Instructions to use cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("fxmarty/tiny-llama-fast-tokenizer") model = PeftModel.from_pretrained(base_model, "cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6: direct link, hf CLI and curl.
- Browser
- Download file 10 kB
-
https://huggingface.co/cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6/resolve/eeb85ae81a7e7c01a8b9556cd5bd6fc71e5f2d80/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6@eeb85ae81a7e7c01a8b9556cd5bd6fc71e5f2d80/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/cimol/3815d577-e401-4bcc-9b7f-fff1f2f8bac6/resolve/eeb85ae81a7e7c01a8b9556cd5bd6fc71e5f2d80/last-checkpoint/trainer_state.json
10 kB
| { | |
| "best_metric": 10.351482391357422, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0846740050804403, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001693480101608806, | |
| "grad_norm": 0.05767215043306351, | |
| "learning_rate": 7e-06, | |
| "loss": 10.3761, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001693480101608806, | |
| "eval_loss": 10.376470565795898, | |
| "eval_runtime": 2.2633, | |
| "eval_samples_per_second": 439.62, | |
| "eval_steps_per_second": 110.016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 0.05682261288166046, | |
| "learning_rate": 1.4e-05, | |
| "loss": 10.3756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005080440304826418, | |
| "grad_norm": 0.05533347651362419, | |
| "learning_rate": 2.1e-05, | |
| "loss": 10.3759, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 0.06400913745164871, | |
| "learning_rate": 2.8e-05, | |
| "loss": 10.3753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00846740050804403, | |
| "grad_norm": 0.06217538192868233, | |
| "learning_rate": 3.5e-05, | |
| "loss": 10.3766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "grad_norm": 0.059953831136226654, | |
| "learning_rate": 4.2e-05, | |
| "loss": 10.3753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011854360711261643, | |
| "grad_norm": 0.06322812288999557, | |
| "learning_rate": 4.899999999999999e-05, | |
| "loss": 10.3751, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013547840812870448, | |
| "grad_norm": 0.06448973715305328, | |
| "learning_rate": 5.6e-05, | |
| "loss": 10.3755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015241320914479255, | |
| "grad_norm": 0.06553128361701965, | |
| "learning_rate": 6.3e-05, | |
| "loss": 10.3754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01693480101608806, | |
| "grad_norm": 0.06717841327190399, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018628281117696866, | |
| "grad_norm": 0.06435838341712952, | |
| "learning_rate": 6.999521567473641e-05, | |
| "loss": 10.3753, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02032176121930567, | |
| "grad_norm": 0.06390493363142014, | |
| "learning_rate": 6.998086400693241e-05, | |
| "loss": 10.3744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02201524132091448, | |
| "grad_norm": 0.06731149554252625, | |
| "learning_rate": 6.995694892019065e-05, | |
| "loss": 10.3745, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023708721422523286, | |
| "grad_norm": 0.08515335619449615, | |
| "learning_rate": 6.99234769526571e-05, | |
| "loss": 10.3737, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02540220152413209, | |
| "grad_norm": 0.08068357408046722, | |
| "learning_rate": 6.988045725523343e-05, | |
| "loss": 10.3727, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027095681625740897, | |
| "grad_norm": 0.08304785192012787, | |
| "learning_rate": 6.982790158907539e-05, | |
| "loss": 10.3722, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028789161727349702, | |
| "grad_norm": 0.08605454862117767, | |
| "learning_rate": 6.976582432237733e-05, | |
| "loss": 10.3725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03048264182895851, | |
| "grad_norm": 0.0890476256608963, | |
| "learning_rate": 6.969424242644413e-05, | |
| "loss": 10.3728, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03217612193056731, | |
| "grad_norm": 0.09603014588356018, | |
| "learning_rate": 6.961317547105138e-05, | |
| "loss": 10.3707, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03386960203217612, | |
| "grad_norm": 0.09333094954490662, | |
| "learning_rate": 6.952264561909527e-05, | |
| "loss": 10.3714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03556308213378493, | |
| "grad_norm": 0.11809182167053223, | |
| "learning_rate": 6.942267762053337e-05, | |
| "loss": 10.3699, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03725656223539373, | |
| "grad_norm": 0.12310867756605148, | |
| "learning_rate": 6.931329880561832e-05, | |
| "loss": 10.3696, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03895004233700254, | |
| "grad_norm": 0.12797869741916656, | |
| "learning_rate": 6.919453907742597e-05, | |
| "loss": 10.3694, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04064352243861134, | |
| "grad_norm": 0.14211532473564148, | |
| "learning_rate": 6.90664309036802e-05, | |
| "loss": 10.3684, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04233700254022015, | |
| "grad_norm": 0.13544224202632904, | |
| "learning_rate": 6.892900930787656e-05, | |
| "loss": 10.3687, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04403048264182896, | |
| "grad_norm": 0.15587803721427917, | |
| "learning_rate": 6.87823118597072e-05, | |
| "loss": 10.3667, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04572396274343776, | |
| "grad_norm": 0.15392404794692993, | |
| "learning_rate": 6.862637866478969e-05, | |
| "loss": 10.3679, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04741744284504657, | |
| "grad_norm": 0.15195734798908234, | |
| "learning_rate": 6.846125235370252e-05, | |
| "loss": 10.3674, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04911092294665537, | |
| "grad_norm": 0.1591203212738037, | |
| "learning_rate": 6.828697807033038e-05, | |
| "loss": 10.3646, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05080440304826418, | |
| "grad_norm": 0.17264410853385925, | |
| "learning_rate": 6.81036034595222e-05, | |
| "loss": 10.3642, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05249788314987299, | |
| "grad_norm": 0.1709284484386444, | |
| "learning_rate": 6.791117865406564e-05, | |
| "loss": 10.3635, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05419136325148179, | |
| "grad_norm": 0.17630036175251007, | |
| "learning_rate": 6.770975626098112e-05, | |
| "loss": 10.365, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0558848433530906, | |
| "grad_norm": 0.1866825520992279, | |
| "learning_rate": 6.749939134713974e-05, | |
| "loss": 10.3628, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.057578323454699404, | |
| "grad_norm": 0.17809787392616272, | |
| "learning_rate": 6.728014142420846e-05, | |
| "loss": 10.3629, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05927180355630821, | |
| "grad_norm": 0.20281663537025452, | |
| "learning_rate": 6.7052066432927e-05, | |
| "loss": 10.3578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06096528365791702, | |
| "grad_norm": 0.19204723834991455, | |
| "learning_rate": 6.681522872672069e-05, | |
| "loss": 10.3585, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06265876375952582, | |
| "grad_norm": 0.1810905933380127, | |
| "learning_rate": 6.656969305465356e-05, | |
| "loss": 10.3592, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06435224386113463, | |
| "grad_norm": 0.19030340015888214, | |
| "learning_rate": 6.631552654372672e-05, | |
| "loss": 10.3601, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06604572396274344, | |
| "grad_norm": 0.16998638212680817, | |
| "learning_rate": 6.60527986805264e-05, | |
| "loss": 10.3573, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06773920406435224, | |
| "grad_norm": 0.1517295241355896, | |
| "learning_rate": 6.578158129222711e-05, | |
| "loss": 10.3549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06943268416596104, | |
| "grad_norm": 0.15249769389629364, | |
| "learning_rate": 6.550194852695469e-05, | |
| "loss": 10.3559, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07112616426756986, | |
| "grad_norm": 0.15435636043548584, | |
| "learning_rate": 6.521397683351509e-05, | |
| "loss": 10.354, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07281964436917866, | |
| "grad_norm": 0.14684386551380157, | |
| "learning_rate": 6.491774494049386e-05, | |
| "loss": 10.355, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07451312447078746, | |
| "grad_norm": 0.15682685375213623, | |
| "learning_rate": 6.461333383473272e-05, | |
| "loss": 10.3522, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07620660457239628, | |
| "grad_norm": 0.14739371836185455, | |
| "learning_rate": 6.430082673918849e-05, | |
| "loss": 10.3518, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07790008467400508, | |
| "grad_norm": 0.14083759486675262, | |
| "learning_rate": 6.398030909018069e-05, | |
| "loss": 10.3527, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07959356477561388, | |
| "grad_norm": 0.11909397691488266, | |
| "learning_rate": 6.365186851403423e-05, | |
| "loss": 10.3539, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08128704487722269, | |
| "grad_norm": 0.11432235687971115, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 10.3531, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0829805249788315, | |
| "grad_norm": 0.13134874403476715, | |
| "learning_rate": 6.297157989132236e-05, | |
| "loss": 10.3544, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "grad_norm": 0.19639384746551514, | |
| "learning_rate": 6.261991782887377e-05, | |
| "loss": 10.3542, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "eval_loss": 10.351482391357422, | |
| "eval_runtime": 2.2614, | |
| "eval_samples_per_second": 439.995, | |
| "eval_steps_per_second": 110.109, | |
| "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": 4, | |
| "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": 5744859021312.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |