Training in progress, epoch 5, checkpoint

last-checkpoint/README.md

@@ -50,7 +50,7 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value: 0.9330878257751465
+      value: 0.9403471946716309
       name: Cosine Accuracy
 ---
 
@@ -115,9 +115,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.7646, 0.3896],
-#         [0.7646, 1.0000, 0.3910],
-#         [0.3896, 0.3910, 1.0000]])
+# tensor([[1.0000, 0.7730, 0.3475],
+#         [0.7730, 1.0000, 0.3615],
+#         [0.3475, 0.3615, 1.0000]])
 ```
 
 <!--
@@ -154,7 +154,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9331** |
+| **cosine_accuracy** | **0.9403** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -367,6 +367,7 @@ You can finetune this model on your own dataset.
 | Epoch | Step | Training Loss | Validation Loss | cosine_accuracy |
 |:-----:|:----:|:-------------:|:---------------:|:---------------:|
 | 4.0   | 4556 | 1.8731        | 0.7003          | 0.9331          |
+| 5.0   | 5695 | 1.7998        | 0.6516          | 0.9403          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2752eb8ccd6b0b27067ab743dbf88be10d7f0ec0acd07f271adac6466a8f5533
+oid sha256:0de1341106721af21f3461d17d84cdb01ceb68a29d60797b692a6ebc5dc4e341
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1aba1b25c91aca84ea8033a997c1f341126a19d27ece980f574b412e4f2590
+oid sha256:26dc20ccee5d8582c5a24824c2fb2a1920ffc8f0ab2af82dfff498ca8bb564ff
 size 180607738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a52c27da178d4afa8ec10888c749f1ddbdcd600f8a415730f56aaf2049e7873
+oid sha256:beed0add748b6ee78ffebe07b792579e5e36c3c5d677ec383f7827475f04c142
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e15eeadf456bba5e7d820c26dd489bf5b9eaafa907595755c9e54b984e4c99
+oid sha256:fef61799cc6177ce1e11499ec8922bebf47a17bd7d75a93d81bd7660fe280058
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3090648633fa78302c01f4e8a9a19ea7264f91a0a6f0c04a8378cf412f6c472b
+oid sha256:670b99a833a518dcb9e5a00953048f2e16a266aa8b49cc6c2d2666037559f3a8
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 4556,
+  "global_step": 5695,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,22 @@
       "eval_samples_per_second": 281.308,
       "eval_steps_per_second": 1.125,
       "step": 4556
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.708077430725098,
+      "learning_rate": 2.1944261575597982e-08,
+      "loss": 1.7998,
+      "step": 5695
+    },
+    {
+      "epoch": 5.0,
+      "eval_cosine_accuracy": 0.9403471946716309,
+      "eval_loss": 0.6516265273094177,
+      "eval_runtime": 33.9685,
+      "eval_samples_per_second": 279.818,
+      "eval_steps_per_second": 1.119,
+      "step": 5695
     }
   ],
   "logging_steps": 500,
@@ -93,7 +109,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }