diff --git a/README.md b/README.md
index 154df8298fab5ecf322016157858e08cd1bccbe1..1fc0eba30f5d1b3cc856457fb7fddc5e6fdd6ac2 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,153 @@
---
license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model-index:
+- name: qlora-out
+ 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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+ - path: totally-not-an-llm/ZorgonChat
+ type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 4
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# qlora-out
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3466
+
+## 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
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.9295 | 0.03 | 1 | 3.9073 |
+| 3.5364 | 0.25 | 8 | 3.6199 |
+| 3.263 | 0.5 | 16 | 3.1821 |
+| 2.798 | 0.75 | 24 | 2.8962 |
+| 2.7787 | 1.0 | 32 | 2.6773 |
+| 2.5959 | 1.25 | 40 | 2.5506 |
+| 2.4793 | 1.5 | 48 | 2.4955 |
+| 2.5221 | 1.75 | 56 | 2.4613 |
+| 2.4384 | 2.0 | 64 | 2.4055 |
+| 2.295 | 2.25 | 72 | 2.3923 |
+| 2.3943 | 2.5 | 80 | 2.3862 |
+| 2.2398 | 2.75 | 88 | 2.3605 |
+| 2.2693 | 3.0 | 96 | 2.3526 |
+| 2.425 | 3.25 | 104 | 2.3471 |
+| 2.2857 | 3.5 | 112 | 2.3468 |
+| 2.2448 | 3.75 | 120 | 2.3451 |
+| 2.1836 | 4.0 | 128 | 2.3466 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.2+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0
\ No newline at end of file
diff --git a/adapter_config.json b/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..28a5d05472d8cd3bfe780706c0eded9ae55cc02a
--- /dev/null
+++ b/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "down_proj",
+ "q_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/adapter_model.bin b/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eb3ca9d56364a8e85cbccf2959527429e61776b7
--- /dev/null
+++ b/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3863c09db8a8ee37f6c92e820fd3918dba26368631f34bba226156413c6f68bd
+size 50573978
diff --git a/checkpoint-128/README.md b/checkpoint-128/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..78aadd3258d05c05cabc678473b6f0942cd441c7
--- /dev/null
+++ b/checkpoint-128/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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
\ No newline at end of file
diff --git a/checkpoint-128/adapter_config.json b/checkpoint-128/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..28a5d05472d8cd3bfe780706c0eded9ae55cc02a
--- /dev/null
+++ b/checkpoint-128/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "down_proj",
+ "q_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-128/adapter_model.safetensors b/checkpoint-128/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..196e6d0818b109c6c700d7652c88c5280c1afb60
--- /dev/null
+++ b/checkpoint-128/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528e075df49b7bbd123228a3b95349c09b3e4aff529a6761814d25530514b3ec
+size 50503848
diff --git a/checkpoint-128/optimizer.pt b/checkpoint-128/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3eee76973544f0a79ba522d8f6aaa319b2075d4d
--- /dev/null
+++ b/checkpoint-128/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2662bde842785223ccfc20324eb816ad2974916f34f883ea7c17e0bfd3e93bd
+size 202035450
diff --git a/checkpoint-128/rng_state.pth b/checkpoint-128/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..adab1e7675bf55fc0dff7d84393e57e138d23f40
--- /dev/null
+++ b/checkpoint-128/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46048a3692b100b154cf7c38df5e2ce5c28c9c56bbbf5e17fe2196b8374656f
+size 14244
diff --git a/checkpoint-128/scheduler.pt b/checkpoint-128/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ee5b484f425ff0c2699435e9c95a9e3b42b52b87
--- /dev/null
+++ b/checkpoint-128/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968a6dcbda34982ad43f2af2e04e5edf94e043c521201e71b1583695497d18e0
+size 1064
diff --git a/checkpoint-128/special_tokens_map.json b/checkpoint-128/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/checkpoint-128/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "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": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-128/tokenizer.model b/checkpoint-128/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/checkpoint-128/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/checkpoint-128/tokenizer_config.json b/checkpoint-128/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86
--- /dev/null
+++ b/checkpoint-128/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "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>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "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,
+ "use_fast": true
+}
diff --git a/checkpoint-128/trainer_state.json b/checkpoint-128/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4beddca44366228dc8e5a3adac5d1b24ffa119b7
--- /dev/null
+++ b/checkpoint-128/trainer_state.json
@@ -0,0 +1,1053 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 4.0,
+ "eval_steps": 8,
+ "global_step": 128,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.5859375,
+ "learning_rate": 2e-05,
+ "loss": 3.9295,
+ "step": 1
+ },
+ {
+ "epoch": 0.03,
+ "eval_loss": 3.907318115234375,
+ "eval_runtime": 1.2713,
+ "eval_samples_per_second": 11.012,
+ "eval_steps_per_second": 5.506,
+ "step": 1
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.5078125,
+ "learning_rate": 4e-05,
+ "loss": 3.805,
+ "step": 2
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.63671875,
+ "learning_rate": 6e-05,
+ "loss": 3.8521,
+ "step": 3
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 0.609375,
+ "learning_rate": 8e-05,
+ "loss": 3.8947,
+ "step": 4
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 0.546875,
+ "learning_rate": 0.0001,
+ "loss": 3.6494,
+ "step": 5
+ },
+ {
+ "epoch": 0.19,
+ "grad_norm": 0.50390625,
+ "learning_rate": 0.00012,
+ "loss": 3.6457,
+ "step": 6
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.640625,
+ "learning_rate": 0.00014,
+ "loss": 3.967,
+ "step": 7
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.494140625,
+ "learning_rate": 0.00016,
+ "loss": 3.5364,
+ "step": 8
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 3.6198840141296387,
+ "eval_runtime": 1.2681,
+ "eval_samples_per_second": 11.04,
+ "eval_steps_per_second": 5.52,
+ "step": 8
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 0.51171875,
+ "learning_rate": 0.00018,
+ "loss": 3.5216,
+ "step": 9
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.0002,
+ "loss": 3.677,
+ "step": 10
+ },
+ {
+ "epoch": 0.34,
+ "grad_norm": 0.734375,
+ "learning_rate": 0.00019996456111234527,
+ "loss": 3.058,
+ "step": 11
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 0.66796875,
+ "learning_rate": 0.0001998582695676762,
+ "loss": 3.1333,
+ "step": 12
+ },
+ {
+ "epoch": 0.41,
+ "grad_norm": 0.8359375,
+ "learning_rate": 0.000199681200703075,
+ "loss": 3.38,
+ "step": 13
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00019943348002101371,
+ "loss": 3.1371,
+ "step": 14
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 0.65625,
+ "learning_rate": 0.00019911528310040074,
+ "loss": 3.1479,
+ "step": 15
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 0.6484375,
+ "learning_rate": 0.00019872683547213446,
+ "loss": 3.263,
+ "step": 16
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 3.1820719242095947,
+ "eval_runtime": 1.2692,
+ "eval_samples_per_second": 11.031,
+ "eval_steps_per_second": 5.515,
+ "step": 16
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 0.53125,
+ "learning_rate": 0.00019826841245925212,
+ "loss": 2.9833,
+ "step": 17
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.5703125,
+ "learning_rate": 0.00019774033898178667,
+ "loss": 3.0787,
+ "step": 18
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.71484375,
+ "learning_rate": 0.00019714298932647098,
+ "loss": 3.4132,
+ "step": 19
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.73046875,
+ "learning_rate": 0.0001964767868814516,
+ "loss": 2.7304,
+ "step": 20
+ },
+ {
+ "epoch": 0.66,
+ "grad_norm": 0.55078125,
+ "learning_rate": 0.00019574220383620055,
+ "loss": 3.0116,
+ "step": 21
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.00019493976084683813,
+ "loss": 2.9474,
+ "step": 22
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.61328125,
+ "learning_rate": 0.00019407002666710336,
+ "loss": 2.9415,
+ "step": 23
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00019313361774523385,
+ "loss": 2.798,
+ "step": 24
+ },
+ {
+ "epoch": 0.75,
+ "eval_loss": 2.896176815032959,
+ "eval_runtime": 1.2765,
+ "eval_samples_per_second": 10.967,
+ "eval_steps_per_second": 5.484,
+ "step": 24
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 0.8046875,
+ "learning_rate": 0.00019213119778704128,
+ "loss": 3.2157,
+ "step": 25
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 0.7109375,
+ "learning_rate": 0.00019106347728549135,
+ "loss": 3.0666,
+ "step": 26
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.59765625,
+ "learning_rate": 0.00018993121301712193,
+ "loss": 2.8219,
+ "step": 27
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 0.75390625,
+ "learning_rate": 0.00018873520750565718,
+ "loss": 3.1164,
+ "step": 28
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.67578125,
+ "learning_rate": 0.00018747630845319612,
+ "loss": 2.7154,
+ "step": 29
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.625,
+ "learning_rate": 0.0001861554081393806,
+ "loss": 2.7395,
+ "step": 30
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001847734427889671,
+ "loss": 2.8282,
+ "step": 31
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 0.86328125,
+ "learning_rate": 0.0001833313919082515,
+ "loss": 2.7787,
+ "step": 32
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 2.67726731300354,
+ "eval_runtime": 1.2769,
+ "eval_samples_per_second": 10.964,
+ "eval_steps_per_second": 5.482,
+ "step": 32
+ },
+ {
+ "epoch": 1.03,
+ "grad_norm": 0.703125,
+ "learning_rate": 0.0001818302775908169,
+ "loss": 2.5957,
+ "step": 33
+ },
+ {
+ "epoch": 1.06,
+ "grad_norm": 0.76953125,
+ "learning_rate": 0.00018027116379309638,
+ "loss": 2.7011,
+ "step": 34
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 0.84765625,
+ "learning_rate": 0.00017865515558026428,
+ "loss": 2.6043,
+ "step": 35
+ },
+ {
+ "epoch": 1.12,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00017698339834299061,
+ "loss": 2.8607,
+ "step": 36
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.7578125,
+ "learning_rate": 0.00017525707698561385,
+ "loss": 2.5949,
+ "step": 37
+ },
+ {
+ "epoch": 1.19,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.00017347741508630672,
+ "loss": 2.7476,
+ "step": 38
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 0.88671875,
+ "learning_rate": 0.00017164567402983152,
+ "loss": 2.7991,
+ "step": 39
+ },
+ {
+ "epoch": 1.25,
+ "grad_norm": 0.8671875,
+ "learning_rate": 0.0001697631521134985,
+ "loss": 2.5959,
+ "step": 40
+ },
+ {
+ "epoch": 1.25,
+ "eval_loss": 2.5505764484405518,
+ "eval_runtime": 1.2761,
+ "eval_samples_per_second": 10.971,
+ "eval_steps_per_second": 5.486,
+ "step": 40
+ },
+ {
+ "epoch": 1.28,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00016783118362696163,
+ "loss": 2.5342,
+ "step": 41
+ },
+ {
+ "epoch": 1.31,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.00016585113790650388,
+ "loss": 2.4969,
+ "step": 42
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 1.125,
+ "learning_rate": 0.00016382441836448202,
+ "loss": 2.5723,
+ "step": 43
+ },
+ {
+ "epoch": 1.38,
+ "grad_norm": 1.015625,
+ "learning_rate": 0.0001617524614946192,
+ "loss": 2.6166,
+ "step": 44
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 0.98828125,
+ "learning_rate": 0.00015963673585385016,
+ "loss": 2.4574,
+ "step": 45
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.0001574787410214407,
+ "loss": 2.5074,
+ "step": 46
+ },
+ {
+ "epoch": 1.47,
+ "grad_norm": 0.953125,
+ "learning_rate": 0.00015528000653611935,
+ "loss": 2.5394,
+ "step": 47
+ },
+ {
+ "epoch": 1.5,
+ "grad_norm": 0.828125,
+ "learning_rate": 0.00015304209081197425,
+ "loss": 2.4793,
+ "step": 48
+ },
+ {
+ "epoch": 1.5,
+ "eval_loss": 2.495466470718384,
+ "eval_runtime": 1.2814,
+ "eval_samples_per_second": 10.926,
+ "eval_steps_per_second": 5.463,
+ "step": 48
+ },
+ {
+ "epoch": 1.53,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.000150766580033884,
+ "loss": 2.2909,
+ "step": 49
+ },
+ {
+ "epoch": 1.56,
+ "grad_norm": 0.74609375,
+ "learning_rate": 0.00014845508703326504,
+ "loss": 2.3424,
+ "step": 50
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 0.87890625,
+ "learning_rate": 0.0001461092501449326,
+ "loss": 2.506,
+ "step": 51
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00014373073204588556,
+ "loss": 2.4829,
+ "step": 52
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00014132121857683783,
+ "loss": 2.481,
+ "step": 53
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 0.9296875,
+ "learning_rate": 0.00013888241754733208,
+ "loss": 2.5512,
+ "step": 54
+ },
+ {
+ "epoch": 1.72,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00013641605752528224,
+ "loss": 2.5405,
+ "step": 55
+ },
+ {
+ "epoch": 1.75,
+ "grad_norm": 0.95703125,
+ "learning_rate": 0.00013392388661180303,
+ "loss": 2.5221,
+ "step": 56
+ },
+ {
+ "epoch": 1.75,
+ "eval_loss": 2.461298704147339,
+ "eval_runtime": 1.28,
+ "eval_samples_per_second": 10.937,
+ "eval_steps_per_second": 5.469,
+ "step": 56
+ },
+ {
+ "epoch": 1.78,
+ "grad_norm": 0.98046875,
+ "learning_rate": 0.0001314076712021949,
+ "loss": 2.5646,
+ "step": 57
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001288691947339621,
+ "loss": 2.5079,
+ "step": 58
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.00012631025642275212,
+ "loss": 2.4743,
+ "step": 59
+ },
+ {
+ "epoch": 1.88,
+ "grad_norm": 0.60546875,
+ "learning_rate": 0.0001237326699871115,
+ "loss": 2.3103,
+ "step": 60
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 0.80859375,
+ "learning_rate": 0.00012113826236296244,
+ "loss": 2.4229,
+ "step": 61
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.671875,
+ "learning_rate": 0.00011852887240871145,
+ "loss": 2.2709,
+ "step": 62
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 0.8203125,
+ "learning_rate": 0.00011590634960190721,
+ "loss": 2.4868,
+ "step": 63
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00011327255272837221,
+ "loss": 2.4384,
+ "step": 64
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 2.4055111408233643,
+ "eval_runtime": 1.2798,
+ "eval_samples_per_second": 10.94,
+ "eval_steps_per_second": 5.47,
+ "step": 64
+ },
+ {
+ "epoch": 2.03,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00011062934856473655,
+ "loss": 2.3671,
+ "step": 65
+ },
+ {
+ "epoch": 2.06,
+ "grad_norm": 0.69140625,
+ "learning_rate": 0.00010797861055530831,
+ "loss": 2.3381,
+ "step": 66
+ },
+ {
+ "epoch": 2.09,
+ "grad_norm": 0.671875,
+ "learning_rate": 0.00010532221748421787,
+ "loss": 2.2134,
+ "step": 67
+ },
+ {
+ "epoch": 2.12,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00010266205214377748,
+ "loss": 2.2687,
+ "step": 68
+ },
+ {
+ "epoch": 2.16,
+ "grad_norm": 0.75,
+ "learning_rate": 0.0001,
+ "loss": 2.4273,
+ "step": 69
+ },
+ {
+ "epoch": 2.19,
+ "grad_norm": 0.8671875,
+ "learning_rate": 9.733794785622253e-05,
+ "loss": 2.4439,
+ "step": 70
+ },
+ {
+ "epoch": 2.22,
+ "grad_norm": 0.953125,
+ "learning_rate": 9.467778251578217e-05,
+ "loss": 2.6631,
+ "step": 71
+ },
+ {
+ "epoch": 2.25,
+ "grad_norm": 0.78125,
+ "learning_rate": 9.202138944469168e-05,
+ "loss": 2.295,
+ "step": 72
+ },
+ {
+ "epoch": 2.25,
+ "eval_loss": 2.3922784328460693,
+ "eval_runtime": 1.282,
+ "eval_samples_per_second": 10.921,
+ "eval_steps_per_second": 5.46,
+ "step": 72
+ },
+ {
+ "epoch": 2.28,
+ "grad_norm": 0.734375,
+ "learning_rate": 8.937065143526347e-05,
+ "loss": 2.4963,
+ "step": 73
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 0.68359375,
+ "learning_rate": 8.672744727162781e-05,
+ "loss": 2.4274,
+ "step": 74
+ },
+ {
+ "epoch": 2.34,
+ "grad_norm": 0.9765625,
+ "learning_rate": 8.409365039809281e-05,
+ "loss": 2.4988,
+ "step": 75
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 0.75390625,
+ "learning_rate": 8.147112759128859e-05,
+ "loss": 2.2886,
+ "step": 76
+ },
+ {
+ "epoch": 2.41,
+ "grad_norm": 0.80078125,
+ "learning_rate": 7.886173763703757e-05,
+ "loss": 2.1944,
+ "step": 77
+ },
+ {
+ "epoch": 2.44,
+ "grad_norm": 0.8828125,
+ "learning_rate": 7.626733001288851e-05,
+ "loss": 2.3283,
+ "step": 78
+ },
+ {
+ "epoch": 2.47,
+ "grad_norm": 0.82421875,
+ "learning_rate": 7.368974357724789e-05,
+ "loss": 2.3855,
+ "step": 79
+ },
+ {
+ "epoch": 2.5,
+ "grad_norm": 0.7890625,
+ "learning_rate": 7.113080526603792e-05,
+ "loss": 2.3943,
+ "step": 80
+ },
+ {
+ "epoch": 2.5,
+ "eval_loss": 2.386228084564209,
+ "eval_runtime": 1.2835,
+ "eval_samples_per_second": 10.908,
+ "eval_steps_per_second": 5.454,
+ "step": 80
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 0.94921875,
+ "learning_rate": 6.859232879780515e-05,
+ "loss": 2.2725,
+ "step": 81
+ },
+ {
+ "epoch": 2.56,
+ "grad_norm": 0.75,
+ "learning_rate": 6.607611338819697e-05,
+ "loss": 2.1989,
+ "step": 82
+ },
+ {
+ "epoch": 2.59,
+ "grad_norm": 0.703125,
+ "learning_rate": 6.358394247471778e-05,
+ "loss": 2.1219,
+ "step": 83
+ },
+ {
+ "epoch": 2.62,
+ "grad_norm": 1.0390625,
+ "learning_rate": 6.111758245266794e-05,
+ "loss": 2.3478,
+ "step": 84
+ },
+ {
+ "epoch": 2.66,
+ "grad_norm": 0.78125,
+ "learning_rate": 5.867878142316221e-05,
+ "loss": 2.4196,
+ "step": 85
+ },
+ {
+ "epoch": 2.69,
+ "grad_norm": 0.6796875,
+ "learning_rate": 5.626926795411447e-05,
+ "loss": 2.1882,
+ "step": 86
+ },
+ {
+ "epoch": 2.72,
+ "grad_norm": 0.8203125,
+ "learning_rate": 5.38907498550674e-05,
+ "loss": 2.4703,
+ "step": 87
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 0.8671875,
+ "learning_rate": 5.1544912966734994e-05,
+ "loss": 2.2398,
+ "step": 88
+ },
+ {
+ "epoch": 2.75,
+ "eval_loss": 2.3605105876922607,
+ "eval_runtime": 1.2887,
+ "eval_samples_per_second": 10.864,
+ "eval_steps_per_second": 5.432,
+ "step": 88
+ },
+ {
+ "epoch": 2.78,
+ "grad_norm": 0.81640625,
+ "learning_rate": 4.9233419966116036e-05,
+ "loss": 2.2939,
+ "step": 89
+ },
+ {
+ "epoch": 2.81,
+ "grad_norm": 1.0234375,
+ "learning_rate": 4.695790918802576e-05,
+ "loss": 2.2835,
+ "step": 90
+ },
+ {
+ "epoch": 2.84,
+ "grad_norm": 0.85546875,
+ "learning_rate": 4.47199934638807e-05,
+ "loss": 2.3145,
+ "step": 91
+ },
+ {
+ "epoch": 2.88,
+ "grad_norm": 0.5546875,
+ "learning_rate": 4.252125897855932e-05,
+ "loss": 2.2521,
+ "step": 92
+ },
+ {
+ "epoch": 2.91,
+ "grad_norm": 0.76953125,
+ "learning_rate": 4.036326414614985e-05,
+ "loss": 2.377,
+ "step": 93
+ },
+ {
+ "epoch": 2.94,
+ "grad_norm": 0.78125,
+ "learning_rate": 3.824753850538082e-05,
+ "loss": 2.4343,
+ "step": 94
+ },
+ {
+ "epoch": 2.97,
+ "grad_norm": 0.8046875,
+ "learning_rate": 3.617558163551802e-05,
+ "loss": 2.2051,
+ "step": 95
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 0.88671875,
+ "learning_rate": 3.414886209349615e-05,
+ "loss": 2.2693,
+ "step": 96
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 2.3525888919830322,
+ "eval_runtime": 1.2821,
+ "eval_samples_per_second": 10.919,
+ "eval_steps_per_second": 5.46,
+ "step": 96
+ },
+ {
+ "epoch": 3.03,
+ "grad_norm": 0.74609375,
+ "learning_rate": 3.216881637303839e-05,
+ "loss": 2.5048,
+ "step": 97
+ },
+ {
+ "epoch": 3.06,
+ "grad_norm": 0.95703125,
+ "learning_rate": 3.0236847886501542e-05,
+ "loss": 2.3404,
+ "step": 98
+ },
+ {
+ "epoch": 3.09,
+ "grad_norm": 0.69140625,
+ "learning_rate": 2.8354325970168484e-05,
+ "loss": 2.3147,
+ "step": 99
+ },
+ {
+ "epoch": 3.12,
+ "grad_norm": 0.765625,
+ "learning_rate": 2.6522584913693294e-05,
+ "loss": 2.448,
+ "step": 100
+ },
+ {
+ "epoch": 3.16,
+ "grad_norm": 0.671875,
+ "learning_rate": 2.4742923014386156e-05,
+ "loss": 2.2212,
+ "step": 101
+ },
+ {
+ "epoch": 3.19,
+ "grad_norm": 0.625,
+ "learning_rate": 2.301660165700936e-05,
+ "loss": 2.3427,
+ "step": 102
+ },
+ {
+ "epoch": 3.22,
+ "grad_norm": 0.6484375,
+ "learning_rate": 2.1344844419735755e-05,
+ "loss": 2.1,
+ "step": 103
+ },
+ {
+ "epoch": 3.25,
+ "grad_norm": 0.73046875,
+ "learning_rate": 1.9728836206903656e-05,
+ "loss": 2.425,
+ "step": 104
+ },
+ {
+ "epoch": 3.25,
+ "eval_loss": 2.3470816612243652,
+ "eval_runtime": 1.2874,
+ "eval_samples_per_second": 10.875,
+ "eval_steps_per_second": 5.437,
+ "step": 104
+ },
+ {
+ "epoch": 3.28,
+ "grad_norm": 0.734375,
+ "learning_rate": 1.8169722409183097e-05,
+ "loss": 2.2268,
+ "step": 105
+ },
+ {
+ "epoch": 3.31,
+ "grad_norm": 0.8359375,
+ "learning_rate": 1.6668608091748495e-05,
+ "loss": 2.3695,
+ "step": 106
+ },
+ {
+ "epoch": 3.34,
+ "grad_norm": 0.58203125,
+ "learning_rate": 1.522655721103291e-05,
+ "loss": 2.1864,
+ "step": 107
+ },
+ {
+ "epoch": 3.38,
+ "grad_norm": 0.5703125,
+ "learning_rate": 1.3844591860619383e-05,
+ "loss": 2.2613,
+ "step": 108
+ },
+ {
+ "epoch": 3.41,
+ "grad_norm": 0.7265625,
+ "learning_rate": 1.2523691546803873e-05,
+ "loss": 2.2771,
+ "step": 109
+ },
+ {
+ "epoch": 3.44,
+ "grad_norm": 0.59765625,
+ "learning_rate": 1.1264792494342857e-05,
+ "loss": 2.2056,
+ "step": 110
+ },
+ {
+ "epoch": 3.47,
+ "grad_norm": 0.6875,
+ "learning_rate": 1.0068786982878087e-05,
+ "loss": 2.4039,
+ "step": 111
+ },
+ {
+ "epoch": 3.5,
+ "grad_norm": 0.77734375,
+ "learning_rate": 8.936522714508678e-06,
+ "loss": 2.2857,
+ "step": 112
+ },
+ {
+ "epoch": 3.5,
+ "eval_loss": 2.3467748165130615,
+ "eval_runtime": 1.2808,
+ "eval_samples_per_second": 10.931,
+ "eval_steps_per_second": 5.466,
+ "step": 112
+ },
+ {
+ "epoch": 3.53,
+ "grad_norm": 0.671875,
+ "learning_rate": 7.868802212958703e-06,
+ "loss": 2.257,
+ "step": 113
+ },
+ {
+ "epoch": 3.56,
+ "grad_norm": 1.21875,
+ "learning_rate": 6.866382254766157e-06,
+ "loss": 2.4278,
+ "step": 114
+ },
+ {
+ "epoch": 3.59,
+ "grad_norm": 0.859375,
+ "learning_rate": 5.929973332896677e-06,
+ "loss": 2.2232,
+ "step": 115
+ },
+ {
+ "epoch": 3.62,
+ "grad_norm": 0.66015625,
+ "learning_rate": 5.060239153161872e-06,
+ "loss": 2.225,
+ "step": 116
+ },
+ {
+ "epoch": 3.66,
+ "grad_norm": 0.6875,
+ "learning_rate": 4.257796163799455e-06,
+ "loss": 2.2133,
+ "step": 117
+ },
+ {
+ "epoch": 3.69,
+ "grad_norm": 0.8671875,
+ "learning_rate": 3.5232131185484076e-06,
+ "loss": 2.2191,
+ "step": 118
+ },
+ {
+ "epoch": 3.72,
+ "grad_norm": 0.77734375,
+ "learning_rate": 2.857010673529015e-06,
+ "loss": 2.0715,
+ "step": 119
+ },
+ {
+ "epoch": 3.75,
+ "grad_norm": 0.72265625,
+ "learning_rate": 2.259661018213333e-06,
+ "loss": 2.2448,
+ "step": 120
+ },
+ {
+ "epoch": 3.75,
+ "eval_loss": 2.3450927734375,
+ "eval_runtime": 1.2817,
+ "eval_samples_per_second": 10.923,
+ "eval_steps_per_second": 5.461,
+ "step": 120
+ },
+ {
+ "epoch": 3.78,
+ "grad_norm": 0.62109375,
+ "learning_rate": 1.7315875407479032e-06,
+ "loss": 2.1337,
+ "step": 121
+ },
+ {
+ "epoch": 3.81,
+ "grad_norm": 0.765625,
+ "learning_rate": 1.2731645278655445e-06,
+ "loss": 2.4334,
+ "step": 122
+ },
+ {
+ "epoch": 3.84,
+ "grad_norm": 0.73828125,
+ "learning_rate": 8.847168995992916e-07,
+ "loss": 2.3989,
+ "step": 123
+ },
+ {
+ "epoch": 3.88,
+ "grad_norm": 0.71484375,
+ "learning_rate": 5.665199789862907e-07,
+ "loss": 2.3509,
+ "step": 124
+ },
+ {
+ "epoch": 3.91,
+ "grad_norm": 0.78125,
+ "learning_rate": 3.1879929692498757e-07,
+ "loss": 2.3366,
+ "step": 125
+ },
+ {
+ "epoch": 3.94,
+ "grad_norm": 0.625,
+ "learning_rate": 1.4173043232380557e-07,
+ "loss": 2.071,
+ "step": 126
+ },
+ {
+ "epoch": 3.97,
+ "grad_norm": 0.6015625,
+ "learning_rate": 3.5438887654737355e-08,
+ "loss": 2.2108,
+ "step": 127
+ },
+ {
+ "epoch": 4.0,
+ "grad_norm": 0.7578125,
+ "learning_rate": 0.0,
+ "loss": 2.1836,
+ "step": 128
+ },
+ {
+ "epoch": 4.0,
+ "eval_loss": 2.3465805053710938,
+ "eval_runtime": 1.2864,
+ "eval_samples_per_second": 10.883,
+ "eval_steps_per_second": 5.441,
+ "step": 128
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 128,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 4,
+ "save_steps": 32,
+ "total_flos": 2.6669324546605056e+16,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-128/training_args.bin b/checkpoint-128/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18814c2c9b675fc3be2d153f474e77fb88d5038e
--- /dev/null
+++ b/checkpoint-128/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
+size 5816
diff --git a/checkpoint-32/README.md b/checkpoint-32/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..78aadd3258d05c05cabc678473b6f0942cd441c7
--- /dev/null
+++ b/checkpoint-32/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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
\ No newline at end of file
diff --git a/checkpoint-32/adapter_config.json b/checkpoint-32/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..28a5d05472d8cd3bfe780706c0eded9ae55cc02a
--- /dev/null
+++ b/checkpoint-32/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "down_proj",
+ "q_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-32/adapter_model.safetensors b/checkpoint-32/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5d77977993e6a3ec786583aa43499c136292bc1b
--- /dev/null
+++ b/checkpoint-32/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec430d847c06078c87671f113c67363bf58b51f662fe0c2c9aac1aea9197c05e
+size 50503848
diff --git a/checkpoint-32/optimizer.pt b/checkpoint-32/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c34b5013e20e2b0762dfdde502bfa17350bb704f
--- /dev/null
+++ b/checkpoint-32/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dcfc1311f5586ce9bc6ab8405e3706e4dcb6ef0050771e2c9bbe97b1fc7874
+size 202035450
diff --git a/checkpoint-32/rng_state.pth b/checkpoint-32/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..58a6ba31ec07fa4f9a8b982f55b673ab48aafb20
--- /dev/null
+++ b/checkpoint-32/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba88830bbf3f3a231c5f7c643ca357bcc703c4a14675504974ab2e003369a61
+size 14244
diff --git a/checkpoint-32/scheduler.pt b/checkpoint-32/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e17718c2286bf3678a89033727e8dc0d7f6b14ca
--- /dev/null
+++ b/checkpoint-32/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fa7fed0c0930926a3524b49ae450b78da12282a81cf57d30f2d1a4044247d8
+size 1064
diff --git a/checkpoint-32/special_tokens_map.json b/checkpoint-32/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/checkpoint-32/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "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": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-32/tokenizer.model b/checkpoint-32/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/checkpoint-32/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/checkpoint-32/tokenizer_config.json b/checkpoint-32/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86
--- /dev/null
+++ b/checkpoint-32/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "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>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "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,
+ "use_fast": true
+}
diff --git a/checkpoint-32/trainer_state.json b/checkpoint-32/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..6d4c385a701d5d69e028762c30a114f372d0f102
--- /dev/null
+++ b/checkpoint-32/trainer_state.json
@@ -0,0 +1,285 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 1.0,
+ "eval_steps": 8,
+ "global_step": 32,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.5859375,
+ "learning_rate": 2e-05,
+ "loss": 3.9295,
+ "step": 1
+ },
+ {
+ "epoch": 0.03,
+ "eval_loss": 3.907318115234375,
+ "eval_runtime": 1.2713,
+ "eval_samples_per_second": 11.012,
+ "eval_steps_per_second": 5.506,
+ "step": 1
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.5078125,
+ "learning_rate": 4e-05,
+ "loss": 3.805,
+ "step": 2
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.63671875,
+ "learning_rate": 6e-05,
+ "loss": 3.8521,
+ "step": 3
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 0.609375,
+ "learning_rate": 8e-05,
+ "loss": 3.8947,
+ "step": 4
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 0.546875,
+ "learning_rate": 0.0001,
+ "loss": 3.6494,
+ "step": 5
+ },
+ {
+ "epoch": 0.19,
+ "grad_norm": 0.50390625,
+ "learning_rate": 0.00012,
+ "loss": 3.6457,
+ "step": 6
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.640625,
+ "learning_rate": 0.00014,
+ "loss": 3.967,
+ "step": 7
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.494140625,
+ "learning_rate": 0.00016,
+ "loss": 3.5364,
+ "step": 8
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 3.6198840141296387,
+ "eval_runtime": 1.2681,
+ "eval_samples_per_second": 11.04,
+ "eval_steps_per_second": 5.52,
+ "step": 8
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 0.51171875,
+ "learning_rate": 0.00018,
+ "loss": 3.5216,
+ "step": 9
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.0002,
+ "loss": 3.677,
+ "step": 10
+ },
+ {
+ "epoch": 0.34,
+ "grad_norm": 0.734375,
+ "learning_rate": 0.00019996456111234527,
+ "loss": 3.058,
+ "step": 11
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 0.66796875,
+ "learning_rate": 0.0001998582695676762,
+ "loss": 3.1333,
+ "step": 12
+ },
+ {
+ "epoch": 0.41,
+ "grad_norm": 0.8359375,
+ "learning_rate": 0.000199681200703075,
+ "loss": 3.38,
+ "step": 13
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00019943348002101371,
+ "loss": 3.1371,
+ "step": 14
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 0.65625,
+ "learning_rate": 0.00019911528310040074,
+ "loss": 3.1479,
+ "step": 15
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 0.6484375,
+ "learning_rate": 0.00019872683547213446,
+ "loss": 3.263,
+ "step": 16
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 3.1820719242095947,
+ "eval_runtime": 1.2692,
+ "eval_samples_per_second": 11.031,
+ "eval_steps_per_second": 5.515,
+ "step": 16
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 0.53125,
+ "learning_rate": 0.00019826841245925212,
+ "loss": 2.9833,
+ "step": 17
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.5703125,
+ "learning_rate": 0.00019774033898178667,
+ "loss": 3.0787,
+ "step": 18
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.71484375,
+ "learning_rate": 0.00019714298932647098,
+ "loss": 3.4132,
+ "step": 19
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.73046875,
+ "learning_rate": 0.0001964767868814516,
+ "loss": 2.7304,
+ "step": 20
+ },
+ {
+ "epoch": 0.66,
+ "grad_norm": 0.55078125,
+ "learning_rate": 0.00019574220383620055,
+ "loss": 3.0116,
+ "step": 21
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.00019493976084683813,
+ "loss": 2.9474,
+ "step": 22
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.61328125,
+ "learning_rate": 0.00019407002666710336,
+ "loss": 2.9415,
+ "step": 23
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00019313361774523385,
+ "loss": 2.798,
+ "step": 24
+ },
+ {
+ "epoch": 0.75,
+ "eval_loss": 2.896176815032959,
+ "eval_runtime": 1.2765,
+ "eval_samples_per_second": 10.967,
+ "eval_steps_per_second": 5.484,
+ "step": 24
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 0.8046875,
+ "learning_rate": 0.00019213119778704128,
+ "loss": 3.2157,
+ "step": 25
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 0.7109375,
+ "learning_rate": 0.00019106347728549135,
+ "loss": 3.0666,
+ "step": 26
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.59765625,
+ "learning_rate": 0.00018993121301712193,
+ "loss": 2.8219,
+ "step": 27
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 0.75390625,
+ "learning_rate": 0.00018873520750565718,
+ "loss": 3.1164,
+ "step": 28
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.67578125,
+ "learning_rate": 0.00018747630845319612,
+ "loss": 2.7154,
+ "step": 29
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.625,
+ "learning_rate": 0.0001861554081393806,
+ "loss": 2.7395,
+ "step": 30
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001847734427889671,
+ "loss": 2.8282,
+ "step": 31
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 0.86328125,
+ "learning_rate": 0.0001833313919082515,
+ "loss": 2.7787,
+ "step": 32
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 2.67726731300354,
+ "eval_runtime": 1.2769,
+ "eval_samples_per_second": 10.964,
+ "eval_steps_per_second": 5.482,
+ "step": 32
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 128,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 4,
+ "save_steps": 32,
+ "total_flos": 6667331136651264.0,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-32/training_args.bin b/checkpoint-32/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18814c2c9b675fc3be2d153f474e77fb88d5038e
--- /dev/null
+++ b/checkpoint-32/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
+size 5816
diff --git a/checkpoint-64/README.md b/checkpoint-64/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..78aadd3258d05c05cabc678473b6f0942cd441c7
--- /dev/null
+++ b/checkpoint-64/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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
\ No newline at end of file
diff --git a/checkpoint-64/adapter_config.json b/checkpoint-64/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..28a5d05472d8cd3bfe780706c0eded9ae55cc02a
--- /dev/null
+++ b/checkpoint-64/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "down_proj",
+ "q_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-64/adapter_model.safetensors b/checkpoint-64/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f64158055261b7dbcd940a09727dfa4714abe709
--- /dev/null
+++ b/checkpoint-64/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478e962adcf5cf2208e94455da60f82ca1058e1b9684714f9c16065ef2896b84
+size 50503848
diff --git a/checkpoint-64/optimizer.pt b/checkpoint-64/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2be7aab5a469d5d346dac676d36939320e43484
--- /dev/null
+++ b/checkpoint-64/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7fae12b68510716cf6c13d76435aadee62c6caf362f7880a7604a4378d4478
+size 202035450
diff --git a/checkpoint-64/rng_state.pth b/checkpoint-64/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ca068a57650e3ee3e1329872d2058d2114c12a06
--- /dev/null
+++ b/checkpoint-64/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926ec53b6c5e5969c7a9dedbcd5e4c4ff81ecd6859afd62f93fd8684f6ac758d
+size 14244
diff --git a/checkpoint-64/scheduler.pt b/checkpoint-64/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..383157bccc0c6456709a28e9b1a3b19603f9651e
--- /dev/null
+++ b/checkpoint-64/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2f121208237af7a1af0cb966f4edc3bb705d4fe4813c302cf1425b7f9228d4
+size 1064
diff --git a/checkpoint-64/special_tokens_map.json b/checkpoint-64/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/checkpoint-64/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "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": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-64/tokenizer.model b/checkpoint-64/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/checkpoint-64/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/checkpoint-64/tokenizer_config.json b/checkpoint-64/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86
--- /dev/null
+++ b/checkpoint-64/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "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>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "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,
+ "use_fast": true
+}
diff --git a/checkpoint-64/trainer_state.json b/checkpoint-64/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..dc8634c0b9dcd481438ba361b8bbb770ad44d783
--- /dev/null
+++ b/checkpoint-64/trainer_state.json
@@ -0,0 +1,541 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 2.0,
+ "eval_steps": 8,
+ "global_step": 64,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.5859375,
+ "learning_rate": 2e-05,
+ "loss": 3.9295,
+ "step": 1
+ },
+ {
+ "epoch": 0.03,
+ "eval_loss": 3.907318115234375,
+ "eval_runtime": 1.2713,
+ "eval_samples_per_second": 11.012,
+ "eval_steps_per_second": 5.506,
+ "step": 1
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.5078125,
+ "learning_rate": 4e-05,
+ "loss": 3.805,
+ "step": 2
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.63671875,
+ "learning_rate": 6e-05,
+ "loss": 3.8521,
+ "step": 3
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 0.609375,
+ "learning_rate": 8e-05,
+ "loss": 3.8947,
+ "step": 4
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 0.546875,
+ "learning_rate": 0.0001,
+ "loss": 3.6494,
+ "step": 5
+ },
+ {
+ "epoch": 0.19,
+ "grad_norm": 0.50390625,
+ "learning_rate": 0.00012,
+ "loss": 3.6457,
+ "step": 6
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.640625,
+ "learning_rate": 0.00014,
+ "loss": 3.967,
+ "step": 7
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.494140625,
+ "learning_rate": 0.00016,
+ "loss": 3.5364,
+ "step": 8
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 3.6198840141296387,
+ "eval_runtime": 1.2681,
+ "eval_samples_per_second": 11.04,
+ "eval_steps_per_second": 5.52,
+ "step": 8
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 0.51171875,
+ "learning_rate": 0.00018,
+ "loss": 3.5216,
+ "step": 9
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.0002,
+ "loss": 3.677,
+ "step": 10
+ },
+ {
+ "epoch": 0.34,
+ "grad_norm": 0.734375,
+ "learning_rate": 0.00019996456111234527,
+ "loss": 3.058,
+ "step": 11
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 0.66796875,
+ "learning_rate": 0.0001998582695676762,
+ "loss": 3.1333,
+ "step": 12
+ },
+ {
+ "epoch": 0.41,
+ "grad_norm": 0.8359375,
+ "learning_rate": 0.000199681200703075,
+ "loss": 3.38,
+ "step": 13
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00019943348002101371,
+ "loss": 3.1371,
+ "step": 14
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 0.65625,
+ "learning_rate": 0.00019911528310040074,
+ "loss": 3.1479,
+ "step": 15
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 0.6484375,
+ "learning_rate": 0.00019872683547213446,
+ "loss": 3.263,
+ "step": 16
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 3.1820719242095947,
+ "eval_runtime": 1.2692,
+ "eval_samples_per_second": 11.031,
+ "eval_steps_per_second": 5.515,
+ "step": 16
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 0.53125,
+ "learning_rate": 0.00019826841245925212,
+ "loss": 2.9833,
+ "step": 17
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.5703125,
+ "learning_rate": 0.00019774033898178667,
+ "loss": 3.0787,
+ "step": 18
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.71484375,
+ "learning_rate": 0.00019714298932647098,
+ "loss": 3.4132,
+ "step": 19
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.73046875,
+ "learning_rate": 0.0001964767868814516,
+ "loss": 2.7304,
+ "step": 20
+ },
+ {
+ "epoch": 0.66,
+ "grad_norm": 0.55078125,
+ "learning_rate": 0.00019574220383620055,
+ "loss": 3.0116,
+ "step": 21
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.00019493976084683813,
+ "loss": 2.9474,
+ "step": 22
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.61328125,
+ "learning_rate": 0.00019407002666710336,
+ "loss": 2.9415,
+ "step": 23
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00019313361774523385,
+ "loss": 2.798,
+ "step": 24
+ },
+ {
+ "epoch": 0.75,
+ "eval_loss": 2.896176815032959,
+ "eval_runtime": 1.2765,
+ "eval_samples_per_second": 10.967,
+ "eval_steps_per_second": 5.484,
+ "step": 24
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 0.8046875,
+ "learning_rate": 0.00019213119778704128,
+ "loss": 3.2157,
+ "step": 25
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 0.7109375,
+ "learning_rate": 0.00019106347728549135,
+ "loss": 3.0666,
+ "step": 26
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.59765625,
+ "learning_rate": 0.00018993121301712193,
+ "loss": 2.8219,
+ "step": 27
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 0.75390625,
+ "learning_rate": 0.00018873520750565718,
+ "loss": 3.1164,
+ "step": 28
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.67578125,
+ "learning_rate": 0.00018747630845319612,
+ "loss": 2.7154,
+ "step": 29
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.625,
+ "learning_rate": 0.0001861554081393806,
+ "loss": 2.7395,
+ "step": 30
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001847734427889671,
+ "loss": 2.8282,
+ "step": 31
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 0.86328125,
+ "learning_rate": 0.0001833313919082515,
+ "loss": 2.7787,
+ "step": 32
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 2.67726731300354,
+ "eval_runtime": 1.2769,
+ "eval_samples_per_second": 10.964,
+ "eval_steps_per_second": 5.482,
+ "step": 32
+ },
+ {
+ "epoch": 1.03,
+ "grad_norm": 0.703125,
+ "learning_rate": 0.0001818302775908169,
+ "loss": 2.5957,
+ "step": 33
+ },
+ {
+ "epoch": 1.06,
+ "grad_norm": 0.76953125,
+ "learning_rate": 0.00018027116379309638,
+ "loss": 2.7011,
+ "step": 34
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 0.84765625,
+ "learning_rate": 0.00017865515558026428,
+ "loss": 2.6043,
+ "step": 35
+ },
+ {
+ "epoch": 1.12,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00017698339834299061,
+ "loss": 2.8607,
+ "step": 36
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.7578125,
+ "learning_rate": 0.00017525707698561385,
+ "loss": 2.5949,
+ "step": 37
+ },
+ {
+ "epoch": 1.19,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.00017347741508630672,
+ "loss": 2.7476,
+ "step": 38
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 0.88671875,
+ "learning_rate": 0.00017164567402983152,
+ "loss": 2.7991,
+ "step": 39
+ },
+ {
+ "epoch": 1.25,
+ "grad_norm": 0.8671875,
+ "learning_rate": 0.0001697631521134985,
+ "loss": 2.5959,
+ "step": 40
+ },
+ {
+ "epoch": 1.25,
+ "eval_loss": 2.5505764484405518,
+ "eval_runtime": 1.2761,
+ "eval_samples_per_second": 10.971,
+ "eval_steps_per_second": 5.486,
+ "step": 40
+ },
+ {
+ "epoch": 1.28,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00016783118362696163,
+ "loss": 2.5342,
+ "step": 41
+ },
+ {
+ "epoch": 1.31,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.00016585113790650388,
+ "loss": 2.4969,
+ "step": 42
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 1.125,
+ "learning_rate": 0.00016382441836448202,
+ "loss": 2.5723,
+ "step": 43
+ },
+ {
+ "epoch": 1.38,
+ "grad_norm": 1.015625,
+ "learning_rate": 0.0001617524614946192,
+ "loss": 2.6166,
+ "step": 44
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 0.98828125,
+ "learning_rate": 0.00015963673585385016,
+ "loss": 2.4574,
+ "step": 45
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.0001574787410214407,
+ "loss": 2.5074,
+ "step": 46
+ },
+ {
+ "epoch": 1.47,
+ "grad_norm": 0.953125,
+ "learning_rate": 0.00015528000653611935,
+ "loss": 2.5394,
+ "step": 47
+ },
+ {
+ "epoch": 1.5,
+ "grad_norm": 0.828125,
+ "learning_rate": 0.00015304209081197425,
+ "loss": 2.4793,
+ "step": 48
+ },
+ {
+ "epoch": 1.5,
+ "eval_loss": 2.495466470718384,
+ "eval_runtime": 1.2814,
+ "eval_samples_per_second": 10.926,
+ "eval_steps_per_second": 5.463,
+ "step": 48
+ },
+ {
+ "epoch": 1.53,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.000150766580033884,
+ "loss": 2.2909,
+ "step": 49
+ },
+ {
+ "epoch": 1.56,
+ "grad_norm": 0.74609375,
+ "learning_rate": 0.00014845508703326504,
+ "loss": 2.3424,
+ "step": 50
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 0.87890625,
+ "learning_rate": 0.0001461092501449326,
+ "loss": 2.506,
+ "step": 51
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00014373073204588556,
+ "loss": 2.4829,
+ "step": 52
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00014132121857683783,
+ "loss": 2.481,
+ "step": 53
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 0.9296875,
+ "learning_rate": 0.00013888241754733208,
+ "loss": 2.5512,
+ "step": 54
+ },
+ {
+ "epoch": 1.72,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00013641605752528224,
+ "loss": 2.5405,
+ "step": 55
+ },
+ {
+ "epoch": 1.75,
+ "grad_norm": 0.95703125,
+ "learning_rate": 0.00013392388661180303,
+ "loss": 2.5221,
+ "step": 56
+ },
+ {
+ "epoch": 1.75,
+ "eval_loss": 2.461298704147339,
+ "eval_runtime": 1.28,
+ "eval_samples_per_second": 10.937,
+ "eval_steps_per_second": 5.469,
+ "step": 56
+ },
+ {
+ "epoch": 1.78,
+ "grad_norm": 0.98046875,
+ "learning_rate": 0.0001314076712021949,
+ "loss": 2.5646,
+ "step": 57
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001288691947339621,
+ "loss": 2.5079,
+ "step": 58
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.00012631025642275212,
+ "loss": 2.4743,
+ "step": 59
+ },
+ {
+ "epoch": 1.88,
+ "grad_norm": 0.60546875,
+ "learning_rate": 0.0001237326699871115,
+ "loss": 2.3103,
+ "step": 60
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 0.80859375,
+ "learning_rate": 0.00012113826236296244,
+ "loss": 2.4229,
+ "step": 61
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.671875,
+ "learning_rate": 0.00011852887240871145,
+ "loss": 2.2709,
+ "step": 62
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 0.8203125,
+ "learning_rate": 0.00011590634960190721,
+ "loss": 2.4868,
+ "step": 63
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00011327255272837221,
+ "loss": 2.4384,
+ "step": 64
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 2.4055111408233643,
+ "eval_runtime": 1.2798,
+ "eval_samples_per_second": 10.94,
+ "eval_steps_per_second": 5.47,
+ "step": 64
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 128,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 4,
+ "save_steps": 32,
+ "total_flos": 1.3334662273302528e+16,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-64/training_args.bin b/checkpoint-64/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18814c2c9b675fc3be2d153f474e77fb88d5038e
--- /dev/null
+++ b/checkpoint-64/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
+size 5816
diff --git a/checkpoint-96/README.md b/checkpoint-96/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..78aadd3258d05c05cabc678473b6f0942cd441c7
--- /dev/null
+++ b/checkpoint-96/README.md
@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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
\ No newline at end of file
diff --git a/checkpoint-96/adapter_config.json b/checkpoint-96/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..28a5d05472d8cd3bfe780706c0eded9ae55cc02a
--- /dev/null
+++ b/checkpoint-96/adapter_config.json
@@ -0,0 +1,34 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "bias": "none",
+ "fan_in_fan_out": null,
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "up_proj",
+ "v_proj",
+ "o_proj",
+ "down_proj",
+ "q_proj",
+ "k_proj",
+ "gate_proj"
+ ],
+ "task_type": "CAUSAL_LM",
+ "use_dora": false,
+ "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-96/adapter_model.safetensors b/checkpoint-96/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b5d711bc4baca835941019d8c3024888b49ac2e4
--- /dev/null
+++ b/checkpoint-96/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f91dafd56822f172630cecc2b2e1daa597fdbbad4c82963c27fc7d9324b236
+size 50503848
diff --git a/checkpoint-96/optimizer.pt b/checkpoint-96/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..35ba7846dec077fdeed05ee25f6ab01ee121ad94
--- /dev/null
+++ b/checkpoint-96/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201f8255e7b843a6dce3b0a0f20c92b3051e4c17064d38df3bcda3aea4710751
+size 202035450
diff --git a/checkpoint-96/rng_state.pth b/checkpoint-96/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2cfa30af03d9380f0d09d29e8bedfe3893e13861
--- /dev/null
+++ b/checkpoint-96/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdd17d0d9f68ae884a6c41c42875839a612f5c867257621410c8670377c4664
+size 14244
diff --git a/checkpoint-96/scheduler.pt b/checkpoint-96/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..86646154be5a560bcc549fed7f3d82dd6fac0066
--- /dev/null
+++ b/checkpoint-96/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b76c8662d73a5a13047466dda569fd16697d4a2a715b2ad8f3567f25cfa42c3
+size 1064
diff --git a/checkpoint-96/special_tokens_map.json b/checkpoint-96/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/checkpoint-96/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "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": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-96/tokenizer.model b/checkpoint-96/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/checkpoint-96/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/checkpoint-96/tokenizer_config.json b/checkpoint-96/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86
--- /dev/null
+++ b/checkpoint-96/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "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>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "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,
+ "use_fast": true
+}
diff --git a/checkpoint-96/trainer_state.json b/checkpoint-96/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9dd58faee91a92c197bf32775a805312c059cdac
--- /dev/null
+++ b/checkpoint-96/trainer_state.json
@@ -0,0 +1,797 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 3.0,
+ "eval_steps": 8,
+ "global_step": 96,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.03,
+ "grad_norm": 0.5859375,
+ "learning_rate": 2e-05,
+ "loss": 3.9295,
+ "step": 1
+ },
+ {
+ "epoch": 0.03,
+ "eval_loss": 3.907318115234375,
+ "eval_runtime": 1.2713,
+ "eval_samples_per_second": 11.012,
+ "eval_steps_per_second": 5.506,
+ "step": 1
+ },
+ {
+ "epoch": 0.06,
+ "grad_norm": 0.5078125,
+ "learning_rate": 4e-05,
+ "loss": 3.805,
+ "step": 2
+ },
+ {
+ "epoch": 0.09,
+ "grad_norm": 0.63671875,
+ "learning_rate": 6e-05,
+ "loss": 3.8521,
+ "step": 3
+ },
+ {
+ "epoch": 0.12,
+ "grad_norm": 0.609375,
+ "learning_rate": 8e-05,
+ "loss": 3.8947,
+ "step": 4
+ },
+ {
+ "epoch": 0.16,
+ "grad_norm": 0.546875,
+ "learning_rate": 0.0001,
+ "loss": 3.6494,
+ "step": 5
+ },
+ {
+ "epoch": 0.19,
+ "grad_norm": 0.50390625,
+ "learning_rate": 0.00012,
+ "loss": 3.6457,
+ "step": 6
+ },
+ {
+ "epoch": 0.22,
+ "grad_norm": 0.640625,
+ "learning_rate": 0.00014,
+ "loss": 3.967,
+ "step": 7
+ },
+ {
+ "epoch": 0.25,
+ "grad_norm": 0.494140625,
+ "learning_rate": 0.00016,
+ "loss": 3.5364,
+ "step": 8
+ },
+ {
+ "epoch": 0.25,
+ "eval_loss": 3.6198840141296387,
+ "eval_runtime": 1.2681,
+ "eval_samples_per_second": 11.04,
+ "eval_steps_per_second": 5.52,
+ "step": 8
+ },
+ {
+ "epoch": 0.28,
+ "grad_norm": 0.51171875,
+ "learning_rate": 0.00018,
+ "loss": 3.5216,
+ "step": 9
+ },
+ {
+ "epoch": 0.31,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.0002,
+ "loss": 3.677,
+ "step": 10
+ },
+ {
+ "epoch": 0.34,
+ "grad_norm": 0.734375,
+ "learning_rate": 0.00019996456111234527,
+ "loss": 3.058,
+ "step": 11
+ },
+ {
+ "epoch": 0.38,
+ "grad_norm": 0.66796875,
+ "learning_rate": 0.0001998582695676762,
+ "loss": 3.1333,
+ "step": 12
+ },
+ {
+ "epoch": 0.41,
+ "grad_norm": 0.8359375,
+ "learning_rate": 0.000199681200703075,
+ "loss": 3.38,
+ "step": 13
+ },
+ {
+ "epoch": 0.44,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00019943348002101371,
+ "loss": 3.1371,
+ "step": 14
+ },
+ {
+ "epoch": 0.47,
+ "grad_norm": 0.65625,
+ "learning_rate": 0.00019911528310040074,
+ "loss": 3.1479,
+ "step": 15
+ },
+ {
+ "epoch": 0.5,
+ "grad_norm": 0.6484375,
+ "learning_rate": 0.00019872683547213446,
+ "loss": 3.263,
+ "step": 16
+ },
+ {
+ "epoch": 0.5,
+ "eval_loss": 3.1820719242095947,
+ "eval_runtime": 1.2692,
+ "eval_samples_per_second": 11.031,
+ "eval_steps_per_second": 5.515,
+ "step": 16
+ },
+ {
+ "epoch": 0.53,
+ "grad_norm": 0.53125,
+ "learning_rate": 0.00019826841245925212,
+ "loss": 2.9833,
+ "step": 17
+ },
+ {
+ "epoch": 0.56,
+ "grad_norm": 0.5703125,
+ "learning_rate": 0.00019774033898178667,
+ "loss": 3.0787,
+ "step": 18
+ },
+ {
+ "epoch": 0.59,
+ "grad_norm": 0.71484375,
+ "learning_rate": 0.00019714298932647098,
+ "loss": 3.4132,
+ "step": 19
+ },
+ {
+ "epoch": 0.62,
+ "grad_norm": 0.73046875,
+ "learning_rate": 0.0001964767868814516,
+ "loss": 2.7304,
+ "step": 20
+ },
+ {
+ "epoch": 0.66,
+ "grad_norm": 0.55078125,
+ "learning_rate": 0.00019574220383620055,
+ "loss": 3.0116,
+ "step": 21
+ },
+ {
+ "epoch": 0.69,
+ "grad_norm": 0.6171875,
+ "learning_rate": 0.00019493976084683813,
+ "loss": 2.9474,
+ "step": 22
+ },
+ {
+ "epoch": 0.72,
+ "grad_norm": 0.61328125,
+ "learning_rate": 0.00019407002666710336,
+ "loss": 2.9415,
+ "step": 23
+ },
+ {
+ "epoch": 0.75,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00019313361774523385,
+ "loss": 2.798,
+ "step": 24
+ },
+ {
+ "epoch": 0.75,
+ "eval_loss": 2.896176815032959,
+ "eval_runtime": 1.2765,
+ "eval_samples_per_second": 10.967,
+ "eval_steps_per_second": 5.484,
+ "step": 24
+ },
+ {
+ "epoch": 0.78,
+ "grad_norm": 0.8046875,
+ "learning_rate": 0.00019213119778704128,
+ "loss": 3.2157,
+ "step": 25
+ },
+ {
+ "epoch": 0.81,
+ "grad_norm": 0.7109375,
+ "learning_rate": 0.00019106347728549135,
+ "loss": 3.0666,
+ "step": 26
+ },
+ {
+ "epoch": 0.84,
+ "grad_norm": 0.59765625,
+ "learning_rate": 0.00018993121301712193,
+ "loss": 2.8219,
+ "step": 27
+ },
+ {
+ "epoch": 0.88,
+ "grad_norm": 0.75390625,
+ "learning_rate": 0.00018873520750565718,
+ "loss": 3.1164,
+ "step": 28
+ },
+ {
+ "epoch": 0.91,
+ "grad_norm": 0.67578125,
+ "learning_rate": 0.00018747630845319612,
+ "loss": 2.7154,
+ "step": 29
+ },
+ {
+ "epoch": 0.94,
+ "grad_norm": 0.625,
+ "learning_rate": 0.0001861554081393806,
+ "loss": 2.7395,
+ "step": 30
+ },
+ {
+ "epoch": 0.97,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001847734427889671,
+ "loss": 2.8282,
+ "step": 31
+ },
+ {
+ "epoch": 1.0,
+ "grad_norm": 0.86328125,
+ "learning_rate": 0.0001833313919082515,
+ "loss": 2.7787,
+ "step": 32
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 2.67726731300354,
+ "eval_runtime": 1.2769,
+ "eval_samples_per_second": 10.964,
+ "eval_steps_per_second": 5.482,
+ "step": 32
+ },
+ {
+ "epoch": 1.03,
+ "grad_norm": 0.703125,
+ "learning_rate": 0.0001818302775908169,
+ "loss": 2.5957,
+ "step": 33
+ },
+ {
+ "epoch": 1.06,
+ "grad_norm": 0.76953125,
+ "learning_rate": 0.00018027116379309638,
+ "loss": 2.7011,
+ "step": 34
+ },
+ {
+ "epoch": 1.09,
+ "grad_norm": 0.84765625,
+ "learning_rate": 0.00017865515558026428,
+ "loss": 2.6043,
+ "step": 35
+ },
+ {
+ "epoch": 1.12,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00017698339834299061,
+ "loss": 2.8607,
+ "step": 36
+ },
+ {
+ "epoch": 1.16,
+ "grad_norm": 0.7578125,
+ "learning_rate": 0.00017525707698561385,
+ "loss": 2.5949,
+ "step": 37
+ },
+ {
+ "epoch": 1.19,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.00017347741508630672,
+ "loss": 2.7476,
+ "step": 38
+ },
+ {
+ "epoch": 1.22,
+ "grad_norm": 0.88671875,
+ "learning_rate": 0.00017164567402983152,
+ "loss": 2.7991,
+ "step": 39
+ },
+ {
+ "epoch": 1.25,
+ "grad_norm": 0.8671875,
+ "learning_rate": 0.0001697631521134985,
+ "loss": 2.5959,
+ "step": 40
+ },
+ {
+ "epoch": 1.25,
+ "eval_loss": 2.5505764484405518,
+ "eval_runtime": 1.2761,
+ "eval_samples_per_second": 10.971,
+ "eval_steps_per_second": 5.486,
+ "step": 40
+ },
+ {
+ "epoch": 1.28,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00016783118362696163,
+ "loss": 2.5342,
+ "step": 41
+ },
+ {
+ "epoch": 1.31,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.00016585113790650388,
+ "loss": 2.4969,
+ "step": 42
+ },
+ {
+ "epoch": 1.34,
+ "grad_norm": 1.125,
+ "learning_rate": 0.00016382441836448202,
+ "loss": 2.5723,
+ "step": 43
+ },
+ {
+ "epoch": 1.38,
+ "grad_norm": 1.015625,
+ "learning_rate": 0.0001617524614946192,
+ "loss": 2.6166,
+ "step": 44
+ },
+ {
+ "epoch": 1.41,
+ "grad_norm": 0.98828125,
+ "learning_rate": 0.00015963673585385016,
+ "loss": 2.4574,
+ "step": 45
+ },
+ {
+ "epoch": 1.44,
+ "grad_norm": 0.94921875,
+ "learning_rate": 0.0001574787410214407,
+ "loss": 2.5074,
+ "step": 46
+ },
+ {
+ "epoch": 1.47,
+ "grad_norm": 0.953125,
+ "learning_rate": 0.00015528000653611935,
+ "loss": 2.5394,
+ "step": 47
+ },
+ {
+ "epoch": 1.5,
+ "grad_norm": 0.828125,
+ "learning_rate": 0.00015304209081197425,
+ "loss": 2.4793,
+ "step": 48
+ },
+ {
+ "epoch": 1.5,
+ "eval_loss": 2.495466470718384,
+ "eval_runtime": 1.2814,
+ "eval_samples_per_second": 10.926,
+ "eval_steps_per_second": 5.463,
+ "step": 48
+ },
+ {
+ "epoch": 1.53,
+ "grad_norm": 0.921875,
+ "learning_rate": 0.000150766580033884,
+ "loss": 2.2909,
+ "step": 49
+ },
+ {
+ "epoch": 1.56,
+ "grad_norm": 0.74609375,
+ "learning_rate": 0.00014845508703326504,
+ "loss": 2.3424,
+ "step": 50
+ },
+ {
+ "epoch": 1.59,
+ "grad_norm": 0.87890625,
+ "learning_rate": 0.0001461092501449326,
+ "loss": 2.506,
+ "step": 51
+ },
+ {
+ "epoch": 1.62,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00014373073204588556,
+ "loss": 2.4829,
+ "step": 52
+ },
+ {
+ "epoch": 1.66,
+ "grad_norm": 0.984375,
+ "learning_rate": 0.00014132121857683783,
+ "loss": 2.481,
+ "step": 53
+ },
+ {
+ "epoch": 1.69,
+ "grad_norm": 0.9296875,
+ "learning_rate": 0.00013888241754733208,
+ "loss": 2.5512,
+ "step": 54
+ },
+ {
+ "epoch": 1.72,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00013641605752528224,
+ "loss": 2.5405,
+ "step": 55
+ },
+ {
+ "epoch": 1.75,
+ "grad_norm": 0.95703125,
+ "learning_rate": 0.00013392388661180303,
+ "loss": 2.5221,
+ "step": 56
+ },
+ {
+ "epoch": 1.75,
+ "eval_loss": 2.461298704147339,
+ "eval_runtime": 1.28,
+ "eval_samples_per_second": 10.937,
+ "eval_steps_per_second": 5.469,
+ "step": 56
+ },
+ {
+ "epoch": 1.78,
+ "grad_norm": 0.98046875,
+ "learning_rate": 0.0001314076712021949,
+ "loss": 2.5646,
+ "step": 57
+ },
+ {
+ "epoch": 1.81,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.0001288691947339621,
+ "loss": 2.5079,
+ "step": 58
+ },
+ {
+ "epoch": 1.84,
+ "grad_norm": 0.8125,
+ "learning_rate": 0.00012631025642275212,
+ "loss": 2.4743,
+ "step": 59
+ },
+ {
+ "epoch": 1.88,
+ "grad_norm": 0.60546875,
+ "learning_rate": 0.0001237326699871115,
+ "loss": 2.3103,
+ "step": 60
+ },
+ {
+ "epoch": 1.91,
+ "grad_norm": 0.80859375,
+ "learning_rate": 0.00012113826236296244,
+ "loss": 2.4229,
+ "step": 61
+ },
+ {
+ "epoch": 1.94,
+ "grad_norm": 0.671875,
+ "learning_rate": 0.00011852887240871145,
+ "loss": 2.2709,
+ "step": 62
+ },
+ {
+ "epoch": 1.97,
+ "grad_norm": 0.8203125,
+ "learning_rate": 0.00011590634960190721,
+ "loss": 2.4868,
+ "step": 63
+ },
+ {
+ "epoch": 2.0,
+ "grad_norm": 0.62109375,
+ "learning_rate": 0.00011327255272837221,
+ "loss": 2.4384,
+ "step": 64
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 2.4055111408233643,
+ "eval_runtime": 1.2798,
+ "eval_samples_per_second": 10.94,
+ "eval_steps_per_second": 5.47,
+ "step": 64
+ },
+ {
+ "epoch": 2.03,
+ "grad_norm": 0.6328125,
+ "learning_rate": 0.00011062934856473655,
+ "loss": 2.3671,
+ "step": 65
+ },
+ {
+ "epoch": 2.06,
+ "grad_norm": 0.69140625,
+ "learning_rate": 0.00010797861055530831,
+ "loss": 2.3381,
+ "step": 66
+ },
+ {
+ "epoch": 2.09,
+ "grad_norm": 0.671875,
+ "learning_rate": 0.00010532221748421787,
+ "loss": 2.2134,
+ "step": 67
+ },
+ {
+ "epoch": 2.12,
+ "grad_norm": 0.7890625,
+ "learning_rate": 0.00010266205214377748,
+ "loss": 2.2687,
+ "step": 68
+ },
+ {
+ "epoch": 2.16,
+ "grad_norm": 0.75,
+ "learning_rate": 0.0001,
+ "loss": 2.4273,
+ "step": 69
+ },
+ {
+ "epoch": 2.19,
+ "grad_norm": 0.8671875,
+ "learning_rate": 9.733794785622253e-05,
+ "loss": 2.4439,
+ "step": 70
+ },
+ {
+ "epoch": 2.22,
+ "grad_norm": 0.953125,
+ "learning_rate": 9.467778251578217e-05,
+ "loss": 2.6631,
+ "step": 71
+ },
+ {
+ "epoch": 2.25,
+ "grad_norm": 0.78125,
+ "learning_rate": 9.202138944469168e-05,
+ "loss": 2.295,
+ "step": 72
+ },
+ {
+ "epoch": 2.25,
+ "eval_loss": 2.3922784328460693,
+ "eval_runtime": 1.282,
+ "eval_samples_per_second": 10.921,
+ "eval_steps_per_second": 5.46,
+ "step": 72
+ },
+ {
+ "epoch": 2.28,
+ "grad_norm": 0.734375,
+ "learning_rate": 8.937065143526347e-05,
+ "loss": 2.4963,
+ "step": 73
+ },
+ {
+ "epoch": 2.31,
+ "grad_norm": 0.68359375,
+ "learning_rate": 8.672744727162781e-05,
+ "loss": 2.4274,
+ "step": 74
+ },
+ {
+ "epoch": 2.34,
+ "grad_norm": 0.9765625,
+ "learning_rate": 8.409365039809281e-05,
+ "loss": 2.4988,
+ "step": 75
+ },
+ {
+ "epoch": 2.38,
+ "grad_norm": 0.75390625,
+ "learning_rate": 8.147112759128859e-05,
+ "loss": 2.2886,
+ "step": 76
+ },
+ {
+ "epoch": 2.41,
+ "grad_norm": 0.80078125,
+ "learning_rate": 7.886173763703757e-05,
+ "loss": 2.1944,
+ "step": 77
+ },
+ {
+ "epoch": 2.44,
+ "grad_norm": 0.8828125,
+ "learning_rate": 7.626733001288851e-05,
+ "loss": 2.3283,
+ "step": 78
+ },
+ {
+ "epoch": 2.47,
+ "grad_norm": 0.82421875,
+ "learning_rate": 7.368974357724789e-05,
+ "loss": 2.3855,
+ "step": 79
+ },
+ {
+ "epoch": 2.5,
+ "grad_norm": 0.7890625,
+ "learning_rate": 7.113080526603792e-05,
+ "loss": 2.3943,
+ "step": 80
+ },
+ {
+ "epoch": 2.5,
+ "eval_loss": 2.386228084564209,
+ "eval_runtime": 1.2835,
+ "eval_samples_per_second": 10.908,
+ "eval_steps_per_second": 5.454,
+ "step": 80
+ },
+ {
+ "epoch": 2.53,
+ "grad_norm": 0.94921875,
+ "learning_rate": 6.859232879780515e-05,
+ "loss": 2.2725,
+ "step": 81
+ },
+ {
+ "epoch": 2.56,
+ "grad_norm": 0.75,
+ "learning_rate": 6.607611338819697e-05,
+ "loss": 2.1989,
+ "step": 82
+ },
+ {
+ "epoch": 2.59,
+ "grad_norm": 0.703125,
+ "learning_rate": 6.358394247471778e-05,
+ "loss": 2.1219,
+ "step": 83
+ },
+ {
+ "epoch": 2.62,
+ "grad_norm": 1.0390625,
+ "learning_rate": 6.111758245266794e-05,
+ "loss": 2.3478,
+ "step": 84
+ },
+ {
+ "epoch": 2.66,
+ "grad_norm": 0.78125,
+ "learning_rate": 5.867878142316221e-05,
+ "loss": 2.4196,
+ "step": 85
+ },
+ {
+ "epoch": 2.69,
+ "grad_norm": 0.6796875,
+ "learning_rate": 5.626926795411447e-05,
+ "loss": 2.1882,
+ "step": 86
+ },
+ {
+ "epoch": 2.72,
+ "grad_norm": 0.8203125,
+ "learning_rate": 5.38907498550674e-05,
+ "loss": 2.4703,
+ "step": 87
+ },
+ {
+ "epoch": 2.75,
+ "grad_norm": 0.8671875,
+ "learning_rate": 5.1544912966734994e-05,
+ "loss": 2.2398,
+ "step": 88
+ },
+ {
+ "epoch": 2.75,
+ "eval_loss": 2.3605105876922607,
+ "eval_runtime": 1.2887,
+ "eval_samples_per_second": 10.864,
+ "eval_steps_per_second": 5.432,
+ "step": 88
+ },
+ {
+ "epoch": 2.78,
+ "grad_norm": 0.81640625,
+ "learning_rate": 4.9233419966116036e-05,
+ "loss": 2.2939,
+ "step": 89
+ },
+ {
+ "epoch": 2.81,
+ "grad_norm": 1.0234375,
+ "learning_rate": 4.695790918802576e-05,
+ "loss": 2.2835,
+ "step": 90
+ },
+ {
+ "epoch": 2.84,
+ "grad_norm": 0.85546875,
+ "learning_rate": 4.47199934638807e-05,
+ "loss": 2.3145,
+ "step": 91
+ },
+ {
+ "epoch": 2.88,
+ "grad_norm": 0.5546875,
+ "learning_rate": 4.252125897855932e-05,
+ "loss": 2.2521,
+ "step": 92
+ },
+ {
+ "epoch": 2.91,
+ "grad_norm": 0.76953125,
+ "learning_rate": 4.036326414614985e-05,
+ "loss": 2.377,
+ "step": 93
+ },
+ {
+ "epoch": 2.94,
+ "grad_norm": 0.78125,
+ "learning_rate": 3.824753850538082e-05,
+ "loss": 2.4343,
+ "step": 94
+ },
+ {
+ "epoch": 2.97,
+ "grad_norm": 0.8046875,
+ "learning_rate": 3.617558163551802e-05,
+ "loss": 2.2051,
+ "step": 95
+ },
+ {
+ "epoch": 3.0,
+ "grad_norm": 0.88671875,
+ "learning_rate": 3.414886209349615e-05,
+ "loss": 2.2693,
+ "step": 96
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 2.3525888919830322,
+ "eval_runtime": 1.2821,
+ "eval_samples_per_second": 10.919,
+ "eval_steps_per_second": 5.46,
+ "step": 96
+ }
+ ],
+ "logging_steps": 1,
+ "max_steps": 128,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 4,
+ "save_steps": 32,
+ "total_flos": 2.000199340995379e+16,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-96/training_args.bin b/checkpoint-96/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18814c2c9b675fc3be2d153f474e77fb88d5038e
--- /dev/null
+++ b/checkpoint-96/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca5508434f64a69e54fc8c46f68907814d91f48e751b7a0eeb4050e5ae3225
+size 5816
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..90a576b0e1406cefb938f55520f89406e75af264
--- /dev/null
+++ b/config.json
@@ -0,0 +1,43 @@
+{
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 2048,
+ "initializer_range": 0.02,
+ "intermediate_size": 5632,
+ "max_position_embeddings": 4096,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 22,
+ "num_key_value_heads": 4,
+ "pretraining_tp": 1,
+ "quantization_config": {
+ "_load_in_4bit": true,
+ "_load_in_8bit": false,
+ "bnb_4bit_compute_dtype": "bfloat16",
+ "bnb_4bit_quant_storage": "bfloat16",
+ "bnb_4bit_quant_type": "nf4",
+ "bnb_4bit_use_double_quant": true,
+ "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-05,
+ "rope_scaling": null,
+ "rope_theta": 10000.0,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.40.0.dev0",
+ "use_cache": false,
+ "vocab_size": 32000
+}
diff --git a/runs/Apr30_02-51-48_663ec5cd7167/events.out.tfevents.1714445508.663ec5cd7167.5280.0 b/runs/Apr30_02-51-48_663ec5cd7167/events.out.tfevents.1714445508.663ec5cd7167.5280.0
new file mode 100644
index 0000000000000000000000000000000000000000..66828609cbc8a3db07a68014d3322946cab862bc
--- /dev/null
+++ b/runs/Apr30_02-51-48_663ec5cd7167/events.out.tfevents.1714445508.663ec5cd7167.5280.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bac99fef0086cdfda4f010adba206b97074810136dff597980b02f3f4736af
+size 37468
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+ "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": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0773857a13ba5a27453a0b462624fe76e8e82a86
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,44 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": true,
+ "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>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "</s>",
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "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,
+ "use_fast": true
+}