| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "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": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 3192.6797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.047058823529411764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2749, | |
| "eval_samples_per_second": 181.865, | |
| "eval_steps_per_second": 47.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994224282269737e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.976911955263529e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.948107459476501e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.907884735636226e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.856347034897919e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.793626653800219e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.719884594661864e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635310152291039e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.540120428068338e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43455977265062e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.31889915872638e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.193435485432745e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.058490816219643e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.914411552117559e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.76156754253104e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.600351135840589e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.431176172250002e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.254476921464484e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.070706967926565e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.880338046471331e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0823529411764705, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.683858831389867e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.481773682009356e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.274601348009935e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2691, | |
| "eval_samples_per_second": 185.803, | |
| "eval_steps_per_second": 48.309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.062873637801692e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2705882352941176, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.847134053380112e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.627936395164243e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3647058823529412, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.40584334039897e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.181424998770595e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4588235294117646, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.955257448943445e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.727921259774208e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5529411764705883, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2720787402257935e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.044742551056556e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8185750012294065e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.594156659601029e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.372063604835758e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.835294117647059, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.152865946619889e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.93712636219831e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9294117647058824, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.725398651990067e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.518226317990646e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.023529411764706, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3161411686101364e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.070588235294118, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.119661953528671e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9292930320734335e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.164705882352941, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.745523078535517e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.211764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.568823827750001e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.2588235294117647, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.39964886415941e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3058823529411763, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2384324574689612e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0855884478824412e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.283, | |
| "eval_samples_per_second": 176.67, | |
| "eval_steps_per_second": 45.934, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 64, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 938425712640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |