upload model checkpoint

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-100/tokenizer.json 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-4k
+  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-4k
+
+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: 3.0527
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 21.1609       | 1.0   | 10   | 12.3637         |
+| 14.2403       | 2.0   | 20   | 7.7626          |
+| 12.4548       | 3.0   | 30   | 6.8741          |
+| 8.6478        | 4.0   | 40   | 6.1412          |
+| 3.1923        | 5.0   | 50   | 4.4401          |
+| 1.9614        | 6.0   | 60   | 3.3292          |
+| 1.692         | 7.0   | 70   | 3.1272          |
+| 1.5661        | 8.0   | 80   | 3.0726          |
+| 1.5417        | 9.0   | 90   | 3.0536          |
+| 1.5287        | 10.0  | 100  | 3.0527          |
+
+
+### 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 sha256:07bdaf2d0dd9da3c645769ad26b5a93a1c24bb68c420ba54a5a01e2bd7a49583
+size 6437384

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 3.052680015563965,
+    "eval_runtime": 0.2405,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.583,
+    "eval_steps_per_second": 4.158,
+    "total_flos": 3.0491778760677786e+17,
+    "train_loss": 7.823821220397949,
+    "train_runtime": 245.6292,
+    "train_samples": 3968,
+    "train_samples_per_second": 25.038,
+    "train_steps_per_second": 0.407
+}

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /hpc2hdd/home/fwang380/OpenSource/Models/gemma-7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/fwang380/OpenSource/Models/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
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bdaf2d0dd9da3c645769ad26b5a93a1c24bb68c420ba54a5a01e2bd7a49583
+size 6437384

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5139ff570652891c589a7c1bd290d124c80243238626ea991ed128490c7ec208
+size 12939322

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df84a3867aab88e0215f9050314d2e412f420c167e3532c918e6fa08628833bf
+size 15984

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc7cdf90ce04e197a4086ea3697e60bb7b0bd977d70bc8e25264b5f73885030
+size 15984

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3e70cf0c4a77ed345315db2f8a132f160557ebddb209976276e9f7da775bb7
+size 15984

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b83b5fe6acc3c2cc448a5e1739a27fe35c2a6b953655ad2f2646c0b3dabba0
+size 15984

checkpoint-100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a3c643bca4b24994802497df06719a3fd1d6adabcbc82cd60764a38d06a92d
+size 15984

checkpoint-100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98daf325551d327eb8b7ded5d76139c22c3b3b6465249777264db331bb0798fc
+size 15984

checkpoint-100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb860996a46e64f142bd7d3923c48cc6c36833fa0ef5e369eea599d2b12e4b8d
+size 15984

checkpoint-100/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15b93383a107c2f5e246c8c7a2a2db90ed71147dbb9d5b70d1fde7fd6738c76
+size 15984

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

checkpoint-100/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
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 204.0,
+      "learning_rate": 2e-05,
+      "loss": 35.5858,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 83.0,
+      "learning_rate": 0.0001,
+      "loss": 33.1551,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.0,
+      "learning_rate": 0.0002,
+      "loss": 21.1609,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 12.363748550415039,
+      "eval_runtime": 0.2492,
+      "eval_samples_per_second": 40.136,
+      "eval_steps_per_second": 4.014,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.40625,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 16.2359,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.234375,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 14.2403,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 7.762616157531738,
+      "eval_runtime": 0.234,
+      "eval_samples_per_second": 42.735,
+      "eval_steps_per_second": 4.274,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 13.444,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.3125,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 12.4548,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.874077796936035,
+      "eval_runtime": 0.2344,
+      "eval_samples_per_second": 42.661,
+      "eval_steps_per_second": 4.266,
+      "step": 30
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 11.875,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 10.8198,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 17.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.6478,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.141203880310059,
+      "eval_runtime": 0.2347,
+      "eval_samples_per_second": 42.609,
+      "eval_steps_per_second": 4.261,
+      "step": 40
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 18.0,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 5.648,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.5625,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 3.1923,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.4401326179504395,
+      "eval_runtime": 0.236,
+      "eval_samples_per_second": 42.379,
+      "eval_steps_per_second": 4.238,
+      "step": 50
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.0001,
+      "loss": 2.2412,
+      "step": 55
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.109375,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.9614,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.3291573524475098,
+      "eval_runtime": 0.2367,
+      "eval_samples_per_second": 42.255,
+      "eval_steps_per_second": 4.225,
+      "step": 60
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 1.9609375,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.7794,
+      "step": 65
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8046875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.692,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.127150297164917,
+      "eval_runtime": 0.2355,
+      "eval_samples_per_second": 42.466,
+      "eval_steps_per_second": 4.247,
+      "step": 70
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.625,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.6184,
+      "step": 75
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.5661,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.0726068019866943,
+      "eval_runtime": 0.2359,
+      "eval_samples_per_second": 42.395,
+      "eval_steps_per_second": 4.24,
+      "step": 80
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.5625,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.5358,
+      "step": 85
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5546875,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.5417,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.0536386966705322,
+      "eval_runtime": 0.2358,
+      "eval_samples_per_second": 42.414,
+      "eval_steps_per_second": 4.241,
+      "step": 90
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.57421875,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 1.5267,
+      "step": 95
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0,
+      "loss": 1.5287,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 3.0491778760677786e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1d5fefb25f3a9e153af2c3a9a456d1a1667a4bc46c0f08a71c0e91c032403a
+size 5176

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": 3.052680015563965,
+    "eval_runtime": 0.2405,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.583,
+    "eval_steps_per_second": 4.158
+}

runs/Jun13_05-25-07_gpu1-1/events.out.tfevents.1718227559.gpu1-1.428390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e999e965f59e1c56ac3def8307dff1fe0b630f7a89b83bfb2f4486331ff71371
+size 12834

runs/Jun13_05-25-07_gpu1-1/events.out.tfevents.1718227805.gpu1-1.428390.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0bac0b27be282ce87e3c5c83fb908b4737f5ae7531b6e7037def9f8af5b9d7
+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": 3.0491778760677786e+17,
+    "train_loss": 7.823821220397949,
+    "train_runtime": 245.6292,
+    "train_samples": 3968,
+    "train_samples_per_second": 25.038,
+    "train_steps_per_second": 0.407
+}

trainer_state.json

@@ -0,0 +1,257 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 204.0,
+      "learning_rate": 2e-05,
+      "loss": 35.5858,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 83.0,
+      "learning_rate": 0.0001,
+      "loss": 33.1551,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.0,
+      "learning_rate": 0.0002,
+      "loss": 21.1609,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 12.363748550415039,
+      "eval_runtime": 0.2492,
+      "eval_samples_per_second": 40.136,
+      "eval_steps_per_second": 4.014,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.40625,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 16.2359,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.234375,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 14.2403,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 7.762616157531738,
+      "eval_runtime": 0.234,
+      "eval_samples_per_second": 42.735,
+      "eval_steps_per_second": 4.274,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 13.444,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.3125,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 12.4548,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.874077796936035,
+      "eval_runtime": 0.2344,
+      "eval_samples_per_second": 42.661,
+      "eval_steps_per_second": 4.266,
+      "step": 30
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 11.875,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 10.8198,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 17.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.6478,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.141203880310059,
+      "eval_runtime": 0.2347,
+      "eval_samples_per_second": 42.609,
+      "eval_steps_per_second": 4.261,
+      "step": 40
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 18.0,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 5.648,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.5625,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 3.1923,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.4401326179504395,
+      "eval_runtime": 0.236,
+      "eval_samples_per_second": 42.379,
+      "eval_steps_per_second": 4.238,
+      "step": 50
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.0001,
+      "loss": 2.2412,
+      "step": 55
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.109375,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.9614,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.3291573524475098,
+      "eval_runtime": 0.2367,
+      "eval_samples_per_second": 42.255,
+      "eval_steps_per_second": 4.225,
+      "step": 60
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 1.9609375,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.7794,
+      "step": 65
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8046875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.692,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.127150297164917,
+      "eval_runtime": 0.2355,
+      "eval_samples_per_second": 42.466,
+      "eval_steps_per_second": 4.247,
+      "step": 70
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.625,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.6184,
+      "step": 75
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.5661,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.0726068019866943,
+      "eval_runtime": 0.2359,
+      "eval_samples_per_second": 42.395,
+      "eval_steps_per_second": 4.24,
+      "step": 80
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.5625,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.5358,
+      "step": 85
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5546875,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.5417,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.0536386966705322,
+      "eval_runtime": 0.2358,
+      "eval_samples_per_second": 42.414,
+      "eval_steps_per_second": 4.241,
+      "step": 90
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.57421875,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 1.5267,
+      "step": 95
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0,
+      "loss": 1.5287,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.052680015563965,
+      "eval_runtime": 0.234,
+      "eval_samples_per_second": 42.735,
+      "eval_steps_per_second": 4.274,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "step": 100,
+      "total_flos": 3.0491778760677786e+17,
+      "train_loss": 7.823821220397949,
+      "train_runtime": 245.6292,
+      "train_samples_per_second": 25.038,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 3.0491778760677786e+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 sha256:2a1d5fefb25f3a9e153af2c3a9a456d1a1667a4bc46c0f08a71c0e91c032403a
+size 5176