Training in progress, step 2810, 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 sha256:1fd67aa84606af41e3268d03e52b13dab7c16b1cbb07e293baf65ea6cfaf7c58
|
| 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 sha256:0cd857a61648ac983efacd995b119442ba2ec7d2673ef41d59339a9a325c3110
|
| 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 sha256:652eac20a228808c8477f4dbad6486fbb972f437a77d30f5d01c9bac921e328b
|
| 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,
|
|
@@ -5048,6 +5048,24 @@
|
|
| 5048 |
"mean_token_accuracy": 0.6602169930934906,
|
| 5049 |
"num_tokens": 10210631.0,
|
| 5050 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5051 |
}
|
| 5052 |
],
|
| 5053 |
"logging_steps": 5,
|
|
@@ -5067,7 +5085,7 @@
|
|
| 5067 |
"attributes": {}
|
| 5068 |
}
|
| 5069 |
},
|
| 5070 |
-
"total_flos": 5.
|
| 5071 |
"train_batch_size": 4,
|
| 5072 |
"trial_name": null,
|
| 5073 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5048 |
"mean_token_accuracy": 0.6602169930934906,
|
| 5049 |
"num_tokens": 10210631.0,
|
| 5050 |
"step": 2800
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 21.576923076923077,
|
| 5054 |
+
"grad_norm": 0.0,
|
| 5055 |
+
"learning_rate": 3.5980000000000004e-05,
|
| 5056 |
+
"loss": 1.6777,
|
| 5057 |
+
"mean_token_accuracy": 0.6621813416481018,
|
| 5058 |
+
"num_tokens": 10229408.0,
|
| 5059 |
+
"step": 2805
|
| 5060 |
+
},
|
| 5061 |
+
{
|
| 5062 |
+
"epoch": 21.615384615384617,
|
| 5063 |
+
"grad_norm": 0.0,
|
| 5064 |
+
"learning_rate": 3.5955e-05,
|
| 5065 |
+
"loss": 1.7332,
|
| 5066 |
+
"mean_token_accuracy": 0.6526377439498902,
|
| 5067 |
+
"num_tokens": 10247835.0,
|
| 5068 |
+
"step": 2810
|
| 5069 |
}
|
| 5070 |
],
|
| 5071 |
"logging_steps": 5,
|
|
|
|
| 5085 |
"attributes": {}
|
| 5086 |
}
|
| 5087 |
},
|
| 5088 |
+
"total_flos": 5.191725592343347e+17,
|
| 5089 |
"train_batch_size": 4,
|
| 5090 |
"trial_name": null,
|
| 5091 |
"trial_params": null
|