| { | |
| "results": [ | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 1, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 8, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 16, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 2, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 8, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 16, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 4, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 8, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "qlora_paged_adamw8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 16, | |
| "status": "failed", | |
| "error": "element 0 of tensors does not require grad and does not have a grad_fn" | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 1, | |
| "status": "ok", | |
| "effective_global_batch_size": 1, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.12944729999981064, | |
| "images_per_sec": 7.7251514709187665, | |
| "mean_loss": 9.920842170715332, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 0.792737899999338, | |
| "images_per_sec": 10.091607831550228, | |
| "mean_loss": 8.131502032279968, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 16, | |
| "optimizer_step_time_sec": 1.6773667999987083, | |
| "images_per_sec": 9.538760395169572, | |
| "mean_loss": 8.80642619729042, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 2, | |
| "status": "ok", | |
| "effective_global_batch_size": 2, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.20009290000052715, | |
| "images_per_sec": 9.995357156574427, | |
| "mean_loss": 9.088608741760254, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 0.8304937000011705, | |
| "images_per_sec": 9.63282442719159, | |
| "mean_loss": 8.245712995529175, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 1.6668036999981268, | |
| "images_per_sec": 9.599210752902685, | |
| "mean_loss": 9.106984257698059, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 4, | |
| "status": "ok", | |
| "effective_global_batch_size": 4, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.4656030999994982, | |
| "images_per_sec": 8.591008092524106, | |
| "mean_loss": 8.862140655517578, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 2, | |
| "optimizer_step_time_sec": 2.6093234999989363, | |
| "images_per_sec": 3.0659287742601715, | |
| "mean_loss": 8.241507053375244, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "lora_adamw", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 18.058491499999946, | |
| "images_per_sec": 0.8860097755119827, | |
| "mean_loss": 8.916554927825928, | |
| "trainable_params": 1106688 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 1, | |
| "status": "ok", | |
| "effective_global_batch_size": 1, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 1.4309436000003188, | |
| "images_per_sec": 0.6988395629288094, | |
| "mean_loss": 8.042855262756348, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 2.7121656999988772, | |
| "images_per_sec": 2.9496722858796245, | |
| "mean_loss": 7.829526960849762, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 16, | |
| "optimizer_step_time_sec": 1.8378386999993381, | |
| "images_per_sec": 8.705878268863183, | |
| "mean_loss": 9.189274996519089, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 2, | |
| "status": "ok", | |
| "effective_global_batch_size": 2, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.23647629999868514, | |
| "images_per_sec": 8.457507158269646, | |
| "mean_loss": 9.128178596496582, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 0.8083188999989943, | |
| "images_per_sec": 9.897083935572896, | |
| "mean_loss": 8.64337944984436, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 1.8274533999974665, | |
| "images_per_sec": 8.755353214490823, | |
| "mean_loss": 8.331470370292664, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 4, | |
| "status": "ok", | |
| "effective_global_batch_size": 4, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.511095199999545, | |
| "images_per_sec": 7.826330593602838, | |
| "mean_loss": 8.954268455505371, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 2, | |
| "optimizer_step_time_sec": 2.2738564999981463, | |
| "images_per_sec": 3.518251921353226, | |
| "mean_loss": 9.192809581756592, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 18.631701800000883, | |
| "images_per_sec": 0.8587513997244869, | |
| "mean_loss": 8.159156560897827, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 1, | |
| "status": "ok", | |
| "effective_global_batch_size": 1, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.13992360000156623, | |
| "images_per_sec": 7.146757230294293, | |
| "mean_loss": 9.259998321533203, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 0.8451360999988538, | |
| "images_per_sec": 9.465930990299492, | |
| "mean_loss": 8.10985803604126, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 1, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 16, | |
| "optimizer_step_time_sec": 1.8945816999930685, | |
| "images_per_sec": 8.445135936897595, | |
| "mean_loss": 8.591163873672485, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 2, | |
| "status": "ok", | |
| "effective_global_batch_size": 2, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.23971350000101666, | |
| "images_per_sec": 8.343293139483249, | |
| "mean_loss": 9.75894832611084, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 0.9259438999997656, | |
| "images_per_sec": 8.6398322835779, | |
| "mean_loss": 8.462790489196777, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 2, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 8, | |
| "optimizer_step_time_sec": 1.8237968999983423, | |
| "images_per_sec": 8.772906676184471, | |
| "mean_loss": 10.191668510437012, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 4, | |
| "status": "ok", | |
| "effective_global_batch_size": 4, | |
| "gradient_accumulation_steps": 1, | |
| "optimizer_step_time_sec": 0.5224713000006886, | |
| "images_per_sec": 7.655922918626779, | |
| "mean_loss": 8.14057445526123, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 8, | |
| "status": "ok", | |
| "effective_global_batch_size": 8, | |
| "gradient_accumulation_steps": 2, | |
| "optimizer_step_time_sec": 3.7809107000011863, | |
| "images_per_sec": 2.1158923430795364, | |
| "mean_loss": 8.521550178527832, | |
| "trainable_params": 125521920 | |
| }, | |
| { | |
| "method": "full_adam8bit", | |
| "local_batch_size": 4, | |
| "global_batch_size_requested": 16, | |
| "status": "ok", | |
| "effective_global_batch_size": 16, | |
| "gradient_accumulation_steps": 4, | |
| "optimizer_step_time_sec": 27.688971800002037, | |
| "images_per_sec": 0.5778473868790903, | |
| "mean_loss": 9.247632026672363, | |
| "trainable_params": 125521920 | |
| } | |
| ] | |
| } |