upload model checkpoint

.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 +1,74 @@
----
-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-1k
+  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-1k
+
+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: 8.5689
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 33.9156       | 0.8   | 2    | 16.5602         |
+| 27.435        | 2.0   | 5    | 13.6870         |
+| 27.435        | 2.8   | 7    | 12.0752         |
+| 17.6281       | 4.0   | 10   | 10.1279         |
+| 17.6281       | 4.8   | 12   | 9.2971          |
+| 15.107        | 6.0   | 15   | 8.7323          |
+| 15.107        | 6.8   | 17   | 8.6064          |
+| 14.5856       | 8.0   | 20   | 8.5689          |
+
+
+### 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": [
+    "q_proj",
+    "v_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 sha256:61f00bb6277ceab6ae4e49684e1c6f0099925a9756505f7bfc72e9a655a1019e
+size 6437384

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.0,
+    "eval_loss": 8.568929672241211,
+    "eval_runtime": 0.2392,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.809,
+    "eval_steps_per_second": 4.181,
+    "total_flos": 6.098355666236211e+16,
+    "train_loss": 19.012953186035155,
+    "train_runtime": 50.5903,
+    "train_samples": 992,
+    "train_samples_per_second": 30.045,
+    "train_steps_per_second": 0.395
+}

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": 8.0,
+    "eval_loss": 8.568929672241211,
+    "eval_runtime": 0.2392,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.809,
+    "eval_steps_per_second": 4.181
+}

runs/Jun13_05-19-43_gpu1-1/events.out.tfevents.1718227223.gpu1-1.425366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7ef0ea1bf105da955ba2492f0a6092d0adcbcee2bd65c6c69ca95b5a97935d
+size 8990

runs/Jun13_05-19-43_gpu1-1/events.out.tfevents.1718227274.gpu1-1.425366.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f334c1fe2eaedc5d178ea1db99adb69698eab8cd48a46e4399f81781e16193
+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": 8.0,
+    "total_flos": 6.098355666236211e+16,
+    "train_loss": 19.012953186035155,
+    "train_runtime": 50.5903,
+    "train_samples": 992,
+    "train_samples_per_second": 30.045,
+    "train_steps_per_second": 0.395
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 166.0,
+      "learning_rate": 0.0001,
+      "loss": 33.9156,
+      "step": 1
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 16.560213088989258,
+      "eval_runtime": 0.2548,
+      "eval_samples_per_second": 39.24,
+      "eval_steps_per_second": 3.924,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 22.625,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 27.435,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 13.68699836730957,
+      "eval_runtime": 0.2314,
+      "eval_samples_per_second": 43.206,
+      "eval_steps_per_second": 4.321,
+      "step": 5
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 12.075172424316406,
+      "eval_runtime": 0.2412,
+      "eval_samples_per_second": 41.466,
+      "eval_steps_per_second": 4.147,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.3125,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 17.6281,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 10.12792682647705,
+      "eval_runtime": 0.2331,
+      "eval_samples_per_second": 42.906,
+      "eval_steps_per_second": 4.291,
+      "step": 10
+    },
+    {
+      "epoch": 4.8,
+      "eval_loss": 9.297090530395508,
+      "eval_runtime": 0.2318,
+      "eval_samples_per_second": 43.135,
+      "eval_steps_per_second": 4.314,
+      "step": 12
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 15.107,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 8.732256889343262,
+      "eval_runtime": 0.2336,
+      "eval_samples_per_second": 42.814,
+      "eval_steps_per_second": 4.281,
+      "step": 15
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 8.606382369995117,
+      "eval_runtime": 0.2466,
+      "eval_samples_per_second": 40.544,
+      "eval_steps_per_second": 4.054,
+      "step": 17
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.984375,
+      "learning_rate": 0.0,
+      "loss": 14.5856,
+      "step": 20
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 8.568929672241211,
+      "eval_runtime": 0.2329,
+      "eval_samples_per_second": 42.94,
+      "eval_steps_per_second": 4.294,
+      "step": 20
+    },
+    {
+      "epoch": 8.0,
+      "step": 20,
+      "total_flos": 6.098355666236211e+16,
+      "train_loss": 19.012953186035155,
+      "train_runtime": 50.5903,
+      "train_samples_per_second": 30.045,
+      "train_steps_per_second": 0.395
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 6.098355666236211e+16,
+  "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:dfa20eb84d934942e356ebb98174bc5b0146d01b3c76f200fef927cbb9fe5f14
+size 5176