Training in progress, step 3200, 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, 0.5851, 0.1104],
-#         [0.5851, 1.0000, 0.1499],
-#         [0.1104, 0.1499, 1.0000]])
+# tensor([[1.0000, 0.6239, 0.0843],
+#         [0.6239, 1.0000, 0.1270],
+#         [0.0843, 0.1270, 1.0000]])
 ```
 
 <!--
@@ -1284,6 +1284,10 @@ You can finetune this model on your own dataset.
 | 0.0512 | 2900 | 0.545         |
 | 0.0521 | 2950 | 0.5299        |
 | 0.0530 | 3000 | 0.5186        |
+| 0.0539 | 3050 | 0.5259        |
+| 0.0548 | 3100 | 0.6663        |
+| 0.0557 | 3150 | 0.5152        |
+| 0.0565 | 3200 | 0.5417        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bbbce60ef16e762bba9f8a3d9a23a215afa3ee462d98aeaeff69de27f89341
+oid sha256:0d2f7da0d95d2430f6d13687995e080c3fed754535ee0392c4ac0d988595c206
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5d645070344294324c8e72697f2c1b516db72cb3276a26e4ef639ee18da667
+oid sha256:512331db4e7bbde846026f7146ee83d4cd409399e1029e49f0bdd154597bf767
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e56f09343792c3d21faf51137b042a641d6fa07972ad9c4af87d2751a155e0e
+oid sha256:e09a17a8985bbbf88900bb9c55cd9603d6be0205a4acbc9e556c560a96f36436
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
+oid sha256:c180209d079915ff6b1a53d381fcf729d9a0c187b6ef7700d80eb57e51fa070b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301ffba56ec75fdb730415687e7a885bf8c0dc112cbdcb4314fb3614afb6e000
+oid sha256:473270958e9e1e76d015dca5bcc9949e4f7aea727004c8a1e7514a0b959338f7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05301196303299111,
+  "epoch": 0.056546093901857185,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,34 @@
       "learning_rate": 2.649293286219081e-05,
       "loss": 0.5186,
       "step": 3000
+    },
+    {
+      "epoch": 0.05389549575020763,
+      "grad_norm": 1.842517375946045,
+      "learning_rate": 2.693462897526502e-05,
+      "loss": 0.5259,
+      "step": 3050
+    },
+    {
+      "epoch": 0.05477902846742415,
+      "grad_norm": 3.319514274597168,
+      "learning_rate": 2.7376325088339223e-05,
+      "loss": 0.6663,
+      "step": 3100
+    },
+    {
+      "epoch": 0.05566256118464067,
+      "grad_norm": 2.7143654823303223,
+      "learning_rate": 2.781802120141343e-05,
+      "loss": 0.5152,
+      "step": 3150
+    },
+    {
+      "epoch": 0.056546093901857185,
+      "grad_norm": 2.8187732696533203,
+      "learning_rate": 2.8259717314487632e-05,
+      "loss": 0.5417,
+      "step": 3200
     }
   ],
   "logging_steps": 50,