Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ef3166d33f4087cf92924c901ede52e6f409d2415cf754cddbf2b1a91212d4
+oid sha256:9ece4d7e70a495bcfb38baf7222a68f0addb014ebe99597f2368f1ef4789351b
 size 267832560

run-2/checkpoint-4276/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": "4.39.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ece4d7e70a495bcfb38baf7222a68f0addb014ebe99597f2368f1ef4789351b
+size 267832560

run-2/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed21fd9ddcd87176bd671e9226d38243cfee31865cc6495856cecff56b88e975
+size 535727290

run-2/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61a246d0a6581c82fe4876987da0fa2112a41aa062420f2d0b74fe07b53d3b1
+size 14244

run-2/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3411e0b71c9232fbc940da6e5f69e4a4d642a976436016bd6081d6be20e8739
+size 1064

run-2/checkpoint-4276/special_tokens_map.json

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

run-2/checkpoint-4276/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-2/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.5049093009936784,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 12.893019676208496,
+      "learning_rate": 1.0194042691078977e-05,
+      "loss": 0.6006,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 15.821282386779785,
+      "learning_rate": 8.844195936433985e-06,
+      "loss": 0.5451,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.875489234924316,
+      "learning_rate": 7.494349181788993e-06,
+      "loss": 0.5134,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 27.784305572509766,
+      "learning_rate": 6.144502427144001e-06,
+      "loss": 0.5264,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4990427494049072,
+      "eval_matthews_correlation": 0.4824335154846928,
+      "eval_runtime": 0.7747,
+      "eval_samples_per_second": 1346.334,
+      "eval_steps_per_second": 85.195,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 7.632354736328125,
+      "learning_rate": 4.79465567249901e-06,
+      "loss": 0.4256,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.4190431833267212,
+      "learning_rate": 3.444808917854018e-06,
+      "loss": 0.4128,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 4.315122604370117,
+      "learning_rate": 2.094962163209027e-06,
+      "loss": 0.4795,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 53.12971115112305,
+      "learning_rate": 7.451154085640354e-07,
+      "loss": 0.4722,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7950040698051453,
+      "eval_matthews_correlation": 0.5049093009936784,
+      "eval_runtime": 0.8018,
+      "eval_samples_per_second": 1300.873,
+      "eval_steps_per_second": 82.318,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 65223117962472.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1543889445723968e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-2/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5368d6f9ef168d66868ee1d65c8303650d37e33738d8551bd3731dc6ff2d507e
+size 4984

runs/Mar23_02-09-13_2ed998b56e2c/events.out.tfevents.1711160890.2ed998b56e2c.195.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec1ba0fe611729352b0647ee16b063ea28ce58cf3959eb557792ffbe9e66fd56
-size 5982
+oid sha256:aa656d845e6f8b71c34817f330fbca093711da9205e21714ace4a78e1345912c
+size 7304