Duplicate from HuggingFaceTB/SmolLM2-Instruct-16k-SeaLong-LongAlign-ST10k-v2-rope500k-1e-4

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+model_name: SmolLM2-Instruct-16k-SeaLong-LongAlign-ST10k-v2-rope500k-1e-4
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for SmolLM2-Instruct-16k-SeaLong-LongAlign-ST10k-v2-rope500k-1e-4
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="HuggingFaceTB/SmolLM2-Instruct-16k-SeaLong-LongAlign-ST10k-v2-rope500k-1e-4", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/loubnabnl/huggingface/runs/y937l2wj) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.14.0.dev0
+- Transformers: 4.48.1
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 84368078012416.0,
+    "train_loss": 0.0,
+    "train_runtime": 1.4481,
+    "train_samples": 15608,
+    "train_samples_per_second": 10777.998,
+    "train_steps_per_second": 168.493
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/fsx/loubna/data/SmolLM2-1.7B-Instruct-rope500k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b31f0cd32d70f0c46092b41d044d46991a901438af30fa10036387b154509e
+size 3422777952

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 84368078012416.0,
+    "train_loss": 0.0,
+    "train_runtime": 1.4481,
+    "train_samples": 15608,
+    "train_samples_per_second": 10777.998,
+    "train_steps_per_second": 168.493
+}

trainer_state.json

@@ -0,0 +1,386 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020491803278688523,
+      "grad_norm": 0.3614635057701486,
+      "learning_rate": 2e-05,
+      "loss": 1.3385,
+      "step": 5
+    },
+    {
+      "epoch": 0.040983606557377046,
+      "grad_norm": 0.2489719842782885,
+      "learning_rate": 4e-05,
+      "loss": 1.3036,
+      "step": 10
+    },
+    {
+      "epoch": 0.06147540983606557,
+      "grad_norm": 0.21147248994437587,
+      "learning_rate": 6e-05,
+      "loss": 1.2625,
+      "step": 15
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 0.19373427885281047,
+      "learning_rate": 8e-05,
+      "loss": 1.1662,
+      "step": 20
+    },
+    {
+      "epoch": 0.10245901639344263,
+      "grad_norm": 0.16443335321911356,
+      "learning_rate": 0.0001,
+      "loss": 1.2303,
+      "step": 25
+    },
+    {
+      "epoch": 0.12295081967213115,
+      "grad_norm": 0.14174512674576367,
+      "learning_rate": 9.987144015627809e-05,
+      "loss": 1.1398,
+      "step": 30
+    },
+    {
+      "epoch": 0.14344262295081966,
+      "grad_norm": 0.1381398528306756,
+      "learning_rate": 9.948642173044905e-05,
+      "loss": 1.3659,
+      "step": 35
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 19.814446058738557,
+      "learning_rate": 9.88469246388591e-05,
+      "loss": 1.2665,
+      "step": 40
+    },
+    {
+      "epoch": 0.18442622950819673,
+      "grad_norm": 0.15246937379745587,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 1.2956,
+      "step": 45
+    },
+    {
+      "epoch": 0.20491803278688525,
+      "grad_norm": 0.11304889245590244,
+      "learning_rate": 9.681894036028365e-05,
+      "loss": 1.3647,
+      "step": 50
+    },
+    {
+      "epoch": 0.22540983606557377,
+      "grad_norm": 0.11799961373671249,
+      "learning_rate": 9.544088186697515e-05,
+      "loss": 1.2491,
+      "step": 55
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 0.0886669617443345,
+      "learning_rate": 9.382914846681047e-05,
+      "loss": 1.1422,
+      "step": 60
+    },
+    {
+      "epoch": 0.26639344262295084,
+      "grad_norm": 0.13383163861854966,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 1.217,
+      "step": 65
+    },
+    {
+      "epoch": 0.28688524590163933,
+      "grad_norm": 0.12664816060876666,
+      "learning_rate": 8.993896864431826e-05,
+      "loss": 1.1728,
+      "step": 70
+    },
+    {
+      "epoch": 0.3073770491803279,
+      "grad_norm": 0.11280543596286248,
+      "learning_rate": 8.76805270583919e-05,
+      "loss": 1.2914,
+      "step": 75
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.11457176824246548,
+      "learning_rate": 8.522831736566607e-05,
+      "loss": 1.2975,
+      "step": 80
+    },
+    {
+      "epoch": 0.3483606557377049,
+      "grad_norm": 0.125952078460287,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 1.2325,
+      "step": 85
+    },
+    {
+      "epoch": 0.36885245901639346,
+      "grad_norm": 0.14141125617004555,
+      "learning_rate": 7.97939661561399e-05,
+      "loss": 1.3628,
+      "step": 90
+    },
+    {
+      "epoch": 0.38934426229508196,
+      "grad_norm": 0.12898427772056165,
+      "learning_rate": 7.68397702130286e-05,
+      "loss": 1.3272,
+      "step": 95
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 0.12462484863790337,
+      "learning_rate": 7.374755360335253e-05,
+      "loss": 1.2025,
+      "step": 100
+    },
+    {
+      "epoch": 0.430327868852459,
+      "grad_norm": 0.15405301651774622,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 1.3946,
+      "step": 105
+    },
+    {
+      "epoch": 0.45081967213114754,
+      "grad_norm": 0.11850088757256459,
+      "learning_rate": 6.721329195113801e-05,
+      "loss": 1.0897,
+      "step": 110
+    },
+    {
+      "epoch": 0.4713114754098361,
+      "grad_norm": 0.10161954341550462,
+      "learning_rate": 6.380484865487347e-05,
+      "loss": 1.3683,
+      "step": 115
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 0.1338711959037296,
+      "learning_rate": 6.032541539118187e-05,
+      "loss": 1.0908,
+      "step": 120
+    },
+    {
+      "epoch": 0.5122950819672131,
+      "grad_norm": 0.12226354104013447,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 1.301,
+      "step": 125
+    },
+    {
+      "epoch": 0.5327868852459017,
+      "grad_norm": 0.11741161974948867,
+      "learning_rate": 5.3225422472465824e-05,
+      "loss": 1.2055,
+      "step": 130
+    },
+    {
+      "epoch": 0.5532786885245902,
+      "grad_norm": 0.1220585245683397,
+      "learning_rate": 4.9641373776643616e-05,
+      "loss": 1.2117,
+      "step": 135
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 0.1283897077062444,
+      "learning_rate": 4.605916927807057e-05,
+      "loss": 1.1798,
+      "step": 140
+    },
+    {
+      "epoch": 0.5942622950819673,
+      "grad_norm": 0.13195983815349108,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 1.2929,
+      "step": 145
+    },
+    {
+      "epoch": 0.6147540983606558,
+      "grad_norm": 0.10033441692536059,
+      "learning_rate": 3.89738730845858e-05,
+      "loss": 1.1865,
+      "step": 150
+    },
+    {
+      "epoch": 0.6352459016393442,
+      "grad_norm": 0.10526603636165197,
+      "learning_rate": 3.550721677252839e-05,
+      "loss": 1.1911,
+      "step": 155
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.11769891562161476,
+      "learning_rate": 3.2115088058343725e-05,
+      "loss": 1.1442,
+      "step": 160
+    },
+    {
+      "epoch": 0.6762295081967213,
+      "grad_norm": 0.09808797452553064,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 1.2862,
+      "step": 165
+    },
+    {
+      "epoch": 0.6967213114754098,
+      "grad_norm": 0.25170420435929075,
+      "learning_rate": 2.5623715117144336e-05,
+      "loss": 1.2449,
+      "step": 170
+    },
+    {
+      "epoch": 0.7172131147540983,
+      "grad_norm": 0.14162820792284236,
+      "learning_rate": 2.2557852085764053e-05,
+      "loss": 1.2093,
+      "step": 175
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 0.09769546802692396,
+      "learning_rate": 1.963310738427367e-05,
+      "loss": 1.1962,
+      "step": 180
+    },
+    {
+      "epoch": 0.7581967213114754,
+      "grad_norm": 0.10477577716382458,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 1.1101,
+      "step": 185
+    },
+    {
+      "epoch": 0.7786885245901639,
+      "grad_norm": 0.1197892608117282,
+      "learning_rate": 1.4266330697851954e-05,
+      "loss": 1.3805,
+      "step": 190
+    },
+    {
+      "epoch": 0.7991803278688525,
+      "grad_norm": 0.10767908097089735,
+      "learning_rate": 1.1851896791804507e-05,
+      "loss": 1.3342,
+      "step": 195
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 0.10976930143838647,
+      "learning_rate": 9.633635453226376e-06,
+      "loss": 1.3511,
+      "step": 200
+    },
+    {
+      "epoch": 0.8401639344262295,
+      "grad_norm": 0.10305982170288747,
+      "learning_rate": 7.6229538553584556e-06,
+      "loss": 1.265,
+      "step": 205
+    },
+    {
+      "epoch": 0.860655737704918,
+      "grad_norm": 0.09095323069274693,
+      "learning_rate": 5.830191714680577e-06,
+      "loss": 1.2826,
+      "step": 210
+    },
+    {
+      "epoch": 0.8811475409836066,
+      "grad_norm": 0.12664820610601704,
+      "learning_rate": 4.26456812001822e-06,
+      "loss": 1.2256,
+      "step": 215
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 0.11352528001951419,
+      "learning_rate": 2.934134124357646e-06,
+      "loss": 1.2583,
+      "step": 220
+    },
+    {
+      "epoch": 0.9221311475409836,
+      "grad_norm": 0.10147400081855255,
+      "learning_rate": 1.8457313431614498e-06,
+      "loss": 1.2593,
+      "step": 225
+    },
+    {
+      "epoch": 0.9426229508196722,
+      "grad_norm": 0.11813110730985737,
+      "learning_rate": 1.004956772087895e-06,
+      "loss": 1.2518,
+      "step": 230
+    },
+    {
+      "epoch": 0.9631147540983607,
+      "grad_norm": 0.10427451227791518,
+      "learning_rate": 4.1613400503550114e-07,
+      "loss": 1.3182,
+      "step": 235
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.10936990134938639,
+      "learning_rate": 8.229100052074556e-08,
+      "loss": 1.2333,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1466403007507324,
+      "eval_runtime": 27.0287,
+      "eval_samples_per_second": 11.802,
+      "eval_steps_per_second": 0.37,
+      "step": 244
+    },
+    {
+      "epoch": 1.0,
+      "step": 244,
+      "total_flos": 84368078012416.0,
+      "train_loss": 0.0,
+      "train_runtime": 1.4481,
+      "train_samples_per_second": 10777.998,
+      "train_steps_per_second": 168.493
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 244,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 84368078012416.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1cc166749728cf7e68ae971019ba8107377034f0a50c697f402de8298515f0
+size 7288