Initial upload of chatbot model checkpoint

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "faisalahmad/autotrain-nsut-nlp-project-textsummarization-791824374",
+  "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": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "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": null,
+  "normalize_before": false,
+  "num_beams": null,
+  "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": "4.47.1",
+  "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": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d986ca36ff64d1331dbcc320c625777a5f833661cce0e648ee65963b48fc5950
+size 1625426996

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9e2b5b1cbd70ef160b6dc33ec54c7d1461e145f997d5f98fd5b50ede03017e
+size 3250745679

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574dd9c596be40809a61060949693a5cd7f802357f4a10f9dac559377c5023af
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a799d5f4a5028d969e87850f936dc2534b34dbdc58357e2d21f799bd46e0e2e5
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 25.306283950805664,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 9.5671,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.41864013671875,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 9.1661,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 16.571876525878906,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 8.5779,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 11.903717041015625,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 8.6565,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.543700218200684,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 7.799,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 9.900014877319336,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 7.1091,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.66036605834961,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 6.9738,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 10.709378242492676,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 6.6687,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 12.942888259887695,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 6.7592,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.488504409790039,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 6.3509,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 16.680503845214844,
+      "learning_rate": 4.4e-06,
+      "loss": 5.9777,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 23.38302993774414,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 5.6314,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 23.684436798095703,
+      "learning_rate": 5.2e-06,
+      "loss": 5.0907,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 21.124048233032227,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 4.4654,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 19.794771194458008,
+      "learning_rate": 6e-06,
+      "loss": 4.3731,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 319986538905600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8528ef06abcf45314015025bb03077c1099febde6bf0ed6f19474d6ad6e42b
+size 5304