Training in progress, step 400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e06277ca8787b7fa33c7a991a49e7c44cedc64537c9a587e3eabe4480d98101
+oid sha256:50c88013d65aeba6cd0320a8bdf542df82418400820ba7cc58b9536963f8a5f6
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1747a1bbfdac934f7ee3e281dffa826558868f822e91fdd1f85e39c452033a
+oid sha256:841fe46d69b0008634a14be512e1e411ce4d65589bfc375f8ecb345f2e8d7f12
 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([[0.8959, 0.0632, 0.0102]])
+# tensor([[0.8570, 0.0561, 0.0702]])
 ```
 
 <!--
@@ -637,6 +637,10 @@ You can finetune this model on your own dataset.
 | 0.0926 | 100  | 0.1353        |
 | 0.1389 | 150  | 0.1541        |
 | 0.1852 | 200  | 0.1499        |
+| 0.2315 | 250  | 0.1335        |
+| 0.2778 | 300  | 0.1225        |
+| 0.3241 | 350  | 0.1248        |
+| 0.3704 | 400  | 0.1141        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abac25e1e6fdf3255533a12e513ba6078edbe7d810a3fa975b6d4d0639fab536
+oid sha256:187b1b756dac2e7a25d7535399df83edcdbe3e7c67adf143f1cc5c2d8d8dd510
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6ae0591084794587e796774ea539c6d9d1c58565ec4d0bf461ec38c34219ab
+oid sha256:d1398abfe945cdadcbfb72545a44274567333ea62c9374fad6a213dc7a74f085
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541a8d7a44578a73d37559badc34c3a1afe0d9b1d50ab26f1598001f3a3c1618
+oid sha256:bf50a8da9b77d1d667aa2be5f7411c48d830b5ed090e0ff1a8209df626c404c4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18518518518518517,
+  "epoch": 0.37037037037037035,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,34 @@
       "learning_rate": 4.531893004115226e-05,
       "loss": 0.1499,
       "step": 200
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.2746913580246915e-05,
+      "loss": 0.1335,
+      "step": 250
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.017489711934157e-05,
+      "loss": 0.1225,
+      "step": 300
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 3.734375,
+      "learning_rate": 3.760288065843622e-05,
+      "loss": 0.1248,
+      "step": 350
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.503086419753087e-05,
+      "loss": 0.1141,
+      "step": 400
     }
   ],
   "logging_steps": 50,