initial model files

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": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36c141d3f65062a3c8981abbecd1a5f9b959d72fa03ceed6b5a731bcb2a9f47
+size 1115513717

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1faac375419c7ab607172de35db13dd8eff17a5b3a63fbf77575732785f2f7
+size 557969145

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c35564f97663942dfc7f304768b30e5744dc74b38a9d16495c0aabbbec03ecb
+size 17563

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bfc68d30d7b1de6bfcb90b000ee9e0c643505b98cadcd874d20b978fde2175
+size 623

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0387498870924037,
+  "global_step": 11500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.954836961430765e-05,
+      "loss": 1.1847,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9096739228615304e-05,
+      "loss": 0.4241,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.8645108842922955e-05,
+      "loss": 0.3364,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.8193478457230606e-05,
+      "loss": 0.2869,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.774184807153825e-05,
+      "loss": 0.2546,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.729021768584591e-05,
+      "loss": 0.2338,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.683858730015356e-05,
+      "loss": 0.2185,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.63869569144612e-05,
+      "loss": 0.2037,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.593532652876886e-05,
+      "loss": 0.1931,
+      "step": 4500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.548369614307651e-05,
+      "loss": 0.1868,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5032065757384155e-05,
+      "loss": 0.1779,
+      "step": 5500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.4580435371691806e-05,
+      "loss": 0.1688,
+      "step": 6000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.4128804985999464e-05,
+      "loss": 0.1628,
+      "step": 6500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.367717460030711e-05,
+      "loss": 0.1602,
+      "step": 7000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.322554421461476e-05,
+      "loss": 0.1533,
+      "step": 7500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.277391382892241e-05,
+      "loss": 0.1493,
+      "step": 8000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.232228344323007e-05,
+      "loss": 0.1457,
+      "step": 8500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.187065305753771e-05,
+      "loss": 0.1421,
+      "step": 9000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.141902267184536e-05,
+      "loss": 0.1393,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.096739228615302e-05,
+      "loss": 0.134,
+      "step": 10000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.0515761900460664e-05,
+      "loss": 0.1312,
+      "step": 10500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.0064131514768315e-05,
+      "loss": 0.128,
+      "step": 11000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.9612501129075966e-05,
+      "loss": 0.121,
+      "step": 11500
+    }
+  ],
+  "max_steps": 55355,
+  "num_train_epochs": 5,
+  "total_flos": 2.80476865363968e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c967f280bdbb1736c672d2def8880100c3a0be2adb37de762c0221ef597dce1a
+size 3311