add model weights and configs

added_tokens.json

@@ -0,0 +1 @@
+{}

cartography_config_dev.json

@@ -0,0 +1,49 @@
+{
+    "adam_epsilon": 1e-08,
+    "cache_dir": "",
+    "config_name": "",
+    "data_dir": "/content/data/glue/SNLI",
+    "dev": null,
+    "device": "cuda",
+    "do_eval": true,
+    "do_lower_case": true,
+    "do_test": false,
+    "do_train": true,
+    "eval_all_checkpoints": false,
+    "eval_batch_size": 96,
+    "evaluate_during_training": true,
+    "evaluate_during_training_epoch": false,
+    "features_cache_dir": "/content/data/glue/SNLI/cache_93078",
+    "fp16": false,
+    "fp16_opt_level": "01",
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 1.0708609960508476e-05,
+    "local_rank": -1,
+    "logging_steps": 1000,
+    "max_grad_norm": 1.0,
+    "max_seq_length": 128,
+    "max_steps": -1,
+    "model_name_or_path": "roberta-base",
+    "model_type": "roberta",
+    "n_gpu": 1,
+    "no_cuda": false,
+    "num_train_epochs": 6,
+    "output_dir": "/content/results",
+    "output_mode": "classification",
+    "overwrite_cache": false,
+    "overwrite_output_dir": false,
+    "patience": 6,
+    "per_gpu_eval_batch_size": 96,
+    "per_gpu_train_batch_size": 64,
+    "save_steps": 0,
+    "seed": 93078,
+    "server_ip": "",
+    "server_port": "",
+    "task_name": "snli",
+    "test": null,
+    "tokenizer_name": "",
+    "train": null,
+    "train_batch_size": 64,
+    "warmup_steps": 0,
+    "weight_decay": 0.0
+}

cartography_config_train.json

@@ -0,0 +1,47 @@
+{
+    "adam_epsilon": 1e-08,
+    "cache_dir": "",
+    "config_name": "",
+    "data_dir": "/content/data/glue/SNLI",
+    "dev": null,
+    "device": "cuda",
+    "do_eval": true,
+    "do_lower_case": true,
+    "do_test": false,
+    "do_train": true,
+    "eval_all_checkpoints": false,
+    "evaluate_during_training": true,
+    "evaluate_during_training_epoch": false,
+    "features_cache_dir": "/content/data/glue/SNLI/cache_93078",
+    "fp16": false,
+    "fp16_opt_level": "01",
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 1.0708609960508476e-05,
+    "local_rank": -1,
+    "logging_steps": 1000,
+    "max_grad_norm": 1.0,
+    "max_seq_length": 128,
+    "max_steps": -1,
+    "model_name_or_path": "roberta-base",
+    "model_type": "roberta",
+    "n_gpu": 1,
+    "no_cuda": false,
+    "num_train_epochs": 6,
+    "output_dir": "/content/results",
+    "output_mode": "classification",
+    "overwrite_cache": false,
+    "overwrite_output_dir": false,
+    "patience": 6,
+    "per_gpu_eval_batch_size": 96,
+    "per_gpu_train_batch_size": 64,
+    "save_steps": 0,
+    "seed": 93078,
+    "server_ip": "",
+    "server_port": "",
+    "task_name": "snli",
+    "test": null,
+    "tokenizer_name": "",
+    "train": null,
+    "warmup_steps": 0,
+    "weight_decay": 0.0
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "snli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_labels": 3,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "pruned_heads": {},
+  "torchscript": false,
+  "type_vocab_size": 1,
+  "use_bfloat16": false,
+  "vocab_size": 50265
+}

eval_metrics_snli_dev_.json

@@ -0,0 +1 @@
+{"acc": 0.9191221296484454}

eval_metrics_snli_dev_in_training.json

@@ -0,0 +1,6 @@
+{"acc": 0.9088599878073562}
+{"acc": 0.9162771794350741}
+{"acc": 0.9182076813655761}
+{"acc": 0.9191221296484454}
+{"acc": 0.9179028652712863}
+{"acc": 0.9175980491769965}

eval_metrics_train.json

@@ -0,0 +1,6 @@
+{"epoch": 0, "train_acc": 0.8615260836562808, "best_dev_performance": 0.9088599878073562, "avg_batch_loss": 49.27200323867146, "learning_rate": 8.923841633757064e-06}
+{"epoch": 1, "train_acc": 0.8973454903552635, "best_dev_performance": 0.9162771794350741, "avg_batch_loss": 37.900505941710435, "learning_rate": 7.13907330700565e-06}
+{"epoch": 2, "train_acc": 0.9121170365165727, "best_dev_performance": 0.9182076813655761, "avg_batch_loss": 32.80486748734256, "learning_rate": 5.354304980254238e-06}
+{"epoch": 3, "train_acc": 0.9230623608625927, "best_dev_performance": 0.9191221296484454, "avg_batch_loss": 29.08752869471209, "learning_rate": 3.569536653502825e-06}
+{"epoch": 4, "train_acc": 0.9308859105115523, "best_dev_performance": 0.9191221296484454, "avg_batch_loss": 26.19556408256176, "learning_rate": 1.7847683267514126e-06}
+{"epoch": 5, "train_acc": 0.9368964644763883, "best_dev_performance": 0.9191221296484454, "avg_batch_loss": 24.088992209290154, "learning_rate": 0.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bbea56fd9d57b3aa1e65b9f68ca94122897f837290789708b8789e847a3c08
+size 501004058

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "max_len": 512, "init_inputs": []}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9430721407d7551cde0a61c3f1de1643360ea0a3eae2742888f7b5668fdc397d
+size 1395