Training in progress, step 200, checkpoint

checkpoint-200/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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1dbbcd6f15afa301ddde3ecef0bf6900dc5eed7257e3f4a7a9a692fe55c16c
+size 997351674

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65be978c0b523aafd9ba41c95ee576ffb10f7465e26d023afc306eb234eb9f8
+size 498661166

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1ae3e48808c2df3e6ccd5e21dd444339846001955bb43e5a1e708d3b6667ab
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d353843655370a49fcc88745baa7883197add82a68082507f54ec48efd10638a
+size 1064

checkpoint-200/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-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 +1,229 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6019563581640331,
+  "eval_steps": 20,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-07,
+      "loss": 1.1046,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1e-06,
+      "loss": 1.0664,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.44479243019924036,
+      "eval_loss": 1.065091609954834,
+      "eval_runtime": 50.348,
+      "eval_samples_per_second": 596.131,
+      "eval_steps_per_second": 1.172,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5e-06,
+      "loss": 1.0672,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-06,
+      "loss": 1.0423,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.5033650962883988,
+      "eval_loss": 1.0188277959823608,
+      "eval_runtime": 49.614,
+      "eval_samples_per_second": 604.95,
+      "eval_steps_per_second": 1.189,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.5e-06,
+      "loss": 1.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3e-06,
+      "loss": 1.0137,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.5279203038581995,
+      "eval_loss": 0.9871189594268799,
+      "eval_runtime": 49.5201,
+      "eval_samples_per_second": 606.098,
+      "eval_steps_per_second": 1.191,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0005,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4e-06,
+      "loss": 1.0027,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.5308189511561271,
+      "eval_loss": 0.9888613224029541,
+      "eval_runtime": 49.4469,
+      "eval_samples_per_second": 606.994,
+      "eval_steps_per_second": 1.193,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.5e-06,
+      "loss": 0.9937,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5e-06,
+      "loss": 0.9914,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.5307856333710935,
+      "eval_loss": 0.9762536883354187,
+      "eval_runtime": 49.4804,
+      "eval_samples_per_second": 606.583,
+      "eval_steps_per_second": 1.192,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 5.5e-06,
+      "loss": 0.9884,
+      "step": 110
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6e-06,
+      "loss": 0.9826,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.5387819017791697,
+      "eval_loss": 0.9713281989097595,
+      "eval_runtime": 49.4983,
+      "eval_samples_per_second": 606.364,
+      "eval_steps_per_second": 1.192,
+      "step": 120
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.5e-06,
+      "loss": 0.9882,
+      "step": 130
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 7e-06,
+      "loss": 0.9788,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.5312520823615646,
+      "eval_loss": 0.9766249656677246,
+      "eval_runtime": 49.5213,
+      "eval_samples_per_second": 606.083,
+      "eval_steps_per_second": 1.191,
+      "step": 140
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.5e-06,
+      "loss": 0.9854,
+      "step": 150
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 8e-06,
+      "loss": 0.984,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.5398147531152129,
+      "eval_loss": 0.9589501619338989,
+      "eval_runtime": 49.4977,
+      "eval_samples_per_second": 606.372,
+      "eval_steps_per_second": 1.192,
+      "step": 160
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 0.9795,
+      "step": 170
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9e-06,
+      "loss": 0.9694,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "eval_accuracy": 0.5423469047777704,
+      "eval_loss": 0.953514814376831,
+      "eval_runtime": 49.4511,
+      "eval_samples_per_second": 606.943,
+      "eval_steps_per_second": 1.193,
+      "step": 180
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.5e-06,
+      "loss": 0.9757,
+      "step": 190
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.9676,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.567201972412874,
+      "eval_loss": 0.9273685812950134,
+      "eval_runtime": 49.4122,
+      "eval_samples_per_second": 607.421,
+      "eval_steps_per_second": 1.194,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 996,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 2.69428130316288e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1be80ebe52f6e43af0b8aa087e72fad77310d5998b6e0b8f66a6a1d53be7b7
+size 4536