| { | |
| "best_metric": 1.7821800708770752, | |
| "best_model_checkpoint": "$../logs/03-08-2024T09-56-31-detailclip-b32/checkpoint-116", | |
| "epoch": 1.008695652173913, | |
| "eval_steps": 58, | |
| "global_step": 116, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05217391304347826, | |
| "grad_norm": 3.0711264610290527, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.8067, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10434782608695652, | |
| "grad_norm": 3.019757032394409, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.8037, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1565217391304348, | |
| "grad_norm": 3.080796003341675, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.835, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20869565217391303, | |
| "grad_norm": 2.9880104064941406, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.6869, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 2.5763087272644043, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5712, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3130434782608696, | |
| "grad_norm": 2.295846462249756, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.5537, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3652173913043478, | |
| "grad_norm": 2.2098076343536377, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.481, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.41739130434782606, | |
| "grad_norm": 1.7029411792755127, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.3933, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.46956521739130436, | |
| "grad_norm": 2.0247466564178467, | |
| "learning_rate": 9.999673735634258e-05, | |
| "loss": 0.3398, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5043478260869565, | |
| "eval_loss": 1.8895907402038574, | |
| "eval_runtime": 362.9542, | |
| "eval_samples_per_second": 6.155, | |
| "eval_steps_per_second": 0.05, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5043478260869565, | |
| "neg_increments": 0.3482297461360652, | |
| "positive_increments": 0.5847584809616501, | |
| "rate_increments": 0.6160316723977289, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 1.6125733852386475, | |
| "learning_rate": 9.997960964140947e-05, | |
| "loss": 0.3224, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5739130434782609, | |
| "grad_norm": 1.9766706228256226, | |
| "learning_rate": 9.994780621691156e-05, | |
| "loss": 0.2817, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6260869565217392, | |
| "grad_norm": 1.4810394048690796, | |
| "learning_rate": 9.990133642141359e-05, | |
| "loss": 0.2746, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6782608695652174, | |
| "grad_norm": 1.8605773448944092, | |
| "learning_rate": 9.984021390002458e-05, | |
| "loss": 0.2948, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7304347826086957, | |
| "grad_norm": 1.2394453287124634, | |
| "learning_rate": 9.976445660039118e-05, | |
| "loss": 0.2688, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 1.2431163787841797, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.2639, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8347826086956521, | |
| "grad_norm": 1.2484493255615234, | |
| "learning_rate": 9.956913093678348e-05, | |
| "loss": 0.2358, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8869565217391304, | |
| "grad_norm": 1.6284162998199463, | |
| "learning_rate": 9.944961992705288e-05, | |
| "loss": 0.2598, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9391304347826087, | |
| "grad_norm": 1.6559319496154785, | |
| "learning_rate": 9.931558883072403e-05, | |
| "loss": 0.2436, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.991304347826087, | |
| "grad_norm": 1.544296383857727, | |
| "learning_rate": 9.916707700387547e-05, | |
| "loss": 0.2499, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.008695652173913, | |
| "eval_loss": 1.7821800708770752, | |
| "eval_runtime": 369.7296, | |
| "eval_samples_per_second": 6.042, | |
| "eval_steps_per_second": 0.049, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.008695652173913, | |
| "neg_increments": 0.3239222537704994, | |
| "positive_increments": 0.5982375050866754, | |
| "rate_increments": 0.6459971370030191, | |
| "step": 116 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 1150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 58, | |
| "total_flos": 2623924029399750.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |