Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7dacefa47d13581c82efb0d23b095435044d5715b7f290f734d02fe1c59c08
+oid sha256:9adfec8c8f9633308a42ae95480e7b4a6c75272196f8b2bc9b03035d7301532f
 size 267832560

run-8/checkpoint-108/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-8/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4feea775c8db3a30650b8c9a2d93307b004a08fb563cf7cb6232d7bc1385780c
+size 267832560

run-8/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1684acf04d3997a4fa1808bfec452583f041bfd261036e0704e16f3792369ea4
+size 535724410

run-8/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88e827600293d68e0d3a74ae63b7019c8e3e6870b358f191616e6f9c7d37e5b
+size 14054

run-8/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1aeecc6e4c86e42a7b5950100a1a08c2b286f10d30f79f209f91482e6f296a6
+size 1064

run-8/checkpoint-108/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-108/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-54",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6624963283538818,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.9551,
+      "eval_samples_per_second": 1092.085,
+      "eval_steps_per_second": 69.106,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6530647277832031,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.027,
+      "eval_samples_per_second": 1015.572,
+      "eval_steps_per_second": 64.264,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9630023719869403e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 21
+  }
+}

run-8/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9219795ef130879b5fcf86461daa6506b0a3bc4344f4550efc9ceece943bb691
+size 4920

run-9/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95d6a53cd3cf9851d9a72187a530371ca62b48efdcb5a98a888c9dc5b402c9a
+oid sha256:9adfec8c8f9633308a42ae95480e7b4a6c75272196f8b2bc9b03035d7301532f
 size 267832560

run-9/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19b1b3fedc6f0891cd478c187787e71cafa41a894610d3c22227856e60c2d6e
+oid sha256:072cb6d0d31a19621fdc28ffd4390aec789063ea261a817476d2e75773ccf49a
 size 535724410

run-9/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62d6467f8b2d76d59a9606222f7bd6658470db8dfbf182c5ee453630bb4bc88
+oid sha256:5922d093e10f3df73a5d519448460cf17ceff9406d825234bfcc1c42bed46ae5
 size 13990

run-9/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ec11f521fd55421a62cc26bf6be888d453dc2268855595cf5b75be21773bc2
+oid sha256:01ff8df2908cf4a1e17a4ac29b84f2f64803b83d79006abeca99fd992957add3
 size 1064

run-9/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-27",
-  "epoch": 2.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-54",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,35 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6144887208938599,
+      "eval_loss": 0.6085762977600098,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8914,
-      "eval_samples_per_second": 1170.101,
-      "eval_steps_per_second": 74.043,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.6105712652206421,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9967,
-      "eval_samples_per_second": 1046.411,
-      "eval_steps_per_second": 66.216,
+      "eval_runtime": 0.9605,
+      "eval_samples_per_second": 1085.879,
+      "eval_steps_per_second": 68.713,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0177755080206268e-05,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 32,
-    "seed": 12
+    "learning_rate": 2.5955692371913252e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 18
   }
 }

run-9/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb524e909b3d74efd270d4b5afce33eb2a12bcfb5df4183ecdb45c59b1d80cf
+oid sha256:f33d694a50a1d5e33379f611a36e27ac1c096bcc507070ae5cbb1ebf8bc65e44
 size 4920

runs/Mar08_16-22-38_MBP-van-RV.home/events.out.tfevents.1709914934.MBP-van-RV.home.1470.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503903c44db61e2651e5990a4dfc1fda4213767d28a345f78075ff47eddcd335
+size 5223

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9219795ef130879b5fcf86461daa6506b0a3bc4344f4550efc9ceece943bb691
+oid sha256:f33d694a50a1d5e33379f611a36e27ac1c096bcc507070ae5cbb1ebf8bc65e44
 size 4920