Push retrained pashto-base-bloom (on base_pashto_clean) and update ModelCard

.gitattributes

@@ -34,3 +34,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2829/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5658/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8487/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

ModelCard.md

@@ -0,0 +1,181 @@
+---
+---
+license: mit # Or your chosen license: apache-2.0, cc-by-4.0, etc.
+language:
+- ps # Pashto
+library_name: transformers
+tags:
+- text-generation
+- pashto
+- bloom
+- zamai-bloom
+datasets:
+
+**Note on Dataset Identifiers:**
+The `datasets` field in the metadata of this model card might list `tasal9/pashto_base_bloom`. This identifier may refer to an earlier version or a different collection of Pashto data. The specific training run culminating in this model update (June 2025) exclusively used the locally processed `datasets/base_pashto_clean` as described above.
+
+
+- tasal9/pashto_base_bloom
+pipeline_tag: text-generation
+widget:
+- text: "پښتو ژبه"
+---
+
+# ZamAI Bloom Pashto - checkpoint5207 (and Final Model)
+
+This model card is for `checkpoint5207` and the final fine-tuned version of a Bloom model for Pashto text generation, developed under the ZamAI Bloom project.
+
+## Model Description
+
+This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on a Pashto text corpus. The goal of this project was to create a language model proficient in generating coherent and contextually relevant Pashto text.
+
+**Base Model:** `bigscience/bloom-560m`
+**Fine-tuning Checkpoint:** `checkpoint5207`
+**Final Model:** [tasal9/zamai-bloom-ps-final]
+
+## Intended Uses & Limitations
+
+### Intended Uses
+
+This model is intended for:
+* Generating Pashto text.
+* Assisting with Pashto language content creation.
+* Research in Pashto NLP.
+* Educational purposes for Pashto language learning.
+
+### Limitations and Bias
+
+* The model's performance is dependent on the quality and diversity of the training data. It may generate text that reflects biases present in the data.
+* It might produce factually incorrect or nonsensical text, especially for complex topics or out-of-domain prompts.
+* The model may not be suitable for critical applications without further evaluation and mitigation of potential harms.
+* Performance on specific Pashto dialects might vary depending on their representation in the training data.
+
+## How to use
+
+You can use this model with the Hugging Face `transformers` library for text generation.
+
+First, install the library:
+```bash
+pip install transformers torch
+```
+
+Then, you can use the model in Python:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "tasal9/zamai-bloom-ps-final" # Or the specific checkpoint identifier if using a checkpoint directly
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+prompt = "په پښتو ژبه کې یو شعر ولیکئ د پسرلي په اړه" # Example prompt: "Write a poem in Pashto about spring"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+# Generate text
+# Adjust generation parameters as needed (max_length, num_beams, do_sample, top_k, top_p, etc.)
+outputs = model.generate(**inputs, max_length=100, num_beams=5, early_stopping=True)
+generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(generated_text)
+```
+
+## Training Data
+
+Describe the dataset(s) used for fine-tuning.
+* **Source:** [e.g., Web scraped data, specific Pashto corpora, data from `datasets/base_pashto/`]
+* **Size:** [e.g., Number of documents, tokens, GBs]
+* **Preprocessing:** [e.g., Cleaning steps, tokenization details]
+* **Language Variety:** [e.g., Predominant dialects, formal/informal text]
+
+If your dataset is on the Hugging Face Hub, link to it.
+
+## Training Procedure
+
+### Preprocessing
+
+The texts were tokenized using the `AutoTokenizer` associated with the base Bloom model.
+[Add any other specific preprocessing steps you took.]
+
+### Fine-tuning
+
+The model was fine-tuned using the Hugging Face `transformers` library with PyTorch.
+* **Training script:** [Link to your `train_base_model.py` if applicable]
+* **Hyperparameters:**
+    * Learning rate: 2e-5
+    * Batch size: 4 # Adjust based on your GPU memory (e.g., 8, 16)
+    * Number of epochs: 3 # Adjust based on convergence and overfitting
+    * Optimizer: AdamW
+    * Weight decay: 0.01
+    * Warmup steps: 500 # Or warmup_ratio, e.g., 0.1
+    * Gradient accumulation steps: 1 # Increase if actual batch size is limited by memory
+    * Seed: 42 # For reproducibility
+* **Infrastructure:**
+    * Hardware: [e.g., 1x NVIDIA A100 40GB, or specify your hardware]
+    * Training time: [e.g., X hours]
+
+This specific model card refers to `checkpoint5207`, which was saved at step 5207 of the training process. The final model represents the model after the completion of all training epochs/steps.
+
+## Evaluation Results
+
+Provide quantitative results if available (e.g., perplexity, BLEU scores on a held-out test set).
+* **Test set:** [Describe your test set]
+* **Metrics:** [e.g., Perplexity, BLEU, ROUGE]
+* **Results for checkpoint5207:**
+  * [Metric 1]: [Value]
+  * [Metric 2]: [Value]
+* **Results for final model:**
+  * [Metric 1]: [Value]
+  * [Metric 2]: [Value]
+
+Qualitative observations can also be included.
+
+## Model Card Contact
+
+**Author:** Yaqoob Tasal  
+**Username:** tasal9  
+**Organization:** ZamAI  
+[GitHub: https://github.com/tasal9](https://github.com/tasal9)
+
+## Citation
+
+If you use this model or its checkpoints, please consider citing:
+
+```bibtex
+@misc{zamai_bloom_pashto_2025,
+  author    = {Yaqoob Tasal},
+  title     = {ZamAI Bloom Pashto - Fine-tuned Language Model},
+  year      = {2025},
+  publisher = {Hugging Face},
+  journal   = {Hugging Face Model Hub},
+  howpublished = {\url{https://huggingface.co/tasal9/zamai-bloom-ps-final}}
+}
+```
+
+And the original Bloom model:
+```bibtex
+@article{scao2022bloom,
+  title={BLOOM: A 176B-Parameter Open-Access Multilingual Language Model},
+  author={Scao, Teven Le and Fan, Angela and Akiki, Christopher and Baran, Efrat and Ben Cheikh, Rim and Coavoux, Maxime and Davison, Thomas and de Vargas, Niklas Deckers and Delangue, C{\'e}line and Demeusy, Thibault and others},
+  journal={arXiv preprint arXiv:2211.05100},
+  year={2022}
+}
+```
+
+---
+
+Remember to replace placeholders like dataset details, hyperparameters, and evaluation results with your actual project details. Save this as a `README.md` file in your model repository on the Hugging Face Hub.
+
+## Training Details (Cleaned Base Model - June 2025)
+
+This model version was trained from `bigscience/bloom-560m` using the `train_base_model.py` script.
+
+- **Training Data:** The model was trained on a locally prepared dataset located at `datasets/base_pashto_clean`. This dataset was created using `prepare_base_dataset.py` and is derived from `pashto_data/base_model/cleaned_base_data.txt`, which primarily contains Pashto text from a bilingual Pashto-English glossary.
+- **Training Objective:** To establish a foundational Pashto language model with improved coherence and reduced issues (e.g., repetition, off-language generation) compared to any prior versions trained on noisier data.
+- **Output Directory (during training):** `models/pashto-bloom-base-clean-colab`
+- **Key Training Hyperparameters:**
+    - Epochs: 3
+    - Per Device Batch Size: 2
+    - Gradient Accumulation Steps: 4
+    - Learning Rate: 5e-5
+    - FP16 (Mixed Precision): True
+    - Optimizer: AdamW

checkpoint-2829/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250680
+}

checkpoint-2829/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.48.3"
+}

checkpoint-2829/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da99209f92544cc5bb67435831c564d4561d5a31cae6e4c3339f91a68579c48
+size 2236073104

checkpoint-2829/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b225d39b8c1adbc720b566e3fb3fb3a1ad81ec75eeb9ce2f14b2a577bf46f97f
+size 4472324430

checkpoint-2829/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-2829/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3415c1b6fabdb38d6655042b70f1c42c937fba17970b0f944c772dba14a441d
+size 1064

checkpoint-2829/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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2829/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

checkpoint-2829/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": false,
+  "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": "<pad>",
+      "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": {},
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

checkpoint-2829/trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997349589186324,
+  "eval_steps": 500,
+  "global_step": 2829,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03533881084901493,
+      "grad_norm": 130.5043487548828,
+      "learning_rate": 5.4181389870435815e-06,
+      "loss": 5.2462,
+      "step": 100
+    },
+    {
+      "epoch": 0.07067762169802987,
+      "grad_norm": 121.2613754272461,
+      "learning_rate": 1.1189634864546526e-05,
+      "loss": 4.293,
+      "step": 200
+    },
+    {
+      "epoch": 0.10601643254704479,
+      "grad_norm": 28631.3515625,
+      "learning_rate": 1.6961130742049473e-05,
+      "loss": 4.2171,
+      "step": 300
+    },
+    {
+      "epoch": 0.14135524339605973,
+      "grad_norm": 2812505.5,
+      "learning_rate": 2.220259128386337e-05,
+      "loss": 6.2637,
+      "step": 400
+    },
+    {
+      "epoch": 0.17669405424507464,
+      "grad_norm": 416.1485290527344,
+      "learning_rate": 2.7561837455830393e-05,
+      "loss": 166.4242,
+      "step": 500
+    },
+    {
+      "epoch": 0.21203286509408958,
+      "grad_norm": 416.1195373535156,
+      "learning_rate": 3.345111896348646e-05,
+      "loss": 187.1228,
+      "step": 600
+    },
+    {
+      "epoch": 0.24737167594310452,
+      "grad_norm": 392.4357604980469,
+      "learning_rate": 3.934040047114253e-05,
+      "loss": 190.0541,
+      "step": 700
+    },
+    {
+      "epoch": 0.28271048679211946,
+      "grad_norm": 318.76153564453125,
+      "learning_rate": 4.5229681978798585e-05,
+      "loss": 150.7144,
+      "step": 800
+    },
+    {
+      "epoch": 0.3180492976411344,
+      "grad_norm": 407.822021484375,
+      "learning_rate": 4.9875621890547264e-05,
+      "loss": 138.6864,
+      "step": 900
+    },
+    {
+      "epoch": 0.3533881084901493,
+      "grad_norm": 382.1808166503906,
+      "learning_rate": 4.922100026184866e-05,
+      "loss": 131.8268,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38872691933916426,
+      "grad_norm": 374.1636047363281,
+      "learning_rate": 4.8566378633150036e-05,
+      "loss": 118.8281,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42406573018817917,
+      "grad_norm": 276.59124755859375,
+      "learning_rate": 4.791175700445143e-05,
+      "loss": 106.5782,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4594045410371941,
+      "grad_norm": 285.5071105957031,
+      "learning_rate": 4.7257135375752815e-05,
+      "loss": 93.512,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49474335188620905,
+      "grad_norm": 306.88946533203125,
+      "learning_rate": 4.660251374705421e-05,
+      "loss": 82.3966,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5300821627352239,
+      "grad_norm": 259.3111877441406,
+      "learning_rate": 4.594789211835559e-05,
+      "loss": 82.1071,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5654209735842389,
+      "grad_norm": 414.5076599121094,
+      "learning_rate": 4.529327048965698e-05,
+      "loss": 78.2349,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6007597844332538,
+      "grad_norm": 249.02976989746094,
+      "learning_rate": 4.463864886095837e-05,
+      "loss": 65.9571,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6360985952822688,
+      "grad_norm": 188.65126037597656,
+      "learning_rate": 4.398402723225975e-05,
+      "loss": 51.9814,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6714374061312837,
+      "grad_norm": 208.6486358642578,
+      "learning_rate": 4.3329405603561146e-05,
+      "loss": 53.3651,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7067762169802986,
+      "grad_norm": 349.70465087890625,
+      "learning_rate": 4.267478397486253e-05,
+      "loss": 58.8342,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7421150278293135,
+      "grad_norm": 327.7672119140625,
+      "learning_rate": 4.2020162346163925e-05,
+      "loss": 75.0863,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7774538386783285,
+      "grad_norm": 174.98016357421875,
+      "learning_rate": 4.1365540717465304e-05,
+      "loss": 81.5808,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8127926495273434,
+      "grad_norm": 243.49595642089844,
+      "learning_rate": 4.07109190887667e-05,
+      "loss": 85.0316,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8481314603763583,
+      "grad_norm": 193.5273895263672,
+      "learning_rate": 4.005629746006808e-05,
+      "loss": 88.9008,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8834702712253732,
+      "grad_norm": 614.0827026367188,
+      "learning_rate": 3.940167583136947e-05,
+      "loss": 84.831,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9188090820743882,
+      "grad_norm": 430.6079406738281,
+      "learning_rate": 3.8747054202670855e-05,
+      "loss": 71.7362,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9541478929234031,
+      "grad_norm": 285.82318115234375,
+      "learning_rate": 3.809243257397225e-05,
+      "loss": 73.4898,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9894867037724181,
+      "grad_norm": 328.9468078613281,
+      "learning_rate": 3.7437810945273634e-05,
+      "loss": 54.771,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9997349589186324,
+      "eval_loss": NaN,
+      "eval_runtime": 50.7142,
+      "eval_samples_per_second": 49.611,
+      "eval_steps_per_second": 24.806,
+      "step": 2829
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8487,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 940609672003584.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2829/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd754075914a8cc7aa6384a77012a824ab1c56880d743f05986a4069b1cd5fc5
+size 5368

checkpoint-5658/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250680
+}

checkpoint-5658/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.48.3"
+}

checkpoint-5658/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684787c615abc52dc81952c3975a1e7d4c07ac88fb56cdbd2e8bb74bd3578c56
+size 2236073104

checkpoint-5658/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7713aac236be7294ccdc7091a6cc3d57dcef4ba927b71be99619d30ab22b4af7
+size 4472324430

checkpoint-5658/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+size 14244

checkpoint-5658/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc70f87b398935da27e9c8e90d71bb6e5ed23c1ba54b99e2a8d5e44635ac52f3
+size 1064

checkpoint-5658/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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-5658/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

checkpoint-5658/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": false,
+  "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": "<pad>",
+      "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": {},
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

checkpoint-5658/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 1.9997349589186324,
+  "eval_steps": 500,
+  "global_step": 5658,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03533881084901493,
+      "grad_norm": 130.5043487548828,
+      "learning_rate": 5.4181389870435815e-06,
+      "loss": 5.2462,
+      "step": 100
+    },
+    {
+      "epoch": 0.07067762169802987,
+      "grad_norm": 121.2613754272461,
+      "learning_rate": 1.1189634864546526e-05,
+      "loss": 4.293,
+      "step": 200
+    },
+    {
+      "epoch": 0.10601643254704479,
+      "grad_norm": 28631.3515625,
+      "learning_rate": 1.6961130742049473e-05,
+      "loss": 4.2171,
+      "step": 300
+    },
+    {
+      "epoch": 0.14135524339605973,
+      "grad_norm": 2812505.5,
+      "learning_rate": 2.220259128386337e-05,
+      "loss": 6.2637,
+      "step": 400
+    },
+    {
+      "epoch": 0.17669405424507464,
+      "grad_norm": 416.1485290527344,
+      "learning_rate": 2.7561837455830393e-05,
+      "loss": 166.4242,
+      "step": 500
+    },
+    {
+      "epoch": 0.21203286509408958,
+      "grad_norm": 416.1195373535156,
+      "learning_rate": 3.345111896348646e-05,
+      "loss": 187.1228,
+      "step": 600
+    },
+    {
+      "epoch": 0.24737167594310452,
+      "grad_norm": 392.4357604980469,
+      "learning_rate": 3.934040047114253e-05,
+      "loss": 190.0541,
+      "step": 700
+    },
+    {
+      "epoch": 0.28271048679211946,
+      "grad_norm": 318.76153564453125,
+      "learning_rate": 4.5229681978798585e-05,
+      "loss": 150.7144,
+      "step": 800
+    },
+    {
+      "epoch": 0.3180492976411344,
+      "grad_norm": 407.822021484375,
+      "learning_rate": 4.9875621890547264e-05,
+      "loss": 138.6864,
+      "step": 900
+    },
+    {
+      "epoch": 0.3533881084901493,
+      "grad_norm": 382.1808166503906,
+      "learning_rate": 4.922100026184866e-05,
+      "loss": 131.8268,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38872691933916426,
+      "grad_norm": 374.1636047363281,
+      "learning_rate": 4.8566378633150036e-05,
+      "loss": 118.8281,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42406573018817917,
+      "grad_norm": 276.59124755859375,
+      "learning_rate": 4.791175700445143e-05,
+      "loss": 106.5782,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4594045410371941,
+      "grad_norm": 285.5071105957031,
+      "learning_rate": 4.7257135375752815e-05,
+      "loss": 93.512,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49474335188620905,
+      "grad_norm": 306.88946533203125,
+      "learning_rate": 4.660251374705421e-05,
+      "loss": 82.3966,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5300821627352239,
+      "grad_norm": 259.3111877441406,
+      "learning_rate": 4.594789211835559e-05,
+      "loss": 82.1071,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5654209735842389,
+      "grad_norm": 414.5076599121094,
+      "learning_rate": 4.529327048965698e-05,
+      "loss": 78.2349,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6007597844332538,
+      "grad_norm": 249.02976989746094,
+      "learning_rate": 4.463864886095837e-05,
+      "loss": 65.9571,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6360985952822688,
+      "grad_norm": 188.65126037597656,
+      "learning_rate": 4.398402723225975e-05,
+      "loss": 51.9814,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6714374061312837,
+      "grad_norm": 208.6486358642578,
+      "learning_rate": 4.3329405603561146e-05,
+      "loss": 53.3651,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7067762169802986,
+      "grad_norm": 349.70465087890625,
+      "learning_rate": 4.267478397486253e-05,
+      "loss": 58.8342,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7421150278293135,
+      "grad_norm": 327.7672119140625,
+      "learning_rate": 4.2020162346163925e-05,
+      "loss": 75.0863,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7774538386783285,
+      "grad_norm": 174.98016357421875,
+      "learning_rate": 4.1365540717465304e-05,
+      "loss": 81.5808,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8127926495273434,
+      "grad_norm": 243.49595642089844,
+      "learning_rate": 4.07109190887667e-05,
+      "loss": 85.0316,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8481314603763583,
+      "grad_norm": 193.5273895263672,
+      "learning_rate": 4.005629746006808e-05,
+      "loss": 88.9008,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8834702712253732,
+      "grad_norm": 614.0827026367188,
+      "learning_rate": 3.940167583136947e-05,
+      "loss": 84.831,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9188090820743882,
+      "grad_norm": 430.6079406738281,
+      "learning_rate": 3.8747054202670855e-05,
+      "loss": 71.7362,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9541478929234031,
+      "grad_norm": 285.82318115234375,
+      "learning_rate": 3.809243257397225e-05,
+      "loss": 73.4898,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9894867037724181,
+      "grad_norm": 328.9468078613281,
+      "learning_rate": 3.7437810945273634e-05,
+      "loss": 54.771,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9997349589186324,
+      "eval_loss": NaN,
+      "eval_runtime": 50.7142,
+      "eval_samples_per_second": 49.611,
+      "eval_steps_per_second": 24.806,
+      "step": 2829
+    },
+    {
+      "epoch": 1.0250905557028005,
+      "grad_norm": 308.40863037109375,
+      "learning_rate": 3.678318931657502e-05,
+      "loss": 51.9766,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0604293665518156,
+      "grad_norm": 189.22195434570312,
+      "learning_rate": 3.6128567687876407e-05,
+      "loss": 44.7251,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0957681774008305,
+      "grad_norm": 638.1983642578125,
+      "learning_rate": 3.54739460591778e-05,
+      "loss": 32.4377,
+      "step": 3100
+    },
+    {
+      "epoch": 1.1311069882498455,
+      "grad_norm": 273.1210632324219,
+      "learning_rate": 3.4819324430479186e-05,
+      "loss": 34.0672,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1664457990988604,
+      "grad_norm": 509.01788330078125,
+      "learning_rate": 3.416470280178057e-05,
+      "loss": 35.6198,
+      "step": 3300
+    },
+    {
+      "epoch": 1.2017846099478753,
+      "grad_norm": 504.3890686035156,
+      "learning_rate": 3.351008117308196e-05,
+      "loss": 38.9046,
+      "step": 3400
+    },
+    {
+      "epoch": 1.2371234207968902,
+      "grad_norm": 236.5414581298828,
+      "learning_rate": 3.285545954438335e-05,
+      "loss": 36.6003,
+      "step": 3500
+    },
+    {
+      "epoch": 1.272462231645905,
+      "grad_norm": 220.0192108154297,
+      "learning_rate": 3.220083791568474e-05,
+      "loss": 45.3013,
+      "step": 3600
+    },
+    {
+      "epoch": 1.30780104249492,
+      "grad_norm": 343.69354248046875,
+      "learning_rate": 3.154621628698612e-05,
+      "loss": 47.3381,
+      "step": 3700
+    },
+    {
+      "epoch": 1.343139853343935,
+      "grad_norm": 286.2487487792969,
+      "learning_rate": 3.089159465828751e-05,
+      "loss": 56.1506,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3784786641929498,
+      "grad_norm": 258.3203430175781,
+      "learning_rate": 3.02369730295889e-05,
+      "loss": 62.5717,
+      "step": 3900
+    },
+    {
+      "epoch": 1.4138174750419648,
+      "grad_norm": 291.66729736328125,
+      "learning_rate": 2.9582351400890285e-05,
+      "loss": 66.6682,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4491562858909797,
+      "grad_norm": 287.23291015625,
+      "learning_rate": 2.8927729772191674e-05,
+      "loss": 73.0452,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4844950967399946,
+      "grad_norm": 263.8997802734375,
+      "learning_rate": 2.827310814349306e-05,
+      "loss": 74.5742,
+      "step": 4200
+    },
+    {
+      "epoch": 1.5198339075890095,
+      "grad_norm": 725.5924072265625,
+      "learning_rate": 2.761848651479445e-05,
+      "loss": 75.3333,
+      "step": 4300
+    },
+    {
+      "epoch": 1.5551727184380244,
+      "grad_norm": 255.7268829345703,
+      "learning_rate": 2.6963864886095836e-05,
+      "loss": 71.4852,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5905115292870395,
+      "grad_norm": 358.010498046875,
+      "learning_rate": 2.6309243257397226e-05,
+      "loss": 73.1212,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6258503401360545,
+      "grad_norm": 382.2020568847656,
+      "learning_rate": 2.565462162869861e-05,
+      "loss": 77.8558,
+      "step": 4600
+    },
+    {
+      "epoch": 1.6611891509850694,
+      "grad_norm": 376.1300048828125,
+      "learning_rate": 2.5e-05,
+      "loss": 82.9754,
+      "step": 4700
+    },
+    {
+      "epoch": 1.6965279618340843,
+      "grad_norm": 270.1905822753906,
+      "learning_rate": 2.4345378371301387e-05,
+      "loss": 87.3897,
+      "step": 4800
+    },
+    {
+      "epoch": 1.7318667726830992,
+      "grad_norm": 263.4345397949219,
+      "learning_rate": 2.3690756742602777e-05,
+      "loss": 86.5547,
+      "step": 4900
+    },
+    {
+      "epoch": 1.767205583532114,
+      "grad_norm": 285.1637268066406,
+      "learning_rate": 2.3036135113904163e-05,
+      "loss": 90.7775,
+      "step": 5000
+    },
+    {
+      "epoch": 1.8025443943811292,
+      "grad_norm": 296.69482421875,
+      "learning_rate": 2.2381513485205552e-05,
+      "loss": 93.2774,
+      "step": 5100
+    },
+    {
+      "epoch": 1.8378832052301441,
+      "grad_norm": 319.2518005371094,
+      "learning_rate": 2.172689185650694e-05,
+      "loss": 92.5169,
+      "step": 5200
+    },
+    {
+      "epoch": 1.873222016079159,
+      "grad_norm": 354.99530029296875,
+      "learning_rate": 2.1072270227808328e-05,
+      "loss": 98.2755,
+      "step": 5300
+    },
+    {
+      "epoch": 1.908560826928174,
+      "grad_norm": 325.14776611328125,
+      "learning_rate": 2.0417648599109714e-05,
+      "loss": 97.8725,
+      "step": 5400
+    },
+    {
+      "epoch": 1.9438996377771889,
+      "grad_norm": 335.0797424316406,
+      "learning_rate": 1.9763026970411104e-05,
+      "loss": 99.2225,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9792384486262038,
+      "grad_norm": 351.8290710449219,
+      "learning_rate": 1.910840534171249e-05,
+      "loss": 100.1383,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9997349589186324,
+      "eval_loss": NaN,
+      "eval_runtime": 51.2483,
+      "eval_samples_per_second": 49.094,
+      "eval_steps_per_second": 24.547,
+      "step": 5658
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8487,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1884306569183232.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5658/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd754075914a8cc7aa6384a77012a824ab1c56880d743f05986a4069b1cd5fc5
+size 5368

checkpoint-8487/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250680
+}

checkpoint-8487/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.48.3"
+}

checkpoint-8487/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c36d5ff990e34d7c8bcbf97484b8adf792d66f36af9917c3f54caac9cca43a3
+size 2236073104

checkpoint-8487/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c579dd0782c64345c329cf6683ba3c19b524eb7b0232798fc32fa74f2929dd3
+size 4472324430

checkpoint-8487/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

checkpoint-8487/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cb5f47cc10848063f533ef07ba2bb2229bb85a359eb996c350f893ab7840b0
+size 1064

checkpoint-8487/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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-8487/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

checkpoint-8487/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": false,
+  "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": "<pad>",
+      "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": {},
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

checkpoint-8487/trainer_state.json

@@ -0,0 +1,645 @@
+{
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 2.9997349589186326,
+  "eval_steps": 500,
+  "global_step": 8487,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03533881084901493,
+      "grad_norm": 130.5043487548828,
+      "learning_rate": 5.4181389870435815e-06,
+      "loss": 5.2462,
+      "step": 100
+    },
+    {
+      "epoch": 0.07067762169802987,
+      "grad_norm": 121.2613754272461,
+      "learning_rate": 1.1189634864546526e-05,
+      "loss": 4.293,
+      "step": 200
+    },
+    {
+      "epoch": 0.10601643254704479,
+      "grad_norm": 28631.3515625,
+      "learning_rate": 1.6961130742049473e-05,
+      "loss": 4.2171,
+      "step": 300
+    },
+    {
+      "epoch": 0.14135524339605973,
+      "grad_norm": 2812505.5,
+      "learning_rate": 2.220259128386337e-05,
+      "loss": 6.2637,
+      "step": 400
+    },
+    {
+      "epoch": 0.17669405424507464,
+      "grad_norm": 416.1485290527344,
+      "learning_rate": 2.7561837455830393e-05,
+      "loss": 166.4242,
+      "step": 500
+    },
+    {
+      "epoch": 0.21203286509408958,
+      "grad_norm": 416.1195373535156,
+      "learning_rate": 3.345111896348646e-05,
+      "loss": 187.1228,
+      "step": 600
+    },
+    {
+      "epoch": 0.24737167594310452,
+      "grad_norm": 392.4357604980469,
+      "learning_rate": 3.934040047114253e-05,
+      "loss": 190.0541,
+      "step": 700
+    },
+    {
+      "epoch": 0.28271048679211946,
+      "grad_norm": 318.76153564453125,
+      "learning_rate": 4.5229681978798585e-05,
+      "loss": 150.7144,
+      "step": 800
+    },
+    {
+      "epoch": 0.3180492976411344,
+      "grad_norm": 407.822021484375,
+      "learning_rate": 4.9875621890547264e-05,
+      "loss": 138.6864,
+      "step": 900
+    },
+    {
+      "epoch": 0.3533881084901493,
+      "grad_norm": 382.1808166503906,
+      "learning_rate": 4.922100026184866e-05,
+      "loss": 131.8268,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38872691933916426,
+      "grad_norm": 374.1636047363281,
+      "learning_rate": 4.8566378633150036e-05,
+      "loss": 118.8281,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42406573018817917,
+      "grad_norm": 276.59124755859375,
+      "learning_rate": 4.791175700445143e-05,
+      "loss": 106.5782,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4594045410371941,
+      "grad_norm": 285.5071105957031,
+      "learning_rate": 4.7257135375752815e-05,
+      "loss": 93.512,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49474335188620905,
+      "grad_norm": 306.88946533203125,
+      "learning_rate": 4.660251374705421e-05,
+      "loss": 82.3966,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5300821627352239,
+      "grad_norm": 259.3111877441406,
+      "learning_rate": 4.594789211835559e-05,
+      "loss": 82.1071,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5654209735842389,
+      "grad_norm": 414.5076599121094,
+      "learning_rate": 4.529327048965698e-05,
+      "loss": 78.2349,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6007597844332538,
+      "grad_norm": 249.02976989746094,
+      "learning_rate": 4.463864886095837e-05,
+      "loss": 65.9571,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6360985952822688,
+      "grad_norm": 188.65126037597656,
+      "learning_rate": 4.398402723225975e-05,
+      "loss": 51.9814,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6714374061312837,
+      "grad_norm": 208.6486358642578,
+      "learning_rate": 4.3329405603561146e-05,
+      "loss": 53.3651,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7067762169802986,
+      "grad_norm": 349.70465087890625,
+      "learning_rate": 4.267478397486253e-05,
+      "loss": 58.8342,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7421150278293135,
+      "grad_norm": 327.7672119140625,
+      "learning_rate": 4.2020162346163925e-05,
+      "loss": 75.0863,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7774538386783285,
+      "grad_norm": 174.98016357421875,
+      "learning_rate": 4.1365540717465304e-05,
+      "loss": 81.5808,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8127926495273434,
+      "grad_norm": 243.49595642089844,
+      "learning_rate": 4.07109190887667e-05,
+      "loss": 85.0316,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8481314603763583,
+      "grad_norm": 193.5273895263672,
+      "learning_rate": 4.005629746006808e-05,
+      "loss": 88.9008,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8834702712253732,
+      "grad_norm": 614.0827026367188,
+      "learning_rate": 3.940167583136947e-05,
+      "loss": 84.831,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9188090820743882,
+      "grad_norm": 430.6079406738281,
+      "learning_rate": 3.8747054202670855e-05,
+      "loss": 71.7362,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9541478929234031,
+      "grad_norm": 285.82318115234375,
+      "learning_rate": 3.809243257397225e-05,
+      "loss": 73.4898,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9894867037724181,
+      "grad_norm": 328.9468078613281,
+      "learning_rate": 3.7437810945273634e-05,
+      "loss": 54.771,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9997349589186324,
+      "eval_loss": NaN,
+      "eval_runtime": 50.7142,
+      "eval_samples_per_second": 49.611,
+      "eval_steps_per_second": 24.806,
+      "step": 2829
+    },
+    {
+      "epoch": 1.0250905557028005,
+      "grad_norm": 308.40863037109375,
+      "learning_rate": 3.678318931657502e-05,
+      "loss": 51.9766,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0604293665518156,
+      "grad_norm": 189.22195434570312,
+      "learning_rate": 3.6128567687876407e-05,
+      "loss": 44.7251,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0957681774008305,
+      "grad_norm": 638.1983642578125,
+      "learning_rate": 3.54739460591778e-05,
+      "loss": 32.4377,
+      "step": 3100
+    },
+    {
+      "epoch": 1.1311069882498455,
+      "grad_norm": 273.1210632324219,
+      "learning_rate": 3.4819324430479186e-05,
+      "loss": 34.0672,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1664457990988604,
+      "grad_norm": 509.01788330078125,
+      "learning_rate": 3.416470280178057e-05,
+      "loss": 35.6198,
+      "step": 3300
+    },
+    {
+      "epoch": 1.2017846099478753,
+      "grad_norm": 504.3890686035156,
+      "learning_rate": 3.351008117308196e-05,
+      "loss": 38.9046,
+      "step": 3400
+    },
+    {
+      "epoch": 1.2371234207968902,
+      "grad_norm": 236.5414581298828,
+      "learning_rate": 3.285545954438335e-05,
+      "loss": 36.6003,
+      "step": 3500
+    },
+    {
+      "epoch": 1.272462231645905,
+      "grad_norm": 220.0192108154297,
+      "learning_rate": 3.220083791568474e-05,
+      "loss": 45.3013,
+      "step": 3600
+    },
+    {
+      "epoch": 1.30780104249492,
+      "grad_norm": 343.69354248046875,
+      "learning_rate": 3.154621628698612e-05,
+      "loss": 47.3381,
+      "step": 3700
+    },
+    {
+      "epoch": 1.343139853343935,
+      "grad_norm": 286.2487487792969,
+      "learning_rate": 3.089159465828751e-05,
+      "loss": 56.1506,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3784786641929498,
+      "grad_norm": 258.3203430175781,
+      "learning_rate": 3.02369730295889e-05,
+      "loss": 62.5717,
+      "step": 3900
+    },
+    {
+      "epoch": 1.4138174750419648,
+      "grad_norm": 291.66729736328125,
+      "learning_rate": 2.9582351400890285e-05,
+      "loss": 66.6682,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4491562858909797,
+      "grad_norm": 287.23291015625,
+      "learning_rate": 2.8927729772191674e-05,
+      "loss": 73.0452,
+      "step": 4100
+    },
+    {
+      "epoch": 1.4844950967399946,
+      "grad_norm": 263.8997802734375,
+      "learning_rate": 2.827310814349306e-05,
+      "loss": 74.5742,
+      "step": 4200
+    },
+    {
+      "epoch": 1.5198339075890095,
+      "grad_norm": 725.5924072265625,
+      "learning_rate": 2.761848651479445e-05,
+      "loss": 75.3333,
+      "step": 4300
+    },
+    {
+      "epoch": 1.5551727184380244,
+      "grad_norm": 255.7268829345703,
+      "learning_rate": 2.6963864886095836e-05,
+      "loss": 71.4852,
+      "step": 4400
+    },
+    {
+      "epoch": 1.5905115292870395,
+      "grad_norm": 358.010498046875,
+      "learning_rate": 2.6309243257397226e-05,
+      "loss": 73.1212,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6258503401360545,
+      "grad_norm": 382.2020568847656,
+      "learning_rate": 2.565462162869861e-05,
+      "loss": 77.8558,
+      "step": 4600
+    },
+    {
+      "epoch": 1.6611891509850694,
+      "grad_norm": 376.1300048828125,
+      "learning_rate": 2.5e-05,
+      "loss": 82.9754,
+      "step": 4700
+    },
+    {
+      "epoch": 1.6965279618340843,
+      "grad_norm": 270.1905822753906,
+      "learning_rate": 2.4345378371301387e-05,
+      "loss": 87.3897,
+      "step": 4800
+    },
+    {
+      "epoch": 1.7318667726830992,
+      "grad_norm": 263.4345397949219,
+      "learning_rate": 2.3690756742602777e-05,
+      "loss": 86.5547,
+      "step": 4900
+    },
+    {
+      "epoch": 1.767205583532114,
+      "grad_norm": 285.1637268066406,
+      "learning_rate": 2.3036135113904163e-05,
+      "loss": 90.7775,
+      "step": 5000
+    },
+    {
+      "epoch": 1.8025443943811292,
+      "grad_norm": 296.69482421875,
+      "learning_rate": 2.2381513485205552e-05,
+      "loss": 93.2774,
+      "step": 5100
+    },
+    {
+      "epoch": 1.8378832052301441,
+      "grad_norm": 319.2518005371094,
+      "learning_rate": 2.172689185650694e-05,
+      "loss": 92.5169,
+      "step": 5200
+    },
+    {
+      "epoch": 1.873222016079159,
+      "grad_norm": 354.99530029296875,
+      "learning_rate": 2.1072270227808328e-05,
+      "loss": 98.2755,
+      "step": 5300
+    },
+    {
+      "epoch": 1.908560826928174,
+      "grad_norm": 325.14776611328125,
+      "learning_rate": 2.0417648599109714e-05,
+      "loss": 97.8725,
+      "step": 5400
+    },
+    {
+      "epoch": 1.9438996377771889,
+      "grad_norm": 335.0797424316406,
+      "learning_rate": 1.9763026970411104e-05,
+      "loss": 99.2225,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9792384486262038,
+      "grad_norm": 351.8290710449219,
+      "learning_rate": 1.910840534171249e-05,
+      "loss": 100.1383,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9997349589186324,
+      "eval_loss": NaN,
+      "eval_runtime": 51.2483,
+      "eval_samples_per_second": 49.094,
+      "eval_steps_per_second": 24.547,
+      "step": 5658
+    },
+    {
+      "epoch": 2.014842300556586,
+      "grad_norm": 339.35479736328125,
+      "learning_rate": 1.845378371301388e-05,
+      "loss": 101.0501,
+      "step": 5700
+    },
+    {
+      "epoch": 2.050181111405601,
+      "grad_norm": 337.0163269042969,
+      "learning_rate": 1.7799162084315266e-05,
+      "loss": 106.9505,
+      "step": 5800
+    },
+    {
+      "epoch": 2.0855199222546164,
+      "grad_norm": 295.1744689941406,
+      "learning_rate": 1.714454045561665e-05,
+      "loss": 103.8797,
+      "step": 5900
+    },
+    {
+      "epoch": 2.1208587331036313,
+      "grad_norm": 313.05487060546875,
+      "learning_rate": 1.648991882691804e-05,
+      "loss": 104.9367,
+      "step": 6000
+    },
+    {
+      "epoch": 2.156197543952646,
+      "grad_norm": 455.3573913574219,
+      "learning_rate": 1.5835297198219427e-05,
+      "loss": 108.2618,
+      "step": 6100
+    },
+    {
+      "epoch": 2.191536354801661,
+      "grad_norm": 413.2171325683594,
+      "learning_rate": 1.5180675569520817e-05,
+      "loss": 108.1512,
+      "step": 6200
+    },
+    {
+      "epoch": 2.226875165650676,
+      "grad_norm": 412.13140869140625,
+      "learning_rate": 1.4526053940822206e-05,
+      "loss": 111.6234,
+      "step": 6300
+    },
+    {
+      "epoch": 2.262213976499691,
+      "grad_norm": 637.2862548828125,
+      "learning_rate": 1.3871432312123594e-05,
+      "loss": 111.8395,
+      "step": 6400
+    },
+    {
+      "epoch": 2.297552787348706,
+      "grad_norm": 289.26751708984375,
+      "learning_rate": 1.3216810683424982e-05,
+      "loss": 113.3466,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3328915981977207,
+      "grad_norm": 295.8336181640625,
+      "learning_rate": 1.256218905472637e-05,
+      "loss": 105.6647,
+      "step": 6600
+    },
+    {
+      "epoch": 2.3682304090467357,
+      "grad_norm": 263.1067810058594,
+      "learning_rate": 1.1907567426027756e-05,
+      "loss": 105.089,
+      "step": 6700
+    },
+    {
+      "epoch": 2.4035692198957506,
+      "grad_norm": 263.7178649902344,
+      "learning_rate": 1.1252945797329144e-05,
+      "loss": 106.2189,
+      "step": 6800
+    },
+    {
+      "epoch": 2.4389080307447655,
+      "grad_norm": 281.2179260253906,
+      "learning_rate": 1.0598324168630532e-05,
+      "loss": 98.9815,
+      "step": 6900
+    },
+    {
+      "epoch": 2.4742468415937804,
+      "grad_norm": 270.7872619628906,
+      "learning_rate": 9.94370253993192e-06,
+      "loss": 97.342,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5095856524427953,
+      "grad_norm": 500.3921813964844,
+      "learning_rate": 9.289080911233309e-06,
+      "loss": 98.0968,
+      "step": 7100
+    },
+    {
+      "epoch": 2.54492446329181,
+      "grad_norm": 322.947021484375,
+      "learning_rate": 8.634459282534697e-06,
+      "loss": 98.3004,
+      "step": 7200
+    },
+    {
+      "epoch": 2.580263274140825,
+      "grad_norm": 253.83358764648438,
+      "learning_rate": 7.979837653836083e-06,
+      "loss": 97.1224,
+      "step": 7300
+    },
+    {
+      "epoch": 2.61560208498984,
+      "grad_norm": 770.7826538085938,
+      "learning_rate": 7.3252160251374715e-06,
+      "loss": 89.2073,
+      "step": 7400
+    },
+    {
+      "epoch": 2.650940895838855,
+      "grad_norm": 497.59124755859375,
+      "learning_rate": 6.670594396438859e-06,
+      "loss": 96.602,
+      "step": 7500
+    },
+    {
+      "epoch": 2.68627970668787,
+      "grad_norm": 257.338623046875,
+      "learning_rate": 6.015972767740246e-06,
+      "loss": 98.7739,
+      "step": 7600
+    },
+    {
+      "epoch": 2.7216185175368848,
+      "grad_norm": 276.27337646484375,
+      "learning_rate": 5.361351139041634e-06,
+      "loss": 93.0737,
+      "step": 7700
+    },
+    {
+      "epoch": 2.7569573283858997,
+      "grad_norm": 301.7321472167969,
+      "learning_rate": 4.706729510343022e-06,
+      "loss": 93.7306,
+      "step": 7800
+    },
+    {
+      "epoch": 2.7922961392349146,
+      "grad_norm": 265.5256652832031,
+      "learning_rate": 4.05210788164441e-06,
+      "loss": 92.7555,
+      "step": 7900
+    },
+    {
+      "epoch": 2.8276349500839295,
+      "grad_norm": 425.70501708984375,
+      "learning_rate": 3.397486252945797e-06,
+      "loss": 95.7403,
+      "step": 8000
+    },
+    {
+      "epoch": 2.8629737609329444,
+      "grad_norm": 254.2684326171875,
+      "learning_rate": 2.7428646242471854e-06,
+      "loss": 94.279,
+      "step": 8100
+    },
+    {
+      "epoch": 2.8983125717819593,
+      "grad_norm": 282.39202880859375,
+      "learning_rate": 2.0882429955485732e-06,
+      "loss": 96.5359,
+      "step": 8200
+    },
+    {
+      "epoch": 2.9336513826309742,
+      "grad_norm": 313.8695068359375,
+      "learning_rate": 1.4336213668499608e-06,
+      "loss": 97.4498,
+      "step": 8300
+    },
+    {
+      "epoch": 2.968990193479989,
+      "grad_norm": 234.9430389404297,
+      "learning_rate": 7.789997381513486e-07,
+      "loss": 95.4695,
+      "step": 8400
+    },
+    {
+      "epoch": 2.9997349589186326,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8651,
+      "eval_samples_per_second": 49.464,
+      "eval_steps_per_second": 24.732,
+      "step": 8487
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8487,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2826570500505600.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8487/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd754075914a8cc7aa6384a77012a824ab1c56880d743f05986a4069b1cd5fc5
+size 5368

final_model/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250680
+}

final_model/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.48.3"
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c36d5ff990e34d7c8bcbf97484b8adf792d66f36af9917c3f54caac9cca43a3
+size 2236073104

final_model/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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

final_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

final_model/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": false,
+  "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": "<pad>",
+      "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": {},
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd754075914a8cc7aa6384a77012a824ab1c56880d743f05986a4069b1cd5fc5
+size 5368

logs/events.out.tfevents.1749891083.51d9157369b8.14130.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde15f0588c68d6346d96578059866fa45524410d2d895af4899f4330158ab07
+size 24135