Training in progress, step 500

epoch-5/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-5/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-5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fff631492c17c75986067c1c4e5b3d8d01a41d4f6a130a150c1ab18b2192761
+size 1053747768

epoch-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86fac3a42ff51e724531848dcd9ef267e8fabe3155686f83744c7c88f2e29fca
+size 2103036541

epoch-5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a441da3761ea05796636af49fafb658f1854628fdc1d10280893b25475370d
+size 14244

epoch-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5defb6579e6f4be110d42fd31917a46d3513da9932ab1f3125b5d56062c0e0c7
+size 1064

epoch-5/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 12500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.992727272727273e-05,
+      "loss": 1.1069,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9854545454545456e-05,
+      "loss": 1.1657,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9781818181818184e-05,
+      "loss": 1.1288,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.970909090909091e-05,
+      "loss": 1.1395,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.963636363636364e-05,
+      "loss": 1.1613,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9563636363636366e-05,
+      "loss": 1.149,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9490909090909093e-05,
+      "loss": 1.1539,
+      "step": 3500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.941818181818182e-05,
+      "loss": 1.1561,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9345454545454548e-05,
+      "loss": 1.1793,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9272727272727275e-05,
+      "loss": 1.1544,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.1414,
+      "step": 5500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.912727272727273e-05,
+      "loss": 1.1439,
+      "step": 6000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.9054545454545457e-05,
+      "loss": 1.1691,
+      "step": 6500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8981818181818185e-05,
+      "loss": 1.1362,
+      "step": 7000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8909090909090912e-05,
+      "loss": 1.1434,
+      "step": 7500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8836363636363636e-05,
+      "loss": 1.1652,
+      "step": 8000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8763636363636367e-05,
+      "loss": 1.1717,
+      "step": 8500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8690909090909094e-05,
+      "loss": 1.135,
+      "step": 9000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.861818181818182e-05,
+      "loss": 1.1031,
+      "step": 9500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8545454545454545e-05,
+      "loss": 1.1322,
+      "step": 10000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.8472727272727273e-05,
+      "loss": 1.1726,
+      "step": 10500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 1.1472,
+      "step": 11000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.832727272727273e-05,
+      "loss": 1.1489,
+      "step": 11500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.8254545454545455e-05,
+      "loss": 1.1528,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 1.1203,
+      "step": 12500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 137500,
+  "num_train_epochs": 11,
+  "save_steps": 500,
+  "total_flos": 8443388560158720.0,
+  "trial_name": null,
+  "trial_params": null
+}

epoch-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a1aff5e41b2b559316bcea79bdb782e319abd5420b7fed37b46bfbce2bf400
+size 4728

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fff631492c17c75986067c1c4e5b3d8d01a41d4f6a130a150c1ab18b2192761
+oid sha256:b4dfad8f1715ef1eda147791b02f1eb9ba9190aae3e88a4ae2b85060ff169c4d
 size 1053747768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a1aff5e41b2b559316bcea79bdb782e319abd5420b7fed37b46bfbce2bf400
+oid sha256:e0dfb50574116b3a00e64de3f63338896131bd825ef544ac404ca04cdd59ee59
 size 4728