| { | |
| "best_metric": 6.902400493621826, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.3529411764705883, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.047058823529411764, | |
| "grad_norm": 0.21490462124347687, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.047058823529411764, | |
| "eval_loss": 6.933736801147461, | |
| "eval_runtime": 0.1116, | |
| "eval_samples_per_second": 1290.552, | |
| "eval_steps_per_second": 161.319, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.2278861701488495, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9345, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": 0.21454234421253204, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.9338, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.24708101153373718, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9328, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.26814326643943787, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.9285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.20831820368766785, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.9317, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": 0.19838033616542816, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.9273, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.22706419229507446, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9266, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": 0.23207911849021912, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.9243, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.24437905848026276, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": 0.22346548736095428, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.9228, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.19627627730369568, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.9242, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": 0.21977098286151886, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.9212, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.24102850258350372, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9168, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.22972021996974945, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.9181, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.24149388074874878, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.9126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.18781936168670654, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.9225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.21479131281375885, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.9173, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": 0.23731189966201782, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.9134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.252737432718277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9082, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": 0.27014854550361633, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.9039, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": 0.3988640606403351, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 12.1942, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0823529411764705, | |
| "grad_norm": 0.22761882841587067, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.7921, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": 0.22885727882385254, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.9676, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.26605308055877686, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.7366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "eval_loss": 6.909616947174072, | |
| "eval_runtime": 0.1141, | |
| "eval_samples_per_second": 1262.017, | |
| "eval_steps_per_second": 157.752, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": 0.2847910225391388, | |
| "learning_rate": 5e-05, | |
| "loss": 7.1571, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2705882352941176, | |
| "grad_norm": 0.26297202706336975, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.7637, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": 0.23891142010688782, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.9968, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3647058823529412, | |
| "grad_norm": 0.2524110674858093, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 6.9215, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.2882583737373352, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.9027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4588235294117646, | |
| "grad_norm": 0.2517209053039551, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.9307, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": 0.29053542017936707, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.6777, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5529411764705883, | |
| "grad_norm": 0.2220264971256256, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 7.0782, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.25292810797691345, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.85, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.2669088840484619, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 7.079, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": 0.26724597811698914, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.7008, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7411764705882353, | |
| "grad_norm": 0.266480028629303, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.7112, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": 0.23365375399589539, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.256, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.835294117647059, | |
| "grad_norm": 0.25366276502609253, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.8007, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.24693305790424347, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.9905, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9294117647058824, | |
| "grad_norm": 0.2845700681209564, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.7647, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": 0.2774038016796112, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 7.0531, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.023529411764706, | |
| "grad_norm": 0.42704179883003235, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9847, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.070588235294118, | |
| "grad_norm": 0.22592473030090332, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.018, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.21758249402046204, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 6.7623, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.164705882352941, | |
| "grad_norm": 0.23572538793087006, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 6.8807, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.211764705882353, | |
| "grad_norm": 0.2834058701992035, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 6.9006, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.2588235294117647, | |
| "grad_norm": 0.25600162148475647, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.7102, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3058823529411763, | |
| "grad_norm": 0.2182091921567917, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 7.1599, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.22837752103805542, | |
| "learning_rate": 0.0, | |
| "loss": 6.9719, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "eval_loss": 6.902400493621826, | |
| "eval_runtime": 0.1136, | |
| "eval_samples_per_second": 1267.459, | |
| "eval_steps_per_second": 158.432, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5830775193600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |