Training in progress, step 1400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c09a5e85744071f43b660f276c30dd0c78a002e829d09339df6553d68e5e9c
+oid sha256:14549a8f2b505a8545ac674725066f9c305d15592336942bb065ad4f6ddeb306
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bce4267c7916e7b1d39e730977890918f472a20904f7cdb5c6470b3bb959efc
+oid sha256:0952aa81b7cdd3daf666c37d0854e5bff5e7a14e28b4874444f7772caeb46f9d
 size 9437272

last-checkpoint/README.md

@@ -450,7 +450,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6289, -0.0545,  0.2478]])
+# tensor([[ 0.6231, -0.0744,  0.1279]])
 ```
 
 <!--
@@ -711,6 +711,10 @@ You can finetune this model on your own dataset.
 | 0.3640 | 1100 | 0.091         |
 | 0.3805 | 1150 | 0.0802        |
 | 0.3971 | 1200 | 0.0824        |
+| 0.4136 | 1250 | 0.0845        |
+| 0.4302 | 1300 | 0.09          |
+| 0.4467 | 1350 | 0.0866        |
+| 0.4633 | 1400 | 0.0826        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9d8f01d2057279be1dd562ae68b04fc16b9056d28e910d54d2259bf7168206
+oid sha256:477457ae6906b9786bffa8dd6309187edd28e664410a059cfffacf1f2cae3bc6
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:763bdcee7c6c388f0295a0946aba7ea97cd1965328c61b7d56cab32345452a48
+oid sha256:6fcb82c0030f2e69a729cae162131808daef058010082ee7c6a1cdc5a1109b47
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53cf553f6434449959e590b32ad22ac0c6e07ffae962a4164d31ea3a75d345e
+oid sha256:3fcfe456f41c489958b10f637ef851405e803e7363ed9925c3152e6d7cebd14a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781bdd0549418e8b91230f3cd2918472966507e472c42f0916b387b617b2e59a
+oid sha256:1807d5c010828dc5af6863500632317772ab24748d2f2f3dc9b74b307531f182
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3970880211780278,
+  "epoch": 0.4632693580410324,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,6 +176,34 @@
       "learning_rate": 1.3409341669731519e-05,
       "loss": 0.0824,
       "step": 1200
+    },
+    {
+      "epoch": 0.41363335539377893,
+      "grad_norm": 2.9681406021118164,
+      "learning_rate": 1.3041559396837074e-05,
+      "loss": 0.0845,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4301786896095301,
+      "grad_norm": 6.426875591278076,
+      "learning_rate": 1.2673777123942627e-05,
+      "loss": 0.09,
+      "step": 1300
+    },
+    {
+      "epoch": 0.44672402382528126,
+      "grad_norm": 8.284296035766602,
+      "learning_rate": 1.2305994851048179e-05,
+      "loss": 0.0866,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4632693580410324,
+      "grad_norm": 5.250367164611816,
+      "learning_rate": 1.1938212578153734e-05,
+      "loss": 0.0826,
+      "step": 1400
     }
   ],
   "logging_steps": 50,