| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6956521739130435, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034782608695652174, | |
| "grad_norm": 27.628698806495482, | |
| "learning_rate": 5e-07, | |
| "loss": 1.6404, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06956521739130435, | |
| "grad_norm": 14.379307335524663, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10434782608695652, | |
| "grad_norm": 7.6171415097012805, | |
| "learning_rate": 9.99648681635985e-07, | |
| "loss": 1.2858, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1391304347826087, | |
| "grad_norm": 5.902380140367801, | |
| "learning_rate": 9.985952202423114e-07, | |
| "loss": 1.2292, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 5.431235666701782, | |
| "learning_rate": 9.96841096220313e-07, | |
| "loss": 1.2035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20869565217391303, | |
| "grad_norm": 5.011022329519287, | |
| "learning_rate": 9.943887745939163e-07, | |
| "loss": 1.1615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24347826086956523, | |
| "grad_norm": 4.933604072753844, | |
| "learning_rate": 9.912417015456088e-07, | |
| "loss": 1.1627, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2782608695652174, | |
| "grad_norm": 4.904429773196176, | |
| "learning_rate": 9.874042995736093e-07, | |
| "loss": 1.1468, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3130434782608696, | |
| "grad_norm": 4.566916992899494, | |
| "learning_rate": 9.828819612770495e-07, | |
| "loss": 1.1457, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 4.618513047328418, | |
| "learning_rate": 9.77681041777897e-07, | |
| "loss": 1.1363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "eval_loss": 1.1214656829833984, | |
| "eval_runtime": 71.1557, | |
| "eval_samples_per_second": 57.423, | |
| "eval_steps_per_second": 0.899, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3826086956521739, | |
| "grad_norm": 4.482447125747761, | |
| "learning_rate": 9.718088497902707e-07, | |
| "loss": 1.1252, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.41739130434782606, | |
| "grad_norm": 4.746315495183657, | |
| "learning_rate": 9.652736373497e-07, | |
| "loss": 1.1144, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.45217391304347826, | |
| "grad_norm": 4.800644875448408, | |
| "learning_rate": 9.580845882167572e-07, | |
| "loss": 1.1048, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.48695652173913045, | |
| "grad_norm": 5.041563912063608, | |
| "learning_rate": 9.502518049713631e-07, | |
| "loss": 1.0967, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 4.834159384378619, | |
| "learning_rate": 9.417862948158997e-07, | |
| "loss": 1.0922, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5565217391304348, | |
| "grad_norm": 4.966276459660724, | |
| "learning_rate": 9.326999541070803e-07, | |
| "loss": 1.1065, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.591304347826087, | |
| "grad_norm": 4.651039844387456, | |
| "learning_rate": 9.23005551638316e-07, | |
| "loss": 1.08, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6260869565217392, | |
| "grad_norm": 4.61712494812361, | |
| "learning_rate": 9.127167106960681e-07, | |
| "loss": 1.0871, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6608695652173913, | |
| "grad_norm": 4.965649778107791, | |
| "learning_rate": 9.018478899154066e-07, | |
| "loss": 1.0791, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 4.710879346221803, | |
| "learning_rate": 8.904143629616732e-07, | |
| "loss": 1.0856, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "eval_loss": 1.074812412261963, | |
| "eval_runtime": 70.7335, | |
| "eval_samples_per_second": 57.766, | |
| "eval_steps_per_second": 0.905, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 429, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 589411381149696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |