Training in progress, step 7780, 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 sha256:0ed68652ba3a2d5567628e3bf71c1db9fd43275d967fa3327644910efb2fffd5
|
| 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 sha256:26af60d94df9483d320bb22717747999778b78812a3d2bba7a97514efa9d8025
|
| 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 sha256:60d3a49be90ab5e3c4931752b42711acfd9ddcf33dd20555285e30615736d381
|
| 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": 59.
|
| 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,
|
|
@@ -13994,6 +13994,24 @@
|
|
| 13994 |
"mean_token_accuracy": 0.6493111461400985,
|
| 13995 |
"num_tokens": 28338521.0,
|
| 13996 |
"step": 7770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13997 |
}
|
| 13998 |
],
|
| 13999 |
"logging_steps": 5,
|
|
@@ -14013,7 +14031,7 @@
|
|
| 14013 |
"attributes": {}
|
| 14014 |
}
|
| 14015 |
},
|
| 14016 |
-
"total_flos": 1.
|
| 14017 |
"train_batch_size": 4,
|
| 14018 |
"trial_name": null,
|
| 14019 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13994 |
"mean_token_accuracy": 0.6493111461400985,
|
| 13995 |
"num_tokens": 28338521.0,
|
| 13996 |
"step": 7770
|
| 13997 |
+
},
|
| 13998 |
+
{
|
| 13999 |
+
"epoch": 59.80769230769231,
|
| 14000 |
+
"grad_norm": 0.0,
|
| 14001 |
+
"learning_rate": 1.113e-05,
|
| 14002 |
+
"loss": 1.7517,
|
| 14003 |
+
"mean_token_accuracy": 0.6488117009401322,
|
| 14004 |
+
"num_tokens": 28356527.0,
|
| 14005 |
+
"step": 7775
|
| 14006 |
+
},
|
| 14007 |
+
{
|
| 14008 |
+
"epoch": 59.84615384615385,
|
| 14009 |
+
"grad_norm": 0.0,
|
| 14010 |
+
"learning_rate": 1.1105e-05,
|
| 14011 |
+
"loss": 1.7549,
|
| 14012 |
+
"mean_token_accuracy": 0.6550350069999695,
|
| 14013 |
+
"num_tokens": 28374046.0,
|
| 14014 |
+
"step": 7780
|
| 14015 |
}
|
| 14016 |
],
|
| 14017 |
"logging_steps": 5,
|
|
|
|
| 14031 |
"attributes": {}
|
| 14032 |
}
|
| 14033 |
},
|
| 14034 |
+
"total_flos": 1.4387188029279437e+18,
|
| 14035 |
"train_batch_size": 4,
|
| 14036 |
"trial_name": null,
|
| 14037 |
"trial_params": null
|