Training in progress, step 316, checkpoint

last-checkpoint/README.md

@@ -557,9 +557,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.5954, -0.0482],
-#         [ 0.5954,  1.0000, -0.0418],
-#         [-0.0482, -0.0418,  1.0000]])
+# tensor([[ 1.0000,  0.5979, -0.0511],
+#         [ 0.5979,  1.0000, -0.0440],
+#         [-0.0511, -0.0440,  1.0000]])
 ```
 
 <!--
@@ -771,6 +771,8 @@ You can finetune this model on your own dataset.
 | 0.6329 | 100  | 0.7848        |
 | 0.9494 | 150  | 0.7202        |
 | 1.2658 | 200  | 0.6965        |
+| 1.5823 | 250  | 0.6903        |
+| 1.8987 | 300  | 0.6684        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314ed59e10e3f32e55a54ee7adfae92609119fa204da978b1c4be047fcca93d1
+oid sha256:efee2e1163a8db6bba28a294a50473cd41dd4cd8cf55dcaedee23603586374ec
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989fd25dbc85b7f65bbbecd848cc0de7421c828ccaf3542f351e61ca8d30491d
+oid sha256:840822f2920e307de8aac2b4662ac4f47ba559e0a01a0df5e10570a012a93242
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657fb80ae02eeeba0ad1daff58678331a190501732edde75bd8503ef3108d9e5
+oid sha256:341a3f6fac90a99a2352e35ffad0f92a70d4118129101f414cd93382d1e42840
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d022e7ab2abc42f21152d63be9345ee6b773ca2c7af82687c343215a2fdc60bf
+oid sha256:4724219abe10ead12ce240c08dbe3ba614a702d77bcfb8388c812d1ad9eecef1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2658227848101267,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 316,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,20 @@
       "learning_rate": 2.0598591549295776e-05,
       "loss": 0.6965,
       "step": 200
+    },
+    {
+      "epoch": 1.5822784810126582,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.1795774647887324e-05,
+      "loss": 0.6903,
+      "step": 250
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.9929577464788733e-06,
+      "loss": 0.6684,
+      "step": 300
     }
   ],
   "logging_steps": 50,
@@ -50,7 +64,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }