Training in progress, step 7000, 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, 0.6386, 0.0907],
-#         [0.6386, 1.0000, 0.1293],
-#         [0.0907, 0.1293, 1.0000]])
+# tensor([[1.0000, 0.6619, 0.0916],
+#         [0.6619, 1.0000, 0.1211],
+#         [0.0916, 0.1211, 1.0000]])
 ```
 
 <!--
@@ -1252,6 +1252,10 @@ You can finetune this model on your own dataset.
 | 0.1184 | 6700 | 0.3458        |
 | 0.1193 | 6750 | 0.4791        |
 | 0.1202 | 6800 | 0.4445        |
+| 0.1210 | 6850 | 0.4907        |
+| 0.1219 | 6900 | 0.5377        |
+| 0.1228 | 6950 | 0.5275        |
+| 0.1237 | 7000 | 0.5489        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b02e9263fae48b1d9ab2f1178fcee32bed4de27687bb815e26abc0ce008c821e
+oid sha256:28a44e0cd1f0ccf12b1dca9efa9b0a109d1425c46e6ee135b4bd9edab468c9fb
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913066d7b5165875dea05ddec8312156da1e56f82e24e99d791ccdb18b2f2155
+oid sha256:c416ec7d63637f42fd412c23b32b2de49e0fc0ccea09c98c6c470af5e0b0abd7
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e882bce39886348a50b26b191125b019e0e62425e804cb094d791f2c1855ea8c
+oid sha256:f2f959cd98ceabc97c807d274c7db83cee5e9c5263d8148d895ba0898affda3b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50fb3d1e5c722b019233137abea1c664e37622c6ede4dfdabd46503c9bbc26b1
+oid sha256:cb26cc4077b901ce929db4f71fc0921ae313290fcd552277dc07d08aeff1cb82
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e206eec8216dd19609780d011982a4e55c6f1b80f70dfd43f28e3b1dc99011
+oid sha256:9bc1ade0b823d69812ec43663888123a640bc3eb21cbec83f295c4c1cde60129
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12016044954144652,
+  "epoch": 0.12369458041031259,
   "eval_steps": 500,
-  "global_step": 6800,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -960,6 +960,34 @@
       "learning_rate": 4.8881820502248144e-05,
       "loss": 0.4445,
       "step": 6800
+    },
+    {
+      "epoch": 0.12104398225866304,
+      "grad_norm": 3.1055896282196045,
+      "learning_rate": 4.88327344839096e-05,
+      "loss": 0.4907,
+      "step": 6850
+    },
+    {
+      "epoch": 0.12192751497587956,
+      "grad_norm": 3.251380681991577,
+      "learning_rate": 4.8783648465571066e-05,
+      "loss": 0.5377,
+      "step": 6900
+    },
+    {
+      "epoch": 0.12281104769309607,
+      "grad_norm": 2.909510850906372,
+      "learning_rate": 4.873456244723254e-05,
+      "loss": 0.5275,
+      "step": 6950
+    },
+    {
+      "epoch": 0.12369458041031259,
+      "grad_norm": 2.0700035095214844,
+      "learning_rate": 4.8685476428893995e-05,
+      "loss": 0.5489,
+      "step": 7000
     }
   ],
   "logging_steps": 50,