diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..71c411a54f1c077ada48ddb10cd74f0afef6e19a --- /dev/null +++ b/README.md @@ -0,0 +1,28 @@ +--- +language: en +license: mit +tags: +- image-segmentation +- medical-imaging +- pytorch +- unet +datasets: +- Angelou0516/kvasir-seg +--- + +# FolashadeO/week4 + +This model is a compact PyTorch U-Net for binary gastrointestinal polyp +segmentation on the Kvasir-SEG dataset. + +## Architecture + +The network uses a four-level U-Net with convolutional encoder blocks, +a bottleneck, transposed-convolution decoder blocks, skip connections, +and a final `1 x 1` convolution that produces one mask logit channel. + +## Loss + +Training uses a combined Dice and binary cross-entropy loss. BCE handles +per-pixel classification, while Dice loss directly optimizes mask overlap +and helps with foreground/background class imbalance. diff --git a/checkpoint-100/model.safetensors b/checkpoint-100/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9508b831953bb87826fe40a8534d2f2468fad668 --- /dev/null +++ b/checkpoint-100/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac50980ebc8eb6587ce3dbd8fddcf798a0755a82d3fe758e0d4d734ec760c02 +size 124209532 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc20a13e0c1b7d0dbaf040e1efd6f9eb9f229159 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992d00dfd2985ef4ec37e30dba5621dd9d983fe61642987141e98292297f9011 +size 248356555 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1feba1a6538e93b94696d3773853dbc8947b0cad --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878 +size 14645 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6099d59e128e72620eec5602a062e1672b488780 --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027203cd324846f900163fad9eecbe4aeb19c35a55cd188f85a03ff3e0f62d81 +size 1465 diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d6e309e0d7b42340e1fa843c0a6151fa07d80c67 --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,72 @@ +{ + "best_global_step": 100, + "best_metric": 0.4649257596145264, + "best_model_checkpoint": "./kvasir-unet/checkpoint-100", + "epoch": 1.0, + "eval_steps": 500, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-1000/model.safetensors b/checkpoint-1000/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f168f857c0524c003b61c6551cb88b5dc77f7a28 --- /dev/null +++ b/checkpoint-1000/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959ba1e85079688a2d7023bf6d0bd785f691070058cf5559a165aa40f2ffc21f +size 124209532 diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5535dfb7f427cf863564d5eb1b1e42ba856673cc --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3875e8db516e5bb464be6740318a33c38c14c1e3a1068da4c4fe1512d9a53d +size 248356555 diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..34de6a691f00a3c99fa08329afb157f8c02fcdad --- /dev/null +++ b/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3753ab7977739b8eda494dd72defae5750f7283141b11a8f562160ba4c1a23 +size 14645 diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a725dc92f471ae1b671c72e978f917bf9e684c37 --- /dev/null +++ b/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9008af82ea2c682c9b64de9d5bd271649247b8bd3c3761983a4def45d64125f2 +size 1465 diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..799e7d2ad10969431d9b454af689a80a76a0ce8b --- /dev/null +++ b/checkpoint-1000/trainer_state.json @@ -0,0 +1,414 @@ +{ + "best_global_step": 1000, + "best_metric": 0.7648203854924553, + "best_model_checkpoint": "./kvasir-unet/checkpoint-1000", + "epoch": 10.0, + "eval_steps": 500, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + }, + { + "epoch": 5.25, + "grad_norm": 9.261576652526855, + "learning_rate": 4.76e-05, + "loss": 0.7240135955810547, + "step": 525 + }, + { + "epoch": 5.5, + "grad_norm": 3.081444501876831, + "learning_rate": 4.5100000000000005e-05, + "loss": 0.7151520538330078, + "step": 550 + }, + { + "epoch": 5.75, + "grad_norm": 4.129289150238037, + "learning_rate": 4.26e-05, + "loss": 0.6827881622314453, + "step": 575 + }, + { + "epoch": 6.0, + "grad_norm": 3.271570920944214, + "learning_rate": 4.0100000000000006e-05, + "loss": 0.6640605926513672, + "step": 600 + }, + { + "epoch": 6.0, + "eval_dice": 0.7196315708151912, + "eval_iou": 0.562050553478283, + "eval_loss": 0.7080976366996765, + "eval_runtime": 4.5035, + "eval_samples_per_second": 22.205, + "eval_steps_per_second": 2.887, + "step": 600 + }, + { + "epoch": 6.25, + "grad_norm": 3.007444143295288, + "learning_rate": 3.76e-05, + "loss": 0.6774704742431641, + "step": 625 + }, + { + "epoch": 6.5, + "grad_norm": 6.9112420082092285, + "learning_rate": 3.51e-05, + "loss": 0.6406173706054688, + "step": 650 + }, + { + "epoch": 6.75, + "grad_norm": 3.0203912258148193, + "learning_rate": 3.26e-05, + "loss": 0.6287059783935547, + "step": 675 + }, + { + "epoch": 7.0, + "grad_norm": 3.216691732406616, + "learning_rate": 3.01e-05, + "loss": 0.647440185546875, + "step": 700 + }, + { + "epoch": 7.0, + "eval_dice": 0.7246417440175368, + "eval_iou": 0.5681869886775344, + "eval_loss": 0.691881000995636, + "eval_runtime": 4.5083, + "eval_samples_per_second": 22.181, + "eval_steps_per_second": 2.884, + "step": 700 + }, + { + "epoch": 7.25, + "grad_norm": 5.566691875457764, + "learning_rate": 2.7600000000000003e-05, + "loss": 0.640998306274414, + "step": 725 + }, + { + "epoch": 7.5, + "grad_norm": 1.7265862226486206, + "learning_rate": 2.51e-05, + "loss": 0.6094163513183594, + "step": 750 + }, + { + "epoch": 7.75, + "grad_norm": 4.541012763977051, + "learning_rate": 2.26e-05, + "loss": 0.6245226287841796, + "step": 775 + }, + { + "epoch": 8.0, + "grad_norm": 3.6882596015930176, + "learning_rate": 2.01e-05, + "loss": 0.56927001953125, + "step": 800 + }, + { + "epoch": 8.0, + "eval_dice": 0.7364048604227745, + "eval_iou": 0.5827856171617375, + "eval_loss": 0.6652660965919495, + "eval_runtime": 4.5763, + "eval_samples_per_second": 21.852, + "eval_steps_per_second": 2.841, + "step": 800 + }, + { + "epoch": 8.25, + "grad_norm": 5.979460716247559, + "learning_rate": 1.76e-05, + "loss": 0.5805312347412109, + "step": 825 + }, + { + "epoch": 8.5, + "grad_norm": 5.097400188446045, + "learning_rate": 1.51e-05, + "loss": 0.5637349700927734, + "step": 850 + }, + { + "epoch": 8.75, + "grad_norm": 3.3682267665863037, + "learning_rate": 1.2600000000000001e-05, + "loss": 0.5543782806396484, + "step": 875 + }, + { + "epoch": 9.0, + "grad_norm": 4.063240051269531, + "learning_rate": 1.0100000000000002e-05, + "loss": 0.5821345520019531, + "step": 900 + }, + { + "epoch": 9.0, + "eval_dice": 0.7544327435690541, + "eval_iou": 0.6056942714502439, + "eval_loss": 0.6264443397521973, + "eval_runtime": 4.4354, + "eval_samples_per_second": 22.546, + "eval_steps_per_second": 2.931, + "step": 900 + }, + { + "epoch": 9.25, + "grad_norm": 3.4463164806365967, + "learning_rate": 7.6e-06, + "loss": 0.5670050048828125, + "step": 925 + }, + { + "epoch": 9.5, + "grad_norm": 2.3057284355163574, + "learning_rate": 5.1e-06, + "loss": 0.5416771697998047, + "step": 950 + }, + { + "epoch": 9.75, + "grad_norm": 6.042228698730469, + "learning_rate": 2.6e-06, + "loss": 0.5341218566894531, + "step": 975 + }, + { + "epoch": 10.0, + "grad_norm": 1.7755556106567383, + "learning_rate": 1.0000000000000001e-07, + "loss": 0.5268088150024414, + "step": 1000 + }, + { + "epoch": 10.0, + "eval_dice": 0.7648203854924553, + "eval_iou": 0.6191978699585076, + "eval_loss": 0.6198652386665344, + "eval_runtime": 4.5227, + "eval_samples_per_second": 22.111, + "eval_steps_per_second": 2.874, + "step": 1000 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-200/model.safetensors b/checkpoint-200/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3715c1f4ea22208cbcf7d5b770ca71ca285b6ed --- /dev/null +++ b/checkpoint-200/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44426de5d0279ae93f64c0ff08650a2dab79f3dac8a23b277c9e683ae6a05634 +size 124209532 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b465ae88812f455ed547fb07be86e7dcea15877 --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d265054cb900b7094002aeb92899b9838dccb7db97641b66e2ac6a7bbd6f83b +size 248356555 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..435e005883bf4440218c894822b086abf80abfc0 --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399 +size 14645 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4709507ec4893e038644e697bcacbae9b37f046a --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793b45e356907c0dd0ce0a30dee131ac2edb92e56cb56cf8c95af4feabe3d5a8 +size 1465 diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..832d94359be1f5cf6c3cb6f862fe8917d6503c81 --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,110 @@ +{ + "best_global_step": 200, + "best_metric": 0.5913469032255761, + "best_model_checkpoint": "./kvasir-unet/checkpoint-200", + "epoch": 2.0, + "eval_steps": 500, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-300/model.safetensors b/checkpoint-300/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db4ec0dafa5eac7fb85377cddb95b156ad9fe237 --- /dev/null +++ b/checkpoint-300/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0115699bedfbb268a96b914377542b23413a5977d1c25f052c55fc9f6c66737f +size 124209532 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..02a832d5c038cdf1c8abd22553892e5e810ecf12 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649c9d2775a7d0d739e3710b6d568cc6e32b656552e94d818f51b6b934aa518f +size 248356555 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ab68364cdd28cbfdc34c4fcc2e4416efba5ff2a --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2 +size 14645 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ed034c36ead1131ef88dbecc229fc5343329529 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd1199dc154edf23304b20c74883b404bdec174b48bea5676d181b512de88bb +size 1465 diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..785f27feb8b52e21c0a5c47783c9fce3c336f50a --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,148 @@ +{ + "best_global_step": 300, + "best_metric": 0.6287870060272235, + "best_model_checkpoint": "./kvasir-unet/checkpoint-300", + "epoch": 3.0, + "eval_steps": 500, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-400/model.safetensors b/checkpoint-400/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1dd8d488a4b1fbc210a266bdffad975285d5d2b8 --- /dev/null +++ b/checkpoint-400/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92a732c4926ab86d715918a1712320d18a352657b6891b8ea8d9a3ac6026067 +size 124209532 diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..57bbce72bafaf1d76790398cb822e913d7e0c633 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49de9e8c7f785dfde1ed38ab3878314d7b18a1a7126750df7831715888c7a0e6 +size 248356555 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fb544a66454d577cf2a3cb06c26493972f57952 --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6 +size 14645 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7eb96ff616d53980e1936c8d6299844a4889c3f --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69df656554bba9e77df00d6792762dde1865a2df0e7d1dc6df12c78c21791c28 +size 1465 diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d7288582f380219a4978cfae0b0dc38dd4dca87f --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,186 @@ +{ + "best_global_step": 400, + "best_metric": 0.6448364361669014, + "best_model_checkpoint": "./kvasir-unet/checkpoint-400", + "epoch": 4.0, + "eval_steps": 500, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-500/model.safetensors b/checkpoint-500/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8725f8b3a88e9f29a9bf6b18f0be281651eaa4ec --- /dev/null +++ b/checkpoint-500/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae0e946e16ae2aeb75d83e7bbc9701161b96f7de613caa3868a42501d6962b6 +size 124209532 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..997828cc423a6ffeb1a14ef9b5784a25d8cd3a40 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb2e2935b8a42ce6d95a401a505e2601c787fcc51a2cf1bc931f44227abc6ee +size 248356555 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cd53ddd51087a39d299073b9d407413ac1f02a5 --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3 +size 14645 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f35501b0d70e0799a5d0e98989692bd78fe6cff1 --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310b94cc33fed5e06d84d656e61170246da35f5377b1130f8d2df6d65c4047dc +size 1465 diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2f014d1500cde8296c8a0790edc11f0c3b8036b8 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,224 @@ +{ + "best_global_step": 500, + "best_metric": 0.6826710522273053, + "best_model_checkpoint": "./kvasir-unet/checkpoint-500", + "epoch": 5.0, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-600/model.safetensors b/checkpoint-600/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7f6bcbd82d0c816a614a43aa30edf617aba1af9 --- /dev/null +++ b/checkpoint-600/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169a17d2842d3d3c0f802d1829bdc26d599f19ce1692e6bf9813ae3b82137d5e +size 124209532 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3d91daf4f2eb13b7d79818c885adf24dd41cc78 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d89ac787895a35f31e00f49fbf66b6061fa48dcd8bc1dd0250d5fb9db001f6 +size 248356555 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a59c7834bf1be9f4f699331266ac781573bb8ff --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7 +size 14645 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0029d75010763eea7921cbb7b6a4a6cd5372434 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccf18be5c41ff4265589382c300ac27c252a672e83a95cf1c2983a2a0b62049 +size 1465 diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5432f775f7ee38f0b6f4028cfd1e6c7629e7c337 --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,262 @@ +{ + "best_global_step": 600, + "best_metric": 0.7196315708151912, + "best_model_checkpoint": "./kvasir-unet/checkpoint-600", + "epoch": 6.0, + "eval_steps": 500, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + }, + { + "epoch": 5.25, + "grad_norm": 9.261576652526855, + "learning_rate": 4.76e-05, + "loss": 0.7240135955810547, + "step": 525 + }, + { + "epoch": 5.5, + "grad_norm": 3.081444501876831, + "learning_rate": 4.5100000000000005e-05, + "loss": 0.7151520538330078, + "step": 550 + }, + { + "epoch": 5.75, + "grad_norm": 4.129289150238037, + "learning_rate": 4.26e-05, + "loss": 0.6827881622314453, + "step": 575 + }, + { + "epoch": 6.0, + "grad_norm": 3.271570920944214, + "learning_rate": 4.0100000000000006e-05, + "loss": 0.6640605926513672, + "step": 600 + }, + { + "epoch": 6.0, + "eval_dice": 0.7196315708151912, + "eval_iou": 0.562050553478283, + "eval_loss": 0.7080976366996765, + "eval_runtime": 4.5035, + "eval_samples_per_second": 22.205, + "eval_steps_per_second": 2.887, + "step": 600 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-700/model.safetensors b/checkpoint-700/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e339342a7a5027afa5f9a2a56959044234cee14a --- /dev/null +++ b/checkpoint-700/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e537ad3d7de71931337d69a359aa74f1fac8b7bf5452ad016686db0f6e29f5a +size 124209532 diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..826fb48217d57e670810020eb90228a9b17bfafb --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece3f70695e6ab6cc0637bd72fefc15e82a1b5e0b78917cf69b6b5efa4b00c39 +size 248356555 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..87919546610808cd2d47cb0bd2f26e5eff756dad --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ea3a198ff666cb4ace1c684b598fe43fc7c3c276b83efc553a1b787e12a304 +size 14645 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..345a7b91a30e72821211887efb996aacb6a3f0b2 --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43ff283015c76f51472644d93941dba2258d316a76706a538d778d318f06460 +size 1465 diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..7665df603642764d6602272a9f8b78ca18f022ef --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,300 @@ +{ + "best_global_step": 700, + "best_metric": 0.7246417440175368, + "best_model_checkpoint": "./kvasir-unet/checkpoint-700", + "epoch": 7.0, + "eval_steps": 500, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + }, + { + "epoch": 5.25, + "grad_norm": 9.261576652526855, + "learning_rate": 4.76e-05, + "loss": 0.7240135955810547, + "step": 525 + }, + { + "epoch": 5.5, + "grad_norm": 3.081444501876831, + "learning_rate": 4.5100000000000005e-05, + "loss": 0.7151520538330078, + "step": 550 + }, + { + "epoch": 5.75, + "grad_norm": 4.129289150238037, + "learning_rate": 4.26e-05, + "loss": 0.6827881622314453, + "step": 575 + }, + { + "epoch": 6.0, + "grad_norm": 3.271570920944214, + "learning_rate": 4.0100000000000006e-05, + "loss": 0.6640605926513672, + "step": 600 + }, + { + "epoch": 6.0, + "eval_dice": 0.7196315708151912, + "eval_iou": 0.562050553478283, + "eval_loss": 0.7080976366996765, + "eval_runtime": 4.5035, + "eval_samples_per_second": 22.205, + "eval_steps_per_second": 2.887, + "step": 600 + }, + { + "epoch": 6.25, + "grad_norm": 3.007444143295288, + "learning_rate": 3.76e-05, + "loss": 0.6774704742431641, + "step": 625 + }, + { + "epoch": 6.5, + "grad_norm": 6.9112420082092285, + "learning_rate": 3.51e-05, + "loss": 0.6406173706054688, + "step": 650 + }, + { + "epoch": 6.75, + "grad_norm": 3.0203912258148193, + "learning_rate": 3.26e-05, + "loss": 0.6287059783935547, + "step": 675 + }, + { + "epoch": 7.0, + "grad_norm": 3.216691732406616, + "learning_rate": 3.01e-05, + "loss": 0.647440185546875, + "step": 700 + }, + { + "epoch": 7.0, + "eval_dice": 0.7246417440175368, + "eval_iou": 0.5681869886775344, + "eval_loss": 0.691881000995636, + "eval_runtime": 4.5083, + "eval_samples_per_second": 22.181, + "eval_steps_per_second": 2.884, + "step": 700 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-800/model.safetensors b/checkpoint-800/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ce95cc1a5873c2723b82160bb93015f7da30385 --- /dev/null +++ b/checkpoint-800/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fcf73cb27f18b31a9ba7d20e4092a1b90723a5fa526c927770ad1f2ab5d63d +size 124209532 diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f0027cdb5c0f3b97a694f3c1b257460f12b9c6e --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb52f4016e9cce52adcf2976c1c95a806ddfe40a51d38da5e46f8b83305a44c +size 248356555 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..e400ab3c1089ab24dbd01c8748889ad29e58e374 --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f +size 14645 diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..683d3f02b067c9519f0031d52a33f0b6645fbfa2 --- /dev/null +++ b/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4698ba2898ee6ba0afd50cb75a0de71d2ea4bc6a19317aa2d8567be32e53394 +size 1465 diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..605653a6f29d6633317daae34665338d6c3cbe59 --- /dev/null +++ b/checkpoint-800/trainer_state.json @@ -0,0 +1,338 @@ +{ + "best_global_step": 800, + "best_metric": 0.7364048604227745, + "best_model_checkpoint": "./kvasir-unet/checkpoint-800", + "epoch": 8.0, + "eval_steps": 500, + "global_step": 800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + }, + { + "epoch": 5.25, + "grad_norm": 9.261576652526855, + "learning_rate": 4.76e-05, + "loss": 0.7240135955810547, + "step": 525 + }, + { + "epoch": 5.5, + "grad_norm": 3.081444501876831, + "learning_rate": 4.5100000000000005e-05, + "loss": 0.7151520538330078, + "step": 550 + }, + { + "epoch": 5.75, + "grad_norm": 4.129289150238037, + "learning_rate": 4.26e-05, + "loss": 0.6827881622314453, + "step": 575 + }, + { + "epoch": 6.0, + "grad_norm": 3.271570920944214, + "learning_rate": 4.0100000000000006e-05, + "loss": 0.6640605926513672, + "step": 600 + }, + { + "epoch": 6.0, + "eval_dice": 0.7196315708151912, + "eval_iou": 0.562050553478283, + "eval_loss": 0.7080976366996765, + "eval_runtime": 4.5035, + "eval_samples_per_second": 22.205, + "eval_steps_per_second": 2.887, + "step": 600 + }, + { + "epoch": 6.25, + "grad_norm": 3.007444143295288, + "learning_rate": 3.76e-05, + "loss": 0.6774704742431641, + "step": 625 + }, + { + "epoch": 6.5, + "grad_norm": 6.9112420082092285, + "learning_rate": 3.51e-05, + "loss": 0.6406173706054688, + "step": 650 + }, + { + "epoch": 6.75, + "grad_norm": 3.0203912258148193, + "learning_rate": 3.26e-05, + "loss": 0.6287059783935547, + "step": 675 + }, + { + "epoch": 7.0, + "grad_norm": 3.216691732406616, + "learning_rate": 3.01e-05, + "loss": 0.647440185546875, + "step": 700 + }, + { + "epoch": 7.0, + "eval_dice": 0.7246417440175368, + "eval_iou": 0.5681869886775344, + "eval_loss": 0.691881000995636, + "eval_runtime": 4.5083, + "eval_samples_per_second": 22.181, + "eval_steps_per_second": 2.884, + "step": 700 + }, + { + "epoch": 7.25, + "grad_norm": 5.566691875457764, + "learning_rate": 2.7600000000000003e-05, + "loss": 0.640998306274414, + "step": 725 + }, + { + "epoch": 7.5, + "grad_norm": 1.7265862226486206, + "learning_rate": 2.51e-05, + "loss": 0.6094163513183594, + "step": 750 + }, + { + "epoch": 7.75, + "grad_norm": 4.541012763977051, + "learning_rate": 2.26e-05, + "loss": 0.6245226287841796, + "step": 775 + }, + { + "epoch": 8.0, + "grad_norm": 3.6882596015930176, + "learning_rate": 2.01e-05, + "loss": 0.56927001953125, + "step": 800 + }, + { + "epoch": 8.0, + "eval_dice": 0.7364048604227745, + "eval_iou": 0.5827856171617375, + "eval_loss": 0.6652660965919495, + "eval_runtime": 4.5763, + "eval_samples_per_second": 21.852, + "eval_steps_per_second": 2.841, + "step": 800 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/checkpoint-900/model.safetensors b/checkpoint-900/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b7710abf0c6a300e03d9c5822d3742b8b59d530 --- /dev/null +++ b/checkpoint-900/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7129a24dcfd042eb72442a342529ea2c7dcdacb0d9ad8616df37b17a3a39c15d +size 124209532 diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..877abe34436f080e2dc6fc45c60fc26e8bbc4ef0 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1db6267a5b563b37a533d9280261d64df307c319054c677ef575881d4387443 +size 248356555 diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad450fb9f8d1ac32776c8b472f0a70f0ff38f0e8 --- /dev/null +++ b/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202 +size 14645 diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6e6401d71b38c75d83b43dcc38913e7ac238bbf --- /dev/null +++ b/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bcb5b51f31a22e3c9f83d2929f4dc0daf30e620d6ad024086b6fbd20eecdee +size 1465 diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ffe8510f734cd412eafbe687eccfcd1b7ccc413b --- /dev/null +++ b/checkpoint-900/trainer_state.json @@ -0,0 +1,376 @@ +{ + "best_global_step": 900, + "best_metric": 0.7544327435690541, + "best_model_checkpoint": "./kvasir-unet/checkpoint-900", + "epoch": 9.0, + "eval_steps": 500, + "global_step": 900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.25, + "grad_norm": 1.4807058572769165, + "learning_rate": 9.76e-05, + "loss": 1.2226847076416016, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 1.6061848402023315, + "learning_rate": 9.51e-05, + "loss": 1.1226789093017577, + "step": 50 + }, + { + "epoch": 0.75, + "grad_norm": 1.5647845268249512, + "learning_rate": 9.260000000000001e-05, + "loss": 1.0822339630126954, + "step": 75 + }, + { + "epoch": 1.0, + "grad_norm": 4.204342365264893, + "learning_rate": 9.010000000000001e-05, + "loss": 1.00395751953125, + "step": 100 + }, + { + "epoch": 1.0, + "eval_dice": 0.4649257596145264, + "eval_iou": 0.3028688409242743, + "eval_loss": 1.0397001504898071, + "eval_runtime": 4.527, + "eval_samples_per_second": 22.09, + "eval_steps_per_second": 2.872, + "step": 100 + }, + { + "epoch": 1.25, + "grad_norm": 2.125596284866333, + "learning_rate": 8.76e-05, + "loss": 0.9969179534912109, + "step": 125 + }, + { + "epoch": 1.5, + "grad_norm": 2.8102705478668213, + "learning_rate": 8.510000000000001e-05, + "loss": 0.9738675689697266, + "step": 150 + }, + { + "epoch": 1.75, + "grad_norm": 2.3319432735443115, + "learning_rate": 8.26e-05, + "loss": 0.9797834777832031, + "step": 175 + }, + { + "epoch": 2.0, + "grad_norm": 3.546826124191284, + "learning_rate": 8.010000000000001e-05, + "loss": 0.936845932006836, + "step": 200 + }, + { + "epoch": 2.0, + "eval_dice": 0.5913469032255761, + "eval_iou": 0.41979614051111847, + "eval_loss": 0.9874243140220642, + "eval_runtime": 4.4621, + "eval_samples_per_second": 22.411, + "eval_steps_per_second": 2.913, + "step": 200 + }, + { + "epoch": 2.25, + "grad_norm": 4.708238124847412, + "learning_rate": 7.76e-05, + "loss": 0.9107416534423828, + "step": 225 + }, + { + "epoch": 2.5, + "grad_norm": 1.9260565042495728, + "learning_rate": 7.510000000000001e-05, + "loss": 0.9003370666503906, + "step": 250 + }, + { + "epoch": 2.75, + "grad_norm": 2.7347285747528076, + "learning_rate": 7.26e-05, + "loss": 0.8682646942138672, + "step": 275 + }, + { + "epoch": 3.0, + "grad_norm": 1.9796888828277588, + "learning_rate": 7.01e-05, + "loss": 0.8491334533691406, + "step": 300 + }, + { + "epoch": 3.0, + "eval_dice": 0.6287870060272235, + "eval_iou": 0.45856278594402466, + "eval_loss": 0.880113422870636, + "eval_runtime": 4.6294, + "eval_samples_per_second": 21.601, + "eval_steps_per_second": 2.808, + "step": 300 + }, + { + "epoch": 3.25, + "grad_norm": 4.970420837402344, + "learning_rate": 6.76e-05, + "loss": 0.8522591400146484, + "step": 325 + }, + { + "epoch": 3.5, + "grad_norm": 2.374986171722412, + "learning_rate": 6.510000000000001e-05, + "loss": 0.7948677825927735, + "step": 350 + }, + { + "epoch": 3.75, + "grad_norm": 5.10560417175293, + "learning_rate": 6.26e-05, + "loss": 0.8352813720703125, + "step": 375 + }, + { + "epoch": 4.0, + "grad_norm": 4.5725274085998535, + "learning_rate": 6.0100000000000004e-05, + "loss": 0.7697490692138672, + "step": 400 + }, + { + "epoch": 4.0, + "eval_dice": 0.6448364361669014, + "eval_iou": 0.4758367704940324, + "eval_loss": 0.8459730744361877, + "eval_runtime": 4.4418, + "eval_samples_per_second": 22.514, + "eval_steps_per_second": 2.927, + "step": 400 + }, + { + "epoch": 4.25, + "grad_norm": 7.802286148071289, + "learning_rate": 5.76e-05, + "loss": 0.7570986175537109, + "step": 425 + }, + { + "epoch": 4.5, + "grad_norm": 7.580319881439209, + "learning_rate": 5.5100000000000004e-05, + "loss": 0.763985366821289, + "step": 450 + }, + { + "epoch": 4.75, + "grad_norm": 3.051490068435669, + "learning_rate": 5.2600000000000005e-05, + "loss": 0.7334027862548829, + "step": 475 + }, + { + "epoch": 5.0, + "grad_norm": 3.4101736545562744, + "learning_rate": 5.0100000000000005e-05, + "loss": 0.7454586791992187, + "step": 500 + }, + { + "epoch": 5.0, + "eval_dice": 0.6826710522273053, + "eval_iou": 0.51822387496614, + "eval_loss": 0.7638939619064331, + "eval_runtime": 4.4461, + "eval_samples_per_second": 22.491, + "eval_steps_per_second": 2.924, + "step": 500 + }, + { + "epoch": 5.25, + "grad_norm": 9.261576652526855, + "learning_rate": 4.76e-05, + "loss": 0.7240135955810547, + "step": 525 + }, + { + "epoch": 5.5, + "grad_norm": 3.081444501876831, + "learning_rate": 4.5100000000000005e-05, + "loss": 0.7151520538330078, + "step": 550 + }, + { + "epoch": 5.75, + "grad_norm": 4.129289150238037, + "learning_rate": 4.26e-05, + "loss": 0.6827881622314453, + "step": 575 + }, + { + "epoch": 6.0, + "grad_norm": 3.271570920944214, + "learning_rate": 4.0100000000000006e-05, + "loss": 0.6640605926513672, + "step": 600 + }, + { + "epoch": 6.0, + "eval_dice": 0.7196315708151912, + "eval_iou": 0.562050553478283, + "eval_loss": 0.7080976366996765, + "eval_runtime": 4.5035, + "eval_samples_per_second": 22.205, + "eval_steps_per_second": 2.887, + "step": 600 + }, + { + "epoch": 6.25, + "grad_norm": 3.007444143295288, + "learning_rate": 3.76e-05, + "loss": 0.6774704742431641, + "step": 625 + }, + { + "epoch": 6.5, + "grad_norm": 6.9112420082092285, + "learning_rate": 3.51e-05, + "loss": 0.6406173706054688, + "step": 650 + }, + { + "epoch": 6.75, + "grad_norm": 3.0203912258148193, + "learning_rate": 3.26e-05, + "loss": 0.6287059783935547, + "step": 675 + }, + { + "epoch": 7.0, + "grad_norm": 3.216691732406616, + "learning_rate": 3.01e-05, + "loss": 0.647440185546875, + "step": 700 + }, + { + "epoch": 7.0, + "eval_dice": 0.7246417440175368, + "eval_iou": 0.5681869886775344, + "eval_loss": 0.691881000995636, + "eval_runtime": 4.5083, + "eval_samples_per_second": 22.181, + "eval_steps_per_second": 2.884, + "step": 700 + }, + { + "epoch": 7.25, + "grad_norm": 5.566691875457764, + "learning_rate": 2.7600000000000003e-05, + "loss": 0.640998306274414, + "step": 725 + }, + { + "epoch": 7.5, + "grad_norm": 1.7265862226486206, + "learning_rate": 2.51e-05, + "loss": 0.6094163513183594, + "step": 750 + }, + { + "epoch": 7.75, + "grad_norm": 4.541012763977051, + "learning_rate": 2.26e-05, + "loss": 0.6245226287841796, + "step": 775 + }, + { + "epoch": 8.0, + "grad_norm": 3.6882596015930176, + "learning_rate": 2.01e-05, + "loss": 0.56927001953125, + "step": 800 + }, + { + "epoch": 8.0, + "eval_dice": 0.7364048604227745, + "eval_iou": 0.5827856171617375, + "eval_loss": 0.6652660965919495, + "eval_runtime": 4.5763, + "eval_samples_per_second": 21.852, + "eval_steps_per_second": 2.841, + "step": 800 + }, + { + "epoch": 8.25, + "grad_norm": 5.979460716247559, + "learning_rate": 1.76e-05, + "loss": 0.5805312347412109, + "step": 825 + }, + { + "epoch": 8.5, + "grad_norm": 5.097400188446045, + "learning_rate": 1.51e-05, + "loss": 0.5637349700927734, + "step": 850 + }, + { + "epoch": 8.75, + "grad_norm": 3.3682267665863037, + "learning_rate": 1.2600000000000001e-05, + "loss": 0.5543782806396484, + "step": 875 + }, + { + "epoch": 9.0, + "grad_norm": 4.063240051269531, + "learning_rate": 1.0100000000000002e-05, + "loss": 0.5821345520019531, + "step": 900 + }, + { + "epoch": 9.0, + "eval_dice": 0.7544327435690541, + "eval_iou": 0.6056942714502439, + "eval_loss": 0.6264443397521973, + "eval_runtime": 4.4354, + "eval_samples_per_second": 22.546, + "eval_steps_per_second": 2.931, + "step": 900 + } + ], + "logging_steps": 25, + "max_steps": 1000, + "num_input_tokens_seen": 0, + "num_train_epochs": 10, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cc0c254df18d61bf5ea485c97bdc151521127f4 --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04792f1700f54edbe0f85471cd1c5824c640ef6ced03e54f94ffcf8b7d12faea +size 5201 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..850bdab1c8768561cf9c81d6402f27a7c61bba84 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb88cdaace780ff10930235b1e9bae449394c2a83abd27f6dca078592b29276 +size 124209500