Training in progress, step 3400, 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, 0.6239, 0.0843],
-#         [0.6239, 1.0000, 0.1270],
-#         [0.0843, 0.1270, 1.0000]])
+# tensor([[1.0000, 0.6213, 0.1034],
+#         [0.6213, 1.0000, 0.1548],
+#         [0.1034, 0.1548, 1.0000]])
 ```
 
 <!--
@@ -1288,6 +1288,10 @@ You can finetune this model on your own dataset.
 | 0.0548 | 3100 | 0.6663        |
 | 0.0557 | 3150 | 0.5152        |
 | 0.0565 | 3200 | 0.5417        |
+| 0.0574 | 3250 | 0.5039        |
+| 0.0583 | 3300 | 0.4647        |
+| 0.0592 | 3350 | 0.4652        |
+| 0.0601 | 3400 | 0.4914        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2f7da0d95d2430f6d13687995e080c3fed754535ee0392c4ac0d988595c206
+oid sha256:96302fbbd7e0f6d0492ce6ba1f9f65f0cba90c6cb4cd835da0c1f3411654d653
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512331db4e7bbde846026f7146ee83d4cd409399e1029e49f0bdd154597bf767
+oid sha256:e781618525c9855e4f157136a16d3e26d3f42648498f20aa5fe31fe6a0aed0f2
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09a17a8985bbbf88900bb9c55cd9603d6be0205a4acbc9e556c560a96f36436
+oid sha256:0305d5c9d4f21839e046a110958334e61d6cefa97054a71fb45b4a1a270d4081
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c180209d079915ff6b1a53d381fcf729d9a0c187b6ef7700d80eb57e51fa070b
+oid sha256:a7f0057f1a0cc52de60522c168cd59fee011d5489cd8505c56661af314a337f0
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473270958e9e1e76d015dca5bcc9949e4f7aea727004c8a1e7514a0b959338f7
+oid sha256:1431f76ecd1262a7cee93f19f73849ff3ccfef9b13f029cc43fe09b5880dedb6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056546093901857185,
+  "epoch": 0.06008022477072326,
   "eval_steps": 500,
-  "global_step": 3200,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -456,6 +456,34 @@
       "learning_rate": 2.8259717314487632e-05,
       "loss": 0.5417,
       "step": 3200
+    },
+    {
+      "epoch": 0.057429626619073706,
+      "grad_norm": 2.8348097801208496,
+      "learning_rate": 2.870141342756184e-05,
+      "loss": 0.5039,
+      "step": 3250
+    },
+    {
+      "epoch": 0.05831315933629022,
+      "grad_norm": 3.6297833919525146,
+      "learning_rate": 2.9143109540636045e-05,
+      "loss": 0.4647,
+      "step": 3300
+    },
+    {
+      "epoch": 0.05919669205350674,
+      "grad_norm": 2.6729063987731934,
+      "learning_rate": 2.9584805653710253e-05,
+      "loss": 0.4652,
+      "step": 3350
+    },
+    {
+      "epoch": 0.06008022477072326,
+      "grad_norm": 3.030548572540283,
+      "learning_rate": 3.0026501766784454e-05,
+      "loss": 0.4914,
+      "step": 3400
     }
   ],
   "logging_steps": 50,