Training in progress, epoch 3, checkpoint

last-checkpoint/README.md

@@ -51,7 +51,7 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value: 0.9241451621055603
+      value: 0.9337190985679626
       name: Cosine Accuracy
 ---
 
@@ -116,9 +116,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.7980, 0.5008],
-#         [0.7980, 1.0000, 0.4856],
-#         [0.5008, 0.4856, 1.0000]])
+# tensor([[1.0000, 0.7955, 0.3891],
+#         [0.7955, 1.0000, 0.4118],
+#         [0.3891, 0.4118, 1.0000]])
 ```
 
 <!--
@@ -155,7 +155,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9241** |
+| **cosine_accuracy** | **0.9337** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -370,6 +370,7 @@ You can finetune this model on your own dataset.
 | 0.0009 | 1    | 5.8495        | -               | -               |
 | 1.0    | 1139 | 3.0136        | 0.8482          | 0.9113          |
 | 2.0    | 2278 | 2.2096        | 0.7465          | 0.9241          |
+| 3.0    | 3417 | 1.966         | 0.6980          | 0.9337          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e39231c7d8067da68842fefd4abad2ff8b91970af67955ad9c5f19ccf161a8
+oid sha256:5e94dfce1c7a8097a517cdc7e18867845b8cf07b8debbb4c7f86dacfe33f0ad0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25fc21c2982d17aa3f6fc707f27442f5d1e5edf6276f4ebcbbe1fc1d17a98a9d
+oid sha256:b6e5d3026902eda477b64ceaeccd2e204dd15555061fe0a6a4f2baabb9021e9a
 size 180607738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2bf362531f74a3fe6ba5f06065875963cf9872e2a6a7835093b5dc7a57b8290
+oid sha256:0bd7c67a9db13a1d1d92181014a6e67813669ee1bbe4529e719f8b5106877aef
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4c7b163f9ecd5aa5916a8a707d0281dceeb0bb3b46ace886ee05988e38d2f2
+oid sha256:67a6b234e82620ea3da8e2a9835166f15a378f21f79ddb4af11eb7a0b287008f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0cbb301e0d0f2e8f6962d0b550760545cc3333a5fead2dc22aebe3963c95d2
+oid sha256:ecbc50cd28f5eb9a427ea169ea55add1d74447c6784544c0cff4a17d832f4ec4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2278,
+  "global_step": 3417,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -47,6 +47,22 @@
       "eval_samples_per_second": 277.551,
       "eval_steps_per_second": 1.11,
       "step": 2278
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.734906196594238,
+      "learning_rate": 2.1939447125932427e-08,
+      "loss": 1.966,
+      "step": 3417
+    },
+    {
+      "epoch": 3.0,
+      "eval_cosine_accuracy": 0.9337190985679626,
+      "eval_loss": 0.6979679465293884,
+      "eval_runtime": 34.569,
+      "eval_samples_per_second": 274.957,
+      "eval_steps_per_second": 1.099,
+      "step": 3417
     }
   ],
   "logging_steps": 500,
@@ -61,7 +77,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }