adapter added

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: HuggingFaceH4/zephyr-7b-beta
+model-index:
+- name: pre_train_v3
+  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. -->
+
+# pre_train_v3
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the wiki_demo 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.3
+- num_epochs: 9.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a8f83acd3cf21f3b659934a1177a13aef77fc50ea280afac0d147eb38d694c
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.78,
+    "train_loss": 2.090980339050293,
+    "train_runtime": 141.8274,
+    "train_samples_per_second": 2.602,
+    "train_steps_per_second": 0.635
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.78,
+    "train_loss": 2.090980339050293,
+    "train_runtime": 141.8274,
+    "train_samples_per_second": 2.602,
+    "train_steps_per_second": 0.635
+}

trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 5, "total_steps": 90, "loss": 2.6568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019864823963335033, "epoch": 0.49, "percentage": 5.56, "elapsed_time": "0:00:08", "remaining_time": "0:02:21"}
+{"current_steps": 10, "total_steps": 90, "loss": 2.4777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019428459070078416, "epoch": 0.98, "percentage": 11.11, "elapsed_time": "0:00:16", "remaining_time": "0:02:09"}
+{"current_steps": 15, "total_steps": 90, "loss": 2.3358, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001870370067496355, "epoch": 1.46, "percentage": 16.67, "elapsed_time": "0:00:23", "remaining_time": "0:01:59"}
+{"current_steps": 20, "total_steps": 90, "loss": 2.2961, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017712717364608328, "epoch": 1.95, "percentage": 22.22, "elapsed_time": "0:00:31", "remaining_time": "0:01:51"}
+{"current_steps": 25, "total_steps": 90, "loss": 2.231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001648582089462756, "epoch": 2.44, "percentage": 27.78, "elapsed_time": "0:00:39", "remaining_time": "0:01:43"}
+{"current_steps": 30, "total_steps": 90, "loss": 2.1653, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015060539027168316, "epoch": 2.93, "percentage": 33.33, "elapsed_time": "0:00:47", "remaining_time": "0:01:35"}
+{"current_steps": 35, "total_steps": 90, "loss": 2.0799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001348046764845511, "epoch": 3.41, "percentage": 38.89, "elapsed_time": "0:00:55", "remaining_time": "0:01:26"}
+{"current_steps": 40, "total_steps": 90, "loss": 2.1272, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000117939372772616, "epoch": 3.9, "percentage": 44.44, "elapsed_time": "0:01:03", "remaining_time": "0:01:19"}
+{"current_steps": 45, "total_steps": 90, "loss": 2.0387, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010052534752553063, "epoch": 4.39, "percentage": 50.0, "elapsed_time": "0:01:10", "remaining_time": "0:01:10"}
+{"current_steps": 50, "total_steps": 90, "loss": 1.9852, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.309525318258826e-05, "epoch": 4.88, "percentage": 55.56, "elapsed_time": "0:01:18", "remaining_time": "0:01:03"}
+{"current_steps": 55, "total_steps": 90, "loss": 1.9507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.618223369742117e-05, "epoch": 5.37, "percentage": 61.11, "elapsed_time": "0:01:26", "remaining_time": "0:00:55"}
+{"current_steps": 60, "total_steps": 90, "loss": 1.9503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.030361696847705e-05, "epoch": 5.85, "percentage": 66.67, "elapsed_time": "0:01:34", "remaining_time": "0:00:47"}
+{"current_steps": 65, "total_steps": 90, "loss": 1.9554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.594509104393951e-05, "epoch": 6.34, "percentage": 72.22, "elapsed_time": "0:01:42", "remaining_time": "0:00:39"}
+{"current_steps": 70, "total_steps": 90, "loss": 1.8693, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3545848112279833e-05, "epoch": 6.83, "percentage": 77.78, "elapsed_time": "0:01:50", "remaining_time": "0:00:31"}
+{"current_steps": 75, "total_steps": 90, "loss": 1.8875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3485150687433167e-05, "epoch": 7.32, "percentage": 83.33, "elapsed_time": "0:01:58", "remaining_time": "0:00:23"}
+{"current_steps": 80, "total_steps": 90, "loss": 1.8837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.070730896136479e-06, "epoch": 7.8, "percentage": 88.89, "elapsed_time": "0:02:06", "remaining_time": "0:00:15"}
+{"current_steps": 85, "total_steps": 90, "loss": 1.889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5293777048546509e-06, "epoch": 8.29, "percentage": 94.44, "elapsed_time": "0:02:13", "remaining_time": "0:00:07"}
+{"current_steps": 90, "total_steps": 90, "loss": 1.8582, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 8.78, "percentage": 100.0, "elapsed_time": "0:02:21", "remaining_time": "0:00:00"}
+{"current_steps": 90, "total_steps": 90, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 8.78, "percentage": 100.0, "elapsed_time": "0:02:21", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.78048780487805,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00019864823963335033,
+      "loss": 2.6568,
+      "step": 5
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00019428459070078416,
+      "loss": 2.4777,
+      "step": 10
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001870370067496355,
+      "loss": 2.3358,
+      "step": 15
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00017712717364608328,
+      "loss": 2.2961,
+      "step": 20
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.0001648582089462756,
+      "loss": 2.231,
+      "step": 25
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.00015060539027168316,
+      "loss": 2.1653,
+      "step": 30
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.0001348046764845511,
+      "loss": 2.0799,
+      "step": 35
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.000117939372772616,
+      "loss": 2.1272,
+      "step": 40
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 0.00010052534752553063,
+      "loss": 2.0387,
+      "step": 45
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 8.309525318258826e-05,
+      "loss": 1.9852,
+      "step": 50
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 6.618223369742117e-05,
+      "loss": 1.9507,
+      "step": 55
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 5.030361696847705e-05,
+      "loss": 1.9503,
+      "step": 60
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 3.594509104393951e-05,
+      "loss": 1.9554,
+      "step": 65
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 2.3545848112279833e-05,
+      "loss": 1.8693,
+      "step": 70
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 1.3485150687433167e-05,
+      "loss": 1.8875,
+      "step": 75
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 6.070730896136479e-06,
+      "loss": 1.8837,
+      "step": 80
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 1.5293777048546509e-06,
+      "loss": 1.889,
+      "step": 85
+    },
+    {
+      "epoch": 8.78,
+      "learning_rate": 0.0,
+      "loss": 1.8582,
+      "step": 90
+    },
+    {
+      "epoch": 8.78,
+      "step": 90,
+      "total_flos": 1.573518009434112e+16,
+      "train_loss": 2.090980339050293,
+      "train_runtime": 141.8274,
+      "train_samples_per_second": 2.602,
+      "train_steps_per_second": 0.635
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 10,
+  "total_flos": 1.573518009434112e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa01e9b6a865bec4ce9711333292842e99e732219479879ceea190a719b9380
+size 4920