Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf744df7804dad2e7c27f62a4bbb9854754dded145721ea0cb366733b23b51a
+oid sha256:4e614966da972499c17f9f3166b5b0423948b0c330677aea98c18c8066fe0802
 size 498612824

run-4/checkpoint-16/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/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,
+  "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-4/checkpoint-16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bff419dc1b731f53039114923078299d34cce8fd032b11556483973c8dcdf4b
+size 498612824

run-4/checkpoint-16/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f5e8987ae8cf410ac9ffd6379319a9a96de81d84cfdddaa683c05d58dc2786
+size 997345530

run-4/checkpoint-16/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b889674d43953fb8f95d6dd4ba7398411990579b7fc65109318935d4c4340ffa
+size 14244

run-4/checkpoint-16/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945643478cc4d23c530809118196f7c31bab701a2e02f5f90c52399014608f94
+size 1064

run-4/checkpoint-16/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>"
+}

run-4/checkpoint-16/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": 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>"
+}

run-4/checkpoint-16/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "roberta-base-finetuned-rte/run-4/checkpoint-8",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7294954061508179,
+      "eval_runtime": 4.3815,
+      "eval_samples_per_second": 63.221,
+      "eval_steps_per_second": 4.108,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7272132635116577,
+      "eval_runtime": 3.6715,
+      "eval_samples_per_second": 75.446,
+      "eval_steps_per_second": 4.903,
+      "step": 16
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6652403087124956e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 39
+  }
+}

run-4/checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4ddbad1a6e2e50f8bfe07ad61091b3c3a8d1968174754c35ac950a16aa57fe
+size 4920

run-4/checkpoint-24/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/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,
+  "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-4/checkpoint-24/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92fc82e1fc1eed9de8bec237ed049bd496a5d28ae18eb3f0cddc6b22fbb6f54c
+size 498612824

run-4/checkpoint-24/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba291e537b2a3517469ed7c981511abf473bb6ef35bf801f4135c4b4e613a00
+size 997345530

run-4/checkpoint-24/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a489fee429c466d065deaabd3a1286fcf55418335e9cd1edd4ca291b678da0
+size 14244

run-4/checkpoint-24/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391d8bf20e04b572284d1c911b67f214c2f236944cf073ad1efb40947d881ba1
+size 1064

run-4/checkpoint-24/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>"
+}

run-4/checkpoint-24/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": 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>"
+}

run-4/checkpoint-24/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "roberta-base-finetuned-rte/run-4/checkpoint-8",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7294954061508179,
+      "eval_runtime": 4.3815,
+      "eval_samples_per_second": 63.221,
+      "eval_steps_per_second": 4.108,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7272132635116577,
+      "eval_runtime": 3.6715,
+      "eval_samples_per_second": 75.446,
+      "eval_steps_per_second": 4.903,
+      "step": 16
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7264065742492676,
+      "eval_runtime": 4.3281,
+      "eval_samples_per_second": 64.0,
+      "eval_steps_per_second": 4.159,
+      "step": 24
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6652403087124956e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 39
+  }
+}

run-4/checkpoint-24/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4ddbad1a6e2e50f8bfe07ad61091b3c3a8d1968174754c35ac950a16aa57fe
+size 4920

run-5/checkpoint-8/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/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,
+  "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-5/checkpoint-8/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e614966da972499c17f9f3166b5b0423948b0c330677aea98c18c8066fe0802
+size 498612824

run-5/checkpoint-8/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bd2715924c98afb2268094967375ac6492a8b030bfe971d6f922e5b6e26387
+size 997345530

run-5/checkpoint-8/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12693af469c0b5371d90e02c09074ece61130a8b9db10b0503299fd426a485a2
+size 14244

run-5/checkpoint-8/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f30ef4470d173dd26b36f9fcc7fcae792f2f1158af1c08cb93b6d7f951cfd5c
+size 1064

run-5/checkpoint-8/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>"
+}

run-5/checkpoint-8/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": 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>"
+}

run-5/checkpoint-8/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "roberta-base-finetuned-rte/run-5/checkpoint-8",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6967751383781433,
+      "eval_runtime": 2.7199,
+      "eval_samples_per_second": 101.843,
+      "eval_steps_per_second": 6.618,
+      "step": 8
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.548475480658427e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 28
+  }
+}

run-5/checkpoint-8/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5aa29e52ef9a87f3453b23a5924bf011b94fd326ff386ccf3a7c2c22d520e1
+size 4920

runs/Mar09_12-48-04_a0f3909bd2ac/events.out.tfevents.1709989775.a0f3909bd2ac.40155.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacfeac144a9562af20a61d7453e0b84d9db464f367725c487251ac059203fe7
+size 5290

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4ddbad1a6e2e50f8bfe07ad61091b3c3a8d1968174754c35ac950a16aa57fe
+oid sha256:7d5aa29e52ef9a87f3453b23a5924bf011b94fd326ff386ccf3a7c2c22d520e1
 size 4920