Training in progress, epoch 3, checkpoint

last-checkpoint/README.md

@@ -93,7 +93,7 @@ model-index:
       type: validation_eval
     metrics:
     - type: cosine_accuracy
-      value: 0.9627359509468079
+      value: 0.9635822772979736
       name: Cosine Accuracy
 ---
 
@@ -198,7 +198,7 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| **cosine_accuracy** | **0.9627** |
+| **cosine_accuracy** | **0.9636** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -433,6 +433,7 @@ You can finetune this model on your own dataset.
 | None  | 0    | -             | 0.9213                          |
 | 1.0   | 835  | 26.455        | 0.9581                          |
 | 2.0   | 1670 | 12.0476       | 0.9627                          |
+| 3.0   | 2505 | 7.3661        | 0.9636                          |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d08e25a63b01b202f572d87ae4aeea67252e02e34a3469fcdc5c131dcbc88b1
+oid sha256:fea8b27fc08c6cd4a81a04c6c85caa5c5b9ceb8806192e42d3abf17bc88ef907
 size 1112197096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176ab230b15d6519afab3210be0460d7980f81666c095aac796177b564d7c1e9
+oid sha256:d685da34be96e414f20c69a2228a75a254ed83336c1c978188c57288cf53f8ed
 size 1712830650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e608683bf0a0df17239b942462c855799007b17c46c86ac75de346d7f8c13f07
+oid sha256:4f423783f8bcf859aff29ed45246cdfe4d5c18ef35d5279c118ba2ed968fd10b
 size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72542e73ffe194c38cfae2e78e12be45749d8876a8ac01e53f8ee3ee8ccc453
+oid sha256:db3b99e61d88d736baa6fd0e3a94f01e1acd99229821cfd2422e29d6875b89ef
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6e95f099c43357b5edfafb88b378a3076c67a8db5b80d9451dfee7962b8f61
+oid sha256:26865453805f3926bdbe81c531a088d85786e5a73d544511eef68b50ddb4e9da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1670,
-  "best_metric": 0.9627359509468079,
-  "best_model_checkpoint": "/kaggle/working/checkpoint-1670",
-  "epoch": 2.0,
+  "best_global_step": 2505,
+  "best_metric": 0.9635822772979736,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-2505",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1670,
+  "global_step": 2505,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -40,6 +40,22 @@
       "eval_steps_per_second": 0.0,
       "eval_validation_eval_cosine_accuracy": 0.9627359509468079,
       "step": 1670
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 86.45789337158203,
+      "learning_rate": 1.666253638382422e-05,
+      "loss": 7.3661,
+      "step": 2505
+    },
+    {
+      "epoch": 3.0,
+      "eval_model_preparation_time": 0.0028,
+      "eval_runtime": 147.6683,
+      "eval_samples_per_second": 0.0,
+      "eval_steps_per_second": 0.0,
+      "eval_validation_eval_cosine_accuracy": 0.9635822772979736,
+      "step": 2505
     }
   ],
   "logging_steps": 500,