| { | |
| "best_metric": 4.55251932144165, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2557544757033248, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005115089514066497, | |
| "grad_norm": 9.48886775970459, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5047, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005115089514066497, | |
| "eval_loss": 7.651984214782715, | |
| "eval_runtime": 23.2283, | |
| "eval_samples_per_second": 14.207, | |
| "eval_steps_per_second": 3.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010230179028132993, | |
| "grad_norm": 7.729719638824463, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8985, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015345268542199489, | |
| "grad_norm": 8.052858352661133, | |
| "learning_rate": 3e-05, | |
| "loss": 6.0288, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020460358056265986, | |
| "grad_norm": 6.788303852081299, | |
| "learning_rate": 4e-05, | |
| "loss": 5.5813, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02557544757033248, | |
| "grad_norm": 4.8062262535095215, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5641, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030690537084398978, | |
| "grad_norm": 3.997166872024536, | |
| "learning_rate": 6e-05, | |
| "loss": 5.9237, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03580562659846547, | |
| "grad_norm": 3.928126811981201, | |
| "learning_rate": 7e-05, | |
| "loss": 5.4307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04092071611253197, | |
| "grad_norm": 5.754164695739746, | |
| "learning_rate": 8e-05, | |
| "loss": 4.9893, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04603580562659847, | |
| "grad_norm": 4.404843807220459, | |
| "learning_rate": 9e-05, | |
| "loss": 5.0629, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "grad_norm": 4.053828716278076, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5917, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.056265984654731455, | |
| "grad_norm": 3.8155884742736816, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 4.2516, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.061381074168797956, | |
| "grad_norm": 3.4340007305145264, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 4.174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06649616368286446, | |
| "grad_norm": 2.701197385787964, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.8316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07161125319693094, | |
| "grad_norm": 3.004122734069824, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 3.987, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07672634271099744, | |
| "grad_norm": 2.845054864883423, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.6807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08184143222506395, | |
| "grad_norm": 3.3714535236358643, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 4.0097, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 2.416005849838257, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 3.2052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09207161125319693, | |
| "grad_norm": 2.8669612407684326, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.2715, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09718670076726342, | |
| "grad_norm": 2.7934770584106445, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.0802, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "grad_norm": 2.592581272125244, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.1131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10741687979539642, | |
| "grad_norm": 3.4438283443450928, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.175, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11253196930946291, | |
| "grad_norm": 3.016294479370117, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.5276, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 2.802727222442627, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 2.9135, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12276214833759591, | |
| "grad_norm": 2.832228422164917, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.1054, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1278772378516624, | |
| "grad_norm": 2.6756863594055176, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 2.9628, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1329923273657289, | |
| "grad_norm": 2.733081817626953, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 2.9537, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13810741687979539, | |
| "grad_norm": 2.7606492042541504, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 3.0507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1432225063938619, | |
| "grad_norm": 2.96380877494812, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 2.7823, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1483375959079284, | |
| "grad_norm": 3.0976133346557617, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.9072, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1534526854219949, | |
| "grad_norm": 3.3771605491638184, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1585677749360614, | |
| "grad_norm": 3.442176580429077, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 2.603, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1636828644501279, | |
| "grad_norm": 3.1501970291137695, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.0066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16879795396419436, | |
| "grad_norm": 3.4222052097320557, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.802, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 3.5420730113983154, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 2.795, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17902813299232737, | |
| "grad_norm": 3.4514718055725098, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.4177, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18414322250639387, | |
| "grad_norm": 4.618533134460449, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.9886, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18925831202046037, | |
| "grad_norm": 4.481081485748291, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 2.0961, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19437340153452684, | |
| "grad_norm": 4.901217460632324, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.8523, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19948849104859334, | |
| "grad_norm": 3.705735921859741, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8015, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "grad_norm": 1.5407553911209106, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.1171, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20971867007672634, | |
| "grad_norm": 2.0642812252044678, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.3588, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21483375959079284, | |
| "grad_norm": 2.8660378456115723, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.2585, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21994884910485935, | |
| "grad_norm": 2.2530696392059326, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.3681, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22506393861892582, | |
| "grad_norm": 2.2244601249694824, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0182, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23017902813299232, | |
| "grad_norm": 0.11490941047668457, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0033, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.13940373063087463, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0032, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.24040920716112532, | |
| "grad_norm": 3.6119070053100586, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.1022, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24552429667519182, | |
| "grad_norm": 1.867747187614441, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0344, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2506393861892583, | |
| "grad_norm": 56.889617919921875, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 12.0252, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2557544757033248, | |
| "grad_norm": 51.18042755126953, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 10.018, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2557544757033248, | |
| "eval_loss": 4.55251932144165, | |
| "eval_runtime": 23.5332, | |
| "eval_samples_per_second": 14.023, | |
| "eval_steps_per_second": 3.527, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.71020323176448e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |