Training in progress, step 1270, 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 sha256:044e3280300ce91f2c02cdfa4d625c43f854a034eca6521f4b5344f9d61100e6
|
| 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 sha256:1d6bcc0130949738e2c3c0e4b5ebe091d55312d9d7872f771b53a5e662011d30
|
| 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 sha256:35ac77b46ca821913a30870e52a83d6470abaa197a1d2d4011ae4938b0e18ed1
|
| 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,
|
|
@@ -2276,6 +2276,24 @@
|
|
| 2276 |
"mean_token_accuracy": 0.6452909797430039,
|
| 2277 |
"num_tokens": 4597291.0,
|
| 2278 |
"step": 1260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2279 |
}
|
| 2280 |
],
|
| 2281 |
"logging_steps": 5,
|
|
@@ -2295,7 +2313,7 @@
|
|
| 2295 |
"attributes": {}
|
| 2296 |
}
|
| 2297 |
},
|
| 2298 |
-
"total_flos": 2.
|
| 2299 |
"train_batch_size": 4,
|
| 2300 |
"trial_name": null,
|
| 2301 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2276 |
"mean_token_accuracy": 0.6452909797430039,
|
| 2277 |
"num_tokens": 4597291.0,
|
| 2278 |
"step": 1260
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 9.73076923076923,
|
| 2282 |
+
"grad_norm": 0.0,
|
| 2283 |
+
"learning_rate": 4.368e-05,
|
| 2284 |
+
"loss": 1.7981,
|
| 2285 |
+
"mean_token_accuracy": 0.6409468352794647,
|
| 2286 |
+
"num_tokens": 4615469.0,
|
| 2287 |
+
"step": 1265
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 9.76923076923077,
|
| 2291 |
+
"grad_norm": 0.0,
|
| 2292 |
+
"learning_rate": 4.3655e-05,
|
| 2293 |
+
"loss": 1.7488,
|
| 2294 |
+
"mean_token_accuracy": 0.6545175701379776,
|
| 2295 |
+
"num_tokens": 4633258.0,
|
| 2296 |
+
"step": 1270
|
| 2297 |
}
|
| 2298 |
],
|
| 2299 |
"logging_steps": 5,
|
|
|
|
| 2313 |
"attributes": {}
|
| 2314 |
}
|
| 2315 |
},
|
| 2316 |
+
"total_flos": 2.3472670502780928e+17,
|
| 2317 |
"train_batch_size": 4,
|
| 2318 |
"trial_name": null,
|
| 2319 |
"trial_params": null
|