Upload folder using huggingface_hub

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "facebook/muppet-roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6860272da4c6bd537aa64a8423e33bbd4be152d31b430db61b65a239f29c88f9
+size 498615900

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31b400bd2e51dcbebfea23a5ccaa8a0ca5d5679f01bc94896178971b1a86b45
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f555dd259b487dd62dd1d4d4135cb9243ab657edfb020284161ae93958d3771
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.9029529506581548,
+  "best_model_checkpoint": "muppet_base_divergence_classifier_v1.0/checkpoint-4800",
+  "epoch": 2.1248339973439574,
+  "eval_steps": 480,
+  "global_step": 4800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21248339973439576,
+      "eval_accuracy": 0.8745519713261649,
+      "eval_f1": 0.874329560354496,
+      "eval_loss": 0.4335894286632538,
+      "eval_runtime": 3.9801,
+      "eval_samples_per_second": 140.196,
+      "eval_steps_per_second": 17.587,
+      "step": 480
+    },
+    {
+      "epoch": 0.4249667994687915,
+      "eval_accuracy": 0.8835125448028673,
+      "eval_f1": 0.8827759092141159,
+      "eval_loss": 0.37165558338165283,
+      "eval_runtime": 4.0199,
+      "eval_samples_per_second": 138.809,
+      "eval_steps_per_second": 17.413,
+      "step": 960
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "eval_accuracy": 0.8853046594982079,
+      "eval_f1": 0.8848186914136107,
+      "eval_loss": 0.37070879340171814,
+      "eval_runtime": 3.9732,
+      "eval_samples_per_second": 140.44,
+      "eval_steps_per_second": 17.618,
+      "step": 1440
+    },
+    {
+      "epoch": 0.849933598937583,
+      "eval_accuracy": 0.8888888888888888,
+      "eval_f1": 0.8877338353414772,
+      "eval_loss": 0.43106743693351746,
+      "eval_runtime": 4.0177,
+      "eval_samples_per_second": 138.885,
+      "eval_steps_per_second": 17.423,
+      "step": 1920
+    },
+    {
+      "epoch": 0.9065958388667552,
+      "grad_norm": 0.671415388584137,
+      "learning_rate": 1.804100815434448e-05,
+      "loss": 0.5386,
+      "step": 2048
+    },
+    {
+      "epoch": 1.0624169986719787,
+      "eval_accuracy": 0.8548387096774194,
+      "eval_f1": 0.8556637971147828,
+      "eval_loss": 0.6500999927520752,
+      "eval_runtime": 4.0038,
+      "eval_samples_per_second": 139.368,
+      "eval_steps_per_second": 17.483,
+      "step": 2400
+    },
+    {
+      "epoch": 1.2749003984063745,
+      "eval_accuracy": 0.8888888888888888,
+      "eval_f1": 0.888992318806512,
+      "eval_loss": 0.5748390555381775,
+      "eval_runtime": 4.0052,
+      "eval_samples_per_second": 139.319,
+      "eval_steps_per_second": 17.477,
+      "step": 2880
+    },
+    {
+      "epoch": 1.4873837981407703,
+      "eval_accuracy": 0.8924731182795699,
+      "eval_f1": 0.8920627439279448,
+      "eval_loss": 0.5230178236961365,
+      "eval_runtime": 4.0216,
+      "eval_samples_per_second": 138.749,
+      "eval_steps_per_second": 17.406,
+      "step": 3360
+    },
+    {
+      "epoch": 1.699867197875166,
+      "eval_accuracy": 0.8942652329749103,
+      "eval_f1": 0.894461310705129,
+      "eval_loss": 0.555411159992218,
+      "eval_runtime": 3.9433,
+      "eval_samples_per_second": 141.506,
+      "eval_steps_per_second": 17.752,
+      "step": 3840
+    },
+    {
+      "epoch": 1.8131916777335104,
+      "grad_norm": 8.14060115814209,
+      "learning_rate": 1.1986926694634988e-05,
+      "loss": 0.4507,
+      "step": 4096
+    },
+    {
+      "epoch": 1.9123505976095618,
+      "eval_accuracy": 0.8906810035842294,
+      "eval_f1": 0.8906975831458821,
+      "eval_loss": 0.5315648317337036,
+      "eval_runtime": 3.9793,
+      "eval_samples_per_second": 140.227,
+      "eval_steps_per_second": 17.591,
+      "step": 4320
+    },
+    {
+      "epoch": 2.1248339973439574,
+      "eval_accuracy": 0.9032258064516129,
+      "eval_f1": 0.9029529506581548,
+      "eval_loss": 0.5185472369194031,
+      "eval_runtime": 4.0159,
+      "eval_samples_per_second": 138.949,
+      "eval_steps_per_second": 17.431,
+      "step": 4800
+    }
+  ],
+  "logging_steps": 2048,
+  "max_steps": 9036,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 480,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9462403342238616.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5f8b9010f8db32fe897d01175f35a5129879aa44e33b2d9bf5700dd6417928
+size 5240