Training in progress, epoch 1

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32005
+}

last-checkpoint/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32005
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff48857e140935905f2d51dd058038971b29df48f11e86540faddcb8cb55788c
+size 236491077

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4803f9e0db327256eb501e38588125bc88c11e1b720f56b57560c04d0edfb58a
+size 118253458

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6704fd65015a992608b80d84ae3a33c9753819f994516e6b0899e5280afdced5
+size 15597

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c55418e1401c7ce23c9d42366610b1a8c2a2596e8b41e0dce8eff0736e359ea
+size 557

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2eaa85b3feb378678992330dad398ea68e96da3317f4bcf13c1084640b7ec5b
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522e963abd859af7d20e174403a6d639af482c17a395587e9d6f0e3aebe64038
+size 2017623

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/IpadicUnigram",
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/IpadicUnigram/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 22940,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5566625155666254e-05,
+      "loss": 8.9454,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.113325031133251e-05,
+      "loss": 6.3983,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6699875466998756e-05,
+      "loss": 5.7848,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.226650062266502e-05,
+      "loss": 5.1787,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.783312577833126e-05,
+      "loss": 4.5006,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.339975093399751e-05,
+      "loss": 4.016,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.990941915030131e-05,
+      "loss": 3.6483,
+      "step": 3500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.975216073068553e-05,
+      "loss": 3.3951,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.959490231106974e-05,
+      "loss": 3.2185,
+      "step": 4500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.943764389145395e-05,
+      "loss": 3.0927,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.928038547183816e-05,
+      "loss": 2.9973,
+      "step": 5500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.912312705222237e-05,
+      "loss": 2.9138,
+      "step": 6000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.89658686326066e-05,
+      "loss": 2.8402,
+      "step": 6500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.880861021299081e-05,
+      "loss": 2.7818,
+      "step": 7000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.865135179337502e-05,
+      "loss": 2.7254,
+      "step": 7500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.849409337375923e-05,
+      "loss": 2.6782,
+      "step": 8000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.833683495414345e-05,
+      "loss": 2.6362,
+      "step": 8500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.817957653452766e-05,
+      "loss": 2.5982,
+      "step": 9000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.802231811491189e-05,
+      "loss": 2.5705,
+      "step": 9500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.78650596952961e-05,
+      "loss": 2.5337,
+      "step": 10000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.77078012756803e-05,
+      "loss": 2.5079,
+      "step": 10500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.755054285606452e-05,
+      "loss": 2.4798,
+      "step": 11000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.739328443644873e-05,
+      "loss": 2.4593,
+      "step": 11500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.723602601683295e-05,
+      "loss": 2.432,
+      "step": 12000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.70790821140564e-05,
+      "loss": 2.408,
+      "step": 12500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.69218236944406e-05,
+      "loss": 2.3853,
+      "step": 13000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.676456527482482e-05,
+      "loss": 2.3635,
+      "step": 13500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.660730685520904e-05,
+      "loss": 2.3485,
+      "step": 14000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.645036295243249e-05,
+      "loss": 2.3328,
+      "step": 14500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.62931045328167e-05,
+      "loss": 2.3185,
+      "step": 15000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.61358461132009e-05,
+      "loss": 2.3014,
+      "step": 15500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.597858769358512e-05,
+      "loss": 2.2902,
+      "step": 16000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.582164379080856e-05,
+      "loss": 2.2746,
+      "step": 16500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.566438537119277e-05,
+      "loss": 2.2592,
+      "step": 17000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 9.5507126951577e-05,
+      "loss": 2.248,
+      "step": 17500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.53498685319612e-05,
+      "loss": 2.24,
+      "step": 18000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.519292462918465e-05,
+      "loss": 2.2215,
+      "step": 18500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.503566620956886e-05,
+      "loss": 2.2128,
+      "step": 19000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.487840778995309e-05,
+      "loss": 2.2036,
+      "step": 19500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.47211493703373e-05,
+      "loss": 2.1933,
+      "step": 20000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.456420546756074e-05,
+      "loss": 2.1816,
+      "step": 20500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.440694704794495e-05,
+      "loss": 2.1657,
+      "step": 21000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.424968862832916e-05,
+      "loss": 2.1611,
+      "step": 21500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.409243020871337e-05,
+      "loss": 2.1546,
+      "step": 22000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.393548630593683e-05,
+      "loss": 2.1439,
+      "step": 22500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6093312991188715,
+      "eval_loss": 1.9991799592971802,
+      "eval_runtime": 294.7692,
+      "eval_samples_per_second": 603.699,
+      "eval_steps_per_second": 37.731,
+      "step": 22940
+    }
+  ],
+  "max_steps": 321160,
+  "num_train_epochs": 14,
+  "total_flos": 1.7442453853030272e+17,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3819be597606ce07478cd807fe197c341ed83c123fc11e3b1a34a00d9e57bd93
+size 3579

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4803f9e0db327256eb501e38588125bc88c11e1b720f56b57560c04d0edfb58a
+size 118253458

runs/Feb20_18-29-06_ubuntu-2004/1676885357.410681/events.out.tfevents.1676885357.ubuntu-2004.887393.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd7f5ec71d3293c7be7457c67a9bb091ebe26034e71f32c03f28b4411bde496
+size 5751

runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78301fc79b73c4bc3a25e318065e0b0fb19b15fc290523ddb23d8d132f535ce
+size 11201

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522e963abd859af7d20e174403a6d639af482c17a395587e9d6f0e3aebe64038
+size 2017623

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/IpadicUnigram",
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/IpadicUnigram/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3819be597606ce07478cd807fe197c341ed83c123fc11e3b1a34a00d9e57bd93
+size 3579