Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b612a580cfac2c9686c1f1d37b4adf5e976ef018b8ab50b7f31ccbb8be979e
+oid sha256:7dd6675074c740b3bba741c2f1786316f7285bc061686a11549791bebfdb905c
 size 267832560

run-0/checkpoint-428/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d304ced2b72473920ee6d108d047640fdd6f1cc7fb601a26c3c3c233797e45
+size 267832560

run-0/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526aa2a1a3875efd49b6272fad722cded93adde0888a05c0433307ac5be5a981
+size 535727290

run-0/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0696474934cbf19c8bab7f79c8c16173fce7b6abf29bc5a1ca8355a37b7a641c
+size 14244

run-0/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02754b7856a22ca7a3a7c3514b1e0a02fd8edd40119c08b1d07a2663024e30ae
+size 1064

run-0/checkpoint-428/special_tokens_map.json

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

run-0/checkpoint-428/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-0/checkpoint-428/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.29149823245901346,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5878534317016602,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.9866,
+      "eval_samples_per_second": 525.026,
+      "eval_steps_per_second": 65.943,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8576925992965698,
+      "eval_matthews_correlation": 0.29149823245901346,
+      "eval_runtime": 2.7291,
+      "eval_samples_per_second": 382.182,
+      "eval_steps_per_second": 48.002,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.143357679659004e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-0/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6380478865745a4c7273017600e79375bf0566f3c411b9e3401106e044e923ec
+size 4984

run-1/checkpoint-214/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c7324d08fd9c45ad1cf8112df6e9d1bc41bf754faf223c8cc0e9af9f2d0451
+oid sha256:7dd6675074c740b3bba741c2f1786316f7285bc061686a11549791bebfdb905c
 size 267832560

run-1/checkpoint-214/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8820a6bb240aa856e8b8e2198c55f9dba81381fd31122efc444aa9a365bf641
+oid sha256:1ebf721c07596b09e47e1e65f7e3b372c2077ae0a008050e3e0d81ac797acda2
 size 535727290

run-1/checkpoint-214/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ceacee9a836f1235b0eff6af56f1cecebc9b9060cdcb253fdd90207c1a2c736
+oid sha256:5ef9814402b010841f9a7c0a3fdf3172cbc65786e21016179eade714928d7525
 size 14244

run-1/checkpoint-214/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd55d95f04a4cf861a732354cad9aadc05a736a70dcb0a01514d4da7b324f10
+oid sha256:f5945272078f2b0fe4c23ce07354940a7bc1cc3ba205aee4867e984efc6f37e8
 size 1064

run-1/checkpoint-214/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-107",
-  "epoch": 2.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-214",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 214,
   "is_hyper_param_search": true,
@@ -10,35 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6247433423995972,
+      "eval_loss": 0.652801513671875,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9442,
-      "eval_samples_per_second": 1104.683,
-      "eval_steps_per_second": 138.747,
-      "step": 107
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.594637393951416,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 1.6592,
-      "eval_samples_per_second": 628.629,
-      "eval_steps_per_second": 78.955,
+      "eval_runtime": 0.9485,
+      "eval_samples_per_second": 1099.598,
+      "eval_steps_per_second": 138.109,
       "step": 214
     }
   ],
   "logging_steps": 500,
-  "max_steps": 428,
+  "max_steps": 214,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0170873699122056e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 1.730769214324866e-06,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 4,
-    "seed": 16
+    "seed": 2
   }
 }

run-1/checkpoint-214/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb79b974e6c474cc87583dfff5dff5d9e65017523a76923a915ff714cc13595c
+oid sha256:871e5c18201ad901886bf00e2e13b444a5b796f055d4018a5c080d3cd77ec364
 size 4984

runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709061726.d3d09c0dfc16.836.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a593dc3a80c1f2ec7eb1e7f59e0336a8bb6d58012472a47de885482e5d7eb5b
+size 5227

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6380478865745a4c7273017600e79375bf0566f3c411b9e3401106e044e923ec
+oid sha256:871e5c18201ad901886bf00e2e13b444a5b796f055d4018a5c080d3cd77ec364
 size 4984