| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07155635062611806, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035778175313059034, | |
| "grad_norm": 0.5825825929641724, | |
| "learning_rate": 0.00019928443649373882, | |
| "loss": 1.248, | |
| "num_input_tokens_seen": 6646, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007155635062611807, | |
| "grad_norm": 0.5380188822746277, | |
| "learning_rate": 0.00019856887298747765, | |
| "loss": 0.5478, | |
| "num_input_tokens_seen": 13063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01073345259391771, | |
| "grad_norm": 0.3872911036014557, | |
| "learning_rate": 0.00019785330948121648, | |
| "loss": 0.5135, | |
| "num_input_tokens_seen": 19512, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014311270125223614, | |
| "grad_norm": 0.4991438686847687, | |
| "learning_rate": 0.0001971377459749553, | |
| "loss": 0.5092, | |
| "num_input_tokens_seen": 26884, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017889087656529516, | |
| "grad_norm": 0.6744784116744995, | |
| "learning_rate": 0.0001964221824686941, | |
| "loss": 0.4799, | |
| "num_input_tokens_seen": 34831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02146690518783542, | |
| "grad_norm": 0.5413841009140015, | |
| "learning_rate": 0.00019570661896243293, | |
| "loss": 0.4738, | |
| "num_input_tokens_seen": 40074, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.025044722719141325, | |
| "grad_norm": 0.33517029881477356, | |
| "learning_rate": 0.00019499105545617174, | |
| "loss": 0.4907, | |
| "num_input_tokens_seen": 47194, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.028622540250447227, | |
| "grad_norm": 0.34275758266448975, | |
| "learning_rate": 0.00019427549194991057, | |
| "loss": 0.4642, | |
| "num_input_tokens_seen": 53439, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03220035778175313, | |
| "grad_norm": 0.4074145257472992, | |
| "learning_rate": 0.00019355992844364938, | |
| "loss": 0.4431, | |
| "num_input_tokens_seen": 59366, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03577817531305903, | |
| "grad_norm": 0.372760534286499, | |
| "learning_rate": 0.0001928443649373882, | |
| "loss": 0.4824, | |
| "num_input_tokens_seen": 66414, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03935599284436494, | |
| "grad_norm": 0.35169002413749695, | |
| "learning_rate": 0.00019212880143112702, | |
| "loss": 0.4863, | |
| "num_input_tokens_seen": 73451, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04293381037567084, | |
| "grad_norm": 0.4088020324707031, | |
| "learning_rate": 0.00019141323792486585, | |
| "loss": 0.4792, | |
| "num_input_tokens_seen": 81934, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.046511627906976744, | |
| "grad_norm": 0.40062326192855835, | |
| "learning_rate": 0.00019069767441860466, | |
| "loss": 0.4607, | |
| "num_input_tokens_seen": 88335, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05008944543828265, | |
| "grad_norm": 0.5044320225715637, | |
| "learning_rate": 0.0001899821109123435, | |
| "loss": 0.456, | |
| "num_input_tokens_seen": 96192, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05366726296958855, | |
| "grad_norm": 0.4566495418548584, | |
| "learning_rate": 0.0001892665474060823, | |
| "loss": 0.429, | |
| "num_input_tokens_seen": 101609, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.057245080500894455, | |
| "grad_norm": 0.4657338559627533, | |
| "learning_rate": 0.0001885509838998211, | |
| "loss": 0.4445, | |
| "num_input_tokens_seen": 107467, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06082289803220036, | |
| "grad_norm": 0.5721924304962158, | |
| "learning_rate": 0.00018783542039355994, | |
| "loss": 0.4304, | |
| "num_input_tokens_seen": 113612, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06440071556350627, | |
| "grad_norm": 0.2883516848087311, | |
| "learning_rate": 0.00018711985688729877, | |
| "loss": 0.4525, | |
| "num_input_tokens_seen": 121416, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06797853309481217, | |
| "grad_norm": 0.5061659216880798, | |
| "learning_rate": 0.00018640429338103758, | |
| "loss": 0.4439, | |
| "num_input_tokens_seen": 128284, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07155635062611806, | |
| "grad_norm": 0.3323754072189331, | |
| "learning_rate": 0.00018568872987477638, | |
| "loss": 0.4489, | |
| "num_input_tokens_seen": 135571, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2795, | |
| "num_input_tokens_seen": 135571, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 3048513035655168.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |