Training in progress, step 800, checkpoint

last-checkpoint/README.md

@@ -505,9 +505,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.6584, -0.0531],
-#         [ 0.6584,  1.0000, -0.0991],
-#         [-0.0531, -0.0991,  1.0000]])
+# tensor([[ 1.0000,  0.6636, -0.0516],
+#         [ 0.6636,  1.0000, -0.0845],
+#         [-0.0516, -0.0845,  1.0000]])
 ```
 
 <!--
@@ -727,6 +727,10 @@ You can finetune this model on your own dataset.
 | 0.4798 | 500  | 0.4291        |
 | 0.5278 | 550  | 0.4192        |
 | 0.5758 | 600  | 0.4287        |
+| 0.6238 | 650  | 0.4093        |
+| 0.6718 | 700  | 0.4118        |
+| 0.7198 | 750  | 0.3923        |
+| 0.7678 | 800  | 0.4183        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020d0d7176e467b6cd601d44d45bfdcd0927689574be8e5af96eafb7f39d4781
+oid sha256:ff756dbb38a75171525943ee07a6245096eef361b8236a195a79e2f4c43e6b40
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69755d55036a1c9c5e74b7da11093ccc408dc752b3193aa2c2a2920b5241214
+oid sha256:519486a3681858d50acde069f580d97e5840fa5ac9d65b3f042141bd25e1cb41
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930d5cc5a42dcd98e15dda5f0b8f8625912aaf157ec6f27c32761a0f3c4e311e
+oid sha256:9f16fa28ebb8e3a1b82ca55c6cf1c0dd60b11d4021c7a97520baf445d2c84fd8
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab5dd7827df6c860a06cbc8d688873b247f37062ba5008ca6bb63249a0eb13
+oid sha256:d57a1899b276deaf9bc6c347b576a36bf470824199b1d1731a5698c732cc5649
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5758157389635317,
+  "epoch": 0.7677543186180422,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 2.3639274279615796e-05,
       "loss": 0.4287,
       "step": 600
+    },
+    {
+      "epoch": 0.6238003838771593,
+      "grad_norm": 1.5440646409988403,
+      "learning_rate": 2.097118463180363e-05,
+      "loss": 0.4093,
+      "step": 650
+    },
+    {
+      "epoch": 0.6717850287907869,
+      "grad_norm": 1.4985594749450684,
+      "learning_rate": 1.830309498399146e-05,
+      "loss": 0.4118,
+      "step": 700
+    },
+    {
+      "epoch": 0.7197696737044146,
+      "grad_norm": 1.6520227193832397,
+      "learning_rate": 1.5635005336179295e-05,
+      "loss": 0.3923,
+      "step": 750
+    },
+    {
+      "epoch": 0.7677543186180422,
+      "grad_norm": 1.6517823934555054,
+      "learning_rate": 1.2966915688367129e-05,
+      "loss": 0.4183,
+      "step": 800
     }
   ],
   "logging_steps": 50,