Training in progress, step 1160, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7ec8210e40ef9bff7e21844dc5c54cfc672dd5f0b6d383b889b06d63ce78bed
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:719a92384cc6dd51403e415afc1f6ae48115fe7a4d0fe5c872ac52233e2ef05b
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83fea4ca6fbd27b9f9af6bebd465d4341515a1fa3bcab48235135fa1dcf1954a
|
| 3 |
size 14645
|
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 sha256:58294efefbc57d410c163650ffb40daaa45a57196d92d68ade97704bb31c1ec1
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1168,6 +1168,16 @@
|
|
| 1168 |
"mean_token_accuracy": 0.765032921731472,
|
| 1169 |
"num_tokens": 5348946.0,
|
| 1170 |
"step": 1150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1171 |
}
|
| 1172 |
],
|
| 1173 |
"logging_steps": 10,
|
|
@@ -1187,7 +1197,7 @@
|
|
| 1187 |
"attributes": {}
|
| 1188 |
}
|
| 1189 |
},
|
| 1190 |
-
"total_flos": 2.
|
| 1191 |
"train_batch_size": 4,
|
| 1192 |
"trial_name": null,
|
| 1193 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.24746666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1168 |
"mean_token_accuracy": 0.765032921731472,
|
| 1169 |
"num_tokens": 5348946.0,
|
| 1170 |
"step": 1150
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 0.8997275173664093,
|
| 1174 |
+
"epoch": 0.24746666666666667,
|
| 1175 |
+
"grad_norm": 0.21643367409706116,
|
| 1176 |
+
"learning_rate": 9.780600762597005e-05,
|
| 1177 |
+
"loss": 0.9590452194213868,
|
| 1178 |
+
"mean_token_accuracy": 0.7714703544974327,
|
| 1179 |
+
"num_tokens": 5393421.0,
|
| 1180 |
+
"step": 1160
|
| 1181 |
}
|
| 1182 |
],
|
| 1183 |
"logging_steps": 10,
|
|
|
|
| 1197 |
"attributes": {}
|
| 1198 |
}
|
| 1199 |
},
|
| 1200 |
+
"total_flos": 2.551277143593677e+16,
|
| 1201 |
"train_batch_size": 4,
|
| 1202 |
"trial_name": null,
|
| 1203 |
"trial_params": null
|