Training in progress, epoch 6, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265525384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04b7776ec725fc9ba341e190b2e795120fe64d7de3564a289bf4a4254c01ef2a
|
| 3 |
size 265525384
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 531111610
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9cf6d102c799a0490d0e6dd2169d1f97d72c6a834cedf2578fc9537225c9c9b
|
| 3 |
size 531111610
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc61cdc771c08f76397963a4a2bb6b09f117ad63275b5d07c7ab9fed47ef6d9d
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5285ade573fcc358f3adc17590ce53c6da25b842d1aff1c6b61ad5445cbe36f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.04970533400774002,
|
| 3 |
"best_model_checkpoint": "BERT_NER/checkpoint-1800",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -100,6 +100,26 @@
|
|
| 100 |
"eval_samples_per_second": 359.017,
|
| 101 |
"eval_steps_per_second": 11.35,
|
| 102 |
"step": 2250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
}
|
| 104 |
],
|
| 105 |
"logging_steps": 500,
|
|
@@ -119,7 +139,7 @@
|
|
| 119 |
"attributes": {}
|
| 120 |
}
|
| 121 |
},
|
| 122 |
-
"total_flos":
|
| 123 |
"train_batch_size": 32,
|
| 124 |
"trial_name": null,
|
| 125 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.04970533400774002,
|
| 3 |
"best_model_checkpoint": "BERT_NER/checkpoint-1800",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 100 |
"eval_samples_per_second": 359.017,
|
| 101 |
"eval_steps_per_second": 11.35,
|
| 102 |
"step": 2250
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.555555555555555,
|
| 106 |
+
"grad_norm": 0.5098891854286194,
|
| 107 |
+
"learning_rate": 8.213938048432697e-06,
|
| 108 |
+
"loss": 0.0342,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"eval_accuracy": 0.9856585263724595,
|
| 114 |
+
"eval_f1": 0.8698832134009673,
|
| 115 |
+
"eval_loss": 0.051208045333623886,
|
| 116 |
+
"eval_model_preparation_time": 0.0017,
|
| 117 |
+
"eval_precision": 0.8544611819235226,
|
| 118 |
+
"eval_recall": 0.8858721768380586,
|
| 119 |
+
"eval_runtime": 5.795,
|
| 120 |
+
"eval_samples_per_second": 354.791,
|
| 121 |
+
"eval_steps_per_second": 11.217,
|
| 122 |
+
"step": 2700
|
| 123 |
}
|
| 124 |
],
|
| 125 |
"logging_steps": 500,
|
|
|
|
| 139 |
"attributes": {}
|
| 140 |
}
|
| 141 |
},
|
| 142 |
+
"total_flos": 1610519273488704.0,
|
| 143 |
"train_batch_size": 32,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|