Training in progress, step 500

epoch-4/config.json

@@ -0,0 +1,184 @@
+{
+  "_name_or_path": "bert/models/transformer-bert-gpt",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "NlpHUST/gpt2-vietnamese",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.0,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "BERT\\models\\bert-culturaX-data",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 50256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2"
+}

epoch-4/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

epoch-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861f09b68b6ae6ff3b69b5537e21d9062f3955e97f62499c565a51550a7322da
+size 1053747768

epoch-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71beab1a69b753a23f326037865c54e007f20e8f4f1e31ca02d3d7894c13600a
+size 2103036541

epoch-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b849a03aaff06e829b8c54a52794a195abb8859168b2cf8f2d1e2e7999eccf11
+size 14244

epoch-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d2ad95bc85d8850982536e63866af01ed8207ea96f1ef65931250119bcf07a
+size 1064

epoch-4/trainer_state.json

@@ -0,0 +1,327 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 25000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 1.2684,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.2858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.88e-05,
+      "loss": 1.2162,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 1.2343,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8e-05,
+      "loss": 1.2604,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.76e-05,
+      "loss": 1.2677,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.72e-05,
+      "loss": 1.2578,
+      "step": 3500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 1.2211,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.64e-05,
+      "loss": 1.259,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.224,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.5600000000000003e-05,
+      "loss": 1.2511,
+      "step": 5500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 1.2556,
+      "step": 6000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.48e-05,
+      "loss": 1.2077,
+      "step": 6500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 1.2261,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2021,
+      "step": 7500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 1.2381,
+      "step": 8000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.3200000000000002e-05,
+      "loss": 1.2355,
+      "step": 8500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 1.2332,
+      "step": 9000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.2400000000000002e-05,
+      "loss": 1.199,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2e-05,
+      "loss": 1.2086,
+      "step": 10000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.16e-05,
+      "loss": 1.2177,
+      "step": 10500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.2126,
+      "step": 11000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 1.1851,
+      "step": 11500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.04e-05,
+      "loss": 1.219,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1e-05,
+      "loss": 1.2116,
+      "step": 12500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.323660969734192,
+      "eval_runtime": 19.2676,
+      "eval_samples_per_second": 103.801,
+      "eval_steps_per_second": 12.975,
+      "step": 12500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.1815,
+      "step": 13000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 1.167,
+      "step": 13500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.8e-06,
+      "loss": 1.1743,
+      "step": 14000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.1567,
+      "step": 14500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.1831,
+      "step": 15000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 1.1804,
+      "step": 15500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 1.1467,
+      "step": 16000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.1758,
+      "step": 16500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.182,
+      "step": 17000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6e-06,
+      "loss": 1.1705,
+      "step": 17500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.1814,
+      "step": 18000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.2e-06,
+      "loss": 1.1931,
+      "step": 18500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.1727,
+      "step": 19000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.4e-06,
+      "loss": 1.176,
+      "step": 19500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1597,
+      "step": 20000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.1616,
+      "step": 20500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.1087,
+      "step": 21000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.1478,
+      "step": 21500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.1471,
+      "step": 22000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1366,
+      "step": 22500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.1719,
+      "step": 23000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.183,
+      "step": 23500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.1675,
+      "step": 24000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.1829,
+      "step": 24500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 1.1523,
+      "step": 25000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 25000,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.686792444807168e+16,
+  "trial_name": null,
+  "trial_params": null
+}

epoch-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07afc0de00e40c368db95c29bf06b40fe50202de687a5d9e72b516503f8e5c86
+size 4728

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861f09b68b6ae6ff3b69b5537e21d9062f3955e97f62499c565a51550a7322da
+oid sha256:9b3e371ac4b17e5d2e820b497f4e1d76272641c6fa18c70a64fa09758be0c2a4
 size 1053747768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07afc0de00e40c368db95c29bf06b40fe50202de687a5d9e72b516503f8e5c86
+oid sha256:f7a1aff5e41b2b559316bcea79bdb782e319abd5420b7fed37b46bfbce2bf400
 size 4728