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: 1.0052
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9999        | 0.67  | 136  | 1.0053          |
+
+
+### 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": "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",
+    "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:d4e7112cc3fd1d00c0dd964482b4fd6c8d9b256193941da9223bddebd8a13392
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.0052200555801392,
+    "eval_runtime": 2917.7145,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 7.921,
+    "eval_steps_per_second": 0.495,
+    "train_loss": 1.030409187078476,
+    "train_runtime": 89444.4373,
+    "train_samples": 207865,
+    "train_samples_per_second": 2.324,
+    "train_steps_per_second": 0.002
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.0052200555801392,
+    "eval_runtime": 2917.7145,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 7.921,
+    "eval_steps_per_second": 0.495
+}

runs/Dec06_15-32-26_469bbe048c6f/events.out.tfevents.1701848086.469bbe048c6f.19798.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1573cc914322b130a2ddc16d0e839416188d65a664772abe3a06ac925ffa37
+size 4260

runs/Dec06_16-41-43_469bbe048c6f/events.out.tfevents.1701852189.469bbe048c6f.34153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa90c79214768dee4db685446f17248706e3c280424ec8f994820e9fd18797f
+size 4260

runs/Dec06_17-57-16_469bbe048c6f/events.out.tfevents.1701856726.469bbe048c6f.48301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315c5b8bc467e384a51410495065800888412393abedaefe7ba75045c8c3f0dc
+size 4260

runs/Dec06_18-00-47_469bbe048c6f/events.out.tfevents.1701856936.469bbe048c6f.49356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4971e1227acaaceff2a52ce38542552e0e89a97631f0c98ef8376106baad0e
+size 4260

runs/Dec06_18-06-11_469bbe048c6f/events.out.tfevents.1701857263.469bbe048c6f.51144.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbc40da4924299ab585759fe464ce0e72270ad4f8d455c35f8bdab782c435db
+size 4260

runs/Dec06_19-09-56_469bbe048c6f/events.out.tfevents.1701861084.469bbe048c6f.67461.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d96db57d7a4d3aae3ff21af3d167539813ccc05f90543483656f2c37a66c9632
+size 4260

runs/Dec06_19-27-03_469bbe048c6f/events.out.tfevents.1701862118.469bbe048c6f.71395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463607779f87972cb2f3c515ea8536ec1c88525cb55288788d5e9128a71d6afe
+size 4260

runs/Dec06_19-31-57_469bbe048c6f/events.out.tfevents.1701862358.469bbe048c6f.73360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46d883b44e7e7942d3ba5c5f28b8c640fdd96b5a964ead2e55a863d61a37ad3
+size 4648

runs/Dec06_19-33-52_469bbe048c6f/events.out.tfevents.1701862474.469bbe048c6f.74562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ed4e06edd5d3c2ae23313ee6ecd36700951c5180f1c98445e0d5e579849885
+size 4648

runs/Dec06_19-45-27_469bbe048c6f/events.out.tfevents.1701863172.469bbe048c6f.77340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d1cd74921402d4edc51a81c08ff677262e4365f0a6ebd6296f5601cab50115
+size 4649

runs/Dec06_20-04-31_469bbe048c6f/events.out.tfevents.1701864314.469bbe048c6f.81476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1fe6b093a633d5b346d47807db3e0afb8a2238c4c55c8131082b540bd81812
+size 5573

runs/Dec08_10-30-02_469bbe048c6f/events.out.tfevents.1702002696.469bbe048c6f.261073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0cc01d4ec585797a4ba3158f0b22e80d41e95a3e5d736a54e162372901d01ba
+size 4260

runs/Dec08_10-39-03_469bbe048c6f/events.out.tfevents.1702003237.469bbe048c6f.263926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461d6821bbeea01ad890e70efe3456c00f98625fb4d1c39170b5ff66d474dd96
+size 4260

runs/Dec08_11-06-32_469bbe048c6f/events.out.tfevents.1702004883.469bbe048c6f.3119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd39f7c3ab234716865e56f9f544461d0d708268022f9600b0c2fd7df0627df
+size 9203

runs/Dec08_11-06-32_469bbe048c6f/events.out.tfevents.1702098840.469bbe048c6f.3119.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73042ab8d5f81071a3ce0157e69c3d357d861821e4b5b462b6361c188df90b2
+size 359

runs/Dec09_13-44-15_469bbe048c6f/events.out.tfevents.1702100817.469bbe048c6f.1525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22259bba26ad7958f9a63d9f777b8400061b8881ff66e51354f7fd35d6d3b803
+size 9203

runs/Dec09_13-44-15_469bbe048c6f/events.out.tfevents.1702193178.469bbe048c6f.1525.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caef691248561fcef04a2d48a867286714c70b681f6daf220a47bff94a53a331
+size 359

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": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "train_loss": 1.030409187078476,
+    "train_runtime": 89444.4373,
+    "train_samples": 207865,
+    "train_samples_per_second": 2.324,
+    "train_steps_per_second": 0.002
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6699507389162561,
+  "eval_steps": 500,
+  "global_step": 136,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9998802517966852e-05,
+      "loss": 1.1244,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 1.122,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 1.1164,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 1.0903,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 1.0803,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 1.0711,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 1.0549,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 1.0363,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 1.038,
+      "step": 40
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 1.0281,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 1.0167,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 1.0258,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 1.0134,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 1.0172,
+      "step": 65
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 1.0135,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 1.0109,
+      "step": 75
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 0.9973,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 1.0118,
+      "step": 85
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1770339692844484e-05,
+      "loss": 1.0013,
+      "step": 90
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1004233054136726e-05,
+      "loss": 1.0107,
+      "step": 95
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0232116539815558e-05,
+      "loss": 1.0039,
+      "step": 100
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 1.0032,
+      "step": 105
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.688345254588579e-06,
+      "loss": 1.008,
+      "step": 110
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.92592924888925e-06,
+      "loss": 1.0066,
+      "step": 115
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.175925608204428e-06,
+      "loss": 1.006,
+      "step": 120
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.442822761362015e-06,
+      "loss": 1.0059,
+      "step": 125
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.731007993667155e-06,
+      "loss": 1.001,
+      "step": 130
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.044741191005908e-06,
+      "loss": 0.9999,
+      "step": 135
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.005275845527649,
+      "eval_runtime": 2913.4219,
+      "eval_samples_per_second": 7.932,
+      "eval_steps_per_second": 0.496,
+      "step": 136
+    },
+    {
+      "epoch": 0.67,
+      "step": 136,
+      "total_flos": 1.227587501862106e+19,
+      "train_loss": 1.030409187078476,
+      "train_runtime": 89444.4373,
+      "train_samples_per_second": 2.324,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 203,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.227587501862106e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4abbb7794a5869c706f86ff93250d606255d477d220e7a635acef423d64f2ec
+size 4664