Upload 14 files

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/kaggle/input/epoch4/checkpoint-18950",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "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,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 512,
+  "min_length": 100,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c44dc808e96d3654d53b1437b65f78e4d3c064aa4d14ef72d6434cbe2e0913
+size 1294929093

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eacebba979759215815672d91845bbf41154f7fd4605c7c092a4ce96a3f61e
+size 647680813

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4bfdcfc801a11f48951918c1a4590bf798d7c837edfe2c23926f3b8455b287
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc9fd59bad2ced472f66372625179293601a4ee0c1d079378d098e5db08113a
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604586f4a4e82fb8b9f92cbc0b477bfb4cf7a2421e15d3543630d766cf9bd69e
+size 627

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 9475,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.736147757255937e-05,
+      "loss": 0.5473,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.4722955145118735e-05,
+      "loss": 0.5618,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.2094986807387866e-05,
+      "loss": 0.5662,
+      "step": 1500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.945646437994723e-05,
+      "loss": 0.5662,
+      "step": 2000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.68179419525066e-05,
+      "loss": 0.5654,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.4179419525065965e-05,
+      "loss": 0.5466,
+      "step": 3000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.154089709762533e-05,
+      "loss": 0.5468,
+      "step": 3500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.8902374670184694e-05,
+      "loss": 0.5387,
+      "step": 4000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.6263852242744064e-05,
+      "loss": 0.5383,
+      "step": 4500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3625329815303433e-05,
+      "loss": 0.5215,
+      "step": 5000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0986807387862796e-05,
+      "loss": 0.5299,
+      "step": 5500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8348284960422166e-05,
+      "loss": 0.541,
+      "step": 6000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.571503957783641e-05,
+      "loss": 0.5235,
+      "step": 6500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.3076517150395778e-05,
+      "loss": 0.5041,
+      "step": 7000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0437994722955146e-05,
+      "loss": 0.5135,
+      "step": 7500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7.804749340369394e-06,
+      "loss": 0.5302,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.16622691292876e-06,
+      "loss": 0.5206,
+      "step": 8500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.5277044854881265e-06,
+      "loss": 0.5454,
+      "step": 9000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 229.9856,
+      "eval_loss": 1.0093897581100464,
+      "eval_rouge1": 0.5781,
+      "eval_rouge2": 0.3786,
+      "eval_rougeL": 0.4342,
+      "eval_rougeLsum": 0.4342,
+      "eval_runtime": 7098.2277,
+      "eval_samples_per_second": 0.461,
+      "eval_steps_per_second": 0.23,
+      "step": 9475
+    }
+  ],
+  "max_steps": 9475,
+  "num_train_epochs": 1,
+  "total_flos": 5.116618141492838e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb66ed82467fb165e47a8ce422f676628a8fdcfd4552b5095f8f1978d8e7bc50
+size 3707