Training in progress, step 200, checkpoint

checkpoint-200/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "sheepy928/default",
+  "architectures": [
+    "RobertaForSentimentClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "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": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cd4020bfe06a829d156a37e24abf8001e7782ebace30e5a04c6db68d8844ba
+size 4747538

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2471c4ba9e57696e2487cc5ab28138adfd04bce3ad5fa74ef869b478673d8c
+size 498661166

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4502b72d7e70304a1778840e3b52e81165f327a51b7ec038a613a37aa965b7
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0c85cee554eb988b3b972b800df49059447cdeacabf48b757bbbda89b5c570
+size 1064

checkpoint-200/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
+  }
+}

checkpoint-200/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>"
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,269 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0638297872340425,
+  "eval_steps": 20,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0004995563442768412,
+      "loss": 1.2913,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0004986690328305235,
+      "loss": 1.1578,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7813256978988647,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.7155,
+      "eval_samples_per_second": 262.444,
+      "eval_steps_per_second": 8.223,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0004977817213842058,
+      "loss": 0.8742,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0004968944099378882,
+      "loss": 0.7537,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.792127251625061,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6846,
+      "eval_samples_per_second": 263.869,
+      "eval_steps_per_second": 8.268,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004960070984915705,
+      "loss": 0.8076,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004951197870452529,
+      "loss": 0.7436,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7419535517692566,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.7977,
+      "eval_samples_per_second": 258.725,
+      "eval_steps_per_second": 8.107,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004942324755989353,
+      "loss": 0.7465,
+      "step": 70
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0004933451641526176,
+      "loss": 0.6516,
+      "step": 80
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7484750747680664,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.7051,
+      "eval_samples_per_second": 262.923,
+      "eval_steps_per_second": 8.238,
+      "step": 80
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0004924578527063,
+      "loss": 0.9634,
+      "step": 90
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0004915705412599822,
+      "loss": 0.8011,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7428026795387268,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.7042,
+      "eval_samples_per_second": 262.962,
+      "eval_steps_per_second": 8.239,
+      "step": 100
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0004906832298136646,
+      "loss": 0.8691,
+      "step": 110
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0004897959183673469,
+      "loss": 0.8761,
+      "step": 120
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7458600997924805,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6685,
+      "eval_samples_per_second": 264.622,
+      "eval_steps_per_second": 8.292,
+      "step": 120
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0004889086069210293,
+      "loss": 0.828,
+      "step": 130
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00048802129547471164,
+      "loss": 0.8708,
+      "step": 140
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7820696830749512,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6616,
+      "eval_samples_per_second": 264.945,
+      "eval_steps_per_second": 8.302,
+      "step": 140
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.000487133984028394,
+      "loss": 0.7489,
+      "step": 150
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0004862466725820763,
+      "loss": 0.9504,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7716627717018127,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6993,
+      "eval_samples_per_second": 263.189,
+      "eval_steps_per_second": 8.247,
+      "step": 160
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0004853593611357587,
+      "loss": 0.5649,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00048447204968944104,
+      "loss": 1.1222,
+      "step": 180
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.9907371401786804,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6565,
+      "eval_samples_per_second": 265.181,
+      "eval_steps_per_second": 8.309,
+      "step": 180
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00048358473824312333,
+      "loss": 0.9109,
+      "step": 190
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00048269742679680566,
+      "loss": 0.7528,
+      "step": 200
+    },
+    {
+      "epoch": 1.06,
+      "eval_accuracy": 0.7386666666666667,
+      "eval_combined_score": 0.6626504648943422,
+      "eval_f1": 0.6276400817995911,
+      "eval_loss": 0.7575691938400269,
+      "eval_precision": 0.5456284444444445,
+      "eval_recall": 0.7386666666666667,
+      "eval_runtime": 5.6695,
+      "eval_samples_per_second": 264.575,
+      "eval_steps_per_second": 8.29,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5640,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 419928999985152.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f7cf02005ce236de7bb1fda33a06f2c3053bafb778c1f449d2ec5279f3a3ec
+size 4472