+
"learning_rate": 6.758494251235275e-05,
|
291 |
+
"loss": 2.0813,
|
292 |
+
"step": 12500
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 8.0,
|
296 |
+
"eval_bleu": 1.0,
|
297 |
+
"eval_brevity_penalty": 1.0,
|
298 |
+
"eval_length_ratio": 1.0,
|
299 |
+
"eval_loss": 2.219463586807251,
|
300 |
+
"eval_precisions": [
|
301 |
+
1.0,
|
302 |
+
1.0,
|
303 |
+
1.0,
|
304 |
+
1.0
|
305 |
+
],
|
306 |
+
"eval_reference_length": 52305,
|
307 |
+
"eval_runtime": 583.0366,
|
308 |
+
"eval_samples_per_second": 4.821,
|
309 |
+
"eval_steps_per_second": 0.604,
|
310 |
+
"eval_translation_length": 52305,
|
311 |
+
"step": 12648
|
312 |
}
|
313 |
],
|
314 |
"logging_steps": 500,
|
315 |
"max_steps": 31620,
|
316 |
"num_train_epochs": 20,
|
317 |
"save_steps": 500,
|
318 |
+
"total_flos": 1.3854558560609894e+17,
|
319 |
"trial_name": null,
|
320 |
"trial_params": null
|
321 |
}
|