Training in progress, step 600, checkpoint

last-checkpoint/README.md

@@ -418,9 +418,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8039, 0.0072],
-#         [0.8039, 1.0000, 0.0365],
-#         [0.0072, 0.0365, 1.0000]])
+# tensor([[1.0000, 0.8255, 0.0183],
+#         [0.8255, 1.0000, 0.0580],
+#         [0.0183, 0.0580, 1.0000]])
 ```
 
 <!--
@@ -633,6 +633,10 @@ You can finetune this model on your own dataset.
 | 0.2778 | 300  | 0.2587        |
 | 0.3241 | 350  | 0.2629        |
 | 0.3704 | 400  | 0.2518        |
+| 0.4167 | 450  | 0.2492        |
+| 0.4630 | 500  | 0.228         |
+| 0.5093 | 550  | 0.2267        |
+| 0.5556 | 600  | 0.2222        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ef8ec0a1171721c804c180346ec3c917c952ed0da36455a504c5863c6c9788
+oid sha256:980f0d4b38375feadd3e6c8d2e4ff0c0c1701d415db84cbfeab147a2b4b273b3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9aea5acedf0733c92a9daea99cb257662f8f5ae5961ec2df047b6e0c75cc91
+oid sha256:c1e63d9b09c1f721f29df757b14a75b61662a1ffe89fccf48e193f7627afbabf
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c19b67f89acc145936e1b518bb5813ff7a56d806e790b9924b0c10aabb6eba24
+oid sha256:916c146daa973d7fe7286d497c85a56ed924f1e756ec82fccdaa57c8c5694c8b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf50a8da9b77d1d667aa2be5f7411c48d830b5ed090e0ff1a8209df626c404c4
+oid sha256:e5ef9347676d52185ae368f376cf1fe5dd55cbd5ed84547d819fe30ad5c5892f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37037037037037035,
+  "epoch": 0.5555555555555556,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 3.503086419753087e-05,
       "loss": 0.2518,
       "step": 400
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.3996431827545166,
+      "learning_rate": 3.245884773662551e-05,
+      "loss": 0.2492,
+      "step": 450
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 1.3424209356307983,
+      "learning_rate": 2.9886831275720166e-05,
+      "loss": 0.228,
+      "step": 500
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 1.3468494415283203,
+      "learning_rate": 2.7314814814814816e-05,
+      "loss": 0.2267,
+      "step": 550
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.1546319723129272,
+      "learning_rate": 2.4742798353909465e-05,
+      "loss": 0.2222,
+      "step": 600
     }
   ],
   "logging_steps": 50,