Training in progress, epoch 6, checkpoint

last-checkpoint/README.md

@@ -50,7 +50,7 @@ model-index:
       type: unknown
     metrics:
     - type: cosine_accuracy
-      value: 0.9435034394264221
+      value: 0.945607602596283
       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, 0.6910, 0.3222],
-#         [0.6910, 1.0000, 0.3099],
-#         [0.3222, 0.3099, 1.0000]])
+# tensor([[1.0000, 0.7013, 0.2786],
+#         [0.7013, 1.0000, 0.2947],
+#         [0.2786, 0.2947, 1.0000]])
 ```
 
 <!--
@@ -154,7 +154,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9435** |
+| **cosine_accuracy** | **0.9456** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -368,6 +368,7 @@ You can finetune this model on your own dataset.
 |:-----:|:-----:|:-------------:|:---------------:|:---------------:|
 | 4.0   | 9112  | 1.4316        | 0.7736          | 0.9375          |
 | 5.0   | 11390 | 1.3415        | 0.7541          | 0.9435          |
+| 6.0   | 13668 | 1.2848        | 0.7366          | 0.9456          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f3402611e3b3c3f41f95210941eb470fba6ed05452b3849a27bd4dd433f91e
+oid sha256:320486c0d72ec95abd1659c8bd328af000fee16acca976234080b60c5808f503
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76893f6607e3ebbfe6341fa0102ea836a998daa1b3f6024dda6df1ae75e07865
+oid sha256:7755d08694b0b98e9f637c1325a98df63baa0531c0b16f44df4b52258ac0dfb8
 size 180607738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37aac35e3c58c9053e71545ace22af7302bb0c360af070fa4f0ab6abc890f773
+oid sha256:5715fd5dd811d8d77c0931f527aac0675f97eb5e3128e2ac71138c0423321a1c
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd86fc34d6a0f3e0667119a9de9c78b3da8a344f393071c4b8da7ec715e0886
+oid sha256:c84fca30e11e9e228eeed287bc390c8efa222d906e82edaf51b0d6ee34d8323c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb1ca70040fe2933c9ba4528086551bb0337a289b19dabf99f736ffc96fdbab
+oid sha256:b0988d979225dbf496efcd05bde3d2241f939432abad17b4ce650c14d14df89c
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 5000,
-  "global_step": 11390,
+  "global_step": 13668,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,22 @@
       "eval_samples_per_second": 298.028,
       "eval_steps_per_second": 2.352,
       "step": 11390
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.055571556091309,
+      "learning_rate": 2.2862368541380888e-08,
+      "loss": 1.2848,
+      "step": 13668
+    },
+    {
+      "epoch": 6.0,
+      "eval_cosine_accuracy": 0.945607602596283,
+      "eval_loss": 0.7366093397140503,
+      "eval_runtime": 32.7761,
+      "eval_samples_per_second": 289.998,
+      "eval_steps_per_second": 2.288,
+      "step": 13668
     }
   ],
   "logging_steps": 5000,
@@ -77,7 +93,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }