| { | |
| "best_metric": 0.24278748, | |
| "best_model_checkpoint": "/home/patrickbarker/output/qwen2-vl-7b-instruct/v6-20241227-225441/checkpoint-110", | |
| "epoch": 5.0, | |
| "eval_steps": 200, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "acc": 0.78167927, | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 43.51957169549305, | |
| "learning_rate": 0.0, | |
| "loss": 1.52152085, | |
| "memory(GiB)": 54.58, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.023688 | |
| }, | |
| { | |
| "acc": 0.80088145, | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 16.698680203670396, | |
| "learning_rate": 8.982444017039271e-06, | |
| "loss": 1.30359197, | |
| "memory(GiB)": 73.76, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.030905 | |
| }, | |
| { | |
| "acc": 0.84716568, | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 99.91773436455576, | |
| "learning_rate": 9.963548016053221e-06, | |
| "loss": 0.91131897, | |
| "memory(GiB)": 73.76, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.032102 | |
| }, | |
| { | |
| "acc": 0.88515282, | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 24.567615978306, | |
| "learning_rate": 9.81637236983706e-06, | |
| "loss": 0.69735923, | |
| "memory(GiB)": 73.76, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.032522 | |
| }, | |
| { | |
| "acc": 0.90119629, | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 23.35765111842572, | |
| "learning_rate": 9.559543280037456e-06, | |
| "loss": 0.60645761, | |
| "memory(GiB)": 73.76, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.032734 | |
| }, | |
| { | |
| "acc": 0.91339293, | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 33.99160825767637, | |
| "learning_rate": 9.198908533295377e-06, | |
| "loss": 0.49396305, | |
| "memory(GiB)": 73.76, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.032803 | |
| }, | |
| { | |
| "acc": 0.90059528, | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 4.634151072804457, | |
| "learning_rate": 8.74267948548142e-06, | |
| "loss": 0.55382419, | |
| "memory(GiB)": 73.76, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.032901 | |
| }, | |
| { | |
| "acc": 0.91889877, | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 4.254827408045218, | |
| "learning_rate": 8.20124409589221e-06, | |
| "loss": 0.45707884, | |
| "memory(GiB)": 73.76, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.032967 | |
| }, | |
| { | |
| "acc": 0.90254698, | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 6.580539345883698, | |
| "learning_rate": 7.586930401981196e-06, | |
| "loss": 0.56463132, | |
| "memory(GiB)": 73.76, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.03302 | |
| }, | |
| { | |
| "acc": 0.89579449, | |
| "epoch": 2.0454545454545454, | |
| "grad_norm": 3.3969823419292546, | |
| "learning_rate": 6.913725820109267e-06, | |
| "loss": 0.55745425, | |
| "memory(GiB)": 73.76, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.033032 | |
| }, | |
| { | |
| "acc": 0.92141371, | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 4.84305034878261, | |
| "learning_rate": 6.196958663605647e-06, | |
| "loss": 0.41976843, | |
| "memory(GiB)": 73.76, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.033069 | |
| }, | |
| { | |
| "acc": 0.92351761, | |
| "epoch": 2.5, | |
| "grad_norm": 2.6573884384738826, | |
| "learning_rate": 5.452949129710276e-06, | |
| "loss": 0.40629215, | |
| "memory(GiB)": 73.76, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.033098 | |
| }, | |
| { | |
| "acc": 0.92366076, | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 3.036673400763093, | |
| "learning_rate": 4.698637702137281e-06, | |
| "loss": 0.3994946, | |
| "memory(GiB)": 73.76, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.033121 | |
| }, | |
| { | |
| "acc": 0.91072569, | |
| "epoch": 2.9545454545454546, | |
| "grad_norm": 3.828367565609907, | |
| "learning_rate": 3.951199430226795e-06, | |
| "loss": 0.53429661, | |
| "memory(GiB)": 73.76, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.033141 | |
| }, | |
| { | |
| "acc": 0.93214283, | |
| "epoch": 3.1818181818181817, | |
| "grad_norm": 1.8070702641555514, | |
| "learning_rate": 3.2276528672308443e-06, | |
| "loss": 0.34567313, | |
| "memory(GiB)": 73.76, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.033141 | |
| }, | |
| { | |
| "acc": 0.9265625, | |
| "epoch": 3.409090909090909, | |
| "grad_norm": 3.329828899150029, | |
| "learning_rate": 2.544472571886156e-06, | |
| "loss": 0.36765969, | |
| "memory(GiB)": 73.76, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.033157 | |
| }, | |
| { | |
| "acc": 0.9177083, | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 4.387483214871812, | |
| "learning_rate": 1.917213996293599e-06, | |
| "loss": 0.40775118, | |
| "memory(GiB)": 73.76, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.033171 | |
| }, | |
| { | |
| "acc": 0.92260418, | |
| "epoch": 3.8636363636363638, | |
| "grad_norm": 1.5187071979407496, | |
| "learning_rate": 1.360159301097995e-06, | |
| "loss": 0.39023507, | |
| "memory(GiB)": 73.76, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.033184 | |
| }, | |
| { | |
| "acc": 0.9348959, | |
| "epoch": 4.090909090909091, | |
| "grad_norm": 2.44279909593675, | |
| "learning_rate": 8.859921624646651e-07, | |
| "loss": 0.32524009, | |
| "memory(GiB)": 73.76, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.03318 | |
| }, | |
| { | |
| "acc": 0.94605656, | |
| "epoch": 4.318181818181818, | |
| "grad_norm": 2.753855151001659, | |
| "learning_rate": 5.055089752297524e-07, | |
| "loss": 0.30881886, | |
| "memory(GiB)": 73.76, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.033191 | |
| }, | |
| { | |
| "acc": 0.94285717, | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 3.100948008341975, | |
| "learning_rate": 2.2737302789052631e-07, | |
| "loss": 0.29091349, | |
| "memory(GiB)": 73.76, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.0332 | |
| }, | |
| { | |
| "acc": 0.93197918, | |
| "epoch": 4.7727272727272725, | |
| "grad_norm": 2.5192185883620883, | |
| "learning_rate": 5.791724666843258e-08, | |
| "loss": 0.33186045, | |
| "memory(GiB)": 73.76, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.033209 | |
| }, | |
| { | |
| "acc": 0.94099703, | |
| "epoch": 5.0, | |
| "grad_norm": 2.4350393332679294, | |
| "learning_rate": 1e-09, | |
| "loss": 0.3012409, | |
| "memory(GiB)": 73.76, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.033217 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_acc": 0.9153225806451613, | |
| "eval_loss": 0.24278748035430908, | |
| "eval_runtime": 14.5391, | |
| "eval_samples_per_second": 1.238, | |
| "eval_steps_per_second": 0.206, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 110, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 265979792457728.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |