Training in progress, step 5700, 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:af4aac22a258ecfada1994e690631abd6a0bd0a616b4159063eccb6c59da20bc
|
| 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:cfbe2e9d816bd415c494fd7d6342059798d2a7c4f388aee506309ad9e94cd6f1
|
| 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 sha256:1c70aea73d84f01002be9e0f8ce20d821cb0722676c5fed33409d67a437a3bc2
|
| 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": 43.
|
| 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,
|
|
@@ -10250,6 +10250,24 @@
|
|
| 10250 |
"mean_token_accuracy": 0.649162980914116,
|
| 10251 |
"num_tokens": 20753638.0,
|
| 10252 |
"step": 5690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10253 |
}
|
| 10254 |
],
|
| 10255 |
"logging_steps": 5,
|
|
@@ -10269,7 +10287,7 @@
|
|
| 10269 |
"attributes": {}
|
| 10270 |
}
|
| 10271 |
},
|
| 10272 |
-
"total_flos": 1.
|
| 10273 |
"train_batch_size": 4,
|
| 10274 |
"trial_name": null,
|
| 10275 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10250 |
"mean_token_accuracy": 0.649162980914116,
|
| 10251 |
"num_tokens": 20753638.0,
|
| 10252 |
"step": 5690
|
| 10253 |
+
},
|
| 10254 |
+
{
|
| 10255 |
+
"epoch": 43.80769230769231,
|
| 10256 |
+
"grad_norm": 0.0,
|
| 10257 |
+
"learning_rate": 2.153e-05,
|
| 10258 |
+
"loss": 1.7555,
|
| 10259 |
+
"mean_token_accuracy": 0.6506625056266785,
|
| 10260 |
+
"num_tokens": 20771873.0,
|
| 10261 |
+
"step": 5695
|
| 10262 |
+
},
|
| 10263 |
+
{
|
| 10264 |
+
"epoch": 43.84615384615385,
|
| 10265 |
+
"grad_norm": 0.0,
|
| 10266 |
+
"learning_rate": 2.1505e-05,
|
| 10267 |
+
"loss": 1.7904,
|
| 10268 |
+
"mean_token_accuracy": 0.6409453451633453,
|
| 10269 |
+
"num_tokens": 20789218.0,
|
| 10270 |
+
"step": 5700
|
| 10271 |
}
|
| 10272 |
],
|
| 10273 |
"logging_steps": 5,
|
|
|
|
| 10287 |
"attributes": {}
|
| 10288 |
}
|
| 10289 |
},
|
| 10290 |
+
"total_flos": 1.0534874093081395e+18,
|
| 10291 |
"train_batch_size": 4,
|
| 10292 |
"trial_name": null,
|
| 10293 |
"trial_params": null
|