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-replicate-1201-52
+  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-replicate-1201-52
+
+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: 1.0663
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0705        | 0.67  | 34   | 1.0663          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1
+- 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": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd74a6d4832e822989801765f295d4727c6eafb63ad389ac112b635e4d335fc2
+size 109086672

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "train_loss": 1.0919692165711348,
+    "train_runtime": 10581.6037,
+    "train_samples": 207865,
+    "train_samples_per_second": 19.644,
+    "train_steps_per_second": 0.005
+}

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": 1.0919692165711348,
+    "train_runtime": 10581.6037,
+    "train_samples": 207865,
+    "train_samples_per_second": 19.644,
+    "train_steps_per_second": 0.005
+}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6699507389162561,
+  "eval_steps": 500,
+  "global_step": 34,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 1.1284,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.1279,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.1117,
+      "step": 10
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 1.0956,
+      "step": 15
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.0814,
+      "step": 20
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 1.0748,
+      "step": 25
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.0705,
+      "step": 30
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.066253662109375,
+      "eval_runtime": 359.4454,
+      "eval_samples_per_second": 64.293,
+      "eval_steps_per_second": 1.007,
+      "step": 34
+    },
+    {
+      "epoch": 0.67,
+      "step": 34,
+      "total_flos": 5.175876094263296e+16,
+      "train_loss": 1.0919692165711348,
+      "train_runtime": 10581.6037,
+      "train_samples_per_second": 19.644,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5.175876094263296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbb7c29564fc02ab161e77f4402558614e22b5cab11f9f0b62c9bc54e5989c7
+size 5688