| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9911504424778761, |
| "eval_steps": 500, |
| "global_step": 112, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04424778761061947, |
| "grad_norm": 41.036746978759766, |
| "learning_rate": 4.081632653061224e-06, |
| "loss": 1.5231, |
| "mean_token_accuracy": 0.8629005670547485, |
| "num_tokens": 532210.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08849557522123894, |
| "grad_norm": 5.500463008880615, |
| "learning_rate": 9.183673469387754e-06, |
| "loss": 0.6266, |
| "mean_token_accuracy": 0.8914964199066162, |
| "num_tokens": 1052455.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13274336283185842, |
| "grad_norm": 1.1571582555770874, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.2266, |
| "mean_token_accuracy": 0.9165656924247741, |
| "num_tokens": 1575484.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.17699115044247787, |
| "grad_norm": 1.298815131187439, |
| "learning_rate": 1.9387755102040814e-05, |
| "loss": 0.1752, |
| "mean_token_accuracy": 0.9378820061683655, |
| "num_tokens": 2105833.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.22123893805309736, |
| "grad_norm": 1.641172170639038, |
| "learning_rate": 2.4489795918367345e-05, |
| "loss": 0.1388, |
| "mean_token_accuracy": 0.950478982925415, |
| "num_tokens": 2632897.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.26548672566371684, |
| "grad_norm": 1.0823891162872314, |
| "learning_rate": 2.9591836734693876e-05, |
| "loss": 0.1067, |
| "mean_token_accuracy": 0.9630774974822998, |
| "num_tokens": 3150274.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30973451327433627, |
| "grad_norm": 0.9955891966819763, |
| "learning_rate": 3.4693877551020405e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9672421336174011, |
| "num_tokens": 3676752.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.35398230088495575, |
| "grad_norm": 0.9644169211387634, |
| "learning_rate": 3.5540851731757757e-05, |
| "loss": 0.0759, |
| "mean_token_accuracy": 0.9740681767463684, |
| "num_tokens": 4206782.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.39823008849557523, |
| "grad_norm": 1.1134227514266968, |
| "learning_rate": 3.484396753596537e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.979525363445282, |
| "num_tokens": 4728354.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.4424778761061947, |
| "grad_norm": 0.7957625985145569, |
| "learning_rate": 3.364093864567582e-05, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9777195930480957, |
| "num_tokens": 5262994.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.48672566371681414, |
| "grad_norm": 1.61801278591156, |
| "learning_rate": 3.198038991978323e-05, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9803045272827149, |
| "num_tokens": 5820035.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.5309734513274337, |
| "grad_norm": 0.7073590159416199, |
| "learning_rate": 2.992943857229226e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9762493968009949, |
| "num_tokens": 6364614.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5752212389380531, |
| "grad_norm": 0.7833342552185059, |
| "learning_rate": 2.7570981382054572e-05, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9782056093215943, |
| "num_tokens": 6884646.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.6194690265486725, |
| "grad_norm": 0.6383201479911804, |
| "learning_rate": 2.500034411307202e-05, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9836207747459411, |
| "num_tokens": 7391696.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6637168141592921, |
| "grad_norm": 0.7982662320137024, |
| "learning_rate": 2.2321428571428568e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9806379914283753, |
| "num_tokens": 7922405.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.7079646017699115, |
| "grad_norm": 0.46043986082077026, |
| "learning_rate": 1.964251302978512e-05, |
| "loss": 0.0451, |
| "mean_token_accuracy": 0.9857396006584167, |
| "num_tokens": 8458492.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7522123893805309, |
| "grad_norm": 0.47699564695358276, |
| "learning_rate": 1.7071875760802567e-05, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.984552001953125, |
| "num_tokens": 8985339.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7964601769911505, |
| "grad_norm": 0.5142015218734741, |
| "learning_rate": 1.4713418570564878e-05, |
| "loss": 0.0432, |
| "mean_token_accuracy": 0.9866464376449585, |
| "num_tokens": 9507079.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8407079646017699, |
| "grad_norm": 0.6872487664222717, |
| "learning_rate": 1.2662467223073912e-05, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.9857795715332032, |
| "num_tokens": 10043068.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8849557522123894, |
| "grad_norm": 0.4310293197631836, |
| "learning_rate": 1.1001918497181323e-05, |
| "loss": 0.0432, |
| "mean_token_accuracy": 0.9876120567321778, |
| "num_tokens": 10556108.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9292035398230089, |
| "grad_norm": 0.40992796421051025, |
| "learning_rate": 9.798889606891767e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9826365828514099, |
| "num_tokens": 11086859.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9734513274336283, |
| "grad_norm": 0.5047562122344971, |
| "learning_rate": 9.10200541109938e-06, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9831238627433777, |
| "num_tokens": 11599332.0, |
| "step": 110 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 113, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 2.760854735064924e+17, |
| "train_batch_size": 20, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
