| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.2, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.758865475654602, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 4.3569, | |
| "num_input_tokens_seen": 5888, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.4234931468963623, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 4.043, | |
| "num_input_tokens_seen": 11872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1.5642849206924438, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 3.7996, | |
| "num_input_tokens_seen": 17616, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.0812954902648926, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 3.7366, | |
| "num_input_tokens_seen": 23584, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3543965816497803, | |
| "learning_rate": 4.867325323737765e-05, | |
| "loss": 3.6712, | |
| "num_input_tokens_seen": 29600, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.436577558517456, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 3.6046, | |
| "num_input_tokens_seen": 35184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.079750657081604, | |
| "learning_rate": 4.742181853831721e-05, | |
| "loss": 3.4873, | |
| "num_input_tokens_seen": 41056, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 1.5652551651000977, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 3.3525, | |
| "num_input_tokens_seen": 47040, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 1.6999948024749756, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 3.2724, | |
| "num_input_tokens_seen": 53072, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.4872270822525024, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 3.3493, | |
| "num_input_tokens_seen": 59360, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 1.450323462486267, | |
| "learning_rate": 4.379599518697444e-05, | |
| "loss": 3.2383, | |
| "num_input_tokens_seen": 64928, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 1.70930016040802, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 3.1941, | |
| "num_input_tokens_seen": 70752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "grad_norm": 1.9510873556137085, | |
| "learning_rate": 4.148364537750172e-05, | |
| "loss": 3.1134, | |
| "num_input_tokens_seen": 76544, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 1.781402826309204, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 3.0551, | |
| "num_input_tokens_seen": 82736, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.4807748794555664, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 3.0148, | |
| "num_input_tokens_seen": 88464, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 1.936543345451355, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.9215, | |
| "num_input_tokens_seen": 94496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "grad_norm": 2.542340040206909, | |
| "learning_rate": 3.6057217255475034e-05, | |
| "loss": 2.8317, | |
| "num_input_tokens_seen": 100192, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 2.17262864112854, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 2.8665, | |
| "num_input_tokens_seen": 105904, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "grad_norm": 1.919408917427063, | |
| "learning_rate": 3.303598663257904e-05, | |
| "loss": 2.8028, | |
| "num_input_tokens_seen": 111856, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 2.5374443531036377, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 2.9059, | |
| "num_input_tokens_seen": 118064, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "grad_norm": 1.868935465812683, | |
| "learning_rate": 2.9877258050403212e-05, | |
| "loss": 2.6716, | |
| "num_input_tokens_seen": 124192, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "grad_norm": 1.9682857990264893, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 2.7336, | |
| "num_input_tokens_seen": 129856, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "grad_norm": 2.1156065464019775, | |
| "learning_rate": 2.663507823075358e-05, | |
| "loss": 2.6835, | |
| "num_input_tokens_seen": 135760, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 2.3779890537261963, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.5898, | |
| "num_input_tokens_seen": 141760, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.671842336654663, | |
| "learning_rate": 2.3364921769246423e-05, | |
| "loss": 2.5017, | |
| "num_input_tokens_seen": 147664, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "grad_norm": 2.809380292892456, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 2.4384, | |
| "num_input_tokens_seen": 153312, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "grad_norm": 3.9723222255706787, | |
| "learning_rate": 2.0122741949596797e-05, | |
| "loss": 2.5169, | |
| "num_input_tokens_seen": 159584, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 2.3110992908477783, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 2.3124, | |
| "num_input_tokens_seen": 165040, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "grad_norm": 2.2998690605163574, | |
| "learning_rate": 1.6964013367420966e-05, | |
| "loss": 2.4734, | |
| "num_input_tokens_seen": 170944, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 3.0829477310180664, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 2.3957, | |
| "num_input_tokens_seen": 177168, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "grad_norm": 2.7017433643341064, | |
| "learning_rate": 1.3942782744524973e-05, | |
| "loss": 2.5141, | |
| "num_input_tokens_seen": 183088, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "grad_norm": 3.001948118209839, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 2.2276, | |
| "num_input_tokens_seen": 188736, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "grad_norm": 3.0778212547302246, | |
| "learning_rate": 1.1110744174509952e-05, | |
| "loss": 2.1839, | |
| "num_input_tokens_seen": 194592, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "grad_norm": 3.4998250007629395, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 2.3212, | |
| "num_input_tokens_seen": 200528, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 2.9788782596588135, | |
| "learning_rate": 8.51635462249828e-06, | |
| "loss": 2.2398, | |
| "num_input_tokens_seen": 206256, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "grad_norm": 3.000025510787964, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 2.2431, | |
| "num_input_tokens_seen": 212480, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "grad_norm": 3.488719940185547, | |
| "learning_rate": 6.204004813025568e-06, | |
| "loss": 2.0743, | |
| "num_input_tokens_seen": 218208, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "grad_norm": 3.7175214290618896, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 2.1343, | |
| "num_input_tokens_seen": 223632, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "grad_norm": 3.5645270347595215, | |
| "learning_rate": 4.213259692436367e-06, | |
| "loss": 2.3751, | |
| "num_input_tokens_seen": 229776, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 3.673673629760742, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 2.0981, | |
| "num_input_tokens_seen": 235392, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "grad_norm": 3.5783541202545166, | |
| "learning_rate": 2.578181461682794e-06, | |
| "loss": 2.151, | |
| "num_input_tokens_seen": 241168, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "grad_norm": 3.5505430698394775, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 2.1801, | |
| "num_input_tokens_seen": 247200, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "grad_norm": 3.7030887603759766, | |
| "learning_rate": 1.3267467626223606e-06, | |
| "loss": 2.3428, | |
| "num_input_tokens_seen": 253536, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "grad_norm": 3.326767921447754, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 2.1907, | |
| "num_input_tokens_seen": 259568, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 3.3685076236724854, | |
| "learning_rate": 4.803679899192392e-07, | |
| "loss": 2.0246, | |
| "num_input_tokens_seen": 265056, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "grad_norm": 3.4106569290161133, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 2.1411, | |
| "num_input_tokens_seen": 271312, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "grad_norm": 3.188873529434204, | |
| "learning_rate": 5.352691903491303e-08, | |
| "loss": 2.0321, | |
| "num_input_tokens_seen": 277008, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "grad_norm": 3.023102045059204, | |
| "learning_rate": 0.0, | |
| "loss": 2.2785, | |
| "num_input_tokens_seen": 282848, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 240, | |
| "num_input_tokens_seen": 282848, | |
| "num_train_epochs": 20, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2240526315257856.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |