Training in progress, step 1968, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400e4f138cc26c5d165ba04ccda48bd7296f46c05e26190bd789555593817a22
+oid sha256:a7d0ba7d53b54f49d42205eab3183bb64577617b8fbaf646c39733ce0fdbe0a7
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec6c2be4f316baca2bdc5689a13674de1c91858439ed131ad1507b0ae68a407
+oid sha256:7bed249eafa02c0ffaa4d2c61796ab36bd14abcadaa9ffcbdf4355bd2979ebf3
 size 4718680

last-checkpoint/README.md

@@ -472,7 +472,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.7067, -0.0843, -0.0921]])
+# tensor([[ 0.7065, -0.0847, -0.0928]])
 ```
 
 <!--
@@ -717,6 +717,9 @@ You can finetune this model on your own dataset.
 | 0.8638 | 1700 | 0.0878        |
 | 0.8892 | 1750 | 0.0822        |
 | 0.9146 | 1800 | 0.0792        |
+| 0.9400 | 1850 | 0.0859        |
+| 0.9654 | 1900 | 0.0826        |
+| 0.9909 | 1950 | 0.0819        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44e01cf741acb803d6e04527da1f664016682833461b366d42997159b0416e6
+oid sha256:8f52db89dd8b2f6dd994531266e62a29c916343fbd1ce12626dbf75c58289bce
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184cdfd28ea4214abe2fcbc868f15877077a7bc59cc6a0683bb50c1246efdbef
+oid sha256:d8673d1f43b3aa29d6b7dd40cc4276731cd9c31b6d3cc6cd806cb55d687a2f57
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec29327b2c793ef05a01c6bae10cd1cf49d3fd34bb421765aad2d8f09bc372c0
+oid sha256:04e88cb3830f9a985bd7f6d2cca6f569425345d84761a9b2c6e58dd048cd58e3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9146341463414634,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1800,
+  "global_step": 1968,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -260,6 +260,27 @@
       "learning_rate": 4.771315640880859e-06,
       "loss": 0.0792,
       "step": 1800
+    },
+    {
+      "epoch": 0.9400406504065041,
+      "grad_norm": 2.984375,
+      "learning_rate": 3.3596837944664035e-06,
+      "loss": 0.0859,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9654471544715447,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.948051948051948e-06,
+      "loss": 0.0826,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9908536585365854,
+      "grad_norm": 2.859375,
+      "learning_rate": 5.364201016374929e-07,
+      "loss": 0.0819,
+      "step": 1950
     }
   ],
   "logging_steps": 50,
@@ -274,7 +295,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }