Training in progress, step 1200, 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,  0.5433, -0.0509],
-#         [ 0.5433,  1.0000, -0.0602],
-#         [-0.0509, -0.0602,  1.0000]])
+# tensor([[ 1.0000,  0.5452, -0.0490],
+#         [ 0.5452,  1.0000, -0.0581],
+#         [-0.0490, -0.0581,  1.0000]])
 ```
 
 <!--
@@ -696,6 +696,10 @@ You can finetune this model on your own dataset.
 | 0.4573 | 900  | 0.4869        |
 | 0.4827 | 950  | 0.4898        |
 | 0.5081 | 1000 | 0.501         |
+| 0.5335 | 1050 | 0.4843        |
+| 0.5589 | 1100 | 0.496         |
+| 0.5843 | 1150 | 0.4878        |
+| 0.6098 | 1200 | 0.4892        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e1e9d5eff6c41809cc50c6c706e397f17bdefc78c905246322008dcb6296db
+oid sha256:b6ccad225ace68dee6e0781e8e27901d71d7fa01d17d06a0b6e3fc454a5478e4
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcbdfcd46b4c04eb85077625bdbae7131e652ba94a811efcd17b9990ba6743b
+oid sha256:9aa4f63fab73d0181a0c9306b4976314c3fecfc2cc8c586e50cb9e5ef066cf9d
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dffc0ceb65e8c69d366f764cae9f9d5143c5e98038853351451b525757197063
+oid sha256:194afcbe1a7663b9e29766856c518f1adcc144fc5b40f9d65d44fac282c10ac3
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6c56263d0a3d675d4f747bb77db752789302abc7e0c5864efa40f605c0194a
+oid sha256:b8e232785d1786cb94e8889d9a79973e568b9bfb82c9ff8f8a12783934ff997c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.508130081300813,
+  "epoch": 0.6097560975609756,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,34 @@
       "learning_rate": 2.7357425183512143e-05,
       "loss": 0.501,
       "step": 1000
+    },
+    {
+      "epoch": 0.5335365853658537,
+      "grad_norm": 1.7578125,
+      "learning_rate": 2.5945793337097685e-05,
+      "loss": 0.4843,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5589430894308943,
+      "grad_norm": 1.9453125,
+      "learning_rate": 2.453416149068323e-05,
+      "loss": 0.496,
+      "step": 1100
+    },
+    {
+      "epoch": 0.584349593495935,
+      "grad_norm": 2.046875,
+      "learning_rate": 2.3122529644268774e-05,
+      "loss": 0.4878,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 1.875,
+      "learning_rate": 2.171089779785432e-05,
+      "loss": 0.4892,
+      "step": 1200
     }
   ],
   "logging_steps": 50,