Training in progress, step 3470, 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:a6fd57edc20f158c69c95c1410c8a700aa55d643e525c4da0bd03d35be4c0ce9
|
| 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 sha256:66c0f9e0ab9e81a3ef3749ae510ccf520ade7e486558e815963c21725c50f8b9
|
| 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 sha256:5d31b2adc78374547b60fc82e6ec3fe033e92bb5f831b8f6b3caff71c20ee44d
|
| 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": 26.
|
| 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,
|
|
@@ -6236,6 +6236,24 @@
|
|
| 6236 |
"mean_token_accuracy": 0.6540741354227066,
|
| 6237 |
"num_tokens": 12619514.0,
|
| 6238 |
"step": 3460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6239 |
}
|
| 6240 |
],
|
| 6241 |
"logging_steps": 5,
|
|
@@ -6255,7 +6273,7 @@
|
|
| 6255 |
"attributes": {}
|
| 6256 |
}
|
| 6257 |
},
|
| 6258 |
-
"total_flos": 6.
|
| 6259 |
"train_batch_size": 4,
|
| 6260 |
"trial_name": null,
|
| 6261 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6236 |
"mean_token_accuracy": 0.6540741354227066,
|
| 6237 |
"num_tokens": 12619514.0,
|
| 6238 |
"step": 3460
|
| 6239 |
+
},
|
| 6240 |
+
{
|
| 6241 |
+
"epoch": 26.653846153846153,
|
| 6242 |
+
"grad_norm": 0.0,
|
| 6243 |
+
"learning_rate": 3.268e-05,
|
| 6244 |
+
"loss": 1.7322,
|
| 6245 |
+
"mean_token_accuracy": 0.6489483207464218,
|
| 6246 |
+
"num_tokens": 12637542.0,
|
| 6247 |
+
"step": 3465
|
| 6248 |
+
},
|
| 6249 |
+
{
|
| 6250 |
+
"epoch": 26.692307692307693,
|
| 6251 |
+
"grad_norm": 0.0,
|
| 6252 |
+
"learning_rate": 3.2655000000000005e-05,
|
| 6253 |
+
"loss": 1.6812,
|
| 6254 |
+
"mean_token_accuracy": 0.6622325748205184,
|
| 6255 |
+
"num_tokens": 12656523.0,
|
| 6256 |
+
"step": 3470
|
| 6257 |
}
|
| 6258 |
],
|
| 6259 |
"logging_steps": 5,
|
|
|
|
| 6273 |
"attributes": {}
|
| 6274 |
}
|
| 6275 |
},
|
| 6276 |
+
"total_flos": 6.412568921033933e+17,
|
| 6277 |
"train_batch_size": 4,
|
| 6278 |
"trial_name": null,
|
| 6279 |
"trial_params": null
|