Upload folder using huggingface_hub

checkpoint-360/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[PRETEXT]": 50265,
+  "[TEXT]": 50266
+}

checkpoint-360/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "no-mgt",
+    "1": "mgt"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "no-mgt": 0,
+    "rel": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50267
+}

checkpoint-360/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dca30df4b624cebe7595ff63e82d107d82b9cdb620d98ce0cf22c6f73c87cd3
+size 1421503608

checkpoint-360/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f979cc6dd12beb430f8ac4472626aff1cb990bacaaea312226c4100fbc5a57
+size 2843239224

checkpoint-360/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807d6e1d98df577e72f8eceed209ce8c32e28aed67d5426565ac795e7601bd4c
+size 14575

checkpoint-360/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4b39b621ef4ed68e6fe5a4652c7e5d3b94a4c2adc992a909729cd5f4fd9b35
+size 627

checkpoint-360/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[PRETEXT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[TEXT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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>"
+}

checkpoint-360/tokenizer_config.json

@@ -0,0 +1,77 @@
+{
+  "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
+    },
+    "50265": {
+      "content": "[PRETEXT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "[TEXT]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[PRETEXT]",
+    "[TEXT]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-360/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.2459656447172165,
+  "best_model_checkpoint": "/nlp/scr/q1zhang/models/mgt_0.000005_0.9/checkpoint-360",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.101648807525635,
+      "learning_rate": 4.75e-06,
+      "loss": 0.365,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8647016011644832,
+      "eval_loss": 0.33019885420799255,
+      "eval_runtime": 2.7097,
+      "eval_samples_per_second": 88.571,
+      "eval_steps_per_second": 11.071,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7355960607528687,
+      "learning_rate": 4.5e-06,
+      "loss": 0.3079,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8647016011644832,
+      "eval_loss": 0.29353153705596924,
+      "eval_runtime": 2.6247,
+      "eval_samples_per_second": 91.438,
+      "eval_steps_per_second": 11.43,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 11.464811325073242,
+      "learning_rate": 4.25e-06,
+      "loss": 0.2211,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9426681783824641,
+      "eval_loss": 0.2459656447172165,
+      "eval_runtime": 2.6376,
+      "eval_samples_per_second": 90.993,
+      "eval_steps_per_second": 11.374,
+      "step": 360
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 215960532023712.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6631f838d88dd1b6387d2ca695672ea828867b1835cb3f0be5050d6cff229a
+size 4795