Model save

README.md

@@ -0,0 +1,67 @@
+---
+base_model: loubnabnl/smollm-1.7b-16k
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: smollm-1.7B-16k-instruct-v0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/7rd4806f)
+# smollm-1.7B-16k-instruct-v0
+
+This model is a fine-tuned version of [loubnabnl/smollm-1.7b-16k](https://huggingface.co/loubnabnl/smollm-1.7b-16k) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0118
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6674        | 0.9951 | 102  | 1.0118          |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9951219512195122,
+    "total_flos": 128481799176192.0,
+    "train_loss": 0.7558732021088693,
+    "train_runtime": 2589.5829,
+    "train_samples": 321330,
+    "train_samples_per_second": 5.059,
+    "train_steps_per_second": 0.039
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "loubnabnl/smollm-1.7b-16k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 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": 273768.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "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": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c189fa7f341c47f0289162c461b0e937ed687df099372ceb93d21cbc2b6754b
+size 3422777952

runs/Sep20_12-08-36_ip-26-0-168-120/events.out.tfevents.1726835177.ip-26-0-168-120.4123050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad99f9c35fb3a3706cdd1c0b29b1840becedbef3baa46cd633b76fafe13e7b9
+size 10036

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "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|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9951219512195122,
+    "total_flos": 128481799176192.0,
+    "train_loss": 0.7558732021088693,
+    "train_runtime": 2589.5829,
+    "train_samples": 321330,
+    "train_samples_per_second": 5.059,
+    "train_steps_per_second": 0.039
+}

trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9951219512195122,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00975609756097561,
+      "grad_norm": 6.261786177237342,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 1.1256,
+      "step": 1
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 2.1112596954065914,
+      "learning_rate": 0.00045454545454545455,
+      "loss": 1.049,
+      "step": 5
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 1.5895813487100507,
+      "learning_rate": 0.0009090909090909091,
+      "loss": 1.0974,
+      "step": 10
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.32863787167794134,
+      "learning_rate": 0.0009952402219937815,
+      "loss": 0.9164,
+      "step": 15
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.23963144918280163,
+      "learning_rate": 0.0009760588329553571,
+      "loss": 0.8434,
+      "step": 20
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.14493890865001488,
+      "learning_rate": 0.0009427280128266049,
+      "loss": 0.8011,
+      "step": 25
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.12052712473534186,
+      "learning_rate": 0.0008962384209755452,
+      "loss": 0.7652,
+      "step": 30
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.0981844421832599,
+      "learning_rate": 0.0008379718220723773,
+      "loss": 0.7453,
+      "step": 35
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.18540719570949135,
+      "learning_rate": 0.0007696600172495997,
+      "loss": 0.7317,
+      "step": 40
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.12172997652512386,
+      "learning_rate": 0.0006933333714707094,
+      "loss": 0.7179,
+      "step": 45
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.1050067175867305,
+      "learning_rate": 0.0006112604669781572,
+      "loss": 0.7047,
+      "step": 50
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.0824375568337565,
+      "learning_rate": 0.0005258806764421047,
+      "loss": 0.6991,
+      "step": 55
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.09661916029526949,
+      "learning_rate": 0.00043973165987233853,
+      "loss": 0.6865,
+      "step": 60
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.07527219081930579,
+      "learning_rate": 0.0003553739402317162,
+      "loss": 0.6833,
+      "step": 65
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.07406811411334399,
+      "learning_rate": 0.00027531479951641924,
+      "loss": 0.6793,
+      "step": 70
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.21265879474641486,
+      "learning_rate": 0.00020193375726538737,
+      "loss": 0.6726,
+      "step": 75
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.06699755926217109,
+      "learning_rate": 0.0001374118464283119,
+      "loss": 0.6685,
+      "step": 80
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 0.0915919461803413,
+      "learning_rate": 8.366678865639687e-05,
+      "loss": 0.6716,
+      "step": 85
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.06490947271665126,
+      "learning_rate": 4.2295995737316854e-05,
+      "loss": 0.6692,
+      "step": 90
+    },
+    {
+      "epoch": 0.926829268292683,
+      "grad_norm": 0.1069137841001841,
+      "learning_rate": 1.4529091286973995e-05,
+      "loss": 0.6654,
+      "step": 95
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.043578368206132125,
+      "learning_rate": 1.1913638493762368e-06,
+      "loss": 0.6674,
+      "step": 100
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "eval_loss": 1.0117870569229126,
+      "eval_runtime": 125.6267,
+      "eval_samples_per_second": 20.871,
+      "eval_steps_per_second": 0.653,
+      "step": 102
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "step": 102,
+      "total_flos": 128481799176192.0,
+      "train_loss": 0.7558732021088693,
+      "train_runtime": 2589.5829,
+      "train_samples_per_second": 5.059,
+      "train_steps_per_second": 0.039
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 102,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 128481799176192.0,
+  "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:b5b552ff60fe9be12b76be82bbe1f7c0e6683b3fea9e4dda9abf21f03cc8277e
+size 6392