Upload folder using huggingface_hub

checkpoint-147/config.json

@@ -0,0 +1,46 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "negative",
+    "5": "neutral",
+    "6": "positive",
+    "7": "sadness",
+    "8": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "negative": 4,
+    "neutral": 5,
+    "positive": 6,
+    "sadness": 7,
+    "surprise": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

checkpoint-147/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0f3271613f4b2ccd0962efaf6e7656426fb79c1793c39eb09b8ea5e44267a2
+size 267854100

checkpoint-147/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6033b4b1662b211d8ba1f613612be1362239edca3127c7968ad665b9b94e875b
+size 535767418

checkpoint-147/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdfe7be492948f5ecb723c356588072e508f65a56f4160e51e3464ada5484c0
+size 14244

checkpoint-147/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3705f8215f188c92bddfd52df869fbe01ce49d2adbd615cb6f52c4e76d715bae
+size 1064

checkpoint-147/special_tokens_map.json

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

checkpoint-147/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-147/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 147,
+  "best_metric": 0.43230944254835035,
+  "best_model_checkpoint": "distilbert_emotion_sentiment_finetuned_cpu/checkpoint-147",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.9348878860473633,
+      "learning_rate": 2.75e-05,
+      "loss": 0.489,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 1.040361762046814,
+      "learning_rate": 2.4948979591836734e-05,
+      "loss": 0.3948,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy_subset": 0.30716723549488056,
+      "eval_f1_samples": 0.43230944254835035,
+      "eval_loss": 0.36293554306030273,
+      "eval_runtime": 32.8378,
+      "eval_samples_per_second": 8.923,
+      "eval_steps_per_second": 0.579,
+      "step": 147
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 38718430071552.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-147/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cbfdbbe95f9bde5c4b5cf4dc89072952ca9334b636a3b6c72ebcab2341d835
+size 5368

checkpoint-294/config.json

@@ -0,0 +1,46 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "negative",
+    "5": "neutral",
+    "6": "positive",
+    "7": "sadness",
+    "8": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "negative": 4,
+    "neutral": 5,
+    "positive": 6,
+    "sadness": 7,
+    "surprise": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

checkpoint-294/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b2d592b342b7f22b63f271b1597fb492948dd47936faeb276ba2bb3a1c7ae0
+size 267854100

checkpoint-294/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627deeaabe5f30d3a5dc332c4dcb3eeb5a740bc9b519efab8aa488416bf572a7
+size 535767418

checkpoint-294/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d48769fb986f7d6abb1ddec7d94b51784039a1b6e7b944e5db82e5a149124e6
+size 14244

checkpoint-294/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467736377c83e2436c969ba7485bdf91bf7813e02ccdfa813690e4aa99756b2b
+size 1064

checkpoint-294/special_tokens_map.json

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

checkpoint-294/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-294/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_global_step": 294,
+  "best_metric": 0.5386803185437997,
+  "best_model_checkpoint": "distilbert_emotion_sentiment_finetuned_cpu/checkpoint-294",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.9348878860473633,
+      "learning_rate": 2.75e-05,
+      "loss": 0.489,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 1.040361762046814,
+      "learning_rate": 2.4948979591836734e-05,
+      "loss": 0.3948,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy_subset": 0.30716723549488056,
+      "eval_f1_samples": 0.43230944254835035,
+      "eval_loss": 0.36293554306030273,
+      "eval_runtime": 32.8378,
+      "eval_samples_per_second": 8.923,
+      "eval_steps_per_second": 0.579,
+      "step": 147
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.7896512746810913,
+      "learning_rate": 2.239795918367347e-05,
+      "loss": 0.3604,
+      "step": 150
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.8474708199501038,
+      "learning_rate": 1.9846938775510205e-05,
+      "loss": 0.3515,
+      "step": 200
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.1555696725845337,
+      "learning_rate": 1.729591836734694e-05,
+      "loss": 0.3323,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy_subset": 0.3003412969283277,
+      "eval_f1_samples": 0.5386803185437997,
+      "eval_loss": 0.33012497425079346,
+      "eval_runtime": 32.6293,
+      "eval_samples_per_second": 8.98,
+      "eval_steps_per_second": 0.582,
+      "step": 294
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 77436860143104.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-294/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cbfdbbe95f9bde5c4b5cf4dc89072952ca9334b636a3b6c72ebcab2341d835
+size 5368

checkpoint-441/config.json

@@ -0,0 +1,46 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "negative",
+    "5": "neutral",
+    "6": "positive",
+    "7": "sadness",
+    "8": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "negative": 4,
+    "neutral": 5,
+    "positive": 6,
+    "sadness": 7,
+    "surprise": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

checkpoint-441/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d86e4863114856955ce345d18e3129c49d35ee0983621b9c5e2561937130d8c
+size 267854100

checkpoint-441/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d72b1e4c680e22064f74035adc338619c6ea1fabe6390e12faf0fab8c75690
+size 535767418

checkpoint-441/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0def758e8d50df7257831a24f2184fd3bcccff2f6fd5b9ceeb8cbbac30eaffc0
+size 14244

checkpoint-441/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e035278ce1a80911828e351551420430f073a777f4de0f543847b8c4157a1c
+size 1064

checkpoint-441/special_tokens_map.json

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

checkpoint-441/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-441/trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_global_step": 441,
+  "best_metric": 0.58646188850967,
+  "best_model_checkpoint": "distilbert_emotion_sentiment_finetuned_cpu/checkpoint-441",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.9348878860473633,
+      "learning_rate": 2.75e-05,
+      "loss": 0.489,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 1.040361762046814,
+      "learning_rate": 2.4948979591836734e-05,
+      "loss": 0.3948,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy_subset": 0.30716723549488056,
+      "eval_f1_samples": 0.43230944254835035,
+      "eval_loss": 0.36293554306030273,
+      "eval_runtime": 32.8378,
+      "eval_samples_per_second": 8.923,
+      "eval_steps_per_second": 0.579,
+      "step": 147
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.7896512746810913,
+      "learning_rate": 2.239795918367347e-05,
+      "loss": 0.3604,
+      "step": 150
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.8474708199501038,
+      "learning_rate": 1.9846938775510205e-05,
+      "loss": 0.3515,
+      "step": 200
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.1555696725845337,
+      "learning_rate": 1.729591836734694e-05,
+      "loss": 0.3323,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy_subset": 0.3003412969283277,
+      "eval_f1_samples": 0.5386803185437997,
+      "eval_loss": 0.33012497425079346,
+      "eval_runtime": 32.6293,
+      "eval_samples_per_second": 8.98,
+      "eval_steps_per_second": 0.582,
+      "step": 294
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.9709883332252502,
+      "learning_rate": 1.4744897959183674e-05,
+      "loss": 0.3121,
+      "step": 300
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 2.1932430267333984,
+      "learning_rate": 1.2193877551020408e-05,
+      "loss": 0.2793,
+      "step": 350
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 2.272308826446533,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.2628,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy_subset": 0.378839590443686,
+      "eval_f1_samples": 0.58646188850967,
+      "eval_loss": 0.3093891739845276,
+      "eval_runtime": 31.9778,
+      "eval_samples_per_second": 9.163,
+      "eval_steps_per_second": 0.594,
+      "step": 441
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 116155290214656.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-441/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cbfdbbe95f9bde5c4b5cf4dc89072952ca9334b636a3b6c72ebcab2341d835
+size 5368

checkpoint-588/config.json

@@ -0,0 +1,46 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "negative",
+    "5": "neutral",
+    "6": "positive",
+    "7": "sadness",
+    "8": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "negative": 4,
+    "neutral": 5,
+    "positive": 6,
+    "sadness": 7,
+    "surprise": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

checkpoint-588/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5aa79e96cbc442fa7e315c39ca010839bfe1c23553233e89c74d0016267e06
+size 267854100

checkpoint-588/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e04843df6dc698ec60c79862722f0dbfe1e4d95d9b522bd6c142431d1ba5e47
+size 535767418

checkpoint-588/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3d378334efdf777b0f96512b71659737b3fc3fd57aa90977dabb8f7934dcfa
+size 14244

checkpoint-588/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10dfccd319137361185dc4882ef690ca7ff02e0b75a4ded52c36e7aa786a38b
+size 1064

checkpoint-588/special_tokens_map.json

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

checkpoint-588/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-588/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_global_step": 588,
+  "best_metric": 0.608646188850967,
+  "best_model_checkpoint": "distilbert_emotion_sentiment_finetuned_cpu/checkpoint-588",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 588,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.9348878860473633,
+      "learning_rate": 2.75e-05,
+      "loss": 0.489,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 1.040361762046814,
+      "learning_rate": 2.4948979591836734e-05,
+      "loss": 0.3948,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy_subset": 0.30716723549488056,
+      "eval_f1_samples": 0.43230944254835035,
+      "eval_loss": 0.36293554306030273,
+      "eval_runtime": 32.8378,
+      "eval_samples_per_second": 8.923,
+      "eval_steps_per_second": 0.579,
+      "step": 147
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.7896512746810913,
+      "learning_rate": 2.239795918367347e-05,
+      "loss": 0.3604,
+      "step": 150
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.8474708199501038,
+      "learning_rate": 1.9846938775510205e-05,
+      "loss": 0.3515,
+      "step": 200
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.1555696725845337,
+      "learning_rate": 1.729591836734694e-05,
+      "loss": 0.3323,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy_subset": 0.3003412969283277,
+      "eval_f1_samples": 0.5386803185437997,
+      "eval_loss": 0.33012497425079346,
+      "eval_runtime": 32.6293,
+      "eval_samples_per_second": 8.98,
+      "eval_steps_per_second": 0.582,
+      "step": 294
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.9709883332252502,
+      "learning_rate": 1.4744897959183674e-05,
+      "loss": 0.3121,
+      "step": 300
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 2.1932430267333984,
+      "learning_rate": 1.2193877551020408e-05,
+      "loss": 0.2793,
+      "step": 350
+    },
+    {
+      "epoch": 2.7210884353741496,
+      "grad_norm": 2.272308826446533,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.2628,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy_subset": 0.378839590443686,
+      "eval_f1_samples": 0.58646188850967,
+      "eval_loss": 0.3093891739845276,
+      "eval_runtime": 31.9778,
+      "eval_samples_per_second": 9.163,
+      "eval_steps_per_second": 0.594,
+      "step": 441
+    },
+    {
+      "epoch": 3.061224489795918,
+      "grad_norm": 0.6931778788566589,
+      "learning_rate": 7.0918367346938785e-06,
+      "loss": 0.2488,
+      "step": 450
+    },
+    {
+      "epoch": 3.4013605442176873,
+      "grad_norm": 1.2945401668548584,
+      "learning_rate": 4.540816326530613e-06,
+      "loss": 0.2215,
+      "step": 500
+    },
+    {
+      "epoch": 3.741496598639456,
+      "grad_norm": 1.3985503911972046,
+      "learning_rate": 1.989795918367347e-06,
+      "loss": 0.236,
+      "step": 550
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy_subset": 0.39590443686006827,
+      "eval_f1_samples": 0.608646188850967,
+      "eval_loss": 0.306503027677536,
+      "eval_runtime": 33.5148,
+      "eval_samples_per_second": 8.742,
+      "eval_steps_per_second": 0.567,
+      "step": 588
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 154873720286208.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-588/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cbfdbbe95f9bde5c4b5cf4dc89072952ca9334b636a3b6c72ebcab2341d835
+size 5368

config.json

@@ -0,0 +1,46 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "negative",
+    "5": "neutral",
+    "6": "positive",
+    "7": "sadness",
+    "8": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "negative": 4,
+    "neutral": 5,
+    "positive": 6,
+    "sadness": 7,
+    "surprise": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1745077025.34600a0164ab.938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b19b18be659d98a34cb15170bfcc606c36064e2e5d69775a1315c756e4c52ee
+size 5684

logs/events.out.tfevents.1745077161.34600a0164ab.938.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e65b85ab5e99875650e2a21222d0532c1f3318c022f3144bb30f94394f8c1b
+size 9511

logs/events.out.tfevents.1745079444.34600a0164ab.938.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d768dc5bae7d1c60cc1e8c9a29a68605d72379eefffcf39f7b198da120ee6362
+size 472

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5aa79e96cbc442fa7e315c39ca010839bfe1c23553233e89c74d0016267e06
+size 267854100

special_tokens_map.json

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