Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
|
@@ -90,7 +90,7 @@ model-index:
|
|
| 90 |
type: validation_eval
|
| 91 |
metrics:
|
| 92 |
- type: cosine_accuracy
|
| 93 |
-
value: 0.
|
| 94 |
name: Cosine Accuracy
|
| 95 |
---
|
| 96 |
|
|
@@ -192,9 +192,9 @@ You can finetune this model on your own dataset.
|
|
| 192 |
* Dataset: `validation_eval`
|
| 193 |
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 194 |
|
| 195 |
-
| Metric | Value
|
| 196 |
-
|
| 197 |
-
| **cosine_accuracy** | **0.
|
| 198 |
|
| 199 |
<!--
|
| 200 |
## Bias, Risks and Limitations
|
|
@@ -425,6 +425,7 @@ You can finetune this model on your own dataset.
|
|
| 425 |
| Epoch | Step | Training Loss | validation_eval_cosine_accuracy |
|
| 426 |
|:-----:|:----:|:-------------:|:-------------------------------:|
|
| 427 |
| 1.0 | 3676 | 8.9556 | 0.9410 |
|
|
|
|
| 428 |
|
| 429 |
|
| 430 |
### Framework Versions
|
|
|
|
| 90 |
type: validation_eval
|
| 91 |
metrics:
|
| 92 |
- type: cosine_accuracy
|
| 93 |
+
value: 0.947425127029419
|
| 94 |
name: Cosine Accuracy
|
| 95 |
---
|
| 96 |
|
|
|
|
| 192 |
* Dataset: `validation_eval`
|
| 193 |
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
|
| 194 |
|
| 195 |
+
| Metric | Value |
|
| 196 |
+
|:--------------------|:-----------|
|
| 197 |
+
| **cosine_accuracy** | **0.9474** |
|
| 198 |
|
| 199 |
<!--
|
| 200 |
## Bias, Risks and Limitations
|
|
|
|
| 425 |
| Epoch | Step | Training Loss | validation_eval_cosine_accuracy |
|
| 426 |
|:-----:|:----:|:-------------:|:-------------------------------:|
|
| 427 |
| 1.0 | 3676 | 8.9556 | 0.9410 |
|
| 428 |
+
| 2.0 | 7352 | 5.7553 | 0.9474 |
|
| 429 |
|
| 430 |
|
| 431 |
### Framework Versions
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 540801896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6751839c970ace7d1c0bba0ce8c2d5109d71bacea24d3588c26fa8ceb9e9cf46
|
| 3 |
size 540801896
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1077002315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da7395ddd9ebdb66355b7cc4c974cf7d8f714ea75778853e3624c5481e377fe
|
| 3 |
size 1077002315
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14581
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4465188dd96bf8ac7587d22be206836e02bdcf54faba9b04a9420a9f57d9b05
|
| 3 |
size 14581
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b837408a3b2fa1e18d2fa8ae5e1da4475c30d979e5f70f8d1a8fda3ce72d658
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b48d11655afbd5b52e8a8fe62dd27af1d016ec30caf42b272fca288b82036ce8
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/kaggle/working/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -23,6 +23,21 @@
|
|
| 23 |
"eval_steps_per_second": 0.0,
|
| 24 |
"eval_validation_eval_cosine_accuracy": 0.9409878849983215,
|
| 25 |
"step": 3676
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 500,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 7352,
|
| 3 |
+
"best_metric": 0.947425127029419,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/checkpoint-7352",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7352,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 23 |
"eval_steps_per_second": 0.0,
|
| 24 |
"eval_validation_eval_cosine_accuracy": 0.9409878849983215,
|
| 25 |
"step": 3676
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 17.716238021850586,
|
| 30 |
+
"learning_rate": 3.0211621605838098e-06,
|
| 31 |
+
"loss": 5.7553,
|
| 32 |
+
"step": 7352
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_runtime": 58.536,
|
| 37 |
+
"eval_samples_per_second": 0.0,
|
| 38 |
+
"eval_steps_per_second": 0.0,
|
| 39 |
+
"eval_validation_eval_cosine_accuracy": 0.947425127029419,
|
| 40 |
+
"step": 7352
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"logging_steps": 500,
|