Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- unsloth
+- generated_from_trainer
+base_model: unsloth/mistral-7b
+model-index:
+- name: shortstep_test
+  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. -->
+
+# shortstep_test
+
+This model is a fine-tuned version of [unsloth/mistral-7b](https://huggingface.co/unsloth/mistral-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3442
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29657552ffc76ade035236e5ed951487d72679e09887ffed5a1f5d85e84000a3
+size 167832240

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 0.344218909740448,
+    "eval_runtime": 88.5315,
+    "eval_samples": 249,
+    "eval_samples_per_second": 2.813,
+    "eval_steps_per_second": 0.361,
+    "train_loss": 0.4382333517074585,
+    "train_runtime": 136.4197,
+    "train_samples": 2854,
+    "train_samples_per_second": 0.586,
+    "train_steps_per_second": 0.037
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.03,
+    "eval_loss": 0.344218909740448,
+    "eval_runtime": 88.5315,
+    "eval_samples": 249,
+    "eval_samples_per_second": 2.813,
+    "eval_steps_per_second": 0.361
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "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": 0.03,
+    "train_loss": 0.4382333517074585,
+    "train_runtime": 136.4197,
+    "train_samples": 2854,
+    "train_samples_per_second": 0.586,
+    "train_steps_per_second": 0.037
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.028011204481792718,
+  "eval_steps": 50,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 0.5943,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.4897,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.3496,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "step": 5,
+      "total_flos": 2.119653912064819e+16,
+      "train_loss": 0.4382333517074585,
+      "train_runtime": 136.4197,
+      "train_samples_per_second": 0.586,
+      "train_steps_per_second": 0.037
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 2.119653912064819e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bff405159ed3e6f58965cbf91f6ad9c23422fbc2ad504e170ea355f6a7db0d6
+size 4728