Upload 11 files

README.md

@@ -1,3 +1,59 @@
----
-license: unknown
----
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: openchat/openchat-3.5-0106
+model-index:
+- name: en-mr
+  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. -->
+
+# en-mr
+
+This model is a fine-tuned version of [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) on the enmr_train_template3 dataset.
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openchat/openchat-3.5-0106",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd716db1f93db0082b36e7213c6f59ca7bd30de3f86bf6ee75a584a6d8af6f6
+size 109069176

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5714873938927284,
+    "train_runtime": 18928.0922,
+    "train_samples_per_second": 1.374,
+    "train_steps_per_second": 0.343
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_turn|>",
+  "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 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'GPT4 Correct User: ' + content + '<|end_of_turn|>' + 'GPT4 Correct Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_turn|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_turn|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5714873938927284,
+    "train_runtime": 18928.0922,
+    "train_samples_per_second": 1.374,
+    "train_steps_per_second": 0.343
+}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9831129908561707,
+      "learning_rate": 4.714201332828372e-05,
+      "loss": 0.6011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8143503665924072,
+      "learning_rate": 3.921156116324626e-05,
+      "loss": 0.58,
+      "step": 2000
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9323546290397644,
+      "learning_rate": 2.8025411603587355e-05,
+      "loss": 0.5678,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5892429947853088,
+      "learning_rate": 1.6146176705708874e-05,
+      "loss": 0.5665,
+      "step": 4000
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8226454257965088,
+      "learning_rate": 6.311288588223915e-06,
+      "loss": 0.564,
+      "step": 5000
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.0760297775268555,
+      "learning_rate": 7.351550661224088e-07,
+      "loss": 0.5565,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "step": 6500,
+      "total_flos": 5.347603338846536e+17,
+      "train_loss": 0.5714873938927284,
+      "train_runtime": 18928.0922,
+      "train_samples_per_second": 1.374,
+      "train_steps_per_second": 0.343
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 6500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 5.347603338846536e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5022354f0429a72a5e7d0a27cb5d6323f1c9214e2795b4c3a429f5b651f1ba5
+size 5176