Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: NousResearch/Yarn-Mistral-7b-128k
+tags:
+- generated_from_trainer
+model-index:
+- name: unraveled-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. -->
+
+# unraveled-7b-sft-lora
+
+This model is a fine-tuned version of [NousResearch/Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0261
+
+## 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: 4
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 2048
+- total_eval_batch_size: 32
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0242        | 0.67  | 68   | 1.0262          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- 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": "NousResearch/Yarn-Mistral-7b-128k",
+  "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",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f75c85c37063822f4fa842f7fe820f90c17337a8ce180d27f56aaeed095c43f
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.026082992553711,
+    "eval_runtime": 316.4775,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 73.023,
+    "eval_steps_per_second": 2.285,
+    "train_loss": 1.052605555338018,
+    "train_runtime": 9462.872,
+    "train_samples": 207865,
+    "train_samples_per_second": 21.966,
+    "train_steps_per_second": 0.011
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.67,
+    "eval_loss": 1.026082992553711,
+    "eval_runtime": 316.4775,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 73.023,
+    "eval_steps_per_second": 2.285
+}

runs/Nov22_06-20-04_401fa5a8015d/events.out.tfevents.1700634336.401fa5a8015d.8816.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e454bb072fa7531eff96504e50ee55150477f74ae89f52c4044d51d7e33d230
+size 4821

runs/Nov22_06-30-36_401fa5a8015d/events.out.tfevents.1700634659.401fa5a8015d.9073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2498af96eef3a5c80051c584689dd8ed2b1de297259178bb9bfc00b11bba760
+size 7437

runs/Nov22_06-30-36_401fa5a8015d/events.out.tfevents.1700644438.401fa5a8015d.9073.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a7f4f1ca9e9c81f6115fbb55b0c446ab49a9b014e8624406cfc9cc3c417651
+size 354

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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 +1,45 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": 1.052605555338018,
+    "train_runtime": 9462.872,
+    "train_samples": 207865,
+    "train_samples_per_second": 21.966,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6699507389162561,
+  "eval_steps": 500,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.999516282291988e-05,
+      "loss": 1.1236,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.987930439740757e-05,
+      "loss": 1.1227,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.95201310753273e-05,
+      "loss": 1.0994,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8931150161867917e-05,
+      "loss": 1.0843,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8126579138282502e-05,
+      "loss": 1.0675,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7125839641475074e-05,
+      "loss": 1.0559,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.595308864276666e-05,
+      "loss": 1.05,
+      "step": 30
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4636635319853274e-05,
+      "loss": 1.0419,
+      "step": 35
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3208257698153677e-05,
+      "loss": 1.0277,
+      "step": 40
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1702435557223988e-05,
+      "loss": 1.0291,
+      "step": 45
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0155518119203511e-05,
+      "loss": 1.029,
+      "step": 50
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.604846610560771e-06,
+      "loss": 1.0268,
+      "step": 55
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.0878528777274814e-06,
+      "loss": 1.0272,
+      "step": 60
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.64115581524629e-06,
+      "loss": 1.0242,
+      "step": 65
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0261898040771484,
+      "eval_runtime": 315.7522,
+      "eval_samples_per_second": 73.19,
+      "eval_steps_per_second": 2.29,
+      "step": 68
+    },
+    {
+      "epoch": 0.67,
+      "step": 68,
+      "total_flos": 1.2276051069330522e+19,
+      "train_loss": 1.052605555338018,
+      "train_runtime": 9462.872,
+      "train_samples_per_second": 21.966,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 101,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.2276051069330522e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11774ef931c1d471de51b199f3d3f1b1b493fa10399f570ef52f22f113abb4d
+size 4664