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-long-align-v2
+  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/zmq3qzqx)
+# smollm-1.7B-16k-instruct-long-align-v2
+
+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: 1.0899
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9527        | 0.9898 | 73   | 1.0899          |
+
+
+### 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": 0.9898305084745763,
+    "total_flos": 91862908010496.0,
+    "train_loss": 1.0252333144619041,
+    "train_runtime": 1907.7952,
+    "train_samples": 189674,
+    "train_samples_per_second": 4.937,
+    "train_steps_per_second": 0.038
+}

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:bf697c02812e9692caed25d73b7d58652792669b323313a76261f8c990d6186d
+size 3422777952

runs/Sep20_14-52-47_ip-26-0-166-36/events.out.tfevents.1726844521.ip-26-0-166-36.350923.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a61741b13adbad56e421c929ef06d468ecc9e1c8d158fe6d6dfc58ca25f688
+size 8837

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": 0.9898305084745763,
+    "total_flos": 91862908010496.0,
+    "train_loss": 1.0252333144619041,
+    "train_runtime": 1907.7952,
+    "train_samples": 189674,
+    "train_samples_per_second": 4.937,
+    "train_steps_per_second": 0.038
+}

trainer_state.json

@@ -0,0 +1,155 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9898305084745763,
+  "eval_steps": 500,
+  "global_step": 73,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013559322033898305,
+      "grad_norm": 5.050205082877998,
+      "learning_rate": 0.000125,
+      "loss": 1.2623,
+      "step": 1
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 2.9389613294125154,
+      "learning_rate": 0.000625,
+      "loss": 1.2343,
+      "step": 5
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 2.7719726396922333,
+      "learning_rate": 0.0009976658173588243,
+      "loss": 1.2732,
+      "step": 10
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 0.5763036252280294,
+      "learning_rate": 0.0009716559066288715,
+      "loss": 1.1358,
+      "step": 15
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.24783483942004164,
+      "learning_rate": 0.0009182350690051134,
+      "loss": 1.0897,
+      "step": 20
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.13051456050984434,
+      "learning_rate": 0.0008405079293933986,
+      "loss": 1.0148,
+      "step": 25
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 0.16709779185955242,
+      "learning_rate": 0.000742991706621303,
+      "loss": 1.0134,
+      "step": 30
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 0.09299287343519272,
+      "learning_rate": 0.0006313536890992934,
+      "loss": 1.0077,
+      "step": 35
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.08379356751538114,
+      "learning_rate": 0.0005120818726180662,
+      "loss": 0.9777,
+      "step": 40
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 0.06580795358809759,
+      "learning_rate": 0.000392107901616097,
+      "loss": 0.9547,
+      "step": 45
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 0.076526418601839,
+      "learning_rate": 0.0002784042272003794,
+      "loss": 0.9417,
+      "step": 50
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 0.08072786402812815,
+      "learning_rate": 0.00017757889363191482,
+      "loss": 0.9267,
+      "step": 55
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 0.08008172204396788,
+      "learning_rate": 9.549150281252633e-05,
+      "loss": 0.9646,
+      "step": 60
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 0.049972195778438866,
+      "learning_rate": 3.691267552111183e-05,
+      "loss": 0.9495,
+      "step": 65
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 0.05054132063952455,
+      "learning_rate": 5.2468002744744395e-06,
+      "loss": 0.9527,
+      "step": 70
+    },
+    {
+      "epoch": 0.9898305084745763,
+      "eval_loss": 1.0899375677108765,
+      "eval_runtime": 139.4951,
+      "eval_samples_per_second": 20.775,
+      "eval_steps_per_second": 0.652,
+      "step": 73
+    },
+    {
+      "epoch": 0.9898305084745763,
+      "step": 73,
+      "total_flos": 91862908010496.0,
+      "train_loss": 1.0252333144619041,
+      "train_runtime": 1907.7952,
+      "train_samples_per_second": 4.937,
+      "train_steps_per_second": 0.038
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 73,
+  "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": 91862908010496.0,
+  "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:e05a9fd8d1c579cec81a9779f14a5cc01bd735e63b43be45a12d10c4f55c1643
+size 6456