Training in progress, step 400, checkpoint

last-checkpoint/README.md

@@ -418,9 +418,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8211, 0.0629],
-#         [0.8211, 1.0000, 0.1016],
-#         [0.0629, 0.1016, 1.0000]])
+# tensor([[1.0000, 0.8039, 0.0072],
+#         [0.8039, 1.0000, 0.0365],
+#         [0.0072, 0.0365, 1.0000]])
 ```
 
 <!--
@@ -629,6 +629,10 @@ You can finetune this model on your own dataset.
 | 0.0926 | 100  | 0.3737        |
 | 0.1389 | 150  | 0.3271        |
 | 0.1852 | 200  | 0.309         |
+| 0.2315 | 250  | 0.2706        |
+| 0.2778 | 300  | 0.2587        |
+| 0.3241 | 350  | 0.2629        |
+| 0.3704 | 400  | 0.2518        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6d5fe7579a8728e8ce1b5a3d16cc6d66c5719392898bc44d8ff0f2fa3b0a9f
+oid sha256:48ef8ec0a1171721c804c180346ec3c917c952ed0da36455a504c5863c6c9788
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bfc8d92d7169e34af54cf060e06b10ee4e5ac9ddc2b191b9c37e4b367c1665
+oid sha256:9d9aea5acedf0733c92a9daea99cb257662f8f5ae5961ec2df047b6e0c75cc91
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb75720d80bc56d0ec34834b2514caa83f7e0d893f31f4afcbf3ca5aa7e264b
+oid sha256:c19b67f89acc145936e1b518bb5813ff7a56d806e790b9924b0c10aabb6eba24
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541a8d7a44578a73d37559badc34c3a1afe0d9b1d50ab26f1598001f3a3c1618
+oid sha256:bf50a8da9b77d1d667aa2be5f7411c48d830b5ed090e0ff1a8209df626c404c4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18518518518518517,
+  "epoch": 0.37037037037037035,
   "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": 4.531893004115226e-05,
       "loss": 0.309,
       "step": 200
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.151724934577942,
+      "learning_rate": 4.2746913580246915e-05,
+      "loss": 0.2706,
+      "step": 250
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.5069067478179932,
+      "learning_rate": 4.017489711934157e-05,
+      "loss": 0.2587,
+      "step": 300
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 1.3596380949020386,
+      "learning_rate": 3.760288065843622e-05,
+      "loss": 0.2629,
+      "step": 350
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.3064409494400024,
+      "learning_rate": 3.503086419753087e-05,
+      "loss": 0.2518,
+      "step": 400
     }
   ],
   "logging_steps": 50,