Training in progress, step 76, checkpoint
Browse files- last-checkpoint/adapter_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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d19583a3e8479f8ff8e945c44f52215fc47e340f82cf8a0d1ef4b8f748202ee
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2e030860ba59a69ca36f23e47c6a640470ee2480ea61bb548ae36fb0fe09ef
|
3 |
size 328468404
|
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 14960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20de6bbbf9cdc577e771c405f9f74d690bb4bdfedfaec96c3dfd013d520923ef
|
3 |
size 14960
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28198f5c5ec8088fd607e24d407a799f573498b266d958d4f11b0bf385b7ad8b
|
3 |
size 15024
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35770e4ff3bf16bf8937c2bfd975442cf7b1dabd257855e43af35192b863a48f
|
3 |
size 15024
|
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 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58112d23ada2896bc027c96f4d1176b13515d7f2aa903033700ffff812145add
|
3 |
size 15024
|
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 sha256:337140ce841cf3510d815bdb42f23785ade9c04144b13389125023bd316ec558
|
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": 7,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -256,6 +256,20 @@
|
|
256 |
"eval_samples_per_second": 66.203,
|
257 |
"eval_steps_per_second": 4.673,
|
258 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
259 |
}
|
260 |
],
|
261 |
"logging_steps": 3,
|
@@ -270,12 +284,12 @@
|
|
270 |
"should_evaluate": false,
|
271 |
"should_log": false,
|
272 |
"should_save": true,
|
273 |
-
"should_training_stop":
|
274 |
},
|
275 |
"attributes": {}
|
276 |
}
|
277 |
},
|
278 |
-
"total_flos":
|
279 |
"train_batch_size": 4,
|
280 |
"trial_name": null,
|
281 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.00990099009901,
|
5 |
"eval_steps": 7,
|
6 |
+
"global_step": 76,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
256 |
"eval_samples_per_second": 66.203,
|
257 |
"eval_steps_per_second": 4.673,
|
258 |
"step": 70
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 2.8514851485148514,
|
262 |
+
"grad_norm": 0.9618849754333496,
|
263 |
+
"learning_rate": 9.035651368646648e-07,
|
264 |
+
"loss": 1.0099,
|
265 |
+
"step": 72
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 2.9702970297029703,
|
269 |
+
"grad_norm": 0.9259308576583862,
|
270 |
+
"learning_rate": 5.663304084960186e-08,
|
271 |
+
"loss": 0.9467,
|
272 |
+
"step": 75
|
273 |
}
|
274 |
],
|
275 |
"logging_steps": 3,
|
|
|
284 |
"should_evaluate": false,
|
285 |
"should_log": false,
|
286 |
"should_save": true,
|
287 |
+
"should_training_stop": true
|
288 |
},
|
289 |
"attributes": {}
|
290 |
}
|
291 |
},
|
292 |
+
"total_flos": 2.1612707507181978e+17,
|
293 |
"train_batch_size": 4,
|
294 |
"trial_name": null,
|
295 |
"trial_params": null
|