Training in progress, step 158, 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 sha256:5c32d6e93c65a9829c430d3010e3d0cf76fc326d4d00858e56a7bccd7336fd03
|
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:c0189ebae6c87ad298de80847bee2ec2f2bbf0c64d940cc20a3adf96f9120233
|
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 sha256:2778f11e01680d148bae3ad73e47fc3eeecdef31f506566b44d27d14bbdd0cb3
|
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,
|
@@ -1106,6 +1106,13 @@
|
|
1106 |
"learning_rate": 0.00015681818181818182,
|
1107 |
"loss": 1.2129,
|
1108 |
"step": 157
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1109 |
}
|
1110 |
],
|
1111 |
"logging_steps": 1,
|
@@ -1125,7 +1132,7 @@
|
|
1125 |
"attributes": {}
|
1126 |
}
|
1127 |
},
|
1128 |
-
"total_flos": 1.
|
1129 |
"train_batch_size": 4,
|
1130 |
"trial_name": null,
|
1131 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4334705075445816,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 158,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1106 |
"learning_rate": 0.00015681818181818182,
|
1107 |
"loss": 1.2129,
|
1108 |
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.4334705075445816,
|
1112 |
+
"grad_norm": 0.1565171182155609,
|
1113 |
+
"learning_rate": 0.00015606060606060607,
|
1114 |
+
"loss": 1.3144,
|
1115 |
+
"step": 158
|
1116 |
}
|
1117 |
],
|
1118 |
"logging_steps": 1,
|
|
|
1132 |
"attributes": {}
|
1133 |
}
|
1134 |
},
|
1135 |
+
"total_flos": 1.9590666619552973e+17,
|
1136 |
"train_batch_size": 4,
|
1137 |
"trial_name": null,
|
1138 |
"trial_params": null
|