Instructions to use dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("echarlaix/tiny-random-mistral") model = PeftModel.from_pretrained(base_model, "dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0: direct link, hf CLI and curl.
- Browser
- Download file 3.08 kB
-
https://huggingface.co/dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/dimasik87/4d203fd0-5ccd-4671-89b2-ae0d228f8de0/resolve/main/last-checkpoint/trainer_state.json
3.08 kB
Invalid JSON:Unexpected token 'N', ..."al_loss": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012084105373398855, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.028035124466285e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.5308, | |
| "eval_samples_per_second": 257.928, | |
| "eval_steps_per_second": 128.964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012084105373398856, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024168210746797713, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003222428099573028, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.2483, | |
| "eval_samples_per_second": 266.355, | |
| "eval_steps_per_second": 133.178, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003625231612019657, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00048336421493595425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006042052686699428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006444856199146056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.5041, | |
| "eval_samples_per_second": 264.631, | |
| "eval_steps_per_second": 132.315, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007250463224039314, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008458873761379199, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009667284298719085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009667284298719085, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.5465, | |
| "eval_samples_per_second": 264.347, | |
| "eval_steps_per_second": 132.174, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010875694836058971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1550057472000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |