Training in progress, step 7290, 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 sha256:2e5cc60f9c32b79d3b4ccaf1e82d12be876ceab78d4b9c47cd48b9abd4d18f5e
|
| 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 sha256:2314bdeca3339399d67a0200de2f7b66afe7709c3cbd7f8ea018ea4cf93cd7c9
|
| 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:c54a3cd25f5bb626c4081bf02ea1fe0ac08a109235b705f34376eee43aaad4c3
|
| 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": 56.
|
| 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,
|
|
@@ -13112,6 +13112,24 @@
|
|
| 13112 |
"mean_token_accuracy": 0.6498360931873322,
|
| 13113 |
"num_tokens": 26549880.0,
|
| 13114 |
"step": 7280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13115 |
}
|
| 13116 |
],
|
| 13117 |
"logging_steps": 5,
|
|
@@ -13131,7 +13149,7 @@
|
|
| 13131 |
"attributes": {}
|
| 13132 |
}
|
| 13133 |
},
|
| 13134 |
-
"total_flos": 1.
|
| 13135 |
"train_batch_size": 4,
|
| 13136 |
"trial_name": null,
|
| 13137 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13112 |
"mean_token_accuracy": 0.6498360931873322,
|
| 13113 |
"num_tokens": 26549880.0,
|
| 13114 |
"step": 7280
|
| 13115 |
+
},
|
| 13116 |
+
{
|
| 13117 |
+
"epoch": 56.03846153846154,
|
| 13118 |
+
"grad_norm": 0.0,
|
| 13119 |
+
"learning_rate": 1.358e-05,
|
| 13120 |
+
"loss": 1.7991,
|
| 13121 |
+
"mean_token_accuracy": 0.6392385989427567,
|
| 13122 |
+
"num_tokens": 26567257.0,
|
| 13123 |
+
"step": 7285
|
| 13124 |
+
},
|
| 13125 |
+
{
|
| 13126 |
+
"epoch": 56.07692307692308,
|
| 13127 |
+
"grad_norm": 0.0,
|
| 13128 |
+
"learning_rate": 1.3555000000000002e-05,
|
| 13129 |
+
"loss": 1.7625,
|
| 13130 |
+
"mean_token_accuracy": 0.6449432462453842,
|
| 13131 |
+
"num_tokens": 26585384.0,
|
| 13132 |
+
"step": 7290
|
| 13133 |
}
|
| 13134 |
],
|
| 13135 |
"logging_steps": 5,
|
|
|
|
| 13149 |
"attributes": {}
|
| 13150 |
}
|
| 13151 |
},
|
| 13152 |
+
"total_flos": 1.3479309512368128e+18,
|
| 13153 |
"train_batch_size": 4,
|
| 13154 |
"trial_name": null,
|
| 13155 |
"trial_params": null
|