Training in progress, step 8800, 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:a9143105b7a0ae7436a781c2123653e59d0bc5777af0f60a58c6e5974e9e17da
|
| 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 sha256:1e17f79128b8c46fea810a73a0596f0c826ea16768d60fc0029154f29c45cb5a
|
| 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:a3dcfe51a302c55f31e9553d92e3297e4cfa0c1aeab5c3ae0f2b9cea4455e2a1
|
| 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 sha256:1bbe87f56d7657538df7f5b961dbd0cd4ea7be68df32dd2910961a0cec5ed736
|
| 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 sha256:13d92d7a789f5a6f7063784219e24e0324caef52bfd4282e5e7f0b883768fd13
|
| 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 sha256:80d4e88850a75847bad142d32f7c90d97c344d26c24cb30bb810406297fdedbf
|
| 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:b95894c8265766c8bce6ab907127675946dc54c598e9b6822c796e30da4c41ea
|
| 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 sha256:2ef85c5173d42b63aea8a1fd8c07be0604b878eebd09ec487489646edf3bcbf0
|
| 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:b4394407f7e5c024d2b81e4054eb912193dcf5838e2888f856dd25a5a9063986
|
| 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 sha256:2e46a2a820de813be1f7d9c5181c505914664d3216706c86e94e5a462108bcd2
|
| 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:f5f778cac1dbe7aba94e2c0d7e193c86e73795716c113cbc126f6dc89b780319
|
| 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,
|
|
@@ -1685,6 +1685,45 @@
|
|
| 1685 |
"eval_samples_per_second": 1668.958,
|
| 1686 |
"eval_steps_per_second": 26.077,
|
| 1687 |
"step": 8600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1688 |
}
|
| 1689 |
],
|
| 1690 |
"logging_steps": 50,
|
|
@@ -1704,7 +1743,7 @@
|
|
| 1704 |
"attributes": {}
|
| 1705 |
}
|
| 1706 |
},
|
| 1707 |
-
"total_flos": 1.
|
| 1708 |
"train_batch_size": 256,
|
| 1709 |
"trial_name": null,
|
| 1710 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 8000,
|
| 3 |
"best_metric": 0.7521935121655035,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-8000",
|
| 5 |
+
"epoch": 2.252367545431277,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 8800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1685 |
"eval_samples_per_second": 1668.958,
|
| 1686 |
"eval_steps_per_second": 26.077,
|
| 1687 |
"step": 8600
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 2.2139749168159715,
|
| 1691 |
+
"grad_norm": 0.18136319518089294,
|
| 1692 |
+
"learning_rate": 4.239744066070345e-06,
|
| 1693 |
+
"loss": 0.0786,
|
| 1694 |
+
"step": 8650
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 2.22677245968774,
|
| 1698 |
+
"grad_norm": 0.23747983574867249,
|
| 1699 |
+
"learning_rate": 4.11091308795988e-06,
|
| 1700 |
+
"loss": 0.0799,
|
| 1701 |
+
"step": 8700
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 2.2395700025595087,
|
| 1705 |
+
"grad_norm": 0.19058053195476532,
|
| 1706 |
+
"learning_rate": 3.983683521582446e-06,
|
| 1707 |
+
"loss": 0.0783,
|
| 1708 |
+
"step": 8750
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 2.252367545431277,
|
| 1712 |
+
"grad_norm": 0.23469321429729462,
|
| 1713 |
+
"learning_rate": 3.858079654077096e-06,
|
| 1714 |
+
"loss": 0.0784,
|
| 1715 |
+
"step": 8800
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 2.252367545431277,
|
| 1719 |
+
"eval_entity_f1": 0.7496111094625957,
|
| 1720 |
+
"eval_entity_precision": 0.674435385576111,
|
| 1721 |
+
"eval_entity_recall": 0.8837985535842411,
|
| 1722 |
+
"eval_loss": 0.08213646709918976,
|
| 1723 |
+
"eval_runtime": 478.1472,
|
| 1724 |
+
"eval_samples_per_second": 1673.125,
|
| 1725 |
+
"eval_steps_per_second": 26.143,
|
| 1726 |
+
"step": 8800
|
| 1727 |
}
|
| 1728 |
],
|
| 1729 |
"logging_steps": 50,
|
|
|
|
| 1743 |
"attributes": {}
|
| 1744 |
}
|
| 1745 |
},
|
| 1746 |
+
"total_flos": 1.1132399592354611e+18,
|
| 1747 |
"train_batch_size": 256,
|
| 1748 |
"trial_name": null,
|
| 1749 |
"trial_params": null
|