| { | |
| "best_metric": 0.7721038460731506, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-3500", | |
| "epoch": 0.39401103230890466, | |
| "eval_steps": 500, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056287290329843524, | |
| "grad_norm": 150.1642303466797, | |
| "learning_rate": 4.929640887087696e-07, | |
| "loss": 0.3486, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.056287290329843524, | |
| "eval_loss": 1.1265727281570435, | |
| "eval_runtime": 123.7806, | |
| "eval_samples_per_second": 15.948, | |
| "eval_steps_per_second": 1.995, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11257458065968705, | |
| "grad_norm": 366.6913146972656, | |
| "learning_rate": 4.859281774175391e-07, | |
| "loss": 0.2733, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11257458065968705, | |
| "eval_loss": 0.9742079377174377, | |
| "eval_runtime": 125.8047, | |
| "eval_samples_per_second": 15.691, | |
| "eval_steps_per_second": 1.963, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16886187098953057, | |
| "grad_norm": 555.5016479492188, | |
| "learning_rate": 4.788922661263087e-07, | |
| "loss": 0.1851, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16886187098953057, | |
| "eval_loss": 0.9162159562110901, | |
| "eval_runtime": 126.7606, | |
| "eval_samples_per_second": 15.573, | |
| "eval_steps_per_second": 1.949, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2251491613193741, | |
| "grad_norm": 0.423260897397995, | |
| "learning_rate": 4.7185635483507824e-07, | |
| "loss": 0.1973, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2251491613193741, | |
| "eval_loss": 0.8716973662376404, | |
| "eval_runtime": 127.6955, | |
| "eval_samples_per_second": 15.459, | |
| "eval_steps_per_second": 1.934, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2814364516492176, | |
| "grad_norm": 6.840139389038086, | |
| "learning_rate": 4.6482044354384774e-07, | |
| "loss": 0.1881, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2814364516492176, | |
| "eval_loss": 0.830047070980072, | |
| "eval_runtime": 128.0771, | |
| "eval_samples_per_second": 15.413, | |
| "eval_steps_per_second": 1.929, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.33772374197906113, | |
| "grad_norm": 729.8377685546875, | |
| "learning_rate": 4.577845322526173e-07, | |
| "loss": 0.1695, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.33772374197906113, | |
| "eval_loss": 0.8265627026557922, | |
| "eval_runtime": 128.052, | |
| "eval_samples_per_second": 15.416, | |
| "eval_steps_per_second": 1.929, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.39401103230890466, | |
| "grad_norm": 7.96999938756926e-06, | |
| "learning_rate": 4.507486209613869e-07, | |
| "loss": 0.155, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.39401103230890466, | |
| "eval_loss": 0.7721038460731506, | |
| "eval_runtime": 128.1871, | |
| "eval_samples_per_second": 15.399, | |
| "eval_steps_per_second": 1.927, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 35532, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1259873746112520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |