Training in progress, step 800, checkpoint

last-checkpoint/README.md

@@ -286,9 +286,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.5948, 0.0953],
-#         [0.5948, 1.0000, 0.1617],
-#         [0.0953, 0.1617, 1.0000]])
+# tensor([[1.0000, 0.5922, 0.0910],
+#         [0.5922, 1.0000, 0.1485],
+#         [0.0910, 0.1485, 1.0000]])
 ```
 
 <!--
@@ -1236,6 +1236,10 @@ You can finetune this model on your own dataset.
 | 0.0088 | 500  | 0.7402        |
 | 0.0097 | 550  | 0.8769        |
 | 0.0106 | 600  | 0.6827        |
+| 0.0115 | 650  | 0.7252        |
+| 0.0124 | 700  | 0.7701        |
+| 0.0133 | 750  | 0.7525        |
+| 0.0141 | 800  | 0.7097        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0331d85acd4fecdd2f31fd21e71c37b15d11fa5d95f1960167c2115865d268eb
+oid sha256:4edf45758f8655b39949040bb376942e3eaf9cabfbd997bdd27d281a59e48fd7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f2a519dd6cd0c172d7135799f3099fbcc09a2457a9690f71edda228c1586f6
+oid sha256:b860245e653a414010bafe2c3c8174c59f95411463e02d1f20aed248e44dc779
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2615f3b3d60e5b013a5494b0df662cc433db404a047bf2af8ab2c80fe288cfc
+oid sha256:6604fa50a947bb7a8c4e40ff3e2a5641ad506d5aa6a161b0cd0a5fa0c1d78ee8
 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:b1791894c32e6460fc9c57eab981d0af91d945f1bc12022ff9b5f30caaac5c8b
+oid sha256:8ec1539c27d7283f1e5aca2a0dde35cb977a77f34c850320b82d506a15f4bbbb
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010602392606598222,
+  "epoch": 0.014136523475464296,
   "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": 5.291519434628975e-06,
       "loss": 0.6827,
       "step": 600
+    },
+    {
+      "epoch": 0.011485925323814742,
+      "grad_norm": 2.5824739933013916,
+      "learning_rate": 5.73321554770318e-06,
+      "loss": 0.7252,
+      "step": 650
+    },
+    {
+      "epoch": 0.01236945804103126,
+      "grad_norm": 2.586138963699341,
+      "learning_rate": 6.174911660777385e-06,
+      "loss": 0.7701,
+      "step": 700
+    },
+    {
+      "epoch": 0.013252990758247778,
+      "grad_norm": 2.3450210094451904,
+      "learning_rate": 6.6166077738515904e-06,
+      "loss": 0.7525,
+      "step": 750
+    },
+    {
+      "epoch": 0.014136523475464296,
+      "grad_norm": 2.7902042865753174,
+      "learning_rate": 7.058303886925795e-06,
+      "loss": 0.7097,
+      "step": 800
     }
   ],
   "logging_steps": 50,