Import

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 7.0,
+    "eval_loss": 2.4415812492370605,
+    "eval_runtime": 3.2126,
+    "eval_samples": 1991,
+    "eval_samples_per_second": 619.755,
+    "eval_steps_per_second": 77.508,
+    "train_loss": 1.3588120859379202,
+    "train_runtime": 1049.6357,
+    "train_samples": 15931,
+    "train_samples_per_second": 106.244,
+    "train_steps_per_second": 13.285
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 0,
+  "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": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "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": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "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": "4.19.4",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "eval_loss": 2.4415812492370605,
+    "eval_runtime": 3.2126,
+    "eval_samples": 1991,
+    "eval_samples_per_second": 619.755,
+    "eval_steps_per_second": 77.508
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ae528c94c737090152a30ace3e6e5ff222826b10ee460fd027b2e2db9eafea
+size 557969145

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 1.3588120859379202,
+    "train_runtime": 1049.6357,
+    "train_samples": 15931,
+    "train_samples_per_second": 106.244,
+    "train_steps_per_second": 13.285
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 13944,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.8207114170969595e-05,
+      "loss": 2.3679,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.641422834193919e-05,
+      "loss": 2.2289,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.462134251290878e-05,
+      "loss": 2.1641,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.2828456683878374e-05,
+      "loss": 2.1632,
+      "step": 2000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.1035570854847967e-05,
+      "loss": 1.7626,
+      "step": 2500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.924268502581756e-05,
+      "loss": 1.7654,
+      "step": 3000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.744979919678715e-05,
+      "loss": 1.7738,
+      "step": 3500
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 3.5656913367756745e-05,
+      "loss": 1.7726,
+      "step": 4000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.386402753872633e-05,
+      "loss": 1.4475,
+      "step": 4500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.207114170969593e-05,
+      "loss": 1.465,
+      "step": 5000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.0278255880665517e-05,
+      "loss": 1.4945,
+      "step": 5500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 2.8485370051635113e-05,
+      "loss": 1.4736,
+      "step": 6000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 2.669248422260471e-05,
+      "loss": 1.2188,
+      "step": 6500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.48995983935743e-05,
+      "loss": 1.2392,
+      "step": 7000
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 2.310671256454389e-05,
+      "loss": 1.244,
+      "step": 7500
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 2.1313826735513484e-05,
+      "loss": 1.2268,
+      "step": 8000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 1.9520940906483077e-05,
+      "loss": 1.0412,
+      "step": 8500
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 1.772805507745267e-05,
+      "loss": 1.0629,
+      "step": 9000
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 1.593516924842226e-05,
+      "loss": 1.0673,
+      "step": 9500
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 1.4142283419391852e-05,
+      "loss": 1.0521,
+      "step": 10000
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 1.2349397590361447e-05,
+      "loss": 0.9034,
+      "step": 10500
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 1.055651176133104e-05,
+      "loss": 0.9072,
+      "step": 11000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 8.763625932300632e-06,
+      "loss": 0.9298,
+      "step": 11500
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 6.970740103270223e-06,
+      "loss": 0.9202,
+      "step": 12000
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 5.177854274239816e-06,
+      "loss": 0.8249,
+      "step": 12500
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 3.384968445209409e-06,
+      "loss": 0.8267,
+      "step": 13000
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 1.5920826161790018e-06,
+      "loss": 0.8203,
+      "step": 13500
+    },
+    {
+      "epoch": 7.0,
+      "step": 13944,
+      "total_flos": 3714812226478080.0,
+      "train_loss": 1.3588120859379202,
+      "train_runtime": 1049.6357,
+      "train_samples_per_second": 106.244,
+      "train_steps_per_second": 13.285
+    }
+  ],
+  "max_steps": 13944,
+  "num_train_epochs": 7,
+  "total_flos": 3714812226478080.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4f3fea89fbe614dfea025ac199544f102a69494361e0829f092bc033c14c960
+size 3311