Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-7b
+datasets:
+- generator
+model-index:
+- name: gemma-7b-sft-qlora-no-robots2
+  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. -->
+
+# gemma-7b-sft-qlora-no-robots2
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3843
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 20.4692       | 0.91  | 5    | 7.4399          |
+| 12.9912       | 2.0   | 11   | 6.6074          |
+| 10.1734       | 2.91  | 16   | 6.0225          |
+| 9.8269        | 4.0   | 22   | 3.5503          |
+| 5.2353        | 4.91  | 27   | 1.6505          |
+| 1.6367        | 6.0   | 33   | 1.4912          |
+| 1.4714        | 6.91  | 38   | 1.4201          |
+| 1.3916        | 8.0   | 44   | 1.3933          |
+| 1.2832        | 8.91  | 49   | 1.3882          |
+| 1.2863        | 9.09  | 50   | 1.3843          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158f6434388d74e740a403f60fbe1f0ba8fb3c2780d68868792155e72c59531c
+size 100060536

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.09,
+    "train_loss": 6.66651237487793,
+    "train_runtime": 191.2414,
+    "train_samples": 926,
+    "train_samples_per_second": 4.602,
+    "train_steps_per_second": 0.261
+}

runs/Apr11_10-57-09_deep-diver-main-stupid-firefox-1-0-0/events.out.tfevents.1712847546.deep-diver-main-stupid-firefox-1-0-0.520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897f667347f0fbc13396f5e91b2c12e95c64395b026720a6c147f32d425cfa57
+size 10672

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.09,
+    "train_loss": 6.66651237487793,
+    "train_runtime": 191.2414,
+    "train_samples": 926,
+    "train_samples_per_second": 4.602,
+    "train_steps_per_second": 0.261
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.090909090909092,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 220.0,
+      "learning_rate": 4e-05,
+      "loss": 24.9691,
+      "step": 1
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 21.75,
+      "learning_rate": 0.0002,
+      "loss": 20.4692,
+      "step": 5
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 7.439934253692627,
+      "eval_runtime": 0.5593,
+      "eval_samples_per_second": 3.576,
+      "eval_steps_per_second": 1.788,
+      "step": 5
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 22.875,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 12.9912,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.607400894165039,
+      "eval_runtime": 0.5606,
+      "eval_samples_per_second": 3.567,
+      "eval_steps_per_second": 1.784,
+      "step": 11
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 3.96875,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 10.1734,
+      "step": 15
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 6.02254581451416,
+      "eval_runtime": 0.5738,
+      "eval_samples_per_second": 3.485,
+      "eval_steps_per_second": 1.743,
+      "step": 16
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 13.875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.8269,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.550281047821045,
+      "eval_runtime": 0.5671,
+      "eval_samples_per_second": 3.527,
+      "eval_steps_per_second": 1.763,
+      "step": 22
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 22.5,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 5.2353,
+      "step": 25
+    },
+    {
+      "epoch": 4.91,
+      "eval_loss": 1.6504679918289185,
+      "eval_runtime": 0.5777,
+      "eval_samples_per_second": 3.462,
+      "eval_steps_per_second": 1.731,
+      "step": 27
+    },
+    {
+      "epoch": 5.45,
+      "grad_norm": 3.078125,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.6367,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.4912230968475342,
+      "eval_runtime": 0.5649,
+      "eval_samples_per_second": 3.54,
+      "eval_steps_per_second": 1.77,
+      "step": 33
+    },
+    {
+      "epoch": 6.36,
+      "grad_norm": 1.109375,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4714,
+      "step": 35
+    },
+    {
+      "epoch": 6.91,
+      "eval_loss": 1.420060157775879,
+      "eval_runtime": 0.5812,
+      "eval_samples_per_second": 3.441,
+      "eval_steps_per_second": 1.72,
+      "step": 38
+    },
+    {
+      "epoch": 7.27,
+      "grad_norm": 1.1171875,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.3916,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.3933132886886597,
+      "eval_runtime": 0.5657,
+      "eval_samples_per_second": 3.536,
+      "eval_steps_per_second": 1.768,
+      "step": 44
+    },
+    {
+      "epoch": 8.18,
+      "grad_norm": 0.95703125,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.2832,
+      "step": 45
+    },
+    {
+      "epoch": 8.91,
+      "eval_loss": 1.3881534337997437,
+      "eval_runtime": 0.5859,
+      "eval_samples_per_second": 3.414,
+      "eval_steps_per_second": 1.707,
+      "step": 49
+    },
+    {
+      "epoch": 9.09,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.0,
+      "loss": 1.2863,
+      "step": 50
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 1.3843274116516113,
+      "eval_runtime": 0.5652,
+      "eval_samples_per_second": 3.539,
+      "eval_steps_per_second": 1.769,
+      "step": 50
+    },
+    {
+      "epoch": 9.09,
+      "step": 50,
+      "total_flos": 7.66894376306606e+16,
+      "train_loss": 6.66651237487793,
+      "train_runtime": 191.2414,
+      "train_samples_per_second": 4.602,
+      "train_steps_per_second": 0.261
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7.66894376306606e+16,
+  "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:ae6561d9a2ba6b19873852cb3e8304930591bbee7c5406b15953f10b919f4e65
+size 5112