Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0542
+
+## 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: 2
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 1024
+- total_eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0498        | 0.66  | 40   | 1.0542          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0a0+32f93b1
+- 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": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32160ca36f88d5f0a2e9826d9033bb4ffefe3fa08c7082e628f5b167dc9d4141
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.66,
+    "eval_loss": 1.0541865825653076,
+    "eval_runtime": 1943.4287,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 11.891,
+    "eval_steps_per_second": 0.744,
+    "train_loss": 1.106418876349926,
+    "train_runtime": 18557.3295,
+    "train_samples": 62359,
+    "train_samples_per_second": 3.36,
+    "train_steps_per_second": 0.003
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.66,
+    "eval_loss": 1.0541865825653076,
+    "eval_runtime": 1943.4287,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 11.891,
+    "eval_steps_per_second": 0.744
+}

runs/Nov12_19-11-33_da8ccdf2e00f/events.out.tfevents.1699816311.da8ccdf2e00f.6983.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4b632f5863ff180b092a3a0c9887b0cd1d05ed27684f284693cbe6d5a1fd97
+size 4600

runs/Nov12_20-44-28_da8ccdf2e00f/events.out.tfevents.1699821891.da8ccdf2e00f.7276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640bf4414f473c88b38fec13c6278272564597a4c9deb7b2939b752f1690d3d4
+size 4600

runs/Nov12_20-49-30_da8ccdf2e00f/events.out.tfevents.1699822184.da8ccdf2e00f.7735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38c38502ca169a9ccdeb0e546f9a6777b154ec07be9f25d8965d8ffebce60c8
+size 4366

runs/Nov12_21-14-27_da8ccdf2e00f/events.out.tfevents.1699823693.da8ccdf2e00f.8224.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da8f42597b4b1405a81e5c658a17181b3b5c8c9601d42cea586a11fc2830612
+size 4600

runs/Nov12_21-16-28_da8ccdf2e00f/events.out.tfevents.1699823823.da8ccdf2e00f.8714.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f17dd2f5aed654bbd44783a92fc3c5951bcdf3bc8b351d47036e15d28611cb8
+size 4600

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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": [],
+  "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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.66,
+    "train_loss": 1.106418876349926,
+    "train_runtime": 18557.3295,
+    "train_samples": 62359,
+    "train_samples_per_second": 3.36,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6568313021167415,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9986295347545738e-05,
+      "loss": 1.1468,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 1.1476,
+      "step": 2
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 1.1366,
+      "step": 4
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.1232,
+      "step": 6
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 1.1253,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.0947,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.1062,
+      "step": 12
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 1.1017,
+      "step": 14
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 1.0888,
+      "step": 16
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.0726,
+      "step": 18
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0734,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 1.0815,
+      "step": 22
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.0628,
+      "step": 24
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 1.0674,
+      "step": 26
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 1.0667,
+      "step": 28
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 1.0732,
+      "step": 30
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 1.0647,
+      "step": 32
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 1.0574,
+      "step": 34
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.0483,
+      "step": 36
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 1.0492,
+      "step": 38
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.0498,
+      "step": 40
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.0541661977767944,
+      "eval_runtime": 1943.1867,
+      "eval_samples_per_second": 11.893,
+      "eval_steps_per_second": 0.744,
+      "step": 40
+    },
+    {
+      "epoch": 0.66,
+      "step": 40,
+      "total_flos": 3.680138604408996e+18,
+      "train_loss": 1.106418876349926,
+      "train_runtime": 18557.3295,
+      "train_samples_per_second": 3.36,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 60,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 3.680138604408996e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adff60bda7422c945eb8aec1ca5a522788ed748871e09ae4873b72da37ce62bd
+size 4664