End of training

README.md

@@ -0,0 +1,49 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: IDEA-CCNL/Randeng-T5-784M-QA-Chinese
+model-index:
+- name: randeng-t5-vta-qa-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. -->
+
+# randeng-t5-vta-qa-lora
+
+This model is a fine-tuned version of [IDEA-CCNL/Randeng-T5-784M-QA-Chinese](https://huggingface.co/IDEA-CCNL/Randeng-T5-784M-QA-Chinese) on the None dataset.
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "IDEA-CCNL/Randeng-T5-784M-QA-Chinese",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v",
+    "q"
+  ],
+  "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:f0e5247d9a2fd522b401cd8ffa9bcb87f0309c1dbb9f6697ad2dcd49e9dae195
+size 18915616

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CTEND]": 32597,
+  "[CTSTART]": 32596,
+  "[KNEND]": 32600,
+  "[KNSTART]": 32599,
+  "[SEP]": 32598
+}

logs/events.out.tfevents.1712674942.aa6fcc5b26c2.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2367d3982c77d02fde6163fb7b5c52ce05acc67c58852a01886b251ffc509344
+size 4184

logs/events.out.tfevents.1712675139.c0e2ac94c9ac.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04aa79371bc90a9682d87d7ff390a2b8ee853891ee8705ead9b27b0b6ba65fa
+size 4184

logs/events.out.tfevents.1712675296.d3660930026f.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb81027c3e04125dfd59d9564e8b1f1f8e3cf12f5b82858b73211333ba3742d
+size 10117

logs/events.out.tfevents.1712727955.6a532391e16b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7bba8fe126aaaffa8780adaf073155bb6fb2e83cece5cfd1c7dd2543d2eddf
+size 4915

logs/events.out.tfevents.1712728310.ee38a48f5db5.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b0c237a301eb73e7166b4b5f3d67e4b230c1734106b5e1ea5ecb8a68515d39
+size 9909

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "[CTSTART]",
+    "[CTEND]",
+    "[SEP]",
+    "[KNSTART]",
+    "[KNEND]"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65feffa65ff0378759778193852083d23349cb1b40c906e9463a12f8076ff32
+size 680811

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32596": {
+      "content": "[CTSTART]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32597": {
+      "content": "[CTEND]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32598": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32599": {
+      "content": "[KNSTART]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32600": {
+      "content": "[KNEND]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[CTSTART]",
+    "[CTEND]",
+    "[SEP]",
+    "[KNSTART]",
+    "[KNEND]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae92ca9cfa0bea99b1fa69f6c47d601e0a9455f3b311b4706b9104510cdc7df3
+size 5112