Training in progress, step 4610, 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 sha256:2e76c1fbca735a0fb94882d703eb63b451e694415529e3ed7e3e9a2d1bccd850
|
| 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 sha256:758c7e82aa4e125a7c7d8749adbf1949d5f5a92455e39de2f9cd08f561196260
|
| 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 sha256:853c46edbef1abdf55aa2301ae1f76fb50fe882c9ec94e127ac8ec4f2910f694
|
| 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": 35.
|
| 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,
|
|
@@ -8288,6 +8288,24 @@
|
|
| 8288 |
"mean_token_accuracy": 0.6545091897249222,
|
| 8289 |
"num_tokens": 16776775.0,
|
| 8290 |
"step": 4600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8291 |
}
|
| 8292 |
],
|
| 8293 |
"logging_steps": 5,
|
|
@@ -8307,7 +8325,7 @@
|
|
| 8307 |
"attributes": {}
|
| 8308 |
}
|
| 8309 |
},
|
| 8310 |
-
"total_flos": 8.
|
| 8311 |
"train_batch_size": 4,
|
| 8312 |
"trial_name": null,
|
| 8313 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8288 |
"mean_token_accuracy": 0.6545091897249222,
|
| 8289 |
"num_tokens": 16776775.0,
|
| 8290 |
"step": 4600
|
| 8291 |
+
},
|
| 8292 |
+
{
|
| 8293 |
+
"epoch": 35.42307692307692,
|
| 8294 |
+
"grad_norm": 0.0,
|
| 8295 |
+
"learning_rate": 2.698e-05,
|
| 8296 |
+
"loss": 1.7509,
|
| 8297 |
+
"mean_token_accuracy": 0.6458514422178269,
|
| 8298 |
+
"num_tokens": 16795006.0,
|
| 8299 |
+
"step": 4605
|
| 8300 |
+
},
|
| 8301 |
+
{
|
| 8302 |
+
"epoch": 35.46153846153846,
|
| 8303 |
+
"grad_norm": 0.0,
|
| 8304 |
+
"learning_rate": 2.6955000000000002e-05,
|
| 8305 |
+
"loss": 1.8091,
|
| 8306 |
+
"mean_token_accuracy": 0.6382217675447464,
|
| 8307 |
+
"num_tokens": 16812133.0,
|
| 8308 |
+
"step": 4610
|
| 8309 |
}
|
| 8310 |
],
|
| 8311 |
"logging_steps": 5,
|
|
|
|
| 8325 |
"attributes": {}
|
| 8326 |
}
|
| 8327 |
},
|
| 8328 |
+
"total_flos": 8.521470365810688e+17,
|
| 8329 |
"train_batch_size": 4,
|
| 8330 |
"trial_name": null,
|
| 8331 |
"trial_params": null
|