Upload fine-tuned and quantized summarization model

checkpoint-293/config.json

@@ -0,0 +1,44 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "sadness_negative",
+    "1": "surprise_negative",
+    "2": "neutral_neutral",
+    "3": "joy_positive",
+    "4": "anger_negative",
+    "5": "surprise_positive",
+    "6": "disgust_negative",
+    "7": "fear_negative"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger_negative": 4,
+    "disgust_negative": 6,
+    "fear_negative": 7,
+    "joy_positive": 3,
+    "neutral_neutral": 2,
+    "sadness_negative": 0,
+    "surprise_negative": 1,
+    "surprise_positive": 5
+  },
+  "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": "4.52.1",
+  "vocab_size": 30522
+}

checkpoint-293/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5918e0c24539151f2e6a5a278ba2a9fbb6de90f16c05d51b5a4b1e5ab8a60a10
+size 267851024

checkpoint-293/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aaa915bf419a2216397dfdbd2d27bcec46ace6410bd073315f8d48c8ef13ef8
+size 535761739

checkpoint-293/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858a11eb33b3e7914d19ef840c8c6485f3dbd1786fe91430816808a1956b9bb7
+size 14455

checkpoint-293/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6411d9a6a8b91983853ee172b932b286b9600464210daa50dc732a1390bd3a5f
+size 1465

checkpoint-293/special_tokens_map.json

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

checkpoint-293/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-293/trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_global_step": 293,
+  "best_metric": 0.5119453924914675,
+  "best_model_checkpoint": "./results_cpu_qfix/checkpoint-293",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 293,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034129692832764506,
+      "grad_norm": 4.731612205505371,
+      "learning_rate": 1.938566552901024e-05,
+      "loss": 2.0437,
+      "step": 10
+    },
+    {
+      "epoch": 0.06825938566552901,
+      "grad_norm": 5.916387557983398,
+      "learning_rate": 1.870307167235495e-05,
+      "loss": 2.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.10238907849829351,
+      "grad_norm": 4.9087233543396,
+      "learning_rate": 1.802047781569966e-05,
+      "loss": 1.9578,
+      "step": 30
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 5.27643346786499,
+      "learning_rate": 1.733788395904437e-05,
+      "loss": 1.8919,
+      "step": 40
+    },
+    {
+      "epoch": 0.17064846416382254,
+      "grad_norm": 5.508472919464111,
+      "learning_rate": 1.6655290102389077e-05,
+      "loss": 1.6533,
+      "step": 50
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 6.766260147094727,
+      "learning_rate": 1.5972696245733788e-05,
+      "loss": 1.8696,
+      "step": 60
+    },
+    {
+      "epoch": 0.23890784982935154,
+      "grad_norm": 5.721550464630127,
+      "learning_rate": 1.52901023890785e-05,
+      "loss": 1.6216,
+      "step": 70
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 7.68924617767334,
+      "learning_rate": 1.4607508532423209e-05,
+      "loss": 1.6407,
+      "step": 80
+    },
+    {
+      "epoch": 0.30716723549488056,
+      "grad_norm": 5.800849437713623,
+      "learning_rate": 1.392491467576792e-05,
+      "loss": 1.4528,
+      "step": 90
+    },
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 5.374143123626709,
+      "learning_rate": 1.3242320819112629e-05,
+      "loss": 1.1909,
+      "step": 100
+    },
+    {
+      "epoch": 0.37542662116040953,
+      "grad_norm": 10.029739379882812,
+      "learning_rate": 1.255972696245734e-05,
+      "loss": 1.9,
+      "step": 110
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 7.377814769744873,
+      "learning_rate": 1.1877133105802047e-05,
+      "loss": 1.739,
+      "step": 120
+    },
+    {
+      "epoch": 0.44368600682593856,
+      "grad_norm": 5.629587173461914,
+      "learning_rate": 1.1194539249146758e-05,
+      "loss": 1.3806,
+      "step": 130
+    },
+    {
+      "epoch": 0.4778156996587031,
+      "grad_norm": 8.637285232543945,
+      "learning_rate": 1.051194539249147e-05,
+      "loss": 1.7475,
+      "step": 140
+    },
+    {
+      "epoch": 0.5119453924914675,
+      "grad_norm": 7.765105247497559,
+      "learning_rate": 9.829351535836179e-06,
+      "loss": 1.6408,
+      "step": 150
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 8.896513938903809,
+      "learning_rate": 9.146757679180888e-06,
+      "loss": 1.4381,
+      "step": 160
+    },
+    {
+      "epoch": 0.5802047781569966,
+      "grad_norm": 9.395094871520996,
+      "learning_rate": 8.464163822525599e-06,
+      "loss": 1.4626,
+      "step": 170
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 5.849052429199219,
+      "learning_rate": 7.781569965870308e-06,
+      "loss": 1.4404,
+      "step": 180
+    },
+    {
+      "epoch": 0.6484641638225256,
+      "grad_norm": 11.358508110046387,
+      "learning_rate": 7.098976109215017e-06,
+      "loss": 1.7092,
+      "step": 190
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 6.5548014640808105,
+      "learning_rate": 6.4163822525597275e-06,
+      "loss": 1.7465,
+      "step": 200
+    },
+    {
+      "epoch": 0.7167235494880546,
+      "grad_norm": 8.163894653320312,
+      "learning_rate": 5.733788395904437e-06,
+      "loss": 1.639,
+      "step": 210
+    },
+    {
+      "epoch": 0.7508532423208191,
+      "grad_norm": 6.512352466583252,
+      "learning_rate": 5.051194539249147e-06,
+      "loss": 1.6322,
+      "step": 220
+    },
+    {
+      "epoch": 0.7849829351535836,
+      "grad_norm": 6.136053085327148,
+      "learning_rate": 4.368600682593857e-06,
+      "loss": 1.2731,
+      "step": 230
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 5.267455577850342,
+      "learning_rate": 3.6860068259385667e-06,
+      "loss": 1.525,
+      "step": 240
+    },
+    {
+      "epoch": 0.8532423208191127,
+      "grad_norm": 5.496407508850098,
+      "learning_rate": 3.003412969283277e-06,
+      "loss": 1.4582,
+      "step": 250
+    },
+    {
+      "epoch": 0.8873720136518771,
+      "grad_norm": 8.91087818145752,
+      "learning_rate": 2.3208191126279866e-06,
+      "loss": 1.6813,
+      "step": 260
+    },
+    {
+      "epoch": 0.9215017064846417,
+      "grad_norm": 6.79412317276001,
+      "learning_rate": 1.6382252559726963e-06,
+      "loss": 1.5778,
+      "step": 270
+    },
+    {
+      "epoch": 0.9556313993174061,
+      "grad_norm": 8.445448875427246,
+      "learning_rate": 9.556313993174062e-07,
+      "loss": 1.3507,
+      "step": 280
+    },
+    {
+      "epoch": 0.9897610921501706,
+      "grad_norm": 8.388998031616211,
+      "learning_rate": 2.7303754266211607e-07,
+      "loss": 1.3616,
+      "step": 290
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5119453924914675,
+      "eval_f1": 0.424672713430414,
+      "eval_loss": 1.4379266500473022,
+      "eval_precision": 0.3831069535218987,
+      "eval_recall": 0.5119453924914675,
+      "eval_runtime": 4.6658,
+      "eval_samples_per_second": 62.797,
+      "eval_steps_per_second": 15.86,
+      "step": 293
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 293,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 38717739669504.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-293/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f532c07c473aa83e897d239048fccdfa02f6de9e3523c70609dcd7e979061ee8
+size 5649