Instructions to use aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/SmolLM2-135M") model = PeftModel.from_pretrained(base_model, "aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c: direct link, hf CLI and curl.
- Browser
- Download file 27.5 kB
-
https://huggingface.co/aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c/resolve/09f638230179fe68f8e1a59aa3ab401f8b0c378e/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c@09f638230179fe68f8e1a59aa3ab401f8b0c378e/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/aleegis10/328c7fca-9a6b-4269-9dfe-e170212caa1c/resolve/09f638230179fe68f8e1a59aa3ab401f8b0c378e/last-checkpoint/trainer_state.json
27.5 kB
| { | |
| "best_metric": 0.9148275852203369, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 2.542372881355932, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01694915254237288, | |
| "grad_norm": 0.9787123203277588, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01694915254237288, | |
| "eval_loss": 4.1999897956848145, | |
| "eval_runtime": 1.4503, | |
| "eval_samples_per_second": 68.951, | |
| "eval_steps_per_second": 17.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 2.4502038955688477, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4497, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05084745762711865, | |
| "grad_norm": 2.665430784225464, | |
| "learning_rate": 3e-05, | |
| "loss": 4.639, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 2.4935710430145264, | |
| "learning_rate": 4e-05, | |
| "loss": 4.4997, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 2.3885178565979004, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 2.521230459213257, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4601, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11864406779661017, | |
| "grad_norm": 2.408069133758545, | |
| "learning_rate": 7e-05, | |
| "loss": 4.3255, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 1.1387848854064941, | |
| "learning_rate": 8e-05, | |
| "loss": 3.355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15254237288135594, | |
| "grad_norm": 1.0923254489898682, | |
| "learning_rate": 9e-05, | |
| "loss": 3.0777, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 1.489324688911438, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1864406779661017, | |
| "grad_norm": 1.415766716003418, | |
| "learning_rate": 9.999115304121457e-05, | |
| "loss": 3.4619, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 1.4508241415023804, | |
| "learning_rate": 9.996461529560553e-05, | |
| "loss": 3.2672, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22033898305084745, | |
| "grad_norm": 1.6372668743133545, | |
| "learning_rate": 9.992039615430648e-05, | |
| "loss": 3.3624, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23728813559322035, | |
| "grad_norm": 2.086595296859741, | |
| "learning_rate": 9.985851126551428e-05, | |
| "loss": 3.8379, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 1.075448751449585, | |
| "learning_rate": 9.977898252895134e-05, | |
| "loss": 2.6479, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 2.2425975799560547, | |
| "learning_rate": 9.968183808811586e-05, | |
| "loss": 2.9848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.288135593220339, | |
| "grad_norm": 2.2366819381713867, | |
| "learning_rate": 9.95671123203224e-05, | |
| "loss": 2.818, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3050847457627119, | |
| "grad_norm": 2.1117076873779297, | |
| "learning_rate": 9.943484582453653e-05, | |
| "loss": 2.6075, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3220338983050847, | |
| "grad_norm": 2.0897672176361084, | |
| "learning_rate": 9.928508540700774e-05, | |
| "loss": 2.5123, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 1.8737945556640625, | |
| "learning_rate": 9.911788406470569e-05, | |
| "loss": 2.3475, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3559322033898305, | |
| "grad_norm": 1.7135223150253296, | |
| "learning_rate": 9.893330096656574e-05, | |
| "loss": 2.2067, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3728813559322034, | |
| "grad_norm": 0.705153226852417, | |
| "learning_rate": 9.873140143255036e-05, | |
| "loss": 2.1873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3898305084745763, | |
| "grad_norm": 0.7329670190811157, | |
| "learning_rate": 9.85122569105338e-05, | |
| "loss": 2.6215, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 1.136795163154602, | |
| "learning_rate": 9.827594495101823e-05, | |
| "loss": 2.8488, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 1.0769141912460327, | |
| "learning_rate": 9.802254917969032e-05, | |
| "loss": 2.8395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4406779661016949, | |
| "grad_norm": 1.4403115510940552, | |
| "learning_rate": 9.775215926782788e-05, | |
| "loss": 2.6802, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4576271186440678, | |
| "grad_norm": 1.4279862642288208, | |
| "learning_rate": 9.746487090056713e-05, | |
| "loss": 2.7192, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 1.699432611465454, | |
| "learning_rate": 9.716078574304189e-05, | |
| "loss": 2.8853, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4915254237288136, | |
| "grad_norm": 1.4521034955978394, | |
| "learning_rate": 9.684001140440639e-05, | |
| "loss": 1.9164, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 2.434119939804077, | |
| "learning_rate": 9.650266139975474e-05, | |
| "loss": 1.3542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5254237288135594, | |
| "grad_norm": 1.6792948246002197, | |
| "learning_rate": 9.614885510995047e-05, | |
| "loss": 1.3436, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 1.6474392414093018, | |
| "learning_rate": 9.577871773938011e-05, | |
| "loss": 1.1094, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.559322033898305, | |
| "grad_norm": 1.6065335273742676, | |
| "learning_rate": 9.539238027164619e-05, | |
| "loss": 0.9116, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.576271186440678, | |
| "grad_norm": 1.514753818511963, | |
| "learning_rate": 9.498997942321483e-05, | |
| "loss": 0.8389, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5932203389830508, | |
| "grad_norm": 1.2533358335494995, | |
| "learning_rate": 9.457165759503493e-05, | |
| "loss": 0.9727, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 0.8802417516708374, | |
| "learning_rate": 9.413756282214537e-05, | |
| "loss": 1.7009, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6271186440677966, | |
| "grad_norm": 1.1750346422195435, | |
| "learning_rate": 9.368784872128878e-05, | |
| "loss": 2.5651, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6440677966101694, | |
| "grad_norm": 1.331346035003662, | |
| "learning_rate": 9.322267443654972e-05, | |
| "loss": 2.5368, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6610169491525424, | |
| "grad_norm": 1.1209417581558228, | |
| "learning_rate": 9.274220458303727e-05, | |
| "loss": 2.8612, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.2335385084152222, | |
| "learning_rate": 9.224660918863104e-05, | |
| "loss": 2.6824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6949152542372882, | |
| "grad_norm": 1.1797600984573364, | |
| "learning_rate": 9.173606363381219e-05, | |
| "loss": 2.4775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.711864406779661, | |
| "grad_norm": 1.6770628690719604, | |
| "learning_rate": 9.121074858959997e-05, | |
| "loss": 2.7293, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7288135593220338, | |
| "grad_norm": 1.0169050693511963, | |
| "learning_rate": 9.067084995361623e-05, | |
| "loss": 1.3915, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": 1.1066895723342896, | |
| "learning_rate": 9.011655878430019e-05, | |
| "loss": 0.5636, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "grad_norm": 0.9063847661018372, | |
| "learning_rate": 8.954807123329704e-05, | |
| "loss": 0.1767, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7796610169491526, | |
| "grad_norm": 0.5006846189498901, | |
| "learning_rate": 8.896558847604414e-05, | |
| "loss": 0.3629, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7966101694915254, | |
| "grad_norm": 0.42200618982315063, | |
| "learning_rate": 8.836931664057935e-05, | |
| "loss": 0.2745, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.3802186846733093, | |
| "learning_rate": 8.775946673459681e-05, | |
| "loss": 0.1882, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8305084745762712, | |
| "grad_norm": 0.3861039876937866, | |
| "learning_rate": 8.713625457077585e-05, | |
| "loss": 0.4487, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 0.9502959847450256, | |
| "learning_rate": 8.649990069040961e-05, | |
| "loss": 2.1698, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "eval_loss": 1.0403923988342285, | |
| "eval_runtime": 1.442, | |
| "eval_samples_per_second": 69.349, | |
| "eval_steps_per_second": 17.337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.864406779661017, | |
| "grad_norm": 1.0427058935165405, | |
| "learning_rate": 8.585063028536016e-05, | |
| "loss": 2.4816, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": 0.9536698460578918, | |
| "learning_rate": 8.518867311836808e-05, | |
| "loss": 2.379, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8983050847457628, | |
| "grad_norm": 1.1528958082199097, | |
| "learning_rate": 8.451426344174433e-05, | |
| "loss": 2.5705, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9152542372881356, | |
| "grad_norm": 1.075803518295288, | |
| "learning_rate": 8.382763991447344e-05, | |
| "loss": 2.3945, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9322033898305084, | |
| "grad_norm": 1.1288622617721558, | |
| "learning_rate": 8.312904551775731e-05, | |
| "loss": 2.536, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 1.494862675666809, | |
| "learning_rate": 8.241872746902935e-05, | |
| "loss": 2.5827, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9661016949152542, | |
| "grad_norm": 0.41931426525115967, | |
| "learning_rate": 8.169693713446959e-05, | |
| "loss": 0.7727, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9830508474576272, | |
| "grad_norm": 0.464871883392334, | |
| "learning_rate": 8.096392994005177e-05, | |
| "loss": 1.2605, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.0274232625961304, | |
| "learning_rate": 8.021996528115335e-05, | |
| "loss": 2.5275, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 0.5695710182189941, | |
| "learning_rate": 7.946530643076138e-05, | |
| "loss": 1.3716, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0338983050847457, | |
| "grad_norm": 0.29576823115348816, | |
| "learning_rate": 7.870022044630569e-05, | |
| "loss": 0.3392, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.0508474576271187, | |
| "grad_norm": 0.29110977053642273, | |
| "learning_rate": 7.792497807515317e-05, | |
| "loss": 0.3041, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0677966101694916, | |
| "grad_norm": 0.27382704615592957, | |
| "learning_rate": 7.713985365879606e-05, | |
| "loss": 0.4193, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.19342516362667084, | |
| "learning_rate": 7.63451250357685e-05, | |
| "loss": 0.1109, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.1016949152542372, | |
| "grad_norm": 0.1454094499349594, | |
| "learning_rate": 7.55410734433254e-05, | |
| "loss": 0.0198, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.11864406779661, | |
| "grad_norm": 0.23074690997600555, | |
| "learning_rate": 7.472798341791877e-05, | |
| "loss": 0.1309, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.1355932203389831, | |
| "grad_norm": 0.47609075903892517, | |
| "learning_rate": 7.390614269450634e-05, | |
| "loss": 1.3382, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.152542372881356, | |
| "grad_norm": 0.7256209254264832, | |
| "learning_rate": 7.307584210472844e-05, | |
| "loss": 2.2253, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.1694915254237288, | |
| "grad_norm": 0.7721383571624756, | |
| "learning_rate": 7.223737547398898e-05, | |
| "loss": 2.1726, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1864406779661016, | |
| "grad_norm": 0.8785566091537476, | |
| "learning_rate": 7.139103951747695e-05, | |
| "loss": 2.4489, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2033898305084745, | |
| "grad_norm": 0.797492265701294, | |
| "learning_rate": 7.053713373516538e-05, | |
| "loss": 2.2085, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.8545417785644531, | |
| "learning_rate": 6.967596030582478e-05, | |
| "loss": 2.4864, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.2372881355932204, | |
| "grad_norm": 1.2952442169189453, | |
| "learning_rate": 6.880782398008862e-05, | |
| "loss": 2.3607, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.2542372881355932, | |
| "grad_norm": 0.4277438223361969, | |
| "learning_rate": 6.793303197260864e-05, | |
| "loss": 1.2012, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.271186440677966, | |
| "grad_norm": 0.23187437653541565, | |
| "learning_rate": 6.70518938533383e-05, | |
| "loss": 0.1912, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.288135593220339, | |
| "grad_norm": 0.13725751638412476, | |
| "learning_rate": 6.616472143798261e-05, | |
| "loss": 0.1406, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.305084745762712, | |
| "grad_norm": 0.23800960183143616, | |
| "learning_rate": 6.527182867765332e-05, | |
| "loss": 0.0717, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.3220338983050848, | |
| "grad_norm": 0.16830310225486755, | |
| "learning_rate": 6.437353154776849e-05, | |
| "loss": 0.1892, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3389830508474576, | |
| "grad_norm": 0.05917459353804588, | |
| "learning_rate": 6.347014793623547e-05, | |
| "loss": 0.0077, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.17031961679458618, | |
| "learning_rate": 6.256199753095745e-05, | |
| "loss": 0.2442, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3728813559322033, | |
| "grad_norm": 0.603077232837677, | |
| "learning_rate": 6.164940170670266e-05, | |
| "loss": 1.8995, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3898305084745763, | |
| "grad_norm": 0.6798323392868042, | |
| "learning_rate": 6.0732683411376935e-05, | |
| "loss": 2.2423, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.4067796610169492, | |
| "grad_norm": 0.8995802998542786, | |
| "learning_rate": 5.98121670517393e-05, | |
| "loss": 2.1578, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.423728813559322, | |
| "grad_norm": 0.7790073752403259, | |
| "learning_rate": 5.8888178378601565e-05, | |
| "loss": 2.3126, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.4406779661016949, | |
| "grad_norm": 0.9033922553062439, | |
| "learning_rate": 5.796104437155213e-05, | |
| "loss": 2.207, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.457627118644068, | |
| "grad_norm": 0.8630293607711792, | |
| "learning_rate": 5.7031093123244925e-05, | |
| "loss": 2.1339, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.4745762711864407, | |
| "grad_norm": 1.140993595123291, | |
| "learning_rate": 5.6098653723294604e-05, | |
| "loss": 2.2742, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.5041856169700623, | |
| "learning_rate": 5.516405614181883e-05, | |
| "loss": 1.2441, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.5084745762711864, | |
| "grad_norm": 0.0990825667977333, | |
| "learning_rate": 5.4227631112668955e-05, | |
| "loss": 0.0708, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.5254237288135593, | |
| "grad_norm": 0.1579853743314743, | |
| "learning_rate": 5.3289710016390535e-05, | |
| "loss": 0.2237, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.542372881355932, | |
| "grad_norm": 0.1326770782470703, | |
| "learning_rate": 5.2350624762954884e-05, | |
| "loss": 0.1283, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.559322033898305, | |
| "grad_norm": 0.13696810603141785, | |
| "learning_rate": 5.14107076743033e-05, | |
| "loss": 0.1354, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.576271186440678, | |
| "grad_norm": 0.039330050349235535, | |
| "learning_rate": 5.047029136674563e-05, | |
| "loss": 0.0049, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5932203389830508, | |
| "grad_norm": 0.17127054929733276, | |
| "learning_rate": 4.95297086332544e-05, | |
| "loss": 0.2072, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.6101694915254239, | |
| "grad_norm": 0.502240777015686, | |
| "learning_rate": 4.858929232569671e-05, | |
| "loss": 1.5421, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.7475689053535461, | |
| "learning_rate": 4.7649375237045135e-05, | |
| "loss": 2.2061, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.6440677966101696, | |
| "grad_norm": 0.7506973743438721, | |
| "learning_rate": 4.671028998360947e-05, | |
| "loss": 2.0706, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.6610169491525424, | |
| "grad_norm": 0.8322485685348511, | |
| "learning_rate": 4.577236888733105e-05, | |
| "loss": 2.3213, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6779661016949152, | |
| "grad_norm": 0.8912888765335083, | |
| "learning_rate": 4.483594385818118e-05, | |
| "loss": 2.2682, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 0.9926512241363525, | |
| "learning_rate": 4.39013462767054e-05, | |
| "loss": 2.2907, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "eval_loss": 0.9476182460784912, | |
| "eval_runtime": 1.4397, | |
| "eval_samples_per_second": 69.46, | |
| "eval_steps_per_second": 17.365, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.711864406779661, | |
| "grad_norm": 1.0757006406784058, | |
| "learning_rate": 4.29689068767551e-05, | |
| "loss": 2.3057, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.7288135593220337, | |
| "grad_norm": 0.5664078593254089, | |
| "learning_rate": 4.203895562844789e-05, | |
| "loss": 1.469, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.7457627118644068, | |
| "grad_norm": 0.09226689487695694, | |
| "learning_rate": 4.1111821621398446e-05, | |
| "loss": 0.0674, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 0.07321758568286896, | |
| "learning_rate": 4.0187832948260705e-05, | |
| "loss": 0.0404, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.7796610169491527, | |
| "grad_norm": 0.24070608615875244, | |
| "learning_rate": 3.926731658862307e-05, | |
| "loss": 0.2084, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7966101694915255, | |
| "grad_norm": 0.027658900246024132, | |
| "learning_rate": 3.835059829329735e-05, | |
| "loss": 0.0039, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.8135593220338984, | |
| "grad_norm": 0.07214166969060898, | |
| "learning_rate": 3.7438002469042565e-05, | |
| "loss": 0.0415, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.8305084745762712, | |
| "grad_norm": 0.22489815950393677, | |
| "learning_rate": 3.6529852063764545e-05, | |
| "loss": 0.3323, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.847457627118644, | |
| "grad_norm": 0.525007963180542, | |
| "learning_rate": 3.562646845223153e-05, | |
| "loss": 1.4499, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.8644067796610169, | |
| "grad_norm": 0.7562161684036255, | |
| "learning_rate": 3.4728171322346694e-05, | |
| "loss": 2.1267, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8813559322033897, | |
| "grad_norm": 0.7749287486076355, | |
| "learning_rate": 3.38352785620174e-05, | |
| "loss": 2.1855, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.8717202544212341, | |
| "learning_rate": 3.29481061466617e-05, | |
| "loss": 2.2716, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.9152542372881356, | |
| "grad_norm": 0.990043580532074, | |
| "learning_rate": 3.2066968027391374e-05, | |
| "loss": 2.1828, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.9322033898305084, | |
| "grad_norm": 0.9501929879188538, | |
| "learning_rate": 3.119217601991139e-05, | |
| "loss": 1.9919, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.9491525423728815, | |
| "grad_norm": 1.3463528156280518, | |
| "learning_rate": 3.0324039694175233e-05, | |
| "loss": 2.3176, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9661016949152543, | |
| "grad_norm": 0.2480294406414032, | |
| "learning_rate": 2.946286626483463e-05, | |
| "loss": 0.4455, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.9830508474576272, | |
| "grad_norm": 0.5426979660987854, | |
| "learning_rate": 2.8608960482523056e-05, | |
| "loss": 1.2601, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9084144234657288, | |
| "learning_rate": 2.7762624526011038e-05, | |
| "loss": 2.1384, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.016949152542373, | |
| "grad_norm": 0.38337242603302, | |
| "learning_rate": 2.6924157895271563e-05, | |
| "loss": 0.9181, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.09438680857419968, | |
| "learning_rate": 2.6093857305493664e-05, | |
| "loss": 0.064, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0508474576271185, | |
| "grad_norm": 0.025368427857756615, | |
| "learning_rate": 2.5272016582081236e-05, | |
| "loss": 0.0037, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.0677966101694913, | |
| "grad_norm": 0.22418174147605896, | |
| "learning_rate": 2.4458926556674615e-05, | |
| "loss": 0.3752, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.084745762711864, | |
| "grad_norm": 0.029728621244430542, | |
| "learning_rate": 2.3654874964231518e-05, | |
| "loss": 0.0035, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.1016949152542375, | |
| "grad_norm": 0.07155339419841766, | |
| "learning_rate": 2.2860146341203937e-05, | |
| "loss": 0.0405, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.1186440677966103, | |
| "grad_norm": 0.08262301981449127, | |
| "learning_rate": 2.207502192484685e-05, | |
| "loss": 0.0428, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.135593220338983, | |
| "grad_norm": 0.5090848803520203, | |
| "learning_rate": 2.1299779553694323e-05, | |
| "loss": 1.3961, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.152542372881356, | |
| "grad_norm": 0.6652891635894775, | |
| "learning_rate": 2.053469356923865e-05, | |
| "loss": 2.0337, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.7932724356651306, | |
| "learning_rate": 1.978003471884665e-05, | |
| "loss": 2.2015, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.1864406779661016, | |
| "grad_norm": 0.828244686126709, | |
| "learning_rate": 1.9036070059948252e-05, | |
| "loss": 2.0406, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.2033898305084745, | |
| "grad_norm": 0.8815770149230957, | |
| "learning_rate": 1.8303062865530406e-05, | |
| "loss": 2.0167, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.2203389830508473, | |
| "grad_norm": 0.9002049565315247, | |
| "learning_rate": 1.7581272530970667e-05, | |
| "loss": 2.0821, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.23728813559322, | |
| "grad_norm": 1.0344882011413574, | |
| "learning_rate": 1.6870954482242707e-05, | |
| "loss": 2.0685, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.2542372881355934, | |
| "grad_norm": 0.44666269421577454, | |
| "learning_rate": 1.6172360085526565e-05, | |
| "loss": 1.1569, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.2711864406779663, | |
| "grad_norm": 0.09210528433322906, | |
| "learning_rate": 1.5485736558255697e-05, | |
| "loss": 0.0479, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.288135593220339, | |
| "grad_norm": 0.038695137947797775, | |
| "learning_rate": 1.4811326881631937e-05, | |
| "loss": 0.0034, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": 0.1461106240749359, | |
| "learning_rate": 1.4149369714639853e-05, | |
| "loss": 0.1391, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.3220338983050848, | |
| "grad_norm": 0.16508442163467407, | |
| "learning_rate": 1.3500099309590397e-05, | |
| "loss": 0.1813, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.3389830508474576, | |
| "grad_norm": 0.12389306724071503, | |
| "learning_rate": 1.2863745429224144e-05, | |
| "loss": 0.097, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.3559322033898304, | |
| "grad_norm": 0.2678169012069702, | |
| "learning_rate": 1.2240533265403198e-05, | |
| "loss": 0.4644, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": 0.6074098348617554, | |
| "learning_rate": 1.1630683359420652e-05, | |
| "loss": 2.0744, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.389830508474576, | |
| "grad_norm": 0.7297008633613586, | |
| "learning_rate": 1.103441152395588e-05, | |
| "loss": 2.0194, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.406779661016949, | |
| "grad_norm": 0.7776730060577393, | |
| "learning_rate": 1.0451928766702979e-05, | |
| "loss": 2.083, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.423728813559322, | |
| "grad_norm": 0.8881759643554688, | |
| "learning_rate": 9.883441215699823e-06, | |
| "loss": 2.5883, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 0.8794331550598145, | |
| "learning_rate": 9.329150046383772e-06, | |
| "loss": 2.0489, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.457627118644068, | |
| "grad_norm": 0.8844050765037537, | |
| "learning_rate": 8.789251410400023e-06, | |
| "loss": 2.1398, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.4745762711864407, | |
| "grad_norm": 1.1741251945495605, | |
| "learning_rate": 8.263936366187824e-06, | |
| "loss": 2.1663, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.4915254237288136, | |
| "grad_norm": 0.4704148471355438, | |
| "learning_rate": 7.753390811368971e-06, | |
| "loss": 1.4645, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.5084745762711864, | |
| "grad_norm": 0.20011013746261597, | |
| "learning_rate": 7.257795416962753e-06, | |
| "loss": 0.308, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.5254237288135593, | |
| "grad_norm": 0.19620303809642792, | |
| "learning_rate": 6.777325563450282e-06, | |
| "loss": 0.1889, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "grad_norm": 0.022152384743094444, | |
| "learning_rate": 6.312151278711237e-06, | |
| "loss": 0.0033, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "eval_loss": 0.9148275852203369, | |
| "eval_runtime": 1.4467, | |
| "eval_samples_per_second": 69.125, | |
| "eval_steps_per_second": 17.281, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 177, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3702083627778048.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |