Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-lora-1
+  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-1
+
+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: 1.0254
+
+## 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: 1
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0313        | 0.67  | 108  | 1.0254          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+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": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086a622d4d3d1c5dc7a1a374d72f1bb3ad55462af07416110e692e63feae2862
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.025382399559021,
+    "eval_runtime": 12687.4465,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 1.821,
+    "eval_steps_per_second": 0.911,
+    "train_loss": 1.0669225134231426,
+    "train_runtime": 50855.7644,
+    "train_samples": 20786,
+    "train_samples_per_second": 0.409,
+    "train_steps_per_second": 0.003
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.025382399559021,
+    "eval_runtime": 12687.4465,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 1.821,
+    "eval_steps_per_second": 0.911
+}

runs/Dec04_19-08-28_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701716931.ip-172-16-178-34.ec2.internal.7250.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6f669a3b3af83f45b6689d7d43ab9507b165676579bf60e1bf333c62428872
+size 4665

runs/Dec04_19-10-11_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701717034.ip-172-16-178-34.ec2.internal.8616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5432354aefa91de6acd0112628f2234f1e292e95fc3de8e70400a30eabde0cbb
+size 4665

runs/Dec04_19-12-55_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701717195.ip-172-16-178-34.ec2.internal.10742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9411a80caf8c0ee558bc759c27b6311c2d2c918028a3273e7f025f64ffcd9e
+size 4665

runs/Dec04_19-14-21_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701717280.ip-172-16-178-34.ec2.internal.11896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eae9751c1d9861bdb86cae08d60f6df50569f5d0fee216f9238d81635e5dcdf
+size 4667

runs/Dec04_19-16-13_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701717397.ip-172-16-178-34.ec2.internal.13747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89438fa4da76e9d0bc026592f97ebffa81fde88b37431623eed71b7d20ab910
+size 8669

runs/Dec04_19-16-13_ip-172-16-178-34.ec2.internal/events.out.tfevents.1701780941.ip-172-16-178-34.ec2.internal.13747.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a771c757e2a192ccee17ea5c6174787c6eed5ee8ab74ee024f894ba729f52c0d
+size 354

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.model

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

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": 0.67,
+    "train_loss": 1.0669225134231426,
+    "train_runtime": 50855.7644,
+    "train_samples": 20786,
+    "train_samples_per_second": 0.409,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6650630231886847,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9998119704485016e-05,
+      "loss": 1.1733,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9953027957931658e-05,
+      "loss": 1.1282,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9812553106273848e-05,
+      "loss": 1.1452,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.957989512315489e-05,
+      "loss": 1.1346,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9257239692688907e-05,
+      "loss": 1.1056,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8847617971766577e-05,
+      "loss": 1.0978,
+      "step": 25
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 1.067,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7783649119241603e-05,
+      "loss": 1.0392,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7139297345578992e-05,
+      "loss": 1.0536,
+      "step": 40
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 1.0547,
+      "step": 45
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5656068754865388e-05,
+      "loss": 1.0304,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4831125992966386e-05,
+      "loss": 1.0428,
+      "step": 55
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 1.0502,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3053259976951134e-05,
+      "loss": 1.0294,
+      "step": 65
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.211703872229411e-05,
+      "loss": 1.0313,
+      "step": 70
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1160929141252303e-05,
+      "loss": 1.0468,
+      "step": 75
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0193913317718245e-05,
+      "loss": 1.0264,
+      "step": 80
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.225075793280693e-06,
+      "loss": 1.0222,
+      "step": 85
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.0264,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.3182738723936255e-06,
+      "loss": 1.0263,
+      "step": 95
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.3982227519528986e-06,
+      "loss": 1.051,
+      "step": 100
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.512008197995379e-06,
+      "loss": 1.0313,
+      "step": 105
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.025382399559021,
+      "eval_runtime": 12686.0816,
+      "eval_samples_per_second": 1.822,
+      "eval_steps_per_second": 0.911,
+      "step": 108
+    },
+    {
+      "epoch": 0.67,
+      "step": 108,
+      "total_flos": 1.227710764417024e+18,
+      "train_loss": 1.0669225134231426,
+      "train_runtime": 50855.7644,
+      "train_samples_per_second": 0.409,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 162,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.227710764417024e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83761e8ea3e80b8e0767530aa91bc4b8884d4311b040dc2687175898479acc3
+size 4664