| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027785495971103084, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001389274798555154, | |
| "eval_loss": 1.2610814571380615, | |
| "eval_runtime": 325.7958, | |
| "eval_samples_per_second": 9.303, | |
| "eval_steps_per_second": 4.653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013892747985551543, | |
| "grad_norm": 0.6781970262527466, | |
| "learning_rate": 0.0002, | |
| "loss": 4.983, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "grad_norm": 1.115883231163025, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 3.8894, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004167824395665463, | |
| "grad_norm": 0.9536935687065125, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 4.4272, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005557099194220617, | |
| "grad_norm": 1.504563570022583, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 3.8803, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "grad_norm": 1.1199132204055786, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 3.8496, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "eval_loss": 0.970268726348877, | |
| "eval_runtime": 325.7662, | |
| "eval_samples_per_second": 9.304, | |
| "eval_steps_per_second": 4.654, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008335648791330925, | |
| "grad_norm": 0.7853994965553284, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 3.9289, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009724923589886079, | |
| "grad_norm": 0.8920758366584778, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 3.7074, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.011114198388441235, | |
| "grad_norm": 1.726579189300537, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 3.8804, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.012503473186996388, | |
| "grad_norm": 0.8373720645904541, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 3.6611, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013892747985551542, | |
| "grad_norm": 1.302909255027771, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 3.6366, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013892747985551542, | |
| "eval_loss": 0.9369964003562927, | |
| "eval_runtime": 325.7277, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015282022784106696, | |
| "grad_norm": 1.1293046474456787, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 4.0177, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01667129758266185, | |
| "grad_norm": 1.976135492324829, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 3.7385, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.018060572381217006, | |
| "grad_norm": 1.222383737564087, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 4.002, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.019449847179772158, | |
| "grad_norm": 2.155904531478882, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 4.1537, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.020839121978327314, | |
| "grad_norm": 1.9505951404571533, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 3.6917, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.020839121978327314, | |
| "eval_loss": 0.9221398234367371, | |
| "eval_runtime": 325.7452, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.654, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02222839677688247, | |
| "grad_norm": 1.581220269203186, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 3.4549, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02361767157543762, | |
| "grad_norm": 1.595863699913025, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 3.7633, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.025006946373992776, | |
| "grad_norm": 1.4789327383041382, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 3.6302, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02639622117254793, | |
| "grad_norm": 1.2791557312011719, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 3.3965, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.027785495971103084, | |
| "grad_norm": 1.3027524948120117, | |
| "learning_rate": 0.0, | |
| "loss": 3.4079, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.027785495971103084, | |
| "eval_loss": 0.9190078377723694, | |
| "eval_runtime": 325.7439, | |
| "eval_samples_per_second": 9.305, | |
| "eval_steps_per_second": 4.654, | |
| "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": 1.2142470211043328e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |