Training in progress, step 400, checkpoint

last-checkpoint/README.md

@@ -416,9 +416,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.4919, -0.0905],
-#         [ 0.4919,  1.0000, -0.1434],
-#         [-0.0905, -0.1434,  1.0000]])
+# tensor([[ 1.0000,  0.4770, -0.1176],
+#         [ 0.4770,  1.0000, -0.1020],
+#         [-0.1176, -0.1020,  1.0000]])
 ```
 
 <!--
@@ -656,6 +656,10 @@ You can finetune this model on your own dataset.
 | 0.1370 | 100  | 0.8715        |
 | 0.2055 | 150  | 0.6398        |
 | 0.2740 | 200  | 0.5817        |
+| 0.3425 | 250  | 0.5193        |
+| 0.4110 | 300  | 0.4935        |
+| 0.4795 | 350  | 0.4662        |
+| 0.5479 | 400  | 0.449         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b34cd2caf9c9a664fd450ad8e21aa0c2b3e6183ddccd46c3619c3365d6d56d
+oid sha256:7b0ce948a95b29189f69f4bba8071558e2eafcdd2bda650a7d92e811b7adc663
 size 437951328

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424db7177d65c3313c0423aa5f09ce23e328390be1474772c77542662b1e8149
+oid sha256:b143d28499d536f548241413acf27b6cd6d0b6f4b90b9551dae666055d777b71
 size 871301195

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bbf71cee7402333ab646e807d281e58eeef0676216252007872f7bb9ed47e2
+oid sha256:ba5d27766d4c8ec6bf269c8a9b25bd0d7627e8a554f5dd75670575d47dd13e23
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e7cced7fef8cba6df9ca4acca2816388a3ba7300d02eba5a64fc90c461ddf7
+oid sha256:284bbe008441815e817218c78fc77324a088b7d2ac68f6350263f485b381c475
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.273972602739726,
+  "epoch": 0.547945205479452,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,34 @@
       "learning_rate": 4.041095890410959e-05,
       "loss": 0.5817,
       "step": 200
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 2.36545991897583,
+      "learning_rate": 3.6605783866057844e-05,
+      "loss": 0.5193,
+      "step": 250
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 2.521606206893921,
+      "learning_rate": 3.280060882800609e-05,
+      "loss": 0.4935,
+      "step": 300
+    },
+    {
+      "epoch": 0.4794520547945205,
+      "grad_norm": 2.228372097015381,
+      "learning_rate": 2.8995433789954342e-05,
+      "loss": 0.4662,
+      "step": 350
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 2.2849905490875244,
+      "learning_rate": 2.519025875190259e-05,
+      "loss": 0.449,
+      "step": 400
     }
   ],
   "logging_steps": 50,