Training in progress, epoch 2, checkpoint

last-checkpoint/README.md

@@ -51,7 +51,7 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value: 0.9113098382949829
+      value: 0.9241451621055603
       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, 0.8445, 0.5412],
-#         [0.8445, 1.0000, 0.5371],
-#         [0.5412, 0.5371, 1.0000]])
+# tensor([[1.0000, 0.7980, 0.5008],
+#         [0.7980, 1.0000, 0.4856],
+#         [0.5008, 0.4856, 1.0000]])
 ```
 
 <!--
@@ -155,7 +155,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9113** |
+| **cosine_accuracy** | **0.9241** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -369,6 +369,7 @@ You can finetune this model on your own dataset.
 | -1     | -1   | -             | -               | 0.8861          |
 | 0.0009 | 1    | 5.8495        | -               | -               |
 | 1.0    | 1139 | 3.0136        | 0.8482          | 0.9113          |
+| 2.0    | 2278 | 2.2096        | 0.7465          | 0.9241          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7647510279a6634879e6b55706fb861bc21e2953feb250a0d0fe9dcb4405c554
+oid sha256:e2e39231c7d8067da68842fefd4abad2ff8b91970af67955ad9c5f19ccf161a8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987844294c28ee0539e0adf659f930ee1318c979a2e7df65fb868d0274e75d09
+oid sha256:25fc21c2982d17aa3f6fc707f27442f5d1e5edf6276f4ebcbbe1fc1d17a98a9d
 size 180607738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5b5e9607de6158a9e54de49221c057530479aca25b6dae8b9647bbe54b8f04
+oid sha256:e2bf362531f74a3fe6ba5f06065875963cf9872e2a6a7835093b5dc7a57b8290
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0cfb78adf6294edf5c4469e8f3eb9f77e5858581e641801cd40503d57996ac
+oid sha256:3c4c7b163f9ecd5aa5916a8a707d0281dceeb0bb3b46ace886ee05988e38d2f2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e474f23cddf7cabca547283530eac1096bae85bff79679315eb2ba8a27b7e248
+oid sha256:6a0cbb301e0d0f2e8f6962d0b550760545cc3333a5fead2dc22aebe3963c95d2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 1139,
+  "global_step": 2278,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,22 @@
       "eval_samples_per_second": 274.608,
       "eval_steps_per_second": 1.098,
       "step": 1139
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.863326072692871,
+      "learning_rate": 2.5010969723562967e-05,
+      "loss": 2.2096,
+      "step": 2278
+    },
+    {
+      "epoch": 2.0,
+      "eval_cosine_accuracy": 0.9241451621055603,
+      "eval_loss": 0.7464810013771057,
+      "eval_runtime": 34.2459,
+      "eval_samples_per_second": 277.551,
+      "eval_steps_per_second": 1.11,
+      "step": 2278
     }
   ],
   "logging_steps": 500,