| [TRAIN] Qwen2.5-0.5B-Instruct / yelp_polarity |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7303, 'grad_norm': 4.7769694328308105, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.7849, 'grad_norm': 0.8657419085502625, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.2527, 'grad_norm': 0.6747444272041321, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 17.0597, 'train_samples_per_second': 46.894, 'train_steps_per_second': 5.862, 'train_loss': 2.5282428288459777, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / yelp_polarity |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1805, 'grad_norm': 2.5839781761169434, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.741, 'grad_norm': 0.8343231678009033, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.1358, 'grad_norm': 0.7408742308616638, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 23.9512, 'train_samples_per_second': 33.401, 'train_steps_per_second': 4.175, 'train_loss': 2.452775387763977, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / yahoo_topics |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.5828, 'grad_norm': 7.462729454040527, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.69, 'grad_norm': 1.3501135110855103, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.6278, 'grad_norm': 0.7101731300354004, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.1499, 'train_samples_per_second': 71.749, 'train_steps_per_second': 8.969, 'train_loss': 1.1778222179412843, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / yahoo_topics |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.0504, 'grad_norm': 3.948367118835449, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.6769, 'grad_norm': 0.8289307951927185, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.719, 'grad_norm': 0.7602887153625488, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.0409, 'train_samples_per_second': 53.188, 'train_steps_per_second': 6.649, 'train_loss': 1.2217226791381837, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_qnli |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.6959, 'grad_norm': 7.206658840179443, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1738, 'grad_norm': 2.3098304271698, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.246, 'grad_norm': 0.8799184560775757, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 13.537, 'train_samples_per_second': 59.097, 'train_steps_per_second': 7.387, 'train_loss': 1.7251459455490112, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_qnli |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.3207, 'grad_norm': 3.4501419067382812, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.3036, 'grad_norm': 1.5148175954818726, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.3368, 'grad_norm': 0.8041808605194092, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 19.2885, 'train_samples_per_second': 41.476, 'train_steps_per_second': 5.184, 'train_loss': 1.840370125770569, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_mnli |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7572, 'grad_norm': 7.329052925109863, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.0955, 'grad_norm': 1.332726001739502, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1722, 'grad_norm': 1.0915731191635132, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 12.5607, 'train_samples_per_second': 63.691, 'train_steps_per_second': 7.961, 'train_loss': 1.6504256796836854, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_mnli |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.5361, 'grad_norm': 3.802908182144165, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.3165, 'grad_norm': 1.068376064300537, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.3286, 'grad_norm': 1.183143973350525, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 17.7105, 'train_samples_per_second': 45.171, 'train_steps_per_second': 5.646, 'train_loss': 1.8447417879104615, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_rte |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7704, 'grad_norm': 6.176489353179932, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.245, 'grad_norm': 1.4168987274169922, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.5001, 'grad_norm': 0.8886827826499939, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.8692, 'train_samples_per_second': 50.412, 'train_steps_per_second': 6.301, 'train_loss': 1.8877661609649659, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_rte |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.3427, 'grad_norm': 3.0718681812286377, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.3075, 'grad_norm': 0.8789539337158203, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.5508, 'grad_norm': 0.8922062516212463, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 22.9748, 'train_samples_per_second': 34.821, 'train_steps_per_second': 4.353, 'train_loss': 1.9495039463043213, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_mrpc |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.5646, 'grad_norm': 6.482349872589111, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1609, 'grad_norm': 1.498671054840088, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1077, 'grad_norm': 1.2300711870193481, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 12.675, 'train_samples_per_second': 63.116, 'train_steps_per_second': 7.89, 'train_loss': 1.6482944440841676, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_mrpc |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1908, 'grad_norm': 3.27897572517395, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2278, 'grad_norm': 1.3972417116165161, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1679, 'grad_norm': 1.1495029926300049, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 17.4505, 'train_samples_per_second': 45.844, 'train_steps_per_second': 5.73, 'train_loss': 1.7174697971343995, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_qqp |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2107, 'grad_norm': 9.564720153808594, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1536, 'grad_norm': 2.2898943424224854, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9036, 'grad_norm': 1.9666653871536255, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.0988, 'train_samples_per_second': 72.08, 'train_steps_per_second': 9.01, 'train_loss': 1.5491774892807006, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_qqp |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.8175, 'grad_norm': 4.59446907043457, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2373, 'grad_norm': 1.7829301357269287, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0236, 'grad_norm': 0.9115185141563416, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 14.7927, 'train_samples_per_second': 54.081, 'train_steps_per_second': 6.76, 'train_loss': 1.656243953704834, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / snli_main |
| FAIL snli_main: 'NoneType' object is not subscriptable |
| [TRAIN] Qwen2.5-0.5B-Instruct / paws |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.5934, 'grad_norm': 6.102503776550293, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.9913, 'grad_norm': 2.3907556533813477, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9893, 'grad_norm': 1.0990138053894043, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 12.8257, 'train_samples_per_second': 62.375, 'train_steps_per_second': 7.797, 'train_loss': 1.5063319826126098, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / paws |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1323, 'grad_norm': 3.2562813758850098, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.0692, 'grad_norm': 1.2330275774002075, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0592, 'grad_norm': 1.0995728969573975, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 18.2495, 'train_samples_per_second': 43.837, 'train_steps_per_second': 5.48, 'train_loss': 1.5848482275009155, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / mteb_emo |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.8069, 'grad_norm': 8.230766296386719, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8378, 'grad_norm': 1.1878981590270996, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.8893, 'grad_norm': 0.9681587219238281, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 10.9856, 'train_samples_per_second': 72.823, 'train_steps_per_second': 9.103, 'train_loss': 1.3832484269142151, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / mteb_emo |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.3094, 'grad_norm': 4.186059951782227, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8931, 'grad_norm': 0.6450718641281128, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9777, 'grad_norm': 0.8589568734169006, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.2721, 'train_samples_per_second': 52.383, 'train_steps_per_second': 6.548, 'train_loss': 1.4595746660232545, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / mteb_tweet_sent |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.174, 'grad_norm': 9.287677764892578, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1783, 'grad_norm': 1.6081738471984863, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0981, 'grad_norm': 1.098804235458374, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 10.0871, 'train_samples_per_second': 79.309, 'train_steps_per_second': 9.914, 'train_loss': 1.6581892824172975, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / mteb_tweet_sent |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.9047, 'grad_norm': 4.823108673095703, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2931, 'grad_norm': 0.8228617906570435, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1957, 'grad_norm': 1.1062841415405273, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 13.3568, 'train_samples_per_second': 59.895, 'train_steps_per_second': 7.487, 'train_loss': 1.770520305633545, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / mteb_toxic_conv |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.8327, 'grad_norm': 5.095354080200195, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.7047, 'grad_norm': 1.2102032899856567, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.8282, 'grad_norm': 0.7912783622741699, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 16.1364, 'train_samples_per_second': 49.577, 'train_steps_per_second': 6.197, 'train_loss': 2.277755131721497, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / mteb_toxic_conv |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2113, 'grad_norm': 2.6563172340393066, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.6816, 'grad_norm': 0.9523308277130127, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.8255, 'grad_norm': 0.8748573660850525, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 23.3874, 'train_samples_per_second': 34.206, 'train_steps_per_second': 4.276, 'train_loss': 2.2688763523101807, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / mteb_amazon_cf |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.0523, 'grad_norm': 9.151971817016602, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1372, 'grad_norm': 1.455265998840332, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0694, 'grad_norm': 0.7700763940811157, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.0029, 'train_samples_per_second': 72.708, 'train_steps_per_second': 9.088, 'train_loss': 1.6224427938461303, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / mteb_amazon_cf |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.6138, 'grad_norm': 4.544278621673584, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1775, 'grad_norm': 0.9337619543075562, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1355, 'grad_norm': 0.723482072353363, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.2983, 'train_samples_per_second': 52.293, 'train_steps_per_second': 6.537, 'train_loss': 1.6808272743225097, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / dair_emo_unsplit |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.8074, 'grad_norm': 8.336443901062012, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8721, 'grad_norm': 1.2432242631912231, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.8747, 'grad_norm': 0.7010195851325989, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.1363, 'train_samples_per_second': 71.837, 'train_steps_per_second': 8.98, 'train_loss': 1.3927378106117247, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / dair_emo_unsplit |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2904, 'grad_norm': 4.192126750946045, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.9423, 'grad_norm': 0.7681553959846497, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9669, 'grad_norm': 0.8587647676467896, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.4846, 'train_samples_per_second': 51.664, 'train_steps_per_second': 6.458, 'train_loss': 1.4780806350708007, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_yelp_full |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7862, 'grad_norm': 5.573526382446289, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.7039, 'grad_norm': 0.8480653166770935, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.1478, 'grad_norm': 0.7421320676803589, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 16.8957, 'train_samples_per_second': 47.349, 'train_steps_per_second': 5.919, 'train_loss': 2.436655189990997, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_yelp_full |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1259, 'grad_norm': 2.8407199382781982, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.5924, 'grad_norm': 0.847999095916748, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.0286, 'grad_norm': 0.8495175838470459, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 24.3012, 'train_samples_per_second': 32.92, 'train_steps_per_second': 4.115, 'train_loss': 2.325834422111511, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_emotion |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.6796, 'grad_norm': 8.679558753967285, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8993, 'grad_norm': 1.4098697900772095, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.8971, 'grad_norm': 0.7674059271812439, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.0804, 'train_samples_per_second': 72.2, 'train_steps_per_second': 9.025, 'train_loss': 1.415963158607483, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_emotion |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2258, 'grad_norm': 4.511800765991211, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.9514, 'grad_norm': 0.8560807108879089, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9838, 'grad_norm': 0.7192825078964233, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.4355, 'train_samples_per_second': 51.829, 'train_steps_per_second': 6.479, 'train_loss': 1.4903493642807006, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_sst5_alt |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.8562, 'grad_norm': 7.73358154296875, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.058, 'grad_norm': 1.4864909648895264, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9958, 'grad_norm': 0.9336028695106506, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.1382, 'train_samples_per_second': 71.825, 'train_steps_per_second': 8.978, 'train_loss': 1.5448474097251892, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_sst5_alt |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.533, 'grad_norm': 4.299591541290283, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1324, 'grad_norm': 0.8781896829605103, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0859, 'grad_norm': 1.1681996583938599, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 14.9527, 'train_samples_per_second': 53.502, 'train_steps_per_second': 6.688, 'train_loss': 1.6331668090820313, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_student_qcat |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.222, 'grad_norm': 6.4504008293151855, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.7676, 'grad_norm': 1.245484471321106, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.9295, 'grad_norm': 0.9734070897102356, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 16.7493, 'train_samples_per_second': 47.763, 'train_steps_per_second': 5.97, 'train_loss': 1.3630782985687255, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_student_qcat |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.6534, 'grad_norm': 3.073930025100708, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8414, 'grad_norm': 1.0740983486175537, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0049, 'grad_norm': 0.8595083355903625, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 23.9597, 'train_samples_per_second': 33.389, 'train_steps_per_second': 4.174, 'train_loss': 1.4412736368179322, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / setfit_movie_reviews |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.3526, 'grad_norm': 8.657792091369629, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1798, 'grad_norm': 1.4296244382858276, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.1388, 'grad_norm': 1.635110855102539, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 10.5597, 'train_samples_per_second': 75.76, 'train_steps_per_second': 9.47, 'train_loss': 1.681065092086792, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / setfit_movie_reviews |
| Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:huggingface_hub.repocard:Repo card metadata block was not found. Setting CardData to empty. |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 5.0628, 'grad_norm': 4.693039894104004, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.3569, 'grad_norm': 1.6031795740127563, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.2367, 'grad_norm': 1.3692783117294312, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 13.7401, 'train_samples_per_second': 58.224, 'train_steps_per_second': 7.278, 'train_loss': 1.8238403606414795, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / sms_spam |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.6678, 'grad_norm': 9.387018203735352, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.5725, 'grad_norm': 2.320296049118042, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.3857, 'grad_norm': 0.8593599200248718, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.7612, 'train_samples_per_second': 68.02, 'train_steps_per_second': 8.503, 'train_loss': 2.0000625324249266, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / sms_spam |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 5.2133, 'grad_norm': 4.438594818115234, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.5525, 'grad_norm': 0.9178706407546997, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.4744, 'grad_norm': 0.9547106027603149, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.3862, 'train_samples_per_second': 51.995, 'train_steps_per_second': 6.499, 'train_loss': 2.040070538520813, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / snips |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7415, 'grad_norm': 6.773946762084961, 'learning_rate': 6.666666666666667e-05, 'epoch': 0.024390243902439025} |
| {'train_runtime': 5.0066, 'train_samples_per_second': 65.514, 'train_steps_per_second': 8.189, 'train_loss': 2.3904829083419425, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / snips |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2322, 'grad_norm': 3.6766297817230225, 'learning_rate': 6.666666666666667e-05, 'epoch': 0.024390243902439025} |
| {'train_runtime': 6.6162, 'train_samples_per_second': 49.575, 'train_steps_per_second': 6.197, 'train_loss': 2.2383127794033144, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / toxic_chat |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.2878, 'grad_norm': 11.425216674804688, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.1228, 'grad_norm': 1.2395150661468506, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.0886, 'grad_norm': 0.9984734058380127, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 14.4319, 'train_samples_per_second': 55.433, 'train_steps_per_second': 6.929, 'train_loss': 1.627325358390808, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / toxic_chat |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.9473, 'grad_norm': 5.387019157409668, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2314, 'grad_norm': 1.1496485471725464, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.2022, 'grad_norm': 1.3217898607254028, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 19.4465, 'train_samples_per_second': 41.138, 'train_steps_per_second': 5.142, 'train_loss': 1.7439907598495483, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / hate_offensive_lang |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1901, 'grad_norm': 7.31283712387085, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.4641, 'grad_norm': 1.5787039995193481, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.4027, 'grad_norm': 0.8544707894325256, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 11.7338, 'train_samples_per_second': 68.179, 'train_steps_per_second': 8.522, 'train_loss': 1.9506223344802855, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / hate_offensive_lang |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.7699, 'grad_norm': 3.9460268020629883, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.4483, 'grad_norm': 1.2194733619689941, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.4445, 'grad_norm': 0.9832725524902344, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 15.3135, 'train_samples_per_second': 52.242, 'train_steps_per_second': 6.53, 'train_loss': 1.969619345664978, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / amazon_massive_scenario |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7737, 'grad_norm': 6.923394203186035, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.8803, 'grad_norm': 3.135934829711914, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.3266, 'grad_norm': 0.7962337136268616, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 12.1362, 'train_samples_per_second': 65.919, 'train_steps_per_second': 8.24, 'train_loss': 1.1223828840255736, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / amazon_massive_scenario |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1677, 'grad_norm': 3.5334181785583496, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 1.7375, 'grad_norm': 0.7452163100242615, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 0.4004, 'grad_norm': 0.6548231840133667, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 16.2556, 'train_samples_per_second': 49.214, 'train_steps_per_second': 6.152, 'train_loss': 1.0932469034194947, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / trec_fine |
| The repository for CogComp/trec contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/CogComp/trec. |
| You can avoid this prompt in future by passing the argument `trust_remote_code=True`. |
|
|
| Do you wish to run the custom code? [y/N] FAIL trec_fine: The repository for CogComp/trec contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/CogComp/trec. |
| Please pass the argument `trust_remote_code=True` to allow custom code to be run. |
| [TRAIN] Qwen2.5-0.5B-Instruct / ag_setfit |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.999, 'grad_norm': 6.8160881996154785, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2971, 'grad_norm': 1.6471203565597534, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| FAIL ag_setfit: Loading this dataset requires you to execute custom code contained in the dataset repository on your local machine. Please set the option `trust_remote_code=True` to permit loading of this dataset. |
| [TRAIN] Qwen2.5-0.5B-Instruct / cardiffnlp_topic |
| FAIL cardiffnlp_topic: 'train' |
| [TRAIN] Qwen2.5-0.5B-Instruct / financial_pb_pos |
| The repository for takala/financial_phrasebank contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/takala/financial_phrasebank. |
| You can avoid this prompt in future by passing the argument `trust_remote_code=True`. |
|
|
| Do you wish to run the custom code? [y/N] FAIL financial_pb_pos: The repository for takala/financial_phrasebank contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/takala/financial_phrasebank. |
| Please pass the argument `trust_remote_code=True` to allow custom code to be run. |
| [TRAIN] Qwen2.5-0.5B-Instruct / clinc_small_skip |
| FAIL clinc_small_skip: 'NoneType' object is not iterable |
| [TRAIN] Qwen2.5-0.5B-Instruct / hate_speech18 |
| The repository for hate_speech18 contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/hate_speech18. |
| You can avoid this prompt in future by passing the argument `trust_remote_code=True`. |
|
|
| Do you wish to run the custom code? [y/N] FAIL hate_speech18: The repository for hate_speech18 contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/hate_speech18. |
| Please pass the argument `trust_remote_code=True` to allow custom code to be run. |
| [TRAIN] Qwen2.5-0.5B-Instruct / rotten_alt |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.433, 'grad_norm': 9.2361478805542, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.2875, 'grad_norm': 1.727787733078003, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.2166, 'grad_norm': 0.9453311562538147, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 10.2424, 'train_samples_per_second': 78.106, 'train_steps_per_second': 9.763, 'train_loss': 1.7735167932510376, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / rotten_alt |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 5.0912, 'grad_norm': 4.759712219238281, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.4038, 'grad_norm': 1.4830732345581055, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 1.2859, 'grad_norm': 1.2477036714553833, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 13.9507, 'train_samples_per_second': 57.345, 'train_steps_per_second': 7.168, 'train_loss': 1.871756911277771, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / yelp_polarity_test |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 3.7862, 'grad_norm': 5.573526382446289, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.7039, 'grad_norm': 0.8480653166770935, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.1478, 'grad_norm': 0.7421320676803589, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 17.1604, 'train_samples_per_second': 46.619, 'train_steps_per_second': 5.827, 'train_loss': 2.436655189990997, 'epoch': 1.0} |
| [TRAIN] Llama-3.2-1B-Instruct / yelp_polarity_test |
| WARNING:accelerate.utils.other:Detected kernel version 4.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| {'loss': 4.1259, 'grad_norm': 2.8407199382781982, 'learning_rate': 4e-05, 'epoch': 0.01} |
| {'loss': 2.5924, 'grad_norm': 0.847999095916748, 'learning_rate': 0.00010825793454723325, 'epoch': 0.5} |
| {'loss': 2.0286, 'grad_norm': 0.8495175838470459, 'learning_rate': 0.0, 'epoch': 1.0} |
| {'train_runtime': 24.3883, 'train_samples_per_second': 32.803, 'train_steps_per_second': 4.1, 'train_loss': 2.325834422111511, 'epoch': 1.0} |
| [TRAIN] Qwen2.5-0.5B-Instruct / dynasent_r1 |
| The repository for dynabench/dynasent contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/dynabench/dynasent. |
| You can avoid this prompt in future by passing the argument `trust_remote_code=True`. |
|
|
| Do you wish to run the custom code? [y/N] FAIL dynasent_r1: The repository for dynabench/dynasent contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/dynabench/dynasent. |
| Please pass the argument `trust_remote_code=True` to allow custom code to be run. |
| [TRAIN] Qwen2.5-0.5B-Instruct / dynasent_r2 |
| The repository for dynabench/dynasent contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/dynabench/dynasent. |
| You can avoid this prompt in future by passing the argument `trust_remote_code=True`. |
|
|
| Do you wish to run the custom code? [y/N] FAIL dynasent_r2: The repository for dynabench/dynasent contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/dynabench/dynasent. |
| Please pass the argument `trust_remote_code=True` to allow custom code to be run. |
|
|
|
|
| FAILED: ['snli_main', 'trec_fine', 'ag_setfit', 'cardiffnlp_topic', 'financial_pb_pos', 'clinc_small_skip', 'hate_speech18', 'dynasent_r1', 'dynasent_r2'] |
| Successfully trained 25 new anchors |
|
|
