Training in progress, step 600, checkpoint

last-checkpoint/README.md

@@ -505,9 +505,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.6415, -0.0405],
-#         [ 0.6415,  1.0000, -0.0528],
-#         [-0.0405, -0.0528,  1.0000]])
+# tensor([[ 1.0000,  0.6584, -0.0531],
+#         [ 0.6584,  1.0000, -0.0991],
+#         [-0.0531, -0.0991,  1.0000]])
 ```
 
 <!--
@@ -723,6 +723,10 @@ You can finetune this model on your own dataset.
 | 0.2879 | 300  | 0.4757        |
 | 0.3359 | 350  | 0.477         |
 | 0.3839 | 400  | 0.4604        |
+| 0.4319 | 450  | 0.4363        |
+| 0.4798 | 500  | 0.4291        |
+| 0.5278 | 550  | 0.4192        |
+| 0.5758 | 600  | 0.4287        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e4673a236c95d0bc4a0ae5ca5eae4eee997d5826d21e669e6418ac6a733790
+oid sha256:020d0d7176e467b6cd601d44d45bfdcd0927689574be8e5af96eafb7f39d4781
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d118b435f05009ed43f3d552c5b45865b77291129c0c33b6f607fed13185aa8b
+oid sha256:f69755d55036a1c9c5e74b7da11093ccc408dc752b3193aa2c2a2920b5241214
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fe371788fff42378dd68792f5fdb6293656d333891448d1b8f5196e3c8fec7
+oid sha256:930d5cc5a42dcd98e15dda5f0b8f8625912aaf157ec6f27c32761a0f3c4e311e
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0af633a4f9f804af5866a99325014522ad3b38b189715886b1cb20a1e95ac1
+oid sha256:edab5dd7827df6c860a06cbc8d688873b247f37062ba5008ca6bb63249a0eb13
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3838771593090211,
+  "epoch": 0.5758157389635317,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 3.431163287086446e-05,
       "loss": 0.4604,
       "step": 400
+    },
+    {
+      "epoch": 0.43186180422264875,
+      "grad_norm": 1.7176055908203125,
+      "learning_rate": 3.16435432230523e-05,
+      "loss": 0.4363,
+      "step": 450
+    },
+    {
+      "epoch": 0.4798464491362764,
+      "grad_norm": 1.6267833709716797,
+      "learning_rate": 2.897545357524013e-05,
+      "loss": 0.4291,
+      "step": 500
+    },
+    {
+      "epoch": 0.527831094049904,
+      "grad_norm": 1.6887868642807007,
+      "learning_rate": 2.6307363927427965e-05,
+      "loss": 0.4192,
+      "step": 550
+    },
+    {
+      "epoch": 0.5758157389635317,
+      "grad_norm": 1.4798693656921387,
+      "learning_rate": 2.3639274279615796e-05,
+      "loss": 0.4287,
+      "step": 600
     }
   ],
   "logging_steps": 50,