Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8857d743a2fe05d5efc3e4f437b70d6ee76601ecdd666aa1536bab8c9378538a
+oid sha256:caa78924d429fea6a097a1c6234566ec5aef06b99bd47b40b6148bf6cc52a9fc
 size 498612824

run-hrrn3119/checkpoint-5084/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": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-hrrn3119/checkpoint-5084/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa78924d429fea6a097a1c6234566ec5aef06b99bd47b40b6148bf6cc52a9fc
+size 498612824

run-hrrn3119/checkpoint-5084/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1909cf51736adfd441ef828a8cbabb1febad02ec2dcbcade733b85a749bb9d9b
+size 997345530

run-hrrn3119/checkpoint-5084/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d87f6f867955a774159fc207a03969a42b82f17bc9294897f569799d1ee9cb
+size 14180

run-hrrn3119/checkpoint-5084/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f891cf674246c1aba5038d1ad794e87756b04595e78b4ed2e96e39b5686e904b
+size 1064

run-hrrn3119/checkpoint-5084/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-hrrn3119/checkpoint-5084/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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",
+  "unk_token": "<unk>"
+}

run-hrrn3119/checkpoint-5084/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5084,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.128891468048096,
+      "learning_rate": 2.9262391817466563e-05,
+      "loss": 0.3492,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.290346145629883,
+      "learning_rate": 2.8524783634933124e-05,
+      "loss": 0.3139,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.3120012283325195,
+      "learning_rate": 2.7787175452399686e-05,
+      "loss": 0.3064,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.9245710372924805,
+      "learning_rate": 2.7049567269866248e-05,
+      "loss": 0.285,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.7431070804595947,
+      "learning_rate": 2.631195908733281e-05,
+      "loss": 0.2719,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 8.229458808898926,
+      "learning_rate": 2.557435090479937e-05,
+      "loss": 0.2635,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 7.368682384490967,
+      "learning_rate": 2.4836742722265933e-05,
+      "loss": 0.2581,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 15.96370792388916,
+      "learning_rate": 2.4099134539732495e-05,
+      "loss": 0.2575,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.469223976135254,
+      "learning_rate": 2.3361526357199057e-05,
+      "loss": 0.2524,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 38.71263122558594,
+      "learning_rate": 2.262391817466562e-05,
+      "loss": 0.2397,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9054996127033308,
+      "eval_F1": 0.8622136172959018,
+      "eval_Precision": 0.9124644280022766,
+      "eval_Recall": 0.8172086859007034,
+      "eval_loss": 0.3134010136127472,
+      "eval_runtime": 102.8535,
+      "eval_samples_per_second": 263.589,
+      "eval_steps_per_second": 32.95,
+      "step": 5084
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 4030195368256320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-hrrn3119/checkpoint-5084/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32a0c0723e093fb9e4eedfc3d49c1c5731ca9445a4a2b2369f6539477f369a0
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602c16475c0c1143f90b1079c90227c1ef914b9fd9650bc47e993d21dc77137f
+oid sha256:a32a0c0723e093fb9e4eedfc3d49c1c5731ca9445a4a2b2369f6539477f369a0
 size 4920