Training in progress, step 400, 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,  0.4864, -0.0477],
-#         [ 0.4864,  1.0000, -0.0628],
-#         [-0.0477, -0.0628,  1.0000]])
+# tensor([[ 1.0000,  0.5340, -0.0489],
+#         [ 0.5340,  1.0000, -0.0623],
+#         [-0.0489, -0.0623,  1.0000]])
 ```
 
 <!--
@@ -680,6 +680,10 @@ You can finetune this model on your own dataset.
 | 0.0508 | 100  | 0.9886        |
 | 0.0762 | 150  | 0.7345        |
 | 0.1016 | 200  | 0.6664        |
+| 0.1270 | 250  | 0.6045        |
+| 0.1524 | 300  | 0.5898        |
+| 0.1778 | 350  | 0.5569        |
+| 0.2033 | 400  | 0.5396        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9cd66af2df3d93b44a7be9da35e1c72b158bddbc6dca683583cea252dd21ad
+oid sha256:ebaadd7ca69549d21e0a9b5a198c58e5df0a12a58aa56635196f10c545d2363b
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2ceafe399e0f67b7e02eadf72ed444135de3040ff7b41718e7e5c2b1b4379b
+oid sha256:c8a26a7a0f56cd6950e1e3ae0ec3c0412ad0bcebd9c3dfa88f2162b4a3e97528
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193ad77f0728afe0c1206dffe24ec29d395eeee0f88a01a3b5ee926dada4548f
+oid sha256:4865ec8a72ed85ad9518ab1ebb67049ddc164edcb9400bda4e9e54f2cabcece1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4e739551319e957e6c472fd8c9bacf3bae41231a764211a8f19abc4bae6961
+oid sha256:8fc56140e5c37825482a26f377f07f74eaa4028a1b2f8b46eaa880f0215c9abf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1016260162601626,
+  "epoch": 0.2032520325203252,
   "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": 4.994353472614343e-05,
       "loss": 0.6664,
       "step": 200
+    },
+    {
+      "epoch": 0.12703252032520326,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.853190287972897e-05,
+      "loss": 0.6045,
+      "step": 250
+    },
+    {
+      "epoch": 0.1524390243902439,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.7120271033314515e-05,
+      "loss": 0.5898,
+      "step": 300
+    },
+    {
+      "epoch": 0.17784552845528456,
+      "grad_norm": 1.6875,
+      "learning_rate": 4.570863918690006e-05,
+      "loss": 0.5569,
+      "step": 350
+    },
+    {
+      "epoch": 0.2032520325203252,
+      "grad_norm": 1.9765625,
+      "learning_rate": 4.42970073404856e-05,
+      "loss": 0.5396,
+      "step": 400
     }
   ],
   "logging_steps": 50,