Training in progress, step 800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89111b92371b9a2deba746060687471336a0d4cfe96973e9574079626d724c62
+oid sha256:f45d87a3222e8eb06a466ab5dfa5150775275ac497c809e075ffadc6ee21433f
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d9933e8dc3511fb603634911f867225eb29d7c8fd74a4559dd878cf05993b9
+oid sha256:b563a3aea396a4563642a218726dda67d3f6067140172e6b40ef0d94743c0bc0
 size 4718680

last-checkpoint/README.md

@@ -424,7 +424,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[0.8942, 0.0534, 0.0618]])
+# tensor([[0.9050, 0.0240, 0.0505]])
 ```
 
 <!--
@@ -645,6 +645,10 @@ You can finetune this model on your own dataset.
 | 0.4630 | 500  | 0.0966        |
 | 0.5093 | 550  | 0.0942        |
 | 0.5556 | 600  | 0.0866        |
+| 0.6019 | 650  | 0.0911        |
+| 0.6481 | 700  | 0.0872        |
+| 0.6944 | 750  | 0.087         |
+| 0.7407 | 800  | 0.0771        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9b7a8327bcd9f26fb726f7f314185b56e82623ee2d12b4d931b6652419f10a
+oid sha256:1b524fd4d0af037372baac781a7e02bde6af66075c966d2f2ae612f58d66ff03
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0511132bcec99cfb81e6cdbe3f440ab29dbefe3ec7dbb1ed13c95d382a5fb775
+oid sha256:a6c6983bf30f51cc12841bdc8966719604748c2803cd6de5d87dffadf3eb3a01
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ef9347676d52185ae368f376cf1fe5dd55cbd5ed84547d819fe30ad5c5892f
+oid sha256:4ad211f85f7952dd56f43d381e1780d6a978df68441ca57ba5688f4ef0c8d4b7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5555555555555556,
+  "epoch": 0.7407407407407407,
   "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": 2.4742798353909465e-05,
       "loss": 0.0866,
       "step": 600
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 2.59375,
+      "learning_rate": 2.2170781893004118e-05,
+      "loss": 0.0911,
+      "step": 650
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 6.625,
+      "learning_rate": 1.9598765432098768e-05,
+      "loss": 0.0872,
+      "step": 700
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.7026748971193414e-05,
+      "loss": 0.087,
+      "step": 750
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.4454732510288065e-05,
+      "loss": 0.0771,
+      "step": 800
     }
   ],
   "logging_steps": 50,