Training in progress, step 4200, 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, 0.6143, 0.1287],
-#         [0.6143, 1.0000, 0.1405],
-#         [0.1287, 0.1405, 1.0000]])
+# tensor([[1.0000, 0.6197, 0.0899],
+#         [0.6197, 1.0000, 0.1018],
+#         [0.0899, 0.1018, 1.0000]])
 ```
 
 <!--
@@ -1304,6 +1304,10 @@ You can finetune this model on your own dataset.
 | 0.0689 | 3900 | 0.479         |
 | 0.0698 | 3950 | 0.5652        |
 | 0.0707 | 4000 | 0.5272        |
+| 0.0716 | 4050 | 0.4904        |
+| 0.0724 | 4100 | 0.4755        |
+| 0.0733 | 4150 | 0.4897        |
+| 0.0742 | 4200 | 0.4679        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afef13a9530b1d37e75e240905ad652534486251038ac7625bca52154bc22ae
+oid sha256:c6edbab9b964e9ca7b0bab9e7c4f66e7e7bc86ba965571aa4d27edf17e6ee9ae
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222633b12bed53261169053ce24d1f241742034e7e3fa10de526bc970a0f195e
+oid sha256:49ef51099777f465890db4e01e4666b0ea051323d10a6459c3da580d7d661a3c
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:439c03324d2ae716408c6813f980622f620c92edbb619c9605e53bbfeb87c5d4
+oid sha256:f6b1fbe40a2f2e085bd8df80fdc83132b78dd273708a845bf0221a8bf75df21c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
+oid sha256:0563f0c122c10b3bb9fb8ef7a029cf4fe15b88c3307945ff50155d3485ee7edd
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a11c3e9771776b1c85d065a9955c717c9aa11482aedb6b822da5fe47cbf5c1f
+oid sha256:77c82cc641eba2e585eb912c19a748e90231d19cc7c5365b3984d32e47cc490a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07068261737732148,
+  "epoch": 0.07421674824618756,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -568,6 +568,34 @@
       "learning_rate": 3.5326855123674914e-05,
       "loss": 0.5272,
       "step": 4000
+    },
+    {
+      "epoch": 0.071566150094538,
+      "grad_norm": 2.356076717376709,
+      "learning_rate": 3.576855123674912e-05,
+      "loss": 0.4904,
+      "step": 4050
+    },
+    {
+      "epoch": 0.07244968281175453,
+      "grad_norm": 1.7549006938934326,
+      "learning_rate": 3.621024734982332e-05,
+      "loss": 0.4755,
+      "step": 4100
+    },
+    {
+      "epoch": 0.07333321552897104,
+      "grad_norm": 2.0377912521362305,
+      "learning_rate": 3.665194346289753e-05,
+      "loss": 0.4897,
+      "step": 4150
+    },
+    {
+      "epoch": 0.07421674824618756,
+      "grad_norm": 2.4711716175079346,
+      "learning_rate": 3.709363957597173e-05,
+      "loss": 0.4679,
+      "step": 4200
     }
   ],
   "logging_steps": 50,