End of training

README.md

@@ -16,15 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [maximuspowers/bert-philosophy-adapted](https://huggingface.co/maximuspowers/bert-philosophy-adapted) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4928
-- Exact Match Accuracy: 0.4069
-- Macro Precision: 0.5825
-- Macro Recall: 0.4180
-- Macro F1: 0.4727
-- Micro Precision: 0.7718
-- Micro Recall: 0.5721
-- Micro F1: 0.6571
-- Hamming Loss: 0.0487
+- Loss: 0.5930
+- Exact Match Accuracy: 0.4138
+- Macro Precision: 0.3910
+- Macro Recall: 0.2935
+- Macro F1: 0.3205
+- Micro Precision: 0.8062
+- Micro Recall: 0.5149
+- Micro F1: 0.6284
+- Hamming Loss: 0.0499
 
 ## Model description
 

all_results.json

@@ -1,5 +1,17 @@
 {
     "epoch": 34.248275862068965,
+    "eval_exact_match_accuracy": 0.41379310344827586,
+    "eval_hamming_loss": 0.04989858012170385,
+    "eval_loss": 0.5930218696594238,
+    "eval_macro_f1": 0.32054514113337645,
+    "eval_macro_precision": 0.3909600203717851,
+    "eval_macro_recall": 0.2934883988593418,
+    "eval_micro_f1": 0.6283987915407855,
+    "eval_micro_precision": 0.8062015503875969,
+    "eval_micro_recall": 0.5148514851485149,
+    "eval_runtime": 0.7302,
+    "eval_samples_per_second": 198.571,
+    "eval_steps_per_second": 26.02,
     "total_flos": 0.0,
     "train_loss": 0.657050135421753,
     "train_runtime": 659.4996,

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "model_type": "bert",
+  "num_labels": 17,
+  "projection_dim": 256,
+  "hidden_size": 768,
+  "base_model": "bert-base-uncased",
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": "float32",
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": 0,
+  "eos_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "maximuspowers/bert-philosophy-adapted",
+  "transformers_version": "4.52.4",
+  "gradient_checkpointing": false,
+  "vocab_size": 30522,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "hidden_act": "gelu",
+  "intermediate_size": 3072,
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "max_position_embeddings": 512,
+  "type_vocab_size": 2,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "position_embedding_type": "absolute",
+  "use_cache": true,
+  "classifier_dropout": null
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1207fa3962d04f8e57c1fdaeed866e81adabce8138756fe502348b0182ec17fa
+size 441215422

runs/Jun16_17-49-10_509eee86a659/events.out.tfevents.1750096991.509eee86a659.15800.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049f3ce6c6101fb2cf71d68702811307b8922a02f57bbed378d203c4f4207b7b
+size 19965

test_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 24.662068965517243,
-    "eval_exact_match_accuracy": 0.3931034482758621,
-    "eval_hamming_loss": 0.05354969574036511,
-    "eval_loss": 0.565125048160553,
-    "eval_macro_f1": 0.24889861157994672,
-    "eval_macro_precision": 0.3151783530460001,
-    "eval_macro_recall": 0.2381291916416587,
-    "eval_micro_f1": 0.5900621118012422,
-    "eval_micro_precision": 0.7916666666666666,
-    "eval_micro_recall": 0.47029702970297027,
-    "eval_runtime": 0.7539,
-    "eval_samples_per_second": 192.34,
-    "eval_steps_per_second": 25.203
+    "epoch": 34.248275862068965,
+    "eval_exact_match_accuracy": 0.41379310344827586,
+    "eval_hamming_loss": 0.04989858012170385,
+    "eval_loss": 0.5930218696594238,
+    "eval_macro_f1": 0.32054514113337645,
+    "eval_macro_precision": 0.3909600203717851,
+    "eval_macro_recall": 0.2934883988593418,
+    "eval_micro_f1": 0.6283987915407855,
+    "eval_micro_precision": 0.8062015503875969,
+    "eval_micro_recall": 0.5148514851485149,
+    "eval_runtime": 0.7302,
+    "eval_samples_per_second": 198.571,
+    "eval_steps_per_second": 26.02
 }

training_args.json

@@ -0,0 +1,144 @@
+{
+  "output_dir": "./bert-philosophy-classifier",
+  "overwrite_output_dir": true,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 8,
+  "per_device_eval_batch_size": 8,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 2e-05,
+  "weight_decay": 0.01,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 500,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.0,
+  "warmup_steps": 100,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "./bert-philosophy-classifier/runs/Jun16_17-49-10_509eee86a659",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 50,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 2000,
+  "save_total_limit": 3,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": false,
+  "fp16": true,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": 100,
+  "dataloader_num_workers": 0,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "./bert-philosophy-classifier",
+  "disable_tqdm": false,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_micro_f1",
+  "greater_is_better": true,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "split_batches": false,
+    "dispatch_batches": null,
+    "even_batches": true,
+    "use_seedable_sampler": true,
+    "non_blocking": false,
+    "gradient_accumulation_kwargs": null
+  },
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": false,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": true,
+  "resume_from_checkpoint": null,
+  "hub_model_id": "maximuspowers/bert-philosophy-classifier",
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": false
+}