Training in progress, step 2000, checkpoint

last-checkpoint/README.md

@@ -286,9 +286,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.6240, 0.1415],
-#         [0.6240, 1.0000, 0.1641],
-#         [0.1415, 0.1641, 1.0000]])
+# tensor([[1.0000, 0.5880, 0.1308],
+#         [0.5880, 1.0000, 0.1611],
+#         [0.1308, 0.1611, 1.0000]])
 ```
 
 <!--
@@ -1260,6 +1260,10 @@ You can finetune this model on your own dataset.
 | 0.0300 | 1700 | 0.5959        |
 | 0.0309 | 1750 | 0.6412        |
 | 0.0318 | 1800 | 0.5065        |
+| 0.0327 | 1850 | 0.5611        |
+| 0.0336 | 1900 | 0.5298        |
+| 0.0345 | 1950 | 0.5759        |
+| 0.0353 | 2000 | 0.5782        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e655f66bc39e233b9c8a58c97b97703f4aeea426a1d4cf2e42279efc281c516e
+oid sha256:814104de2dc74a0f467b27e454f11429bcabde4ec4e6cb0bee382acda4bd2af8
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edb9779f991324ee4a3850ff5e072ec580ee76e1759218d64fde606def14c42
+oid sha256:00eef042f462bb454219ea2918cf958fd5615f13c9bb9103c136a3d4d342d822
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c069f50ffa5dd2b5cfe72eb0edf43eb9716de220eca4477d056e688e57407292
+oid sha256:639c58a7c0af444791cd5711ba19270a82e589f2ee67d587a74f8240b2f70eec
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0408efb69cab96d5bab9a1aaf44cedbc9fc8d34f4cef378d81605e5c026d5c
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd0879a5aed9e5750d6784df10ece392dd4d2a4115b2e37d50a195c94de0560
+oid sha256:d3bd0299fa211f42a5bbf3d13d4c1b67f9745816753ebca5d122c47f94c26a70
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03180717781979467,
+  "epoch": 0.03534130868866074,
   "eval_steps": 500,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -260,6 +260,34 @@
       "learning_rate": 1.5892226148409894e-05,
       "loss": 0.5065,
       "step": 1800
+    },
+    {
+      "epoch": 0.03269071053701118,
+      "grad_norm": 2.010875940322876,
+      "learning_rate": 1.63339222614841e-05,
+      "loss": 0.5611,
+      "step": 1850
+    },
+    {
+      "epoch": 0.033574243254227705,
+      "grad_norm": 2.408937692642212,
+      "learning_rate": 1.6775618374558306e-05,
+      "loss": 0.5298,
+      "step": 1900
+    },
+    {
+      "epoch": 0.03445777597144422,
+      "grad_norm": 2.3144407272338867,
+      "learning_rate": 1.721731448763251e-05,
+      "loss": 0.5759,
+      "step": 1950
+    },
+    {
+      "epoch": 0.03534130868866074,
+      "grad_norm": 2.944115400314331,
+      "learning_rate": 1.7659010600706715e-05,
+      "loss": 0.5782,
+      "step": 2000
     }
   ],
   "logging_steps": 50,