Training completed!

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2723
-- Accuracy: 0.9519
+- Accuracy: 0.9513
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5073        | 1.0   | 1907 | 0.3478          | 0.9326   |
-| 0.2369        | 2.0   | 3814 | 0.2873          | 0.9487   |
-| 0.1934        | 3.0   | 5721 | 0.2723          | 0.9519   |
+| 0.5075        | 1.0   | 1907 | 0.3479          | 0.9335   |
+| 0.2369        | 2.0   | 3814 | 0.2871          | 0.9487   |
+| 0.1935        | 3.0   | 5721 | 0.2723          | 0.9513   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ced43b8a0b6554d61567483f3369efac6b44d8c7f8babe48d3d809889d62a3
+oid sha256:055cb95e2546f762bcd19111d922daa8d28c2a770f597006317ad45d08121ede
 size 268290900

run-0/checkpoint-1000/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d099ab42b59369bd97c9d9136c82ab167a50001e719092050b8568e86c85081b
+oid sha256:f152acf9df496a52a6ff0b4c531789ca2104ad3164cf46baa16f82d491590204
 size 268290900

run-0/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3fb19e26c3090ed72434fbd7df7fa10a2174918b5d20737edc027c2592ff9e4
+oid sha256:f715d21d56cef446f00d2e5cbc41a7aa6581ad22a74ffdac52bce1cf0dabed1a
 size 536641018

run-0/checkpoint-1000/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 0.5243838489774515,
@@ -11,16 +10,16 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     }
   ],
@@ -45,8 +44,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-1500/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6857d4e392b5a4122ef8fd39750e4aa63392725ff38fca121bb5c0a3e3206a
+oid sha256:de6d860cb7b072a34d199ca1362e21f6f7248106c9630b2eb96134056579f060
 size 268290900

run-0/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b040192653efebacf17873c7a4fb5932526030f7a07644fe289ecd1bee20e5b7
+oid sha256:fe8d51c6d0bf45ff582e531102a35885bdd5258edc99b585aed00b91c33efae8
 size 536641018

run-0/checkpoint-1500/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 0.7865757734661772,
@@ -11,23 +10,23 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     }
   ],
@@ -52,8 +51,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-2000/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1ddcd3aa971bfdb7e2477d4e689adaa23a8b925c45edd2efefe40192f2ac49
+oid sha256:74d0155612f84102fe3ee79e14f9a2c2836ede41d44ba4ba356fb4acb5bf88f5
 size 268290900

run-0/checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b80c14abc4038ec22a4c59fcd3c1e6be0576f9880f7332a69b9e5496a9cbcfc
+oid sha256:2b6ef85afcdbde397f3df55b90c5c87211dd2aa7ddafbb2025abd3555389b4e7
 size 536641018

run-0/checkpoint-2000/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.048767697954903,
@@ -11,39 +10,39 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287096774193548,
-      "eval_loss": 0.31620076298713684,
-      "eval_runtime": 11.4103,
-      "eval_samples_per_second": 271.684,
-      "eval_steps_per_second": 34.004,
+      "eval_accuracy": 0.9325806451612904,
+      "eval_loss": 0.4170600473880768,
+      "eval_runtime": 12.0659,
+      "eval_samples_per_second": 256.923,
+      "eval_steps_per_second": 32.157,
       "step": 1907
     },
     {
       "epoch": 1.048767697954903,
-      "grad_norm": 0.9413483738899231,
+      "grad_norm": 0.9997719526290894,
       "learning_rate": 2.3780807551127425e-05,
-      "loss": 0.3371,
+      "loss": 0.4093,
       "step": 2000
     }
   ],
@@ -68,8 +67,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-2500/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-2500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98045d2335151c9708da38002a16b296cc60a490b48013d1d038c10aee3d1547
+oid sha256:90215328d7d593d62089eeaf8312cee74715cd005752a8d9fce1a549b95d57a1
 size 268290900

run-0/checkpoint-2500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cffb16e9ab425e0ca57b48ab9f779379c21a1ffc92d8af5ec3fbd679989c2e1
+oid sha256:20e6c38fcbc55c9beca0bf3ce36fccd135ac59ed633a56fcdd6ef7c869efcdf3
 size 536641018

run-0/checkpoint-2500/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.3109596224436286,
@@ -11,46 +10,46 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287096774193548,
-      "eval_loss": 0.31620076298713684,
-      "eval_runtime": 11.4103,
-      "eval_samples_per_second": 271.684,
-      "eval_steps_per_second": 34.004,
+      "eval_accuracy": 0.9325806451612904,
+      "eval_loss": 0.4170600473880768,
+      "eval_runtime": 12.0659,
+      "eval_samples_per_second": 256.923,
+      "eval_steps_per_second": 32.157,
       "step": 1907
     },
     {
       "epoch": 1.048767697954903,
-      "grad_norm": 0.9413483738899231,
+      "grad_norm": 0.9997719526290894,
       "learning_rate": 2.3780807551127425e-05,
-      "loss": 0.3371,
+      "loss": 0.4093,
       "step": 2000
     },
     {
       "epoch": 1.3109596224436286,
-      "grad_norm": 0.5355716943740845,
+      "grad_norm": 0.7809360027313232,
       "learning_rate": 1.7226009438909284e-05,
-      "loss": 0.2077,
+      "loss": 0.2884,
       "step": 2500
     }
   ],
@@ -75,8 +74,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-2500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-3000/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-3000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04364e7a046950a1060aeba15eb06223ba7b6d8f12360fd83a07ac225afc4aea
+oid sha256:281449ff956775ab7f9f6d2d52b881df5b7e1249d29af1e37c9b6cf039ce2c49
 size 268290900

run-0/checkpoint-3000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaedd8657a8b44fb7f01e5fe00ce0702995d2127243c3fc9b63399331556c941
+oid sha256:ccb6ecddea3666b0bf588b806481cd793ddf6a666de1ca08831e998f0cbe501f
 size 536641018

run-0/checkpoint-3000/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.5731515469323545,
@@ -11,53 +10,53 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287096774193548,
-      "eval_loss": 0.31620076298713684,
-      "eval_runtime": 11.4103,
-      "eval_samples_per_second": 271.684,
-      "eval_steps_per_second": 34.004,
+      "eval_accuracy": 0.9325806451612904,
+      "eval_loss": 0.4170600473880768,
+      "eval_runtime": 12.0659,
+      "eval_samples_per_second": 256.923,
+      "eval_steps_per_second": 32.157,
       "step": 1907
     },
     {
       "epoch": 1.048767697954903,
-      "grad_norm": 0.9413483738899231,
+      "grad_norm": 0.9997719526290894,
       "learning_rate": 2.3780807551127425e-05,
-      "loss": 0.3371,
+      "loss": 0.4093,
       "step": 2000
     },
     {
       "epoch": 1.3109596224436286,
-      "grad_norm": 0.5355716943740845,
+      "grad_norm": 0.7809360027313232,
       "learning_rate": 1.7226009438909284e-05,
-      "loss": 0.2077,
+      "loss": 0.2884,
       "step": 2500
     },
     {
       "epoch": 1.5731515469323545,
-      "grad_norm": 2.629396915435791,
+      "grad_norm": 4.421374797821045,
       "learning_rate": 1.0671211326691138e-05,
-      "loss": 0.1636,
+      "loss": 0.2488,
       "step": 3000
     }
   ],
@@ -82,8 +81,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-3000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-3500/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-3500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2ce664011ba87ab9663ab8c070402b10beb55ca174395a5ea14822c54034af
+oid sha256:0e91bc2b10359e272c4f8096503f70d5015a72f4cb9da2f35045b19540a6869e
 size 268290900

run-0/checkpoint-3500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480d9761cf0f5d434fc79551c19392795f2c90d5609c0945866a8e438103999b
+oid sha256:78074bd1f550e0456f1424fdfa5bd46bdd054bbe5e63b7ff796faa36a0dd9f6b
 size 536641018

run-0/checkpoint-3500/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.8353434714210803,
@@ -11,60 +10,60 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287096774193548,
-      "eval_loss": 0.31620076298713684,
-      "eval_runtime": 11.4103,
-      "eval_samples_per_second": 271.684,
-      "eval_steps_per_second": 34.004,
+      "eval_accuracy": 0.9325806451612904,
+      "eval_loss": 0.4170600473880768,
+      "eval_runtime": 12.0659,
+      "eval_samples_per_second": 256.923,
+      "eval_steps_per_second": 32.157,
       "step": 1907
     },
     {
       "epoch": 1.048767697954903,
-      "grad_norm": 0.9413483738899231,
+      "grad_norm": 0.9997719526290894,
       "learning_rate": 2.3780807551127425e-05,
-      "loss": 0.3371,
+      "loss": 0.4093,
       "step": 2000
     },
     {
       "epoch": 1.3109596224436286,
-      "grad_norm": 0.5355716943740845,
+      "grad_norm": 0.7809360027313232,
       "learning_rate": 1.7226009438909284e-05,
-      "loss": 0.2077,
+      "loss": 0.2884,
       "step": 2500
     },
     {
       "epoch": 1.5731515469323545,
-      "grad_norm": 2.629396915435791,
+      "grad_norm": 4.421374797821045,
       "learning_rate": 1.0671211326691138e-05,
-      "loss": 0.1636,
+      "loss": 0.2488,
       "step": 3000
     },
     {
       "epoch": 1.8353434714210803,
-      "grad_norm": 0.37704744935035706,
+      "grad_norm": 0.42712241411209106,
       "learning_rate": 4.116413214472994e-06,
-      "loss": 0.1548,
+      "loss": 0.2439,
       "step": 3500
     }
   ],
@@ -89,8 +88,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-3500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-3814/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-3814/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15c0665e1219a2f7d98b739a0d779a82e3a31ad78faabdc34b748450eec59127
+oid sha256:a7e8791dc546d9797ab4103d61f4e4d93e080914ce9c625450d05de7d416c43d
 size 268290900

run-0/checkpoint-3814/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91bb83da71d4a2bf468a5035f04c27a2bf3d8d721f03e8efd9e20ea9818b0760
+oid sha256:a531c38b680ebe63660896f3953a0453b1f9e22236fb476bacabdebadc2036f4
 size 536641018

run-0/checkpoint-3814/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 2.0,
@@ -11,60 +10,60 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     },
     {
       "epoch": 0.5243838489774515,
-      "grad_norm": 4.833480358123779,
+      "grad_norm": 5.755916118621826,
       "learning_rate": 3.689040377556371e-05,
-      "loss": 1.0736,
+      "loss": 1.2205,
       "step": 1000
     },
     {
       "epoch": 0.7865757734661772,
-      "grad_norm": 8.822789192199707,
+      "grad_norm": 12.255783081054688,
       "learning_rate": 3.0335605663345567e-05,
-      "loss": 0.5549,
+      "loss": 0.6277,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9287096774193548,
-      "eval_loss": 0.31620076298713684,
-      "eval_runtime": 11.4103,
-      "eval_samples_per_second": 271.684,
-      "eval_steps_per_second": 34.004,
+      "eval_accuracy": 0.9325806451612904,
+      "eval_loss": 0.4170600473880768,
+      "eval_runtime": 12.0659,
+      "eval_samples_per_second": 256.923,
+      "eval_steps_per_second": 32.157,
       "step": 1907
     },
     {
       "epoch": 1.048767697954903,
-      "grad_norm": 0.9413483738899231,
+      "grad_norm": 0.9997719526290894,
       "learning_rate": 2.3780807551127425e-05,
-      "loss": 0.3371,
+      "loss": 0.4093,
       "step": 2000
     },
     {
       "epoch": 1.3109596224436286,
-      "grad_norm": 0.5355716943740845,
+      "grad_norm": 0.7809360027313232,
       "learning_rate": 1.7226009438909284e-05,
-      "loss": 0.2077,
+      "loss": 0.2884,
       "step": 2500
     },
     {
       "epoch": 1.5731515469323545,
-      "grad_norm": 2.629396915435791,
+      "grad_norm": 4.421374797821045,
       "learning_rate": 1.0671211326691138e-05,
-      "loss": 0.1636,
+      "loss": 0.2488,
       "step": 3000
     },
     {
       "epoch": 1.8353434714210803,
-      "grad_norm": 0.37704744935035706,
+      "grad_norm": 0.42712241411209106,
       "learning_rate": 4.116413214472994e-06,
-      "loss": 0.1548,
+      "loss": 0.2439,
       "step": 3500
     }
   ],
@@ -89,8 +88,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-3814/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

run-0/checkpoint-500/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -325,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.48.3",
   "vocab_size": 30522
 }

run-0/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e0c0ef2d0e2e5cfc483df3a567da8929db73de92b23eb4688172b6a2b774f1
+oid sha256:b39a757a6d412d6ab5247c086594f40c4504b6c4d65ec80d8980bcaf95a7264c
 size 268290900

run-0/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495c48354ebc74ab706d341fcf6ab9a783e98cacacdad12803c857bdf6035437
+oid sha256:0c034801d1c05d6c49aec861919744a6ddda54fbe83b48c81751557f64fcccb0
 size 536641018

run-0/checkpoint-500/trainer_state.json

@@ -1,5 +1,4 @@
 {
-  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 0.26219192448872575,
@@ -11,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.26219192448872575,
-      "grad_norm": 5.230668544769287,
+      "grad_norm": 6.470641136169434,
       "learning_rate": 4.344520188778186e-05,
-      "loss": 2.5366,
+      "loss": 3.0539,
       "step": 500
     }
   ],
@@ -38,8 +37,8 @@
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6285062161593025,
+    "alpha": 0.7623327118000192,
     "num_train_epochs": 2,
-    "temperature": 19
+    "temperature": 2
   }
 }

run-0/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc2741da77e84d989ec3be6a5121a81316f5baed2c3186d5b1f85ec054c42c7
+oid sha256:7fa689c7463480003e7ea6184a75c01c2bcaff7c0590f5c865b32ed995ba2c41
 size 5368

runs/May10_19-46-07_Haris-MacBook-Air-3.local/events.out.tfevents.1746900470.Haris-MacBook-Air-3.local.36963.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97fd17bcd3a43ec5857e651fd1cdf3bf4de4fd047078bb0d3daa22ec5062848
+size 14994

runs/May10_19-46-07_Haris-MacBook-Air-3.local/events.out.tfevents.1746900976.Haris-MacBook-Air-3.local.36963.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53388a006f6f3bbbf60af40dfbd3e0d93972ffb92d57526d210ba64ec2930f67
+size 15022

runs/May13_20-23-41_Haris-MacBook-Air-3.local/events.out.tfevents.1747182226.Haris-MacBook-Air-3.local.32376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24904e9a38b37df03be66a96e81f50f1613d95a60ed52b8c66ff81d672e8aff
+size 16161

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46dd637c69cb579672e516450fcd33b7ff7bed8ee49f427d8775178d9f158db
+oid sha256:46d9715ec9d33515dbe5394ee668f99b27d3f88a8a0e6532950c69dcdca41748
 size 5368