Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM-360M-Instruct",
+  "_name_or_path": "HuggingFaceTB/SmolLM-1.7B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -8,15 +8,15 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 960,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 2560,
+  "intermediate_size": 8192,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 15,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 5,
+  "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,

logs/training_args.json

@@ -1 +1 @@
-{"output_dir": "SmolLM-1.7B-Instruct-dpo-16k", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "eval_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 2, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 2, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 5e-06, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 6, "max_steps": -1, "lr_scheduler_type": "cosine", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 2, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "SmolLM-1.7B-Instruct-dpo-16k/runs/Sep11_18-20-21_ip-172-16-34-142.eu-west-1.compute.internal", "logging_strategy": "epoch", "logging_first_step": false, "logging_steps": 1, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "SmolLM-1.7B-Instruct-dpo-16k", "disable_tqdm": false, "remove_unused_columns": false, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": {"split_batches": false, "dispatch_batches": null, "even_batches": true, "use_seedable_sampler": true, "non_blocking": false, "gradient_accumulation_kwargs": null}, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "paged_adamw_32bit", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": {"use_reentrant": false}, "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": null, "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false}
+{"output_dir": "SmolLM-1.7B-Instruct-dpo-16k", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "eval_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 2, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 2, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 5e-06, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 10, "max_steps": -1, "lr_scheduler_type": "cosine", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 2, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "SmolLM-1.7B-Instruct-dpo-16k/runs/Sep16_04-20-31_ip-172-16-3-91.eu-west-1.compute.internal", "logging_strategy": "epoch", "logging_first_step": false, "logging_steps": 1, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "SmolLM-1.7B-Instruct-dpo-16k", "disable_tqdm": false, "remove_unused_columns": false, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": {"split_batches": false, "dispatch_batches": null, "even_batches": true, "use_seedable_sampler": true, "non_blocking": false, "gradient_accumulation_kwargs": null}, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "paged_adamw_32bit", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": true, "resume_from_checkpoint": null, "hub_model_id": "SmolLM-1.7B-Instruct-dpo-16k", "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": {"use_reentrant": false}, "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": null, "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false}

logs/training_data/state.json

@@ -4,7 +4,7 @@
       "filename": "data-00000-of-00001.arrow"
     }
   ],
-  "_fingerprint": "85df5ed416154a2b",
+  "_fingerprint": "7b84e812a83cc6f8",
   "_format_columns": null,
   "_format_kwargs": {},
   "_format_type": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd3c7acfde1f18af359c176a123809fe6124e0313e214c36c0397113fd79020
-size 723674912
+oid sha256:dbc6f34432664050f6b77083b91afeaedb4f0b7983754b84a554eceac942db05
+size 3422777952

runs/Sep16_04-20-31_ip-172-16-3-91.eu-west-1.compute.internal/events.out.tfevents.1726460500.ip-172-16-3-91.eu-west-1.compute.internal.47601.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af683a6c83d3872ea0a0b03aff572a8ffec4e55f49ad8c899d8c46752c24db1
+size 6446

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e034f3d169289747604bc1a47201558a91e32774131b383183b3a7b077a229d2
+oid sha256:dcaaed1508e09214e500abf9bbf838c831d7cbf0c99a3fe1463d12f0ec986efa
 size 5176