Training in progress, epoch 3, checkpoint

checkpoint-13884/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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
+}

checkpoint-13884/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462fe2d451f234cac3123ca3c48ee63237a0fc8aea1856a8ba0e531d0fce8ad2
+size 267832560

checkpoint-13884/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9862da8827e17b0d5e0d94f70b6e4c34959c578bb0683b05c6972f5bff3d6044
+size 535727290

checkpoint-13884/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5b93df34e20cd89220272cb3f1958ddc9aae5db2d69bf02939e9bd1fea3a43
+size 14244

checkpoint-13884/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9023c8f4d0ac3369745669544086a3739a91879ce67d485ee102472fd185e3
+size 1064

checkpoint-13884/special_tokens_map.json

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

checkpoint-13884/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]"
+}

checkpoint-13884/trainer_state.json

@@ -0,0 +1,309 @@
+{
+  "best_metric": 4.978057290827564e-07,
+  "best_model_checkpoint": "insuff_supported_arguments/checkpoint-13884",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 13884,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.03457513824105263,
+      "learning_rate": 1.9279746470757707e-05,
+      "loss": 0.1457,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0055348570458590984,
+      "learning_rate": 1.8559492941515416e-05,
+      "loss": 0.0066,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.002291068434715271,
+      "learning_rate": 1.783923941227312e-05,
+      "loss": 0.0014,
+      "step": 1500
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.003473889548331499,
+      "learning_rate": 1.7118985883030827e-05,
+      "loss": 0.0114,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0016763019375503063,
+      "learning_rate": 1.6398732353788535e-05,
+      "loss": 0.0031,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0010241195559501648,
+      "learning_rate": 1.567847882454624e-05,
+      "loss": 0.0012,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.00029286000062711537,
+      "learning_rate": 1.4958225295303948e-05,
+      "loss": 0.0,
+      "step": 3500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.0003028396749868989,
+      "learning_rate": 1.4237971766061655e-05,
+      "loss": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.0002893279306590557,
+      "learning_rate": 1.3517718236819362e-05,
+      "loss": 0.0,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "eval_NEGATIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 13620.0
+      },
+      "eval_POSITIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 6960.0
+      },
+      "eval_accuracy": 1.0,
+      "eval_loss": 5.741369932366069e-06,
+      "eval_macro avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "eval_runtime": 11.5238,
+      "eval_samples_per_second": 1785.875,
+      "eval_steps_per_second": 111.682,
+      "eval_weighted avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "step": 4628
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.0001347838988294825,
+      "learning_rate": 1.2797464707577067e-05,
+      "loss": 0.0,
+      "step": 5000
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.00012342508125584573,
+      "learning_rate": 1.2077211178334776e-05,
+      "loss": 0.0,
+      "step": 5500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.00016712247452232987,
+      "learning_rate": 1.1356957649092481e-05,
+      "loss": 0.0,
+      "step": 6000
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6.524023046949878e-05,
+      "learning_rate": 1.0636704119850187e-05,
+      "loss": 0.0,
+      "step": 6500
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 7.143516995711252e-05,
+      "learning_rate": 9.916450590607894e-06,
+      "loss": 0.0,
+      "step": 7000
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.0009180093766190112,
+      "learning_rate": 9.196197061365601e-06,
+      "loss": 0.0109,
+      "step": 7500
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.00015384699509013444,
+      "learning_rate": 8.475943532123308e-06,
+      "loss": 0.0007,
+      "step": 8000
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.0011837659403681755,
+      "learning_rate": 7.755690002881015e-06,
+      "loss": 0.0,
+      "step": 8500
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 8.039615931920707e-05,
+      "learning_rate": 7.035436473638721e-06,
+      "loss": 0.0,
+      "step": 9000
+    },
+    {
+      "epoch": 2.0,
+      "eval_NEGATIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 13620.0
+      },
+      "eval_POSITIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 6960.0
+      },
+      "eval_accuracy": 1.0,
+      "eval_loss": 1.1887321988979238e-06,
+      "eval_macro avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "eval_runtime": 11.5561,
+      "eval_samples_per_second": 1780.878,
+      "eval_steps_per_second": 111.37,
+      "eval_weighted avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "step": 9256
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.00039502361323684454,
+      "learning_rate": 6.3151829443964284e-06,
+      "loss": 0.0014,
+      "step": 9500
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 9.729123121360317e-05,
+      "learning_rate": 5.594929415154135e-06,
+      "loss": 0.0005,
+      "step": 10000
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 2.681278419913724e-05,
+      "learning_rate": 4.874675885911842e-06,
+      "loss": 0.0,
+      "step": 10500
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.2711697965860367e-05,
+      "learning_rate": 4.154422356669548e-06,
+      "loss": 0.0,
+      "step": 11000
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 3.7230620364425704e-05,
+      "learning_rate": 3.4341688274272546e-06,
+      "loss": 0.0,
+      "step": 11500
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 5.341789801605046e-05,
+      "learning_rate": 2.7139152981849613e-06,
+      "loss": 0.0,
+      "step": 12000
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.8995728169102222e-05,
+      "learning_rate": 1.993661768942668e-06,
+      "loss": 0.0,
+      "step": 12500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 3.693885446409695e-05,
+      "learning_rate": 1.2734082397003748e-06,
+      "loss": 0.0,
+      "step": 13000
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.6792944481712766e-05,
+      "learning_rate": 5.531547104580813e-07,
+      "loss": 0.0,
+      "step": 13500
+    },
+    {
+      "epoch": 3.0,
+      "eval_NEGATIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 13620.0
+      },
+      "eval_POSITIVE": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 6960.0
+      },
+      "eval_accuracy": 1.0,
+      "eval_loss": 4.978057290827564e-07,
+      "eval_macro avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "eval_runtime": 11.5311,
+      "eval_samples_per_second": 1784.731,
+      "eval_steps_per_second": 111.611,
+      "eval_weighted avg": {
+        "f1-score": 1.0,
+        "precision": 1.0,
+        "recall": 1.0,
+        "support": 20580.0
+      },
+      "step": 13884
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13884,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8954868592254240.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-13884/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcc91ae6efcb4a19e77c6c0c5e98c1e2ddf87cbe2bd793b17ef56c157e4dc5d
+size 4984