Training in progress, step 300, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -4
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 250490408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7063ac72bc493c2ecd4369c55c21d5de8db965f71780aadc11da18aa21d9329f
|
3 |
size 250490408
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 255266042
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d69b2147df9ff1ad66fb6ee03e554b608555b9dbe5f3d868491082ce84269e03
|
3 |
size 255266042
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b21d47cc7a4882efa3cfcffab7b0a295e807aa32cf4d422f2ea0fee6fdc78b5
|
3 |
size 15984
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08154ff6d5c399867155df805827bb349adaeaef25fdf6ef80c05783808ea6d0
|
3 |
size 15984
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46026d2af163f08f85e957f0222b624a010a302546a564969fabdb6bc7041c10
|
3 |
size 15984
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6df445c62f2ad56caaae41468d1a5cce30880f7650579c3cdba80ec12821e5de
|
3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76900c3a49367b21bcd4b796fdf1376987ed660638bdf98ccd45d1a87f5c184
|
3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a446f1cd24dab7caff9cadff49a53cd1909d2fb5bba7af3112c5b9d54f4308b
|
3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507ef075351dc4050f0467f54693ae3336a7708023dc0aefe5fd3e986b17b4a8
|
3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7dde0309a85b36fb0802e6f2c30acf442b986826853119d1478a511a694e77
|
3 |
size 15984
|
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 sha256:74485e67705dc36efbfb69b1e54f842e1ff07894d01bb0e36d6d2526a318b300
|
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": 40,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -267,6 +267,20 @@
|
|
267 |
"eval_samples_per_second": 584.495,
|
268 |
"eval_steps_per_second": 2.336,
|
269 |
"step": 280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
270 |
}
|
271 |
],
|
272 |
"logging_steps": 10,
|
@@ -281,12 +295,12 @@
|
|
281 |
"should_evaluate": false,
|
282 |
"should_log": false,
|
283 |
"should_save": true,
|
284 |
-
"should_training_stop":
|
285 |
},
|
286 |
"attributes": {}
|
287 |
}
|
288 |
},
|
289 |
-
"total_flos": 7.
|
290 |
"train_batch_size": 32,
|
291 |
"trial_name": null,
|
292 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
"eval_steps": 40,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
267 |
"eval_samples_per_second": 584.495,
|
268 |
"eval_steps_per_second": 2.336,
|
269 |
"step": 280
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 96.66666666666667,
|
273 |
+
"grad_norm": 1.1640625,
|
274 |
+
"learning_rate": 5.478104631726711e-07,
|
275 |
+
"loss": 2.8196,
|
276 |
+
"step": 290
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 100.0,
|
280 |
+
"grad_norm": 1.1796875,
|
281 |
+
"learning_rate": 0.0,
|
282 |
+
"loss": 2.8249,
|
283 |
+
"step": 300
|
284 |
}
|
285 |
],
|
286 |
"logging_steps": 10,
|
|
|
295 |
"should_evaluate": false,
|
296 |
"should_log": false,
|
297 |
"should_save": true,
|
298 |
+
"should_training_stop": true
|
299 |
},
|
300 |
"attributes": {}
|
301 |
}
|
302 |
},
|
303 |
+
"total_flos": 7.774796614362726e+16,
|
304 |
"train_batch_size": 32,
|
305 |
"trial_name": null,
|
306 |
"trial_params": null
|