End of training

README.md

@@ -0,0 +1,81 @@
+---
+base_model: allenai/PRIMERA-multinews
+library_name: peft
+metrics:
+- rouge
+tags:
+- generated_from_trainer
+model-index:
+- name: PRIMERA-multinews-lora-finetuned
+  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. -->
+
+# PRIMERA-multinews-lora-finetuned
+
+This model is a fine-tuned version of [allenai/PRIMERA-multinews](https://huggingface.co/allenai/PRIMERA-multinews) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6767
+- Rouge1: 13.1661
+- Rouge2: 6.075
+- Rougel: 11.1948
+- Rougelsum: 12.1382
+- Gen Len: 20.0
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 16
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.2385        | 1.0   | 4725  | 1.9183          | 15.8308 | 7.6039 | 12.6624 | 14.1866   | 20.0    |
+| 2.1419        | 2.0   | 9450  | 1.8933          | 14.8545 | 6.8893 | 12.144  | 13.4623   | 20.0    |
+| 2.1286        | 3.0   | 14175 | 1.8619          | 16.2585 | 8.1431 | 13.4226 | 14.8653   | 20.0    |
+| 2.0669        | 4.0   | 18900 | 1.8129          | 15.9624 | 7.5293 | 13.3809 | 14.7765   | 20.0    |
+| 2.0448        | 5.0   | 23625 | 1.7636          | 16.2801 | 8.045  | 13.6178 | 14.996    | 20.0    |
+| 1.9831        | 6.0   | 28350 | 1.7037          | 13.8735 | 5.9956 | 10.8251 | 12.2545   | 20.0    |
+| 1.9926        | 7.0   | 33075 | 1.7623          | 13.9591 | 5.8861 | 11.112  | 12.4349   | 20.0    |
+| 1.99          | 8.0   | 37800 | 1.7247          | 13.1441 | 5.2565 | 10.7117 | 11.851    | 20.0    |
+| 1.9495        | 9.0   | 42525 | 1.7065          | 12.4863 | 4.6444 | 10.0155 | 11.3874   | 20.0    |
+| 1.9782        | 10.0  | 47250 | 1.6919          | 11.8394 | 4.0068 | 9.4554  | 10.6421   | 20.0    |
+| 1.9087        | 11.0  | 51975 | 1.6910          | 13.011  | 5.5644 | 10.7255 | 11.8532   | 20.0    |
+| 1.9693        | 12.0  | 56700 | 1.6872          | 13.2678 | 5.7966 | 11.0537 | 12.1103   | 20.0    |
+| 1.9445        | 13.0  | 61425 | 1.7084          | 13.2757 | 5.9337 | 11.084  | 12.2354   | 20.0    |
+| 1.9467        | 14.0  | 66150 | 1.6729          | 12.9202 | 5.424  | 10.5315 | 11.6661   | 20.0    |
+| 1.9582        | 15.0  | 70875 | 1.6786          | 13.2851 | 6.0806 | 11.291  | 12.2518   | 20.0    |
+| 1.9186        | 16.0  | 75600 | 1.6767          | 13.1661 | 6.075  | 11.1948 | 12.1382   | 20.0    |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/PRIMERA-multinews",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "led.decoder.layers.0.self_attn.longformer_self_attn.key",
+    "led.decoder.layers.0.self_attn.longformer_self_attn.value",
+    "led.decoder.layers.0.self_attn.longformer_self_attn.query",
+    "led.encoder.layers.0.self_attn.longformer_self_attn.key",
+    "led.encoder.layers.0.self_attn.longformer_self_attn.value",
+    "led.encoder.layers.0.self_attn.longformer_self_attn.query"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f444fff0bf4920402e1fef099a21d9792a82c14fa9b9ba7bee53ecc180e0fa2
+size 394184

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<doc-sep>": 50265
+}

runs/Jul25_05-11-06_ip-10-192-12-185/events.out.tfevents.1721884277.ip-10-192-12-185.3343.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87eafc302528ab051f4c3e2d628ef1f8fe0450464b47ddab75ba6bd373a4d43e
+size 6677

runs/Jul25_05-31-15_ip-10-192-12-14/events.out.tfevents.1721885476.ip-10-192-12-14.3246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9da9cba8409b1827fb2fa8ed09bf5a7ca7cd2f624dbadb2df61857c8a4c1915
+size 47692

special_tokens_map.json

@@ -0,0 +1,54 @@
+{
+  "additional_special_tokens": [
+    "<doc-sep>"
+  ],
+  "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": false,
+    "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 +1,68 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<doc-sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<doc-sep>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206f595aabe0bb9f8cb1495280b7a418214340ea1286e67834fdfeb6e9ea6fce
+size 5368