End of training
Browse files- README.md +1 -1
- logs/events.out.tfevents.1705498568.ed78651fcb5b.26.0 +2 -2
- model.safetensors +1 -1
- trainer_state.json +19 -5
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 1.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.5587
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
logs/events.out.tfevents.1705498568.ed78651fcb5b.26.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6930e8a3fc148f0b83589ac71c1d45acbb4ad6bf4afd865906970acae7214028
|
| 3 |
+
size 1719498
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535667604
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7cc5ba3f90f232edfad73676b80ea03a8dc0d8f69cdafb55b65b23f28013d7e
|
| 3 |
size 535667604
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 750,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -86,6 +86,20 @@
|
|
| 86 |
"eval_samples_per_second": 59.246,
|
| 87 |
"eval_steps_per_second": 0.936,
|
| 88 |
"step": 3750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
}
|
| 90 |
],
|
| 91 |
"logging_steps": 750,
|
|
@@ -93,7 +107,7 @@
|
|
| 93 |
"num_input_tokens_seen": 0,
|
| 94 |
"num_train_epochs": 50,
|
| 95 |
"save_steps": 750,
|
| 96 |
-
"total_flos": 1.
|
| 97 |
"train_batch_size": 16,
|
| 98 |
"trial_name": null,
|
| 99 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.7031219005584717,
|
| 3 |
+
"best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-3750",
|
| 4 |
+
"epoch": 6.062984169754126,
|
| 5 |
"eval_steps": 750,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 86 |
"eval_samples_per_second": 59.246,
|
| 87 |
"eval_steps_per_second": 0.936,
|
| 88 |
"step": 3750
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.06,
|
| 92 |
+
"learning_rate": 4.4936657681940705e-05,
|
| 93 |
+
"loss": 1.4881,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 6.06,
|
| 98 |
+
"eval_loss": 1.558716893196106,
|
| 99 |
+
"eval_runtime": 84.4241,
|
| 100 |
+
"eval_samples_per_second": 59.225,
|
| 101 |
+
"eval_steps_per_second": 0.936,
|
| 102 |
+
"step": 4500
|
| 103 |
}
|
| 104 |
],
|
| 105 |
"logging_steps": 750,
|
|
|
|
| 107 |
"num_input_tokens_seen": 0,
|
| 108 |
"num_train_epochs": 50,
|
| 109 |
"save_steps": 750,
|
| 110 |
+
"total_flos": 1.947618386638848e+17,
|
| 111 |
"train_batch_size": 16,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|