Instructions to use aleegis12/e44ab6e4-8c71-45b8-a00b-5b8a30673a0c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis12/e44ab6e4-8c71-45b8-a00b-5b8a30673a0c with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("facebook/opt-1.3b") model = PeftModel.from_pretrained(base_model, "aleegis12/e44ab6e4-8c71-45b8-a00b-5b8a30673a0c") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.7880479693412781, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.022313335006833458, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "grad_norm": 2.4033002853393555, | |
| "learning_rate": 1e-05, | |
| "loss": 5.0137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "eval_loss": 1.3168914318084717, | |
| "eval_runtime": 397.5675, | |
| "eval_samples_per_second": 37.973, | |
| "eval_steps_per_second": 9.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "grad_norm": 2.582024335861206, | |
| "learning_rate": 2e-05, | |
| "loss": 4.9758, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003347000251025019, | |
| "grad_norm": 2.492556095123291, | |
| "learning_rate": 3e-05, | |
| "loss": 4.7961, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004462667001366692, | |
| "grad_norm": 2.796631336212158, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005578333751708364, | |
| "grad_norm": 2.698577880859375, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006694000502050038, | |
| "grad_norm": 3.773116111755371, | |
| "learning_rate": 6e-05, | |
| "loss": 4.2965, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000780966725239171, | |
| "grad_norm": 3.0108513832092285, | |
| "learning_rate": 7e-05, | |
| "loss": 4.5566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008925334002733384, | |
| "grad_norm": 2.9917564392089844, | |
| "learning_rate": 8e-05, | |
| "loss": 4.6606, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010041000753075056, | |
| "grad_norm": 2.929912805557251, | |
| "learning_rate": 9e-05, | |
| "loss": 4.1257, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011156667503416729, | |
| "grad_norm": 2.983640670776367, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012272334253758403, | |
| "grad_norm": 3.1720612049102783, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 4.1727, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0013388001004100076, | |
| "grad_norm": 3.0805060863494873, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.9789, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014503667754441748, | |
| "grad_norm": 3.3445961475372314, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.7248, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001561933450478342, | |
| "grad_norm": 3.2860052585601807, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 4.2294, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0016735001255125093, | |
| "grad_norm": 3.773343324661255, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.9823, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0017850668005466768, | |
| "grad_norm": 2.975407838821411, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 3.9519, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001896633475580844, | |
| "grad_norm": 3.0227627754211426, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 4.0763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0020082001506150113, | |
| "grad_norm": 2.3230745792388916, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.9814, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0021197668256491787, | |
| "grad_norm": 2.459735631942749, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.4303, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0022313335006833458, | |
| "grad_norm": 2.0410797595977783, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.6781, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002342900175717513, | |
| "grad_norm": 2.1810357570648193, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 4.2456, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024544668507516807, | |
| "grad_norm": 2.251356601715088, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.9207, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0025660335257858477, | |
| "grad_norm": 2.3650405406951904, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 4.0707, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002677600200820015, | |
| "grad_norm": 2.328626871109009, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.7685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002789166875854182, | |
| "grad_norm": 2.030519485473633, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 3.8375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0029007335508883497, | |
| "grad_norm": 2.167370557785034, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 3.8536, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003012300225922517, | |
| "grad_norm": 2.3776462078094482, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 3.8012, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003123866900956684, | |
| "grad_norm": 2.1572935581207275, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.9087, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0032354335759908516, | |
| "grad_norm": 2.0606510639190674, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.4919, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0033470002510250186, | |
| "grad_norm": 2.1421420574188232, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.6863, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003458566926059186, | |
| "grad_norm": 2.2042953968048096, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 3.5695, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0035701336010933536, | |
| "grad_norm": 2.478196144104004, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.3942, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0036817002761275206, | |
| "grad_norm": 2.29473614692688, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 3.4505, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003793266951161688, | |
| "grad_norm": 2.356095552444458, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 3.5893, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0039048336261958555, | |
| "grad_norm": 2.2125542163848877, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 3.3168, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0040164003012300225, | |
| "grad_norm": 2.5465099811553955, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 3.5003, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0041279669762641896, | |
| "grad_norm": 2.355133056640625, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.5295, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0042395336512983575, | |
| "grad_norm": 2.8939781188964844, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 3.7897, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0043511003263325245, | |
| "grad_norm": 2.6924989223480225, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 3.4813, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0044626670013666915, | |
| "grad_norm": 2.7324650287628174, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.7742, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004574233676400859, | |
| "grad_norm": 2.728142738342285, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.4449, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004685800351435026, | |
| "grad_norm": 2.9953949451446533, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.4634, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0047973670264691935, | |
| "grad_norm": 2.820913076400757, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.5552, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.004908933701503361, | |
| "grad_norm": 2.5653891563415527, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.6813, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005020500376537528, | |
| "grad_norm": 2.772585153579712, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 3.7978, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005132067051571695, | |
| "grad_norm": 3.1895604133605957, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.8935, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005243633726605862, | |
| "grad_norm": 3.031067132949829, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 3.486, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00535520040164003, | |
| "grad_norm": 3.098876953125, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.1027, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005466767076674197, | |
| "grad_norm": 3.4631571769714355, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 3.8982, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.005578333751708364, | |
| "grad_norm": 4.86317777633667, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 3.9976, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005578333751708364, | |
| "eval_loss": 0.8996915221214294, | |
| "eval_runtime": 399.5411, | |
| "eval_samples_per_second": 37.786, | |
| "eval_steps_per_second": 9.448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "grad_norm": 10.76298999786377, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 4.9106, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.005801467101776699, | |
| "grad_norm": 6.88174295425415, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 4.4816, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.005913033776810866, | |
| "grad_norm": 3.502387285232544, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 4.3097, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006024600451845034, | |
| "grad_norm": 2.290653944015503, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 3.8382, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006136167126879201, | |
| "grad_norm": 2.3226394653320312, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 4.047, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.006247733801913368, | |
| "grad_norm": 2.5223870277404785, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 4.0226, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.006359300476947536, | |
| "grad_norm": 2.2635581493377686, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 3.9961, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.006470867151981703, | |
| "grad_norm": 2.086395502090454, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 3.5025, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.00658243382701587, | |
| "grad_norm": 2.0545003414154053, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 3.573, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.006694000502050037, | |
| "grad_norm": 2.1522152423858643, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 3.3387, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.006805567177084205, | |
| "grad_norm": 2.0804038047790527, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 3.3949, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.006917133852118372, | |
| "grad_norm": 2.520615577697754, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 3.6544, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.007028700527152539, | |
| "grad_norm": 2.2839410305023193, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 3.7582, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.007140267202186707, | |
| "grad_norm": 2.1401476860046387, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 3.4141, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.007251833877220874, | |
| "grad_norm": 2.0271806716918945, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 3.2848, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.007363400552255041, | |
| "grad_norm": 1.8410320281982422, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 3.3645, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.007474967227289209, | |
| "grad_norm": 1.8437024354934692, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 3.4631, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.007586533902323376, | |
| "grad_norm": 1.688860535621643, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 3.84, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.007698100577357543, | |
| "grad_norm": 1.5914733409881592, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 3.5901, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.007809667252391711, | |
| "grad_norm": 1.4916577339172363, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 3.5046, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.007921233927425877, | |
| "grad_norm": 1.5571781396865845, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 3.5231, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.008032800602460045, | |
| "grad_norm": 1.6727362871170044, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 3.3664, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.008144367277494213, | |
| "grad_norm": 1.6456553936004639, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 3.4724, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.008255933952528379, | |
| "grad_norm": 1.7136516571044922, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 3.2833, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.008367500627562547, | |
| "grad_norm": 1.761388897895813, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 3.3869, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.008479067302596715, | |
| "grad_norm": 1.7746692895889282, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 3.3226, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.008590633977630881, | |
| "grad_norm": 1.8088513612747192, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 3.1141, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.008702200652665049, | |
| "grad_norm": 1.7707371711730957, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 3.2918, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.008813767327699217, | |
| "grad_norm": 1.7933939695358276, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 3.3643, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.008925334002733383, | |
| "grad_norm": 1.8138039112091064, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 3.4321, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009036900677767551, | |
| "grad_norm": 1.8923362493515015, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 3.3017, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.009148467352801719, | |
| "grad_norm": 1.8164533376693726, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 3.24, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.009260034027835885, | |
| "grad_norm": 1.8007550239562988, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 3.0843, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.009371600702870053, | |
| "grad_norm": 1.9609441757202148, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 3.8118, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.00948316737790422, | |
| "grad_norm": 1.782038688659668, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 3.3396, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.009594734052938387, | |
| "grad_norm": 1.8468660116195679, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.2268, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.009706300727972555, | |
| "grad_norm": 1.9659234285354614, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 3.2085, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.009817867403006723, | |
| "grad_norm": 1.9230685234069824, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 3.1074, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.009929434078040889, | |
| "grad_norm": 2.003465175628662, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 3.3625, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.010041000753075057, | |
| "grad_norm": 2.074953079223633, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 3.0505, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.010152567428109223, | |
| "grad_norm": 2.1427836418151855, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 3.5386, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.01026413410314339, | |
| "grad_norm": 2.1172902584075928, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 3.2341, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.010375700778177559, | |
| "grad_norm": 2.3117504119873047, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 3.6411, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.010487267453211725, | |
| "grad_norm": 2.5828921794891357, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 3.8207, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.010598834128245893, | |
| "grad_norm": 2.4636621475219727, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 3.082, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01071040080328006, | |
| "grad_norm": 2.580232858657837, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 3.4842, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.010821967478314227, | |
| "grad_norm": 2.9706976413726807, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 4.0714, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.010933534153348395, | |
| "grad_norm": 2.936147451400757, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 3.8877, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.011045100828382563, | |
| "grad_norm": 3.6913647651672363, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 3.9742, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.011156667503416729, | |
| "grad_norm": 3.572354316711426, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 3.806, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011156667503416729, | |
| "eval_loss": 0.8263590335845947, | |
| "eval_runtime": 399.2945, | |
| "eval_samples_per_second": 37.809, | |
| "eval_steps_per_second": 9.454, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011268234178450897, | |
| "grad_norm": 2.1806721687316895, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 3.9732, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.011379800853485065, | |
| "grad_norm": 2.1661012172698975, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 3.9877, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.01149136752851923, | |
| "grad_norm": 1.9605587720870972, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 3.9126, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.011602934203553399, | |
| "grad_norm": 1.6957565546035767, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 3.4668, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.011714500878587567, | |
| "grad_norm": 1.6682507991790771, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9276, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.011826067553621733, | |
| "grad_norm": 1.5366711616516113, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 3.7503, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.0119376342286559, | |
| "grad_norm": 1.7268996238708496, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 3.6094, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.012049200903690068, | |
| "grad_norm": 1.6949690580368042, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 3.3207, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.012160767578724235, | |
| "grad_norm": 1.7867645025253296, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 3.5671, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.012272334253758403, | |
| "grad_norm": 1.9672300815582275, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 3.4584, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 1.9163389205932617, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 3.4172, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.012495467603826737, | |
| "grad_norm": 1.88857102394104, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 3.328, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.012607034278860904, | |
| "grad_norm": 2.051499128341675, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 3.0952, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.012718600953895072, | |
| "grad_norm": 2.2822840213775635, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 3.4056, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.012830167628929239, | |
| "grad_norm": 2.0844478607177734, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 3.3351, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.012941734303963406, | |
| "grad_norm": 1.7774839401245117, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 3.3559, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.013053300978997573, | |
| "grad_norm": 1.659458041191101, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 3.4428, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.01316486765403174, | |
| "grad_norm": 1.6343141794204712, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 3.4599, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.013276434329065908, | |
| "grad_norm": 1.636792778968811, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 3.6869, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.013388001004100075, | |
| "grad_norm": 1.8275372982025146, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 3.5715, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.013499567679134242, | |
| "grad_norm": 1.7859272956848145, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 3.2784, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.01361113435416841, | |
| "grad_norm": 1.575589895248413, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 3.3952, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.013722701029202576, | |
| "grad_norm": 1.6178736686706543, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 3.4391, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.013834267704236744, | |
| "grad_norm": 1.5677655935287476, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.1391, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.013945834379270912, | |
| "grad_norm": 1.7418873310089111, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 3.1754, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.014057401054305078, | |
| "grad_norm": 1.7793954610824585, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 3.3338, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.014168967729339246, | |
| "grad_norm": 1.7160708904266357, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 3.1305, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.014280534404373414, | |
| "grad_norm": 1.6351280212402344, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 3.4695, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.01439210107940758, | |
| "grad_norm": 1.8030728101730347, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 3.2462, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.014503667754441748, | |
| "grad_norm": 1.8812822103500366, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 3.0244, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.014615234429475916, | |
| "grad_norm": 1.8913522958755493, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 3.2875, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.014726801104510082, | |
| "grad_norm": 1.9062559604644775, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 3.249, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.01483836777954425, | |
| "grad_norm": 1.777759313583374, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 3.1799, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.014949934454578418, | |
| "grad_norm": 1.847739815711975, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 3.2525, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.015061501129612584, | |
| "grad_norm": 2.195852518081665, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 2.9181, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.015173067804646752, | |
| "grad_norm": 1.9075164794921875, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 3.3438, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.01528463447968092, | |
| "grad_norm": 2.017794609069824, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 3.4935, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.015396201154715086, | |
| "grad_norm": 1.9309802055358887, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 2.7941, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.015507767829749254, | |
| "grad_norm": 2.0513269901275635, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 3.3368, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.015619334504783422, | |
| "grad_norm": 1.8563671112060547, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 2.9058, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01573090117981759, | |
| "grad_norm": 2.1501331329345703, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 3.3191, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.015842467854851754, | |
| "grad_norm": 2.2470195293426514, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 2.9002, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.015954034529885922, | |
| "grad_norm": 2.110045909881592, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.9074, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.01606560120492009, | |
| "grad_norm": 2.2036666870117188, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 3.2012, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.016177167879954258, | |
| "grad_norm": 2.467076539993286, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 3.4463, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.016288734554988426, | |
| "grad_norm": 2.675964832305908, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 3.5574, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.016400301230022594, | |
| "grad_norm": 3.0534911155700684, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 3.8608, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.016511867905056758, | |
| "grad_norm": 2.7436158657073975, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 3.8338, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.016623434580090926, | |
| "grad_norm": 3.3680295944213867, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 3.6343, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.016735001255125094, | |
| "grad_norm": 3.899643659591675, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 3.7711, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.016735001255125094, | |
| "eval_loss": 0.7967259883880615, | |
| "eval_runtime": 399.429, | |
| "eval_samples_per_second": 37.796, | |
| "eval_steps_per_second": 9.451, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.016846567930159262, | |
| "grad_norm": 1.6897090673446655, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 3.7796, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.01695813460519343, | |
| "grad_norm": 1.6531765460968018, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 4.096, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.017069701280227598, | |
| "grad_norm": 1.7427165508270264, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 3.7728, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.017181267955261762, | |
| "grad_norm": 1.6362138986587524, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 3.6285, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.01729283463029593, | |
| "grad_norm": 1.7968734502792358, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 3.7348, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.017404401305330098, | |
| "grad_norm": 1.6966251134872437, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 3.5419, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.017515967980364266, | |
| "grad_norm": 1.7548437118530273, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 3.472, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.017627534655398434, | |
| "grad_norm": 1.6398605108261108, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 3.4743, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.017739101330432598, | |
| "grad_norm": 1.843963623046875, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 3.5881, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.017850668005466766, | |
| "grad_norm": 1.750859022140503, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 3.1869, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.017962234680500934, | |
| "grad_norm": 1.7632453441619873, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 2.8033, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.018073801355535102, | |
| "grad_norm": 1.835609793663025, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.5118, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.01818536803056927, | |
| "grad_norm": 1.968835473060608, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 3.1825, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.018296934705603438, | |
| "grad_norm": 2.0736947059631348, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 3.3546, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.018408501380637602, | |
| "grad_norm": 1.9064536094665527, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 3.1893, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.01852006805567177, | |
| "grad_norm": 1.8090455532073975, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 3.579, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.018631634730705938, | |
| "grad_norm": 1.951940894126892, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 3.2458, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.018743201405740106, | |
| "grad_norm": 1.7783336639404297, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 3.3161, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.018854768080774274, | |
| "grad_norm": 1.6926987171173096, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 3.3881, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.01896633475580844, | |
| "grad_norm": 1.631276249885559, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 3.1959, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.019077901430842606, | |
| "grad_norm": 1.65015709400177, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 3.491, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.019189468105876774, | |
| "grad_norm": 1.7475810050964355, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 3.3288, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.01930103478091094, | |
| "grad_norm": 1.6400350332260132, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 3.2379, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.01941260145594511, | |
| "grad_norm": 1.6550151109695435, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 3.2239, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.019524168130979278, | |
| "grad_norm": 1.763994812965393, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 3.3569, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.019635734806013445, | |
| "grad_norm": 1.581963300704956, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 3.3377, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.01974730148104761, | |
| "grad_norm": 1.754233956336975, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 3.1917, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.019858868156081778, | |
| "grad_norm": 1.7126407623291016, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 3.1997, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.019970434831115946, | |
| "grad_norm": 1.8401472568511963, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 3.0342, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.020082001506150114, | |
| "grad_norm": 1.8019397258758545, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 2.8997, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02019356818118428, | |
| "grad_norm": 1.8011956214904785, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.1892, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.020305134856218446, | |
| "grad_norm": 1.9675805568695068, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 3.2641, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.020416701531252614, | |
| "grad_norm": 1.8635698556900024, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 3.2314, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.02052826820628678, | |
| "grad_norm": 1.8356258869171143, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 3.1204, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.02063983488132095, | |
| "grad_norm": 2.011965036392212, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 3.1925, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.020751401556355117, | |
| "grad_norm": 1.981431007385254, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 2.9529, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.020862968231389285, | |
| "grad_norm": 1.9463725090026855, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 3.2915, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.02097453490642345, | |
| "grad_norm": 2.119337797164917, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 3.252, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.021086101581457618, | |
| "grad_norm": 2.0271079540252686, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 3.2871, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.021197668256491786, | |
| "grad_norm": 2.328778028488159, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 3.0631, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.021309234931525953, | |
| "grad_norm": 2.3687922954559326, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 3.1417, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.02142080160656012, | |
| "grad_norm": 2.1857614517211914, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 3.0704, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.02153236828159429, | |
| "grad_norm": 2.255352735519409, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 3.1714, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.021643934956628454, | |
| "grad_norm": 2.6467716693878174, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 3.1792, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.02175550163166262, | |
| "grad_norm": 2.3636562824249268, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 3.1862, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.02186706830669679, | |
| "grad_norm": 2.6564090251922607, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 3.7893, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.021978634981730957, | |
| "grad_norm": 3.0563623905181885, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 3.6992, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.022090201656765125, | |
| "grad_norm": 3.0911147594451904, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 3.8142, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.022201768331799293, | |
| "grad_norm": 3.8989179134368896, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 3.8958, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.022313335006833458, | |
| "grad_norm": 3.7806591987609863, | |
| "learning_rate": 0.0, | |
| "loss": 3.2953, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.022313335006833458, | |
| "eval_loss": 0.7880479693412781, | |
| "eval_runtime": 399.1948, | |
| "eval_samples_per_second": 37.819, | |
| "eval_steps_per_second": 9.457, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.703906823130317e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |