init

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.24.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9fd4de1e984decab851647d8c15acb550dd5bea56d41927160293a0ae638e4
+size 535737925

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d2b3abe1366efabff7045304a52381aa783dd781dfda653f922c96b64cda6b
+size 267873965

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5925d118dff5d3da0a89671e8c3d82a0ffc4caac7a3ff03cbe398f4fb66c22f
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37c4c55734a7b23b67a52dc38591535d44b5d49d1f810e7169201282351ebfe
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.2238,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1.1391,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.5486156940460205,
+      "eval_ratings_accuracy": 0.4162,
+      "eval_runtime": 77.505,
+      "eval_samples_per_second": 64.512,
+      "eval_sentiment_accuracy": 0.9124,
+      "eval_steps_per_second": 8.064,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4e-05,
+      "loss": 1.4143,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 1.3635,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.3658400774002075,
+      "eval_ratings_accuracy": 0.4458,
+      "eval_runtime": 74.927,
+      "eval_samples_per_second": 66.732,
+      "eval_sentiment_accuracy": 0.9146,
+      "eval_steps_per_second": 8.341,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.374,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 1.1193,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.3039019107818604,
+      "eval_ratings_accuracy": 0.501,
+      "eval_runtime": 81.9688,
+      "eval_samples_per_second": 60.999,
+      "eval_sentiment_accuracy": 0.9238,
+      "eval_steps_per_second": 7.625,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.0751,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.0864,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.3203859329223633,
+      "eval_ratings_accuracy": 0.507,
+      "eval_runtime": 67.5001,
+      "eval_samples_per_second": 74.074,
+      "eval_sentiment_accuracy": 0.932,
+      "eval_steps_per_second": 9.259,
+      "step": 4000
+    }
+  ],
+  "max_steps": 7500,
+  "num_train_epochs": 3,
+  "total_flos": 3985863371456640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866a91c1c3717aa2e99d6583e0cd80c28d683a3f8ae48fc419b645faa970fd85
+size 3387