| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0457482701435352, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022874135071767598, | |
| "eval_loss": 1.1480321884155273, | |
| "eval_runtime": 105.0378, | |
| "eval_samples_per_second": 17.527, | |
| "eval_steps_per_second": 8.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00228741350717676, | |
| "grad_norm": 1.7144492864608765, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 3.3063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00457482701435352, | |
| "grad_norm": 0.5607960820198059, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.4784, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006862240521530279, | |
| "grad_norm": 0.9973358511924744, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.3966, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00914965402870704, | |
| "grad_norm": 0.5728177428245544, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.3681, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0114370675358838, | |
| "grad_norm": 0.9639943242073059, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.3547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0114370675358838, | |
| "eval_loss": 0.0816531851887703, | |
| "eval_runtime": 105.0499, | |
| "eval_samples_per_second": 17.525, | |
| "eval_steps_per_second": 8.767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013724481043060559, | |
| "grad_norm": 0.4775783121585846, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.3395, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01601189455023732, | |
| "grad_norm": 0.8813615441322327, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3269, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01829930805741408, | |
| "grad_norm": 0.8237825632095337, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.3222, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.020586721564590838, | |
| "grad_norm": 1.3891379833221436, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.2931, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0228741350717676, | |
| "grad_norm": 1.738103985786438, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.2698, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0228741350717676, | |
| "eval_loss": 0.07809711992740631, | |
| "eval_runtime": 105.0784, | |
| "eval_samples_per_second": 17.52, | |
| "eval_steps_per_second": 8.765, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02516154857894436, | |
| "grad_norm": 1.4739457368850708, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.3014, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.027448962086121118, | |
| "grad_norm": 0.8857227563858032, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.3152, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02973637559329788, | |
| "grad_norm": 0.8156161308288574, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.311, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03202378910047464, | |
| "grad_norm": 0.7602283358573914, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.2718, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0343112026076514, | |
| "grad_norm": 0.7048013210296631, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.2719, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0343112026076514, | |
| "eval_loss": 0.06394735723733902, | |
| "eval_runtime": 105.1836, | |
| "eval_samples_per_second": 17.503, | |
| "eval_steps_per_second": 8.756, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03659861611482816, | |
| "grad_norm": 0.8852552771568298, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.2929, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.038886029622004915, | |
| "grad_norm": 0.8863615989685059, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.2717, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.041173443129181676, | |
| "grad_norm": 0.7533473372459412, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.2377, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04346085663635844, | |
| "grad_norm": 0.8003175854682922, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.2844, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0457482701435352, | |
| "grad_norm": 0.7734489440917969, | |
| "learning_rate": 0.0, | |
| "loss": 0.2607, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0457482701435352, | |
| "eval_loss": 0.06249726563692093, | |
| "eval_runtime": 105.2622, | |
| "eval_samples_per_second": 17.49, | |
| "eval_steps_per_second": 8.75, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.794734731264e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |