Feature Extraction
sentence-transformers
Safetensors
PEFT
English
sentence-similarity
lora
embedding
retrieval
rag
Instructions to use DinoStackAI/Qwen3-Emb-4b-lora-ctx-narrativeqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use DinoStackAI/Qwen3-Emb-4b-lora-ctx-narrativeqa with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("DinoStackAI/Qwen3-Emb-4b-lora-ctx-narrativeqa") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - PEFT
How to use DinoStackAI/Qwen3-Emb-4b-lora-ctx-narrativeqa with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 1400, | |
| "best_metric": 0.8905989672725512, | |
| "best_model_checkpoint": "/petrobr/home/ronaldinho.olivera/E2E_RAG_FT/models/qwen3-embedding-4b-lora-ctx/narrativeqa-ctx-b32-e10/checkpoint-1400", | |
| "epoch": 2.734375, | |
| "eval_steps": 50, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001953125, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 0.0, | |
| "loss": 0.4023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00390625, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 3.90625e-08, | |
| "loss": 0.3516, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005859375, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 7.8125e-08, | |
| "loss": 0.5859, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0078125, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.1718750000000002e-07, | |
| "loss": 0.3359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009765625, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 1.5625e-07, | |
| "loss": 0.4375, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01171875, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.953125e-07, | |
| "loss": 0.332, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013671875, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 2.3437500000000003e-07, | |
| "loss": 0.4023, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 2.7343750000000003e-07, | |
| "loss": 0.5039, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017578125, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 3.125e-07, | |
| "loss": 0.3223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01953125, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 3.515625e-07, | |
| "loss": 0.3184, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021484375, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 3.90625e-07, | |
| "loss": 0.5625, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0234375, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 4.296875e-07, | |
| "loss": 0.5391, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025390625, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 4.6875000000000006e-07, | |
| "loss": 0.4746, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02734375, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 5.078125000000001e-07, | |
| "loss": 0.5859, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.029296875, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 5.468750000000001e-07, | |
| "loss": 0.5938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 5.859375000000001e-07, | |
| "loss": 0.5469, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.033203125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.4902, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03515625, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 6.640625e-07, | |
| "loss": 0.3477, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.037109375, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 7.03125e-07, | |
| "loss": 0.4609, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 7.421875e-07, | |
| "loss": 0.5938, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.041015625, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 7.8125e-07, | |
| "loss": 0.6836, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04296875, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 8.203125e-07, | |
| "loss": 0.4961, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.044921875, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 8.59375e-07, | |
| "loss": 0.5508, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 8.984375e-07, | |
| "loss": 0.6719, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.048828125, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 9.375000000000001e-07, | |
| "loss": 0.4141, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05078125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 9.765625e-07, | |
| "loss": 0.3008, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.052734375, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.0156250000000001e-06, | |
| "loss": 0.4473, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0546875, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 1.0546875e-06, | |
| "loss": 0.3984, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.056640625, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.0937500000000001e-06, | |
| "loss": 0.4375, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05859375, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.1328125e-06, | |
| "loss": 0.5039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.060546875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.1718750000000001e-06, | |
| "loss": 0.4785, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.2109375e-06, | |
| "loss": 0.3457, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.064453125, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.4512, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06640625, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 1.2890625000000002e-06, | |
| "loss": 0.2393, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.068359375, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.328125e-06, | |
| "loss": 0.5469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0703125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.3671875000000002e-06, | |
| "loss": 0.5469, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.072265625, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.40625e-06, | |
| "loss": 0.3457, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07421875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.4453125000000002e-06, | |
| "loss": 0.6406, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.076171875, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.484375e-06, | |
| "loss": 0.4141, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.5234375000000002e-06, | |
| "loss": 0.3984, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.080078125, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.5625e-06, | |
| "loss": 0.6914, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08203125, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.6015625000000002e-06, | |
| "loss": 0.7266, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.083984375, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 1.640625e-06, | |
| "loss": 0.3867, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0859375, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.6796875000000002e-06, | |
| "loss": 0.3438, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.087890625, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 1.71875e-06, | |
| "loss": 0.3125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08984375, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 1.7578125000000002e-06, | |
| "loss": 0.7188, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.091796875, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.796875e-06, | |
| "loss": 0.4453, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.8359375000000002e-06, | |
| "loss": 0.3867, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.095703125, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.8750000000000003e-06, | |
| "loss": 0.3711, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09765625, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.9140625000000004e-06, | |
| "loss": 0.3496, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09765625, | |
| "eval_loss": 0.4437343180179596, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7310948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9147445255474452, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8703649635036497, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9001459854014598, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8040502891141843, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8022022940563088, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.830259269294427, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7310948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09147445255474451, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.2901216545012165, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18002919708029194, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7310948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9147445255474452, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8703649635036497, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9001459854014598, | |
| "eval_runtime": 442.6468, | |
| "eval_samples_per_second": 7.819, | |
| "eval_steps_per_second": 0.124, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.099609375, | |
| "grad_norm": 0.4609375, | |
| "learning_rate": 1.953125e-06, | |
| "loss": 0.3281, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1015625, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.9921875e-06, | |
| "loss": 0.459, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.103515625, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 2.0312500000000002e-06, | |
| "loss": 0.5078, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.10546875, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 2.0703125000000003e-06, | |
| "loss": 0.3848, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.107421875, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 2.109375e-06, | |
| "loss": 0.4297, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.109375, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 2.1484375e-06, | |
| "loss": 0.2832, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.111328125, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 2.1875000000000002e-06, | |
| "loss": 0.3496, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11328125, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 2.2265625000000003e-06, | |
| "loss": 0.4805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.115234375, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 2.265625e-06, | |
| "loss": 0.4258, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1171875, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 2.3046875e-06, | |
| "loss": 0.2832, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.119140625, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 2.3437500000000002e-06, | |
| "loss": 0.6484, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12109375, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 2.3828125000000003e-06, | |
| "loss": 0.6289, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.123046875, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 2.421875e-06, | |
| "loss": 0.3477, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.416015625, | |
| "learning_rate": 2.4609375e-06, | |
| "loss": 0.3867, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.126953125, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.4688, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12890625, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 2.5390625000000003e-06, | |
| "loss": 0.3965, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.130859375, | |
| "grad_norm": 0.421875, | |
| "learning_rate": 2.5781250000000004e-06, | |
| "loss": 0.2832, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1328125, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 2.6171875e-06, | |
| "loss": 0.2852, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.134765625, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 2.65625e-06, | |
| "loss": 0.6797, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.13671875, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 2.6953125000000003e-06, | |
| "loss": 0.4629, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.138671875, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 2.7343750000000004e-06, | |
| "loss": 0.7148, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.140625, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 2.7734375e-06, | |
| "loss": 0.3516, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.142578125, | |
| "grad_norm": 0.37890625, | |
| "learning_rate": 2.8125e-06, | |
| "loss": 0.2041, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.14453125, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 2.8515625000000003e-06, | |
| "loss": 0.4414, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.146484375, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 2.8906250000000004e-06, | |
| "loss": 0.6367, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1484375, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 2.9296875e-06, | |
| "loss": 0.6172, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.150390625, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 2.96875e-06, | |
| "loss": 0.4883, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.15234375, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 3.0078125000000003e-06, | |
| "loss": 0.4727, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.154296875, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 3.0468750000000004e-06, | |
| "loss": 0.6211, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 3.0859375e-06, | |
| "loss": 0.7656, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.158203125, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.3359, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16015625, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 3.1640625000000003e-06, | |
| "loss": 0.4453, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.162109375, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 3.2031250000000004e-06, | |
| "loss": 0.5078, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1640625, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 3.2421875000000005e-06, | |
| "loss": 0.3027, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.166015625, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 3.28125e-06, | |
| "loss": 0.1973, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16796875, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 3.3203125000000002e-06, | |
| "loss": 0.5078, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.169921875, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 3.3593750000000003e-06, | |
| "loss": 0.5586, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.171875, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 3.3984375000000004e-06, | |
| "loss": 0.4141, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.173828125, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 3.4375e-06, | |
| "loss": 0.3594, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.17578125, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 3.4765625000000002e-06, | |
| "loss": 0.4414, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.177734375, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 3.5156250000000003e-06, | |
| "loss": 0.4766, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.1796875, | |
| "grad_norm": 0.490234375, | |
| "learning_rate": 3.5546875000000004e-06, | |
| "loss": 0.4941, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.181640625, | |
| "grad_norm": 0.625, | |
| "learning_rate": 3.59375e-06, | |
| "loss": 0.5078, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.18359375, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 3.6328125e-06, | |
| "loss": 0.3047, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.185546875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 3.6718750000000003e-06, | |
| "loss": 0.3672, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 3.7109375000000004e-06, | |
| "loss": 0.5547, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.189453125, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.5664, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.19140625, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 3.7890625e-06, | |
| "loss": 0.5742, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.193359375, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 3.828125000000001e-06, | |
| "loss": 0.4141, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1953125, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 3.8671875e-06, | |
| "loss": 0.418, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1953125, | |
| "eval_loss": 0.4338429868221283, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7316788321167883, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9176642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8724087591240876, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9027737226277373, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8052888200844313, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.803543042521145, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8319607892613864, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7316788321167883, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09176642335766422, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.2908029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18055474452554743, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7316788321167883, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9176642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8724087591240876, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9027737226277373, | |
| "eval_runtime": 440.9764, | |
| "eval_samples_per_second": 7.848, | |
| "eval_steps_per_second": 0.125, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.197265625, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 3.90625e-06, | |
| "loss": 0.3828, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.19921875, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 3.9453125e-06, | |
| "loss": 0.3203, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.201171875, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 3.984375e-06, | |
| "loss": 0.5078, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.203125, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 4.0234375e-06, | |
| "loss": 0.5273, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.205078125, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 4.0625000000000005e-06, | |
| "loss": 0.4258, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.20703125, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 4.101562500000001e-06, | |
| "loss": 0.4805, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.208984375, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 4.140625000000001e-06, | |
| "loss": 0.1992, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.2109375, | |
| "grad_norm": 0.4921875, | |
| "learning_rate": 4.1796875e-06, | |
| "loss": 0.2891, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.212890625, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 4.21875e-06, | |
| "loss": 0.4023, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.21484375, | |
| "grad_norm": 0.37109375, | |
| "learning_rate": 4.2578125e-06, | |
| "loss": 0.293, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.216796875, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 4.296875e-06, | |
| "loss": 0.291, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 4.3359375e-06, | |
| "loss": 0.5352, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.220703125, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 0.5469, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.22265625, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 4.4140625000000006e-06, | |
| "loss": 0.3203, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.224609375, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 4.453125000000001e-06, | |
| "loss": 0.3105, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2265625, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 4.492187500000001e-06, | |
| "loss": 0.5703, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.228515625, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 4.53125e-06, | |
| "loss": 0.6055, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.23046875, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 4.5703125e-06, | |
| "loss": 0.5234, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.232421875, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 4.609375e-06, | |
| "loss": 0.6328, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.234375, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 4.6484375e-06, | |
| "loss": 0.4023, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.236328125, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 4.6875000000000004e-06, | |
| "loss": 0.3008, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.23828125, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 4.7265625000000005e-06, | |
| "loss": 0.5273, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.240234375, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 4.765625000000001e-06, | |
| "loss": 0.3691, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.2421875, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 4.804687500000001e-06, | |
| "loss": 0.4531, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.244140625, | |
| "grad_norm": 0.453125, | |
| "learning_rate": 4.84375e-06, | |
| "loss": 0.3887, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.24609375, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 4.8828125e-06, | |
| "loss": 0.3438, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.248046875, | |
| "grad_norm": 0.3515625, | |
| "learning_rate": 4.921875e-06, | |
| "loss": 0.2002, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 4.9609375e-06, | |
| "loss": 0.4961, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.251953125, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5352, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.25390625, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 5.0390625000000005e-06, | |
| "loss": 0.7812, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.255859375, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 5.078125000000001e-06, | |
| "loss": 0.5195, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.2578125, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 5.117187500000001e-06, | |
| "loss": 0.3477, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.259765625, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 5.156250000000001e-06, | |
| "loss": 0.3887, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.26171875, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 5.1953125e-06, | |
| "loss": 0.4199, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.263671875, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 5.234375e-06, | |
| "loss": 0.5039, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.265625, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 5.2734375e-06, | |
| "loss": 0.5508, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.267578125, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 5.3125e-06, | |
| "loss": 0.4844, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.26953125, | |
| "grad_norm": 0.404296875, | |
| "learning_rate": 5.3515625000000005e-06, | |
| "loss": 0.4805, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.271484375, | |
| "grad_norm": 0.625, | |
| "learning_rate": 5.390625000000001e-06, | |
| "loss": 0.3457, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.2734375, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 5.429687500000001e-06, | |
| "loss": 0.3203, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.275390625, | |
| "grad_norm": 0.75, | |
| "learning_rate": 5.468750000000001e-06, | |
| "loss": 0.6992, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.27734375, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 5.5078125e-06, | |
| "loss": 0.4141, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.279296875, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 5.546875e-06, | |
| "loss": 0.3281, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 5.5859375e-06, | |
| "loss": 0.5469, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.283203125, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 5.625e-06, | |
| "loss": 0.3965, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.28515625, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 5.6640625000000005e-06, | |
| "loss": 0.3086, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.287109375, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 5.7031250000000006e-06, | |
| "loss": 0.3984, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.2890625, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 5.742187500000001e-06, | |
| "loss": 0.2578, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.291015625, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 5.781250000000001e-06, | |
| "loss": 0.2988, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.29296875, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 5.820312500000001e-06, | |
| "loss": 0.2773, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29296875, | |
| "eval_loss": 0.4100289046764374, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7299270072992701, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9214598540145985, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8744525547445255, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9056934306569343, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8060556235908349, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8043950874753792, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8335551669928356, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7299270072992701, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09214598540145987, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29148418491484185, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18113868613138687, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7299270072992701, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9214598540145985, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8744525547445255, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9056934306569343, | |
| "eval_runtime": 441.1401, | |
| "eval_samples_per_second": 7.846, | |
| "eval_steps_per_second": 0.125, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.294921875, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 5.859375e-06, | |
| "loss": 0.2266, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.296875, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 5.8984375e-06, | |
| "loss": 0.4199, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.298828125, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 5.9375e-06, | |
| "loss": 0.6523, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.30078125, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 5.9765625000000004e-06, | |
| "loss": 0.3086, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.302734375, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 6.0156250000000005e-06, | |
| "loss": 0.375, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3046875, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 6.054687500000001e-06, | |
| "loss": 0.5078, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.306640625, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 6.093750000000001e-06, | |
| "loss": 0.5781, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.30859375, | |
| "grad_norm": 0.470703125, | |
| "learning_rate": 6.132812500000001e-06, | |
| "loss": 0.2393, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.310546875, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 6.171875e-06, | |
| "loss": 0.5, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.75, | |
| "learning_rate": 6.2109375e-06, | |
| "loss": 0.375, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.314453125, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.5195, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.31640625, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 6.2890625e-06, | |
| "loss": 0.2969, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.318359375, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 6.3281250000000005e-06, | |
| "loss": 0.4375, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.3203125, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 6.367187500000001e-06, | |
| "loss": 0.4727, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.322265625, | |
| "grad_norm": 0.75, | |
| "learning_rate": 6.406250000000001e-06, | |
| "loss": 0.6484, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.32421875, | |
| "grad_norm": 0.466796875, | |
| "learning_rate": 6.445312500000001e-06, | |
| "loss": 0.3164, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.326171875, | |
| "grad_norm": 0.625, | |
| "learning_rate": 6.484375000000001e-06, | |
| "loss": 0.6172, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.328125, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 6.5234375e-06, | |
| "loss": 0.3555, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.330078125, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 6.5625e-06, | |
| "loss": 0.4336, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.33203125, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 6.6015625e-06, | |
| "loss": 0.459, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.333984375, | |
| "grad_norm": 0.349609375, | |
| "learning_rate": 6.6406250000000005e-06, | |
| "loss": 0.2197, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.3359375, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 6.679687500000001e-06, | |
| "loss": 0.377, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.337890625, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 6.718750000000001e-06, | |
| "loss": 0.4434, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.33984375, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 6.757812500000001e-06, | |
| "loss": 0.5156, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.341796875, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 6.796875000000001e-06, | |
| "loss": 0.2812, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 6.8359375e-06, | |
| "loss": 0.8906, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.345703125, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 6.875e-06, | |
| "loss": 0.5312, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.34765625, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 6.9140625e-06, | |
| "loss": 0.4062, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.349609375, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 6.9531250000000004e-06, | |
| "loss": 0.457, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.3515625, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 6.9921875000000006e-06, | |
| "loss": 0.2021, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.353515625, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 7.031250000000001e-06, | |
| "loss": 0.4121, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.35546875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 7.070312500000001e-06, | |
| "loss": 0.4453, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.357421875, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 7.109375000000001e-06, | |
| "loss": 0.4844, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.359375, | |
| "grad_norm": 0.4140625, | |
| "learning_rate": 7.148437500000001e-06, | |
| "loss": 0.2734, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.361328125, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 7.1875e-06, | |
| "loss": 0.4746, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.36328125, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 7.2265625e-06, | |
| "loss": 0.3203, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.365234375, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 7.265625e-06, | |
| "loss": 0.582, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.3671875, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 7.3046875000000005e-06, | |
| "loss": 0.1973, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.369140625, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 7.343750000000001e-06, | |
| "loss": 0.2891, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.37109375, | |
| "grad_norm": 0.462890625, | |
| "learning_rate": 7.382812500000001e-06, | |
| "loss": 0.3711, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.373046875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 7.421875000000001e-06, | |
| "loss": 0.6523, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 7.460937500000001e-06, | |
| "loss": 0.4766, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.376953125, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.3906, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.37890625, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 7.5390625e-06, | |
| "loss": 0.4727, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.380859375, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 7.578125e-06, | |
| "loss": 0.5234, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3828125, | |
| "grad_norm": 0.4921875, | |
| "learning_rate": 7.6171875000000005e-06, | |
| "loss": 0.291, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.384765625, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 7.656250000000001e-06, | |
| "loss": 0.3535, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.38671875, | |
| "grad_norm": 0.5, | |
| "learning_rate": 7.6953125e-06, | |
| "loss": 0.4883, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.388671875, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 7.734375e-06, | |
| "loss": 0.2637, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.390625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.7734375e-06, | |
| "loss": 0.5977, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.390625, | |
| "eval_loss": 0.38356783986091614, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7267153284671533, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9255474452554745, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8753284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9100729927007299, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8053700856977697, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8037700150619859, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8341192610191318, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7267153284671533, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09255474452554745, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29177615571776155, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18201459854014598, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7267153284671533, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9255474452554745, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8753284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9100729927007299, | |
| "eval_runtime": 441.0488, | |
| "eval_samples_per_second": 7.847, | |
| "eval_steps_per_second": 0.125, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.392578125, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 7.8125e-06, | |
| "loss": 0.6445, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.39453125, | |
| "grad_norm": 0.49609375, | |
| "learning_rate": 7.8515625e-06, | |
| "loss": 0.3281, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.396484375, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 7.890625e-06, | |
| "loss": 0.3281, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.3984375, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 7.9296875e-06, | |
| "loss": 0.4004, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.400390625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 7.96875e-06, | |
| "loss": 0.5195, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.40234375, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 8.0078125e-06, | |
| "loss": 0.3398, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.404296875, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 8.046875e-06, | |
| "loss": 0.4043, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 8.085937500000001e-06, | |
| "loss": 0.4102, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.408203125, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 0.3242, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.41015625, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 8.164062500000001e-06, | |
| "loss": 0.5938, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.412109375, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 8.203125000000001e-06, | |
| "loss": 0.291, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.4140625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 8.242187500000001e-06, | |
| "loss": 0.6094, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.416015625, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 8.281250000000001e-06, | |
| "loss": 0.418, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.41796875, | |
| "grad_norm": 0.625, | |
| "learning_rate": 8.320312500000001e-06, | |
| "loss": 0.4883, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.419921875, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 8.359375e-06, | |
| "loss": 0.6367, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.421875, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 8.3984375e-06, | |
| "loss": 0.3516, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.423828125, | |
| "grad_norm": 0.43359375, | |
| "learning_rate": 8.4375e-06, | |
| "loss": 0.2891, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.42578125, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 8.4765625e-06, | |
| "loss": 0.4453, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.427734375, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 8.515625e-06, | |
| "loss": 0.2441, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.4296875, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 8.5546875e-06, | |
| "loss": 0.6172, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.431640625, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 8.59375e-06, | |
| "loss": 0.127, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.43359375, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 8.6328125e-06, | |
| "loss": 0.3145, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.435546875, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 8.671875e-06, | |
| "loss": 0.293, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.453125, | |
| "learning_rate": 8.7109375e-06, | |
| "loss": 0.334, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.439453125, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 0.1768, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.44140625, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 8.789062500000001e-06, | |
| "loss": 0.2754, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.443359375, | |
| "grad_norm": 0.4765625, | |
| "learning_rate": 8.828125000000001e-06, | |
| "loss": 0.3789, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.4453125, | |
| "grad_norm": 0.5, | |
| "learning_rate": 8.867187500000001e-06, | |
| "loss": 0.2539, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.447265625, | |
| "grad_norm": 0.318359375, | |
| "learning_rate": 8.906250000000001e-06, | |
| "loss": 0.1602, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.44921875, | |
| "grad_norm": 0.388671875, | |
| "learning_rate": 8.945312500000001e-06, | |
| "loss": 0.3281, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.451171875, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 8.984375000000002e-06, | |
| "loss": 0.8398, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.453125, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 9.0234375e-06, | |
| "loss": 0.4219, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.455078125, | |
| "grad_norm": 0.4765625, | |
| "learning_rate": 9.0625e-06, | |
| "loss": 0.2412, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.45703125, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 9.1015625e-06, | |
| "loss": 0.3477, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.458984375, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 9.140625e-06, | |
| "loss": 0.2715, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4609375, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 9.1796875e-06, | |
| "loss": 0.4902, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.462890625, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 9.21875e-06, | |
| "loss": 0.2207, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.46484375, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 9.2578125e-06, | |
| "loss": 0.3867, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.466796875, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 9.296875e-06, | |
| "loss": 0.2656, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 9.3359375e-06, | |
| "loss": 0.4453, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.470703125, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.2773, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.47265625, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 9.414062500000001e-06, | |
| "loss": 0.3633, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.474609375, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 9.453125000000001e-06, | |
| "loss": 0.5, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.4765625, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 9.492187500000001e-06, | |
| "loss": 0.2988, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.478515625, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 9.531250000000001e-06, | |
| "loss": 0.3262, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.48046875, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 9.570312500000001e-06, | |
| "loss": 0.4531, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.482421875, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 9.609375000000001e-06, | |
| "loss": 0.3086, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.484375, | |
| "grad_norm": 0.625, | |
| "learning_rate": 9.648437500000002e-06, | |
| "loss": 0.4492, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.486328125, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 9.6875e-06, | |
| "loss": 0.2129, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.48828125, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 9.7265625e-06, | |
| "loss": 0.2871, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.48828125, | |
| "eval_loss": 0.3588917553424835, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.727007299270073, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9296350364963504, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.88, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9144525547445256, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8078226822934962, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8062518827482327, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8370477909322919, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.727007299270073, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09296350364963503, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29333333333333333, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1828905109489051, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.727007299270073, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9296350364963504, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.88, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9144525547445256, | |
| "eval_runtime": 440.736, | |
| "eval_samples_per_second": 7.853, | |
| "eval_steps_per_second": 0.125, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.490234375, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 9.765625e-06, | |
| "loss": 0.3477, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.4921875, | |
| "grad_norm": 0.30859375, | |
| "learning_rate": 9.8046875e-06, | |
| "loss": 0.2139, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.494140625, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 9.84375e-06, | |
| "loss": 0.4121, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.49609375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 9.8828125e-06, | |
| "loss": 0.2041, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.498046875, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 9.921875e-06, | |
| "loss": 0.3848, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 9.9609375e-06, | |
| "loss": 0.2217, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.501953125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1572, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.50390625, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.0039062500000001e-05, | |
| "loss": 0.4141, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.505859375, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.0078125000000001e-05, | |
| "loss": 0.1777, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.5078125, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.0117187500000001e-05, | |
| "loss": 0.4375, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.509765625, | |
| "grad_norm": 0.22265625, | |
| "learning_rate": 1.0156250000000001e-05, | |
| "loss": 0.041, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.51171875, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 1.0195312500000001e-05, | |
| "loss": 0.1973, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.513671875, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.0234375000000001e-05, | |
| "loss": 0.2656, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.515625, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.0273437500000002e-05, | |
| "loss": 0.4258, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.517578125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.0312500000000002e-05, | |
| "loss": 0.5781, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.51953125, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.03515625e-05, | |
| "loss": 0.2451, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.521484375, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.0390625e-05, | |
| "loss": 0.4727, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.5234375, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.04296875e-05, | |
| "loss": 0.4492, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.525390625, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.046875e-05, | |
| "loss": 0.2812, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.52734375, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.05078125e-05, | |
| "loss": 0.25, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.529296875, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.0546875e-05, | |
| "loss": 0.2871, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.53125, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.05859375e-05, | |
| "loss": 0.4707, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.533203125, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.0625e-05, | |
| "loss": 0.5742, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.53515625, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.0664062500000001e-05, | |
| "loss": 0.4961, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.537109375, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.0703125000000001e-05, | |
| "loss": 0.5859, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5390625, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.0742187500000001e-05, | |
| "loss": 0.3906, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.541015625, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 1.0781250000000001e-05, | |
| "loss": 0.2539, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.54296875, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.0820312500000001e-05, | |
| "loss": 0.4336, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.544921875, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.0859375000000001e-05, | |
| "loss": 0.1992, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.546875, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.0898437500000001e-05, | |
| "loss": 0.2227, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.548828125, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.0937500000000002e-05, | |
| "loss": 0.2773, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.55078125, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.0976562500000002e-05, | |
| "loss": 0.2754, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.552734375, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.1015625e-05, | |
| "loss": 0.3047, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.5546875, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 1.10546875e-05, | |
| "loss": 0.2041, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.556640625, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 1.109375e-05, | |
| "loss": 0.3477, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.55859375, | |
| "grad_norm": 0.44140625, | |
| "learning_rate": 1.11328125e-05, | |
| "loss": 0.373, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.560546875, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 1.1171875e-05, | |
| "loss": 0.2832, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.12109375e-05, | |
| "loss": 0.3047, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.564453125, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.125e-05, | |
| "loss": 0.2227, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.56640625, | |
| "grad_norm": 0.4765625, | |
| "learning_rate": 1.12890625e-05, | |
| "loss": 0.3535, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.568359375, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.1328125000000001e-05, | |
| "loss": 0.5547, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.5703125, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.1367187500000001e-05, | |
| "loss": 0.1953, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.572265625, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.1406250000000001e-05, | |
| "loss": 0.6367, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.57421875, | |
| "grad_norm": 0.5, | |
| "learning_rate": 1.1445312500000001e-05, | |
| "loss": 0.1191, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.576171875, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 1.1484375000000001e-05, | |
| "loss": 0.5, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.578125, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.1523437500000001e-05, | |
| "loss": 0.5234, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.580078125, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 1.1562500000000002e-05, | |
| "loss": 0.2471, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.58203125, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.1601562500000002e-05, | |
| "loss": 0.3301, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.583984375, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 1.1640625000000002e-05, | |
| "loss": 0.2119, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.5859375, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.16796875e-05, | |
| "loss": 0.1699, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5859375, | |
| "eval_loss": 0.33511248230934143, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7275912408759124, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9345985401459854, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8861313868613139, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9194160583941606, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8108965691146827, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8093314795504575, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8406275616199421, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7275912408759124, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09345985401459855, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29537712895377133, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1838832116788321, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7275912408759124, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9345985401459854, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8861313868613139, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9194160583941606, | |
| "eval_runtime": 441.0159, | |
| "eval_samples_per_second": 7.848, | |
| "eval_steps_per_second": 0.125, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.587890625, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.171875e-05, | |
| "loss": 0.2793, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.58984375, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.17578125e-05, | |
| "loss": 0.375, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.591796875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.1796875e-05, | |
| "loss": 0.4219, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.59375, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.18359375e-05, | |
| "loss": 0.4238, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.595703125, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.1875e-05, | |
| "loss": 0.5156, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.59765625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.19140625e-05, | |
| "loss": 0.4492, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.599609375, | |
| "grad_norm": 0.419921875, | |
| "learning_rate": 1.1953125000000001e-05, | |
| "loss": 0.2559, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.6015625, | |
| "grad_norm": 0.375, | |
| "learning_rate": 1.1992187500000001e-05, | |
| "loss": 0.0933, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.603515625, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.2031250000000001e-05, | |
| "loss": 0.4199, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.60546875, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.2070312500000001e-05, | |
| "loss": 0.3906, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.607421875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.2109375000000001e-05, | |
| "loss": 0.3906, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.609375, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 1.2148437500000001e-05, | |
| "loss": 0.1758, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.611328125, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.2187500000000001e-05, | |
| "loss": 0.6094, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.61328125, | |
| "grad_norm": 0.51953125, | |
| "learning_rate": 1.2226562500000002e-05, | |
| "loss": 0.3066, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.615234375, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.2265625000000002e-05, | |
| "loss": 0.375, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.6171875, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 1.2304687500000002e-05, | |
| "loss": 0.1328, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.619140625, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.234375e-05, | |
| "loss": 0.2451, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.62109375, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.23828125e-05, | |
| "loss": 0.5625, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.623046875, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.2421875e-05, | |
| "loss": 0.5391, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.24609375e-05, | |
| "loss": 0.5156, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.626953125, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3066, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.62890625, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 1.25390625e-05, | |
| "loss": 0.2891, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.630859375, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.2578125e-05, | |
| "loss": 0.4883, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.6328125, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 1.2617187500000001e-05, | |
| "loss": 0.5234, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.634765625, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.2656250000000001e-05, | |
| "loss": 0.5391, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.63671875, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 1.2695312500000001e-05, | |
| "loss": 0.4121, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.638671875, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.2734375000000001e-05, | |
| "loss": 0.6641, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.640625, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 1.2773437500000001e-05, | |
| "loss": 0.4297, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.642578125, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 1.2812500000000001e-05, | |
| "loss": 0.1777, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.64453125, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 1.2851562500000002e-05, | |
| "loss": 0.1904, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.646484375, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.2890625000000002e-05, | |
| "loss": 0.3809, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.6484375, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.2929687500000002e-05, | |
| "loss": 0.1758, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.650390625, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 1.2968750000000002e-05, | |
| "loss": 0.375, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.65234375, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.30078125e-05, | |
| "loss": 0.4141, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.654296875, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 1.3046875e-05, | |
| "loss": 0.2617, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.30859375e-05, | |
| "loss": 0.2773, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.658203125, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 1.3125e-05, | |
| "loss": 0.5547, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.66015625, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 1.31640625e-05, | |
| "loss": 0.1167, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.662109375, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 1.3203125e-05, | |
| "loss": 0.2109, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.6640625, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.3242187500000001e-05, | |
| "loss": 0.416, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.666015625, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.3281250000000001e-05, | |
| "loss": 0.3672, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.66796875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.3320312500000001e-05, | |
| "loss": 0.3887, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.669921875, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 1.3359375000000001e-05, | |
| "loss": 0.4121, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.671875, | |
| "grad_norm": 0.37890625, | |
| "learning_rate": 1.3398437500000001e-05, | |
| "loss": 0.0713, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.673828125, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.3437500000000001e-05, | |
| "loss": 0.4043, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.67578125, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 1.3476562500000001e-05, | |
| "loss": 0.166, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.677734375, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.3515625000000002e-05, | |
| "loss": 0.5234, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.6796875, | |
| "grad_norm": 0.55859375, | |
| "learning_rate": 1.3554687500000002e-05, | |
| "loss": 0.2285, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.681640625, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 1.3593750000000002e-05, | |
| "loss": 0.2031, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.68359375, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.3632812500000002e-05, | |
| "loss": 0.2676, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.68359375, | |
| "eval_loss": 0.31380608677864075, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7632116788321168, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9378102189781022, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9217518248175183, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8319165334654423, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8302823543042526, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8570432330509711, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7632116788321168, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09378102189781024, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29703163017031625, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18435036496350368, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7632116788321168, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9378102189781022, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9217518248175183, | |
| "eval_runtime": 440.9224, | |
| "eval_samples_per_second": 7.849, | |
| "eval_steps_per_second": 0.125, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.685546875, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.3671875e-05, | |
| "loss": 0.4121, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.37109375e-05, | |
| "loss": 0.3398, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.689453125, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.375e-05, | |
| "loss": 0.2852, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.69140625, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.37890625e-05, | |
| "loss": 0.3477, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.693359375, | |
| "grad_norm": 1.3984375, | |
| "learning_rate": 1.3828125e-05, | |
| "loss": 0.3887, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.6953125, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.38671875e-05, | |
| "loss": 0.3535, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.697265625, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.3906250000000001e-05, | |
| "loss": 0.1836, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.69921875, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.3945312500000001e-05, | |
| "loss": 0.2891, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.701171875, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.3984375000000001e-05, | |
| "loss": 0.3242, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.703125, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.4023437500000001e-05, | |
| "loss": 0.5547, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.705078125, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.4062500000000001e-05, | |
| "loss": 0.2334, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.70703125, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.4101562500000001e-05, | |
| "loss": 0.4004, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.708984375, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.4140625000000002e-05, | |
| "loss": 0.3086, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.7109375, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.4179687500000002e-05, | |
| "loss": 0.4512, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.712890625, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 1.4218750000000002e-05, | |
| "loss": 0.1973, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.71484375, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.4257812500000002e-05, | |
| "loss": 0.375, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.716796875, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.4296875000000002e-05, | |
| "loss": 0.2578, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.71875, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.43359375e-05, | |
| "loss": 0.2246, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.720703125, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.4375e-05, | |
| "loss": 0.5078, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.72265625, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.44140625e-05, | |
| "loss": 0.4746, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.724609375, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.4453125e-05, | |
| "loss": 0.2109, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.7265625, | |
| "grad_norm": 0.34765625, | |
| "learning_rate": 1.44921875e-05, | |
| "loss": 0.1777, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.728515625, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.453125e-05, | |
| "loss": 0.5469, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.73046875, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 1.4570312500000001e-05, | |
| "loss": 0.6172, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.732421875, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.4609375000000001e-05, | |
| "loss": 0.1689, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.734375, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 1.4648437500000001e-05, | |
| "loss": 0.4883, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.736328125, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.4687500000000001e-05, | |
| "loss": 0.2695, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.73828125, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 1.4726562500000001e-05, | |
| "loss": 0.5234, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.740234375, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.4765625000000001e-05, | |
| "loss": 0.2227, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.7421875, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.4804687500000002e-05, | |
| "loss": 0.3223, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.744140625, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.4843750000000002e-05, | |
| "loss": 0.2461, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.74609375, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.4882812500000002e-05, | |
| "loss": 0.2715, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.748046875, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.4921875000000002e-05, | |
| "loss": 0.2949, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.4960937500000002e-05, | |
| "loss": 0.2227, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.751953125, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.3789, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.75390625, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.50390625e-05, | |
| "loss": 0.3047, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.755859375, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.5078125e-05, | |
| "loss": 0.2422, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.7578125, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.51171875e-05, | |
| "loss": 0.3535, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.759765625, | |
| "grad_norm": 0.3203125, | |
| "learning_rate": 1.515625e-05, | |
| "loss": 0.0996, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.76171875, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 1.5195312500000001e-05, | |
| "loss": 0.2539, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.763671875, | |
| "grad_norm": 0.46484375, | |
| "learning_rate": 1.5234375000000001e-05, | |
| "loss": 0.209, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.765625, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.52734375e-05, | |
| "loss": 0.3398, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.767578125, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.5312500000000003e-05, | |
| "loss": 0.5977, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.76953125, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.53515625e-05, | |
| "loss": 0.2432, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.771484375, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 1.5390625e-05, | |
| "loss": 0.1826, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.7734375, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.54296875e-05, | |
| "loss": 0.1465, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.775390625, | |
| "grad_norm": 0.40625, | |
| "learning_rate": 1.546875e-05, | |
| "loss": 0.1963, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.77734375, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.5507812500000002e-05, | |
| "loss": 0.1758, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.779296875, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.5546875e-05, | |
| "loss": 0.3418, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.5585937500000002e-05, | |
| "loss": 0.4805, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "eval_loss": 0.2925780117511749, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7684671532846715, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9448175182481752, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8928467153284672, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9293430656934306, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8369961580601945, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8355570617541427, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8626713894987468, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7684671532846715, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09448175182481752, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.2976155717761557, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18586861313868613, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7684671532846715, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9448175182481752, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8928467153284672, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9293430656934306, | |
| "eval_runtime": 441.0216, | |
| "eval_samples_per_second": 7.848, | |
| "eval_steps_per_second": 0.125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.783203125, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.4648, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.78515625, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.5664062500000002e-05, | |
| "loss": 0.0967, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.787109375, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 1.5703125e-05, | |
| "loss": 0.3281, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.7890625, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.5742187500000002e-05, | |
| "loss": 0.2676, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.791015625, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 1.578125e-05, | |
| "loss": 0.1455, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.79296875, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.5820312500000003e-05, | |
| "loss": 0.3711, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.794921875, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.5859375e-05, | |
| "loss": 0.2852, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.796875, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.5898437500000003e-05, | |
| "loss": 0.3164, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.798828125, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.59375e-05, | |
| "loss": 0.2256, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.80078125, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.5976562500000003e-05, | |
| "loss": 0.3887, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.802734375, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.6015625e-05, | |
| "loss": 0.2158, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.8046875, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.60546875e-05, | |
| "loss": 0.375, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.806640625, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.609375e-05, | |
| "loss": 0.5078, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.80859375, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.61328125e-05, | |
| "loss": 0.291, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.810546875, | |
| "grad_norm": 0.392578125, | |
| "learning_rate": 1.6171875000000002e-05, | |
| "loss": 0.1416, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 1.62109375e-05, | |
| "loss": 0.3496, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.814453125, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.6250000000000002e-05, | |
| "loss": 0.4199, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.81640625, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.62890625e-05, | |
| "loss": 0.2852, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.818359375, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 1.6328125000000002e-05, | |
| "loss": 0.1177, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.8203125, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 1.63671875e-05, | |
| "loss": 0.3125, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.822265625, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.6406250000000002e-05, | |
| "loss": 0.3496, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.82421875, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.64453125e-05, | |
| "loss": 0.2109, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.826171875, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 1.6484375000000003e-05, | |
| "loss": 0.3398, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.828125, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.65234375e-05, | |
| "loss": 0.2539, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.830078125, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.6562500000000003e-05, | |
| "loss": 0.3555, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.83203125, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 1.66015625e-05, | |
| "loss": 0.0874, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.833984375, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.6640625000000003e-05, | |
| "loss": 0.1602, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.8359375, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.66796875e-05, | |
| "loss": 0.3789, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.837890625, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.671875e-05, | |
| "loss": 0.3672, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.83984375, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.67578125e-05, | |
| "loss": 0.291, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.841796875, | |
| "grad_norm": 0.244140625, | |
| "learning_rate": 1.6796875e-05, | |
| "loss": 0.0444, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.6835937500000002e-05, | |
| "loss": 0.2461, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.845703125, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.6875e-05, | |
| "loss": 0.1816, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.84765625, | |
| "grad_norm": 1.2421875, | |
| "learning_rate": 1.6914062500000002e-05, | |
| "loss": 0.5625, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.849609375, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.6953125e-05, | |
| "loss": 0.2119, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.8515625, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.6992187500000002e-05, | |
| "loss": 0.4355, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.853515625, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.703125e-05, | |
| "loss": 0.2441, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.85546875, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.7070312500000002e-05, | |
| "loss": 0.457, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.857421875, | |
| "grad_norm": 1.640625, | |
| "learning_rate": 1.7109375e-05, | |
| "loss": 0.8125, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.859375, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 1.7148437500000003e-05, | |
| "loss": 0.1396, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.861328125, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.71875e-05, | |
| "loss": 0.3008, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.86328125, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.7226562500000003e-05, | |
| "loss": 0.4961, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.865234375, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.7265625e-05, | |
| "loss": 0.3809, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.8671875, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.7304687500000003e-05, | |
| "loss": 0.5703, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.869140625, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.734375e-05, | |
| "loss": 0.3535, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.87109375, | |
| "grad_norm": 0.9921875, | |
| "learning_rate": 1.73828125e-05, | |
| "loss": 0.3867, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.873046875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.7421875e-05, | |
| "loss": 0.2324, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.74609375e-05, | |
| "loss": 0.668, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.876953125, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 0.3828, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.87890625, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.75390625e-05, | |
| "loss": 0.377, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.87890625, | |
| "eval_loss": 0.27973058819770813, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.774014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.948029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.8972262773722628, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9293430656934306, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.841606220352893, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8401620901401925, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8669085045078865, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.774014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.0948029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.29907542579075425, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18586861313868613, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.774014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.948029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.8972262773722628, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9293430656934306, | |
| "eval_runtime": 440.8119, | |
| "eval_samples_per_second": 7.851, | |
| "eval_steps_per_second": 0.125, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.880859375, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.7578125000000002e-05, | |
| "loss": 0.3848, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.8828125, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 1.76171875e-05, | |
| "loss": 0.3359, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.884765625, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.7656250000000002e-05, | |
| "loss": 0.2871, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.88671875, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.76953125e-05, | |
| "loss": 0.3828, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.888671875, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 1.7734375000000002e-05, | |
| "loss": 0.4414, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.890625, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 1.77734375e-05, | |
| "loss": 0.2451, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.892578125, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.7812500000000003e-05, | |
| "loss": 0.2656, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.89453125, | |
| "grad_norm": 0.375, | |
| "learning_rate": 1.78515625e-05, | |
| "loss": 0.1475, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.896484375, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 1.7890625000000003e-05, | |
| "loss": 0.1533, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.8984375, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.79296875e-05, | |
| "loss": 0.1934, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.900390625, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.7968750000000003e-05, | |
| "loss": 0.4062, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.90234375, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 1.80078125e-05, | |
| "loss": 0.2422, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.904296875, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.8046875e-05, | |
| "loss": 0.3242, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.90625, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.8085937500000002e-05, | |
| "loss": 0.334, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.908203125, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.8125e-05, | |
| "loss": 0.5469, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.91015625, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.8164062500000002e-05, | |
| "loss": 0.3066, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.912109375, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.8203125e-05, | |
| "loss": 0.3086, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.9140625, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.8242187500000002e-05, | |
| "loss": 0.1147, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.916015625, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.828125e-05, | |
| "loss": 0.1914, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.91796875, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.8320312500000002e-05, | |
| "loss": 0.2002, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.919921875, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.8359375e-05, | |
| "loss": 0.2314, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.921875, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.8398437500000003e-05, | |
| "loss": 0.1279, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.923828125, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.84375e-05, | |
| "loss": 0.2598, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.92578125, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.8476562500000003e-05, | |
| "loss": 0.2432, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.927734375, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.8515625e-05, | |
| "loss": 0.3809, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.9296875, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 1.8554687500000003e-05, | |
| "loss": 0.1543, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.931640625, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.859375e-05, | |
| "loss": 0.3105, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.93359375, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.8632812500000003e-05, | |
| "loss": 0.3398, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.935546875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.8671875e-05, | |
| "loss": 0.2656, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.9921875, | |
| "learning_rate": 1.87109375e-05, | |
| "loss": 0.3594, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.939453125, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.249, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.94140625, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.87890625e-05, | |
| "loss": 0.1572, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.943359375, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.8828125000000002e-05, | |
| "loss": 0.2578, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.9453125, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.88671875e-05, | |
| "loss": 0.2852, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.947265625, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.8906250000000002e-05, | |
| "loss": 0.3125, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.94921875, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.89453125e-05, | |
| "loss": 0.1279, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.951171875, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.8984375000000002e-05, | |
| "loss": 0.2754, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.953125, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.90234375e-05, | |
| "loss": 0.1641, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.955078125, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.9062500000000003e-05, | |
| "loss": 0.2773, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.95703125, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.91015625e-05, | |
| "loss": 0.1719, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.958984375, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 1.9140625000000003e-05, | |
| "loss": 0.0869, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.9609375, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.91796875e-05, | |
| "loss": 0.1553, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.962890625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.9218750000000003e-05, | |
| "loss": 0.1934, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.96484375, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.92578125e-05, | |
| "loss": 0.2363, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.966796875, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.9296875000000003e-05, | |
| "loss": 0.2246, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.96875, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.93359375e-05, | |
| "loss": 0.1826, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.970703125, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9375e-05, | |
| "loss": 0.3652, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.97265625, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 1.9414062500000002e-05, | |
| "loss": 0.2637, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.974609375, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.9453125e-05, | |
| "loss": 0.2461, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.9765625, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.9492187500000002e-05, | |
| "loss": 0.1523, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9765625, | |
| "eval_loss": 0.268071711063385, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7845255474452555, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.95007299270073, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9004379562043796, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9305109489051094, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8482058693352702, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8469362762136489, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8724460288288585, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7845255474452555, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09500729927007298, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30014598540145987, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1861021897810219, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7845255474452555, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.95007299270073, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9004379562043796, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9305109489051094, | |
| "eval_runtime": 441.3348, | |
| "eval_samples_per_second": 7.842, | |
| "eval_steps_per_second": 0.125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.978515625, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.953125e-05, | |
| "loss": 0.3438, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.98046875, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.9570312500000002e-05, | |
| "loss": 0.2197, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.982421875, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.9609375e-05, | |
| "loss": 0.332, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.984375, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 1.9648437500000002e-05, | |
| "loss": 0.3145, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.986328125, | |
| "grad_norm": 0.39453125, | |
| "learning_rate": 1.96875e-05, | |
| "loss": 0.1377, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.98828125, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 1.9726562500000003e-05, | |
| "loss": 0.3867, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.990234375, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.9765625e-05, | |
| "loss": 0.3242, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.9921875, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 1.9804687500000003e-05, | |
| "loss": 0.4766, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.994140625, | |
| "grad_norm": 0.4140625, | |
| "learning_rate": 1.984375e-05, | |
| "loss": 0.1406, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.99609375, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9882812500000003e-05, | |
| "loss": 0.2832, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.998046875, | |
| "grad_norm": 0.44140625, | |
| "learning_rate": 1.9921875e-05, | |
| "loss": 0.1973, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.9960937500000003e-05, | |
| "loss": 0.3359, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.001953125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2148, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.00390625, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.9995659722222226e-05, | |
| "loss": 0.2832, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.005859375, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 1.9991319444444447e-05, | |
| "loss": 0.3145, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.0078125, | |
| "grad_norm": 0.4921875, | |
| "learning_rate": 1.9986979166666668e-05, | |
| "loss": 0.1689, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.009765625, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 1.998263888888889e-05, | |
| "loss": 0.2734, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.01171875, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.9978298611111113e-05, | |
| "loss": 0.3438, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.013671875, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.9973958333333334e-05, | |
| "loss": 0.2988, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.015625, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.9969618055555558e-05, | |
| "loss": 0.2188, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.017578125, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.996527777777778e-05, | |
| "loss": 0.3027, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.01953125, | |
| "grad_norm": 0.470703125, | |
| "learning_rate": 1.9960937500000003e-05, | |
| "loss": 0.1895, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.021484375, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.9956597222222224e-05, | |
| "loss": 0.2236, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.0234375, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.9952256944444445e-05, | |
| "loss": 0.2168, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.025390625, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 1.994791666666667e-05, | |
| "loss": 0.2295, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.02734375, | |
| "grad_norm": 1.375, | |
| "learning_rate": 1.994357638888889e-05, | |
| "loss": 0.3047, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.029296875, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.9939236111111114e-05, | |
| "loss": 0.1582, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.03125, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 1.9934895833333335e-05, | |
| "loss": 0.2305, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.033203125, | |
| "grad_norm": 0.9375, | |
| "learning_rate": 1.9930555555555556e-05, | |
| "loss": 0.0981, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.03515625, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 1.9926215277777777e-05, | |
| "loss": 0.293, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.037109375, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.9921875e-05, | |
| "loss": 0.498, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.0390625, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.9917534722222226e-05, | |
| "loss": 0.1406, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.041015625, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.9913194444444447e-05, | |
| "loss": 0.0903, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.04296875, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.9908854166666667e-05, | |
| "loss": 0.2471, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.044921875, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.990451388888889e-05, | |
| "loss": 0.2617, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.046875, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.9900173611111113e-05, | |
| "loss": 0.2432, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.048828125, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.9895833333333334e-05, | |
| "loss": 0.3223, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.05078125, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 1.9891493055555558e-05, | |
| "loss": 0.1543, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.052734375, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.988715277777778e-05, | |
| "loss": 0.3262, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.0546875, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.9882812500000003e-05, | |
| "loss": 0.2188, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.056640625, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.9878472222222224e-05, | |
| "loss": 0.418, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.05859375, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.9874131944444445e-05, | |
| "loss": 0.2695, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.060546875, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.986979166666667e-05, | |
| "loss": 0.2773, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 1.986545138888889e-05, | |
| "loss": 0.3652, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.064453125, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.9861111111111114e-05, | |
| "loss": 0.1309, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.06640625, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.9856770833333335e-05, | |
| "loss": 0.1582, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.068359375, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.9852430555555556e-05, | |
| "loss": 0.2285, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.0703125, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.9848090277777777e-05, | |
| "loss": 0.4688, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.072265625, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.984375e-05, | |
| "loss": 0.1191, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.07421875, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 1.9839409722222226e-05, | |
| "loss": 0.2148, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.07421875, | |
| "eval_loss": 0.25791481137275696, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9503649635036496, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9042335766423357, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9305109489051094, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8553397951621605, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8540360329046466, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8778040779246763, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09503649635036496, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3014111922141119, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1861021897810219, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9503649635036496, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9042335766423357, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9305109489051094, | |
| "eval_runtime": 440.6072, | |
| "eval_samples_per_second": 7.855, | |
| "eval_steps_per_second": 0.125, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.076171875, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.9835069444444446e-05, | |
| "loss": 0.373, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.078125, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.983072916666667e-05, | |
| "loss": 0.2617, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.080078125, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 1.982638888888889e-05, | |
| "loss": 0.1641, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.08203125, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 1.9822048611111112e-05, | |
| "loss": 0.2197, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.083984375, | |
| "grad_norm": 0.345703125, | |
| "learning_rate": 1.9817708333333333e-05, | |
| "loss": 0.0952, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.0859375, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.9813368055555558e-05, | |
| "loss": 0.2324, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.087890625, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.980902777777778e-05, | |
| "loss": 0.4355, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.08984375, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.9804687500000003e-05, | |
| "loss": 0.2344, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.091796875, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.9800347222222224e-05, | |
| "loss": 0.1904, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.09375, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 1.9796006944444445e-05, | |
| "loss": 0.1934, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.095703125, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.979166666666667e-05, | |
| "loss": 0.1934, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.09765625, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.978732638888889e-05, | |
| "loss": 0.2246, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.099609375, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.9782986111111114e-05, | |
| "loss": 0.1719, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.1015625, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 1.9778645833333335e-05, | |
| "loss": 0.207, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.103515625, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 1.9774305555555556e-05, | |
| "loss": 0.2051, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.10546875, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.9769965277777777e-05, | |
| "loss": 0.334, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.107421875, | |
| "grad_norm": 1.25, | |
| "learning_rate": 1.9765625e-05, | |
| "loss": 0.3867, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.109375, | |
| "grad_norm": 1.6953125, | |
| "learning_rate": 1.9761284722222225e-05, | |
| "loss": 0.5547, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.111328125, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.9756944444444446e-05, | |
| "loss": 0.1826, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.11328125, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.975260416666667e-05, | |
| "loss": 0.3438, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.115234375, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 1.974826388888889e-05, | |
| "loss": 0.1953, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.1171875, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 1.9743923611111112e-05, | |
| "loss": 0.2578, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.119140625, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 1.9739583333333333e-05, | |
| "loss": 0.209, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.12109375, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.9735243055555557e-05, | |
| "loss": 0.106, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.123046875, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.973090277777778e-05, | |
| "loss": 0.2559, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.9726562500000003e-05, | |
| "loss": 0.375, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.126953125, | |
| "grad_norm": 1.1953125, | |
| "learning_rate": 1.9722222222222224e-05, | |
| "loss": 0.3203, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.12890625, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.9717881944444444e-05, | |
| "loss": 0.1484, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.130859375, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.971354166666667e-05, | |
| "loss": 0.3984, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.1328125, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.970920138888889e-05, | |
| "loss": 0.2676, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.134765625, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.9704861111111114e-05, | |
| "loss": 0.3027, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.13671875, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.9700520833333335e-05, | |
| "loss": 0.4629, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.138671875, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.969618055555556e-05, | |
| "loss": 0.1748, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.140625, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 1.969184027777778e-05, | |
| "loss": 0.2617, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.142578125, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.96875e-05, | |
| "loss": 0.1465, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.14453125, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.9683159722222225e-05, | |
| "loss": 0.2188, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.146484375, | |
| "grad_norm": 1.5, | |
| "learning_rate": 1.9678819444444446e-05, | |
| "loss": 0.2471, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.1484375, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.967447916666667e-05, | |
| "loss": 0.2852, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.150390625, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.967013888888889e-05, | |
| "loss": 0.2695, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.15234375, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.9665798611111112e-05, | |
| "loss": 0.166, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.154296875, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.9661458333333333e-05, | |
| "loss": 0.2891, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.9657118055555557e-05, | |
| "loss": 0.2412, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.158203125, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.9652777777777778e-05, | |
| "loss": 0.334, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.16015625, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.9648437500000002e-05, | |
| "loss": 0.3672, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.162109375, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 1.9644097222222223e-05, | |
| "loss": 0.4727, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.1640625, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.9639756944444444e-05, | |
| "loss": 0.1631, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.166015625, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.963541666666667e-05, | |
| "loss": 0.3242, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.16796875, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.963107638888889e-05, | |
| "loss": 0.2402, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.169921875, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.9626736111111114e-05, | |
| "loss": 0.1426, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.171875, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.9622395833333335e-05, | |
| "loss": 0.2617, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.171875, | |
| "eval_loss": 0.25290167331695557, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9515328467153285, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9036496350364963, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9313868613138686, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8554933384559645, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8542511875796557, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8782362187493271, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09515328467153283, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3012165450121654, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18627737226277372, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7967883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9515328467153285, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9036496350364963, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9313868613138686, | |
| "eval_runtime": 440.6478, | |
| "eval_samples_per_second": 7.854, | |
| "eval_steps_per_second": 0.125, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.173828125, | |
| "grad_norm": 0.984375, | |
| "learning_rate": 1.961805555555556e-05, | |
| "loss": 0.3281, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.17578125, | |
| "grad_norm": 0.9921875, | |
| "learning_rate": 1.961371527777778e-05, | |
| "loss": 0.4668, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.177734375, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 1.9609375e-05, | |
| "loss": 0.0811, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.1796875, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 1.9605034722222225e-05, | |
| "loss": 0.334, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.181640625, | |
| "grad_norm": 1.2734375, | |
| "learning_rate": 1.9600694444444446e-05, | |
| "loss": 0.4883, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.18359375, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.959635416666667e-05, | |
| "loss": 0.2539, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.185546875, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.959201388888889e-05, | |
| "loss": 0.3125, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.1875, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.9587673611111112e-05, | |
| "loss": 0.21, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.189453125, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.9583333333333333e-05, | |
| "loss": 0.105, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.19140625, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.9578993055555557e-05, | |
| "loss": 0.2227, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.193359375, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.9574652777777778e-05, | |
| "loss": 0.2012, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.1953125, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.9570312500000002e-05, | |
| "loss": 0.2383, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.197265625, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.9565972222222226e-05, | |
| "loss": 0.2246, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.19921875, | |
| "grad_norm": 1.9765625, | |
| "learning_rate": 1.9561631944444447e-05, | |
| "loss": 0.1357, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.201171875, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.9557291666666668e-05, | |
| "loss": 0.1318, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.203125, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.955295138888889e-05, | |
| "loss": 0.1406, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.205078125, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.9548611111111113e-05, | |
| "loss": 0.2197, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.20703125, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.9544270833333334e-05, | |
| "loss": 0.2041, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.208984375, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.953993055555556e-05, | |
| "loss": 0.1348, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.2109375, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 1.953559027777778e-05, | |
| "loss": 0.1621, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.212890625, | |
| "grad_norm": 1.2109375, | |
| "learning_rate": 1.953125e-05, | |
| "loss": 0.1328, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.21484375, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.9526909722222225e-05, | |
| "loss": 0.1953, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.216796875, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.9522569444444446e-05, | |
| "loss": 0.2871, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.21875, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.951822916666667e-05, | |
| "loss": 0.1602, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.220703125, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.951388888888889e-05, | |
| "loss": 0.1162, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.22265625, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.950954861111111e-05, | |
| "loss": 0.2148, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.224609375, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.9505208333333333e-05, | |
| "loss": 0.3359, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.2265625, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.9500868055555557e-05, | |
| "loss": 0.5312, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.228515625, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.9496527777777778e-05, | |
| "loss": 0.2285, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.23046875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.9492187500000002e-05, | |
| "loss": 0.2852, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.232421875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.9487847222222226e-05, | |
| "loss": 0.1426, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.234375, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.9483506944444447e-05, | |
| "loss": 0.2246, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.236328125, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.9479166666666668e-05, | |
| "loss": 0.2305, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.23828125, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.947482638888889e-05, | |
| "loss": 0.0825, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.240234375, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 1.9470486111111113e-05, | |
| "loss": 0.332, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.2421875, | |
| "grad_norm": 0.41796875, | |
| "learning_rate": 1.9466145833333334e-05, | |
| "loss": 0.0952, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.244140625, | |
| "grad_norm": 1.734375, | |
| "learning_rate": 1.946180555555556e-05, | |
| "loss": 0.25, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.24609375, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.945746527777778e-05, | |
| "loss": 0.2129, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.248046875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.9453125e-05, | |
| "loss": 0.125, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 1.640625, | |
| "learning_rate": 1.9448784722222224e-05, | |
| "loss": 0.3281, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.251953125, | |
| "grad_norm": 1.2109375, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.2402, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.25390625, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.944010416666667e-05, | |
| "loss": 0.3516, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.255859375, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 1.943576388888889e-05, | |
| "loss": 0.2207, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.2578125, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.9431423611111115e-05, | |
| "loss": 0.3789, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.259765625, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9427083333333336e-05, | |
| "loss": 0.4258, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.26171875, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.9422743055555557e-05, | |
| "loss": 0.2559, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.263671875, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 1.9418402777777778e-05, | |
| "loss": 0.1436, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.265625, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.9414062500000002e-05, | |
| "loss": 0.1602, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.267578125, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.9409722222222226e-05, | |
| "loss": 0.2891, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.26953125, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.9405381944444447e-05, | |
| "loss": 0.291, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.26953125, | |
| "eval_loss": 0.24764688313007355, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.7906569343065694, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9538686131386861, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9039416058394161, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9325547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8524077447628757, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8512641640597852, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8765610516970377, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.7906569343065694, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09538686131386861, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3013138686131387, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18651094890510947, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.7906569343065694, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9538686131386861, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9039416058394161, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9325547445255474, | |
| "eval_runtime": 441.6098, | |
| "eval_samples_per_second": 7.837, | |
| "eval_steps_per_second": 0.125, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.271484375, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 1.9401041666666668e-05, | |
| "loss": 0.1484, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.2734375, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 1.939670138888889e-05, | |
| "loss": 0.1055, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.275390625, | |
| "grad_norm": 1.25, | |
| "learning_rate": 1.9392361111111113e-05, | |
| "loss": 0.2773, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.27734375, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.9388020833333334e-05, | |
| "loss": 0.3125, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.279296875, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.9383680555555558e-05, | |
| "loss": 0.1953, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.28125, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.937934027777778e-05, | |
| "loss": 0.2617, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.283203125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.9375e-05, | |
| "loss": 0.1445, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.28515625, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.9370659722222224e-05, | |
| "loss": 0.1689, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.287109375, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 1.9366319444444445e-05, | |
| "loss": 0.2656, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.2890625, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 1.936197916666667e-05, | |
| "loss": 0.3945, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.291015625, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 1.935763888888889e-05, | |
| "loss": 0.1504, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.29296875, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.9353298611111115e-05, | |
| "loss": 0.248, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.294921875, | |
| "grad_norm": 1.796875, | |
| "learning_rate": 1.9348958333333336e-05, | |
| "loss": 0.3281, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.296875, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.9344618055555556e-05, | |
| "loss": 0.1387, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.298828125, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.9340277777777777e-05, | |
| "loss": 0.1377, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.30078125, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 1.93359375e-05, | |
| "loss": 0.2188, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.302734375, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.9331597222222226e-05, | |
| "loss": 0.1748, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.3046875, | |
| "grad_norm": 1.5703125, | |
| "learning_rate": 1.9327256944444447e-05, | |
| "loss": 0.1016, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.306640625, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.9322916666666668e-05, | |
| "loss": 0.1836, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.30859375, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.931857638888889e-05, | |
| "loss": 0.2891, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.310546875, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.9314236111111113e-05, | |
| "loss": 0.3281, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.9309895833333334e-05, | |
| "loss": 0.293, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.314453125, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.9305555555555558e-05, | |
| "loss": 0.2402, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.31640625, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.930121527777778e-05, | |
| "loss": 0.1846, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.318359375, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.9296875000000003e-05, | |
| "loss": 0.2852, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.3203125, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.9292534722222224e-05, | |
| "loss": 0.1328, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.322265625, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.9288194444444445e-05, | |
| "loss": 0.1475, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.32421875, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 1.928385416666667e-05, | |
| "loss": 0.1816, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.326171875, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.927951388888889e-05, | |
| "loss": 0.2422, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.328125, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.9275173611111114e-05, | |
| "loss": 0.1504, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.330078125, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.9270833333333335e-05, | |
| "loss": 0.1436, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.33203125, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.9266493055555556e-05, | |
| "loss": 0.332, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.333984375, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.9262152777777777e-05, | |
| "loss": 0.3555, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.3359375, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.92578125e-05, | |
| "loss": 0.3828, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.337890625, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.9253472222222226e-05, | |
| "loss": 0.2969, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.33984375, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.9249131944444447e-05, | |
| "loss": 0.2178, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.341796875, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.9244791666666667e-05, | |
| "loss": 0.2695, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.34375, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.924045138888889e-05, | |
| "loss": 0.3965, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.345703125, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 1.9236111111111113e-05, | |
| "loss": 0.1504, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.34765625, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9231770833333334e-05, | |
| "loss": 0.2734, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.349609375, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.9227430555555558e-05, | |
| "loss": 0.1641, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.3515625, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.922309027777778e-05, | |
| "loss": 0.2988, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.353515625, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.9218750000000003e-05, | |
| "loss": 0.3086, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.35546875, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 1.9214409722222224e-05, | |
| "loss": 0.3066, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.357421875, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.9210069444444445e-05, | |
| "loss": 0.25, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.359375, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 1.920572916666667e-05, | |
| "loss": 0.4805, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.361328125, | |
| "grad_norm": 1.78125, | |
| "learning_rate": 1.920138888888889e-05, | |
| "loss": 0.248, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.36328125, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.9197048611111114e-05, | |
| "loss": 0.2246, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.365234375, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.9192708333333335e-05, | |
| "loss": 0.1895, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.3671875, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 1.9188368055555556e-05, | |
| "loss": 0.2656, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.3671875, | |
| "eval_loss": 0.24312134087085724, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8061313868613139, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9553284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9068613138686131, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9331386861313868, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.861092890004559, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8600187695516173, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8834104338330537, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8061313868613139, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09553284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.302287104622871, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18662773722627737, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8061313868613139, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9553284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9068613138686131, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9331386861313868, | |
| "eval_runtime": 441.946, | |
| "eval_samples_per_second": 7.831, | |
| "eval_steps_per_second": 0.124, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.369140625, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.9184027777777777e-05, | |
| "loss": 0.2148, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.37109375, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 1.91796875e-05, | |
| "loss": 0.2441, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.373046875, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.9175347222222225e-05, | |
| "loss": 0.1289, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.9171006944444446e-05, | |
| "loss": 0.2324, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.376953125, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 1.916666666666667e-05, | |
| "loss": 0.3809, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.37890625, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.916232638888889e-05, | |
| "loss": 0.1201, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 1.380859375, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.9157986111111112e-05, | |
| "loss": 0.2617, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 1.3828125, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.9153645833333333e-05, | |
| "loss": 0.1011, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 1.384765625, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.9149305555555558e-05, | |
| "loss": 0.373, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 1.38671875, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.914496527777778e-05, | |
| "loss": 0.2012, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.388671875, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 1.9140625000000003e-05, | |
| "loss": 0.5195, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 1.390625, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 1.9136284722222224e-05, | |
| "loss": 0.2598, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 1.392578125, | |
| "grad_norm": 1.2265625, | |
| "learning_rate": 1.9131944444444445e-05, | |
| "loss": 0.4141, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 1.39453125, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.912760416666667e-05, | |
| "loss": 0.2441, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 1.396484375, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.912326388888889e-05, | |
| "loss": 0.3086, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.3984375, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.9118923611111114e-05, | |
| "loss": 0.3379, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 1.400390625, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 1.9114583333333335e-05, | |
| "loss": 0.0669, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 1.40234375, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.9110243055555556e-05, | |
| "loss": 0.2305, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 1.404296875, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 1.9105902777777777e-05, | |
| "loss": 0.04, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 1.40625, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.91015625e-05, | |
| "loss": 0.1367, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.408203125, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.9097222222222225e-05, | |
| "loss": 0.2383, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 1.41015625, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.9092881944444446e-05, | |
| "loss": 0.3301, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 1.412109375, | |
| "grad_norm": 2.0625, | |
| "learning_rate": 1.908854166666667e-05, | |
| "loss": 0.2021, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 1.4140625, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 1.908420138888889e-05, | |
| "loss": 0.2754, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 1.416015625, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.9079861111111112e-05, | |
| "loss": 0.1318, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.41796875, | |
| "grad_norm": 1.2421875, | |
| "learning_rate": 1.9075520833333333e-05, | |
| "loss": 0.2354, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.419921875, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.9071180555555557e-05, | |
| "loss": 0.2656, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 1.421875, | |
| "grad_norm": 0.9921875, | |
| "learning_rate": 1.9066840277777778e-05, | |
| "loss": 0.4141, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 1.423828125, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.9062500000000003e-05, | |
| "loss": 0.207, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 1.42578125, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 1.9058159722222223e-05, | |
| "loss": 0.2695, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.427734375, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.9053819444444444e-05, | |
| "loss": 0.3906, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 1.4296875, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.904947916666667e-05, | |
| "loss": 0.2393, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 1.431640625, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.904513888888889e-05, | |
| "loss": 0.2051, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 1.43359375, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.9040798611111114e-05, | |
| "loss": 0.207, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 1.435546875, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.9036458333333335e-05, | |
| "loss": 0.209, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 1.265625, | |
| "learning_rate": 1.903211805555556e-05, | |
| "loss": 0.4785, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 1.439453125, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.902777777777778e-05, | |
| "loss": 0.2559, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 1.44140625, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.90234375e-05, | |
| "loss": 0.1426, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 1.443359375, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.9019097222222225e-05, | |
| "loss": 0.2344, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 1.4453125, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.9014756944444446e-05, | |
| "loss": 0.1328, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.447265625, | |
| "grad_norm": 1.375, | |
| "learning_rate": 1.901041666666667e-05, | |
| "loss": 0.3359, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 1.44921875, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 1.900607638888889e-05, | |
| "loss": 0.2695, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 1.451171875, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.9001736111111112e-05, | |
| "loss": 0.1846, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 1.453125, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.8997395833333333e-05, | |
| "loss": 0.2324, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 1.455078125, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.8993055555555557e-05, | |
| "loss": 0.3828, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 1.45703125, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.8988715277777778e-05, | |
| "loss": 0.3203, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 1.458984375, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.8984375000000002e-05, | |
| "loss": 0.2334, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 1.4609375, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.8980034722222223e-05, | |
| "loss": 0.2422, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.462890625, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.8975694444444444e-05, | |
| "loss": 0.2119, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 1.46484375, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.897135416666667e-05, | |
| "loss": 0.1943, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.46484375, | |
| "eval_loss": 0.24227674305438995, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8008759124087591, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9103649635036496, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9343065693430657, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8593047422647561, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8581260572355471, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8820313017011214, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8008759124087591, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.0955036496350365, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3034549878345499, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18686131386861313, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8008759124087591, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9103649635036496, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9343065693430657, | |
| "eval_runtime": 440.6879, | |
| "eval_samples_per_second": 7.854, | |
| "eval_steps_per_second": 0.125, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.466796875, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 1.896701388888889e-05, | |
| "loss": 0.3203, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 1.46875, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 1.8962673611111114e-05, | |
| "loss": 0.3594, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 1.470703125, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.8958333333333334e-05, | |
| "loss": 0.1895, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 1.47265625, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.895399305555556e-05, | |
| "loss": 0.2197, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 1.474609375, | |
| "grad_norm": 0.455078125, | |
| "learning_rate": 1.894965277777778e-05, | |
| "loss": 0.1182, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 1.4765625, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.89453125e-05, | |
| "loss": 0.2363, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 1.478515625, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.8940972222222225e-05, | |
| "loss": 0.2168, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 1.48046875, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 1.8936631944444446e-05, | |
| "loss": 0.375, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 1.482421875, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 1.893229166666667e-05, | |
| "loss": 0.2578, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 1.484375, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.892795138888889e-05, | |
| "loss": 0.2871, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.486328125, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.8923611111111112e-05, | |
| "loss": 0.2217, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 1.48828125, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.8919270833333333e-05, | |
| "loss": 0.3047, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 1.490234375, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.8914930555555557e-05, | |
| "loss": 0.1748, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 1.4921875, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.8910590277777778e-05, | |
| "loss": 0.2461, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 1.494140625, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.8906250000000002e-05, | |
| "loss": 0.1729, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 1.49609375, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.8901909722222226e-05, | |
| "loss": 0.1592, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 1.498046875, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.8897569444444447e-05, | |
| "loss": 0.4277, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.8893229166666668e-05, | |
| "loss": 0.1602, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 1.501953125, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0752, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 1.50390625, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.8884548611111113e-05, | |
| "loss": 0.2832, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.505859375, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.8880208333333334e-05, | |
| "loss": 0.2422, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 1.5078125, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.887586805555556e-05, | |
| "loss": 0.25, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 1.509765625, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.887152777777778e-05, | |
| "loss": 0.4004, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 1.51171875, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.88671875e-05, | |
| "loss": 0.2207, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 1.513671875, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.8862847222222225e-05, | |
| "loss": 0.209, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.515625, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.8858506944444446e-05, | |
| "loss": 0.2695, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 1.517578125, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.885416666666667e-05, | |
| "loss": 0.1553, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 1.51953125, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.884982638888889e-05, | |
| "loss": 0.1455, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 1.521484375, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 1.884548611111111e-05, | |
| "loss": 0.1455, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 1.5234375, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.8841145833333332e-05, | |
| "loss": 0.1226, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.525390625, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.8836805555555557e-05, | |
| "loss": 0.1914, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 1.52734375, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.8832465277777778e-05, | |
| "loss": 0.2109, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 1.529296875, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.8828125000000002e-05, | |
| "loss": 0.2539, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 1.53125, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.8823784722222226e-05, | |
| "loss": 0.2139, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 1.533203125, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 1.8819444444444447e-05, | |
| "loss": 0.1865, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 1.53515625, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.8815104166666668e-05, | |
| "loss": 0.1157, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 1.537109375, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.881076388888889e-05, | |
| "loss": 0.1582, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 1.5390625, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.8806423611111113e-05, | |
| "loss": 0.1592, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 1.541015625, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.8802083333333334e-05, | |
| "loss": 0.3105, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 1.54296875, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.879774305555556e-05, | |
| "loss": 0.2871, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.544921875, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.879340277777778e-05, | |
| "loss": 0.2236, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 1.546875, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.87890625e-05, | |
| "loss": 0.4453, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.548828125, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 1.8784722222222224e-05, | |
| "loss": 0.4492, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 1.55078125, | |
| "grad_norm": 1.375, | |
| "learning_rate": 1.8780381944444445e-05, | |
| "loss": 0.4414, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 1.552734375, | |
| "grad_norm": 1.7109375, | |
| "learning_rate": 1.877604166666667e-05, | |
| "loss": 0.377, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 1.5546875, | |
| "grad_norm": 1.2890625, | |
| "learning_rate": 1.877170138888889e-05, | |
| "loss": 0.4082, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 1.556640625, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 1.8767361111111115e-05, | |
| "loss": 0.3418, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 1.55859375, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.8763020833333336e-05, | |
| "loss": 0.1099, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 1.560546875, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.8758680555555557e-05, | |
| "loss": 0.3691, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.8754340277777777e-05, | |
| "loss": 0.0903, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "eval_loss": 0.23666280508041382, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8064233576642336, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9544525547445255, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9062773722627737, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9334306569343066, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8618246874556312, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8607057119684862, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8837761181209626, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8064233576642336, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09544525547445255, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30209245742092455, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18668613138686135, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8064233576642336, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9544525547445255, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9062773722627737, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9334306569343066, | |
| "eval_runtime": 440.8788, | |
| "eval_samples_per_second": 7.85, | |
| "eval_steps_per_second": 0.125, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.564453125, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.1719, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.56640625, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.8745659722222226e-05, | |
| "loss": 0.168, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 1.568359375, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.8741319444444447e-05, | |
| "loss": 0.2441, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 1.5703125, | |
| "grad_norm": 0.4921875, | |
| "learning_rate": 1.8736979166666668e-05, | |
| "loss": 0.1104, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 1.572265625, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.873263888888889e-05, | |
| "loss": 0.1543, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 1.57421875, | |
| "grad_norm": 0.77734375, | |
| "learning_rate": 1.8728298611111113e-05, | |
| "loss": 0.3203, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 1.576171875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.8723958333333334e-05, | |
| "loss": 0.0835, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 1.578125, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 1.8719618055555558e-05, | |
| "loss": 0.062, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 1.580078125, | |
| "grad_norm": 0.625, | |
| "learning_rate": 1.871527777777778e-05, | |
| "loss": 0.1602, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 1.58203125, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 1.87109375e-05, | |
| "loss": 0.208, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.583984375, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.8706597222222224e-05, | |
| "loss": 0.2061, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 1.5859375, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 1.8702256944444445e-05, | |
| "loss": 0.2773, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 1.587890625, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.869791666666667e-05, | |
| "loss": 0.1416, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 1.58984375, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 1.869357638888889e-05, | |
| "loss": 0.3477, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 1.591796875, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.8689236111111115e-05, | |
| "loss": 0.2812, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.59375, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 1.8684895833333335e-05, | |
| "loss": 0.4395, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 1.595703125, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.8680555555555556e-05, | |
| "loss": 0.2988, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 1.59765625, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.8676215277777777e-05, | |
| "loss": 0.3594, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 1.599609375, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.8671875e-05, | |
| "loss": 0.334, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.6015625, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.8667534722222226e-05, | |
| "loss": 0.166, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.603515625, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.8663194444444447e-05, | |
| "loss": 0.1445, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 1.60546875, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.8658854166666668e-05, | |
| "loss": 0.2969, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 1.607421875, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.865451388888889e-05, | |
| "loss": 0.25, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 1.609375, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.8650173611111113e-05, | |
| "loss": 0.124, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 1.611328125, | |
| "grad_norm": 0.41015625, | |
| "learning_rate": 1.8645833333333334e-05, | |
| "loss": 0.0894, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.61328125, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 1.8641493055555558e-05, | |
| "loss": 0.1084, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 1.615234375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.863715277777778e-05, | |
| "loss": 0.1504, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 1.6171875, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.8632812500000003e-05, | |
| "loss": 0.2812, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 1.619140625, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.8628472222222224e-05, | |
| "loss": 0.4023, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 1.62109375, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.8624131944444445e-05, | |
| "loss": 0.5078, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.623046875, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.861979166666667e-05, | |
| "loss": 0.1348, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.861545138888889e-05, | |
| "loss": 0.1855, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 1.626953125, | |
| "grad_norm": 1.3046875, | |
| "learning_rate": 1.8611111111111114e-05, | |
| "loss": 0.3066, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 1.62890625, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.8606770833333335e-05, | |
| "loss": 0.373, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 1.630859375, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.8602430555555556e-05, | |
| "loss": 0.2227, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 1.6328125, | |
| "grad_norm": 1.65625, | |
| "learning_rate": 1.8598090277777777e-05, | |
| "loss": 0.3711, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.634765625, | |
| "grad_norm": 1.9375, | |
| "learning_rate": 1.859375e-05, | |
| "loss": 0.1875, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 1.63671875, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.8589409722222226e-05, | |
| "loss": 0.1895, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 1.638671875, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 1.8585069444444447e-05, | |
| "loss": 0.1846, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 1.640625, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.8580729166666667e-05, | |
| "loss": 0.2285, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.642578125, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.8576388888888888e-05, | |
| "loss": 0.2266, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 1.64453125, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.8572048611111113e-05, | |
| "loss": 0.1777, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 1.646484375, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.8567708333333333e-05, | |
| "loss": 0.2695, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 1.6484375, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 1.8563368055555558e-05, | |
| "loss": 0.3203, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 1.650390625, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.855902777777778e-05, | |
| "loss": 0.2422, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 1.65234375, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.8554687500000003e-05, | |
| "loss": 0.207, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 1.654296875, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.8550347222222224e-05, | |
| "loss": 0.3574, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 1.65625, | |
| "grad_norm": 0.40234375, | |
| "learning_rate": 1.8546006944444445e-05, | |
| "loss": 0.0405, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 1.658203125, | |
| "grad_norm": 0.4765625, | |
| "learning_rate": 1.854166666666667e-05, | |
| "loss": 0.1426, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 1.66015625, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 1.853732638888889e-05, | |
| "loss": 0.3008, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.66015625, | |
| "eval_loss": 0.23428575694561005, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8102189781021898, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9071532846715329, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9345985401459854, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8637674561270959, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8626299385934427, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8853440183292811, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8102189781021898, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.0955036496350365, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30238442822384426, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1869197080291971, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8102189781021898, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9071532846715329, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9345985401459854, | |
| "eval_runtime": 441.5288, | |
| "eval_samples_per_second": 7.839, | |
| "eval_steps_per_second": 0.125, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.662109375, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 1.8532986111111114e-05, | |
| "loss": 0.1602, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 1.6640625, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.8528645833333335e-05, | |
| "loss": 0.1387, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 1.666015625, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 1.8524305555555556e-05, | |
| "loss": 0.064, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 1.66796875, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.8519965277777777e-05, | |
| "loss": 0.0815, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 1.669921875, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.8515625e-05, | |
| "loss": 0.1836, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 1.671875, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 1.8511284722222225e-05, | |
| "loss": 0.3359, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 1.673828125, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 1.8506944444444446e-05, | |
| "loss": 0.1001, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 1.67578125, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.850260416666667e-05, | |
| "loss": 0.1562, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 1.677734375, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 1.849826388888889e-05, | |
| "loss": 0.377, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 1.6796875, | |
| "grad_norm": 1.3203125, | |
| "learning_rate": 1.8493923611111112e-05, | |
| "loss": 0.249, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.681640625, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 1.8489583333333333e-05, | |
| "loss": 0.0835, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 1.68359375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.8485243055555558e-05, | |
| "loss": 0.1143, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 1.685546875, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.848090277777778e-05, | |
| "loss": 0.3398, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 1.6875, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 1.8476562500000003e-05, | |
| "loss": 0.1797, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 1.689453125, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.8472222222222224e-05, | |
| "loss": 0.2695, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 1.69140625, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.8467881944444445e-05, | |
| "loss": 0.2773, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 1.693359375, | |
| "grad_norm": 0.423828125, | |
| "learning_rate": 1.846354166666667e-05, | |
| "loss": 0.0718, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 1.6953125, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 1.845920138888889e-05, | |
| "loss": 0.0613, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 1.697265625, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.8454861111111114e-05, | |
| "loss": 0.1699, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 1.69921875, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 1.8450520833333335e-05, | |
| "loss": 0.1953, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.701171875, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 1.8446180555555556e-05, | |
| "loss": 0.2051, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 1.703125, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 1.8441840277777777e-05, | |
| "loss": 0.1807, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 1.705078125, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 1.84375e-05, | |
| "loss": 0.2812, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 1.70703125, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.8433159722222225e-05, | |
| "loss": 0.1084, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 1.708984375, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.8428819444444446e-05, | |
| "loss": 0.2129, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.7109375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.842447916666667e-05, | |
| "loss": 0.3145, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 1.712890625, | |
| "grad_norm": 1.6171875, | |
| "learning_rate": 1.842013888888889e-05, | |
| "loss": 0.2324, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 1.71484375, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.8415798611111112e-05, | |
| "loss": 0.334, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 1.716796875, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.8411458333333333e-05, | |
| "loss": 0.2002, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 1.71875, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 1.8407118055555557e-05, | |
| "loss": 0.2031, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.720703125, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.8402777777777778e-05, | |
| "loss": 0.1582, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 1.72265625, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.8398437500000003e-05, | |
| "loss": 0.1816, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 1.724609375, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.8394097222222223e-05, | |
| "loss": 0.3691, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 1.7265625, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.8389756944444444e-05, | |
| "loss": 0.1777, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 1.728515625, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.838541666666667e-05, | |
| "loss": 0.293, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 1.73046875, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.838107638888889e-05, | |
| "loss": 0.2051, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 1.732421875, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 1.8376736111111114e-05, | |
| "loss": 0.5469, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 1.734375, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 1.8372395833333335e-05, | |
| "loss": 0.2344, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 1.736328125, | |
| "grad_norm": 0.45703125, | |
| "learning_rate": 1.836805555555556e-05, | |
| "loss": 0.1328, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 1.73828125, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.836371527777778e-05, | |
| "loss": 0.1484, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.740234375, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.8359375e-05, | |
| "loss": 0.2988, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 1.7421875, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.8355034722222225e-05, | |
| "loss": 0.1543, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 1.744140625, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.8350694444444446e-05, | |
| "loss": 0.1885, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 1.74609375, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.834635416666667e-05, | |
| "loss": 0.166, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 1.748046875, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.834201388888889e-05, | |
| "loss": 0.2148, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 1.8337673611111112e-05, | |
| "loss": 0.127, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.751953125, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.2461, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 1.75390625, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.8328993055555557e-05, | |
| "loss": 0.3301, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 1.755859375, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 1.8324652777777778e-05, | |
| "loss": 0.3027, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 1.7578125, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.8320312500000002e-05, | |
| "loss": 0.3594, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.7578125, | |
| "eval_loss": 0.23208175599575043, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8078832116788321, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9547445255474453, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9068613138686131, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9345985401459854, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8631237777515689, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8619469354651839, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8848111660941772, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8078832116788321, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09547445255474453, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3022871046228711, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1869197080291971, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8078832116788321, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9547445255474453, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9068613138686131, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9345985401459854, | |
| "eval_runtime": 441.8236, | |
| "eval_samples_per_second": 7.833, | |
| "eval_steps_per_second": 0.124, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.759765625, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.8315972222222223e-05, | |
| "loss": 0.1953, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 1.76171875, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.8311631944444444e-05, | |
| "loss": 0.1123, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 1.763671875, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.830729166666667e-05, | |
| "loss": 0.1699, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 1.765625, | |
| "grad_norm": 1.4453125, | |
| "learning_rate": 1.830295138888889e-05, | |
| "loss": 0.1709, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 1.767578125, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.8298611111111114e-05, | |
| "loss": 0.1621, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 1.76953125, | |
| "grad_norm": 1.703125, | |
| "learning_rate": 1.8294270833333334e-05, | |
| "loss": 0.3516, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 1.771484375, | |
| "grad_norm": 0.474609375, | |
| "learning_rate": 1.828993055555556e-05, | |
| "loss": 0.1445, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 1.7734375, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.828559027777778e-05, | |
| "loss": 0.1865, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 1.775390625, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.828125e-05, | |
| "loss": 0.3164, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 1.77734375, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.8276909722222225e-05, | |
| "loss": 0.2695, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.779296875, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.8272569444444446e-05, | |
| "loss": 0.3945, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 1.78125, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.826822916666667e-05, | |
| "loss": 0.3027, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 1.783203125, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.826388888888889e-05, | |
| "loss": 0.3066, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 1.78515625, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.8259548611111112e-05, | |
| "loss": 0.3223, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 1.787109375, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 1.8255208333333333e-05, | |
| "loss": 0.2539, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 1.7890625, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.8250868055555557e-05, | |
| "loss": 0.3242, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 1.791015625, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.8246527777777778e-05, | |
| "loss": 0.1348, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 1.79296875, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 1.8242187500000002e-05, | |
| "loss": 0.2275, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 1.794921875, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 1.8237847222222226e-05, | |
| "loss": 0.252, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 1.796875, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.8233506944444447e-05, | |
| "loss": 0.1738, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.798828125, | |
| "grad_norm": 0.318359375, | |
| "learning_rate": 1.8229166666666668e-05, | |
| "loss": 0.0283, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 1.80078125, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 1.822482638888889e-05, | |
| "loss": 0.3086, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 1.802734375, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.8220486111111113e-05, | |
| "loss": 0.1914, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 1.8046875, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.8216145833333334e-05, | |
| "loss": 0.1787, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 1.806640625, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.821180555555556e-05, | |
| "loss": 0.1611, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.80859375, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.820746527777778e-05, | |
| "loss": 0.1572, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 1.810546875, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.8203125e-05, | |
| "loss": 0.1885, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 1.8198784722222225e-05, | |
| "loss": 0.5508, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 1.814453125, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.8194444444444445e-05, | |
| "loss": 0.1973, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 1.81640625, | |
| "grad_norm": 1.78125, | |
| "learning_rate": 1.819010416666667e-05, | |
| "loss": 0.4238, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.818359375, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.818576388888889e-05, | |
| "loss": 0.1445, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 1.8203125, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.818142361111111e-05, | |
| "loss": 0.2461, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 1.822265625, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.8177083333333332e-05, | |
| "loss": 0.3613, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 1.82421875, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.8172743055555557e-05, | |
| "loss": 0.2393, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 1.826171875, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.8168402777777778e-05, | |
| "loss": 0.21, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 1.828125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.8164062500000002e-05, | |
| "loss": 0.3457, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 1.830078125, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.8159722222222226e-05, | |
| "loss": 0.1309, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 1.83203125, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 1.8155381944444447e-05, | |
| "loss": 0.293, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 1.833984375, | |
| "grad_norm": 1.0859375, | |
| "learning_rate": 1.8151041666666668e-05, | |
| "loss": 0.1846, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 1.8359375, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.814670138888889e-05, | |
| "loss": 0.4727, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.837890625, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.8142361111111113e-05, | |
| "loss": 0.2695, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 1.83984375, | |
| "grad_norm": 1.421875, | |
| "learning_rate": 1.8138020833333334e-05, | |
| "loss": 0.5195, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 1.841796875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.813368055555556e-05, | |
| "loss": 0.1914, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 1.84375, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.812934027777778e-05, | |
| "loss": 0.3086, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 1.845703125, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 1.8125e-05, | |
| "loss": 0.1904, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.84765625, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.8120659722222224e-05, | |
| "loss": 0.2832, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 1.849609375, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.8116319444444445e-05, | |
| "loss": 0.1484, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 1.8515625, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.811197916666667e-05, | |
| "loss": 0.2891, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 1.853515625, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.810763888888889e-05, | |
| "loss": 0.373, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 1.85546875, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.8103298611111115e-05, | |
| "loss": 0.2988, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.85546875, | |
| "eval_loss": 0.23012372851371765, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.811970802919708, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9360583941605839, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8659550126943659, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8647350249102075, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.88700575504157, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.811970802919708, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30364963503649633, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1872116788321168, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.811970802919708, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9550364963503649, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9360583941605839, | |
| "eval_runtime": 441.948, | |
| "eval_samples_per_second": 7.831, | |
| "eval_steps_per_second": 0.124, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.857421875, | |
| "grad_norm": 0.25, | |
| "learning_rate": 1.8098958333333336e-05, | |
| "loss": 0.0264, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 1.859375, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 1.8094618055555557e-05, | |
| "loss": 0.2539, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 1.861328125, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 1.8090277777777777e-05, | |
| "loss": 0.5195, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 1.86328125, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 1.8085937500000002e-05, | |
| "loss": 0.3047, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 1.865234375, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 1.8081597222222226e-05, | |
| "loss": 0.2432, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 1.8671875, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.8077256944444447e-05, | |
| "loss": 0.2754, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 1.869140625, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 1.8072916666666668e-05, | |
| "loss": 0.2412, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 1.87109375, | |
| "grad_norm": 0.384765625, | |
| "learning_rate": 1.806857638888889e-05, | |
| "loss": 0.0986, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 1.873046875, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.8064236111111113e-05, | |
| "loss": 0.2539, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 1.6171875, | |
| "learning_rate": 1.8059895833333334e-05, | |
| "loss": 0.3984, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.876953125, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.8055555555555558e-05, | |
| "loss": 0.1865, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 1.87890625, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.805121527777778e-05, | |
| "loss": 0.1924, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 1.880859375, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.8046875e-05, | |
| "loss": 0.125, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 1.8828125, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.8042534722222224e-05, | |
| "loss": 0.4297, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 1.884765625, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.8038194444444445e-05, | |
| "loss": 0.2188, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 1.88671875, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.803385416666667e-05, | |
| "loss": 0.1631, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 1.888671875, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 1.802951388888889e-05, | |
| "loss": 0.1797, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 1.890625, | |
| "grad_norm": 1.53125, | |
| "learning_rate": 1.8025173611111115e-05, | |
| "loss": 0.2344, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 1.892578125, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 1.8020833333333335e-05, | |
| "loss": 0.168, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 1.89453125, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.8016493055555556e-05, | |
| "loss": 0.207, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.896484375, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 1.8012152777777777e-05, | |
| "loss": 0.4199, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 1.8984375, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 1.80078125e-05, | |
| "loss": 0.248, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 1.900390625, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.8003472222222226e-05, | |
| "loss": 0.2012, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 1.90234375, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.7999131944444447e-05, | |
| "loss": 0.3984, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 1.904296875, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.7994791666666668e-05, | |
| "loss": 0.207, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.90625, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.799045138888889e-05, | |
| "loss": 0.2207, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 1.908203125, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.7986111111111113e-05, | |
| "loss": 0.0801, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 1.91015625, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.7981770833333334e-05, | |
| "loss": 0.1318, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 1.912109375, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.7977430555555558e-05, | |
| "loss": 0.2734, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 1.9140625, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.797309027777778e-05, | |
| "loss": 0.2109, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.916015625, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 1.7968750000000003e-05, | |
| "loss": 0.4043, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 1.91796875, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.7964409722222224e-05, | |
| "loss": 0.0747, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 1.919921875, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.7960069444444445e-05, | |
| "loss": 0.1914, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 1.921875, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.795572916666667e-05, | |
| "loss": 0.2139, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 1.923828125, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.795138888888889e-05, | |
| "loss": 0.1797, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 1.92578125, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.7947048611111114e-05, | |
| "loss": 0.5195, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 1.927734375, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.7942708333333335e-05, | |
| "loss": 0.2041, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 1.9296875, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 1.7938368055555556e-05, | |
| "loss": 0.1572, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 1.931640625, | |
| "grad_norm": 2.078125, | |
| "learning_rate": 1.7934027777777777e-05, | |
| "loss": 0.6992, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 1.93359375, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.79296875e-05, | |
| "loss": 0.2832, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.935546875, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.7925347222222226e-05, | |
| "loss": 0.1309, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 1.9375, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.7921006944444446e-05, | |
| "loss": 0.4121, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 1.939453125, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 1.7916666666666667e-05, | |
| "loss": 0.1953, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 1.94140625, | |
| "grad_norm": 0.52734375, | |
| "learning_rate": 1.7912326388888888e-05, | |
| "loss": 0.1025, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 1.943359375, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 1.7907986111111113e-05, | |
| "loss": 0.1543, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 1.9453125, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.7903645833333333e-05, | |
| "loss": 0.2285, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 1.947265625, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.7899305555555558e-05, | |
| "loss": 0.4355, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 1.94921875, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.789496527777778e-05, | |
| "loss": 0.3066, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 1.951171875, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.7890625000000003e-05, | |
| "loss": 0.2578, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 1.953125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.7886284722222224e-05, | |
| "loss": 0.2812, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.953125, | |
| "eval_loss": 0.22827781736850739, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8105109489051094, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9567883211678833, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9097810218978102, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9351824817518248, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8648911844464655, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8638131155138458, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8866707151991599, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8105109489051094, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09567883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3032603406326034, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18703649635036498, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8105109489051094, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9567883211678833, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9097810218978102, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9351824817518248, | |
| "eval_runtime": 440.6039, | |
| "eval_samples_per_second": 7.855, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.955078125, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.7881944444444445e-05, | |
| "loss": 0.2246, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 1.95703125, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.787760416666667e-05, | |
| "loss": 0.2275, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 1.958984375, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.787326388888889e-05, | |
| "loss": 0.2012, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 1.9609375, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.7868923611111114e-05, | |
| "loss": 0.1924, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 1.962890625, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.7864583333333335e-05, | |
| "loss": 0.2676, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.96484375, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.7860243055555556e-05, | |
| "loss": 0.1914, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 1.966796875, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.7855902777777777e-05, | |
| "loss": 0.2002, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 1.96875, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.78515625e-05, | |
| "loss": 0.5156, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 1.970703125, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.7847222222222225e-05, | |
| "loss": 0.3281, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 1.97265625, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.7842881944444446e-05, | |
| "loss": 0.1787, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.974609375, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 1.783854166666667e-05, | |
| "loss": 0.1309, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 1.9765625, | |
| "grad_norm": 1.78125, | |
| "learning_rate": 1.783420138888889e-05, | |
| "loss": 0.4414, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 1.978515625, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 1.7829861111111112e-05, | |
| "loss": 0.1289, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 1.98046875, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.7825520833333333e-05, | |
| "loss": 0.2852, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 1.982421875, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 1.7821180555555558e-05, | |
| "loss": 0.1157, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.984375, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.781684027777778e-05, | |
| "loss": 0.1973, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 1.986328125, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.7812500000000003e-05, | |
| "loss": 0.2334, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 1.98828125, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.7808159722222224e-05, | |
| "loss": 0.4355, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 1.990234375, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 1.7803819444444444e-05, | |
| "loss": 0.082, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 1.9921875, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.779947916666667e-05, | |
| "loss": 0.334, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.994140625, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 1.779513888888889e-05, | |
| "loss": 0.3984, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 1.99609375, | |
| "grad_norm": 0.6328125, | |
| "learning_rate": 1.7790798611111114e-05, | |
| "loss": 0.1768, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 1.998046875, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.7786458333333335e-05, | |
| "loss": 0.1289, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.7782118055555556e-05, | |
| "loss": 0.2637, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 2.001953125, | |
| "grad_norm": 0.99609375, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.2363, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.00390625, | |
| "grad_norm": 0.5859375, | |
| "learning_rate": 1.77734375e-05, | |
| "loss": 0.1797, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 2.005859375, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.7769097222222225e-05, | |
| "loss": 0.2061, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 2.0078125, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.7764756944444446e-05, | |
| "loss": 0.2812, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 2.009765625, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 1.776041666666667e-05, | |
| "loss": 0.2041, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 2.01171875, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.775607638888889e-05, | |
| "loss": 0.2061, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.013671875, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 1.7751736111111112e-05, | |
| "loss": 0.3184, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 2.015625, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.7747395833333333e-05, | |
| "loss": 0.2432, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 2.017578125, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.7743055555555557e-05, | |
| "loss": 0.2373, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 2.01953125, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.7738715277777778e-05, | |
| "loss": 0.2949, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 2.021484375, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.7734375000000002e-05, | |
| "loss": 0.0991, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.0234375, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.7730034722222223e-05, | |
| "loss": 0.1387, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 2.025390625, | |
| "grad_norm": 0.9765625, | |
| "learning_rate": 1.7725694444444444e-05, | |
| "loss": 0.2148, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 2.02734375, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.772135416666667e-05, | |
| "loss": 0.2441, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 2.029296875, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 1.771701388888889e-05, | |
| "loss": 0.3008, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 2.03125, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.7712673611111114e-05, | |
| "loss": 0.1641, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.033203125, | |
| "grad_norm": 1.3046875, | |
| "learning_rate": 1.7708333333333335e-05, | |
| "loss": 0.2812, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 2.03515625, | |
| "grad_norm": 0.5, | |
| "learning_rate": 1.770399305555556e-05, | |
| "loss": 0.1406, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 2.037109375, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.769965277777778e-05, | |
| "loss": 0.1914, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 2.0390625, | |
| "grad_norm": 1.3125, | |
| "learning_rate": 1.76953125e-05, | |
| "loss": 0.1641, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 2.041015625, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.7690972222222225e-05, | |
| "loss": 0.1377, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.04296875, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.7686631944444446e-05, | |
| "loss": 0.1758, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 2.044921875, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.768229166666667e-05, | |
| "loss": 0.293, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 2.046875, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.767795138888889e-05, | |
| "loss": 0.2773, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 2.048828125, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.7673611111111112e-05, | |
| "loss": 0.1621, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 2.05078125, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.7669270833333333e-05, | |
| "loss": 0.1865, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.05078125, | |
| "eval_loss": 0.22633610665798187, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8108029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9115328467153284, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9351824817518248, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8654028134652041, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8643836171938365, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8871891641189541, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8108029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09570802919708028, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3038442822384428, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18703649635036498, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8108029197080292, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9115328467153284, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9351824817518248, | |
| "eval_runtime": 441.0862, | |
| "eval_samples_per_second": 7.847, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.052734375, | |
| "grad_norm": 1.5546875, | |
| "learning_rate": 1.7664930555555557e-05, | |
| "loss": 0.1553, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 2.0546875, | |
| "grad_norm": 1.375, | |
| "learning_rate": 1.7660590277777778e-05, | |
| "loss": 0.2734, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 2.056640625, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.7656250000000002e-05, | |
| "loss": 0.2891, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.05859375, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.7651909722222223e-05, | |
| "loss": 0.0811, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.060546875, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.7647569444444444e-05, | |
| "loss": 0.2871, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.0625, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 1.764322916666667e-05, | |
| "loss": 0.2715, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.064453125, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.763888888888889e-05, | |
| "loss": 0.0972, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 2.06640625, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.7634548611111114e-05, | |
| "loss": 0.2021, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 2.068359375, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.7630208333333334e-05, | |
| "loss": 0.1846, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 2.0703125, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.762586805555556e-05, | |
| "loss": 0.2734, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.072265625, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.762152777777778e-05, | |
| "loss": 0.1367, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 2.07421875, | |
| "grad_norm": 0.390625, | |
| "learning_rate": 1.76171875e-05, | |
| "loss": 0.0581, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 2.076171875, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 1.7612847222222225e-05, | |
| "loss": 0.21, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 2.078125, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 1.7608506944444446e-05, | |
| "loss": 0.0527, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 2.080078125, | |
| "grad_norm": 1.2734375, | |
| "learning_rate": 1.760416666666667e-05, | |
| "loss": 0.1816, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.08203125, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 1.759982638888889e-05, | |
| "loss": 0.1699, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 2.083984375, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.7595486111111112e-05, | |
| "loss": 0.252, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 2.0859375, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.7591145833333333e-05, | |
| "loss": 0.2637, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 2.087890625, | |
| "grad_norm": 0.40234375, | |
| "learning_rate": 1.7586805555555557e-05, | |
| "loss": 0.0859, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 2.08984375, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.7582465277777778e-05, | |
| "loss": 0.1602, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.091796875, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 1.7578125000000002e-05, | |
| "loss": 0.207, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 2.09375, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.7573784722222223e-05, | |
| "loss": 0.3613, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 2.095703125, | |
| "grad_norm": 0.9921875, | |
| "learning_rate": 1.7569444444444447e-05, | |
| "loss": 0.2617, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 2.09765625, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 1.7565104166666668e-05, | |
| "loss": 0.5898, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 2.099609375, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.756076388888889e-05, | |
| "loss": 0.1523, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.1015625, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.7556423611111113e-05, | |
| "loss": 0.1562, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 2.103515625, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.7552083333333334e-05, | |
| "loss": 0.1719, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 2.10546875, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.754774305555556e-05, | |
| "loss": 0.3242, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 2.107421875, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.754340277777778e-05, | |
| "loss": 0.2275, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 2.109375, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.75390625e-05, | |
| "loss": 0.2051, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.111328125, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.7534722222222225e-05, | |
| "loss": 0.2559, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 2.11328125, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.7530381944444445e-05, | |
| "loss": 0.1826, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 2.115234375, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.752604166666667e-05, | |
| "loss": 0.2324, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 2.1171875, | |
| "grad_norm": 0.5546875, | |
| "learning_rate": 1.752170138888889e-05, | |
| "loss": 0.0562, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 2.119140625, | |
| "grad_norm": 1.9296875, | |
| "learning_rate": 1.751736111111111e-05, | |
| "loss": 0.3066, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.12109375, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.7513020833333332e-05, | |
| "loss": 0.2852, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 2.123046875, | |
| "grad_norm": 1.875, | |
| "learning_rate": 1.7508680555555557e-05, | |
| "loss": 0.3398, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.7504340277777778e-05, | |
| "loss": 0.1377, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 2.126953125, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 0.3848, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 2.12890625, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.7495659722222226e-05, | |
| "loss": 0.1592, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.130859375, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 1.7491319444444447e-05, | |
| "loss": 0.1172, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 2.1328125, | |
| "grad_norm": 0.93359375, | |
| "learning_rate": 1.7486979166666668e-05, | |
| "loss": 0.0864, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 2.134765625, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 1.748263888888889e-05, | |
| "loss": 0.3008, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 2.13671875, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 1.7478298611111113e-05, | |
| "loss": 0.3633, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 2.138671875, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 1.7473958333333334e-05, | |
| "loss": 0.377, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.140625, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.7469618055555558e-05, | |
| "loss": 0.3691, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 2.142578125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.746527777777778e-05, | |
| "loss": 0.1387, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 2.14453125, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.74609375e-05, | |
| "loss": 0.1914, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 2.146484375, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.7456597222222224e-05, | |
| "loss": 0.3984, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 2.1484375, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.7452256944444445e-05, | |
| "loss": 0.2578, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.1484375, | |
| "eval_loss": 0.2263731211423874, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9118248175182482, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9354744525547445, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8664490671761211, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8653803730738038, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.887929121521704, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.0957080291970803, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30394160583941604, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18709489051094894, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9118248175182482, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9354744525547445, | |
| "eval_runtime": 441.5755, | |
| "eval_samples_per_second": 7.838, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.150390625, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 1.744791666666667e-05, | |
| "loss": 0.3145, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 2.15234375, | |
| "grad_norm": 0.484375, | |
| "learning_rate": 1.744357638888889e-05, | |
| "loss": 0.0576, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 2.154296875, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.7439236111111115e-05, | |
| "loss": 0.1777, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 2.15625, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.7434895833333336e-05, | |
| "loss": 0.3477, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 2.158203125, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 1.7430555555555556e-05, | |
| "loss": 0.0933, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.16015625, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.7426215277777777e-05, | |
| "loss": 0.1992, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 2.162109375, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.7421875e-05, | |
| "loss": 0.2246, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 2.1640625, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 1.7417534722222226e-05, | |
| "loss": 0.2178, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 2.166015625, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.7413194444444447e-05, | |
| "loss": 0.2324, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 2.16796875, | |
| "grad_norm": 1.2265625, | |
| "learning_rate": 1.7408854166666668e-05, | |
| "loss": 0.2832, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.169921875, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.740451388888889e-05, | |
| "loss": 0.166, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 2.171875, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.7400173611111113e-05, | |
| "loss": 0.2812, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 2.173828125, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 1.7395833333333334e-05, | |
| "loss": 0.3008, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 2.17578125, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.7391493055555558e-05, | |
| "loss": 0.1699, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 2.177734375, | |
| "grad_norm": 0.482421875, | |
| "learning_rate": 1.738715277777778e-05, | |
| "loss": 0.1426, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 2.1796875, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 1.73828125e-05, | |
| "loss": 0.2256, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 2.181640625, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.7378472222222224e-05, | |
| "loss": 0.2539, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 2.18359375, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.7374131944444445e-05, | |
| "loss": 0.2578, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 2.185546875, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 1.736979166666667e-05, | |
| "loss": 0.2891, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 2.1875, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.736545138888889e-05, | |
| "loss": 0.3047, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.189453125, | |
| "grad_norm": 0.984375, | |
| "learning_rate": 1.7361111111111114e-05, | |
| "loss": 0.1992, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 2.19140625, | |
| "grad_norm": 1.078125, | |
| "learning_rate": 1.7356770833333335e-05, | |
| "loss": 0.2344, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 2.193359375, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.7352430555555556e-05, | |
| "loss": 0.2578, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 2.1953125, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.7348090277777777e-05, | |
| "loss": 0.1807, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 2.197265625, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.734375e-05, | |
| "loss": 0.3887, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.19921875, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.7339409722222226e-05, | |
| "loss": 0.1836, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.201171875, | |
| "grad_norm": 0.4375, | |
| "learning_rate": 1.7335069444444447e-05, | |
| "loss": 0.1035, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 2.203125, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.7330729166666668e-05, | |
| "loss": 0.2266, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 2.205078125, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.732638888888889e-05, | |
| "loss": 0.3672, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 2.20703125, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.7322048611111113e-05, | |
| "loss": 0.2021, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.208984375, | |
| "grad_norm": 0.53125, | |
| "learning_rate": 1.7317708333333334e-05, | |
| "loss": 0.1816, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 2.2109375, | |
| "grad_norm": 0.9765625, | |
| "learning_rate": 1.7313368055555558e-05, | |
| "loss": 0.3789, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 2.212890625, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.730902777777778e-05, | |
| "loss": 0.2734, | |
| "step": 1133 | |
| }, | |
| { | |
| "epoch": 2.21484375, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 1.7304687500000003e-05, | |
| "loss": 0.2373, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 2.216796875, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.7300347222222224e-05, | |
| "loss": 0.1973, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 2.21875, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 1.7296006944444445e-05, | |
| "loss": 0.2969, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 2.220703125, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 1.729166666666667e-05, | |
| "loss": 0.0786, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 2.22265625, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.728732638888889e-05, | |
| "loss": 0.2578, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 2.224609375, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 1.7282986111111114e-05, | |
| "loss": 0.165, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 2.2265625, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.7278645833333335e-05, | |
| "loss": 0.1484, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.228515625, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.7274305555555556e-05, | |
| "loss": 0.168, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 2.23046875, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.7269965277777777e-05, | |
| "loss": 0.1377, | |
| "step": 1142 | |
| }, | |
| { | |
| "epoch": 2.232421875, | |
| "grad_norm": 0.392578125, | |
| "learning_rate": 1.7265625e-05, | |
| "loss": 0.1055, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 2.234375, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.7261284722222226e-05, | |
| "loss": 0.1914, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 2.236328125, | |
| "grad_norm": 1.0859375, | |
| "learning_rate": 1.7256944444444446e-05, | |
| "loss": 0.3965, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 2.23828125, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.7252604166666667e-05, | |
| "loss": 0.3398, | |
| "step": 1146 | |
| }, | |
| { | |
| "epoch": 2.240234375, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.7248263888888888e-05, | |
| "loss": 0.2207, | |
| "step": 1147 | |
| }, | |
| { | |
| "epoch": 2.2421875, | |
| "grad_norm": 0.94921875, | |
| "learning_rate": 1.7243923611111112e-05, | |
| "loss": 0.3281, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 2.244140625, | |
| "grad_norm": 1.5546875, | |
| "learning_rate": 1.7239583333333333e-05, | |
| "loss": 0.2871, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 2.24609375, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 1.7235243055555558e-05, | |
| "loss": 0.2715, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.24609375, | |
| "eval_loss": 0.2248167097568512, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9366423357664233, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8665553817079553, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.86549785656355, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.888036432452033, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09570802919708028, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30364963503649633, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1873284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8125547445255474, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9366423357664233, | |
| "eval_runtime": 440.7242, | |
| "eval_samples_per_second": 7.853, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.248046875, | |
| "grad_norm": 1.265625, | |
| "learning_rate": 1.723090277777778e-05, | |
| "loss": 0.3066, | |
| "step": 1151 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 1.578125, | |
| "learning_rate": 1.7226562500000003e-05, | |
| "loss": 0.2969, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 2.251953125, | |
| "grad_norm": 1.1953125, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.2217, | |
| "step": 1153 | |
| }, | |
| { | |
| "epoch": 2.25390625, | |
| "grad_norm": 1.3828125, | |
| "learning_rate": 1.7217881944444445e-05, | |
| "loss": 0.3281, | |
| "step": 1154 | |
| }, | |
| { | |
| "epoch": 2.255859375, | |
| "grad_norm": 0.96875, | |
| "learning_rate": 1.721354166666667e-05, | |
| "loss": 0.3027, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 2.2578125, | |
| "grad_norm": 1.671875, | |
| "learning_rate": 1.720920138888889e-05, | |
| "loss": 0.4062, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 2.259765625, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.7204861111111114e-05, | |
| "loss": 0.3242, | |
| "step": 1157 | |
| }, | |
| { | |
| "epoch": 2.26171875, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 1.7200520833333335e-05, | |
| "loss": 0.2285, | |
| "step": 1158 | |
| }, | |
| { | |
| "epoch": 2.263671875, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.7196180555555556e-05, | |
| "loss": 0.209, | |
| "step": 1159 | |
| }, | |
| { | |
| "epoch": 2.265625, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 1.7191840277777777e-05, | |
| "loss": 0.3945, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.267578125, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.71875e-05, | |
| "loss": 0.2578, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 2.26953125, | |
| "grad_norm": 1.6015625, | |
| "learning_rate": 1.7183159722222225e-05, | |
| "loss": 0.0879, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 2.271484375, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.7178819444444446e-05, | |
| "loss": 0.0874, | |
| "step": 1163 | |
| }, | |
| { | |
| "epoch": 2.2734375, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.717447916666667e-05, | |
| "loss": 0.2598, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 2.275390625, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.717013888888889e-05, | |
| "loss": 0.1592, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 2.27734375, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 1.7165798611111112e-05, | |
| "loss": 0.2422, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 2.279296875, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.7161458333333333e-05, | |
| "loss": 0.1074, | |
| "step": 1167 | |
| }, | |
| { | |
| "epoch": 2.28125, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.7157118055555557e-05, | |
| "loss": 0.209, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 2.283203125, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.715277777777778e-05, | |
| "loss": 0.1602, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 2.28515625, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.7148437500000003e-05, | |
| "loss": 0.1758, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.287109375, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.7144097222222224e-05, | |
| "loss": 0.291, | |
| "step": 1171 | |
| }, | |
| { | |
| "epoch": 2.2890625, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 1.7139756944444444e-05, | |
| "loss": 0.3906, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 2.291015625, | |
| "grad_norm": 0.453125, | |
| "learning_rate": 1.713541666666667e-05, | |
| "loss": 0.0786, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 2.29296875, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 1.713107638888889e-05, | |
| "loss": 0.2285, | |
| "step": 1174 | |
| }, | |
| { | |
| "epoch": 2.294921875, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.7126736111111114e-05, | |
| "loss": 0.1699, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.296875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.7122395833333335e-05, | |
| "loss": 0.0967, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 2.298828125, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.7118055555555556e-05, | |
| "loss": 0.1504, | |
| "step": 1177 | |
| }, | |
| { | |
| "epoch": 2.30078125, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 1.7113715277777777e-05, | |
| "loss": 0.3574, | |
| "step": 1178 | |
| }, | |
| { | |
| "epoch": 2.302734375, | |
| "grad_norm": 0.875, | |
| "learning_rate": 1.7109375e-05, | |
| "loss": 0.2305, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 2.3046875, | |
| "grad_norm": 0.8828125, | |
| "learning_rate": 1.7105034722222225e-05, | |
| "loss": 0.1177, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.306640625, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.7100694444444446e-05, | |
| "loss": 0.127, | |
| "step": 1181 | |
| }, | |
| { | |
| "epoch": 2.30859375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.709635416666667e-05, | |
| "loss": 0.1875, | |
| "step": 1182 | |
| }, | |
| { | |
| "epoch": 2.310546875, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.709201388888889e-05, | |
| "loss": 0.1504, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.7087673611111112e-05, | |
| "loss": 0.1855, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 2.314453125, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.7083333333333333e-05, | |
| "loss": 0.1338, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 2.31640625, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 1.7078993055555557e-05, | |
| "loss": 0.1777, | |
| "step": 1186 | |
| }, | |
| { | |
| "epoch": 2.318359375, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.7074652777777778e-05, | |
| "loss": 0.3516, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 2.3203125, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.7070312500000002e-05, | |
| "loss": 0.1113, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 2.322265625, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.7065972222222223e-05, | |
| "loss": 0.1602, | |
| "step": 1189 | |
| }, | |
| { | |
| "epoch": 2.32421875, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 1.7061631944444444e-05, | |
| "loss": 0.0718, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.326171875, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.705729166666667e-05, | |
| "loss": 0.2275, | |
| "step": 1191 | |
| }, | |
| { | |
| "epoch": 2.328125, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.705295138888889e-05, | |
| "loss": 0.2559, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 2.330078125, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.7048611111111114e-05, | |
| "loss": 0.106, | |
| "step": 1193 | |
| }, | |
| { | |
| "epoch": 2.33203125, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.7044270833333335e-05, | |
| "loss": 0.1904, | |
| "step": 1194 | |
| }, | |
| { | |
| "epoch": 2.333984375, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 1.703993055555556e-05, | |
| "loss": 0.1641, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 2.3359375, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.703559027777778e-05, | |
| "loss": 0.168, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 2.337890625, | |
| "grad_norm": 1.203125, | |
| "learning_rate": 1.703125e-05, | |
| "loss": 0.2148, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 2.33984375, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.7026909722222225e-05, | |
| "loss": 0.1992, | |
| "step": 1198 | |
| }, | |
| { | |
| "epoch": 2.341796875, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.7022569444444446e-05, | |
| "loss": 0.1582, | |
| "step": 1199 | |
| }, | |
| { | |
| "epoch": 2.34375, | |
| "grad_norm": 0.87109375, | |
| "learning_rate": 1.701822916666667e-05, | |
| "loss": 0.3066, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.34375, | |
| "eval_loss": 0.22392641007900238, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8143065693430657, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9118248175182482, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9366423357664233, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8675482412810842, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8664633298574905, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8887686134979592, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8143065693430657, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09570802919708028, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30394160583941604, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1873284671532847, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8143065693430657, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9118248175182482, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9366423357664233, | |
| "eval_runtime": 440.88, | |
| "eval_samples_per_second": 7.85, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.345703125, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.701388888888889e-05, | |
| "loss": 0.064, | |
| "step": 1201 | |
| }, | |
| { | |
| "epoch": 2.34765625, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 1.7009548611111112e-05, | |
| "loss": 0.0537, | |
| "step": 1202 | |
| }, | |
| { | |
| "epoch": 2.349609375, | |
| "grad_norm": 0.51171875, | |
| "learning_rate": 1.7005208333333333e-05, | |
| "loss": 0.0771, | |
| "step": 1203 | |
| }, | |
| { | |
| "epoch": 2.3515625, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 1.7000868055555557e-05, | |
| "loss": 0.1387, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 2.353515625, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.6996527777777778e-05, | |
| "loss": 0.4609, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 2.35546875, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 1.6992187500000002e-05, | |
| "loss": 0.1387, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 2.357421875, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.6987847222222223e-05, | |
| "loss": 0.168, | |
| "step": 1207 | |
| }, | |
| { | |
| "epoch": 2.359375, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.6983506944444444e-05, | |
| "loss": 0.1963, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 2.361328125, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.6979166666666668e-05, | |
| "loss": 0.2793, | |
| "step": 1209 | |
| }, | |
| { | |
| "epoch": 2.36328125, | |
| "grad_norm": 0.4296875, | |
| "learning_rate": 1.697482638888889e-05, | |
| "loss": 0.1128, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.365234375, | |
| "grad_norm": 1.34375, | |
| "learning_rate": 1.6970486111111113e-05, | |
| "loss": 0.3008, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 2.3671875, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 1.6966145833333334e-05, | |
| "loss": 0.0566, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 2.369140625, | |
| "grad_norm": 0.349609375, | |
| "learning_rate": 1.696180555555556e-05, | |
| "loss": 0.0422, | |
| "step": 1213 | |
| }, | |
| { | |
| "epoch": 2.37109375, | |
| "grad_norm": 1.4375, | |
| "learning_rate": 1.695746527777778e-05, | |
| "loss": 0.2734, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 2.373046875, | |
| "grad_norm": 1.21875, | |
| "learning_rate": 1.6953125e-05, | |
| "loss": 0.2852, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 2.375, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.6948784722222225e-05, | |
| "loss": 0.1719, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 2.376953125, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.6944444444444446e-05, | |
| "loss": 0.1982, | |
| "step": 1217 | |
| }, | |
| { | |
| "epoch": 2.37890625, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.694010416666667e-05, | |
| "loss": 0.1445, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 2.380859375, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 1.693576388888889e-05, | |
| "loss": 0.1309, | |
| "step": 1219 | |
| }, | |
| { | |
| "epoch": 2.3828125, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.693142361111111e-05, | |
| "loss": 0.2363, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.384765625, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.6927083333333333e-05, | |
| "loss": 0.0981, | |
| "step": 1221 | |
| }, | |
| { | |
| "epoch": 2.38671875, | |
| "grad_norm": 0.91015625, | |
| "learning_rate": 1.6922743055555557e-05, | |
| "loss": 0.293, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 2.388671875, | |
| "grad_norm": 1.2421875, | |
| "learning_rate": 1.6918402777777778e-05, | |
| "loss": 0.2168, | |
| "step": 1223 | |
| }, | |
| { | |
| "epoch": 2.390625, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.6914062500000002e-05, | |
| "loss": 0.1855, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 2.392578125, | |
| "grad_norm": 0.341796875, | |
| "learning_rate": 1.6909722222222223e-05, | |
| "loss": 0.0532, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.39453125, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.6905381944444447e-05, | |
| "loss": 0.1328, | |
| "step": 1226 | |
| }, | |
| { | |
| "epoch": 2.396484375, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 1.6901041666666668e-05, | |
| "loss": 0.166, | |
| "step": 1227 | |
| }, | |
| { | |
| "epoch": 2.3984375, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.689670138888889e-05, | |
| "loss": 0.1348, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 2.400390625, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 1.6892361111111113e-05, | |
| "loss": 0.3125, | |
| "step": 1229 | |
| }, | |
| { | |
| "epoch": 2.40234375, | |
| "grad_norm": 1.4765625, | |
| "learning_rate": 1.6888020833333334e-05, | |
| "loss": 0.3027, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.404296875, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.688368055555556e-05, | |
| "loss": 0.2773, | |
| "step": 1231 | |
| }, | |
| { | |
| "epoch": 2.40625, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.687934027777778e-05, | |
| "loss": 0.2676, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 2.408203125, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 1.6875e-05, | |
| "loss": 0.1523, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 2.41015625, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 1.6870659722222224e-05, | |
| "loss": 0.293, | |
| "step": 1234 | |
| }, | |
| { | |
| "epoch": 2.412109375, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 1.6866319444444445e-05, | |
| "loss": 0.2012, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 2.4140625, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.686197916666667e-05, | |
| "loss": 0.3262, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 2.416015625, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.685763888888889e-05, | |
| "loss": 0.2695, | |
| "step": 1237 | |
| }, | |
| { | |
| "epoch": 2.41796875, | |
| "grad_norm": 1.2421875, | |
| "learning_rate": 1.685329861111111e-05, | |
| "loss": 0.2988, | |
| "step": 1238 | |
| }, | |
| { | |
| "epoch": 2.419921875, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.6848958333333332e-05, | |
| "loss": 0.2559, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 2.421875, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 1.6844618055555557e-05, | |
| "loss": 0.1953, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.423828125, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 1.6840277777777778e-05, | |
| "loss": 0.2559, | |
| "step": 1241 | |
| }, | |
| { | |
| "epoch": 2.42578125, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 1.6835937500000002e-05, | |
| "loss": 0.3477, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 2.427734375, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 1.6831597222222226e-05, | |
| "loss": 0.1855, | |
| "step": 1243 | |
| }, | |
| { | |
| "epoch": 2.4296875, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.6827256944444447e-05, | |
| "loss": 0.1621, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 2.431640625, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 1.6822916666666668e-05, | |
| "loss": 0.2119, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 2.43359375, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.681857638888889e-05, | |
| "loss": 0.1191, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 2.435546875, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 1.6814236111111113e-05, | |
| "loss": 0.2246, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 2.4375, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.6809895833333334e-05, | |
| "loss": 0.2793, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 2.439453125, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.6805555555555558e-05, | |
| "loss": 0.1797, | |
| "step": 1249 | |
| }, | |
| { | |
| "epoch": 2.44140625, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.680121527777778e-05, | |
| "loss": 0.1758, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.44140625, | |
| "eval_loss": 0.2237958014011383, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8131386861313868, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9115328467153284, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9366423357664233, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8668355300196242, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8657497393117832, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8882259668064703, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8131386861313868, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.0957080291970803, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3038442822384428, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18732846715328463, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8131386861313868, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9115328467153284, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9366423357664233, | |
| "eval_runtime": 441.0159, | |
| "eval_samples_per_second": 7.848, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.443359375, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.6796875e-05, | |
| "loss": 0.1348, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 2.4453125, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.6792534722222224e-05, | |
| "loss": 0.106, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 2.447265625, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.6788194444444445e-05, | |
| "loss": 0.2402, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 2.44921875, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.678385416666667e-05, | |
| "loss": 0.1973, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 2.451171875, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 1.677951388888889e-05, | |
| "loss": 0.2002, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 2.453125, | |
| "grad_norm": 1.6953125, | |
| "learning_rate": 1.6775173611111115e-05, | |
| "loss": 0.4355, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 2.455078125, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 1.6770833333333336e-05, | |
| "loss": 0.1191, | |
| "step": 1257 | |
| }, | |
| { | |
| "epoch": 2.45703125, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.6766493055555556e-05, | |
| "loss": 0.2949, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 2.458984375, | |
| "grad_norm": 0.9375, | |
| "learning_rate": 1.6762152777777777e-05, | |
| "loss": 0.2422, | |
| "step": 1259 | |
| }, | |
| { | |
| "epoch": 2.4609375, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.67578125e-05, | |
| "loss": 0.2129, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.462890625, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 1.6753472222222226e-05, | |
| "loss": 0.3008, | |
| "step": 1261 | |
| }, | |
| { | |
| "epoch": 2.46484375, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.6749131944444447e-05, | |
| "loss": 0.2871, | |
| "step": 1262 | |
| }, | |
| { | |
| "epoch": 2.466796875, | |
| "grad_norm": 1.6796875, | |
| "learning_rate": 1.6744791666666668e-05, | |
| "loss": 0.2197, | |
| "step": 1263 | |
| }, | |
| { | |
| "epoch": 2.46875, | |
| "grad_norm": 1.1171875, | |
| "learning_rate": 1.674045138888889e-05, | |
| "loss": 0.2178, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 2.470703125, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.6736111111111113e-05, | |
| "loss": 0.293, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 2.47265625, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 1.6731770833333334e-05, | |
| "loss": 0.2441, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 2.474609375, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 1.6727430555555558e-05, | |
| "loss": 0.3086, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 2.4765625, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 1.672309027777778e-05, | |
| "loss": 0.2012, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 2.478515625, | |
| "grad_norm": 0.984375, | |
| "learning_rate": 1.671875e-05, | |
| "loss": 0.4258, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 2.48046875, | |
| "grad_norm": 0.5078125, | |
| "learning_rate": 1.6714409722222224e-05, | |
| "loss": 0.0776, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.482421875, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 1.6710069444444445e-05, | |
| "loss": 0.2295, | |
| "step": 1271 | |
| }, | |
| { | |
| "epoch": 2.484375, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 1.670572916666667e-05, | |
| "loss": 0.1104, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 2.486328125, | |
| "grad_norm": 1.3359375, | |
| "learning_rate": 1.670138888888889e-05, | |
| "loss": 0.2695, | |
| "step": 1273 | |
| }, | |
| { | |
| "epoch": 2.48828125, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.6697048611111114e-05, | |
| "loss": 0.2354, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 2.490234375, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 1.6692708333333335e-05, | |
| "loss": 0.2578, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.4921875, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 1.6688368055555556e-05, | |
| "loss": 0.1206, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 2.494140625, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.6684027777777777e-05, | |
| "loss": 0.291, | |
| "step": 1277 | |
| }, | |
| { | |
| "epoch": 2.49609375, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 1.66796875e-05, | |
| "loss": 0.126, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 2.498046875, | |
| "grad_norm": 1.4375, | |
| "learning_rate": 1.6675347222222226e-05, | |
| "loss": 0.3047, | |
| "step": 1279 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.6671006944444447e-05, | |
| "loss": 0.4258, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.501953125, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1055, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 2.50390625, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.666232638888889e-05, | |
| "loss": 0.2285, | |
| "step": 1282 | |
| }, | |
| { | |
| "epoch": 2.505859375, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.6657986111111113e-05, | |
| "loss": 0.1777, | |
| "step": 1283 | |
| }, | |
| { | |
| "epoch": 2.5078125, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 1.6653645833333334e-05, | |
| "loss": 0.248, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 2.509765625, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.6649305555555558e-05, | |
| "loss": 0.1943, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 2.51171875, | |
| "grad_norm": 1.40625, | |
| "learning_rate": 1.664496527777778e-05, | |
| "loss": 0.2949, | |
| "step": 1286 | |
| }, | |
| { | |
| "epoch": 2.513671875, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.6640625000000003e-05, | |
| "loss": 0.2354, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 2.515625, | |
| "grad_norm": 0.859375, | |
| "learning_rate": 1.6636284722222224e-05, | |
| "loss": 0.1309, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 2.517578125, | |
| "grad_norm": 1.1796875, | |
| "learning_rate": 1.6631944444444445e-05, | |
| "loss": 0.1924, | |
| "step": 1289 | |
| }, | |
| { | |
| "epoch": 2.51953125, | |
| "grad_norm": 0.9609375, | |
| "learning_rate": 1.662760416666667e-05, | |
| "loss": 0.3984, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.521484375, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.662326388888889e-05, | |
| "loss": 0.2109, | |
| "step": 1291 | |
| }, | |
| { | |
| "epoch": 2.5234375, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 1.6618923611111114e-05, | |
| "loss": 0.2178, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 2.525390625, | |
| "grad_norm": 1.0, | |
| "learning_rate": 1.6614583333333335e-05, | |
| "loss": 0.2832, | |
| "step": 1293 | |
| }, | |
| { | |
| "epoch": 2.52734375, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 1.6610243055555556e-05, | |
| "loss": 0.126, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 2.529296875, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 1.6605902777777777e-05, | |
| "loss": 0.3281, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 2.53125, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.66015625e-05, | |
| "loss": 0.1309, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 2.533203125, | |
| "grad_norm": 1.28125, | |
| "learning_rate": 1.6597222222222225e-05, | |
| "loss": 0.416, | |
| "step": 1297 | |
| }, | |
| { | |
| "epoch": 2.53515625, | |
| "grad_norm": 1.3984375, | |
| "learning_rate": 1.6592881944444446e-05, | |
| "loss": 0.2773, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 2.537109375, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.6588541666666667e-05, | |
| "loss": 0.167, | |
| "step": 1299 | |
| }, | |
| { | |
| "epoch": 2.5390625, | |
| "grad_norm": 1.0859375, | |
| "learning_rate": 1.6584201388888888e-05, | |
| "loss": 0.1709, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.5390625, | |
| "eval_loss": 0.22107917070388794, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.814014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9369343065693431, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.867436584626782, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8663883675124555, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8887148667884714, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.814014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09570802919708028, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.30364963503649633, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1873868613138686, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.814014598540146, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9570802919708029, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.910948905109489, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9369343065693431, | |
| "eval_runtime": 441.2189, | |
| "eval_samples_per_second": 7.844, | |
| "eval_steps_per_second": 0.125, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.541015625, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.6579861111111112e-05, | |
| "loss": 0.2559, | |
| "step": 1301 | |
| }, | |
| { | |
| "epoch": 2.54296875, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 1.6575520833333333e-05, | |
| "loss": 0.3223, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 2.544921875, | |
| "grad_norm": 0.85546875, | |
| "learning_rate": 1.6571180555555558e-05, | |
| "loss": 0.1855, | |
| "step": 1303 | |
| }, | |
| { | |
| "epoch": 2.546875, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.656684027777778e-05, | |
| "loss": 0.2441, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 2.548828125, | |
| "grad_norm": 0.53515625, | |
| "learning_rate": 1.6562500000000003e-05, | |
| "loss": 0.1406, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 2.55078125, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.6558159722222224e-05, | |
| "loss": 0.1021, | |
| "step": 1306 | |
| }, | |
| { | |
| "epoch": 2.552734375, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 1.6553819444444445e-05, | |
| "loss": 0.0505, | |
| "step": 1307 | |
| }, | |
| { | |
| "epoch": 2.5546875, | |
| "grad_norm": 1.8515625, | |
| "learning_rate": 1.654947916666667e-05, | |
| "loss": 0.1387, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 2.556640625, | |
| "grad_norm": 0.515625, | |
| "learning_rate": 1.654513888888889e-05, | |
| "loss": 0.1021, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 2.55859375, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.6540798611111114e-05, | |
| "loss": 0.1064, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.560546875, | |
| "grad_norm": 1.515625, | |
| "learning_rate": 1.6536458333333335e-05, | |
| "loss": 0.3809, | |
| "step": 1311 | |
| }, | |
| { | |
| "epoch": 2.5625, | |
| "grad_norm": 1.1640625, | |
| "learning_rate": 1.6532118055555556e-05, | |
| "loss": 0.293, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 2.564453125, | |
| "grad_norm": 1.5234375, | |
| "learning_rate": 1.6527777777777777e-05, | |
| "loss": 0.2461, | |
| "step": 1313 | |
| }, | |
| { | |
| "epoch": 2.56640625, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 1.65234375e-05, | |
| "loss": 0.166, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.568359375, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.6519097222222225e-05, | |
| "loss": 0.0977, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 2.5703125, | |
| "grad_norm": 1.4140625, | |
| "learning_rate": 1.6514756944444446e-05, | |
| "loss": 0.2754, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 2.572265625, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 1.651041666666667e-05, | |
| "loss": 0.3008, | |
| "step": 1317 | |
| }, | |
| { | |
| "epoch": 2.57421875, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.650607638888889e-05, | |
| "loss": 0.2461, | |
| "step": 1318 | |
| }, | |
| { | |
| "epoch": 2.576171875, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.6501736111111112e-05, | |
| "loss": 0.2041, | |
| "step": 1319 | |
| }, | |
| { | |
| "epoch": 2.578125, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.6497395833333333e-05, | |
| "loss": 0.0967, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.580078125, | |
| "grad_norm": 0.396484375, | |
| "learning_rate": 1.6493055555555557e-05, | |
| "loss": 0.0278, | |
| "step": 1321 | |
| }, | |
| { | |
| "epoch": 2.58203125, | |
| "grad_norm": 0.58203125, | |
| "learning_rate": 1.6488715277777778e-05, | |
| "loss": 0.0762, | |
| "step": 1322 | |
| }, | |
| { | |
| "epoch": 2.583984375, | |
| "grad_norm": 1.546875, | |
| "learning_rate": 1.6484375000000003e-05, | |
| "loss": 0.1836, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 2.5859375, | |
| "grad_norm": 0.9296875, | |
| "learning_rate": 1.6480034722222223e-05, | |
| "loss": 0.3066, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 2.587890625, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 1.6475694444444444e-05, | |
| "loss": 0.2539, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.58984375, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.647135416666667e-05, | |
| "loss": 0.3496, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 2.591796875, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 1.646701388888889e-05, | |
| "loss": 0.3555, | |
| "step": 1327 | |
| }, | |
| { | |
| "epoch": 2.59375, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.6462673611111114e-05, | |
| "loss": 0.2637, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 2.595703125, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.6458333333333335e-05, | |
| "loss": 0.1787, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 2.59765625, | |
| "grad_norm": 0.99609375, | |
| "learning_rate": 1.6453993055555556e-05, | |
| "loss": 0.3203, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.599609375, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 1.6449652777777777e-05, | |
| "loss": 0.2637, | |
| "step": 1331 | |
| }, | |
| { | |
| "epoch": 2.6015625, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.64453125e-05, | |
| "loss": 0.291, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 2.603515625, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 1.6440972222222225e-05, | |
| "loss": 0.1826, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 2.60546875, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 1.6436631944444446e-05, | |
| "loss": 0.2158, | |
| "step": 1334 | |
| }, | |
| { | |
| "epoch": 2.607421875, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 1.643229166666667e-05, | |
| "loss": 0.3555, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 2.609375, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 1.642795138888889e-05, | |
| "loss": 0.085, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 2.611328125, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.6423611111111112e-05, | |
| "loss": 0.2539, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 2.61328125, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 1.6419270833333333e-05, | |
| "loss": 0.1914, | |
| "step": 1338 | |
| }, | |
| { | |
| "epoch": 2.615234375, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 1.6414930555555557e-05, | |
| "loss": 0.2139, | |
| "step": 1339 | |
| }, | |
| { | |
| "epoch": 2.6171875, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.6410590277777778e-05, | |
| "loss": 0.0894, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.619140625, | |
| "grad_norm": 1.609375, | |
| "learning_rate": 1.6406250000000002e-05, | |
| "loss": 0.1621, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 2.62109375, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 1.6401909722222223e-05, | |
| "loss": 0.4453, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 2.623046875, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 1.6397569444444444e-05, | |
| "loss": 0.2109, | |
| "step": 1343 | |
| }, | |
| { | |
| "epoch": 2.625, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 1.639322916666667e-05, | |
| "loss": 0.2441, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 2.626953125, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.638888888888889e-05, | |
| "loss": 0.2197, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 2.62890625, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.6384548611111114e-05, | |
| "loss": 0.2109, | |
| "step": 1346 | |
| }, | |
| { | |
| "epoch": 2.630859375, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 1.6380208333333335e-05, | |
| "loss": 0.3496, | |
| "step": 1347 | |
| }, | |
| { | |
| "epoch": 2.6328125, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.637586805555556e-05, | |
| "loss": 0.1748, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 2.634765625, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 1.637152777777778e-05, | |
| "loss": 0.1572, | |
| "step": 1349 | |
| }, | |
| { | |
| "epoch": 2.63671875, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 1.63671875e-05, | |
| "loss": 0.0581, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.63671875, | |
| "eval_loss": 0.22165383398532867, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8160583941605839, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.9124087591240876, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9383941605839416, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8690031654787571, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8678734793187354, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8899813446977543, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8160583941605839, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.3041362530413625, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.18767883211678832, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8160583941605839, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.9124087591240876, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9383941605839416, | |
| "eval_runtime": 447.5294, | |
| "eval_samples_per_second": 7.734, | |
| "eval_steps_per_second": 0.123, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.638671875, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 1.6362847222222225e-05, | |
| "loss": 0.1699, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 2.640625, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 1.6358506944444446e-05, | |
| "loss": 0.2002, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 2.642578125, | |
| "grad_norm": 1.6484375, | |
| "learning_rate": 1.635416666666667e-05, | |
| "loss": 0.3164, | |
| "step": 1353 | |
| }, | |
| { | |
| "epoch": 2.64453125, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 1.634982638888889e-05, | |
| "loss": 0.3184, | |
| "step": 1354 | |
| }, | |
| { | |
| "epoch": 2.646484375, | |
| "grad_norm": 0.494140625, | |
| "learning_rate": 1.6345486111111112e-05, | |
| "loss": 0.0908, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 2.6484375, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 1.6341145833333333e-05, | |
| "loss": 0.1875, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 2.650390625, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 1.6336805555555557e-05, | |
| "loss": 0.2754, | |
| "step": 1357 | |
| }, | |
| { | |
| "epoch": 2.65234375, | |
| "grad_norm": 1.390625, | |
| "learning_rate": 1.6332465277777778e-05, | |
| "loss": 0.1699, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 2.654296875, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 1.6328125000000002e-05, | |
| "loss": 0.3164, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 2.65625, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 1.6323784722222223e-05, | |
| "loss": 0.2207, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.658203125, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 1.6319444444444444e-05, | |
| "loss": 0.2285, | |
| "step": 1361 | |
| }, | |
| { | |
| "epoch": 2.66015625, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.6315104166666668e-05, | |
| "loss": 0.165, | |
| "step": 1362 | |
| }, | |
| { | |
| "epoch": 2.662109375, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 1.631076388888889e-05, | |
| "loss": 0.2637, | |
| "step": 1363 | |
| }, | |
| { | |
| "epoch": 2.6640625, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 1.6306423611111113e-05, | |
| "loss": 0.291, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 2.666015625, | |
| "grad_norm": 0.380859375, | |
| "learning_rate": 1.6302083333333334e-05, | |
| "loss": 0.1094, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 2.66796875, | |
| "grad_norm": 1.578125, | |
| "learning_rate": 1.629774305555556e-05, | |
| "loss": 0.3008, | |
| "step": 1366 | |
| }, | |
| { | |
| "epoch": 2.669921875, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 1.629340277777778e-05, | |
| "loss": 0.1357, | |
| "step": 1367 | |
| }, | |
| { | |
| "epoch": 2.671875, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 1.62890625e-05, | |
| "loss": 0.1079, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 2.673828125, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.6284722222222225e-05, | |
| "loss": 0.3125, | |
| "step": 1369 | |
| }, | |
| { | |
| "epoch": 2.67578125, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 1.6280381944444446e-05, | |
| "loss": 0.3926, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.677734375, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 1.627604166666667e-05, | |
| "loss": 0.3086, | |
| "step": 1371 | |
| }, | |
| { | |
| "epoch": 2.6796875, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 1.627170138888889e-05, | |
| "loss": 0.2891, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 2.681640625, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 1.626736111111111e-05, | |
| "loss": 0.21, | |
| "step": 1373 | |
| }, | |
| { | |
| "epoch": 2.68359375, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 1.6263020833333333e-05, | |
| "loss": 0.1914, | |
| "step": 1374 | |
| }, | |
| { | |
| "epoch": 2.685546875, | |
| "grad_norm": 1.75, | |
| "learning_rate": 1.6258680555555557e-05, | |
| "loss": 0.3594, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.6875, | |
| "grad_norm": 1.4609375, | |
| "learning_rate": 1.6254340277777778e-05, | |
| "loss": 0.3203, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 2.689453125, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 1.6250000000000002e-05, | |
| "loss": 0.2676, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 2.69140625, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 1.6245659722222223e-05, | |
| "loss": 0.1582, | |
| "step": 1378 | |
| }, | |
| { | |
| "epoch": 2.693359375, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 1.6241319444444447e-05, | |
| "loss": 0.3984, | |
| "step": 1379 | |
| }, | |
| { | |
| "epoch": 2.6953125, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 1.6236979166666668e-05, | |
| "loss": 0.1426, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.697265625, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 1.623263888888889e-05, | |
| "loss": 0.2891, | |
| "step": 1381 | |
| }, | |
| { | |
| "epoch": 2.69921875, | |
| "grad_norm": 1.046875, | |
| "learning_rate": 1.6228298611111113e-05, | |
| "loss": 0.2354, | |
| "step": 1382 | |
| }, | |
| { | |
| "epoch": 2.701171875, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 1.6223958333333334e-05, | |
| "loss": 0.1406, | |
| "step": 1383 | |
| }, | |
| { | |
| "epoch": 2.703125, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 1.621961805555556e-05, | |
| "loss": 0.2148, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 2.705078125, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.621527777777778e-05, | |
| "loss": 0.1196, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 2.70703125, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.62109375e-05, | |
| "loss": 0.1816, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 2.708984375, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 1.6206597222222224e-05, | |
| "loss": 0.127, | |
| "step": 1387 | |
| }, | |
| { | |
| "epoch": 2.7109375, | |
| "grad_norm": 1.2578125, | |
| "learning_rate": 1.6202256944444445e-05, | |
| "loss": 0.2051, | |
| "step": 1388 | |
| }, | |
| { | |
| "epoch": 2.712890625, | |
| "grad_norm": 1.125, | |
| "learning_rate": 1.619791666666667e-05, | |
| "loss": 0.2656, | |
| "step": 1389 | |
| }, | |
| { | |
| "epoch": 2.71484375, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.619357638888889e-05, | |
| "loss": 0.168, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.716796875, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 1.618923611111111e-05, | |
| "loss": 0.2207, | |
| "step": 1391 | |
| }, | |
| { | |
| "epoch": 2.71875, | |
| "grad_norm": 1.1015625, | |
| "learning_rate": 1.6184895833333332e-05, | |
| "loss": 0.1953, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 2.720703125, | |
| "grad_norm": 0.95703125, | |
| "learning_rate": 1.6180555555555557e-05, | |
| "loss": 0.3574, | |
| "step": 1393 | |
| }, | |
| { | |
| "epoch": 2.72265625, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.6176215277777777e-05, | |
| "loss": 0.1992, | |
| "step": 1394 | |
| }, | |
| { | |
| "epoch": 2.724609375, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 1.6171875000000002e-05, | |
| "loss": 0.4043, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 2.7265625, | |
| "grad_norm": 1.1484375, | |
| "learning_rate": 1.6167534722222226e-05, | |
| "loss": 0.168, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 2.728515625, | |
| "grad_norm": 0.609375, | |
| "learning_rate": 1.6163194444444447e-05, | |
| "loss": 0.1216, | |
| "step": 1397 | |
| }, | |
| { | |
| "epoch": 2.73046875, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.6158854166666668e-05, | |
| "loss": 0.1641, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 2.732421875, | |
| "grad_norm": 1.2421875, | |
| "learning_rate": 1.615451388888889e-05, | |
| "loss": 0.1523, | |
| "step": 1399 | |
| }, | |
| { | |
| "epoch": 2.734375, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.6150173611111113e-05, | |
| "loss": 0.1797, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.734375, | |
| "eval_loss": 0.21922454237937927, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@1": 0.8169343065693431, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@10": 0.9576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@3": 0.912992700729927, | |
| "eval_narrativeqa-ctx-dev_cosine_accuracy@5": 0.9381021897810219, | |
| "eval_narrativeqa-ctx-dev_cosine_map@100": 0.8697791664252698, | |
| "eval_narrativeqa-ctx-dev_cosine_mrr@10": 0.8686896072297537, | |
| "eval_narrativeqa-ctx-dev_cosine_ndcg@10": 0.8905989672725512, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@1": 0.8169343065693431, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@10": 0.09576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@3": 0.304330900243309, | |
| "eval_narrativeqa-ctx-dev_cosine_precision@5": 0.1876204379562044, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@1": 0.8169343065693431, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@10": 0.9576642335766423, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@3": 0.912992700729927, | |
| "eval_narrativeqa-ctx-dev_cosine_recall@5": 0.9381021897810219, | |
| "eval_runtime": 447.705, | |
| "eval_samples_per_second": 7.731, | |
| "eval_steps_per_second": 0.123, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |