Training in progress, step 1968, 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,  0.5466, -0.0454],
-#         [ 0.5466,  1.0000, -0.0568],
-#         [-0.0454, -0.0568,  1.0000]])
+# tensor([[ 1.0000,  0.5476, -0.0452],
+#         [ 0.5476,  1.0000, -0.0572],
+#         [-0.0452, -0.0572,  1.0000]])
 ```
 
 <!--
@@ -712,6 +712,9 @@ You can finetune this model on your own dataset.
 | 0.8638 | 1700 | 0.4797        |
 | 0.8892 | 1750 | 0.4836        |
 | 0.9146 | 1800 | 0.4832        |
+| 0.9400 | 1850 | 0.4945        |
+| 0.9654 | 1900 | 0.4686        |
+| 0.9909 | 1950 | 0.4889        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17554aba416dac32662ee4493f2bcaa68570b7683a6b8940eb5d0031827f3358
+oid sha256:9080ef7277f0217e3fcbbed443d4e5ddc988fbc3584f2d4e802ff68df0a7bdac
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7df775c39fa3b71bbba8fbfd34191533c8b284b769351bdb0714a10d07e26c
+oid sha256:27d3829e1ab12246a2cf294916488e1316baa979819e854e9daf959d2b57cba6
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4383e099fde8143073bc583376ee59e15bec296ef152a2f16e0f5296290e06e4
+oid sha256:bbb5e9a64c60aa1634b1d1197ab20d54415e7d3be09731170c25ff71a460e2a5
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec29327b2c793ef05a01c6bae10cd1cf49d3fd34bb421765aad2d8f09bc372c0
+oid sha256:04e88cb3830f9a985bd7f6d2cca6f569425345d84761a9b2c6e58dd048cd58e3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9146341463414634,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1800,
+  "global_step": 1968,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -260,6 +260,27 @@
       "learning_rate": 4.771315640880859e-06,
       "loss": 0.4832,
       "step": 1800
+    },
+    {
+      "epoch": 0.9400406504065041,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.3596837944664035e-06,
+      "loss": 0.4945,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9654471544715447,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.948051948051948e-06,
+      "loss": 0.4686,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9908536585365854,
+      "grad_norm": 1.796875,
+      "learning_rate": 5.364201016374929e-07,
+      "loss": 0.4889,
+      "step": 1950
     }
   ],
   "logging_steps": 50,
@@ -274,7 +295,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }