Training in progress, step 1400, 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, 0.6149, 0.1330],
-#         [0.6149, 1.0000, 0.1618],
-#         [0.1330, 0.1618, 1.0000]])
+# tensor([[1.0000, 0.6098, 0.1159],
+#         [0.6098, 1.0000, 0.1612],
+#         [0.1159, 0.1612, 1.0000]])
 ```
 
 <!--
@@ -1248,6 +1248,10 @@ You can finetune this model on your own dataset.
 | 0.0194 | 1100 | 0.6169        |
 | 0.0203 | 1150 | 0.6367        |
 | 0.0212 | 1200 | 0.615         |
+| 0.0221 | 1250 | 0.6869        |
+| 0.0230 | 1300 | 0.7527        |
+| 0.0239 | 1350 | 0.6124        |
+| 0.0247 | 1400 | 0.6511        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a3361ca69436d4dea95cdcd29cea53aad0e253053cdc5876ca978a2c32a909
+oid sha256:50f82f7a3e99ac380e6c75e094e8a65af18eab74684e14810366f1f357e41d60
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7762e45714247d845b98566f70065d2e826d2dad86f6f5a0df3a0f6e4cc3e852
+oid sha256:075842c04a113f74618952773066d4169a59d801ccaeebc81d0b3d4f339980ae
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92073e2121fa1a50d2393b4b193256ae067f8269c786bb12674760941abf850b
+oid sha256:e01322e389b4b8eb7d66bcbb01e77ee7865373b24e1202361d2a597222b56d92
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18783150ac09b6b81cea5af47876a10bfe5f36c3d76aca4ffce5382bdfaf7b28
+oid sha256:f3b03c8c40e45be48b5956b82e1abb2c1ec5641f4fc77e6fdec0942a77964500
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed3eff7033631ee9ecca3bfddfbb19428dfe42f7f70d962500698dee83c17e2
+oid sha256:f365945c29bbfef6ade3ff30db3a8d39cad690fb183ff7034a93fcc76535d32d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021204785213196443,
+  "epoch": 0.02473891608206252,
   "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": 1.0591872791519434e-05,
       "loss": 0.615,
       "step": 1200
+    },
+    {
+      "epoch": 0.02208831793041296,
+      "grad_norm": 3.260239601135254,
+      "learning_rate": 1.103356890459364e-05,
+      "loss": 0.6869,
+      "step": 1250
+    },
+    {
+      "epoch": 0.022971850647629483,
+      "grad_norm": 2.485383987426758,
+      "learning_rate": 1.1475265017667845e-05,
+      "loss": 0.7527,
+      "step": 1300
+    },
+    {
+      "epoch": 0.023855383364846,
+      "grad_norm": 2.26680326461792,
+      "learning_rate": 1.191696113074205e-05,
+      "loss": 0.6124,
+      "step": 1350
+    },
+    {
+      "epoch": 0.02473891608206252,
+      "grad_norm": 2.348688840866089,
+      "learning_rate": 1.2358657243816255e-05,
+      "loss": 0.6511,
+      "step": 1400
     }
   ],
   "logging_steps": 50,