Training in progress, step 1230, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ef67e110d67529414f326e41a9e5b7e8afdf76ee46268b92bd29858fb7272a4
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f03bd6f83e9eefb6dfc0c22fbedeebfe98facce99bb206072b671baa577ae15
|
| 3 |
size 14709
|
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 sha256:5f12913d6e9d1d5399f8da47f6d7226ddbafbc069c66e9b92a72db2bab227b67
|
| 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": 9.
|
| 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,
|
|
@@ -2204,6 +2204,24 @@
|
|
| 2204 |
"mean_token_accuracy": 0.6511468648910522,
|
| 2205 |
"num_tokens": 4450737.0,
|
| 2206 |
"step": 1220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2207 |
}
|
| 2208 |
],
|
| 2209 |
"logging_steps": 5,
|
|
@@ -2223,7 +2241,7 @@
|
|
| 2223 |
"attributes": {}
|
| 2224 |
}
|
| 2225 |
},
|
| 2226 |
-
"total_flos": 2.
|
| 2227 |
"train_batch_size": 4,
|
| 2228 |
"trial_name": null,
|
| 2229 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2204 |
"mean_token_accuracy": 0.6511468648910522,
|
| 2205 |
"num_tokens": 4450737.0,
|
| 2206 |
"step": 1220
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 9.423076923076923,
|
| 2210 |
+
"grad_norm": 0.0,
|
| 2211 |
+
"learning_rate": 4.388000000000001e-05,
|
| 2212 |
+
"loss": 1.7185,
|
| 2213 |
+
"mean_token_accuracy": 0.6551208138465882,
|
| 2214 |
+
"num_tokens": 4469277.0,
|
| 2215 |
+
"step": 1225
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 9.461538461538462,
|
| 2219 |
+
"grad_norm": 0.0,
|
| 2220 |
+
"learning_rate": 4.3855e-05,
|
| 2221 |
+
"loss": 1.7301,
|
| 2222 |
+
"mean_token_accuracy": 0.6529223084449768,
|
| 2223 |
+
"num_tokens": 4487471.0,
|
| 2224 |
+
"step": 1230
|
| 2225 |
}
|
| 2226 |
],
|
| 2227 |
"logging_steps": 5,
|
|
|
|
| 2241 |
"attributes": {}
|
| 2242 |
}
|
| 2243 |
},
|
| 2244 |
+
"total_flos": 2.2751829056765952e+17,
|
| 2245 |
"train_batch_size": 4,
|
| 2246 |
"trial_name": null,
|
| 2247 |
"trial_params": null
|