Instructions to use 1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use 1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("peft-internal-testing/tiny-dummy-qwen2") model = PeftModel.from_pretrained(base_model, "1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from 1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35: direct link, hf CLI and curl.
- Browser
- Download file 10.4 kB
-
https://huggingface.co/1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/1-lock/aba53603-c1e7-44b1-a8d2-a464157f7d35/resolve/main/last-checkpoint/trainer_state.json
10.4 kB
| { | |
| "best_metric": 11.92679214477539, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12463000467362517, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "grad_norm": 0.01624242402613163, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024926000934725034, | |
| "eval_loss": 11.928278923034668, | |
| "eval_runtime": 0.2062, | |
| "eval_samples_per_second": 242.507, | |
| "eval_steps_per_second": 63.052, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004985200186945007, | |
| "grad_norm": 0.019356613978743553, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9314, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00747780028041751, | |
| "grad_norm": 0.018038224428892136, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9318, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009970400373890013, | |
| "grad_norm": 0.017358308658003807, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9319, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012463000467362517, | |
| "grad_norm": 0.01515874546021223, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9319, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01495560056083502, | |
| "grad_norm": 0.016358934342861176, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017448200654307525, | |
| "grad_norm": 0.01606920175254345, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9313, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019940800747780027, | |
| "grad_norm": 0.018448540940880775, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9309, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022433400841252532, | |
| "grad_norm": 0.016899872571229935, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9305, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024926000934725034, | |
| "grad_norm": 0.01905122771859169, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.93, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02741860102819754, | |
| "grad_norm": 0.02314680814743042, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9266, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02991120112167004, | |
| "grad_norm": 0.03203649818897247, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9281, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032403801215142546, | |
| "grad_norm": 0.017591670155525208, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9318, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03489640130861505, | |
| "grad_norm": 0.017415422946214676, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9314, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037389001402087556, | |
| "grad_norm": 0.018619945272803307, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9316, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039881601495560054, | |
| "grad_norm": 0.019837915897369385, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9308, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04237420158903256, | |
| "grad_norm": 0.019587306305766106, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.044866801682505064, | |
| "grad_norm": 0.018927328288555145, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04735940177597757, | |
| "grad_norm": 0.01774817332625389, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9306, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04985200186945007, | |
| "grad_norm": 0.01934223063290119, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.93, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05234460196292257, | |
| "grad_norm": 0.016140593215823174, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9306, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05483720205639508, | |
| "grad_norm": 0.01889203116297722, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9299, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05732980214986758, | |
| "grad_norm": 0.02152014896273613, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9289, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05982240224334008, | |
| "grad_norm": 0.026987668126821518, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9276, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "grad_norm": 0.05688172206282616, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.062315002336812586, | |
| "eval_loss": 11.927356719970703, | |
| "eval_runtime": 0.1999, | |
| "eval_samples_per_second": 250.105, | |
| "eval_steps_per_second": 65.027, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06480760243028509, | |
| "grad_norm": 0.027307763695716858, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9309, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0673002025237576, | |
| "grad_norm": 0.02421778067946434, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9311, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0697928026172301, | |
| "grad_norm": 0.02540089190006256, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9309, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0722854027107026, | |
| "grad_norm": 0.019033024087548256, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.931, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07477800280417511, | |
| "grad_norm": 0.02582223154604435, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0772706028976476, | |
| "grad_norm": 0.027421683073043823, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9311, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07976320299112011, | |
| "grad_norm": 0.0327715128660202, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9297, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08225580308459261, | |
| "grad_norm": 0.02419387362897396, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9295, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08474840317806512, | |
| "grad_norm": 0.023017315194010735, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9282, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08724100327153762, | |
| "grad_norm": 0.0338151752948761, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08973360336501013, | |
| "grad_norm": 0.02851535566151142, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9279, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09222620345848263, | |
| "grad_norm": 0.04185821861028671, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.929, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09471880355195514, | |
| "grad_norm": 0.03193657100200653, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.931, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09721140364542763, | |
| "grad_norm": 0.03217791020870209, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9304, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09970400373890013, | |
| "grad_norm": 0.031128505244851112, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9307, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10219660383237264, | |
| "grad_norm": 0.03158225491642952, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9304, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10468920392584515, | |
| "grad_norm": 0.034790318459272385, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10718180401931765, | |
| "grad_norm": 0.037614643573760986, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9298, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10967440411279016, | |
| "grad_norm": 0.03061523847281933, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9292, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11216700420626266, | |
| "grad_norm": 0.03246842697262764, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9296, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11465960429973517, | |
| "grad_norm": 0.02890903502702713, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9288, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11715220439320767, | |
| "grad_norm": 0.026723528280854225, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9302, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11964480448668016, | |
| "grad_norm": 0.027072373777627945, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9284, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.04512767866253853, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9276, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "grad_norm": 0.051480695605278015, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9278, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12463000467362517, | |
| "eval_loss": 11.92679214477539, | |
| "eval_runtime": 0.1966, | |
| "eval_samples_per_second": 254.37, | |
| "eval_steps_per_second": 66.136, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |