Training in progress, step 8000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- pytorch_model.bin +1 -1
- runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1987250795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc98c7c2bc0c4206028dfacf943fe417a45fd1a4921f341f0b750bb0a800eb46
|
3 |
size 1987250795
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
|
3 |
size 996026489
|
last-checkpoint/rng_state.pth
CHANGED
@@ -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:cda6569db1bc2d3d0435133aaa63d6f8465fafb2497de735ccd7d68f26426942
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daae6f8fb25a77228382add9166586e74f66ba572bb14f90a533805d7d13d5a9
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -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:cc1a99d87e2c39ac247735b2acf3b937a77d263374455fdfc4d46375e8f8af01
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -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,
|
@@ -258,11 +258,47 @@
|
|
258 |
"eval_samples_per_second": 2.501,
|
259 |
"eval_steps_per_second": 0.318,
|
260 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
261 |
}
|
262 |
],
|
263 |
"max_steps": 11700,
|
264 |
"num_train_epochs": 300,
|
265 |
-
"total_flos":
|
266 |
"trial_name": null,
|
267 |
"trial_params": null
|
268 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 205.12820512820514,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
258 |
"eval_samples_per_second": 2.501,
|
259 |
"eval_steps_per_second": 0.318,
|
260 |
"step": 7000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 192.31,
|
264 |
+
"learning_rate": 2.1675257731958766e-05,
|
265 |
+
"loss": 0.0036,
|
266 |
+
"step": 7500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 192.31,
|
270 |
+
"eval_bleu": 96.5899,
|
271 |
+
"eval_em": 0.6163,
|
272 |
+
"eval_gen_len": 80.7794,
|
273 |
+
"eval_loss": 0.2510390877723694,
|
274 |
+
"eval_rm": 0.7314,
|
275 |
+
"eval_runtime": 173.7032,
|
276 |
+
"eval_samples_per_second": 2.401,
|
277 |
+
"eval_steps_per_second": 0.305,
|
278 |
+
"step": 7500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 205.13,
|
282 |
+
"learning_rate": 1.9097938144329897e-05,
|
283 |
+
"loss": 0.0034,
|
284 |
+
"step": 8000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 205.13,
|
288 |
+
"eval_bleu": 96.4759,
|
289 |
+
"eval_em": 0.6331,
|
290 |
+
"eval_gen_len": 81.7578,
|
291 |
+
"eval_loss": 0.2551712095737457,
|
292 |
+
"eval_rm": 0.7434,
|
293 |
+
"eval_runtime": 170.3668,
|
294 |
+
"eval_samples_per_second": 2.448,
|
295 |
+
"eval_steps_per_second": 0.311,
|
296 |
+
"step": 8000
|
297 |
}
|
298 |
],
|
299 |
"max_steps": 11700,
|
300 |
"num_train_epochs": 300,
|
301 |
+
"total_flos": 6373629529551360.0,
|
302 |
"trial_name": null,
|
303 |
"trial_params": null
|
304 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
|
3 |
size 996026489
|
runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0
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 sha256:83a0c0976b343685aea77955cc06b9e04bc75d95b3dd3fab3c2ac650bd511676
|
3 |
+
size 18465
|