Initialize v2 from v1 (safe copy before resume training)

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Navid-AI/Yehia-7B-preview
+library_name: transformers
+model_name: Shaer-7B-v1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Shaer-7B-v1
+
+This model is a fine-tuned version of [Navid-AI/Yehia-7B-preview](https://huggingface.co/Navid-AI/Yehia-7B-preview).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Shaer-AI/Shaer-7B-v1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.57.1
+- Pytorch: 2.4.0
+- Datasets: 2.21.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Navid-AI/Yehia-7B-preview",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a09ebcdc80ed107324598c4bffb8e2f0b006a766a909e1eb3edd933a66151b
+size 319876032

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}

last-checkpoint/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Navid-AI/Yehia-7B-preview
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Navid-AI/Yehia-7B-preview
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

last-checkpoint/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Navid-AI/Yehia-7B-preview",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a09ebcdc80ed107324598c4bffb8e2f0b006a766a909e1eb3edd933a66151b
+size 319876032

last-checkpoint/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb20ba2205df500ef9ab02ed436174c6619a4b9769b5b7aebf0f95f3c41db6c
+size 640009682

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ca5f99d0d364ce5cf70e2b8a6900efb50a685e1c38c231a210045bb0e12db7
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbaddaa44c992ea9bc16709e10de696f828c0ca1140780a2327a56516e00656
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feff3deb3537c4a47b77585053ad2aa00484da7907b188e0111cbed1f4592e67
+size 1228714

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "3": {
+      "content": "0",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "1",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "2",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "3",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "4",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "5",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "6",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "7",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "8",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "9",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "٠",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "١",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "٢",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "٣",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "٤",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "٥",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "٦",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "٧",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "٨",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "٩",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,472 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 150,
+  "global_step": 959,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010437732402635528,
+      "grad_norm": 3.6640398502349854,
+      "learning_rate": 0.0,
+      "loss": 1.293,
+      "mean_token_accuracy": 0.7315249554812908,
+      "step": 1
+    },
+    {
+      "epoch": 0.020875464805271055,
+      "grad_norm": 0.33989453315734863,
+      "learning_rate": 6.551724137931034e-05,
+      "loss": 1.1105,
+      "mean_token_accuracy": 0.7687016786321214,
+      "step": 20
+    },
+    {
+      "epoch": 0.04175092961054211,
+      "grad_norm": 0.2829172909259796,
+      "learning_rate": 9.892473118279571e-05,
+      "loss": 0.9714,
+      "mean_token_accuracy": 0.7907559825107455,
+      "step": 40
+    },
+    {
+      "epoch": 0.06262639441581316,
+      "grad_norm": 0.3811407685279846,
+      "learning_rate": 9.677419354838711e-05,
+      "loss": 0.9236,
+      "mean_token_accuracy": 0.7986495142802597,
+      "step": 60
+    },
+    {
+      "epoch": 0.08350185922108422,
+      "grad_norm": 0.40331247448921204,
+      "learning_rate": 9.46236559139785e-05,
+      "loss": 0.8964,
+      "mean_token_accuracy": 0.8034458922222256,
+      "step": 80
+    },
+    {
+      "epoch": 0.10437732402635527,
+      "grad_norm": 0.3131363093852997,
+      "learning_rate": 9.247311827956989e-05,
+      "loss": 0.8733,
+      "mean_token_accuracy": 0.807321792282164,
+      "step": 100
+    },
+    {
+      "epoch": 0.12525278883162633,
+      "grad_norm": 0.28229933977127075,
+      "learning_rate": 9.032258064516129e-05,
+      "loss": 0.8659,
+      "mean_token_accuracy": 0.8081387735903263,
+      "step": 120
+    },
+    {
+      "epoch": 0.14612825363689738,
+      "grad_norm": 0.3455071747303009,
+      "learning_rate": 8.81720430107527e-05,
+      "loss": 0.8573,
+      "mean_token_accuracy": 0.8092190572991967,
+      "step": 140
+    },
+    {
+      "epoch": 0.15656598603953292,
+      "eval_loss": 0.8501774668693542,
+      "eval_mean_token_accuracy": 0.8104509812072511,
+      "eval_runtime": 477.3649,
+      "eval_samples_per_second": 24.139,
+      "eval_steps_per_second": 1.51,
+      "step": 150
+    },
+    {
+      "epoch": 0.16700371844216844,
+      "grad_norm": 0.2634192705154419,
+      "learning_rate": 8.60215053763441e-05,
+      "loss": 0.8539,
+      "mean_token_accuracy": 0.8096571587026119,
+      "step": 160
+    },
+    {
+      "epoch": 0.1878791832474395,
+      "grad_norm": 0.24897566437721252,
+      "learning_rate": 8.387096774193549e-05,
+      "loss": 0.8394,
+      "mean_token_accuracy": 0.8123498395085335,
+      "step": 180
+    },
+    {
+      "epoch": 0.20875464805271055,
+      "grad_norm": 0.25399449467658997,
+      "learning_rate": 8.172043010752689e-05,
+      "loss": 0.8411,
+      "mean_token_accuracy": 0.8118746573105454,
+      "step": 200
+    },
+    {
+      "epoch": 0.2296301128579816,
+      "grad_norm": 0.30704858899116516,
+      "learning_rate": 7.956989247311829e-05,
+      "loss": 0.8198,
+      "mean_token_accuracy": 0.8161308566108346,
+      "step": 220
+    },
+    {
+      "epoch": 0.25050557766325265,
+      "grad_norm": 0.26868879795074463,
+      "learning_rate": 7.741935483870968e-05,
+      "loss": 0.8306,
+      "mean_token_accuracy": 0.8135106340050697,
+      "step": 240
+    },
+    {
+      "epoch": 0.27138104246852374,
+      "grad_norm": 0.39215439558029175,
+      "learning_rate": 7.526881720430108e-05,
+      "loss": 0.8097,
+      "mean_token_accuracy": 0.8179622774943709,
+      "step": 260
+    },
+    {
+      "epoch": 0.29225650727379476,
+      "grad_norm": 0.2937132716178894,
+      "learning_rate": 7.311827956989248e-05,
+      "loss": 0.8073,
+      "mean_token_accuracy": 0.8181498864665627,
+      "step": 280
+    },
+    {
+      "epoch": 0.31313197207906585,
+      "grad_norm": 0.4043816030025482,
+      "learning_rate": 7.096774193548388e-05,
+      "loss": 0.804,
+      "mean_token_accuracy": 0.8183059839531779,
+      "step": 300
+    },
+    {
+      "epoch": 0.31313197207906585,
+      "eval_loss": 0.822810709476471,
+      "eval_mean_token_accuracy": 0.8151241214364643,
+      "eval_runtime": 478.8102,
+      "eval_samples_per_second": 24.066,
+      "eval_steps_per_second": 1.506,
+      "step": 300
+    },
+    {
+      "epoch": 0.3340074368843369,
+      "grad_norm": 0.5106801986694336,
+      "learning_rate": 6.881720430107527e-05,
+      "loss": 0.7944,
+      "mean_token_accuracy": 0.8205162849277258,
+      "step": 320
+    },
+    {
+      "epoch": 0.35488290168960795,
+      "grad_norm": 0.2678694725036621,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.7946,
+      "mean_token_accuracy": 0.8205837696790695,
+      "step": 340
+    },
+    {
+      "epoch": 0.375758366494879,
+      "grad_norm": 0.31555888056755066,
+      "learning_rate": 6.451612903225807e-05,
+      "loss": 0.7842,
+      "mean_token_accuracy": 0.8227896897122264,
+      "step": 360
+    },
+    {
+      "epoch": 0.39663383130015006,
+      "grad_norm": 0.25338518619537354,
+      "learning_rate": 6.236559139784946e-05,
+      "loss": 0.7839,
+      "mean_token_accuracy": 0.8224633572623133,
+      "step": 380
+    },
+    {
+      "epoch": 0.4175092961054211,
+      "grad_norm": 0.3376692831516266,
+      "learning_rate": 6.021505376344086e-05,
+      "loss": 0.7837,
+      "mean_token_accuracy": 0.8224168518558145,
+      "step": 400
+    },
+    {
+      "epoch": 0.4383847609106922,
+      "grad_norm": 0.3099437654018402,
+      "learning_rate": 5.8064516129032266e-05,
+      "loss": 0.7709,
+      "mean_token_accuracy": 0.8251230824738741,
+      "step": 420
+    },
+    {
+      "epoch": 0.4592602257159632,
+      "grad_norm": 0.38553759455680847,
+      "learning_rate": 5.5913978494623656e-05,
+      "loss": 0.7716,
+      "mean_token_accuracy": 0.8242331562563777,
+      "step": 440
+    },
+    {
+      "epoch": 0.4696979581185987,
+      "eval_loss": 0.8102629780769348,
+      "eval_mean_token_accuracy": 0.8185677231372959,
+      "eval_runtime": 479.9076,
+      "eval_samples_per_second": 24.011,
+      "eval_steps_per_second": 1.502,
+      "step": 450
+    },
+    {
+      "epoch": 0.4801356905212343,
+      "grad_norm": 0.4562067985534668,
+      "learning_rate": 5.3763440860215054e-05,
+      "loss": 0.7673,
+      "mean_token_accuracy": 0.8257499437779188,
+      "step": 460
+    },
+    {
+      "epoch": 0.5010111553265053,
+      "grad_norm": 0.3461894690990448,
+      "learning_rate": 5.161290322580645e-05,
+      "loss": 0.764,
+      "mean_token_accuracy": 0.8258528942242265,
+      "step": 480
+    },
+    {
+      "epoch": 0.5218866201317763,
+      "grad_norm": 0.3894698917865753,
+      "learning_rate": 4.9462365591397855e-05,
+      "loss": 0.7629,
+      "mean_token_accuracy": 0.8263893555849791,
+      "step": 500
+    },
+    {
+      "epoch": 0.5427620849370475,
+      "grad_norm": 0.3671281337738037,
+      "learning_rate": 4.731182795698925e-05,
+      "loss": 0.7637,
+      "mean_token_accuracy": 0.825993400812149,
+      "step": 520
+    },
+    {
+      "epoch": 0.5636375497423185,
+      "grad_norm": 0.27911612391471863,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 0.7571,
+      "mean_token_accuracy": 0.8272387059405446,
+      "step": 540
+    },
+    {
+      "epoch": 0.5845130145475895,
+      "grad_norm": 0.35994264483451843,
+      "learning_rate": 4.301075268817205e-05,
+      "loss": 0.7514,
+      "mean_token_accuracy": 0.8287154756486416,
+      "step": 560
+    },
+    {
+      "epoch": 0.6053884793528606,
+      "grad_norm": 0.27501070499420166,
+      "learning_rate": 4.0860215053763444e-05,
+      "loss": 0.7352,
+      "mean_token_accuracy": 0.8320884253829718,
+      "step": 580
+    },
+    {
+      "epoch": 0.6262639441581317,
+      "grad_norm": 0.31373465061187744,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 0.7459,
+      "mean_token_accuracy": 0.8291032826527953,
+      "step": 600
+    },
+    {
+      "epoch": 0.6262639441581317,
+      "eval_loss": 0.8052937388420105,
+      "eval_mean_token_accuracy": 0.818547232719797,
+      "eval_runtime": 478.5563,
+      "eval_samples_per_second": 24.079,
+      "eval_steps_per_second": 1.507,
+      "step": 600
+    },
+    {
+      "epoch": 0.6471394089634027,
+      "grad_norm": 0.28387895226478577,
+      "learning_rate": 3.655913978494624e-05,
+      "loss": 0.7383,
+      "mean_token_accuracy": 0.8311796387657523,
+      "step": 620
+    },
+    {
+      "epoch": 0.6680148737686737,
+      "grad_norm": 0.2989550828933716,
+      "learning_rate": 3.4408602150537636e-05,
+      "loss": 0.7401,
+      "mean_token_accuracy": 0.8308440973982215,
+      "step": 640
+    },
+    {
+      "epoch": 0.6888903385739448,
+      "grad_norm": 0.3100236654281616,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.7301,
+      "mean_token_accuracy": 0.8333285139873624,
+      "step": 660
+    },
+    {
+      "epoch": 0.7097658033792159,
+      "grad_norm": 0.3028460741043091,
+      "learning_rate": 3.010752688172043e-05,
+      "loss": 0.724,
+      "mean_token_accuracy": 0.8343087159097194,
+      "step": 680
+    },
+    {
+      "epoch": 0.7306412681844869,
+      "grad_norm": 0.29025018215179443,
+      "learning_rate": 2.7956989247311828e-05,
+      "loss": 0.7279,
+      "mean_token_accuracy": 0.8334941100329161,
+      "step": 700
+    },
+    {
+      "epoch": 0.751516732989758,
+      "grad_norm": 0.31064796447753906,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 0.7258,
+      "mean_token_accuracy": 0.833451921492815,
+      "step": 720
+    },
+    {
+      "epoch": 0.772392197795029,
+      "grad_norm": 0.2918741703033447,
+      "learning_rate": 2.3655913978494626e-05,
+      "loss": 0.7223,
+      "mean_token_accuracy": 0.8338876113295555,
+      "step": 740
+    },
+    {
+      "epoch": 0.7828299301976646,
+      "eval_loss": 0.8058114647865295,
+      "eval_mean_token_accuracy": 0.8215587672256314,
+      "eval_runtime": 480.3181,
+      "eval_samples_per_second": 23.99,
+      "eval_steps_per_second": 1.501,
+      "step": 750
+    },
+    {
+      "epoch": 0.7932676626003001,
+      "grad_norm": 0.30113646388053894,
+      "learning_rate": 2.1505376344086024e-05,
+      "loss": 0.7232,
+      "mean_token_accuracy": 0.8343004129827023,
+      "step": 760
+    },
+    {
+      "epoch": 0.8141431274055712,
+      "grad_norm": 0.297846257686615,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.7169,
+      "mean_token_accuracy": 0.8357257222756743,
+      "step": 780
+    },
+    {
+      "epoch": 0.8350185922108422,
+      "grad_norm": 0.290519118309021,
+      "learning_rate": 1.7204301075268818e-05,
+      "loss": 0.7214,
+      "mean_token_accuracy": 0.8349421635270119,
+      "step": 800
+    },
+    {
+      "epoch": 0.8558940570161132,
+      "grad_norm": 0.288723349571228,
+      "learning_rate": 1.5053763440860215e-05,
+      "loss": 0.7192,
+      "mean_token_accuracy": 0.8351026430726052,
+      "step": 820
+    },
+    {
+      "epoch": 0.8767695218213843,
+      "grad_norm": 0.3073173463344574,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.7136,
+      "mean_token_accuracy": 0.83632858004421,
+      "step": 840
+    },
+    {
+      "epoch": 0.8976449866266554,
+      "grad_norm": 0.30293524265289307,
+      "learning_rate": 1.0752688172043012e-05,
+      "loss": 0.7065,
+      "mean_token_accuracy": 0.8384585160762071,
+      "step": 860
+    },
+    {
+      "epoch": 0.9185204514319264,
+      "grad_norm": 0.2873519957065582,
+      "learning_rate": 8.602150537634409e-06,
+      "loss": 0.7079,
+      "mean_token_accuracy": 0.837334163300693,
+      "step": 880
+    },
+    {
+      "epoch": 0.9393959162371974,
+      "grad_norm": 0.296587198972702,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.7125,
+      "mean_token_accuracy": 0.8367217551916838,
+      "step": 900
+    },
+    {
+      "epoch": 0.9393959162371974,
+      "eval_loss": 0.8067903518676758,
+      "eval_mean_token_accuracy": 0.8190384064897915,
+      "eval_runtime": 479.0964,
+      "eval_samples_per_second": 24.052,
+      "eval_steps_per_second": 1.505,
+      "step": 900
+    },
+    {
+      "epoch": 0.9602713810424686,
+      "grad_norm": 0.27917736768722534,
+      "learning_rate": 4.3010752688172045e-06,
+      "loss": 0.7063,
+      "mean_token_accuracy": 0.8376741111278534,
+      "step": 920
+    },
+    {
+      "epoch": 0.9811468458477396,
+      "grad_norm": 0.29608383774757385,
+      "learning_rate": 2.1505376344086023e-06,
+      "loss": 0.7029,
+      "mean_token_accuracy": 0.8386383946985007,
+      "step": 940
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 959,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.705866842583073e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4de7a8f290f12afd27f95624e7316370f66104ef925d974503c0026cab33f5d
+size 5752

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feff3deb3537c4a47b77585053ad2aa00484da7907b188e0111cbed1f4592e67
+size 1228714

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "3": {
+      "content": "0",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "1",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "2",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "3",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "4",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "5",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "6",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "7",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "8",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "9",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "٠",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "١",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "٢",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "٣",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "٤",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "٥",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "٦",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "٧",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "٨",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "٩",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4de7a8f290f12afd27f95624e7316370f66104ef925d974503c0026cab33f5d
+size 5752