Instructions to use antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-2b-it") model = PeftModel.from_pretrained(base_model, "antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d: direct link, hf CLI and curl.
- Browser
- Download file 11 kB
-
https://huggingface.co/antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d/resolve/main/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/antimage88/395d9bb7-52e4-475e-8a8c-5638ca879a6d/resolve/main/last-checkpoint/trainer_state.json
11 kB
| { | |
| "best_metric": 1.1817097663879395, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 5.714753150939941, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "eval_loss": 2.4003829956054688, | |
| "eval_runtime": 1.4264, | |
| "eval_samples_per_second": 22.434, | |
| "eval_steps_per_second": 5.608, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 7.170670986175537, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2306, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 7.550725936889648, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4062, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 6.948938846588135, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2318, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 6.083446502685547, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 5.913970470428467, | |
| "learning_rate": 6e-05, | |
| "loss": 1.371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 5.238213062286377, | |
| "learning_rate": 7e-05, | |
| "loss": 1.5717, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 5.236299991607666, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3621, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 2.496065378189087, | |
| "learning_rate": 9e-05, | |
| "loss": 1.143, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 2.8024847507476807, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 3.0046355724334717, | |
| "learning_rate": 9.988834393115767e-05, | |
| "loss": 1.2389, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 3.0082316398620605, | |
| "learning_rate": 9.9553874407739e-05, | |
| "loss": 1.2786, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 2.118980646133423, | |
| "learning_rate": 9.899808525182935e-05, | |
| "loss": 1.2954, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 2.031477689743042, | |
| "learning_rate": 9.822345875271883e-05, | |
| "loss": 0.9797, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 2.3263585567474365, | |
| "learning_rate": 9.723345458039594e-05, | |
| "loss": 1.2429, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.6109251976013184, | |
| "learning_rate": 9.603249433382144e-05, | |
| "loss": 1.2715, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 1.9126944541931152, | |
| "learning_rate": 9.462594179299406e-05, | |
| "loss": 1.109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 1.9470820426940918, | |
| "learning_rate": 9.302007896300698e-05, | |
| "loss": 0.8364, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.2464423179626465, | |
| "learning_rate": 9.122207801708802e-05, | |
| "loss": 1.1474, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 1.3209232091903687, | |
| "learning_rate": 8.923996926393305e-05, | |
| "loss": 0.9024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 1.6488995552062988, | |
| "learning_rate": 8.708260528239788e-05, | |
| "loss": 0.8782, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 1.6716432571411133, | |
| "learning_rate": 8.475962138373213e-05, | |
| "loss": 0.8521, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 2.1739349365234375, | |
| "learning_rate": 8.228139257794012e-05, | |
| "loss": 0.9933, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 1.4730769395828247, | |
| "learning_rate": 7.965898723646776e-05, | |
| "loss": 0.7727, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 1.5656155347824097, | |
| "learning_rate": 7.690411765816864e-05, | |
| "loss": 0.8817, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 2.1506686210632324, | |
| "learning_rate": 7.402908775933419e-05, | |
| "loss": 1.0105, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 2.0018692016601562, | |
| "learning_rate": 7.104673812141675e-05, | |
| "loss": 0.7928, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 1.695372223854065, | |
| "learning_rate": 6.797038864187564e-05, | |
| "loss": 0.8946, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 1.8244125843048096, | |
| "learning_rate": 6.481377904428171e-05, | |
| "loss": 0.8284, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 1.7244329452514648, | |
| "learning_rate": 6.159100751337642e-05, | |
| "loss": 0.7186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 2.0243990421295166, | |
| "learning_rate": 5.831646772915651e-05, | |
| "loss": 0.8093, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 1.6297742128372192, | |
| "learning_rate": 5.5004784581204927e-05, | |
| "loss": 0.8709, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 1.8952237367630005, | |
| "learning_rate": 5.167074885038373e-05, | |
| "loss": 0.8952, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 1.7852932214736938, | |
| "learning_rate": 4.832925114961629e-05, | |
| "loss": 0.7839, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 2.1525204181671143, | |
| "learning_rate": 4.4995215418795085e-05, | |
| "loss": 0.8763, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 1.8198322057724, | |
| "learning_rate": 4.1683532270843504e-05, | |
| "loss": 0.8486, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 1.5310567617416382, | |
| "learning_rate": 3.840899248662358e-05, | |
| "loss": 0.5251, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.179245710372925, | |
| "learning_rate": 3.5186220955718306e-05, | |
| "loss": 0.8381, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 1.1245640516281128, | |
| "learning_rate": 3.202961135812437e-05, | |
| "loss": 0.6164, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 1.41566002368927, | |
| "learning_rate": 2.895326187858326e-05, | |
| "loss": 0.6059, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 1.5508769750595093, | |
| "learning_rate": 2.5970912240665813e-05, | |
| "loss": 0.6455, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 1.7090671062469482, | |
| "learning_rate": 2.3095882341831372e-05, | |
| "loss": 0.5792, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 1.374485731124878, | |
| "learning_rate": 2.0341012763532243e-05, | |
| "loss": 0.6782, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 1.590584397315979, | |
| "learning_rate": 1.771860742205988e-05, | |
| "loss": 0.7556, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 1.459409236907959, | |
| "learning_rate": 1.5240378616267886e-05, | |
| "loss": 0.4689, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 1.5467756986618042, | |
| "learning_rate": 1.2917394717602121e-05, | |
| "loss": 0.4195, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 1.3657021522521973, | |
| "learning_rate": 1.0760030736066951e-05, | |
| "loss": 0.4721, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 1.7539397478103638, | |
| "learning_rate": 8.777921982911996e-06, | |
| "loss": 0.5767, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 1.5453059673309326, | |
| "learning_rate": 6.979921036993042e-06, | |
| "loss": 0.6237, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 2.2058823108673096, | |
| "learning_rate": 5.374058207005944e-06, | |
| "loss": 0.6392, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "eval_loss": 1.1817097663879395, | |
| "eval_runtime": 1.4393, | |
| "eval_samples_per_second": 22.234, | |
| "eval_steps_per_second": 5.558, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 1.3148783445358276, | |
| "learning_rate": 3.967505666178556e-06, | |
| "loss": 0.5752, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 1.693260669708252, | |
| "learning_rate": 2.7665454196040664e-06, | |
| "loss": 0.5934, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 1.6923569440841675, | |
| "learning_rate": 1.7765412472811771e-06, | |
| "loss": 0.6168, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 1.6930750608444214, | |
| "learning_rate": 1.0019147481706625e-06, | |
| "loss": 0.5091, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 1.4638423919677734, | |
| "learning_rate": 4.461255922609986e-07, | |
| "loss": 0.634, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 1.329147219657898, | |
| "learning_rate": 1.1165606884234181e-07, | |
| "loss": 0.4201, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.8009886741638184, | |
| "learning_rate": 0.0, | |
| "loss": 0.5192, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 57, | |
| "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": 2.338589547115315e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |