Training in progress, step 4000, 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, 0.6042, 0.1308],
-#         [0.6042, 1.0000, 0.1578],
-#         [0.1308, 0.1578, 1.0000]])
+# tensor([[1.0000, 0.6143, 0.1287],
+#         [0.6143, 1.0000, 0.1405],
+#         [0.1287, 0.1405, 1.0000]])
 ```
 
 <!--
@@ -1300,6 +1300,10 @@ You can finetune this model on your own dataset.
 | 0.0654 | 3700 | 0.5369        |
 | 0.0663 | 3750 | 0.5014        |
 | 0.0671 | 3800 | 0.5128        |
+| 0.0680 | 3850 | 0.5345        |
+| 0.0689 | 3900 | 0.479         |
+| 0.0698 | 3950 | 0.5652        |
+| 0.0707 | 4000 | 0.5272        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897960436843d5c9a1c425e6db1c1503aa06a63a7f2fb8c908e144bba151febf
+oid sha256:3afef13a9530b1d37e75e240905ad652534486251038ac7625bca52154bc22ae
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060a174b917d9184a5b50a8726fe66ae63586ccc23d2305493a5338da2826e75
+oid sha256:222633b12bed53261169053ce24d1f241742034e7e3fa10de526bc970a0f195e
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9972509440ac3b65de1bed64e2e65c53cdb22f4a6ef4fd3051c31579884fa084
+oid sha256:439c03324d2ae716408c6813f980622f620c92edbb619c9605e53bbfeb87c5d4
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b831e7986e0350928fba31ac9273aa336c1c6fa67a9d2d87f294d90bb3e919fc
+oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a83b707965eabacd6bc32e8357a0712dd4d97c0978b2ff329d3ecefa2343faa
+oid sha256:8a11c3e9771776b1c85d065a9955c717c9aa11482aedb6b822da5fe47cbf5c1f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06714848650845541,
+  "epoch": 0.07068261737732148,
   "eval_steps": 500,
-  "global_step": 3800,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -540,6 +540,34 @@
       "learning_rate": 3.356007067137809e-05,
       "loss": 0.5128,
       "step": 3800
+    },
+    {
+      "epoch": 0.06803201922567192,
+      "grad_norm": 2.095426559448242,
+      "learning_rate": 3.40017667844523e-05,
+      "loss": 0.5345,
+      "step": 3850
+    },
+    {
+      "epoch": 0.06891555194288844,
+      "grad_norm": 2.1965081691741943,
+      "learning_rate": 3.4443462897526505e-05,
+      "loss": 0.479,
+      "step": 3900
+    },
+    {
+      "epoch": 0.06979908466010497,
+      "grad_norm": 2.1722958087921143,
+      "learning_rate": 3.488515901060071e-05,
+      "loss": 0.5652,
+      "step": 3950
+    },
+    {
+      "epoch": 0.07068261737732148,
+      "grad_norm": 2.7183449268341064,
+      "learning_rate": 3.5326855123674914e-05,
+      "loss": 0.5272,
+      "step": 4000
     }
   ],
   "logging_steps": 50,