Training in progress, step 6200, 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, 0.6825, 0.0849],
-#         [0.6825, 1.0000, 0.1574],
-#         [0.0849, 0.1574, 1.0000]])
+# tensor([[1.0000, 0.6439, 0.1032],
+#         [0.6439, 1.0000, 0.1639],
+#         [0.1032, 0.1639, 1.0000]])
 ```
 
 <!--
@@ -1236,6 +1236,10 @@ You can finetune this model on your own dataset.
 | 0.1043 | 5900 | 0.5589        |
 | 0.1051 | 5950 | 0.4507        |
 | 0.1060 | 6000 | 0.5429        |
+| 0.1069 | 6050 | 0.3789        |
+| 0.1078 | 6100 | 0.3949        |
+| 0.1087 | 6150 | 0.4491        |
+| 0.1096 | 6200 | 0.435         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7789fd8be583c6cd52a2b3c49d3926b4c97ae306770f1629fc1b7121d168f986
+oid sha256:4a5270b151b39c586df44055763986b001c438f14893a5a40f6c947ee59b4dc8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02388678163538169399bda8fffa8df551692b3bfa9b7ca53bde07a66c2a6e0
+oid sha256:427a25cee731ef25ec82aa31f31d5a9a97bf0eeea4714138f8d9bf9fc951230f
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72d2db1e1a80b4db59e84d70863f853ea4793c1b3630fdd9ffed5098f03c668
+oid sha256:9bbae8b7e39c2440f246453cba4933379e4e2419770e59220962ebd5772f6447
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
+oid sha256:aced43cc9ad9f7501c29ad5e5ca57ee953f249e122ae417e48492911cc37f15d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df255e26e463b4fc70f27b3a2f6c9b68f20dc79363ed0890520e03d68a77d6b1
+oid sha256:0476ebd1df369b140089da74c2363c20e1328e3a729f4bbbf994d19625550ab9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10602392606598222,
+  "epoch": 0.1095580569348483,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -848,6 +848,34 @@
       "learning_rate": 4.966719679566473e-05,
       "loss": 0.5429,
       "step": 6000
+    },
+    {
+      "epoch": 0.10690745878319874,
+      "grad_norm": 1.6127039194107056,
+      "learning_rate": 4.961811077732619e-05,
+      "loss": 0.3789,
+      "step": 6050
+    },
+    {
+      "epoch": 0.10779099150041525,
+      "grad_norm": 2.230015993118286,
+      "learning_rate": 4.956902475898765e-05,
+      "loss": 0.3949,
+      "step": 6100
+    },
+    {
+      "epoch": 0.10867452421763178,
+      "grad_norm": 1.9963310956954956,
+      "learning_rate": 4.9519938740649116e-05,
+      "loss": 0.4491,
+      "step": 6150
+    },
+    {
+      "epoch": 0.1095580569348483,
+      "grad_norm": 2.2731542587280273,
+      "learning_rate": 4.947085272231058e-05,
+      "loss": 0.435,
+      "step": 6200
     }
   ],
   "logging_steps": 50,