Upload folder using huggingface_hub

mymodel/README.md

@@ -0,0 +1,96 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: TinyLlama/TinyLlama_v1.1
+tags:
+- generated_from_trainer
+datasets:
+- mhenrichsen/alpaca_2k_test
+model-index:
+- name: outputs/mymodel
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+base_model: TinyLlama/TinyLlama_v1.1
+datasets:
+  - path: mhenrichsen/alpaca_2k_test
+    type: alpaca
+output_dir: ./outputs/mymodel
+
+sequence_len: 4096
+adapter: lora
+
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+  - gate_proj
+  - down_proj
+  - up_proj
+
+gradient_accumulation_steps: 1
+micro_batch_size: 16
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+learning_rate: 0.0002
+load_in_8bit: true
+train_on_inputs: false
+bf16: auto
+
+```
+
+</details><br>
+
+# outputs/mymodel
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the mhenrichsen/alpaca_2k_test dataset.
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 3
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

mymodel/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama_v1.1",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

mymodel/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c529fe66de09910700daf25c2f9db5057c907b9a77da7635ba456b7f636154ae
+size 25271744

mymodel/checkpoint-125/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama_v1.1
+library_name: peft
+---
+
+# 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 0.14.0

mymodel/checkpoint-125/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama_v1.1",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

mymodel/checkpoint-125/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c529fe66de09910700daf25c2f9db5057c907b9a77da7635ba456b7f636154ae
+size 25271744

mymodel/checkpoint-125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ada9c173c5ab8d5a7b20d44be70c4fb23f2211337a33b4d835a5c6584ff0fd6
+size 13685516

mymodel/checkpoint-125/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a042700280ac65beb16851c66a67236838bbcad661d0a3ffcf57df745911427
+size 14244

mymodel/checkpoint-125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c0243da09e051ffbb600413baac079966a139cd6939cbef7eb321283bd0767
+size 1064

mymodel/checkpoint-125/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
+  }
+}

mymodel/checkpoint-125/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

mymodel/checkpoint-125/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

mymodel/checkpoint-125/trainer_state.json

@@ -0,0 +1,908 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 5.004910271743918e+17,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.381,
+      "step": 1
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 1.083608291591848e+18,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.5955,
+      "step": 2
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 3.5660872940519424e+18,
+      "learning_rate": 0.0002,
+      "loss": 1.5354,
+      "step": 3
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 1.274530789173756e+18,
+      "learning_rate": 0.0001999668467514313,
+      "loss": 1.1766,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.021463715817718e+17,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 1.4703,
+      "step": 5
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 4.0442277924542874e+18,
+      "learning_rate": 0.00019970175264485266,
+      "loss": 1.7172,
+      "step": 6
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.5871626799069266e+18,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 1.4297,
+      "step": 7
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 3.5305142446026916e+18,
+      "learning_rate": 0.00019917226741361015,
+      "loss": 1.393,
+      "step": 8
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.102768762147832e+18,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 1.1948,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.467851533720748e+18,
+      "learning_rate": 0.00019837979515735166,
+      "loss": 1.4613,
+      "step": 10
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.927067078907134e+18,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 1.3976,
+      "step": 11
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 4.846886948771463e+18,
+      "learning_rate": 0.00019732643737003827,
+      "loss": 1.7678,
+      "step": 12
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 4.131409718688088e+18,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 1.3976,
+      "step": 13
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.0517513715421544e+19,
+      "learning_rate": 0.00019601498736716017,
+      "loss": 1.4297,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1194569886061822e+19,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 1.6025,
+      "step": 15
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.4724186929176248e+19,
+      "learning_rate": 0.00019444892287836613,
+      "loss": 1.4496,
+      "step": 16
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 1.3999,
+      "step": 17
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019263239682514952,
+      "loss": 1.3827,
+      "step": 18
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 1.3712,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019057022630804716,
+      "loss": 1.3113,
+      "step": 20
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 1.2724,
+      "step": 21
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018826787983255473,
+      "loss": 1.3431,
+      "step": 22
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 1.4561,
+      "step": 23
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018573146280763324,
+      "loss": 1.5095,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 1.2004,
+      "step": 25
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001829677013552619,
+      "loss": 1.4357,
+      "step": 26
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 1.4816,
+      "step": 27
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017998392447397197,
+      "loss": 1.3496,
+      "step": 28
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 1.5659,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017678804460366,
+      "loss": 1.3827,
+      "step": 30
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 1.4859,
+      "step": 31
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017338853664321992,
+      "loss": 1.3258,
+      "step": 32
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 1.2653,
+      "step": 33
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016979441547663435,
+      "loss": 1.497,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 1.2957,
+      "step": 35
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016601521206712318,
+      "loss": 1.33,
+      "step": 36
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 1.2754,
+      "step": 37
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016206094818274229,
+      "loss": 1.4231,
+      "step": 38
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 1.4111,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015794210982045636,
+      "loss": 1.3893,
+      "step": 40
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 1.5119,
+      "step": 41
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015366961939916008,
+      "loss": 1.1767,
+      "step": 42
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 1.3673,
+      "step": 43
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014925480679538647,
+      "loss": 1.2728,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": Infinity,
+      "learning_rate": 0.000146997674302732,
+      "loss": 1.4004,
+      "step": 45
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001447093792985114,
+      "loss": 1.2985,
+      "step": 46
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 1.3591,
+      "step": 47
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014004539056512667,
+      "loss": 1.3075,
+      "step": 48
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 1.4115,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001352752086549095,
+      "loss": 1.5869,
+      "step": 50
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 1.7463,
+      "step": 51
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001304114832327518,
+      "loss": 1.5202,
+      "step": 52
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 1.3242,
+      "step": 53
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012546711202412287,
+      "loss": 1.3785,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 1.2749,
+      "step": 55
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001204552066126201,
+      "loss": 1.3878,
+      "step": 56
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 1.3636,
+      "step": 57
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001153890576704062,
+      "loss": 1.3355,
+      "step": 58
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 1.3793,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011028209971373605,
+      "loss": 1.5472,
+      "step": 60
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 1.4279,
+      "step": 61
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010514787547703466,
+      "loss": 1.1971,
+      "step": 62
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00010257479136549889,
+      "loss": 1.4396,
+      "step": 63
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001,
+      "loss": 1.6474,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": Infinity,
+      "learning_rate": 9.742520863450115e-05,
+      "loss": 1.2276,
+      "step": 65
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": Infinity,
+      "learning_rate": 9.485212452296535e-05,
+      "loss": 1.5576,
+      "step": 66
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": Infinity,
+      "learning_rate": 9.228245378733537e-05,
+      "loss": 1.3965,
+      "step": 67
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": Infinity,
+      "learning_rate": 8.971790028626395e-05,
+      "loss": 1.3127,
+      "step": 68
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": Infinity,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 1.2903,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": Infinity,
+      "learning_rate": 8.461094232959381e-05,
+      "loss": 1.5581,
+      "step": 70
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": Infinity,
+      "learning_rate": 8.207192411892646e-05,
+      "loss": 1.2974,
+      "step": 71
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": Infinity,
+      "learning_rate": 7.954479338737995e-05,
+      "loss": 1.419,
+      "step": 72
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": Infinity,
+      "learning_rate": 7.703122578682046e-05,
+      "loss": 1.1411,
+      "step": 73
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": Infinity,
+      "learning_rate": 7.453288797587714e-05,
+      "loss": 1.4877,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": Infinity,
+      "learning_rate": 7.205143651483906e-05,
+      "loss": 1.3649,
+      "step": 75
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": Infinity,
+      "learning_rate": 6.958851676724823e-05,
+      "loss": 1.1338,
+      "step": 76
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": Infinity,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 1.6106,
+      "step": 77
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": Infinity,
+      "learning_rate": 6.472479134509052e-05,
+      "loss": 1.3229,
+      "step": 78
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": Infinity,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 1.5485,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": Infinity,
+      "learning_rate": 5.9954609434873344e-05,
+      "loss": 1.4849,
+      "step": 80
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": Infinity,
+      "learning_rate": 5.7608560929013946e-05,
+      "loss": 1.5165,
+      "step": 81
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": Infinity,
+      "learning_rate": 5.5290620701488594e-05,
+      "loss": 1.4454,
+      "step": 82
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": Infinity,
+      "learning_rate": 5.300232569726804e-05,
+      "loss": 1.5015,
+      "step": 83
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": Infinity,
+      "learning_rate": 5.074519320461357e-05,
+      "loss": 1.3703,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": Infinity,
+      "learning_rate": 4.852071984901696e-05,
+      "loss": 1.5138,
+      "step": 85
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": Infinity,
+      "learning_rate": 4.633038060083996e-05,
+      "loss": 1.3649,
+      "step": 86
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": Infinity,
+      "learning_rate": 4.417562779731355e-05,
+      "loss": 1.3127,
+      "step": 87
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": Infinity,
+      "learning_rate": 4.205789017954364e-05,
+      "loss": 1.6108,
+      "step": 88
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": Infinity,
+      "learning_rate": 3.997857194516319e-05,
+      "loss": 1.2395,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": Infinity,
+      "learning_rate": 3.793905181725772e-05,
+      "loss": 1.6598,
+      "step": 90
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": Infinity,
+      "learning_rate": 3.594068213018249e-05,
+      "loss": 1.5338,
+      "step": 91
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": Infinity,
+      "learning_rate": 3.3984787932876814e-05,
+      "loss": 1.3984,
+      "step": 92
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": Infinity,
+      "learning_rate": 3.207266611027069e-05,
+      "loss": 1.4177,
+      "step": 93
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": Infinity,
+      "learning_rate": 3.0205584523365626e-05,
+      "loss": 1.453,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": Infinity,
+      "learning_rate": 2.8384781168560693e-05,
+      "loss": 1.3531,
+      "step": 95
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": Infinity,
+      "learning_rate": 2.6611463356780096e-05,
+      "loss": 1.3001,
+      "step": 96
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": Infinity,
+      "learning_rate": 2.4886806912948035e-05,
+      "loss": 1.3886,
+      "step": 97
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": Infinity,
+      "learning_rate": 2.3211955396340002e-05,
+      "loss": 1.2448,
+      "step": 98
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": Infinity,
+      "learning_rate": 2.1588019342328968e-05,
+      "loss": 1.2232,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": Infinity,
+      "learning_rate": 2.0016075526028065e-05,
+      "loss": 1.4335,
+      "step": 100
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": Infinity,
+      "learning_rate": 1.8497166248318876e-05,
+      "loss": 1.2922,
+      "step": 101
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": Infinity,
+      "learning_rate": 1.703229864473811e-05,
+      "loss": 1.312,
+      "step": 102
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": Infinity,
+      "learning_rate": 1.562244401768144e-05,
+      "loss": 1.4499,
+      "step": 103
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": Infinity,
+      "learning_rate": 1.426853719236676e-05,
+      "loss": 1.185,
+      "step": 104
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": Infinity,
+      "learning_rate": 1.2971475896984475e-05,
+      "loss": 1.457,
+      "step": 105
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": Infinity,
+      "learning_rate": 1.1732120167445248e-05,
+      "loss": 1.5606,
+      "step": 106
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0551291777120464e-05,
+      "loss": 1.2389,
+      "step": 107
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": Infinity,
+      "learning_rate": 9.429773691952858e-06,
+      "loss": 1.2696,
+      "step": 108
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": Infinity,
+      "learning_rate": 8.368309551299536e-06,
+      "loss": 1.4387,
+      "step": 109
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": Infinity,
+      "learning_rate": 7.367603174850502e-06,
+      "loss": 1.2714,
+      "step": 110
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": Infinity,
+      "learning_rate": 6.428318095950647e-06,
+      "loss": 1.2515,
+      "step": 111
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": Infinity,
+      "learning_rate": 5.551077121633874e-06,
+      "loss": 1.365,
+      "step": 112
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": Infinity,
+      "learning_rate": 4.7364619196617495e-06,
+      "loss": 1.586,
+      "step": 113
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": Infinity,
+      "learning_rate": 3.985012632839824e-06,
+      "loss": 1.2308,
+      "step": 114
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": Infinity,
+      "learning_rate": 3.2972275208679625e-06,
+      "loss": 1.4232,
+      "step": 115
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": Infinity,
+      "learning_rate": 2.6735626299617457e-06,
+      "loss": 1.3548,
+      "step": 116
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": Infinity,
+      "learning_rate": 2.1144314904642195e-06,
+      "loss": 1.4619,
+      "step": 117
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": Infinity,
+      "learning_rate": 1.6202048426483651e-06,
+      "loss": 1.5824,
+      "step": 118
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": Infinity,
+      "learning_rate": 1.1912103908922945e-06,
+      "loss": 1.6972,
+      "step": 119
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": Infinity,
+      "learning_rate": 8.277325863898511e-07,
+      "loss": 1.304,
+      "step": 120
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": Infinity,
+      "learning_rate": 5.300124385410943e-07,
+      "loss": 1.3053,
+      "step": 121
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": Infinity,
+      "learning_rate": 2.9824735514732974e-07,
+      "loss": 1.4267,
+      "step": 122
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": Infinity,
+      "learning_rate": 1.3259101151694708e-07,
+      "loss": 1.4401,
+      "step": 123
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": Infinity,
+      "learning_rate": 3.3153248568695835e-08,
+      "loss": 1.4421,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 1.4619,
+      "step": 125
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 125,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6995910605144064.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

mymodel/checkpoint-125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0163a1df6208d188f7e15f528d4d1e9803c4f256950971ac31d2b8b667a2b9d
+size 6456

mymodel/config.json

@@ -0,0 +1,46 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "TinyLlama/TinyLlama_v1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mymodel/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
+  }
+}

mymodel/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

mymodel/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}