End of training

README.md

@@ -1,16 +1,14 @@
----
-library_name: peft
-base_model: owenMills/bart-pas-model
-tags:
-- base_model:adapter:owenMills/bart-pas-model
-- lora
-- transformers
-metrics:
-- rouge
-model-index:
-- name: bart-pas-lora
-  results: []
----
+---
+library_name: peft
+base_model: owenMills/bart-pas-model
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart-pas-lora
+  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. -->
@@ -19,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [owenMills/bart-pas-model](https://huggingface.co/owenMills/bart-pas-model) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6618
-- Rouge1: 46.92
-- Rouge2: 38.48
-- Rougel: 43.2
-- Rougelsum: 43.34
+- Loss: 2.6566
+- Rouge1: 47.54
+- Rouge2: 39.76
+- Rougel: 44.21
+- Rougelsum: 44.06
 
 ## Model description
 
@@ -42,29 +40,33 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 16
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 1
+- num_epochs: 10
+- mixed_precision_training: Native AMP
 - label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 4.4614        | 1.0   | 13   | 2.6618          | 46.92  | 38.48  | 43.2   | 43.34     |
+| 0.6531        | 1.0   | 12   | 2.6566          | 47.54  | 39.76  | 44.21  | 44.06     |
+| 0.3393        | 2.0   | 24   | 2.6433          | 43.83  | 36.99  | 41.69  | 41.9      |
+| 0.6332        | 3.0   | 36   | 2.6427          | 44.43  | 37.55  | 42.21  | 42.11     |
+| 0.5081        | 4.0   | 48   | 2.6570          | 41.08  | 33.84  | 38.08  | 38.37     |
 
 
 ### Framework versions
 
-- PEFT 0.17.1
-- Transformers 4.57.1
-- Pytorch 2.8.0+cpu
-- Datasets 4.2.0
-- Tokenizers 0.22.1
+- PEFT 0.13.2
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.4

adapter_config.json

@@ -1,39 +1,31 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "owenMills/bart-pas-model",
-  "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "q_proj",
-    "v_proj",
-    "out_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "SEQ_2_SEQ_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "owenMills/bart-pas-model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "out_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46dd291dd9aff30ee62021f617563be413d61b36e57540c40218b43995d62155
+oid sha256:102bc46c87182e794cf7ccee1e84b51d1369888d6e6476457e6a3114d6eee9da
 size 3558984

eval_results.json

@@ -0,0 +1,11 @@
+{
+  "eval_loss": 2.656590223312378,
+  "eval_rouge1": 47.54,
+  "eval_rouge2": 39.76,
+  "eval_rougeL": 44.21,
+  "eval_rougeLsum": 44.06,
+  "eval_runtime": 5.9984,
+  "eval_samples_per_second": 3.334,
+  "eval_steps_per_second": 1.667,
+  "epoch": 4.0
+}

special_tokens_map.json

@@ -1,51 +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
-  }
-}
+{
+  "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.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 192,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -1,62 +1,62 @@
-{
-  "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>",
-  "max_length": 256,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "stride": 0,
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
-}
+{
+  "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>",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,5 @@
+{
+  "train_loss": null,
+  "epoch": 4.0,
+  "best_model_checkpoint": "/opt/ml/output/data/checkpoint-12"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88605e9b4b9a12758e996712f8e0760d330610b609bae362b1057908e4f85e1c
-size 5969
+oid sha256:5761eec7e20fbda4837ae4eaa526fa1655ca941c29bb05f0a752453969c394d7
+size 5496