Training in progress, step 800, 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, 0.8255, 0.0183],
-#         [0.8255, 1.0000, 0.0580],
-#         [0.0183, 0.0580, 1.0000]])
+# tensor([[    1.0000,     0.8238,     0.0007],
+#         [    0.8238,     1.0000,     0.0379],
+#         [    0.0007,     0.0379,     1.0000]])
 ```
 
 <!--
@@ -637,6 +637,10 @@ You can finetune this model on your own dataset.
 | 0.4630 | 500  | 0.228         |
 | 0.5093 | 550  | 0.2267        |
 | 0.5556 | 600  | 0.2222        |
+| 0.6019 | 650  | 0.2283        |
+| 0.6481 | 700  | 0.2233        |
+| 0.6944 | 750  | 0.2239        |
+| 0.7407 | 800  | 0.2107        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980f0d4b38375feadd3e6c8d2e4ff0c0c1701d415db84cbfeab147a2b4b273b3
+oid sha256:f56ae000ad3df8b9ddbc58f562eabbf1eb1c4635d3298efe2688ce7e1f3939c5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e63d9b09c1f721f29df757b14a75b61662a1ffe89fccf48e193f7627afbabf
+oid sha256:9fbb6df4b0c6b1eeabf081b1e19d2abd93a909d4231185afdbaccb35c459fc1c
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916c146daa973d7fe7286d497c85a56ed924f1e756ec82fccdaa57c8c5694c8b
+oid sha256:28b66082d265e60bf5570bafb6654a76e495fb2c00d97a2e2d702d4cef23c098
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
+oid sha256:6fef122931c86c2d2736773be787da21ac6460d41580735381e953556fb410be
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ef9347676d52185ae368f376cf1fe5dd55cbd5ed84547d819fe30ad5c5892f
+oid sha256:4ad211f85f7952dd56f43d381e1780d6a978df68441ca57ba5688f4ef0c8d4b7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5555555555555556,
+  "epoch": 0.7407407407407407,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 2.4742798353909465e-05,
       "loss": 0.2222,
       "step": 600
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 1.1849355697631836,
+      "learning_rate": 2.2170781893004118e-05,
+      "loss": 0.2283,
+      "step": 650
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 1.095701813697815,
+      "learning_rate": 1.9598765432098768e-05,
+      "loss": 0.2233,
+      "step": 700
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 1.258505940437317,
+      "learning_rate": 1.7026748971193414e-05,
+      "loss": 0.2239,
+      "step": 750
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.29531729221344,
+      "learning_rate": 1.4454732510288065e-05,
+      "loss": 0.2107,
+      "step": 800
     }
   ],
   "logging_steps": 50,