Training in progress, step 250, checkpoint

checkpoint-250/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "roberta-base",
+  "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-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5448a0025d259d2181cc480da3337528e539337fc448142f9ee4b8a13e72470a
+size 997351674

checkpoint-250/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691e8e37c428297e37b02d50a3743b0d67a9337ae695344ce8e75dc08b81d5d2
+size 498661166

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa2881dae9cbf4af7b23ee8c341a3bdb5ee1031991afbf5ca6c9f53ac8f4b96
+size 14244

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70c5a19d0726e52e4a7fcb291ae0f0f47fb283c75fcf14a555cede2a1be9dd9
+size 1064

checkpoint-250/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>"
+}

checkpoint-250/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-250/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.18811136192626035,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-07,
+      "loss": 1.1001,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-06,
+      "loss": 1.0661,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5e-06,
+      "loss": 1.0782,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-06,
+      "loss": 1.0578,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0395,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.4754781102152329,
+      "eval_loss": 1.0322505235671997,
+      "eval_runtime": 49.5848,
+      "eval_samples_per_second": 605.307,
+      "eval_steps_per_second": 1.19,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3e-06,
+      "loss": 1.0308,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0044,
+      "step": 70
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4e-06,
+      "loss": 1.0398,
+      "step": 80
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.5e-06,
+      "loss": 1.0116,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5e-06,
+      "loss": 1.0067,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.5313187179316319,
+      "eval_loss": 0.9863238334655762,
+      "eval_runtime": 49.2356,
+      "eval_samples_per_second": 609.599,
+      "eval_steps_per_second": 1.198,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.5e-06,
+      "loss": 1.0131,
+      "step": 110
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6e-06,
+      "loss": 1.0235,
+      "step": 120
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.5e-06,
+      "loss": 1.0073,
+      "step": 130
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7e-06,
+      "loss": 0.9856,
+      "step": 140
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.5e-06,
+      "loss": 1.0062,
+      "step": 150
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.5358499366962084,
+      "eval_loss": 0.9735665917396545,
+      "eval_runtime": 49.4568,
+      "eval_samples_per_second": 606.874,
+      "eval_steps_per_second": 1.193,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8e-06,
+      "loss": 0.9622,
+      "step": 160
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 0.9583,
+      "step": 170
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9e-06,
+      "loss": 0.987,
+      "step": 180
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.5e-06,
+      "loss": 0.9995,
+      "step": 190
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1e-05,
+      "loss": 0.9953,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.5406476977410541,
+      "eval_loss": 0.9847397804260254,
+      "eval_runtime": 49.5469,
+      "eval_samples_per_second": 605.769,
+      "eval_steps_per_second": 1.191,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.0500000000000001e-05,
+      "loss": 0.9894,
+      "step": 210
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1e-05,
+      "loss": 0.9857,
+      "step": 220
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.15e-05,
+      "loss": 0.9806,
+      "step": 230
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.2e-05,
+      "loss": 0.9802,
+      "step": 240
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.25e-05,
+      "loss": 0.9559,
+      "step": 250
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.5136269740787632,
+      "eval_loss": 1.0206754207611084,
+      "eval_runtime": 49.5108,
+      "eval_samples_per_second": 606.212,
+      "eval_steps_per_second": 1.192,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3987,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "total_flos": 8419629072384000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842788c44aca7ccbca2d57d8869e43eb15da3880b4cadb0b091bb46a3e020fcc
+size 4536