Add model checkpoint

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "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": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2ec1788f9c8e48243dbf85ae52c3d108b9da07d395ee05f99a5e4c773e6a55
+size 1625426996

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8165a2708d97b42db31640048781dbdd4dac5c129cfd341f2880cc0b7c7bc555
+size 3250759951

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe8e0e44b4c13ab05326c6c60eca19733d46ff21431ad7dd2087077d271d063
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da07f4bc6a42da189cc0168c278eeb6c954af047743c7cc8ef9379424d71370
+size 1064

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.857142857142857,
+  "eval_steps": 500,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 5e-05,
+      "loss": 0.0898,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.683544303797468e-05,
+      "loss": 0.0637,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.367088607594937e-05,
+      "loss": 0.0706,
+      "step": 1500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.050632911392405e-05,
+      "loss": 0.0894,
+      "step": 2000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.7341772151898736e-05,
+      "loss": 0.1138,
+      "step": 2500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.4177215189873416e-05,
+      "loss": 0.1484,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.10126582278481e-05,
+      "loss": 0.1201,
+      "step": 3500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.7848101265822786e-05,
+      "loss": 0.1216,
+      "step": 4000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.468354430379747e-05,
+      "loss": 0.1238,
+      "step": 4500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.1518987341772153e-05,
+      "loss": 0.1255,
+      "step": 5000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.1305,
+      "step": 5500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.5189873417721521e-05,
+      "loss": 0.1012,
+      "step": 6000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.2025316455696203e-05,
+      "loss": 0.0969,
+      "step": 6500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.860759493670886e-06,
+      "loss": 0.1036,
+      "step": 7000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.69620253164557e-06,
+      "loss": 0.1146,
+      "step": 7500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.531645569620253e-06,
+      "loss": 0.1198,
+      "step": 8000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8400,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.4673673633792e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:747828469188eed9e710be3490b8946d03d6473ac83e16c89b65d7577a9ea3a7
+size 4728