Training in progress, step 400, 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,  0.6097, -0.0412],
-#         [ 0.6097,  1.0000, -0.0067],
-#         [-0.0412, -0.0067,  1.0000]])
+# tensor([[ 1.0000,  0.6415, -0.0405],
+#         [ 0.6415,  1.0000, -0.0528],
+#         [-0.0405, -0.0528,  1.0000]])
 ```
 
 <!--
@@ -719,6 +719,10 @@ You can finetune this model on your own dataset.
 | 0.0960 | 100  | 0.6884        |
 | 0.1440 | 150  | 0.5902        |
 | 0.1919 | 200  | 0.5362        |
+| 0.2399 | 250  | 0.5196        |
+| 0.2879 | 300  | 0.4757        |
+| 0.3359 | 350  | 0.477         |
+| 0.3839 | 400  | 0.4604        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45678ca92701e2b21d762de3576e475d0d9a1bd02f16d5e2320057ec6fa09465
+oid sha256:e1e4673a236c95d0bc4a0ae5ca5eae4eee997d5826d21e669e6418ac6a733790
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e4b9ec6534cb3bfecf2195dc89b9aecba29d7b8f791ee24ecb9b2f2b2f1cf8
+oid sha256:d118b435f05009ed43f3d552c5b45865b77291129c0c33b6f607fed13185aa8b
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bef9076975c77b5c8cc319158c1ecd2196bb244317040f0ca1f1eedc950136
+oid sha256:44fe371788fff42378dd68792f5fdb6293656d333891448d1b8f5196e3c8fec7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d88407aff68ef8509234fd2211bb50888896b55849641ad9180c09511a40fab
+oid sha256:df0af633a4f9f804af5866a99325014522ad3b38b189715886b1cb20a1e95ac1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19193857965451055,
+  "epoch": 0.3838771593090211,
   "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": 4.4983991462113126e-05,
       "loss": 0.5362,
       "step": 200
+    },
+    {
+      "epoch": 0.2399232245681382,
+      "grad_norm": 1.8430039882659912,
+      "learning_rate": 4.231590181430096e-05,
+      "loss": 0.5196,
+      "step": 250
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "grad_norm": 1.9631397724151611,
+      "learning_rate": 3.9647812166488794e-05,
+      "loss": 0.4757,
+      "step": 300
+    },
+    {
+      "epoch": 0.33589251439539347,
+      "grad_norm": 1.9073326587677002,
+      "learning_rate": 3.697972251867663e-05,
+      "loss": 0.477,
+      "step": 350
+    },
+    {
+      "epoch": 0.3838771593090211,
+      "grad_norm": 1.7632094621658325,
+      "learning_rate": 3.431163287086446e-05,
+      "loss": 0.4604,
+      "step": 400
     }
   ],
   "logging_steps": 50,