Training in progress, step 3800, 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, 0.6194, 0.1435],
-#         [0.6194, 1.0000, 0.1726],
-#         [0.1435, 0.1726, 1.0000]])
+# tensor([[1.0000, 0.6042, 0.1308],
+#         [0.6042, 1.0000, 0.1578],
+#         [0.1308, 0.1578, 1.0000]])
 ```
 
 <!--
@@ -1296,6 +1296,10 @@ You can finetune this model on your own dataset.
 | 0.0618 | 3500 | 0.5072        |
 | 0.0627 | 3550 | 0.5639        |
 | 0.0636 | 3600 | 0.4729        |
+| 0.0645 | 3650 | 0.6047        |
+| 0.0654 | 3700 | 0.5369        |
+| 0.0663 | 3750 | 0.5014        |
+| 0.0671 | 3800 | 0.5128        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca20a406e292e76470b215099de7fd529457d8cb2dcb51edb2d8cc0c54a7d84
+oid sha256:897960436843d5c9a1c425e6db1c1503aa06a63a7f2fb8c908e144bba151febf
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893256695d57723f84eb532bbc6684a2823d6b7a86ce840bdff5d57803b4ee3d
+oid sha256:060a174b917d9184a5b50a8726fe66ae63586ccc23d2305493a5338da2826e75
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338476a870fd77d6e2a600e13b412756ba4bcad01f47d9e17c52ffe1b9d95af9
+oid sha256:9972509440ac3b65de1bed64e2e65c53cdb22f4a6ef4fd3051c31579884fa084
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7788c7cc60bd991bb584c9a8631c7010707cb818c6f2829b9625a72fb3ec1a89
+oid sha256:b831e7986e0350928fba31ac9273aa336c1c6fa67a9d2d87f294d90bb3e919fc
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78830fc2cf66f7695494cde0cc4ab780d875d3f710f7c385f24ad0580d00b60e
+oid sha256:4a83b707965eabacd6bc32e8357a0712dd4d97c0978b2ff329d3ecefa2343faa
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06361435563958934,
+  "epoch": 0.06714848650845541,
   "eval_steps": 500,
-  "global_step": 3600,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -512,6 +512,34 @@
       "learning_rate": 3.179328621908128e-05,
       "loss": 0.4729,
       "step": 3600
+    },
+    {
+      "epoch": 0.06449788835680585,
+      "grad_norm": 2.134610414505005,
+      "learning_rate": 3.2234982332155476e-05,
+      "loss": 0.6047,
+      "step": 3650
+    },
+    {
+      "epoch": 0.06538142107402237,
+      "grad_norm": 1.8596552610397339,
+      "learning_rate": 3.267667844522969e-05,
+      "loss": 0.5369,
+      "step": 3700
+    },
+    {
+      "epoch": 0.0662649537912389,
+      "grad_norm": 2.5137698650360107,
+      "learning_rate": 3.311837455830389e-05,
+      "loss": 0.5014,
+      "step": 3750
+    },
+    {
+      "epoch": 0.06714848650845541,
+      "grad_norm": 2.8211522102355957,
+      "learning_rate": 3.356007067137809e-05,
+      "loss": 0.5128,
+      "step": 3800
     }
   ],
   "logging_steps": 50,