Training in progress, step 162, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca06cfe440d39a1e1fb871aaf6fc6d59c82997564474bfffd9e950e458625b3
+oid sha256:567f3dbf4ab3bb972f02a97f4434faa92ca020703b61912d50a8d17145bcb3bb
 size 2362528

last-checkpoint/README.md

@@ -524,6 +524,18 @@ You can finetune this model on your own dataset.
 | 2.7407 | 148  | 0.2397        | -               | -                            |
 | 2.7593 | 149  | 0.2448        | -               | -                            |
 | 2.7778 | 150  | 0.2431        | 0.0084          | 0.9791                       |
+| 2.7963 | 151  | 0.2408        | -               | -                            |
+| 2.8148 | 152  | 0.2394        | -               | -                            |
+| 2.8333 | 153  | 0.2317        | -               | -                            |
+| 2.8519 | 154  | 0.2367        | -               | -                            |
+| 2.8704 | 155  | 0.2375        | -               | -                            |
+| 2.8889 | 156  | 0.2351        | -               | -                            |
+| 2.9074 | 157  | 0.2448        | -               | -                            |
+| 2.9259 | 158  | 0.229         | -               | -                            |
+| 2.9444 | 159  | 0.2274        | -               | -                            |
+| 2.9630 | 160  | 0.2313        | -               | -                            |
+| 2.9815 | 161  | 0.2269        | -               | -                            |
+| 3.0    | 162  | 0.2298        | -               | -                            |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d6db61b0b7d9d1bae9c4b714748a0c0adac2ef774f2a74f674fcd39f83698
+oid sha256:e4e0b4ac780e12a3493da36fc06dc5bc0e1804d77f6fc3177c7591fbd03d4924
 size 735216376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2807a9acc950ff1e7baa887af2e4f7a2e9ba0cf01a47099d2a1023bfc494023a
+oid sha256:58dcd91962a421b3bd1f895143c1cf93caf62cf37d057c669274d148c8f016a2
 size 1475248442

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b074fcbd4de7291eb93634857c7ea7aadd27bba5e33cd735740b9c7250484019
+oid sha256:18047793e069e796780116e68c886aefe3991c2b5d10deed7f9aaac307ff5268
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7777777777777777,
+  "epoch": 3.0,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 162,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1111,6 +1111,90 @@
       "eval_steps_per_second": 1.088,
       "eval_test_triplet_cosine_accuracy": 0.9791250228881836,
       "step": 150
+    },
+    {
+      "epoch": 2.7962962962962963,
+      "grad_norm": 0.24518300592899323,
+      "learning_rate": 5.741444866920153e-06,
+      "loss": 0.2408,
+      "step": 151
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.3211422264575958,
+      "learning_rate": 5.779467680608365e-06,
+      "loss": 0.2394,
+      "step": 152
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.2589081823825836,
+      "learning_rate": 5.817490494296578e-06,
+      "loss": 0.2317,
+      "step": 153
+    },
+    {
+      "epoch": 2.851851851851852,
+      "grad_norm": 0.26596707105636597,
+      "learning_rate": 5.855513307984791e-06,
+      "loss": 0.2367,
+      "step": 154
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.25816991925239563,
+      "learning_rate": 5.8935361216730046e-06,
+      "loss": 0.2375,
+      "step": 155
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.24328885972499847,
+      "learning_rate": 5.931558935361217e-06,
+      "loss": 0.2351,
+      "step": 156
+    },
+    {
+      "epoch": 2.9074074074074074,
+      "grad_norm": 0.2682211995124817,
+      "learning_rate": 5.9695817490494305e-06,
+      "loss": 0.2448,
+      "step": 157
+    },
+    {
+      "epoch": 2.925925925925926,
+      "grad_norm": 0.23873576521873474,
+      "learning_rate": 6.007604562737643e-06,
+      "loss": 0.229,
+      "step": 158
+    },
+    {
+      "epoch": 2.9444444444444446,
+      "grad_norm": 0.23763084411621094,
+      "learning_rate": 6.0456273764258555e-06,
+      "loss": 0.2274,
+      "step": 159
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.24440748989582062,
+      "learning_rate": 6.083650190114069e-06,
+      "loss": 0.2313,
+      "step": 160
+    },
+    {
+      "epoch": 2.9814814814814814,
+      "grad_norm": 0.24925145506858826,
+      "learning_rate": 6.121673003802282e-06,
+      "loss": 0.2269,
+      "step": 161
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2385304570198059,
+      "learning_rate": 6.159695817490496e-06,
+      "loss": 0.2298,
+      "step": 162
     }
   ],
   "logging_steps": 1.0,
@@ -1125,7 +1209,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }