Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+model-index:
+- name: Tukan-1.1B-Chat-reasoning-sft-COLA
+  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. -->
+
+# Tukan-1.1B-Chat-reasoning-sft-COLA
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5464
+
+## 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: 6
+- eval_batch_size: 3
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 20
+- total_train_batch_size: 120
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.2.0a0+gitd925d94
+- Datasets 2.14.6
+- Tokenizers 0.15.0
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "lm_head",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b264ea9c5c8573c5bac38b0d63c8d49f62b4bc8f9b8b97dcb0cff3e141bf3a
+size 26361536

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.95,
+    "eval_loss": 1.5464149713516235,
+    "eval_runtime": 1.3809,
+    "eval_samples": 36,
+    "eval_samples_per_second": 5.069,
+    "eval_steps_per_second": 2.173,
+    "train_loss": 1.5683434009552002,
+    "train_runtime": 86.2787,
+    "train_samples": 682,
+    "train_samples_per_second": 1.414,
+    "train_steps_per_second": 0.012
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.95,
+    "eval_loss": 1.5464149713516235,
+    "eval_runtime": 1.3809,
+    "eval_samples": 36,
+    "eval_samples_per_second": 5.069,
+    "eval_steps_per_second": 2.173
+}

runs/Jan21_18-40-14_98f107f1aa39/events.out.tfevents.1705862438.98f107f1aa39.92986.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712ed0cd8b4fa3fa8a064b153e70e9a6956ca7b1d003ee82fe1acd9cbd30e66a
+size 5042

runs/Jan21_18-40-14_98f107f1aa39/events.out.tfevents.1705862526.98f107f1aa39.92986.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ea68664fafb944f5d533adc86401d8cc257e5835795112c6ee6679a642eebd
+size 354

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": "</s>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

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
+    }
+  },
+  "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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "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": 0.95,
+    "train_loss": 1.5683434009552002,
+    "train_runtime": 86.2787,
+    "train_samples": 682,
+    "train_samples_per_second": 1.414,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9523809523809523,
+  "eval_steps": 10,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0,
+      "loss": 1.5683,
+      "step": 1
+    },
+    {
+      "epoch": 0.95,
+      "step": 1,
+      "total_flos": 1535153516052480.0,
+      "train_loss": 1.5683434009552002,
+      "train_runtime": 86.2787,
+      "train_samples_per_second": 1.414,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "total_flos": 1535153516052480.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb0ef68df7eba155819ecadf94529b54aabf6815f0cfce9a25ffa9c9040fe91
+size 4792