Instructions to use prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("scb10x/llama-3-typhoon-v1.5-8b-instruct") model = PeftModel.from_pretrained(base_model, "prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a: direct link, hf CLI and curl.
- Browser
- Download file 15.5 kB
-
https://huggingface.co/prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/prxy5604/a3c52648-f93a-41de-8f41-b2cf5f485e8a/resolve/main/last-checkpoint/trainer_state.json
15.5 kB
| { | |
| "best_metric": 1.0678768157958984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 1.699779748916626, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "eval_loss": 1.6286729574203491, | |
| "eval_runtime": 3.8315, | |
| "eval_samples_per_second": 12.267, | |
| "eval_steps_per_second": 3.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.9459228515625, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 1.5444223880767822, | |
| "learning_rate": 3e-05, | |
| "loss": 1.485, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 1.828545331954956, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5345, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 1.6014165878295898, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6242, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 1.756152629852295, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6398, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.0617715120315552, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.2845737934112549, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4341, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 1.1846259832382202, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3764, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.9985613822937012, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 1.181240200996399, | |
| "learning_rate": 9.995494831023409e-05, | |
| "loss": 1.4043, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.2978146076202393, | |
| "learning_rate": 9.981987442712633e-05, | |
| "loss": 1.2975, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 0.8944197297096252, | |
| "learning_rate": 9.959502176294383e-05, | |
| "loss": 1.2176, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.7838349342346191, | |
| "learning_rate": 9.928079551738543e-05, | |
| "loss": 1.1616, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.667181670665741, | |
| "learning_rate": 9.887776194738432e-05, | |
| "loss": 1.139, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.715985894203186, | |
| "learning_rate": 9.838664734667495e-05, | |
| "loss": 1.175, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 0.8861929774284363, | |
| "learning_rate": 9.780833673696254e-05, | |
| "loss": 1.2037, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 1.0346869230270386, | |
| "learning_rate": 9.714387227305422e-05, | |
| "loss": 1.2577, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 0.6048142910003662, | |
| "learning_rate": 9.639445136482548e-05, | |
| "loss": 1.2117, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.6575442552566528, | |
| "learning_rate": 9.55614245194068e-05, | |
| "loss": 1.1469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.5992381572723389, | |
| "learning_rate": 9.464629290747842e-05, | |
| "loss": 1.1609, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.8459616303443909, | |
| "learning_rate": 9.365070565805941e-05, | |
| "loss": 1.0932, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 0.8620023727416992, | |
| "learning_rate": 9.257645688666556e-05, | |
| "loss": 1.2146, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.9809871315956116, | |
| "learning_rate": 9.142548246219212e-05, | |
| "loss": 1.1341, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 0.4556620121002197, | |
| "learning_rate": 9.019985651834703e-05, | |
| "loss": 1.0431, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.6410847902297974, | |
| "learning_rate": 8.890178771592199e-05, | |
| "loss": 1.145, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 0.6918867826461792, | |
| "learning_rate": 8.753361526263621e-05, | |
| "loss": 1.0548, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.03254234790802, | |
| "learning_rate": 8.609780469772623e-05, | |
| "loss": 1.0624, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0357142857142858, | |
| "grad_norm": 0.4657690227031708, | |
| "learning_rate": 8.459694344887732e-05, | |
| "loss": 1.0837, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.5787471532821655, | |
| "learning_rate": 8.303373616950408e-05, | |
| "loss": 0.993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1071428571428572, | |
| "grad_norm": 0.6005241274833679, | |
| "learning_rate": 8.141099986478212e-05, | |
| "loss": 0.9823, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.6915076375007629, | |
| "learning_rate": 7.973165881521434e-05, | |
| "loss": 0.9212, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1785714285714286, | |
| "grad_norm": 0.7980732321739197, | |
| "learning_rate": 7.799873930687978e-05, | |
| "loss": 0.8616, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2142857142857142, | |
| "grad_norm": 0.8493084907531738, | |
| "learning_rate": 7.621536417786159e-05, | |
| "loss": 0.7512, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.5029008388519287, | |
| "learning_rate": 7.438474719068173e-05, | |
| "loss": 0.9363, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.6272581219673157, | |
| "learning_rate": 7.251018724088367e-05, | |
| "loss": 0.9813, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3214285714285714, | |
| "grad_norm": 0.7248469591140747, | |
| "learning_rate": 7.059506241219965e-05, | |
| "loss": 0.8941, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3571428571428572, | |
| "grad_norm": 0.7229782342910767, | |
| "learning_rate": 6.864282388901544e-05, | |
| "loss": 0.8525, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3928571428571428, | |
| "grad_norm": 0.8697368502616882, | |
| "learning_rate": 6.665698973710288e-05, | |
| "loss": 0.8085, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.9230009317398071, | |
| "learning_rate": 6.464113856382752e-05, | |
| "loss": 0.8435, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4642857142857144, | |
| "grad_norm": 0.47812873125076294, | |
| "learning_rate": 6.259890306925627e-05, | |
| "loss": 0.9226, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.5833685994148254, | |
| "learning_rate": 6.0533963499786314e-05, | |
| "loss": 0.9486, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5357142857142856, | |
| "grad_norm": 0.5935266613960266, | |
| "learning_rate": 5.8450041016092464e-05, | |
| "loss": 0.8815, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.7497686743736267, | |
| "learning_rate": 5.6350890987343944e-05, | |
| "loss": 0.8752, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 0.8591090440750122, | |
| "learning_rate": 5.4240296223775465e-05, | |
| "loss": 0.9177, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": 0.8800234198570251, | |
| "learning_rate": 5.212206015980742e-05, | |
| "loss": 0.7726, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6785714285714286, | |
| "grad_norm": 0.5047954320907593, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9669, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.6673800945281982, | |
| "learning_rate": 4.78779398401926e-05, | |
| "loss": 0.9553, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.6023098230361938, | |
| "learning_rate": 4.575970377622456e-05, | |
| "loss": 0.8924, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 0.7557825446128845, | |
| "learning_rate": 4.364910901265606e-05, | |
| "loss": 0.7967, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "eval_loss": 1.0678768157958984, | |
| "eval_runtime": 3.9244, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 3.058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8214285714285714, | |
| "grad_norm": 0.9605938792228699, | |
| "learning_rate": 4.1549958983907555e-05, | |
| "loss": 0.8505, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.9948092103004456, | |
| "learning_rate": 3.94660365002137e-05, | |
| "loss": 0.8254, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.8928571428571428, | |
| "grad_norm": 0.5172920823097229, | |
| "learning_rate": 3.740109693074375e-05, | |
| "loss": 0.997, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 0.618449866771698, | |
| "learning_rate": 3.5358861436172485e-05, | |
| "loss": 0.8848, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.9642857142857144, | |
| "grad_norm": 0.7257911562919617, | |
| "learning_rate": 3.334301026289712e-05, | |
| "loss": 0.8151, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9913805723190308, | |
| "learning_rate": 3.135717611098458e-05, | |
| "loss": 0.6593, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0357142857142856, | |
| "grad_norm": 0.509917140007019, | |
| "learning_rate": 2.9404937587800375e-05, | |
| "loss": 0.9468, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.0714285714285716, | |
| "grad_norm": 0.5384827852249146, | |
| "learning_rate": 2.748981275911633e-05, | |
| "loss": 0.8333, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.107142857142857, | |
| "grad_norm": 0.6404847502708435, | |
| "learning_rate": 2.5615252809318284e-05, | |
| "loss": 0.7695, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.7586694359779358, | |
| "learning_rate": 2.3784635822138424e-05, | |
| "loss": 0.7043, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1785714285714284, | |
| "grad_norm": 0.886222779750824, | |
| "learning_rate": 2.2001260693120233e-05, | |
| "loss": 0.5816, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.2142857142857144, | |
| "grad_norm": 0.9940441846847534, | |
| "learning_rate": 2.026834118478567e-05, | |
| "loss": 0.5794, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 0.5342968702316284, | |
| "learning_rate": 1.858900013521788e-05, | |
| "loss": 0.8532, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.6643630266189575, | |
| "learning_rate": 1.6966263830495936e-05, | |
| "loss": 0.8265, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.3214285714285716, | |
| "grad_norm": 0.6381016373634338, | |
| "learning_rate": 1.5403056551122697e-05, | |
| "loss": 0.7252, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.357142857142857, | |
| "grad_norm": 0.6933656334877014, | |
| "learning_rate": 1.3902195302273779e-05, | |
| "loss": 0.6327, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.392857142857143, | |
| "grad_norm": 0.8817493915557861, | |
| "learning_rate": 1.246638473736378e-05, | |
| "loss": 0.5871, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 1.0448442697525024, | |
| "learning_rate": 1.1098212284078036e-05, | |
| "loss": 0.6083, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.4642857142857144, | |
| "grad_norm": 0.6664843559265137, | |
| "learning_rate": 9.800143481652979e-06, | |
| "loss": 0.8117, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.8378458023071289, | |
| "learning_rate": 8.574517537807897e-06, | |
| "loss": 0.8003, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5357142857142856, | |
| "grad_norm": 0.7771973013877869, | |
| "learning_rate": 7.423543113334436e-06, | |
| "loss": 0.7034, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.8301295638084412, | |
| "learning_rate": 6.349294341940593e-06, | |
| "loss": 0.6515, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.607142857142857, | |
| "grad_norm": 0.9299514293670654, | |
| "learning_rate": 5.353707092521582e-06, | |
| "loss": 0.4939, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.642857142857143, | |
| "grad_norm": 1.0564358234405518, | |
| "learning_rate": 4.43857548059321e-06, | |
| "loss": 0.4689, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.678571428571429, | |
| "grad_norm": 0.6848633885383606, | |
| "learning_rate": 3.605548635174533e-06, | |
| "loss": 0.83, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 0.7416503429412842, | |
| "learning_rate": 2.85612772694579e-06, | |
| "loss": 0.7841, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 0.7347410917282104, | |
| "learning_rate": 2.191663263037458e-06, | |
| "loss": 0.741, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.7857142857142856, | |
| "grad_norm": 0.7589361667633057, | |
| "learning_rate": 1.6133526533250565e-06, | |
| "loss": 0.5824, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.821428571428571, | |
| "grad_norm": 0.964680016040802, | |
| "learning_rate": 1.1222380526156928e-06, | |
| "loss": 0.6366, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.945676863193512, | |
| "learning_rate": 7.192044826145771e-07, | |
| "loss": 0.4343, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.892857142857143, | |
| "grad_norm": 0.6502677202224731, | |
| "learning_rate": 4.049782370561583e-07, | |
| "loss": 0.8532, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.928571428571429, | |
| "grad_norm": 0.7305717468261719, | |
| "learning_rate": 1.8012557287367392e-07, | |
| "loss": 0.7416, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.9642857142857144, | |
| "grad_norm": 0.7641732692718506, | |
| "learning_rate": 4.5051689765929214e-08, | |
| "loss": 0.5735, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.0511471033096313, | |
| "learning_rate": 0.0, | |
| "loss": 0.5306, | |
| "step": 84 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 84, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3114639925221786e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |