Training in progress, step 1000, 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,  0.6636, -0.0516],
-#         [ 0.6636,  1.0000, -0.0845],
-#         [-0.0516, -0.0845,  1.0000]])
+# tensor([[ 1.0000,  0.6589, -0.0461],
+#         [ 0.6589,  1.0000, -0.0710],
+#         [-0.0461, -0.0710,  1.0000]])
 ```
 
 <!--
@@ -731,6 +731,10 @@ You can finetune this model on your own dataset.
 | 0.6718 | 700  | 0.4118        |
 | 0.7198 | 750  | 0.3923        |
 | 0.7678 | 800  | 0.4183        |
+| 0.8157 | 850  | 0.3991        |
+| 0.8637 | 900  | 0.3947        |
+| 0.9117 | 950  | 0.3777        |
+| 0.9597 | 1000 | 0.3942        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff756dbb38a75171525943ee07a6245096eef361b8236a195a79e2f4c43e6b40
+oid sha256:16ed94def781e3941dec110dda20c76143833c045568e9b68f20230a6ae8dd0e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519486a3681858d50acde069f580d97e5840fa5ac9d65b3f042141bd25e1cb41
+oid sha256:109c98bb23626540dc184662d8b7b94cc56388db552e4887f65978941a59d183
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f16fa28ebb8e3a1b82ca55c6cf1c0dd60b11d4021c7a97520baf445d2c84fd8
+oid sha256:f906e0b5b6d6a9c4fe87955d19f0e941b5338d2f71853b6ff2c15b409507ceee
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57a1899b276deaf9bc6c347b576a36bf470824199b1d1731a5698c732cc5649
+oid sha256:8f05941cd5d89b2195b06001cebc4cb31c0ae73bf191526abcbbf01177ebf8dc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7677543186180422,
+  "epoch": 0.9596928982725528,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,34 @@
       "learning_rate": 1.2966915688367129e-05,
       "loss": 0.4183,
       "step": 800
+    },
+    {
+      "epoch": 0.8157389635316699,
+      "grad_norm": 1.7299295663833618,
+      "learning_rate": 1.0298826040554963e-05,
+      "loss": 0.3991,
+      "step": 850
+    },
+    {
+      "epoch": 0.8637236084452975,
+      "grad_norm": 1.717519998550415,
+      "learning_rate": 7.630736392742796e-06,
+      "loss": 0.3947,
+      "step": 900
+    },
+    {
+      "epoch": 0.9117082533589251,
+      "grad_norm": 1.5044348239898682,
+      "learning_rate": 4.96264674493063e-06,
+      "loss": 0.3777,
+      "step": 950
+    },
+    {
+      "epoch": 0.9596928982725528,
+      "grad_norm": 1.5577826499938965,
+      "learning_rate": 2.294557097118463e-06,
+      "loss": 0.3942,
+      "step": 1000
     }
   ],
   "logging_steps": 50,