Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-alpha
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-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. -->
+
+# zephyr-7b-sft-lora
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1445
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 4096
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.1612        | 0.36  | 16   | 2.1446          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-alpha",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b45551401b18fb70da2d3945e0eaaee1daa7943356c7ee49c1fedccbc0e306b
+size 109086672

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.36,
+    "eval_loss": 2.1445040702819824,
+    "eval_runtime": 1282.8922,
+    "eval_samples": 20342,
+    "eval_samples_per_second": 15.856,
+    "eval_steps_per_second": 0.248,
+    "train_loss": 2.1917571127414703,
+    "train_runtime": 41679.8817,
+    "train_samples": 183082,
+    "train_samples_per_second": 4.393,
+    "train_steps_per_second": 0.001
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.36,
+    "eval_loss": 2.1445040702819824,
+    "eval_runtime": 1282.8922,
+    "eval_samples": 20342,
+    "eval_samples_per_second": 15.856,
+    "eval_steps_per_second": 0.248
+}

runs/Nov27_15-21-17_ip-172-31-32-227/events.out.tfevents.1701098592.ip-172-31-32-227.26886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963297a724388c4a412e08965bdab7c77ba37717b9e2eacbea945adb541a4506
+size 4443

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_config.json

@@ -0,0 +1,46 @@
+{
+  "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": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.36,
+    "train_loss": 2.1917571127414703,
+    "train_runtime": 41679.8817,
+    "train_samples": 183082,
+    "train_samples_per_second": 4.393,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3579168123033904,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9974521146102535e-05,
+      "loss": 2.203,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.936949724999762e-05,
+      "loss": 2.2028,
+      "step": 5
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7557495743542586e-05,
+      "loss": 2.182,
+      "step": 10
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.479248986720057e-05,
+      "loss": 2.1612,
+      "step": 15
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.144601583480835,
+      "eval_runtime": 1290.2046,
+      "eval_samples_per_second": 15.766,
+      "eval_steps_per_second": 0.246,
+      "step": 16
+    },
+    {
+      "epoch": 0.36,
+      "step": 16,
+      "total_flos": 4.891029434007552e+16,
+      "train_loss": 2.1917571127414703,
+      "train_runtime": 41679.8817,
+      "train_samples_per_second": 4.393,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 44,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.891029434007552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e101299f26d499ab1b7d1309f7ac9f492a97c3154a408800887804380afe5af
+size 5624