Training in progress, step 730, checkpoint

last-checkpoint/README.md

@@ -416,9 +416,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.4984, -0.0999],
-#         [ 0.4984,  1.0000, -0.0665],
-#         [-0.0999, -0.0665,  1.0000]])
+# tensor([[ 1.0000,  0.4872, -0.1172],
+#         [ 0.4872,  1.0000, -0.0891],
+#         [-0.1172, -0.0891,  1.0000]])
 ```
 
 <!--
@@ -664,6 +664,8 @@ You can finetune this model on your own dataset.
 | 0.6849 | 500  | 0.4035        |
 | 0.7534 | 550  | 0.4031        |
 | 0.8219 | 600  | 0.3928        |
+| 0.8904 | 650  | 0.3978        |
+| 0.9589 | 700  | 0.3825        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42737ca487f64b2ba0a490df3c1016ede96f9e04bc367ce6fcb5349782d57fd
+oid sha256:2e76a4b2fb3c0733c12ae07cd3e0f4d875be188fd8938ce2014837b99779ee54
 size 437951328

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bdd1b459b57b607629063b2fa6365026d82857ad958e3cc875f260b4feb3ed3
+oid sha256:f2f881cdd4fbadbeed0ef1305747cfe1c55dfdce013684e2a5df5cb7ba0558b5
 size 871301195

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76943be04f8b05d95c854799f3634427a1630c4299e02fd4a7cffa5a2077ccd9
+oid sha256:504f8ee025f27793137df10695026a0da0e5051f8bccc8c4973299bed48fc121
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03d30d642b0c4e8e2abbdc65933da67b7407e7d449bd380792a2bf635ff9333
+oid sha256:d33660fd2d77daa0cdfa768b8e1bfd3ff165bc08a039957c7b15665ed77b87cd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.821917808219178,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 730,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,20 @@
       "learning_rate": 9.969558599695586e-06,
       "loss": 0.3928,
       "step": 600
+    },
+    {
+      "epoch": 0.8904109589041096,
+      "grad_norm": 2.14909029006958,
+      "learning_rate": 6.1643835616438354e-06,
+      "loss": 0.3978,
+      "step": 650
+    },
+    {
+      "epoch": 0.958904109589041,
+      "grad_norm": 1.899760365486145,
+      "learning_rate": 2.3592085235920852e-06,
+      "loss": 0.3825,
+      "step": 700
     }
   ],
   "logging_steps": 50,
@@ -106,7 +120,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }