youdiniplays
commited on
Training in progress, step 20000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e48685c58809f94b252a10e8e6d04de63dbc84d87ed5974d0b0633fe288b589
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5348156f7b5e2d7d0ebcf5817e9992d12be92e5ff19af901899ea2c1280662f6
|
3 |
size 484163514
|
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:c82b39d0f295e42b547445c4bc57a0ba084df61eb2dc44cece0bc7da8fb97132
|
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 sha256:9be406df989c6f57d4b4574ae1f09da87eda95f9f48a11f762ade61581501779
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
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,
|
@@ -261,13 +261,29 @@
|
|
261 |
"learning_rate": 0.0004016881522406384,
|
262 |
"loss": 0.525,
|
263 |
"step": 19500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
264 |
}
|
265 |
],
|
266 |
"logging_steps": 500,
|
267 |
"max_steps": 32580,
|
268 |
"num_train_epochs": 5,
|
269 |
"save_steps": 500,
|
270 |
-
"total_flos": 1.
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|
273 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0693677102516883,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
261 |
"learning_rate": 0.0004016881522406384,
|
262 |
"loss": 0.525,
|
263 |
"step": 19500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 3.0,
|
267 |
+
"eval_bleu": 3.8722,
|
268 |
+
"eval_gen_len": 18.219,
|
269 |
+
"eval_loss": 0.4868793785572052,
|
270 |
+
"eval_runtime": 23.2067,
|
271 |
+
"eval_samples_per_second": 43.091,
|
272 |
+
"eval_steps_per_second": 2.715,
|
273 |
+
"step": 19548
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 3.07,
|
277 |
+
"learning_rate": 0.00038637200736648254,
|
278 |
+
"loss": 0.4934,
|
279 |
+
"step": 20000
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 500,
|
283 |
"max_steps": 32580,
|
284 |
"num_train_epochs": 5,
|
285 |
"save_steps": 500,
|
286 |
+
"total_flos": 1.0601906970820608e+16,
|
287 |
"trial_name": null,
|
288 |
"trial_params": null
|
289 |
}
|