Training in progress, step 2820, 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 sha256:0a71f0dee458d9c2732c4ba3b97bb237817cc51a236f697c823608ea18eeb3c1
|
| 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 sha256:18098e39361d5399050f71b2929990d3cd0d6593c5e7f92bf9fabb760b7241c9
|
| 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 sha256:81735eae90f2eade8fac67750f9929f013532d6708e9b014211dad1702988b57
|
| 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": 21.
|
| 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,
|
|
@@ -5066,6 +5066,24 @@
|
|
| 5066 |
"mean_token_accuracy": 0.6526377439498902,
|
| 5067 |
"num_tokens": 10247835.0,
|
| 5068 |
"step": 2810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5069 |
}
|
| 5070 |
],
|
| 5071 |
"logging_steps": 5,
|
|
@@ -5085,7 +5103,7 @@
|
|
| 5085 |
"attributes": {}
|
| 5086 |
}
|
| 5087 |
},
|
| 5088 |
-
"total_flos": 5.
|
| 5089 |
"train_batch_size": 4,
|
| 5090 |
"trial_name": null,
|
| 5091 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5066 |
"mean_token_accuracy": 0.6526377439498902,
|
| 5067 |
"num_tokens": 10247835.0,
|
| 5068 |
"step": 2810
|
| 5069 |
+
},
|
| 5070 |
+
{
|
| 5071 |
+
"epoch": 21.653846153846153,
|
| 5072 |
+
"grad_norm": 0.0,
|
| 5073 |
+
"learning_rate": 3.593e-05,
|
| 5074 |
+
"loss": 1.7106,
|
| 5075 |
+
"mean_token_accuracy": 0.6549345046281815,
|
| 5076 |
+
"num_tokens": 10266504.0,
|
| 5077 |
+
"step": 2815
|
| 5078 |
+
},
|
| 5079 |
+
{
|
| 5080 |
+
"epoch": 21.692307692307693,
|
| 5081 |
+
"grad_norm": 0.0,
|
| 5082 |
+
"learning_rate": 3.5905e-05,
|
| 5083 |
+
"loss": 1.7201,
|
| 5084 |
+
"mean_token_accuracy": 0.6562414228916168,
|
| 5085 |
+
"num_tokens": 10284706.0,
|
| 5086 |
+
"step": 2820
|
| 5087 |
}
|
| 5088 |
],
|
| 5089 |
"logging_steps": 5,
|
|
|
|
| 5103 |
"attributes": {}
|
| 5104 |
}
|
| 5105 |
},
|
| 5106 |
+
"total_flos": 5.2112998854918144e+17,
|
| 5107 |
"train_batch_size": 4,
|
| 5108 |
"trial_name": null,
|
| 5109 |
"trial_params": null
|