Hash-tag Producer

README.md

@@ -2,6 +2,7 @@
 license: mit
 base_model: gogamza/kobart-summarization
 tags:
+- kobart-hashtag
 - generated_from_trainer
 model-index:
 - name: modelling

summary/README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: gogamza/kobart-summarization
+tags:
+- generated_from_trainer
+model-index:
+- name: summary
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# summary
+
+This model is a fine-tuned version of [gogamza/kobart-summarization](https://huggingface.co/gogamza/kobart-summarization) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3772
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5.6e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4775        | 1.42  | 500  | 0.3851          |
+| 0.2468        | 2.85  | 1000 | 0.3772          |
+| 0.1299        | 4.27  | 1500 | 0.4203          |
+| 0.0721        | 5.7   | 2000 | 0.4461          |
+| 0.0425        | 7.12  | 2500 | 0.4582          |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

summary/checkpoint-1000/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "gogamza/kobart-summarization",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon([email protected])",
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

summary/checkpoint-1000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.37.1"
+}

summary/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaaefe8555148be9c217d03389c6f318a062734e3d21c862428dc24dd077c966
+size 495589768

summary/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe823b34aad96a0aad5a48d7105899b4a0d93666f2505de9b7ebb3f8031b0d55
+size 991096314

summary/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc3860843d2f28a8166d3b37d46989af44566fae53e55aac0dfe4537f8511e0
+size 14244

summary/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933464ad2184cbaa671990e8d169bfba24f19cc3ee21645e3920a0851f745585
+size 1064

summary/checkpoint-1000/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.37720897793769836,
+  "best_model_checkpoint": "C:/Users/user/Documents/EWHA/log/log/modelling/summary/checkpoint-1000",
+  "epoch": 2.849002849002849,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.5350724637681156e-05,
+      "loss": 1.4776,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 0.3854794204235077,
+      "eval_runtime": 3.9836,
+      "eval_samples_per_second": 78.572,
+      "eval_steps_per_second": 10.041,
+      "step": 500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.372753623188405e-05,
+      "loss": 0.2469,
+      "step": 1000
+    },
+    {
+      "epoch": 2.85,
+      "eval_loss": 0.37720897793769836,
+      "eval_runtime": 3.9849,
+      "eval_samples_per_second": 78.547,
+      "eval_steps_per_second": 10.038,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17550,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 1000,
+  "total_flos": 2438945832960000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

summary/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
+size 4920

summary/checkpoint-2000/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "gogamza/kobart-summarization",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon([email protected])",
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

summary/checkpoint-2000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.37.1"
+}

summary/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58dc8ee0c3c6e3e50f12cbf70efb982c804e68635ab14b1819a9720d6180e061
+size 495589768

summary/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0c55dfb531c09dc50373061e36273159e0a62a424c23d6a40df63f0ceba0b2
+size 991096314

summary/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ec748c674904e17fc31da63c0d46571d28a546e5f3640632f0982b16f18198
+size 14244

summary/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dadf3cf33ef7ebd5ad575ddf367de7b19bed3e6759b50c3955496605ab9082
+size 1064

summary/checkpoint-2000/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.37720897793769836,
+  "best_model_checkpoint": "C:/Users/user/Documents/EWHA/log/log/modelling/summary/checkpoint-1000",
+  "epoch": 5.698005698005698,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.5350724637681156e-05,
+      "loss": 1.4776,
+      "step": 500
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 0.3854794204235077,
+      "eval_runtime": 3.9836,
+      "eval_samples_per_second": 78.572,
+      "eval_steps_per_second": 10.041,
+      "step": 500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.372753623188405e-05,
+      "loss": 0.2469,
+      "step": 1000
+    },
+    {
+      "epoch": 2.85,
+      "eval_loss": 0.37720897793769836,
+      "eval_runtime": 3.9849,
+      "eval_samples_per_second": 78.547,
+      "eval_steps_per_second": 10.038,
+      "step": 1000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 5.210434782608695e-05,
+      "loss": 0.1303,
+      "step": 1500
+    },
+    {
+      "epoch": 4.27,
+      "eval_loss": 0.4201067090034485,
+      "eval_runtime": 3.9854,
+      "eval_samples_per_second": 78.536,
+      "eval_steps_per_second": 10.037,
+      "step": 1500
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 5.0481159420289856e-05,
+      "loss": 0.0722,
+      "step": 2000
+    },
+    {
+      "epoch": 5.7,
+      "eval_loss": 0.4348262846469879,
+      "eval_runtime": 3.9835,
+      "eval_samples_per_second": 78.574,
+      "eval_steps_per_second": 10.041,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17550,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 1000,
+  "total_flos": 4877891665920000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

summary/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
+size 4920

summary/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "gogamza/kobart-summarization",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon([email protected])",
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

summary/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.37.1"
+}

summary/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58dc8ee0c3c6e3e50f12cbf70efb982c804e68635ab14b1819a9720d6180e061
+size 495589768

summary/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a3fccd80e5474dd784ce999ac5d814a06dd74525db50ff68adc5fc250eba2a
+size 4920