Training in progress, step 7200, 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, 0.6619, 0.0916],
-#         [0.6619, 1.0000, 0.1211],
-#         [0.0916, 0.1211, 1.0000]])
+# tensor([[1.0000, 0.6879, 0.1286],
+#         [0.6879, 1.0000, 0.1688],
+#         [0.1286, 0.1688, 1.0000]])
 ```
 
 <!--
@@ -1256,6 +1256,10 @@ You can finetune this model on your own dataset.
 | 0.1219 | 6900 | 0.5377        |
 | 0.1228 | 6950 | 0.5275        |
 | 0.1237 | 7000 | 0.5489        |
+| 0.1246 | 7050 | 0.3931        |
+| 0.1255 | 7100 | 0.5155        |
+| 0.1263 | 7150 | 0.4282        |
+| 0.1272 | 7200 | 0.4639        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a44e0cd1f0ccf12b1dca9efa9b0a109d1425c46e6ee135b4bd9edab468c9fb
+oid sha256:67e0640c0093f6938269cf5b0ca154261896c0baa13615b9ac24acbc00815c24
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c416ec7d63637f42fd412c23b32b2de49e0fc0ccea09c98c6c470af5e0b0abd7
+oid sha256:5fca48ccb7c4a584f7af19fddac5f49e519b33cedea2b5a68a882138149c59ef
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f959cd98ceabc97c807d274c7db83cee5e9c5263d8148d895ba0898affda3b
+oid sha256:309540c657541ac81d087cbb68ec4167d38f8c9f78a01a5baabdd0e371dee4d2
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb26cc4077b901ce929db4f71fc0921ae313290fcd552277dc07d08aeff1cb82
+oid sha256:1789ba0d507fa201879591abbc90e77d1dba00075efb5f28f2624ffc56affbc2
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc1ade0b823d69812ec43663888123a640bc3eb21cbec83f295c4c1cde60129
+oid sha256:eb2d3fce775411949a9aaee54964b6ea09aaa40534b915c7642ea1c1b586b54a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12369458041031259,
+  "epoch": 0.12722871127917867,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -988,6 +988,34 @@
       "learning_rate": 4.8685476428893995e-05,
       "loss": 0.5489,
       "step": 7000
+    },
+    {
+      "epoch": 0.12457811312752912,
+      "grad_norm": 1.9759315252304077,
+      "learning_rate": 4.863639041055546e-05,
+      "loss": 0.3931,
+      "step": 7050
+    },
+    {
+      "epoch": 0.12546164584474562,
+      "grad_norm": 1.9036837816238403,
+      "learning_rate": 4.8587304392216925e-05,
+      "loss": 0.5155,
+      "step": 7100
+    },
+    {
+      "epoch": 0.12634517856196215,
+      "grad_norm": 3.4224536418914795,
+      "learning_rate": 4.853821837387838e-05,
+      "loss": 0.4282,
+      "step": 7150
+    },
+    {
+      "epoch": 0.12722871127917867,
+      "grad_norm": 3.1725916862487793,
+      "learning_rate": 4.8489132355539854e-05,
+      "loss": 0.4639,
+      "step": 7200
     }
   ],
   "logging_steps": 50,