Training in progress, step 251, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51d670e3d79bfffb5e042b5a3ce721b3dac237b5e9f862d93b021230929bd440
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92c4b9a1038c3864c6aebfb5f80fb47be5cb30b63f2ac18316cd50f58f7c5813
|
3 |
size 37430836
|
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 sha256:7657b3ddb2232aa8012a32fb00c3fb92277ec0be13fceb0c90bdaa595cabccac
|
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": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1757,6 +1757,13 @@
|
|
1757 |
"learning_rate": 8.636363636363637e-05,
|
1758 |
"loss": 1.1622,
|
1759 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1760 |
}
|
1761 |
],
|
1762 |
"logging_steps": 1,
|
@@ -1776,7 +1783,7 @@
|
|
1776 |
"attributes": {}
|
1777 |
}
|
1778 |
},
|
1779 |
-
"total_flos": 3.
|
1780 |
"train_batch_size": 4,
|
1781 |
"trial_name": null,
|
1782 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6886145404663924,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 251,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1757 |
"learning_rate": 8.636363636363637e-05,
|
1758 |
"loss": 1.1622,
|
1759 |
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.6886145404663924,
|
1763 |
+
"grad_norm": 0.16669955849647522,
|
1764 |
+
"learning_rate": 8.560606060606061e-05,
|
1765 |
+
"loss": 1.1737,
|
1766 |
+
"step": 251
|
1767 |
}
|
1768 |
],
|
1769 |
"logging_steps": 1,
|
|
|
1783 |
"attributes": {}
|
1784 |
}
|
1785 |
},
|
1786 |
+
"total_flos": 3.1050607333850726e+17,
|
1787 |
"train_batch_size": 4,
|
1788 |
"trial_name": null,
|
1789 |
"trial_params": null
|