First model version

checkpoint-5000/config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "Ayaka/bart-base-cantonese",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 101,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 102,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 102,
+  "forced_eos_token_id": 102,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": true,
+  "vocab_size": 12660
+}

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1c08132b0f862627c8c36d8723ea67473f9c8c06156ac2edbc7827e66bd973
+size 878178757

checkpoint-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bafe081584ac04b9bb378832ac4b62f077f9b6da538cdbbace2e600f587c4c
+size 439152541

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f49a2d9109f17593cd276b2f09bac182f79d4174ebe06a60a6fcd6cbbce9663
+size 14639

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83caee8b9af2828b7ad1c11fed6c614a6a10fb4014f29e5af58bfaa914cc6adc
+size 557

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368fd9b380339405aaf568e7765fdf3c6cb3506ff7f2f2550bb1af1aff8ab1c7
+size 627

checkpoint-5000/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.895193977996526,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.8093032233159624e-05,
+      "loss": 5.93,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.617062343176993e-05,
+      "loss": 5.1165,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.4240494113105579e-05,
+      "loss": 4.748,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.125702381134033,
+      "eval_runtime": 102.7952,
+      "eval_samples_per_second": 299.518,
+      "eval_steps_per_second": 37.443,
+      "step": 1727
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.2314225053078557e-05,
+      "loss": 4.5216,
+      "step": 2000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.0384095734414205e-05,
+      "loss": 4.3356,
+      "step": 2500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.457826674387185e-06,
+      "loss": 4.1988,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.5067617893218994,
+      "eval_runtime": 103.1393,
+      "eval_samples_per_second": 298.519,
+      "eval_steps_per_second": 37.318,
+      "step": 3454
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 6.527697355722834e-06,
+      "loss": 4.0849,
+      "step": 3500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 4.597568037058483e-06,
+      "loss": 3.9975,
+      "step": 4000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.6674387183941326e-06,
+      "loss": 3.9402,
+      "step": 4500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 7.37309399729782e-07,
+      "loss": 3.8973,
+      "step": 5000
+    }
+  ],
+  "max_steps": 5181,
+  "num_train_epochs": 3,
+  "total_flos": 2.74331103920128e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6691b3a39b434704456c64bc069893b018dc17c0953d52fbeeff7d14897c8
+size 3515