tiny exp

configs/qa_short_ctx_self_gen_lv3_tiny_temp_1.0.yaml

@@ -1,52 +0,0 @@
-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_1.0/fw_qa_v2_2k_len_level_3_tiny
-  - self_gen/google/gemma-2-2b-it_temp_1.0/squad_compact
-  - self_gen/google/gemma-2-2b-it_temp_1.0/pwc_compact
-  - self_gen/google/gemma-2-2b-it_temp_1.0/ropes_compact
-  - self_gen/google/gemma-2-2b-it_temp_1.0/drop_compact
-
-val_ds_names:
-  - squad
-  - pwc
-  - drop
-  - ropes

configs/tiny_exp/fw_qa_v2_level_0_tiny.yaml

@@ -44,3 +44,6 @@ train_ds_names:
 val_ds_names:
   - fw_qa_v2_2k_len_level_0
   - squad
+  - drop
+  - ropes
+  - pwc

configs/tiny_exp/fw_qa_v2_level_1_tiny.yaml

@@ -39,14 +39,11 @@ target_modules:
 
 # data
 train_ds_names:
-  - self_gen/google/gemma-2-2b-it_temp_0.3/fw_qa_v2_2k_len_level_3_tiny
-  - self_gen/google/gemma-2-2b-it_temp_0.3/squad_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.3/pwc_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.3/ropes_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.3/drop_compact
+  - fw_qa_v2_2k_len_level_1_tiny
 
 val_ds_names:
+  - fw_qa_v2_2k_len_level_0
   - squad
-  - pwc
   - drop
   - ropes
+  - pwc

configs/tiny_exp/fw_qa_v2_level_2_tiny.yaml

@@ -39,14 +39,11 @@ target_modules:
 
 # data
 train_ds_names:
-  - self_gen/google/gemma-2-2b-it_temp_0.5/fw_qa_v2_2k_len_level_3_tiny
-  - self_gen/google/gemma-2-2b-it_temp_0.5/squad_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.5/pwc_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.5/ropes_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.5/drop_compact
+  - fw_qa_v2_2k_len_level_2_tiny
 
 val_ds_names:
+  - fw_qa_v2_2k_len_level_0
   - squad
-  - pwc
   - drop
   - ropes
+  - pwc

configs/tiny_exp/fw_qa_v2_level_3_tiny.yaml

@@ -44,3 +44,6 @@ train_ds_names:
 val_ds_names:
   - fw_qa_v2_2k_len_level_0
   - squad
+  - drop
+  - ropes
+  - pwc

configs/tiny_exp/qa_short_ctx_tiny.yaml

@@ -37,16 +37,23 @@ lora_dropout: 0.0
 target_modules:
   - down_proj
 
-# data
+# short ctx data
 train_ds_names:
-  - self_gen/google/gemma-2-2b-it_temp_0.7/fw_qa_v2_2k_len_level_3_tiny
-  - self_gen/google/gemma-2-2b-it_temp_0.7/squad_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.7/pwc_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.7/ropes_compact
-  - self_gen/google/gemma-2-2b-it_temp_0.7/drop_compact
+  - fw_qa_v2_2k_len_level_3_tiny
+  - 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
-  - pwc
   - drop
   - ropes
+  - pwc
+

scripts/short_ctx/gemma_qa_short_ctx_exp_concat_latent_context_attn.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+#SBATCH --job-name=ctxlora
+#SBATCH --nodes=1
+#SBATCH --partition=a3
+#SBATCH --gpus=4
+#SBATCH --output=slurm_logs/%x-%j.out
+#SBATCH --error=slurm_logs/%x-%j.out
+
+port=$((10000 + ($SLURM_JOBID % 50000)))
+echo "Using port: $port"
+
+# --gradient_accumulation_steps=8 --gradient_clipping=1.0
+uv run accelerate launch --main_process_port $port \
+--num_processes=4 --gpu_ids all intx_sft.py $1 \
+--model_name_or_path=google/gemma-2-2b-it \
+--max_steps=12_000 \
+--per_device_train_batch_size=-1 \
+--gradient_accumulation_steps=2 \
+--per_device_eval_batch_size=64 \
+--target_modules=down_proj \
+--num_self_attends_per_block=8 \
+--n_cross_attn_layers=8 \
+--concat_latents_context=True \
+--num_latent_factor=1 \
+--num_pre_head_layers=1 \
+--lora_r=8 \
+--eval_steps=1000 \
+--save_steps=1000 \
+--learning_rate=4e-5 \
+--lora_dropout=0.0 \
+--neftune_noise_alpha=5 \
+--add_negative_prompt=False \
+--add_repeat_prompt=False \
+--use_sequence_packing=True \
+--max_packed_inp_len=8192 \
+--max_packed_ctx_len=16384 \
+--per_rank_gen=True \
+--per_layer_processing=True \
+--gen_lora_l1_reg_coef=0.1 \
+--logging_steps=50

scripts/short_ctx/gemma_qa_short_ctx_exp_default.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+#SBATCH --job-name=ctxlora
+#SBATCH --nodes=1
+#SBATCH --partition=a3
+#SBATCH --gpus=4
+#SBATCH --output=slurm_logs/%x-%j.out
+#SBATCH --error=slurm_logs/%x-%j.out
+
+port=$((10000 + ($SLURM_JOBID % 50000)))
+echo "Using port: $port"
+
+# --gradient_accumulation_steps=8 --gradient_clipping=1.0
+uv run accelerate launch --main_process_port $port \
+--num_processes=4 --gpu_ids all intx_sft.py $1 \
+--model_name_or_path=google/gemma-2-2b-it \
+--max_steps=12_000 \
+--per_device_train_batch_size=-1 \
+--gradient_accumulation_steps=2 \
+--per_device_eval_batch_size=64 \
+--target_modules=down_proj \
+--num_self_attends_per_block=8 \
+--n_cross_attn_layers=8 \
+--num_latent_factor=1 \
+--num_pre_head_layers=1 \
+--lora_r=8 \
+--eval_steps=1000 \
+--save_steps=1000 \
+--learning_rate=4e-5 \
+--lora_dropout=0.0 \
+--neftune_noise_alpha=5 \
+--add_negative_prompt=False \
+--add_repeat_prompt=False \
+--use_sequence_packing=True \
+--max_packed_inp_len=8192 \
+--max_packed_ctx_len=16384 \
+--per_rank_gen=True \
+--per_layer_processing=True \
+--gen_lora_l1_reg_coef=0.1 \
+--logging_steps=50

scripts/short_ctx/gemma_qa_short_ctx_exp_self_attn.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+#SBATCH --job-name=ctxlora
+#SBATCH --nodes=1
+#SBATCH --partition=a3
+#SBATCH --gpus=4
+#SBATCH --output=slurm_logs/%x-%j.out
+#SBATCH --error=slurm_logs/%x-%j.out
+
+port=$((10000 + ($SLURM_JOBID % 50000)))
+echo "Using port: $port"
+
+# --gradient_accumulation_steps=8 --gradient_clipping=1.0
+uv run accelerate launch --main_process_port $port \
+--num_processes=4 --gpu_ids all intx_sft.py $1 \
+--model_name_or_path=google/gemma-2-2b-it \
+--max_steps=12_000 \
+--per_device_train_batch_size=-1 \
+--gradient_accumulation_steps=2 \
+--per_device_eval_batch_size=64 \
+--target_modules=down_proj \
+--num_self_attends_per_block=8 \
+--n_cross_attn_layers=1 \
+--num_latent_factor=1 \
+--num_pre_head_layers=1 \
+--lora_r=8 \
+--eval_steps=1000 \
+--save_steps=1000 \
+--learning_rate=4e-5 \
+--lora_dropout=0.0 \
+--neftune_noise_alpha=5 \
+--add_negative_prompt=False \
+--add_repeat_prompt=False \
+--use_sequence_packing=True \
+--max_packed_inp_len=8192 \
+--max_packed_ctx_len=16384 \
+--per_rank_gen=True \
+--per_layer_processing=True \
+--gen_lora_l1_reg_coef=0.1 \
+--logging_steps=50

scripts/submit_tiny_exp_jobs.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+
+# Script to submit SLURM jobs for all configs in configs/tiny_exp/
+# with random sleep intervals between submissions
+
+CONFIG_DIR="configs/tiny_exp"
+SCRIPT_PATH="scripts/short_ctx/gemma_qa_short_ctx_exp_default.sh"
+
+# Check if config directory exists
+if [ ! -d "$CONFIG_DIR" ]; then
+    echo "Error: Config directory $CONFIG_DIR does not exist"
+    exit 1
+fi
+
+# Check if script exists
+if [ ! -f "$SCRIPT_PATH" ]; then
+    echo "Error: Script $SCRIPT_PATH does not exist"
+    exit 1
+fi
+
+# Get all yaml config files
+configs=($(find "$CONFIG_DIR" -name "*.yaml" -type f))
+
+if [ ${#configs[@]} -eq 0 ]; then
+    echo "No .yaml config files found in $CONFIG_DIR"
+    exit 1
+fi
+
+echo "Found ${#configs[@]} config files:"
+for config in "${configs[@]}"; do
+    echo "  - $config"
+done
+
+echo ""
+echo "Starting job submissions..."
+
+# Submit jobs with random sleep intervals
+for config in "${configs[@]}"; do
+    echo "Submitting job for config: $config"
+    sbatch "$SCRIPT_PATH" "$config"
+
+    # Random sleep between 3-30 seconds
+    sleep_time=$((3 + RANDOM % 28))
+    echo "Waiting $sleep_time seconds before next submission..."
+    sleep $sleep_time
+done
+
+echo "All jobs submitted!"