Training in progress, epoch 1, checkpoint

checkpoint-43/README.md

@@ -35,30 +35,6 @@ widget:
   - knicers
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy
-model-index:
-- name: SentenceTransformer
-  results:
-  - task:
-      type: triplet
-      name: Triplet
-    dataset:
-      name: Unknown
-      type: unknown
-    metrics:
-    - type: cosine_accuracy
-      value: 0.9632667899131775
-      name: Cosine Accuracy
-    - type: cosine_accuracy
-      value: 0.9632217288017273
-      name: Cosine Accuracy
-    - type: cosine_accuracy
-      value: 0.9632217288017273
-      name: Cosine Accuracy
-    - type: cosine_accuracy
-      value: 0.9583539962768555
-      name: Cosine Accuracy
 ---
 
 # SentenceTransformer
@@ -122,9 +98,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8887, 0.2941],
-#         [0.8887, 1.0000, 0.3008],
-#         [0.2941, 0.3008, 1.0000]])
+# tensor([[1.0000, 0.8997, 0.4344],
+#         [0.8997, 1.0000, 0.4352],
+#         [0.4344, 0.4352, 1.0000]])
 ```
 
 <!--
@@ -151,42 +127,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Triplet
-
-* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| **cosine_accuracy** | **0.9633** |
-
-#### Triplet
-
-* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| **cosine_accuracy** | **0.9632** |
-
-#### Triplet
-
-* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| **cosine_accuracy** | **0.9632** |
-
-#### Triplet
-
-* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
-
-| Metric              | Value      |
-|:--------------------|:-----------|
-| **cosine_accuracy** | **0.9584** |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -234,7 +174,7 @@ You can finetune this model on your own dataset.
 - `per_device_eval_batch_size`: 16
 - `learning_rate`: 2e-05
 - `weight_decay`: 0.001
-- `num_train_epochs`: 5
+- `num_train_epochs`: 2
 - `warmup_ratio`: 0.2
 - `fp16`: True
 - `dataloader_num_workers`: 2
@@ -265,7 +205,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 5
+- `num_train_epochs`: 2
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -369,22 +309,10 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | cosine_accuracy |
-|:------:|:----:|:-------------:|:---------------:|
-| -1     | -1   | -             | 0.9633          |
-| 0.0233 | 1    | 2.5914        | -               |
-| 1.0    | 43   | 2.1651        | -               |
-| 2.0    | 86   | 1.6946        | -               |
-| -1     | -1   | -             | 0.9632          |
-| 0.0233 | 1    | 1.4613        | -               |
-| 1.0    | 43   | 1.3255        | -               |
-| 2.0    | 86   | 1.2934        | -               |
-| 3.0    | 129  | 1.1581        | -               |
-| 4.0    | 172  | 1.013         | -               |
-| 5.0    | 215  | 0.9318        | -               |
-| -1     | -1   | -             | 0.9584          |
-| 0.0233 | 1    | 0.6549        | -               |
-| 1.0    | 43   | 0.5541        | -               |
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0233 | 1    | 2.5914        |
+| 1.0    | 43   | 2.3934        |
 
 
 ### Framework Versions

checkpoint-43/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc07c00b7a4447a056133d8bcad4c913971857b920188d8c0a059fe226503a2
+oid sha256:bc37eec69b2ff11f042f540df2c67334dcbc3b1136928fbe97bd822b81badf28
 size 90864192

checkpoint-43/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db4228de4b77bb34074d24de28374c3060b359640261bc2053d802dd81d512b
+oid sha256:3bed2afeb4b6a842a6c8b06260b74d5bd41cfa690e77358d4dc50fbeff4bc465
 size 14209646

checkpoint-43/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe66d9c48caaf103c6eeb9eb51341b219fe1a8cac3b4d1a48ce587e04c0699f
+oid sha256:723244b8e9c288764a8b72007263cf06ef75abeadb3c5daada39327731a5ffea
 size 14244

checkpoint-43/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d61092ff010a05362fe1a4816145f21b91114be3d4098ad57b56c41d4f257556
+oid sha256:5045d897384bef211b0f01e8d5a118eae6b0f330b3b62e2565fa163b64c42378
 size 1064

checkpoint-43/trainer_state.json

@@ -11,23 +11,23 @@
   "log_history": [
     {
       "epoch": 0.023255813953488372,
-      "grad_norm": 4.422857761383057,
+      "grad_norm": 7.708588600158691,
       "learning_rate": 0.0,
-      "loss": 0.6549,
+      "loss": 2.5914,
       "step": 1
     },
     {
       "epoch": 1.0,
-      "grad_norm": 4.249887943267822,
-      "learning_rate": 1.9534883720930235e-05,
-      "loss": 0.5541,
+      "grad_norm": 9.752615928649902,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 2.3934,
       "step": 43
     }
   ],
   "logging_steps": 500,
-  "max_steps": 215,
+  "max_steps": 86,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-43/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79fd1a09c159d9daeaec1ccacbfdca2f117618b32bd218578e14582e7989e06
+oid sha256:15c0d63a0b1bb7c444aeeaf05781c73b12d94a5a1226d7b5edbdf4844380ee4d
 size 5752