Upload 14 files

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</t>": 50268,
+  "</y>": 50266,
+  "<t>": 50267,
+  "<y>": 50265
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "/lustre/projects/cardiff/bart/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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50269
+}

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": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4c83d1eb834c25de63fcf7824f5bad9f406238a1c46c5fe501863156ec9a11
+size 1115539909

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d782716cf1ce1ff640e15fd51d52da4345ac69301c7bbb63b7c406233df8acf
+size 557983517

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387ae6e8ba4ee851dcc51b14b35f963e0e72ed6f6e1553f809b8c92ea741b060
+size 17641

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59fbdd7fc2f2a37411ab9caa9162342c6dc907eab42605d92b41b86a140a26d
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae00c8447b588fcb5d139f5b093c7f392279e0f811a782b0fa382e588e8bfc0
+size 627

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<y>",
+    "</y>",
+    "<t>",
+    "</t>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/lustre/projects/cardiff/bart/bart-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.7840577960014343,
+  "best_model_checkpoint": "/lustre/projects/cardiff/husu_expts/results/expt3/checkpoint-2000",
+  "epoch": 10.52553785514863,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.26,
+      "learning_rate": 3.7851351351351354e-05,
+      "loss": 1.2598,
+      "step": 1000
+    },
+    {
+      "epoch": 5.26,
+      "eval_loss": 0.7679372429847717,
+      "eval_runtime": 1717.5381,
+      "eval_samples_per_second": 911.289,
+      "eval_steps_per_second": 14.239,
+      "step": 1000
+    },
+    {
+      "epoch": 10.53,
+      "learning_rate": 2.433783783783784e-05,
+      "loss": 0.5466,
+      "step": 2000
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 0.7840577960014343,
+      "eval_runtime": 1693.2394,
+      "eval_samples_per_second": 924.366,
+      "eval_steps_per_second": 14.443,
+      "step": 2000
+    }
+  ],
+  "max_steps": 3800,
+  "num_train_epochs": 20,
+  "total_flos": 3.12611882139648e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6e3495a3a4251cfafcb91243ad320788b115c70505a22456f7f42cbeab0a1a
+size 3643