Instructions to use aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") model = PeftModel.from_pretrained(base_model, "aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2: direct link, hf CLI and curl.
- Browser
- Download file 9.9 kB
-
https://huggingface.co/aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2/resolve/fe6d01c373008451ca456cbc1c2b1c221acf8e33/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2@fe6d01c373008451ca456cbc1c2b1c221acf8e33/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/aleegis10/0aa7975a-2431-4f55-be8e-d7b2eb6326f2/resolve/fe6d01c373008451ca456cbc1c2b1c221acf8e33/last-checkpoint/trainer_state.json
9.9 kB
| { | |
| "best_metric": 0.745703935623169, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1558846453624318, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003117692907248636, | |
| "grad_norm": 11.655372619628906, | |
| "learning_rate": 1e-05, | |
| "loss": 9.4725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003117692907248636, | |
| "eval_loss": 2.0170581340789795, | |
| "eval_runtime": 19.8075, | |
| "eval_samples_per_second": 27.262, | |
| "eval_steps_per_second": 6.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006235385814497272, | |
| "grad_norm": 13.125012397766113, | |
| "learning_rate": 2e-05, | |
| "loss": 11.8029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009353078721745909, | |
| "grad_norm": 12.141226768493652, | |
| "learning_rate": 3e-05, | |
| "loss": 11.4664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012470771628994544, | |
| "grad_norm": 14.667614936828613, | |
| "learning_rate": 4e-05, | |
| "loss": 12.0023, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01558846453624318, | |
| "grad_norm": 12.08423137664795, | |
| "learning_rate": 5e-05, | |
| "loss": 10.5206, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018706157443491817, | |
| "grad_norm": 11.249734878540039, | |
| "learning_rate": 6e-05, | |
| "loss": 9.5772, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021823850350740453, | |
| "grad_norm": 22.513164520263672, | |
| "learning_rate": 7e-05, | |
| "loss": 9.5923, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02494154325798909, | |
| "grad_norm": 18.979618072509766, | |
| "learning_rate": 8e-05, | |
| "loss": 9.3301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028059236165237724, | |
| "grad_norm": 29.20528221130371, | |
| "learning_rate": 9e-05, | |
| "loss": 10.607, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03117692907248636, | |
| "grad_norm": 25.135574340820312, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5226, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.034294621979735, | |
| "grad_norm": 15.285947799682617, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 8.4817, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.037412314886983634, | |
| "grad_norm": 15.414291381835938, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 7.4645, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04053000779423227, | |
| "grad_norm": 13.062957763671875, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 5.7704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.043647700701480906, | |
| "grad_norm": 13.44833755493164, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 6.9123, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04676539360872954, | |
| "grad_norm": 12.443500518798828, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 5.7389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04988308651597818, | |
| "grad_norm": 12.959155082702637, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 5.9033, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05300077942322681, | |
| "grad_norm": 9.476544380187988, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 5.9961, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05611847233047545, | |
| "grad_norm": 11.186797142028809, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 5.6498, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.059236165237724084, | |
| "grad_norm": 11.144340515136719, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 5.4165, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06235385814497272, | |
| "grad_norm": 12.207180976867676, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 6.3502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06547155105222136, | |
| "grad_norm": 12.063061714172363, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 5.482, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06858924395947, | |
| "grad_norm": 13.639694213867188, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 5.8621, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07170693686671863, | |
| "grad_norm": 10.871453285217285, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 5.3057, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07482462977396727, | |
| "grad_norm": 11.467005729675293, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 4.4601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0779423226812159, | |
| "grad_norm": 11.330914497375488, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 4.9252, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08106001558846454, | |
| "grad_norm": 11.97061538696289, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 4.8823, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08417770849571317, | |
| "grad_norm": 13.585055351257324, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 5.3709, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08729540140296181, | |
| "grad_norm": 13.680033683776855, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 5.6623, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09041309431021044, | |
| "grad_norm": 14.604742050170898, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.3659, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09353078721745908, | |
| "grad_norm": 13.014104843139648, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 5.0338, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09664848012470771, | |
| "grad_norm": 13.416587829589844, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 4.5345, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09976617303195635, | |
| "grad_norm": 13.330890655517578, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 4.7284, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10288386593920498, | |
| "grad_norm": 14.181489944458008, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.1683, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10600155884645363, | |
| "grad_norm": 14.32101058959961, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 4.4735, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10911925175370225, | |
| "grad_norm": 11.41262435913086, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 4.555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1122369446609509, | |
| "grad_norm": 11.651115417480469, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 4.3732, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11535463756819954, | |
| "grad_norm": 10.54432487487793, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 4.2542, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11847233047544817, | |
| "grad_norm": 13.021109580993652, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 4.5108, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12159002338269681, | |
| "grad_norm": 13.503449440002441, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 4.2284, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12470771628994544, | |
| "grad_norm": 13.191174507141113, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 4.2834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12782540919719407, | |
| "grad_norm": 12.584697723388672, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.8461, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1309431021044427, | |
| "grad_norm": 14.472663879394531, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.8354, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13406079501169135, | |
| "grad_norm": 12.175851821899414, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.9488, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13717848791894, | |
| "grad_norm": 28.482507705688477, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.8271, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1402961808261886, | |
| "grad_norm": 18.594249725341797, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 4.1931, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14341387373343725, | |
| "grad_norm": 15.749979019165039, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.1982, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1465315666406859, | |
| "grad_norm": 20.301923751831055, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 4.3817, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14964925954793454, | |
| "grad_norm": 13.996861457824707, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.1606, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15276695245518315, | |
| "grad_norm": 19.21599006652832, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 4.6406, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1558846453624318, | |
| "grad_norm": 19.336666107177734, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 4.3495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1558846453624318, | |
| "eval_loss": 0.745703935623169, | |
| "eval_runtime": 20.391, | |
| "eval_samples_per_second": 26.482, | |
| "eval_steps_per_second": 6.621, | |
| "step": 50 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.92427982176256e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |