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:
|
| 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: 1.9960
|
| 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 sha256:67e1516e292c6ebb7c315d8af3e03af99a120f0347fc3bc6c1d4187b8d041d14
|
| 3 |
+
size 1718642
|
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 sha256:40945b1e1b326835d42bda4cb2b00f879db6762cddba4ad91db57b8b5f62bc5b
|
| 3 |
size 535667604
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 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,
|
|
@@ -58,6 +58,20 @@
|
|
| 58 |
"eval_samples_per_second": 59.249,
|
| 59 |
"eval_steps_per_second": 0.936,
|
| 60 |
"step": 2250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 750,
|
|
@@ -65,7 +79,7 @@
|
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
"num_train_epochs": 50,
|
| 67 |
"save_steps": 750,
|
| 68 |
-
"total_flos":
|
| 69 |
"train_batch_size": 16,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.4815261363983154,
|
| 3 |
+
"best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-2250",
|
| 4 |
+
"epoch": 4.042101717750084,
|
| 5 |
"eval_steps": 750,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 58 |
"eval_samples_per_second": 59.249,
|
| 59 |
"eval_steps_per_second": 0.936,
|
| 60 |
"step": 2250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.04,
|
| 64 |
+
"learning_rate": 4.6958221024258764e-05,
|
| 65 |
+
"loss": 2.1885,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.04,
|
| 70 |
+
"eval_loss": 1.9960429668426514,
|
| 71 |
+
"eval_runtime": 84.3112,
|
| 72 |
+
"eval_samples_per_second": 59.304,
|
| 73 |
+
"eval_steps_per_second": 0.937,
|
| 74 |
+
"step": 3000
|
| 75 |
}
|
| 76 |
],
|
| 77 |
"logging_steps": 750,
|
|
|
|
| 79 |
"num_input_tokens_seen": 0,
|
| 80 |
"num_train_epochs": 50,
|
| 81 |
"save_steps": 750,
|
| 82 |
+
"total_flos": 1.2984212751372288e+17,
|
| 83 |
"train_batch_size": 16,
|
| 84 |
"trial_name": null,
|
| 85 |
"trial_params": null
|