small configs

configs/qa_short_ctx.yaml

@@ -40,10 +40,10 @@ target_modules:
 # short ctx data
 train_ds_names:
   - fw_qa_v2_2k_len_level_3
-  - squad_compact
-  - pwc_compact
-  - drop_compact
-  - ropes_compact
+  - squad
+  - pwc
+  - drop
+  - ropes
 
 # the contexts are kinda long-ish
 # - narrativeqa

configs/qa_short_ctx_compact.yaml

@@ -0,0 +1,59 @@
+output_dir: "" # just a placeholder
+bf16: true
+model_name_or_path: google/gemma-3-1b-it
+label_names: ["labels"]
+# eval_on_start: True
+# eval_strategy: "steps"
+# eval_steps: 500
+# save_strategy: "no"
+# # save_steps: 500
+# logging_strategy: "steps"
+# logging_steps: 100
+# use_liger_kernel: true
+# remove_unused_columns: false
+
+# needed to avoid OOM by compute the metrics batch by batch
+# w/o this the trainer stores logits of all sample in memory...
+# batch_eval_metrics: true
+
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+max_val_samples_per_ds: 1000
+# optim: schedule_free_adamw
+
+learning_rate: 0.00004
+# lr_scheduler_type: "constant_with_warmup"
+neftune_noise_alpha: 1
+weight_decay: 0.01
+
+warmup_steps: 100
+
+dataloader_prefetch_factor: 16
+dataloader_num_workers: 8
+
+# LoRA
+lora_r: 8
+lora_dropout: 0.0
+target_modules:
+  - down_proj
+
+# short ctx data
+train_ds_names:
+  - fw_qa_v2_2k_len_level_3
+  - squad_compact
+  - pwc_compact
+  - drop_compact
+  - ropes_compact
+
+# the contexts are kinda long-ish
+# - narrativeqa
+# - quoref
+# - synthetic_convqa 
+
+val_ds_names:
+  - fw_qa_v2_2k_len_level_0
+  - squad
+  - drop
+  - ropes
+  - pwc
+

configs/small_exp/qa_short_ctx_lv1_small.yaml

@@ -0,0 +1,53 @@
+output_dir: "" # just a placeholder
+bf16: true
+model_name_or_path: google/gemma-3-1b-it
+label_names: ["labels"]
+# eval_on_start: True
+# eval_strategy: "steps"
+# eval_steps: 500
+# save_strategy: "no"
+# # save_steps: 500
+# logging_strategy: "steps"
+# logging_steps: 100
+# use_liger_kernel: true
+# remove_unused_columns: false
+
+# needed to avoid OOM by compute the metrics batch by batch
+# w/o this the trainer stores logits of all sample in memory...
+# batch_eval_metrics: true
+
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+max_val_samples_per_ds: 1000
+# optim: schedule_free_adamw
+
+learning_rate: 0.00004
+# lr_scheduler_type: "constant_with_warmup"
+neftune_noise_alpha: 1
+weight_decay: 0.01
+
+warmup_steps: 100
+
+dataloader_prefetch_factor: 16
+dataloader_num_workers: 8
+
+# LoRA
+lora_r: 8
+lora_dropout: 0.0
+target_modules:
+  - down_proj
+
+# data
+train_ds_names:
+  - fw_qa_v2_2k_len_level_1_small
+  - pwc_compact
+  # these provide exact tokens needed, no need to use self-gen data
+  - squad_compact
+  - ropes_compact
+  - drop_compact
+
+val_ds_names:
+  - squad
+  - pwc
+  - drop
+  - ropes

configs/small_exp/qa_short_ctx_self_gen_lv0_closed_qa_1_small.yaml

@@ -0,0 +1,53 @@
+output_dir: "" # just a placeholder
+bf16: true
+model_name_or_path: google/gemma-3-1b-it
+label_names: ["labels"]
+# eval_on_start: True
+# eval_strategy: "steps"
+# eval_steps: 500
+# save_strategy: "no"
+# # save_steps: 500
+# logging_strategy: "steps"
+# logging_steps: 100
+# use_liger_kernel: true
+# remove_unused_columns: false
+
+# needed to avoid OOM by compute the metrics batch by batch
+# w/o this the trainer stores logits of all sample in memory...
+# batch_eval_metrics: true
+
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+max_val_samples_per_ds: 1000
+# optim: schedule_free_adamw
+
+learning_rate: 0.00004
+# lr_scheduler_type: "constant_with_warmup"
+neftune_noise_alpha: 1
+weight_decay: 0.01
+
+warmup_steps: 100
+
+dataloader_prefetch_factor: 16
+dataloader_num_workers: 8
+
+# LoRA
+lora_r: 8
+lora_dropout: 0.0
+target_modules:
+  - down_proj
+
+# data
+train_ds_names:
+  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/train/*level_0.parquet
+  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
+  # these provide exact tokens needed, no need to use self-gen data
+  - squad_compact
+  - ropes_compact
+  - drop_compact
+
+val_ds_names:
+  - squad
+  - pwc
+  - drop
+  - ropes

configs/small_exp/qa_short_ctx_self_gen_lv1_closed_qa_0_small.yaml

@@ -0,0 +1,53 @@
+output_dir: "" # just a placeholder
+bf16: true
+model_name_or_path: google/gemma-3-1b-it
+label_names: ["labels"]
+# eval_on_start: True
+# eval_strategy: "steps"
+# eval_steps: 500
+# save_strategy: "no"
+# # save_steps: 500
+# logging_strategy: "steps"
+# logging_steps: 100
+# use_liger_kernel: true
+# remove_unused_columns: false
+
+# needed to avoid OOM by compute the metrics batch by batch
+# w/o this the trainer stores logits of all sample in memory...
+# batch_eval_metrics: true
+
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+max_val_samples_per_ds: 1000
+# optim: schedule_free_adamw
+
+learning_rate: 0.00004
+# lr_scheduler_type: "constant_with_warmup"
+neftune_noise_alpha: 1
+weight_decay: 0.01
+
+warmup_steps: 100
+
+dataloader_prefetch_factor: 16
+dataloader_num_workers: 8
+
+# LoRA
+lora_r: 8
+lora_dropout: 0.0
+target_modules:
+  - down_proj
+
+# data
+train_ds_names:
+  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/fw_qa_v2/min_0_to_2000/train/*level_1.parquet
+  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
+  # these provide exact tokens needed, no need to use self-gen data
+  - squad_compact
+  - ropes_compact
+  - drop_compact
+
+val_ds_names:
+  - squad
+  - pwc
+  - drop
+  - ropes

configs/small_exp/qa_short_ctx_self_gen_lv1_closed_qa_1_small.yaml

@@ -39,7 +39,7 @@ target_modules:
 
 # data
 train_ds_names:
-  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/train/*level_0.parquet
+  - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/train/*level_1.parquet
   - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
   # these provide exact tokens needed, no need to use self-gen data
   - squad_compact

configs/squad_compact.yaml

@@ -0,0 +1,45 @@
+output_dir: "" # just a placeholder
+bf16: true
+model_name_or_path: google/gemma-3-1b-it
+label_names: ["labels"]
+# eval_on_start: True
+# eval_strategy: "steps"
+# eval_steps: 500
+# save_strategy: "no"
+# # save_steps: 500
+# logging_strategy: "steps"
+# logging_steps: 100
+# use_liger_kernel: true
+# remove_unused_columns: false
+
+# needed to avoid OOM by compute the metrics batch by batch
+# w/o this the trainer stores logits of all sample in memory...
+# batch_eval_metrics: true
+
+per_device_train_batch_size: 8
+per_device_eval_batch_size: 8
+max_val_samples_per_ds: 1000
+# optim: schedule_free_adamw
+
+learning_rate: 0.00004
+# lr_scheduler_type: "constant_with_warmup"
+neftune_noise_alpha: 1
+weight_decay: 0.01
+
+warmup_steps: 100
+
+dataloader_prefetch_factor: 16
+dataloader_num_workers: 8
+
+# LoRA
+lora_r: 8
+lora_dropout: 0.0
+target_modules:
+  - down_proj
+
+# data
+train_ds_names:
+  - squad_compact
+
+val_ds_names:
+  - squad