Training in progress, step 1800, 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, 0.5831, 0.1091],
-#         [0.5831, 1.0000, 0.1491],
-#         [0.1091, 0.1491, 1.0000]])
+# tensor([[1.0000, 0.6240, 0.1415],
+#         [0.6240, 1.0000, 0.1641],
+#         [0.1415, 0.1641, 1.0000]])
 ```
 
 <!--
@@ -1256,6 +1256,10 @@ You can finetune this model on your own dataset.
 | 0.0265 | 1500 | 0.6639        |
 | 0.0274 | 1550 | 0.6795        |
 | 0.0283 | 1600 | 0.6341        |
+| 0.0292 | 1650 | 0.6031        |
+| 0.0300 | 1700 | 0.5959        |
+| 0.0309 | 1750 | 0.6412        |
+| 0.0318 | 1800 | 0.5065        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61a082ce4f7292aa8d2ccb7ce494bab8f2b629411a594d12d441a6b6b4b0923
+oid sha256:e655f66bc39e233b9c8a58c97b97703f4aeea426a1d4cf2e42279efc281c516e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9774e69968408986a253b355147319deaf91c49e1a0418b0c871e674bc9e7d
+oid sha256:8edb9779f991324ee4a3850ff5e072ec580ee76e1759218d64fde606def14c42
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c221931df6dfe32bf8ee57ce8b3fe8867a8a29cca913a459c26e86b456713867
+oid sha256:c069f50ffa5dd2b5cfe72eb0edf43eb9716de220eca4477d056e688e57407292
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4420338904222790575638e536e5d59f25756f58070a9dfc3e73602e7fbef5
+oid sha256:fa0408efb69cab96d5bab9a1aaf44cedbc9fc8d34f4cef378d81605e5c026d5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5f1576da158c64c9c0e76311baa11fecb51a267280f5c39299d29d917bc401
+oid sha256:0cd0879a5aed9e5750d6784df10ece392dd4d2a4115b2e37d50a195c94de0560
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028273046950928592,
+  "epoch": 0.03180717781979467,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,34 @@
       "learning_rate": 1.4125441696113076e-05,
       "loss": 0.6341,
       "step": 1600
+    },
+    {
+      "epoch": 0.02915657966814511,
+      "grad_norm": 1.9698214530944824,
+      "learning_rate": 1.456713780918728e-05,
+      "loss": 0.6031,
+      "step": 1650
+    },
+    {
+      "epoch": 0.03004011238536163,
+      "grad_norm": 2.495985507965088,
+      "learning_rate": 1.5008833922261484e-05,
+      "loss": 0.5959,
+      "step": 1700
+    },
+    {
+      "epoch": 0.030923645102578147,
+      "grad_norm": 2.990360975265503,
+      "learning_rate": 1.545053003533569e-05,
+      "loss": 0.6412,
+      "step": 1750
+    },
+    {
+      "epoch": 0.03180717781979467,
+      "grad_norm": 3.658212184906006,
+      "learning_rate": 1.5892226148409894e-05,
+      "loss": 0.5065,
+      "step": 1800
     }
   ],
   "logging_steps": 50,