Training in progress, step 1400, checkpoint

last-checkpoint/README.md

@@ -466,9 +466,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.5452, -0.0490],
-#         [ 0.5452,  1.0000, -0.0581],
-#         [-0.0490, -0.0581,  1.0000]])
+# tensor([[ 1.0000,  0.5480, -0.0458],
+#         [ 0.5480,  1.0000, -0.0586],
+#         [-0.0458, -0.0586,  1.0000]])
 ```
 
 <!--
@@ -700,6 +700,10 @@ You can finetune this model on your own dataset.
 | 0.5589 | 1100 | 0.496         |
 | 0.5843 | 1150 | 0.4878        |
 | 0.6098 | 1200 | 0.4892        |
+| 0.6352 | 1250 | 0.4915        |
+| 0.6606 | 1300 | 0.4868        |
+| 0.6860 | 1350 | 0.4819        |
+| 0.7114 | 1400 | 0.486         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ccad225ace68dee6e0781e8e27901d71d7fa01d17d06a0b6e3fc454a5478e4
+oid sha256:75920a4e97e5b78b8f2aef96fae35a0db4f205a5343091523547609bce4b1d9f
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa4f63fab73d0181a0c9306b4976314c3fecfc2cc8c586e50cb9e5ef066cf9d
+oid sha256:9e095a8f770b2b09aeb0a9f8fb5ddd7dac988fa28d75f73b4e4ef2b0581b1b05
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194afcbe1a7663b9e29766856c518f1adcc144fc5b40f9d65d44fac282c10ac3
+oid sha256:f7e4625f78173d74ff3d9f6deda2944ea87976ad1f424f0e59922e3adcae27fc
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e232785d1786cb94e8889d9a79973e568b9bfb82c9ff8f8a12783934ff997c
+oid sha256:0299032156c99cc748a49daedbaed704010a8fef256e5ec9b90ef95f2e77d9cd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6097560975609756,
+  "epoch": 0.7113821138211383,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,6 +176,34 @@
       "learning_rate": 2.171089779785432e-05,
       "loss": 0.4892,
       "step": 1200
+    },
+    {
+      "epoch": 0.6351626016260162,
+      "grad_norm": 1.8203125,
+      "learning_rate": 2.0299265951439866e-05,
+      "loss": 0.4915,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6605691056910569,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.888763410502541e-05,
+      "loss": 0.4868,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6859756097560976,
+      "grad_norm": 1.75,
+      "learning_rate": 1.7476002258610955e-05,
+      "loss": 0.4819,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7113821138211383,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.60643704121965e-05,
+      "loss": 0.486,
+      "step": 1400
     }
   ],
   "logging_steps": 50,