Training in progress, step 48400, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -1257,6 +1257,10 @@ You can finetune this model on your own dataset.
|
|
1257 |
| 0.8500 | 48100 | 0.2989 |
|
1258 |
| 0.8508 | 48150 | 0.3259 |
|
1259 |
| 0.8517 | 48200 | 0.2949 |
|
|
|
|
|
|
|
|
|
1260 |
|
1261 |
|
1262 |
### Framework Versions
|
|
|
1257 |
| 0.8500 | 48100 | 0.2989 |
|
1258 |
| 0.8508 | 48150 | 0.3259 |
|
1259 |
| 0.8517 | 48200 | 0.2949 |
|
1260 |
+
| 0.8526 | 48250 | 0.3914 |
|
1261 |
+
| 0.8535 | 48300 | 0.2645 |
|
1262 |
+
| 0.8544 | 48350 | 0.3358 |
|
1263 |
+
| 0.8553 | 48400 | 0.2939 |
|
1264 |
|
1265 |
|
1266 |
### Framework Versions
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90864192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b3690fa2a143ecb0d4643a209624dc7188c601389b80bc7eadb77baedd884c8
|
3 |
size 90864192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 180609210
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b68bdb8f5b522fdce4d5c267f15db43e12a7fbffda0d7ac355cca5fe6e2293a9
|
3 |
size 180609210
|
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 sha256:1337b9c73878b431640eabbf713a3fc3ffa1889559f5fe2e1f50b06fa34639d6
|
3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 988
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b78f9ce48aa6920e09eb307b60e2b49742b779f95ad33075f31c6652ec108e55
|
3 |
size 988
|
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 sha256:0bd8a22cf09f7fa5f8eaecff8876d6b0aa930d2f190895e8ce37c95ed1dd7a48
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
-
"epoch": 0.
|
6 |
"eval_steps": 500,
|
7 |
-
"global_step":
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
@@ -6756,6 +6756,34 @@
|
|
6756 |
"learning_rate": 8.256268284541832e-06,
|
6757 |
"loss": 0.2949,
|
6758 |
"step": 48200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6759 |
}
|
6760 |
],
|
6761 |
"logging_steps": 50,
|
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.8552596702655899,
|
6 |
"eval_steps": 500,
|
7 |
+
"global_step": 48400,
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
|
|
6756 |
"learning_rate": 8.256268284541832e-06,
|
6757 |
"loss": 0.2949,
|
6758 |
"step": 48200
|
6759 |
+
},
|
6760 |
+
{
|
6761 |
+
"epoch": 0.8526090721139403,
|
6762 |
+
"grad_norm": 1.490918517112732,
|
6763 |
+
"learning_rate": 8.207182266203294e-06,
|
6764 |
+
"loss": 0.3914,
|
6765 |
+
"step": 48250
|
6766 |
+
},
|
6767 |
+
{
|
6768 |
+
"epoch": 0.8534926048311569,
|
6769 |
+
"grad_norm": 1.5268231630325317,
|
6770 |
+
"learning_rate": 8.158096247864759e-06,
|
6771 |
+
"loss": 0.2645,
|
6772 |
+
"step": 48300
|
6773 |
+
},
|
6774 |
+
{
|
6775 |
+
"epoch": 0.8543761375483734,
|
6776 |
+
"grad_norm": 1.9607213735580444,
|
6777 |
+
"learning_rate": 8.109010229526222e-06,
|
6778 |
+
"loss": 0.3358,
|
6779 |
+
"step": 48350
|
6780 |
+
},
|
6781 |
+
{
|
6782 |
+
"epoch": 0.8552596702655899,
|
6783 |
+
"grad_norm": 1.4697561264038086,
|
6784 |
+
"learning_rate": 8.059924211187687e-06,
|
6785 |
+
"loss": 0.2939,
|
6786 |
+
"step": 48400
|
6787 |
}
|
6788 |
],
|
6789 |
"logging_steps": 50,
|