upload model checkpoints

.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

@@ -1,3 +1,76 @@
----
-license: gemma
----
+---
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- llama-duo/synth_summarize_dataset_dedup
+base_model: google/gemma-7b
+model-index:
+- name: gemma7b-summarize-claude3sonnet-2k
+  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. -->
+
+# gemma7b-summarize-claude3sonnet-2k
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset_dedup dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.6985
+
+## 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: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_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
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 29.9207       | 1.0   | 5    | 14.4322         |
+| 18.5488       | 2.0   | 10   | 10.5610         |
+| 15.0605       | 3.0   | 15   | 8.2259          |
+| 13.929        | 4.0   | 20   | 7.6256          |
+| 13.2624       | 5.0   | 25   | 7.3464          |
+| 12.6383       | 6.0   | 30   | 7.0769          |
+| 11.963        | 7.0   | 35   | 6.8804          |
+| 11.3592       | 8.0   | 40   | 6.7488          |
+| 11.0502       | 9.0   | 45   | 6.7065          |
+| 10.9441       | 10.0  | 50   | 6.6985          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "layer_replication": null,
+  "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": 8,
+  "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 sha256:50516ee4776ea07fed4dcd9472411ebe1b78194dc73de4fd1438490af368e56c
+size 6437384

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 6.698519229888916,
+    "eval_runtime": 0.2389,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.86,
+    "eval_steps_per_second": 4.186,
+    "total_flos": 1.52458893266518e+17,
+    "train_loss": 14.990281143188476,
+    "train_runtime": 123.5377,
+    "train_samples": 1984,
+    "train_samples_per_second": 24.851,
+    "train_steps_per_second": 0.405
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 6.698519229888916,
+    "eval_runtime": 0.2389,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.86,
+    "eval_steps_per_second": 4.186
+}

runs/Jun13_05-21-41_gpu1-1/events.out.tfevents.1718227351.gpu1-1.426890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cbec684ee565b4caa4dd25133e42c4b0c9bc10f1472468317cc715adbc84c5
+size 10764

runs/Jun13_05-21-41_gpu1-1/events.out.tfevents.1718227475.gpu1-1.426890.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e9d17df221fae207f9e9caea8e5560e4cd4eeb1a70ceeb87fa10404595ef87
+size 354

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 sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

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 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 1.52458893266518e+17,
+    "train_loss": 14.990281143188476,
+    "train_runtime": 123.5377,
+    "train_samples": 1984,
+    "train_samples_per_second": 24.851,
+    "train_steps_per_second": 0.405
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 187.0,
+      "learning_rate": 4e-05,
+      "loss": 36.0545,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 59.75,
+      "learning_rate": 0.0002,
+      "loss": 29.9207,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 14.432188034057617,
+      "eval_runtime": 0.2474,
+      "eval_samples_per_second": 40.424,
+      "eval_steps_per_second": 4.042,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.75,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 18.5488,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 10.560973167419434,
+      "eval_runtime": 0.2335,
+      "eval_samples_per_second": 42.825,
+      "eval_steps_per_second": 4.282,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.53125,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 15.0605,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 8.22590160369873,
+      "eval_runtime": 0.2341,
+      "eval_samples_per_second": 42.711,
+      "eval_steps_per_second": 4.271,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.3125,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 13.929,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 7.625598907470703,
+      "eval_runtime": 0.2337,
+      "eval_samples_per_second": 42.796,
+      "eval_steps_per_second": 4.28,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.78125,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 13.2624,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 7.346440315246582,
+      "eval_runtime": 0.234,
+      "eval_samples_per_second": 42.736,
+      "eval_steps_per_second": 4.274,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.625,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 12.6383,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 7.076879024505615,
+      "eval_runtime": 0.2334,
+      "eval_samples_per_second": 42.842,
+      "eval_steps_per_second": 4.284,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.0,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.963,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 6.880378723144531,
+      "eval_runtime": 0.2349,
+      "eval_samples_per_second": 42.563,
+      "eval_steps_per_second": 4.256,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 10.125,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 11.3592,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 6.748847007751465,
+      "eval_runtime": 0.2339,
+      "eval_samples_per_second": 42.76,
+      "eval_steps_per_second": 4.276,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 10.5,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 11.0502,
+      "step": 45
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 6.706507682800293,
+      "eval_runtime": 0.2365,
+      "eval_samples_per_second": 42.29,
+      "eval_steps_per_second": 4.229,
+      "step": 45
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 10.625,
+      "learning_rate": 0.0,
+      "loss": 10.9441,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 6.698519229888916,
+      "eval_runtime": 0.2341,
+      "eval_samples_per_second": 42.721,
+      "eval_steps_per_second": 4.272,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "step": 50,
+      "total_flos": 1.52458893266518e+17,
+      "train_loss": 14.990281143188476,
+      "train_runtime": 123.5377,
+      "train_samples_per_second": 24.851,
+      "train_steps_per_second": 0.405
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.52458893266518e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2f33ee2866b642c792ecedeacc8557a36d136273a6ad359d4ad4eddebe8599
+size 5176