Commit
·
a981095
1
Parent(s):
456e62e
End of training
Browse files- README.md +5 -5
- logs/events.out.tfevents.1704595715.d90d7534d98a.27.0 +2 -2
- model.safetensors +1 -1
- trainer_state.json +19 -5
README.md
CHANGED
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- eval_loss: 1.
|
19 |
-
- eval_runtime: 84.
|
20 |
-
- eval_samples_per_second: 59.
|
21 |
- eval_steps_per_second: 0.938
|
22 |
-
- epoch:
|
23 |
-
- step:
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 1.5282
|
19 |
+
- eval_runtime: 84.2371
|
20 |
+
- eval_samples_per_second: 59.356
|
21 |
- eval_steps_per_second: 0.938
|
22 |
+
- epoch: 6.06
|
23 |
+
- step: 4500
|
24 |
|
25 |
## Model description
|
26 |
|
logs/events.out.tfevents.1704595715.d90d7534d98a.27.0
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:f9e5da318c8357d485ab966bddd11dfa836bee503cf9e23ca4e623074805d1fb
|
3 |
+
size 1719406
|
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:ae13ecd9fc839ef94736671faab0dcc0acd342d63ac53d36f3f434917fb712b3
|
3 |
size 535667604
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "ner-bert-ingredients/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,
|
@@ -77,6 +77,20 @@
|
|
77 |
"eval_samples_per_second": 59.391,
|
78 |
"eval_steps_per_second": 0.938,
|
79 |
"step": 3750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 750,
|
@@ -84,7 +98,7 @@
|
|
84 |
"num_input_tokens_seen": 0,
|
85 |
"num_train_epochs": 100,
|
86 |
"save_steps": 750,
|
87 |
-
"total_flos": 1.
|
88 |
"train_batch_size": 16,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.6346299648284912,
|
3 |
+
"best_model_checkpoint": "ner-bert-ingredients/checkpoint-3750",
|
4 |
+
"epoch": 6.062647356012126,
|
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,
|
|
|
77 |
"eval_samples_per_second": 59.391,
|
78 |
"eval_steps_per_second": 0.938,
|
79 |
"step": 3750
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 6.06,
|
83 |
+
"learning_rate": 4.696900269541779e-05,
|
84 |
+
"loss": 1.437,
|
85 |
+
"step": 4500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 6.06,
|
89 |
+
"eval_loss": 1.5281634330749512,
|
90 |
+
"eval_runtime": 84.2371,
|
91 |
+
"eval_samples_per_second": 59.356,
|
92 |
+
"eval_steps_per_second": 0.938,
|
93 |
+
"step": 4500
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 750,
|
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 100,
|
100 |
"save_steps": 750,
|
101 |
+
"total_flos": 1.9475913345048576e+17,
|
102 |
"train_batch_size": 16,
|
103 |
"trial_name": null,
|
104 |
"trial_params": null
|