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: 1.5604
|
| 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:cecb48776cf21de5f456d83cb806dd5ffb7469347503db0100921b826c040deb
|
| 3 |
+
size 1719926
|
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:b0f86e07570c9439b202aa621ffe5ab835342ee19bd675b389c8e450472ec42d
|
| 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,
|
|
@@ -100,6 +100,20 @@
|
|
| 100 |
"eval_samples_per_second": 59.225,
|
| 101 |
"eval_steps_per_second": 0.936,
|
| 102 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
}
|
| 104 |
],
|
| 105 |
"logging_steps": 750,
|
|
@@ -107,7 +121,7 @@
|
|
| 107 |
"num_input_tokens_seen": 0,
|
| 108 |
"num_train_epochs": 50,
|
| 109 |
"save_steps": 750,
|
| 110 |
-
"total_flos":
|
| 111 |
"train_batch_size": 16,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.558716893196106,
|
| 3 |
+
"best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-4500",
|
| 4 |
+
"epoch": 7.073425395756147,
|
| 5 |
"eval_steps": 750,
|
| 6 |
+
"global_step": 5250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 100 |
"eval_samples_per_second": 59.225,
|
| 101 |
"eval_steps_per_second": 0.936,
|
| 102 |
"step": 4500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.07,
|
| 106 |
+
"learning_rate": 4.392587601078167e-05,
|
| 107 |
+
"loss": 1.2897,
|
| 108 |
+
"step": 5250
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.07,
|
| 112 |
+
"eval_loss": 1.5603703260421753,
|
| 113 |
+
"eval_runtime": 84.4569,
|
| 114 |
+
"eval_samples_per_second": 59.202,
|
| 115 |
+
"eval_steps_per_second": 0.935,
|
| 116 |
+
"step": 5250
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"logging_steps": 750,
|
|
|
|
| 121 |
"num_input_tokens_seen": 0,
|
| 122 |
"num_train_epochs": 50,
|
| 123 |
"save_steps": 750,
|
| 124 |
+
"total_flos": 2.2722169423896576e+17,
|
| 125 |
"train_batch_size": 16,
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|