Training in progress, step 8000, checkpoint

checkpoint-8000/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

checkpoint-8000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "demdecuong/vihealthbert-base-word",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "word-level",
+  "gradient_checkpointing": false,
+  "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": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

checkpoint-8000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac94969bfb0508f5dc69c81c3dae12ca60924d71bb6aa6fa1c5a3c5c9e3a597
+size 540279452

checkpoint-8000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced9d64c0bb8ac7412e367c8df01ab31ccd80115f0b5984427589df954ffab0e
+size 1080631290

checkpoint-8000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b4a814877817cc7efcd971fdd991fdadabc167c088b80ccb37e0e3402c52b8
+size 14244

checkpoint-8000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6df18b18df6f5df75c786c827ea9cac7b352442b2343ea2cf96cb85c23014c
+size 1064

checkpoint-8000/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-8000/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-8000/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.5771132321637026,
+  "best_model_checkpoint": "output/pretraining/vihealthbert-w_unsup-SynPD/lr3e-5_wr0.1_wd0.0/checkpoint-6000",
+  "epoch": 1.3785972772703774,
+  "eval_steps": 2000,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00017232465965879716,
+      "grad_norm": 35.608882904052734,
+      "learning_rate": 5.169739789763915e-09,
+      "loss": 10.7382,
+      "step": 1
+    },
+    {
+      "epoch": 0.34464931931759435,
+      "grad_norm": 4.884454250335693,
+      "learning_rate": 1.033947957952783e-05,
+      "loss": 5.8543,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34464931931759435,
+      "eval_accuracy": 0.3950195480446223,
+      "eval_loss": 3.896709680557251,
+      "eval_runtime": 24.6709,
+      "eval_samples_per_second": 396.175,
+      "eval_steps_per_second": 24.766,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6892986386351887,
+      "grad_norm": 5.278345108032227,
+      "learning_rate": 2.067895915905566e-05,
+      "loss": 3.4544,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6892986386351887,
+      "eval_accuracy": 0.530626322082222,
+      "eval_loss": 2.811899423599243,
+      "eval_runtime": 24.6443,
+      "eval_samples_per_second": 396.602,
+      "eval_steps_per_second": 24.793,
+      "step": 4000
+    },
+    {
+      "epoch": 1.033947957952783,
+      "grad_norm": 4.731122016906738,
+      "learning_rate": 2.988684014015739e-05,
+      "loss": 2.8312,
+      "step": 6000
+    },
+    {
+      "epoch": 1.033947957952783,
+      "eval_accuracy": 0.5771132321637026,
+      "eval_loss": 2.4039628505706787,
+      "eval_runtime": 24.6266,
+      "eval_samples_per_second": 396.889,
+      "eval_steps_per_second": 24.811,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3785972772703774,
+      "grad_norm": 12.213573455810547,
+      "learning_rate": 2.873800907576541e-05,
+      "loss": 2.5914,
+      "step": 8000
+    },
+    {
+      "epoch": 1.3785972772703774,
+      "eval_accuracy": 0.5349752225383133,
+      "eval_loss": 2.6481692790985107,
+      "eval_runtime": 24.6033,
+      "eval_samples_per_second": 397.264,
+      "eval_steps_per_second": 24.834,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 58030,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2000,
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828a11e9b75940b4120312d1450c3472eb18a2c7fa0179d8afafbcd0800beb75
+size 5304