Training in progress, step 9200, 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 +42 -3
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735396724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f771d7b5ffd0a8d7190364bbadf6af62c0db85637b8db11da9ee112cd87d9874
|
| 3 |
size 735396724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470915147
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:327f6bb8bcec07c5d4401fec1471b0745e6b8dd15458f9530e61bdb432684760
|
| 3 |
size 1470915147
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64327997d62356b0511b416e4d0fefaa151527fa6dedc8dd70a297f4f4c832d8
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fa0252a46646172eb26d1700fcaea8bd925a77dd50c805acb8128f84e6fd2d4
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca67274a2d3504766771d85596bfe994f3a0326e827bf542f52033d72568226a
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62f3403513092c99c8cdb6795941cae298da0d006383ed1e7eed75bff65d63a0
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f171d2c2e97f8f2afff5cd59488f9fe54b8ff1a7106a97e2d9d2c087972e7882
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a12522daf8b4d06a66f9e5bb4e517ba6dd31bc86c3c4183be7c670615fea178c
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1f166c6172bcf9bfc8a0a55d67f945c0b4cfc10e402897e47626b664d4ba2c
|
| 3 |
size 16325
|
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 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94a52c85cef4c9a787135b078449166d7cd6f87c54b0022bf71b252e13e95ebd
|
| 3 |
size 16325
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51b6dd7a170c90865f47d8c4e0b4edcba77f0c60d0b85a7d42e5fab1ac2ce087
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 8000,
|
| 3 |
"best_metric": 0.7521935121655035,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-8000",
|
| 5 |
-
"epoch": 2.
|
| 6 |
"eval_steps": 200,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1763,6 +1763,45 @@
|
|
| 1763 |
"eval_samples_per_second": 1673.479,
|
| 1764 |
"eval_steps_per_second": 26.148,
|
| 1765 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1766 |
}
|
| 1767 |
],
|
| 1768 |
"logging_steps": 50,
|
|
@@ -1782,7 +1821,7 @@
|
|
| 1782 |
"attributes": {}
|
| 1783 |
}
|
| 1784 |
},
|
| 1785 |
-
"total_flos": 1.
|
| 1786 |
"train_batch_size": 256,
|
| 1787 |
"trial_name": null,
|
| 1788 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 8000,
|
| 3 |
"best_metric": 0.7521935121655035,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-8000",
|
| 5 |
+
"epoch": 2.3547478884054263,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 9200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1763 |
"eval_samples_per_second": 1673.479,
|
| 1764 |
"eval_steps_per_second": 26.148,
|
| 1765 |
"step": 9000
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 2.3163552597901202,
|
| 1769 |
+
"grad_norm": 0.21703936159610748,
|
| 1770 |
+
"learning_rate": 3.255273871544537e-06,
|
| 1771 |
+
"loss": 0.078,
|
| 1772 |
+
"step": 9050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 2.329152802661889,
|
| 1776 |
+
"grad_norm": 0.23036812245845795,
|
| 1777 |
+
"learning_rate": 3.1399165315269554e-06,
|
| 1778 |
+
"loss": 0.0806,
|
| 1779 |
+
"step": 9100
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 2.3419503455336574,
|
| 1783 |
+
"grad_norm": 0.20973245799541473,
|
| 1784 |
+
"learning_rate": 3.0263459589663894e-06,
|
| 1785 |
+
"loss": 0.078,
|
| 1786 |
+
"step": 9150
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 2.3547478884054263,
|
| 1790 |
+
"grad_norm": 0.2752493917942047,
|
| 1791 |
+
"learning_rate": 2.914583833605744e-06,
|
| 1792 |
+
"loss": 0.0788,
|
| 1793 |
+
"step": 9200
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 2.3547478884054263,
|
| 1797 |
+
"eval_entity_f1": 0.7506557005415369,
|
| 1798 |
+
"eval_entity_precision": 0.6757645846667153,
|
| 1799 |
+
"eval_entity_recall": 0.8837241536755593,
|
| 1800 |
+
"eval_loss": 0.08177012950181961,
|
| 1801 |
+
"eval_runtime": 477.916,
|
| 1802 |
+
"eval_samples_per_second": 1673.934,
|
| 1803 |
+
"eval_steps_per_second": 26.155,
|
| 1804 |
+
"step": 9200
|
| 1805 |
}
|
| 1806 |
],
|
| 1807 |
"logging_steps": 50,
|
|
|
|
| 1821 |
"attributes": {}
|
| 1822 |
}
|
| 1823 |
},
|
| 1824 |
+
"total_flos": 1.1637788598085878e+18,
|
| 1825 |
"train_batch_size": 256,
|
| 1826 |
"trial_name": null,
|
| 1827 |
"trial_params": null
|