Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa9b34bd7baaa4ef423f6a45fa951ded687f80db95da761f16626b401bd91b4
+oid sha256:37466992bbddbf0c2d8919ef9c44899c3cc56d8165a104a87d103973ea1d4057
 size 267832560

run-0/checkpoint-8552/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37466992bbddbf0c2d8919ef9c44899c3cc56d8165a104a87d103973ea1d4057
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3917a70988c2cc68ecbb259317815607ded64fdc38f7f852cb48c4dc92126267
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a69cc9c8417161a72d6296931407c41855d5e8e03476149541fce72fa9ad9c
+size 14244

run-0/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c57534261bcecf088a6869e67f4ae407ca10c2e74c52f6c8d05aa19d366b3081
+size 1064

run-0/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.5089318947112005,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-6414",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 7.735239505767822,
+      "learning_rate": 2.6390165938520652e-05,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 7.558316707611084,
+      "learning_rate": 2.5095260838495103e-05,
+      "loss": 0.6036,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 13.932698249816895,
+      "learning_rate": 2.3800355738469558e-05,
+      "loss": 0.5557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 34.20298767089844,
+      "learning_rate": 2.250545063844401e-05,
+      "loss": 0.5638,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5530476570129395,
+      "eval_matthews_correlation": 0.42688451387061943,
+      "eval_runtime": 0.7717,
+      "eval_samples_per_second": 1351.602,
+      "eval_steps_per_second": 85.528,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 144.64892578125,
+      "learning_rate": 2.121054553841846e-05,
+      "loss": 0.4739,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 2.190452814102173,
+      "learning_rate": 1.9915640438392912e-05,
+      "loss": 0.4525,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 0.23798206448554993,
+      "learning_rate": 1.8620735338367367e-05,
+      "loss": 0.4923,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 0.12765388190746307,
+      "learning_rate": 1.732583023834182e-05,
+      "loss": 0.487,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7405813336372375,
+      "eval_matthews_correlation": 0.4412540944135295,
+      "eval_runtime": 0.7667,
+      "eval_samples_per_second": 1360.289,
+      "eval_steps_per_second": 86.078,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 117.8426513671875,
+      "learning_rate": 1.6030925138316273e-05,
+      "loss": 0.4266,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 33.24169158935547,
+      "learning_rate": 1.4736020038290725e-05,
+      "loss": 0.3034,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 0.07295671850442886,
+      "learning_rate": 1.344111493826518e-05,
+      "loss": 0.3253,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 0.11024939268827438,
+      "learning_rate": 1.2146209838239631e-05,
+      "loss": 0.3189,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9346533417701721,
+      "eval_matthews_correlation": 0.5089318947112005,
+      "eval_runtime": 0.7664,
+      "eval_samples_per_second": 1360.979,
+      "eval_steps_per_second": 86.121,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 21.940523147583008,
+      "learning_rate": 1.0851304738214084e-05,
+      "loss": 0.3316,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 0.016046803444623947,
+      "learning_rate": 9.556399638188537e-06,
+      "loss": 0.1546,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 0.03574672341346741,
+      "learning_rate": 8.26149453816299e-06,
+      "loss": 0.1826,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 0.02293764054775238,
+      "learning_rate": 6.966589438137444e-06,
+      "loss": 0.2169,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 0.022199153900146484,
+      "learning_rate": 5.6716843381118964e-06,
+      "loss": 0.2425,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1374236345291138,
+      "eval_matthews_correlation": 0.4779281382373973,
+      "eval_runtime": 0.7806,
+      "eval_samples_per_second": 1336.237,
+      "eval_steps_per_second": 84.556,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 138709407366888.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7685071038546197e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 15
+  }
+}

run-0/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b964aa5aa9339d0b8aefc9da6b043087cadf17ef5539248b4bcb2cf628431848
+size 5240

runs/Aug17_02-12-22_2566451b250f/events.out.tfevents.1723861339.2566451b250f.233.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2d8ba6705551507198eb3f087e0effa9af4b6377cef566f14e9dd6e2bb5007
-size 8642
+oid sha256:f26cb2a25e6337b042d07aa2b65a39e0ad048ee20b005afa87424d971eef2ae1
+size 9821