| { | |
| "best_metric": 0.29077759, | |
| "best_model_checkpoint": "/home/patrickbarker/output/qwen2-vl-7b-instruct/v1-20241219-214811/checkpoint-200", | |
| "epoch": 4.449438202247191, | |
| "eval_steps": 200, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.76875001, | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 29.470391176777557, | |
| "learning_rate": 0.0, | |
| "loss": 1.35673797, | |
| "memory(GiB)": 54.56, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.02296 | |
| }, | |
| { | |
| "acc": 0.77820516, | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 16.84515659540099, | |
| "learning_rate": 6.711877414712397e-06, | |
| "loss": 1.3136692, | |
| "memory(GiB)": 73.74, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.030625 | |
| }, | |
| { | |
| "acc": 0.82758846, | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 16.512337769405548, | |
| "learning_rate": 9.602525677891276e-06, | |
| "loss": 0.96648178, | |
| "memory(GiB)": 73.74, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.031938 | |
| }, | |
| { | |
| "acc": 0.83512478, | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 9.246001103598038, | |
| "learning_rate": 9.990965733615236e-06, | |
| "loss": 0.86084976, | |
| "memory(GiB)": 73.74, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.032388 | |
| }, | |
| { | |
| "acc": 0.86416492, | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 12.349159321784564, | |
| "learning_rate": 9.954319977802235e-06, | |
| "loss": 0.74885101, | |
| "memory(GiB)": 73.74, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.032624 | |
| }, | |
| { | |
| "acc": 0.86872597, | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 5.739918942992134, | |
| "learning_rate": 9.889704834236431e-06, | |
| "loss": 0.67363873, | |
| "memory(GiB)": 73.74, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.03277 | |
| }, | |
| { | |
| "acc": 0.87583218, | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 4.32721377918037, | |
| "learning_rate": 9.797485121585682e-06, | |
| "loss": 0.74702172, | |
| "memory(GiB)": 73.74, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.032865 | |
| }, | |
| { | |
| "acc": 0.9008894, | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 4.562714773064729, | |
| "learning_rate": 9.678181514584457e-06, | |
| "loss": 0.54894347, | |
| "memory(GiB)": 73.74, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.032932 | |
| }, | |
| { | |
| "acc": 0.90051165, | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 13.503139801961135, | |
| "learning_rate": 9.532467604291679e-06, | |
| "loss": 0.62093091, | |
| "memory(GiB)": 73.74, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.032984 | |
| }, | |
| { | |
| "acc": 0.8186779, | |
| "epoch": 1.0, | |
| "grad_norm": 6.94765792847355, | |
| "learning_rate": 9.397429019156841e-06, | |
| "loss": 0.47887707, | |
| "memory(GiB)": 73.74, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.03339 | |
| }, | |
| { | |
| "acc": 0.90204411, | |
| "epoch": 1.1123595505617978, | |
| "grad_norm": 5.053805856749545, | |
| "learning_rate": 9.206347037389492e-06, | |
| "loss": 0.55135803, | |
| "memory(GiB)": 73.74, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.033362 | |
| }, | |
| { | |
| "acc": 0.90205927, | |
| "epoch": 1.2247191011235956, | |
| "grad_norm": 4.031404833953091, | |
| "learning_rate": 8.991518741233478e-06, | |
| "loss": 0.53315639, | |
| "memory(GiB)": 73.74, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.033361 | |
| }, | |
| { | |
| "acc": 0.89569025, | |
| "epoch": 1.3370786516853932, | |
| "grad_norm": 4.80807450740523, | |
| "learning_rate": 8.754157056459702e-06, | |
| "loss": 0.58139644, | |
| "memory(GiB)": 73.74, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.033359 | |
| }, | |
| { | |
| "acc": 0.89294872, | |
| "epoch": 1.449438202247191, | |
| "grad_norm": 2.4132119888812698, | |
| "learning_rate": 8.495602132897754e-06, | |
| "loss": 0.59313574, | |
| "memory(GiB)": 73.74, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.033356 | |
| }, | |
| { | |
| "acc": 0.89750004, | |
| "epoch": 1.5617977528089888, | |
| "grad_norm": 3.83237148706138, | |
| "learning_rate": 8.21731377791749e-06, | |
| "loss": 0.53816686, | |
| "memory(GiB)": 73.74, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.033357 | |
| }, | |
| { | |
| "acc": 0.90059528, | |
| "epoch": 1.6741573033707864, | |
| "grad_norm": 4.066079361707885, | |
| "learning_rate": 7.920863214321187e-06, | |
| "loss": 0.54892931, | |
| "memory(GiB)": 73.74, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.033355 | |
| }, | |
| { | |
| "acc": 0.908568, | |
| "epoch": 1.7865168539325844, | |
| "grad_norm": 4.4036447401323455, | |
| "learning_rate": 7.607924209181516e-06, | |
| "loss": 0.50489616, | |
| "memory(GiB)": 73.74, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.033354 | |
| }, | |
| { | |
| "acc": 0.91108637, | |
| "epoch": 1.898876404494382, | |
| "grad_norm": 2.303374188105592, | |
| "learning_rate": 7.280263623712031e-06, | |
| "loss": 0.46924047, | |
| "memory(GiB)": 73.74, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.033354 | |
| }, | |
| { | |
| "acc": 0.81755037, | |
| "epoch": 2.0, | |
| "grad_norm": 3.6316429893731392, | |
| "learning_rate": 6.93973143752592e-06, | |
| "loss": 0.45278177, | |
| "memory(GiB)": 73.74, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.033536 | |
| }, | |
| { | |
| "acc": 0.9171875, | |
| "epoch": 2.1123595505617976, | |
| "grad_norm": 2.43556110559636, | |
| "learning_rate": 6.588250303606212e-06, | |
| "loss": 0.46200504, | |
| "memory(GiB)": 73.74, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.033514 | |
| }, | |
| { | |
| "acc": 0.91527672, | |
| "epoch": 2.2247191011235956, | |
| "grad_norm": 3.160658304441712, | |
| "learning_rate": 6.2278046929604265e-06, | |
| "loss": 0.46762981, | |
| "memory(GiB)": 73.74, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.033505 | |
| }, | |
| { | |
| "acc": 0.91525297, | |
| "epoch": 2.337078651685393, | |
| "grad_norm": 3.4672725798628012, | |
| "learning_rate": 5.860429690249112e-06, | |
| "loss": 0.46896749, | |
| "memory(GiB)": 73.74, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.033496 | |
| }, | |
| { | |
| "acc": 0.91085396, | |
| "epoch": 2.449438202247191, | |
| "grad_norm": 4.264836814343864, | |
| "learning_rate": 5.488199503648495e-06, | |
| "loss": 0.49584384, | |
| "memory(GiB)": 73.74, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.033488 | |
| }, | |
| { | |
| "acc": 0.91369057, | |
| "epoch": 2.561797752808989, | |
| "grad_norm": 1.8519201548674813, | |
| "learning_rate": 5.113215753820809e-06, | |
| "loss": 0.45219369, | |
| "memory(GiB)": 74.75, | |
| "step": 115, | |
| "train_speed(iter/s)": 0.033481 | |
| }, | |
| { | |
| "acc": 0.9125, | |
| "epoch": 2.6741573033707864, | |
| "grad_norm": 4.899506906273797, | |
| "learning_rate": 4.737595608113059e-06, | |
| "loss": 0.4595274, | |
| "memory(GiB)": 74.75, | |
| "step": 120, | |
| "train_speed(iter/s)": 0.033476 | |
| }, | |
| { | |
| "acc": 0.90626717, | |
| "epoch": 2.7865168539325844, | |
| "grad_norm": 2.3927675084287645, | |
| "learning_rate": 4.363459826978817e-06, | |
| "loss": 0.49834228, | |
| "memory(GiB)": 74.75, | |
| "step": 125, | |
| "train_speed(iter/s)": 0.033471 | |
| }, | |
| { | |
| "acc": 0.92366066, | |
| "epoch": 2.898876404494382, | |
| "grad_norm": 2.463284179520905, | |
| "learning_rate": 3.9929207901132785e-06, | |
| "loss": 0.39038134, | |
| "memory(GiB)": 74.75, | |
| "step": 130, | |
| "train_speed(iter/s)": 0.033466 | |
| }, | |
| { | |
| "acc": 0.81810102, | |
| "epoch": 3.0, | |
| "grad_norm": 2.4652024602525677, | |
| "learning_rate": 3.700486073914168e-06, | |
| "loss": 0.40796843, | |
| "memory(GiB)": 74.75, | |
| "step": 135, | |
| "train_speed(iter/s)": 0.033586 | |
| }, | |
| { | |
| "acc": 0.91892242, | |
| "epoch": 3.1123595505617976, | |
| "grad_norm": 2.7719335270024406, | |
| "learning_rate": 3.3416720076404165e-06, | |
| "loss": 0.40879712, | |
| "memory(GiB)": 74.75, | |
| "step": 140, | |
| "train_speed(iter/s)": 0.033569 | |
| }, | |
| { | |
| "acc": 0.9270833, | |
| "epoch": 3.2247191011235956, | |
| "grad_norm": 1.9611434725282086, | |
| "learning_rate": 2.99222372444748e-06, | |
| "loss": 0.41382871, | |
| "memory(GiB)": 74.75, | |
| "step": 145, | |
| "train_speed(iter/s)": 0.033562 | |
| }, | |
| { | |
| "acc": 0.92385416, | |
| "epoch": 3.337078651685393, | |
| "grad_norm": 2.8780597897464637, | |
| "learning_rate": 2.6541142178183634e-06, | |
| "loss": 0.39298267, | |
| "memory(GiB)": 74.75, | |
| "step": 150, | |
| "train_speed(iter/s)": 0.033551 | |
| }, | |
| { | |
| "acc": 0.9191987, | |
| "epoch": 3.449438202247191, | |
| "grad_norm": 3.7005032328018257, | |
| "learning_rate": 2.329252462228559e-06, | |
| "loss": 0.44139132, | |
| "memory(GiB)": 74.75, | |
| "step": 155, | |
| "train_speed(iter/s)": 0.033545 | |
| }, | |
| { | |
| "acc": 0.92789841, | |
| "epoch": 3.561797752808989, | |
| "grad_norm": 3.204039430908735, | |
| "learning_rate": 2.019472635029862e-06, | |
| "loss": 0.36037457, | |
| "memory(GiB)": 74.75, | |
| "step": 160, | |
| "train_speed(iter/s)": 0.033535 | |
| }, | |
| { | |
| "acc": 0.92560101, | |
| "epoch": 3.6741573033707864, | |
| "grad_norm": 2.2869606081065506, | |
| "learning_rate": 1.7265237606405478e-06, | |
| "loss": 0.39443879, | |
| "memory(GiB)": 74.75, | |
| "step": 165, | |
| "train_speed(iter/s)": 0.03353 | |
| }, | |
| { | |
| "acc": 0.9338542, | |
| "epoch": 3.7865168539325844, | |
| "grad_norm": 2.4065886112138943, | |
| "learning_rate": 1.4520598355110829e-06, | |
| "loss": 0.36085033, | |
| "memory(GiB)": 74.75, | |
| "step": 170, | |
| "train_speed(iter/s)": 0.033524 | |
| }, | |
| { | |
| "acc": 0.92566967, | |
| "epoch": 3.898876404494382, | |
| "grad_norm": 2.082750093607268, | |
| "learning_rate": 1.1976304896200528e-06, | |
| "loss": 0.38640497, | |
| "memory(GiB)": 74.75, | |
| "step": 175, | |
| "train_speed(iter/s)": 0.033518 | |
| }, | |
| { | |
| "acc": 0.8370594, | |
| "epoch": 4.0, | |
| "grad_norm": 2.5249629065672883, | |
| "learning_rate": 9.64672237225702e-07, | |
| "loss": 0.32685859, | |
| "memory(GiB)": 74.75, | |
| "step": 180, | |
| "train_speed(iter/s)": 0.033605 | |
| }, | |
| { | |
| "acc": 0.9390625, | |
| "epoch": 4.112359550561798, | |
| "grad_norm": 1.8419541872377712, | |
| "learning_rate": 7.545003662716096e-07, | |
| "loss": 0.32183304, | |
| "memory(GiB)": 74.75, | |
| "step": 185, | |
| "train_speed(iter/s)": 0.033592 | |
| }, | |
| { | |
| "acc": 0.93617792, | |
| "epoch": 4.224719101123595, | |
| "grad_norm": 2.5663433640548448, | |
| "learning_rate": 5.683015122390326e-07, | |
| "loss": 0.32805934, | |
| "memory(GiB)": 74.75, | |
| "step": 190, | |
| "train_speed(iter/s)": 0.033585 | |
| }, | |
| { | |
| "acc": 0.95014877, | |
| "epoch": 4.337078651685394, | |
| "grad_norm": 2.75420957077066, | |
| "learning_rate": 4.071269583742181e-07, | |
| "loss": 0.29385498, | |
| "memory(GiB)": 74.75, | |
| "step": 195, | |
| "train_speed(iter/s)": 0.033578 | |
| }, | |
| { | |
| "acc": 0.92983627, | |
| "epoch": 4.449438202247191, | |
| "grad_norm": 3.2025724539840863, | |
| "learning_rate": 2.718867001176766e-07, | |
| "loss": 0.35593481, | |
| "memory(GiB)": 74.75, | |
| "step": 200, | |
| "train_speed(iter/s)": 0.033572 | |
| }, | |
| { | |
| "epoch": 4.449438202247191, | |
| "eval_acc": 0.8987898789878987, | |
| "eval_loss": 0.2907775938510895, | |
| "eval_runtime": 23.6124, | |
| "eval_samples_per_second": 1.567, | |
| "eval_steps_per_second": 0.212, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 476842183622656.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |