Training in progress, epoch 2, checkpoint

last-checkpoint/README.md

@@ -67,7 +67,7 @@ model-index:
       type: validation_eval
     metrics:
     - type: cosine_accuracy
-      value: 0.9636484980583191
+      value: 0.9669108986854553
       name: Cosine Accuracy
 ---
 
@@ -172,7 +172,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9636** |
+| **cosine_accuracy** | **0.9669** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -404,6 +404,7 @@ You can finetune this model on your own dataset.
 |:-----:|:----:|:-------------:|:-------------------------------:|
 | None  | 0    | -             | 0.9376                          |
 | 1.0   | 3374 | 22.5359       | 0.9636                          |
+| 2.0   | 6748 | 12.387        | 0.9669                          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea72e32d9345b2f2f07d6ddeafd6fd903ecf1137d390067a59f9bd50bdd68b10
+oid sha256:47f45b709189f10005c531c512d16fb09ef3d6e63e17ec739dab661444f1c7e1
 size 1112197096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94a32bd57510e6fdd0c6e161c53d8d56476df292d3c91195aea1abc5be67f48
+oid sha256:d835f6164cae9cfcc79e04be75997ec26b3c808d84e04c121ad4cbb6008cdc6b
 size 1712831051

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e87d30a6472bfb5fb12962857644296ba62093a7692ecaa4c1d9a0b0a0d7980
+oid sha256:cfac7d3bc2b72378c1bf4f5d3aaef89d3e826b5add66b63f70b5a6a7445108f5
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0baddc6906d196aa3d67aa37602fac789ffa01c6f418b5f7517073d2468875
+oid sha256:26071fac0a5a2d20a87fc638a2db503999ac83894881340f96948ea63414522f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ea43e83b5d60e868479c2abdf8e8df79b9860ef80bf01971acb921cbf0d2ee
+oid sha256:6a097af662cf910e136a0a6b4d2d74f5cec8c2c42c0a692b8fa0f065b7ea1f65
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3374,
-  "best_metric": 0.9636484980583191,
-  "best_model_checkpoint": "/kaggle/working/checkpoint-3374",
-  "epoch": 1.0,
+  "best_global_step": 6748,
+  "best_metric": 0.9669108986854553,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-6748",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 3374,
+  "global_step": 6748,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,6 +24,22 @@
       "eval_steps_per_second": 0.0,
       "eval_validation_eval_cosine_accuracy": 0.9636484980583191,
       "step": 3374
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 177.7242431640625,
+      "learning_rate": 1.2150011406441293e-05,
+      "loss": 12.387,
+      "step": 6748
+    },
+    {
+      "epoch": 2.0,
+      "eval_model_preparation_time": 0.0078,
+      "eval_runtime": 142.7381,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "eval_validation_eval_cosine_accuracy": 0.9669108986854553,
+      "step": 6748
     }
   ],
   "logging_steps": 500,