Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unhelpful",
+    "1": "helpful"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": [
+    {
+      "helpful": 1,
+      "unhelpful": 0
+    }
+  ],
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_of_labels": 2,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384d70e2dbaffad3acd30357e28cb28ed5e589620a336128be74c75f5bc013c2
+size 498612824

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161f8e43cc69e38e0c8a87d0c0f7a243c2eaf15cf1c408fe7d4a35377b3b34dc
+size 997345530

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bcc3feefcf44cb150e0de844296a90162b0b70edb9794b8d75a37cf75a3a19
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6285544880c2bcf6cea400eeb634fcba4e96023a55b17ba311fce73259a0c10
+size 1064

last-checkpoint/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>"
+}

last-checkpoint/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>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.5436379875739142,
+  "best_model_checkpoint": "micro_base_help_class_no_pre_seed_1/checkpoint-313",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9361022364217256e-05,
+      "loss": 0.4095,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8722044728434506e-05,
+      "loss": 0.3862,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.808306709265176e-05,
+      "loss": 0.3574,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8544,
+      "eval_f1_macro": 0.5436379875739142,
+      "eval_loss": 0.39146947860717773,
+      "eval_runtime": 35.8717,
+      "eval_samples_per_second": 139.386,
+      "eval_steps_per_second": 8.726,
+      "step": 313
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1221895963312320.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de266c123b24d2e24a9d4061fad70e8f469d0b9b0ad074d035e50f0e8933af57
+size 4792