| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 42, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 5.127803325653076, |
| "learning_rate": 1e-05, |
| "loss": 1.4306640625, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 3.6908929347991943, |
| "learning_rate": 9.986018985905901e-06, |
| "loss": 1.17626953125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 3.3771724700927734, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 1.1640625, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.9032037258148193, |
| "learning_rate": 9.874639560909118e-06, |
| "loss": 0.972900390625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 1.0897910594940186, |
| "learning_rate": 9.777864028930705e-06, |
| "loss": 0.787841796875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.8675116300582886, |
| "learning_rate": 9.654368743221022e-06, |
| "loss": 0.7349853515625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.812888503074646, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 0.74072265625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.6985803246498108, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 0.7099609375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.615455687046051, |
| "learning_rate": 9.131193871579975e-06, |
| "loss": 0.68475341796875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.3938266336917877, |
| "learning_rate": 8.90915741234015e-06, |
| "loss": 0.607421875, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 0.3581027388572693, |
| "learning_rate": 8.665259359149132e-06, |
| "loss": 0.6424560546875, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.3398467004299164, |
| "learning_rate": 8.400863688854598e-06, |
| "loss": 0.526123046875, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.3203947842121124, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 0.6064453125, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.25640663504600525, |
| "learning_rate": 7.81660029031811e-06, |
| "loss": 0.55712890625, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.2466166913509369, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.561767578125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.2087976634502411, |
| "learning_rate": 7.169418695587791e-06, |
| "loss": 0.585205078125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 0.1981160044670105, |
| "learning_rate": 6.8267051218319766e-06, |
| "loss": 0.5845947265625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.23099476099014282, |
| "learning_rate": 6.473775872054522e-06, |
| "loss": 0.55615234375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 0.1761576235294342, |
| "learning_rate": 6.112604669781572e-06, |
| "loss": 0.5364990234375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.13233958184719086, |
| "learning_rate": 5.745211330880872e-06, |
| "loss": 0.53143310546875, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.1458617001771927, |
| "learning_rate": 5.373650467932122e-06, |
| "loss": 0.55023193359375, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0476190476190477, |
| "grad_norm": 0.14638561010360718, |
| "learning_rate": 5e-06, |
| "loss": 0.5335693359375, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0952380952380953, |
| "grad_norm": 0.12037061154842377, |
| "learning_rate": 4.626349532067879e-06, |
| "loss": 0.5196533203125, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 0.1666404753923416, |
| "learning_rate": 4.254788669119127e-06, |
| "loss": 0.504150390625, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.1904761904761905, |
| "grad_norm": 0.13170073926448822, |
| "learning_rate": 3.887395330218429e-06, |
| "loss": 0.5443115234375, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.2380952380952381, |
| "grad_norm": 0.10464588552713394, |
| "learning_rate": 3.526224127945479e-06, |
| "loss": 0.5283203125, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.2857142857142856, |
| "grad_norm": 0.1039387509226799, |
| "learning_rate": 3.173294878168025e-06, |
| "loss": 0.51904296875, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.11678706109523773, |
| "learning_rate": 2.83058130441221e-06, |
| "loss": 0.5396728515625, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.380952380952381, |
| "grad_norm": 0.11786361038684845, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.546142578125, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.12542256712913513, |
| "learning_rate": 2.1833997096818897e-06, |
| "loss": 0.547821044921875, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4761904761904763, |
| "grad_norm": 0.09986096620559692, |
| "learning_rate": 1.8825509907063328e-06, |
| "loss": 0.5177001953125, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.5238095238095237, |
| "grad_norm": 0.10526420921087265, |
| "learning_rate": 1.5991363111454023e-06, |
| "loss": 0.5609130859375, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.10897090286016464, |
| "learning_rate": 1.3347406408508695e-06, |
| "loss": 0.46478271484375, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.619047619047619, |
| "grad_norm": 0.12242302298545837, |
| "learning_rate": 1.0908425876598512e-06, |
| "loss": 0.5355224609375, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 0.1036498174071312, |
| "learning_rate": 8.688061284200266e-07, |
| "loss": 0.50653076171875, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 0.12078234553337097, |
| "learning_rate": 6.698729810778065e-07, |
| "loss": 0.51123046875, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.7619047619047619, |
| "grad_norm": 0.10183688998222351, |
| "learning_rate": 4.951556604879049e-07, |
| "loss": 0.547119140625, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.8095238095238095, |
| "grad_norm": 0.10784828662872314, |
| "learning_rate": 3.4563125677897936e-07, |
| "loss": 0.5501708984375, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.8571428571428572, |
| "grad_norm": 0.13649021089076996, |
| "learning_rate": 2.2213597106929608e-07, |
| "loss": 0.5185546875, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 0.1147688627243042, |
| "learning_rate": 1.253604390908819e-07, |
| "loss": 0.5076904296875, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.9523809523809523, |
| "grad_norm": 0.09135836362838745, |
| "learning_rate": 5.584586887435739e-08, |
| "loss": 0.51202392578125, |
| "step": 41 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.11010171473026276, |
| "learning_rate": 1.3981014094099354e-08, |
| "loss": 0.52972412109375, |
| "step": 42 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.515625, |
| "eval_runtime": 10.8414, |
| "eval_samples_per_second": 0.092, |
| "eval_steps_per_second": 0.092, |
| "step": 42 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 42, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.05301937307648e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
