Training in progress, step 13300, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4103a2add7fb89c1b79882e7fb8c6de8cc76be806c788d6de2a3740a555b7c9c
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07856b3f020773c2b2571cf5b26bd9050afcac89d3a152df7e3fd595b927d69c
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f50e513ed146397e0157d8860ccde6d3ee73cd5ca826ca991c743b54369d411f
|
| 3 |
size 15006
|
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:ac652e298728dd54f7655367206bd90df753b21de87616802de685012895f259
|
| 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": 26.
|
| 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,
|
|
@@ -1139,6 +1139,13 @@
|
|
| 1139 |
"learning_rate": 1.2e-05,
|
| 1140 |
"loss": 1.2179,
|
| 1141 |
"step": 13200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1142 |
}
|
| 1143 |
],
|
| 1144 |
"logging_steps": 100,
|
|
@@ -1158,7 +1165,7 @@
|
|
| 1158 |
"attributes": {}
|
| 1159 |
}
|
| 1160 |
},
|
| 1161 |
-
"total_flos": 2.
|
| 1162 |
"train_batch_size": 8,
|
| 1163 |
"trial_name": null,
|
| 1164 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 26.595844399312607,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 13300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1139 |
"learning_rate": 1.2e-05,
|
| 1140 |
"loss": 1.2179,
|
| 1141 |
"step": 13200
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 26.595844399312607,
|
| 1145 |
+
"grad_norm": 0.25216609239578247,
|
| 1146 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 1147 |
+
"loss": 1.2237,
|
| 1148 |
+
"step": 13300
|
| 1149 |
}
|
| 1150 |
],
|
| 1151 |
"logging_steps": 100,
|
|
|
|
| 1165 |
"attributes": {}
|
| 1166 |
}
|
| 1167 |
},
|
| 1168 |
+
"total_flos": 2.0757733089399013e+19,
|
| 1169 |
"train_batch_size": 8,
|
| 1170 |
"trial_name": null,
|
| 1171 |
"trial_params": null
|