Instructions to use GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt") model = AutoModelForMultimodalLM.from_pretrained("GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt
- SGLang
How to use GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt with Docker Model Runner:
docker model run hf.co/GritLM/gen_m7_sq2048_tulu2_ep1_zephfmt
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7980845969672785, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.263157894736843e-07, | |
| "loss": 0.7396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0526315789473685e-06, | |
| "loss": 0.6635, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.5789473684210526e-06, | |
| "loss": 0.7036, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 0.6616, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.7004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.157894736842105e-06, | |
| "loss": 0.637, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.6842105263157896e-06, | |
| "loss": 0.6202, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.210526315789474e-06, | |
| "loss": 0.6074, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.736842105263158e-06, | |
| "loss": 0.6147, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 0.6723, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.789473684210527e-06, | |
| "loss": 0.6024, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.31578947368421e-06, | |
| "loss": 0.6143, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.842105263157896e-06, | |
| "loss": 0.6261, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.368421052631579e-06, | |
| "loss": 0.6334, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.894736842105265e-06, | |
| "loss": 0.6041, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.421052631578948e-06, | |
| "loss": 0.6071, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.947368421052632e-06, | |
| "loss": 0.6264, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.473684210526315e-06, | |
| "loss": 0.5899, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.628, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.6481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.105263157894737e-05, | |
| "loss": 0.5854, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1578947368421053e-05, | |
| "loss": 0.5735, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.2105263157894737e-05, | |
| "loss": 0.6635, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.263157894736842e-05, | |
| "loss": 0.5895, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.3157894736842108e-05, | |
| "loss": 0.6014, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.3684210526315791e-05, | |
| "loss": 0.623, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.4210526315789475e-05, | |
| "loss": 0.5791, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.4736842105263159e-05, | |
| "loss": 0.6215, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5263157894736846e-05, | |
| "loss": 0.6359, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.578947368421053e-05, | |
| "loss": 0.6282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.6315789473684213e-05, | |
| "loss": 0.644, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6842105263157896e-05, | |
| "loss": 0.6252, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.736842105263158e-05, | |
| "loss": 0.6518, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.7894736842105264e-05, | |
| "loss": 0.6346, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.8421052631578947e-05, | |
| "loss": 0.6537, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.894736842105263e-05, | |
| "loss": 0.5812, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9473684210526318e-05, | |
| "loss": 0.6329, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6777, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9983498349834986e-05, | |
| "loss": 0.6258, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.996699669966997e-05, | |
| "loss": 0.6399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9950495049504954e-05, | |
| "loss": 0.6712, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9933993399339934e-05, | |
| "loss": 0.6586, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9917491749174918e-05, | |
| "loss": 0.6319, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9900990099009902e-05, | |
| "loss": 0.6588, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9884488448844886e-05, | |
| "loss": 0.6542, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.986798679867987e-05, | |
| "loss": 0.6493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9851485148514854e-05, | |
| "loss": 0.624, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9834983498349835e-05, | |
| "loss": 0.6032, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9818481848184822e-05, | |
| "loss": 0.6462, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9801980198019803e-05, | |
| "loss": 0.6265, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9785478547854787e-05, | |
| "loss": 0.667, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.976897689768977e-05, | |
| "loss": 0.7015, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9752475247524755e-05, | |
| "loss": 0.667, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9735973597359735e-05, | |
| "loss": 0.6689, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9719471947194723e-05, | |
| "loss": 0.6587, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9702970297029703e-05, | |
| "loss": 0.6549, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9686468646864687e-05, | |
| "loss": 0.697, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.966996699669967e-05, | |
| "loss": 0.6115, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9653465346534655e-05, | |
| "loss": 0.6558, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.963696369636964e-05, | |
| "loss": 0.6415, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9620462046204623e-05, | |
| "loss": 0.6442, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9603960396039604e-05, | |
| "loss": 0.62, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9587458745874588e-05, | |
| "loss": 0.6786, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.957095709570957e-05, | |
| "loss": 0.6905, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9554455445544556e-05, | |
| "loss": 0.6507, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.953795379537954e-05, | |
| "loss": 0.6649, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9521452145214524e-05, | |
| "loss": 0.6098, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9504950495049508e-05, | |
| "loss": 0.5978, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.948844884488449e-05, | |
| "loss": 0.6344, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9471947194719475e-05, | |
| "loss": 0.6606, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9455445544554456e-05, | |
| "loss": 0.6793, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.943894389438944e-05, | |
| "loss": 0.6635, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9422442244224424e-05, | |
| "loss": 0.6407, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9405940594059408e-05, | |
| "loss": 0.6476, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9389438943894392e-05, | |
| "loss": 0.6434, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9372937293729376e-05, | |
| "loss": 0.6561, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9356435643564357e-05, | |
| "loss": 0.6489, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9339933993399344e-05, | |
| "loss": 0.6775, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9323432343234325e-05, | |
| "loss": 0.63, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.930693069306931e-05, | |
| "loss": 0.6778, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9290429042904292e-05, | |
| "loss": 0.6809, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9273927392739276e-05, | |
| "loss": 0.6401, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9257425742574257e-05, | |
| "loss": 0.6388, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9240924092409244e-05, | |
| "loss": 0.6422, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9224422442244225e-05, | |
| "loss": 0.5752, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.920792079207921e-05, | |
| "loss": 0.6527, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9191419141914193e-05, | |
| "loss": 0.683, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9174917491749177e-05, | |
| "loss": 0.6494, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9158415841584158e-05, | |
| "loss": 0.6725, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9141914191419145e-05, | |
| "loss": 0.6538, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9125412541254126e-05, | |
| "loss": 0.6121, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.910891089108911e-05, | |
| "loss": 0.6573, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9092409240924093e-05, | |
| "loss": 0.6869, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9075907590759077e-05, | |
| "loss": 0.6573, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.905940594059406e-05, | |
| "loss": 0.6516, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9042904290429045e-05, | |
| "loss": 0.6857, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.902640264026403e-05, | |
| "loss": 0.6865, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.900990099009901e-05, | |
| "loss": 0.6181, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8993399339933994e-05, | |
| "loss": 0.6548, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8976897689768978e-05, | |
| "loss": 0.714, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8960396039603962e-05, | |
| "loss": 0.6515, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8943894389438946e-05, | |
| "loss": 0.6421, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.892739273927393e-05, | |
| "loss": 0.6284, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.891089108910891e-05, | |
| "loss": 0.7068, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8894389438943898e-05, | |
| "loss": 0.7048, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.887788778877888e-05, | |
| "loss": 0.6819, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8861386138613862e-05, | |
| "loss": 0.6773, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8844884488448846e-05, | |
| "loss": 0.6911, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.882838283828383e-05, | |
| "loss": 0.6353, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.881188118811881e-05, | |
| "loss": 0.6425, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.87953795379538e-05, | |
| "loss": 0.5878, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.877887788778878e-05, | |
| "loss": 0.6712, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8762376237623763e-05, | |
| "loss": 0.6068, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8745874587458747e-05, | |
| "loss": 0.6573, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.872937293729373e-05, | |
| "loss": 0.6677, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8712871287128715e-05, | |
| "loss": 0.6443, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.86963696369637e-05, | |
| "loss": 0.6311, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.867986798679868e-05, | |
| "loss": 0.7183, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.8663366336633667e-05, | |
| "loss": 0.6484, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8646864686468647e-05, | |
| "loss": 0.6561, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.863036303630363e-05, | |
| "loss": 0.6085, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8613861386138615e-05, | |
| "loss": 0.6587, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.85973597359736e-05, | |
| "loss": 0.6274, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8580858085808583e-05, | |
| "loss": 0.6347, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8564356435643567e-05, | |
| "loss": 0.6464, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8547854785478548e-05, | |
| "loss": 0.636, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8531353135313532e-05, | |
| "loss": 0.6038, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8514851485148516e-05, | |
| "loss": 0.6457, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.84983498349835e-05, | |
| "loss": 0.6406, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8481848184818484e-05, | |
| "loss": 0.6365, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8465346534653468e-05, | |
| "loss": 0.628, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8448844884488452e-05, | |
| "loss": 0.6738, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8432343234323432e-05, | |
| "loss": 0.6525, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.841584158415842e-05, | |
| "loss": 0.635, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.83993399339934e-05, | |
| "loss": 0.6527, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8382838283828384e-05, | |
| "loss": 0.6939, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8366336633663368e-05, | |
| "loss": 0.6522, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8349834983498352e-05, | |
| "loss": 0.6485, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.6562, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.831683168316832e-05, | |
| "loss": 0.626, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.83003300330033e-05, | |
| "loss": 0.6433, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8283828382838285e-05, | |
| "loss": 0.6408, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.826732673267327e-05, | |
| "loss": 0.57, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8250825082508253e-05, | |
| "loss": 0.6462, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8234323432343233e-05, | |
| "loss": 0.5984, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.821782178217822e-05, | |
| "loss": 0.6415, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.82013201320132e-05, | |
| "loss": 0.6493, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8184818481848185e-05, | |
| "loss": 0.6246, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.816831683168317e-05, | |
| "loss": 0.6273, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8151815181518153e-05, | |
| "loss": 0.6823, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8135313531353137e-05, | |
| "loss": 0.6246, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.811881188118812e-05, | |
| "loss": 0.6132, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8102310231023105e-05, | |
| "loss": 0.6466, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8085808580858086e-05, | |
| "loss": 0.6547, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.806930693069307e-05, | |
| "loss": 0.6246, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8052805280528054e-05, | |
| "loss": 0.6227, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.8036303630363038e-05, | |
| "loss": 0.5829, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.8019801980198022e-05, | |
| "loss": 0.6334, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.8003300330033006e-05, | |
| "loss": 0.6252, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7986798679867986e-05, | |
| "loss": 0.5979, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7970297029702974e-05, | |
| "loss": 0.6162, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7953795379537954e-05, | |
| "loss": 0.6287, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7937293729372938e-05, | |
| "loss": 0.6063, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7920792079207922e-05, | |
| "loss": 0.5693, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7904290429042906e-05, | |
| "loss": 0.6643, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.788778877887789e-05, | |
| "loss": 0.6257, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7871287128712874e-05, | |
| "loss": 0.6113, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7854785478547855e-05, | |
| "loss": 0.6142, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.7838283828382842e-05, | |
| "loss": 0.6252, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7821782178217823e-05, | |
| "loss": 0.6227, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7805280528052807e-05, | |
| "loss": 0.6171, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.778877887788779e-05, | |
| "loss": 0.638, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7772277227722775e-05, | |
| "loss": 0.616, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7755775577557755e-05, | |
| "loss": 0.6266, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7739273927392743e-05, | |
| "loss": 0.5931, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7722772277227723e-05, | |
| "loss": 0.6347, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7706270627062707e-05, | |
| "loss": 0.669, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.768976897689769e-05, | |
| "loss": 0.659, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7673267326732675e-05, | |
| "loss": 0.6111, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.765676567656766e-05, | |
| "loss": 0.6475, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.7640264026402643e-05, | |
| "loss": 0.6458, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7623762376237624e-05, | |
| "loss": 0.5915, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7607260726072608e-05, | |
| "loss": 0.6795, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.759075907590759e-05, | |
| "loss": 0.6699, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7574257425742576e-05, | |
| "loss": 0.6135, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.755775577557756e-05, | |
| "loss": 0.582, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7541254125412544e-05, | |
| "loss": 0.6012, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7524752475247528e-05, | |
| "loss": 0.6681, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7508250825082508e-05, | |
| "loss": 0.6592, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7491749174917496e-05, | |
| "loss": 0.5882, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7475247524752476e-05, | |
| "loss": 0.5977, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.745874587458746e-05, | |
| "loss": 0.6002, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7442244224422444e-05, | |
| "loss": 0.6631, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.7425742574257428e-05, | |
| "loss": 0.6665, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.740924092409241e-05, | |
| "loss": 0.6041, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7392739273927396e-05, | |
| "loss": 0.6649, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7376237623762377e-05, | |
| "loss": 0.6451, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.735973597359736e-05, | |
| "loss": 0.6347, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7343234323432345e-05, | |
| "loss": 0.652, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.732673267326733e-05, | |
| "loss": 0.6621, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.731023102310231e-05, | |
| "loss": 0.6536, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7293729372937297e-05, | |
| "loss": 0.6164, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7277227722772277e-05, | |
| "loss": 0.6775, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.726072607260726e-05, | |
| "loss": 0.6434, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.7244224422442245e-05, | |
| "loss": 0.6415, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.722772277227723e-05, | |
| "loss": 0.6019, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7211221122112213e-05, | |
| "loss": 0.6241, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7194719471947197e-05, | |
| "loss": 0.6813, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.717821782178218e-05, | |
| "loss": 0.6123, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.716171617161716e-05, | |
| "loss": 0.6924, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7145214521452146e-05, | |
| "loss": 0.6142, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.712871287128713e-05, | |
| "loss": 0.6105, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7112211221122114e-05, | |
| "loss": 0.6289, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7095709570957098e-05, | |
| "loss": 0.6449, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.707920792079208e-05, | |
| "loss": 0.6199, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7062706270627065e-05, | |
| "loss": 0.6133, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.704620462046205e-05, | |
| "loss": 0.6827, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.702970297029703e-05, | |
| "loss": 0.6249, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.7013201320132014e-05, | |
| "loss": 0.5773, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6996699669966998e-05, | |
| "loss": 0.611, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6980198019801982e-05, | |
| "loss": 0.6695, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6963696369636966e-05, | |
| "loss": 0.6275, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.694719471947195e-05, | |
| "loss": 0.6499, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.693069306930693e-05, | |
| "loss": 0.6483, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6914191419141918e-05, | |
| "loss": 0.6217, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.68976897689769e-05, | |
| "loss": 0.6555, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6881188118811882e-05, | |
| "loss": 0.636, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6864686468646866e-05, | |
| "loss": 0.614, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.684818481848185e-05, | |
| "loss": 0.6508, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.683168316831683e-05, | |
| "loss": 0.5982, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.681518151815182e-05, | |
| "loss": 0.6098, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.67986798679868e-05, | |
| "loss": 0.6044, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6782178217821783e-05, | |
| "loss": 0.6185, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6765676567656767e-05, | |
| "loss": 0.6169, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.674917491749175e-05, | |
| "loss": 0.6331, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6732673267326735e-05, | |
| "loss": 0.6002, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.671617161716172e-05, | |
| "loss": 0.6199, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.66996699669967e-05, | |
| "loss": 0.5983, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6683168316831683e-05, | |
| "loss": 0.6432, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.603, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.665016501650165e-05, | |
| "loss": 0.6689, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6633663366336635e-05, | |
| "loss": 0.5661, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.661716171617162e-05, | |
| "loss": 0.6168, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.6600660066006603e-05, | |
| "loss": 0.5778, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6584158415841584e-05, | |
| "loss": 0.569, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.656765676567657e-05, | |
| "loss": 0.5578, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6551155115511552e-05, | |
| "loss": 0.5997, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6534653465346536e-05, | |
| "loss": 0.6453, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.651815181518152e-05, | |
| "loss": 0.6069, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6501650165016504e-05, | |
| "loss": 0.6215, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6485148514851484e-05, | |
| "loss": 0.617, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6468646864686472e-05, | |
| "loss": 0.6192, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6452145214521452e-05, | |
| "loss": 0.6175, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6435643564356436e-05, | |
| "loss": 0.6468, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.641914191419142e-05, | |
| "loss": 0.6445, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6402640264026404e-05, | |
| "loss": 0.6322, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6386138613861385e-05, | |
| "loss": 0.6014, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6369636963696372e-05, | |
| "loss": 0.6023, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6353135313531353e-05, | |
| "loss": 0.6608, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6336633663366337e-05, | |
| "loss": 0.6199, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.632013201320132e-05, | |
| "loss": 0.6199, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6303630363036305e-05, | |
| "loss": 0.6059, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.628712871287129e-05, | |
| "loss": 0.6056, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6270627062706273e-05, | |
| "loss": 0.6276, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6254125412541253e-05, | |
| "loss": 0.5902, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.623762376237624e-05, | |
| "loss": 0.6265, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.622112211221122e-05, | |
| "loss": 0.6065, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.6204620462046205e-05, | |
| "loss": 0.6258, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.618811881188119e-05, | |
| "loss": 0.585, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6171617161716173e-05, | |
| "loss": 0.5867, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6155115511551157e-05, | |
| "loss": 0.6345, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.613861386138614e-05, | |
| "loss": 0.5722, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6122112211221125e-05, | |
| "loss": 0.6453, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6105610561056106e-05, | |
| "loss": 0.6093, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.608910891089109e-05, | |
| "loss": 0.6353, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6072607260726074e-05, | |
| "loss": 0.6177, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6056105610561058e-05, | |
| "loss": 0.6442, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6039603960396042e-05, | |
| "loss": 0.6133, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6023102310231026e-05, | |
| "loss": 0.5901, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.6006600660066006e-05, | |
| "loss": 0.5915, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.5990099009900994e-05, | |
| "loss": 0.6012, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5973597359735974e-05, | |
| "loss": 0.5721, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5957095709570958e-05, | |
| "loss": 0.6112, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5940594059405942e-05, | |
| "loss": 0.6102, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5924092409240926e-05, | |
| "loss": 0.6079, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5907590759075907e-05, | |
| "loss": 0.6427, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5891089108910894e-05, | |
| "loss": 0.643, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5874587458745875e-05, | |
| "loss": 0.5941, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.585808580858086e-05, | |
| "loss": 0.6082, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5841584158415843e-05, | |
| "loss": 0.6186, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5825082508250827e-05, | |
| "loss": 0.5935, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.580858085808581e-05, | |
| "loss": 0.6275, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5792079207920795e-05, | |
| "loss": 0.6246, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.5775577557755775e-05, | |
| "loss": 0.6296, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.575907590759076e-05, | |
| "loss": 0.5688, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5742574257425743e-05, | |
| "loss": 0.5895, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5726072607260727e-05, | |
| "loss": 0.6286, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.570957095709571e-05, | |
| "loss": 0.5989, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5693069306930695e-05, | |
| "loss": 0.5972, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.567656765676568e-05, | |
| "loss": 0.6156, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.566006600660066e-05, | |
| "loss": 0.6106, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5643564356435644e-05, | |
| "loss": 0.5751, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5627062706270628e-05, | |
| "loss": 0.6321, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5610561056105612e-05, | |
| "loss": 0.6577, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5594059405940596e-05, | |
| "loss": 0.6388, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.557755775577558e-05, | |
| "loss": 0.5894, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.556105610561056e-05, | |
| "loss": 0.5897, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5544554455445548e-05, | |
| "loss": 0.5822, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5528052805280528e-05, | |
| "loss": 0.6529, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5511551155115512e-05, | |
| "loss": 0.5884, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5495049504950496e-05, | |
| "loss": 0.5927, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.547854785478548e-05, | |
| "loss": 0.6098, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.546204620462046e-05, | |
| "loss": 0.6624, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5445544554455448e-05, | |
| "loss": 0.6307, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.542904290429043e-05, | |
| "loss": 0.6354, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5412541254125416e-05, | |
| "loss": 0.5333, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5396039603960397e-05, | |
| "loss": 0.6148, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.537953795379538e-05, | |
| "loss": 0.5703, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.5363036303630365e-05, | |
| "loss": 0.5843, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.534653465346535e-05, | |
| "loss": 0.5906, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.533003300330033e-05, | |
| "loss": 0.5813, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5313531353135317e-05, | |
| "loss": 0.6106, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5297029702970297e-05, | |
| "loss": 0.5847, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.528052805280528e-05, | |
| "loss": 0.6285, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5264026402640265e-05, | |
| "loss": 0.6288, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5247524752475249e-05, | |
| "loss": 0.5704, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5231023102310231e-05, | |
| "loss": 0.641, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5214521452145217e-05, | |
| "loss": 0.6141, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.51980198019802e-05, | |
| "loss": 0.6374, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5181518151815182e-05, | |
| "loss": 0.6133, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.5165016501650167e-05, | |
| "loss": 0.5784, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.514851485148515e-05, | |
| "loss": 0.5831, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5132013201320132e-05, | |
| "loss": 0.6319, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5115511551155118e-05, | |
| "loss": 0.5662, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.50990099009901e-05, | |
| "loss": 0.5743, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5082508250825084e-05, | |
| "loss": 0.6239, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5066006600660068e-05, | |
| "loss": 0.551, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.504950495049505e-05, | |
| "loss": 0.5712, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5033003300330034e-05, | |
| "loss": 0.6283, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5016501650165018e-05, | |
| "loss": 0.5741, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5502, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4983498349834984e-05, | |
| "loss": 0.5688, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4966996699669968e-05, | |
| "loss": 0.6159, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4950495049504952e-05, | |
| "loss": 0.6406, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4933993399339935e-05, | |
| "loss": 0.584, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4917491749174919e-05, | |
| "loss": 0.5867, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4900990099009903e-05, | |
| "loss": 0.6106, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4884488448844885e-05, | |
| "loss": 0.6126, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.486798679867987e-05, | |
| "loss": 0.5755, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4851485148514853e-05, | |
| "loss": 0.5997, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4834983498349835e-05, | |
| "loss": 0.6071, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.481848184818482e-05, | |
| "loss": 0.6309, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4801980198019803e-05, | |
| "loss": 0.5608, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4785478547854785e-05, | |
| "loss": 0.6024, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4768976897689771e-05, | |
| "loss": 0.6461, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4752475247524753e-05, | |
| "loss": 0.5974, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4735973597359736e-05, | |
| "loss": 0.5963, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4719471947194721e-05, | |
| "loss": 0.5701, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4702970297029704e-05, | |
| "loss": 0.5713, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4686468646864686e-05, | |
| "loss": 0.6087, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4669966996699672e-05, | |
| "loss": 0.5479, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4653465346534654e-05, | |
| "loss": 0.5647, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4636963696369638e-05, | |
| "loss": 0.6127, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4620462046204622e-05, | |
| "loss": 0.6212, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4603960396039604e-05, | |
| "loss": 0.5675, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4587458745874588e-05, | |
| "loss": 0.5938, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4570957095709572e-05, | |
| "loss": 0.5255, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4554455445544556e-05, | |
| "loss": 0.5837, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.453795379537954e-05, | |
| "loss": 0.5926, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4521452145214522e-05, | |
| "loss": 0.5825, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4504950495049506e-05, | |
| "loss": 0.5738, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.448844884488449e-05, | |
| "loss": 0.5941, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4471947194719474e-05, | |
| "loss": 0.5932, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4455445544554456e-05, | |
| "loss": 0.5819, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.443894389438944e-05, | |
| "loss": 0.5942, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4422442244224424e-05, | |
| "loss": 0.64, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4405940594059407e-05, | |
| "loss": 0.612, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.438943894389439e-05, | |
| "loss": 0.6179, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4372937293729375e-05, | |
| "loss": 0.5963, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4356435643564357e-05, | |
| "loss": 0.61, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4339933993399343e-05, | |
| "loss": 0.5477, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.4323432343234325e-05, | |
| "loss": 0.6623, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4306930693069307e-05, | |
| "loss": 0.5672, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4290429042904293e-05, | |
| "loss": 0.644, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4273927392739275e-05, | |
| "loss": 0.5575, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4257425742574257e-05, | |
| "loss": 0.5979, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4240924092409243e-05, | |
| "loss": 0.6261, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4224422442244225e-05, | |
| "loss": 0.6078, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4207920792079208e-05, | |
| "loss": 0.5697, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4191419141914193e-05, | |
| "loss": 0.6361, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4174917491749176e-05, | |
| "loss": 0.5651, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4158415841584158e-05, | |
| "loss": 0.5863, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4141914191419144e-05, | |
| "loss": 0.6279, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.4125412541254126e-05, | |
| "loss": 0.6082, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.410891089108911e-05, | |
| "loss": 0.6308, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.4092409240924094e-05, | |
| "loss": 0.567, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.4075907590759076e-05, | |
| "loss": 0.5742, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.405940594059406e-05, | |
| "loss": 0.5751, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.4042904290429044e-05, | |
| "loss": 0.5782, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.4026402640264028e-05, | |
| "loss": 0.5713, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.400990099009901e-05, | |
| "loss": 0.5917, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3993399339933994e-05, | |
| "loss": 0.6088, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3976897689768978e-05, | |
| "loss": 0.5703, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.396039603960396e-05, | |
| "loss": 0.6044, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3943894389438946e-05, | |
| "loss": 0.5768, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3927392739273929e-05, | |
| "loss": 0.5817, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3910891089108911e-05, | |
| "loss": 0.6193, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3894389438943897e-05, | |
| "loss": 0.6118, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3877887788778879e-05, | |
| "loss": 0.5857, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3861386138613861e-05, | |
| "loss": 0.6479, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3844884488448847e-05, | |
| "loss": 0.6191, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3828382838283829e-05, | |
| "loss": 0.5745, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3811881188118811e-05, | |
| "loss": 0.5324, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3795379537953797e-05, | |
| "loss": 0.6109, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.377887788778878e-05, | |
| "loss": 0.5768, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3762376237623762e-05, | |
| "loss": 0.5848, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3745874587458747e-05, | |
| "loss": 0.5844, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.372937293729373e-05, | |
| "loss": 0.584, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.3712871287128715e-05, | |
| "loss": 0.5731, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3696369636963698e-05, | |
| "loss": 0.576, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.367986798679868e-05, | |
| "loss": 0.5933, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3663366336633666e-05, | |
| "loss": 0.5731, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3646864686468648e-05, | |
| "loss": 0.5282, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3630363036303632e-05, | |
| "loss": 0.55, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3613861386138616e-05, | |
| "loss": 0.7658, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3597359735973598e-05, | |
| "loss": 0.5938, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3580858085808582e-05, | |
| "loss": 0.566, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3564356435643566e-05, | |
| "loss": 0.5827, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3547854785478548e-05, | |
| "loss": 0.5589, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3531353135313532e-05, | |
| "loss": 0.6081, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3514851485148516e-05, | |
| "loss": 0.571, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.34983498349835e-05, | |
| "loss": 0.6014, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3481848184818483e-05, | |
| "loss": 0.5386, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3465346534653467e-05, | |
| "loss": 0.5562, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.344884488448845e-05, | |
| "loss": 0.614, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3432343234323433e-05, | |
| "loss": 0.585, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3415841584158418e-05, | |
| "loss": 0.6117, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.33993399339934e-05, | |
| "loss": 0.565, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3382838283828383e-05, | |
| "loss": 0.6197, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3366336633663369e-05, | |
| "loss": 0.5808, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3349834983498351e-05, | |
| "loss": 0.5886, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.5721, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3316831683168319e-05, | |
| "loss": 0.5888, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.3300330033003301e-05, | |
| "loss": 0.587, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3283828382838284e-05, | |
| "loss": 0.6135, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.326732673267327e-05, | |
| "loss": 0.597, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3250825082508252e-05, | |
| "loss": 0.5774, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3234323432343234e-05, | |
| "loss": 0.5731, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.321782178217822e-05, | |
| "loss": 0.5597, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3201320132013202e-05, | |
| "loss": 0.5494, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3184818481848186e-05, | |
| "loss": 0.5836, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.316831683168317e-05, | |
| "loss": 0.657, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3151815181518152e-05, | |
| "loss": 0.628, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3135313531353136e-05, | |
| "loss": 0.5776, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.311881188118812e-05, | |
| "loss": 0.5562, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3102310231023104e-05, | |
| "loss": 0.5953, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.3085808580858086e-05, | |
| "loss": 0.5618, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.306930693069307e-05, | |
| "loss": 0.5269, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.3052805280528054e-05, | |
| "loss": 0.5561, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.3036303630363036e-05, | |
| "loss": 0.5658, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.3019801980198022e-05, | |
| "loss": 0.6267, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.3003300330033004e-05, | |
| "loss": 0.5221, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2986798679867987e-05, | |
| "loss": 0.549, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2970297029702972e-05, | |
| "loss": 0.6091, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2953795379537955e-05, | |
| "loss": 0.5349, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2937293729372937e-05, | |
| "loss": 0.5977, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2920792079207923e-05, | |
| "loss": 0.5872, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.2904290429042905e-05, | |
| "loss": 0.6398, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.288778877887789e-05, | |
| "loss": 0.5777, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2871287128712873e-05, | |
| "loss": 0.6078, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2854785478547855e-05, | |
| "loss": 0.5672, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2838283828382841e-05, | |
| "loss": 0.5793, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2821782178217823e-05, | |
| "loss": 0.5832, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2805280528052805e-05, | |
| "loss": 0.6152, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2788778877887791e-05, | |
| "loss": 0.553, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2772277227722773e-05, | |
| "loss": 0.566, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2755775577557756e-05, | |
| "loss": 0.5676, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2739273927392741e-05, | |
| "loss": 0.549, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2722772277227724e-05, | |
| "loss": 0.6024, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2706270627062706e-05, | |
| "loss": 0.584, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2689768976897692e-05, | |
| "loss": 0.5732, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.2673267326732674e-05, | |
| "loss": 0.5964, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2656765676567658e-05, | |
| "loss": 0.6146, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2640264026402642e-05, | |
| "loss": 0.5602, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2623762376237624e-05, | |
| "loss": 0.5801, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2607260726072608e-05, | |
| "loss": 0.5555, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2590759075907592e-05, | |
| "loss": 0.5187, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2574257425742576e-05, | |
| "loss": 0.6006, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2557755775577558e-05, | |
| "loss": 0.5743, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2541254125412542e-05, | |
| "loss": 0.5775, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2524752475247526e-05, | |
| "loss": 0.6282, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2508250825082509e-05, | |
| "loss": 0.5613, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2491749174917494e-05, | |
| "loss": 0.5226, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.2475247524752477e-05, | |
| "loss": 0.6239, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2458745874587459e-05, | |
| "loss": 0.6089, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2442244224422445e-05, | |
| "loss": 0.5943, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2425742574257427e-05, | |
| "loss": 0.5683, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2409240924092409e-05, | |
| "loss": 0.5771, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2392739273927395e-05, | |
| "loss": 0.5497, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2376237623762377e-05, | |
| "loss": 0.5626, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.235973597359736e-05, | |
| "loss": 0.5393, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2343234323432345e-05, | |
| "loss": 0.5641, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2326732673267327e-05, | |
| "loss": 0.5101, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.231023102310231e-05, | |
| "loss": 0.5399, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2293729372937295e-05, | |
| "loss": 0.5329, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2277227722772278e-05, | |
| "loss": 0.5292, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2260726072607262e-05, | |
| "loss": 0.5562, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2244224422442246e-05, | |
| "loss": 0.565, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2227722772277228e-05, | |
| "loss": 0.5755, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2211221122112212e-05, | |
| "loss": 0.5562, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2194719471947196e-05, | |
| "loss": 0.5682, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.217821782178218e-05, | |
| "loss": 0.574, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2161716171617162e-05, | |
| "loss": 0.577, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2145214521452146e-05, | |
| "loss": 0.5921, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.212871287128713e-05, | |
| "loss": 0.5538, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2112211221122112e-05, | |
| "loss": 0.6061, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2095709570957096e-05, | |
| "loss": 0.5833, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.207920792079208e-05, | |
| "loss": 0.5189, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.2062706270627064e-05, | |
| "loss": 0.5854, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.2046204620462048e-05, | |
| "loss": 0.5877, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.202970297029703e-05, | |
| "loss": 0.5833, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.2013201320132014e-05, | |
| "loss": 0.5366, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1996699669966998e-05, | |
| "loss": 0.5533, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.198019801980198e-05, | |
| "loss": 0.5593, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1963696369636966e-05, | |
| "loss": 0.5911, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1947194719471949e-05, | |
| "loss": 0.5572, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1930693069306931e-05, | |
| "loss": 0.5473, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1914191419141917e-05, | |
| "loss": 0.5136, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1897689768976899e-05, | |
| "loss": 0.5983, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1881188118811881e-05, | |
| "loss": 0.54, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.1864686468646867e-05, | |
| "loss": 0.5918, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.184818481848185e-05, | |
| "loss": 0.5771, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1831683168316831e-05, | |
| "loss": 0.5697, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1815181518151817e-05, | |
| "loss": 0.5683, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.17986798679868e-05, | |
| "loss": 0.5565, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1782178217821782e-05, | |
| "loss": 0.5993, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1765676567656767e-05, | |
| "loss": 0.5527, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.174917491749175e-05, | |
| "loss": 0.5422, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1732673267326734e-05, | |
| "loss": 0.5853, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1716171617161718e-05, | |
| "loss": 0.556, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.16996699669967e-05, | |
| "loss": 0.5564, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1683168316831684e-05, | |
| "loss": 0.5859, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.538, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1650165016501652e-05, | |
| "loss": 0.5486, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.1633663366336634e-05, | |
| "loss": 0.5749, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1617161716171618e-05, | |
| "loss": 0.5034, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1600660066006602e-05, | |
| "loss": 0.5916, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1584158415841584e-05, | |
| "loss": 0.5312, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.156765676567657e-05, | |
| "loss": 0.5559, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1551155115511552e-05, | |
| "loss": 0.5804, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1534653465346535e-05, | |
| "loss": 0.5369, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.151815181518152e-05, | |
| "loss": 0.5717, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1501650165016503e-05, | |
| "loss": 0.5791, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1485148514851485e-05, | |
| "loss": 0.5216, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.146864686468647e-05, | |
| "loss": 0.5546, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1452145214521453e-05, | |
| "loss": 0.5378, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1435643564356435e-05, | |
| "loss": 0.5306, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.141914191419142e-05, | |
| "loss": 0.5596, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1402640264026403e-05, | |
| "loss": 0.5718, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1386138613861385e-05, | |
| "loss": 0.6207, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1369636963696371e-05, | |
| "loss": 0.5392, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1353135313531353e-05, | |
| "loss": 0.5452, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1336633663366337e-05, | |
| "loss": 0.5588, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1320132013201321e-05, | |
| "loss": 0.5755, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1303630363036304e-05, | |
| "loss": 0.5758, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1287128712871288e-05, | |
| "loss": 0.5236, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1270627062706272e-05, | |
| "loss": 0.5726, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1254125412541254e-05, | |
| "loss": 0.5672, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.123762376237624e-05, | |
| "loss": 0.5504, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.1221122112211222e-05, | |
| "loss": 0.5608, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1204620462046206e-05, | |
| "loss": 0.5271, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.118811881188119e-05, | |
| "loss": 0.5953, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1171617161716172e-05, | |
| "loss": 0.5576, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1155115511551156e-05, | |
| "loss": 0.584, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.113861386138614e-05, | |
| "loss": 0.5025, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1122112211221124e-05, | |
| "loss": 0.5568, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1105610561056106e-05, | |
| "loss": 0.5764, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.108910891089109e-05, | |
| "loss": 0.5569, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1072607260726074e-05, | |
| "loss": 0.5476, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1056105610561057e-05, | |
| "loss": 0.5626, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1039603960396042e-05, | |
| "loss": 0.5663, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1023102310231025e-05, | |
| "loss": 0.5558, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.1006600660066007e-05, | |
| "loss": 0.5525, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0990099009900992e-05, | |
| "loss": 0.5032, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0973597359735975e-05, | |
| "loss": 0.5689, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0957095709570957e-05, | |
| "loss": 0.5796, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0940594059405943e-05, | |
| "loss": 0.5351, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0924092409240925e-05, | |
| "loss": 0.5108, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0907590759075907e-05, | |
| "loss": 0.5273, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0891089108910893e-05, | |
| "loss": 0.5647, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0874587458745875e-05, | |
| "loss": 0.5297, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0858085808580858e-05, | |
| "loss": 0.5854, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0841584158415843e-05, | |
| "loss": 0.5997, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.0825082508250826e-05, | |
| "loss": 0.5767, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.080858085808581e-05, | |
| "loss": 0.5706, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0792079207920793e-05, | |
| "loss": 0.5272, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0775577557755776e-05, | |
| "loss": 0.5405, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.075907590759076e-05, | |
| "loss": 0.5068, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0742574257425744e-05, | |
| "loss": 0.5629, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0726072607260728e-05, | |
| "loss": 0.5564, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.070957095709571e-05, | |
| "loss": 0.5348, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0693069306930694e-05, | |
| "loss": 0.5344, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0676567656765678e-05, | |
| "loss": 0.5614, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.066006600660066e-05, | |
| "loss": 0.5229, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0643564356435644e-05, | |
| "loss": 0.5849, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0627062706270628e-05, | |
| "loss": 0.5624, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.061056105610561e-05, | |
| "loss": 0.5469, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0594059405940596e-05, | |
| "loss": 0.6092, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0577557755775578e-05, | |
| "loss": 0.5748, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.056105610561056e-05, | |
| "loss": 0.5553, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0544554455445546e-05, | |
| "loss": 0.5628, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0528052805280529e-05, | |
| "loss": 0.5432, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0511551155115511e-05, | |
| "loss": 0.533, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0495049504950497e-05, | |
| "loss": 0.59, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0478547854785479e-05, | |
| "loss": 0.5241, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0462046204620461e-05, | |
| "loss": 0.6021, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0445544554455447e-05, | |
| "loss": 0.5187, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.042904290429043e-05, | |
| "loss": 0.55, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0412541254125415e-05, | |
| "loss": 0.5933, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0396039603960397e-05, | |
| "loss": 0.6064, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.037953795379538e-05, | |
| "loss": 0.5995, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0363036303630365e-05, | |
| "loss": 0.5459, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0346534653465347e-05, | |
| "loss": 0.5385, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.033003300330033e-05, | |
| "loss": 0.511, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0313531353135315e-05, | |
| "loss": 0.5146, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0297029702970298e-05, | |
| "loss": 0.5254, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0280528052805282e-05, | |
| "loss": 0.5733, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0264026402640266e-05, | |
| "loss": 0.5374, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0247524752475248e-05, | |
| "loss": 0.5395, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0231023102310232e-05, | |
| "loss": 0.5296, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0214521452145216e-05, | |
| "loss": 0.5598, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.01980198019802e-05, | |
| "loss": 0.5341, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0181518151815182e-05, | |
| "loss": 0.5776, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0165016501650166e-05, | |
| "loss": 0.5276, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.014851485148515e-05, | |
| "loss": 0.5322, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0132013201320132e-05, | |
| "loss": 0.547, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0115511551155116e-05, | |
| "loss": 0.5553, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.00990099009901e-05, | |
| "loss": 0.5293, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0082508250825083e-05, | |
| "loss": 0.5554, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0066006600660068e-05, | |
| "loss": 0.519, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.004950495049505e-05, | |
| "loss": 0.572, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0033003300330033e-05, | |
| "loss": 0.5519, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.0016501650165019e-05, | |
| "loss": 0.5449, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6103, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.983498349834985e-06, | |
| "loss": 0.5895, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.966996699669967e-06, | |
| "loss": 0.5708, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.950495049504951e-06, | |
| "loss": 0.5117, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.933993399339935e-06, | |
| "loss": 0.5718, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.917491749174917e-06, | |
| "loss": 0.5492, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.900990099009901e-06, | |
| "loss": 0.5479, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.884488448844885e-06, | |
| "loss": 0.5697, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.867986798679868e-06, | |
| "loss": 0.5238, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.851485148514852e-06, | |
| "loss": 0.5419, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.834983498349836e-06, | |
| "loss": 0.5129, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.81848184818482e-06, | |
| "loss": 0.4988, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.801980198019802e-06, | |
| "loss": 0.5586, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.785478547854786e-06, | |
| "loss": 0.522, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.76897689768977e-06, | |
| "loss": 0.5896, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.752475247524754e-06, | |
| "loss": 0.5542, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.735973597359738e-06, | |
| "loss": 0.5944, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.71947194719472e-06, | |
| "loss": 0.5701, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.702970297029704e-06, | |
| "loss": 0.5555, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.686468646864688e-06, | |
| "loss": 0.5392, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.669966996699672e-06, | |
| "loss": 0.5642, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.653465346534654e-06, | |
| "loss": 0.5159, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.636963696369638e-06, | |
| "loss": 0.5746, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.620462046204622e-06, | |
| "loss": 0.59, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.603960396039604e-06, | |
| "loss": 0.5798, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.587458745874588e-06, | |
| "loss": 0.5523, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.570957095709572e-06, | |
| "loss": 0.5682, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.554455445544555e-06, | |
| "loss": 0.5377, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.537953795379539e-06, | |
| "loss": 0.5731, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.521452145214523e-06, | |
| "loss": 0.5539, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.504950495049505e-06, | |
| "loss": 0.506, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.488448844884489e-06, | |
| "loss": 0.5503, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.471947194719473e-06, | |
| "loss": 0.5347, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.455445544554455e-06, | |
| "loss": 0.5528, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.43894389438944e-06, | |
| "loss": 0.5215, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.422442244224423e-06, | |
| "loss": 0.5188, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.405940594059405e-06, | |
| "loss": 0.5502, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.38943894389439e-06, | |
| "loss": 0.5029, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.372937293729373e-06, | |
| "loss": 0.5261, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.356435643564357e-06, | |
| "loss": 0.5351, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.33993399339934e-06, | |
| "loss": 0.5477, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.323432343234324e-06, | |
| "loss": 0.5614, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.306930693069308e-06, | |
| "loss": 0.5552, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.290429042904292e-06, | |
| "loss": 0.4946, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.273927392739274e-06, | |
| "loss": 0.5149, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.257425742574258e-06, | |
| "loss": 0.5425, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.240924092409242e-06, | |
| "loss": 0.5408, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.224422442244226e-06, | |
| "loss": 0.5651, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.20792079207921e-06, | |
| "loss": 0.5431, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.191419141914192e-06, | |
| "loss": 0.5208, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.174917491749176e-06, | |
| "loss": 0.505, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.15841584158416e-06, | |
| "loss": 0.5308, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.141914191419142e-06, | |
| "loss": 0.5656, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.125412541254126e-06, | |
| "loss": 0.5934, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.10891089108911e-06, | |
| "loss": 0.5294, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.092409240924093e-06, | |
| "loss": 0.518, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.075907590759077e-06, | |
| "loss": 0.5413, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.05940594059406e-06, | |
| "loss": 0.5235, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.042904290429043e-06, | |
| "loss": 0.5348, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.026402640264027e-06, | |
| "loss": 0.541, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.009900990099011e-06, | |
| "loss": 0.5769, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.993399339933993e-06, | |
| "loss": 0.5638, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.976897689768977e-06, | |
| "loss": 0.4854, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.960396039603961e-06, | |
| "loss": 0.523, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.943894389438945e-06, | |
| "loss": 0.5413, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.927392739273927e-06, | |
| "loss": 0.548, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.910891089108911e-06, | |
| "loss": 0.5222, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.894389438943895e-06, | |
| "loss": 0.5398, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.877887788778878e-06, | |
| "loss": 0.5215, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.861386138613862e-06, | |
| "loss": 0.5385, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.844884488448846e-06, | |
| "loss": 0.5018, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.82838283828383e-06, | |
| "loss": 0.5202, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.811881188118812e-06, | |
| "loss": 0.5645, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.795379537953796e-06, | |
| "loss": 0.5304, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.77887788778878e-06, | |
| "loss": 0.539, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.762376237623764e-06, | |
| "loss": 0.5037, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.745874587458748e-06, | |
| "loss": 0.4562, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.72937293729373e-06, | |
| "loss": 0.511, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.712871287128714e-06, | |
| "loss": 0.5315, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.696369636963698e-06, | |
| "loss": 0.5177, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.67986798679868e-06, | |
| "loss": 0.5428, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.663366336633664e-06, | |
| "loss": 0.5344, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.646864686468648e-06, | |
| "loss": 0.5461, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.63036303630363e-06, | |
| "loss": 0.526, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.613861386138615e-06, | |
| "loss": 0.4874, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.597359735973599e-06, | |
| "loss": 0.552, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.58085808580858e-06, | |
| "loss": 0.4941, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.564356435643565e-06, | |
| "loss": 0.5594, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.547854785478549e-06, | |
| "loss": 0.5658, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.531353135313533e-06, | |
| "loss": 0.525, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.514851485148515e-06, | |
| "loss": 0.5423, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.498349834983499e-06, | |
| "loss": 0.5081, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.481848184818483e-06, | |
| "loss": 0.4847, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.465346534653465e-06, | |
| "loss": 0.5757, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.44884488448845e-06, | |
| "loss": 0.5371, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.432343234323433e-06, | |
| "loss": 0.5271, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.415841584158416e-06, | |
| "loss": 0.5045, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.3993399339934e-06, | |
| "loss": 0.5246, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.382838283828383e-06, | |
| "loss": 0.5451, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.366336633663367e-06, | |
| "loss": 0.5785, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.34983498349835e-06, | |
| "loss": 0.5336, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.5427, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.316831683168318e-06, | |
| "loss": 0.5793, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.300330033003302e-06, | |
| "loss": 0.5419, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.283828382838286e-06, | |
| "loss": 0.4903, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.267326732673268e-06, | |
| "loss": 0.5921, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.250825082508252e-06, | |
| "loss": 0.5009, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.234323432343236e-06, | |
| "loss": 0.4896, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.217821782178218e-06, | |
| "loss": 0.5422, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.201320132013202e-06, | |
| "loss": 0.5286, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.184818481848186e-06, | |
| "loss": 0.5029, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.168316831683168e-06, | |
| "loss": 0.518, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.151815181518152e-06, | |
| "loss": 0.6075, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.135313531353136e-06, | |
| "loss": 0.5119, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.11881188118812e-06, | |
| "loss": 0.568, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.102310231023103e-06, | |
| "loss": 0.5164, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.085808580858087e-06, | |
| "loss": 0.4782, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.06930693069307e-06, | |
| "loss": 0.5262, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.052805280528053e-06, | |
| "loss": 0.5287, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.036303630363037e-06, | |
| "loss": 0.5716, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.019801980198021e-06, | |
| "loss": 0.5163, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.003300330033003e-06, | |
| "loss": 0.5671, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.986798679867987e-06, | |
| "loss": 0.5133, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.970297029702971e-06, | |
| "loss": 0.507, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.953795379537953e-06, | |
| "loss": 0.5125, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.937293729372937e-06, | |
| "loss": 0.5161, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.920792079207921e-06, | |
| "loss": 0.4831, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.904290429042905e-06, | |
| "loss": 0.5461, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.887788778877888e-06, | |
| "loss": 0.5148, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.871287128712872e-06, | |
| "loss": 0.5373, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.854785478547856e-06, | |
| "loss": 0.525, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.83828382838284e-06, | |
| "loss": 0.5572, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.821782178217822e-06, | |
| "loss": 0.5546, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.805280528052806e-06, | |
| "loss": 0.5288, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.78877887788779e-06, | |
| "loss": 0.5498, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.772277227722774e-06, | |
| "loss": 0.5608, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.755775577557756e-06, | |
| "loss": 0.5596, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.73927392739274e-06, | |
| "loss": 0.5609, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.722772277227724e-06, | |
| "loss": 0.5061, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.706270627062708e-06, | |
| "loss": 0.5036, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.68976897689769e-06, | |
| "loss": 0.5344, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.673267326732674e-06, | |
| "loss": 0.5631, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.656765676567658e-06, | |
| "loss": 0.5485, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.64026402640264e-06, | |
| "loss": 0.542, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.6237623762376246e-06, | |
| "loss": 0.4833, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.6072607260726086e-06, | |
| "loss": 0.4901, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.590759075907591e-06, | |
| "loss": 0.5171, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.574257425742575e-06, | |
| "loss": 0.5121, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.557755775577559e-06, | |
| "loss": 0.4988, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.541254125412542e-06, | |
| "loss": 0.5355, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.524752475247525e-06, | |
| "loss": 0.5409, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.508250825082509e-06, | |
| "loss": 0.5416, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.491749174917492e-06, | |
| "loss": 0.5764, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.475247524752476e-06, | |
| "loss": 0.5364, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.458745874587459e-06, | |
| "loss": 0.5347, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.4422442244224424e-06, | |
| "loss": 0.5235, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.425742574257426e-06, | |
| "loss": 0.5405, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.40924092409241e-06, | |
| "loss": 0.5466, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.392739273927393e-06, | |
| "loss": 0.521, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.376237623762377e-06, | |
| "loss": 0.5223, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.359735973597361e-06, | |
| "loss": 0.5266, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.343234323432343e-06, | |
| "loss": 0.504, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.326732673267327e-06, | |
| "loss": 0.5502, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.310231023102311e-06, | |
| "loss": 0.5317, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.293729372937294e-06, | |
| "loss": 0.5268, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.277227722772278e-06, | |
| "loss": 0.5207, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.260726072607261e-06, | |
| "loss": 0.5464, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.244224422442245e-06, | |
| "loss": 0.5014, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.227722772277228e-06, | |
| "loss": 0.5227, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.211221122112212e-06, | |
| "loss": 0.5729, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.194719471947195e-06, | |
| "loss": 0.551, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.1782178217821785e-06, | |
| "loss": 0.5016, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.1617161716171625e-06, | |
| "loss": 0.4834, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.1452145214521465e-06, | |
| "loss": 0.5052, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.128712871287129e-06, | |
| "loss": 0.4771, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.112211221122113e-06, | |
| "loss": 0.4736, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.095709570957097e-06, | |
| "loss": 0.5049, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.079207920792079e-06, | |
| "loss": 0.5077, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.062706270627063e-06, | |
| "loss": 0.5493, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.046204620462047e-06, | |
| "loss": 0.4917, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.02970297029703e-06, | |
| "loss": 0.5247, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.013201320132014e-06, | |
| "loss": 0.5168, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.996699669966997e-06, | |
| "loss": 0.5009, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.98019801980198e-06, | |
| "loss": 0.5139, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.963696369636964e-06, | |
| "loss": 0.4608, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.947194719471948e-06, | |
| "loss": 0.4859, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.930693069306931e-06, | |
| "loss": 0.5315, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.9141914191419146e-06, | |
| "loss": 0.5276, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.8976897689768985e-06, | |
| "loss": 0.5472, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.881188118811881e-06, | |
| "loss": 0.5368, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.864686468646865e-06, | |
| "loss": 0.5019, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.848184818481849e-06, | |
| "loss": 0.501, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.831683168316833e-06, | |
| "loss": 0.4828, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.815181518151816e-06, | |
| "loss": 0.4927, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.798679867986799e-06, | |
| "loss": 0.5306, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.782178217821783e-06, | |
| "loss": 0.5388, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.765676567656766e-06, | |
| "loss": 0.4892, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.74917491749175e-06, | |
| "loss": 0.5158, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.732673267326733e-06, | |
| "loss": 0.5211, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.716171617161716e-06, | |
| "loss": 0.4972, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.6996699669967e-06, | |
| "loss": 0.5293, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.683168316831684e-06, | |
| "loss": 0.493, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5186, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.650165016501651e-06, | |
| "loss": 0.5443, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.633663366336635e-06, | |
| "loss": 0.5191, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.617161716171617e-06, | |
| "loss": 0.5636, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.600660066006601e-06, | |
| "loss": 0.5546, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.584158415841585e-06, | |
| "loss": 0.584, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.567656765676568e-06, | |
| "loss": 0.5388, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.551155115511552e-06, | |
| "loss": 0.4756, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.534653465346535e-06, | |
| "loss": 0.4862, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.518151815181518e-06, | |
| "loss": 0.4913, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.501650165016502e-06, | |
| "loss": 0.5333, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.485148514851486e-06, | |
| "loss": 0.5439, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.4686468646864685e-06, | |
| "loss": 0.5067, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.4521452145214525e-06, | |
| "loss": 0.541, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.4356435643564364e-06, | |
| "loss": 0.5363, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.4191419141914204e-06, | |
| "loss": 0.5208, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.402640264026403e-06, | |
| "loss": 0.5333, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.386138613861387e-06, | |
| "loss": 0.5048, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.369636963696371e-06, | |
| "loss": 0.5428, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.353135313531353e-06, | |
| "loss": 0.5751, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.336633663366337e-06, | |
| "loss": 0.5046, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.320132013201321e-06, | |
| "loss": 0.4954, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.303630363036304e-06, | |
| "loss": 0.5376, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.287128712871288e-06, | |
| "loss": 0.5353, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.270627062706271e-06, | |
| "loss": 0.5156, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.254125412541254e-06, | |
| "loss": 0.464, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.237623762376238e-06, | |
| "loss": 0.5073, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.221122112211222e-06, | |
| "loss": 0.5364, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.2046204620462046e-06, | |
| "loss": 0.5324, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.1881188118811885e-06, | |
| "loss": 0.5458, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.1716171617161725e-06, | |
| "loss": 0.5682, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.155115511551155e-06, | |
| "loss": 0.5796, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.138613861386139e-06, | |
| "loss": 0.5223, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.122112211221123e-06, | |
| "loss": 0.5266, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.105610561056106e-06, | |
| "loss": 0.5382, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.08910891089109e-06, | |
| "loss": 0.4713, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.072607260726073e-06, | |
| "loss": 0.4912, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.056105610561056e-06, | |
| "loss": 0.5103, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.03960396039604e-06, | |
| "loss": 0.5032, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.023102310231024e-06, | |
| "loss": 0.5495, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.006600660066007e-06, | |
| "loss": 0.4878, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.99009900990099e-06, | |
| "loss": 0.5095, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.973597359735974e-06, | |
| "loss": 0.5221, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.957095709570958e-06, | |
| "loss": 0.522, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.940594059405941e-06, | |
| "loss": 0.512, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.924092409240925e-06, | |
| "loss": 0.531, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.907590759075909e-06, | |
| "loss": 0.4759, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.891089108910891e-06, | |
| "loss": 0.5209, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.874587458745875e-06, | |
| "loss": 0.4937, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.858085808580859e-06, | |
| "loss": 0.5166, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.841584158415842e-06, | |
| "loss": 0.473, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.825082508250826e-06, | |
| "loss": 0.5615, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.808580858085809e-06, | |
| "loss": 0.5121, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.792079207920792e-06, | |
| "loss": 0.4906, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.775577557755776e-06, | |
| "loss": 0.5163, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.75907590759076e-06, | |
| "loss": 0.5809, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.7425742574257425e-06, | |
| "loss": 0.5459, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.7260726072607264e-06, | |
| "loss": 0.4919, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.70957095709571e-06, | |
| "loss": 0.5123, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.693069306930693e-06, | |
| "loss": 0.5309, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.676567656765677e-06, | |
| "loss": 0.5496, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.660066006600661e-06, | |
| "loss": 0.5144, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.643564356435644e-06, | |
| "loss": 0.5126, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.627062706270627e-06, | |
| "loss": 0.4796, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.610561056105611e-06, | |
| "loss": 0.5417, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.594059405940595e-06, | |
| "loss": 0.4922, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.577557755775578e-06, | |
| "loss": 0.5188, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.561056105610562e-06, | |
| "loss": 0.4676, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.544554455445545e-06, | |
| "loss": 0.5076, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.528052805280528e-06, | |
| "loss": 0.5256, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.511551155115512e-06, | |
| "loss": 0.4906, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.495049504950496e-06, | |
| "loss": 0.5268, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.4785478547854785e-06, | |
| "loss": 0.5112, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.4620462046204625e-06, | |
| "loss": 0.4938, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.4455445544554465e-06, | |
| "loss": 0.5611, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.429042904290429e-06, | |
| "loss": 0.5532, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.412541254125413e-06, | |
| "loss": 0.5343, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.396039603960397e-06, | |
| "loss": 0.5404, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.37953795379538e-06, | |
| "loss": 0.5418, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.363036303630364e-06, | |
| "loss": 0.4836, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.346534653465347e-06, | |
| "loss": 0.4891, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.33003300330033e-06, | |
| "loss": 0.4727, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.313531353135314e-06, | |
| "loss": 0.4926, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.297029702970298e-06, | |
| "loss": 0.515, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.28052805280528e-06, | |
| "loss": 0.5263, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.264026402640264e-06, | |
| "loss": 0.5381, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.247524752475248e-06, | |
| "loss": 0.5259, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 5.231023102310231e-06, | |
| "loss": 0.494, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.214521452145215e-06, | |
| "loss": 0.5681, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.1980198019801986e-06, | |
| "loss": 0.5146, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.1815181518151826e-06, | |
| "loss": 0.5885, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.165016501650165e-06, | |
| "loss": 0.5182, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.148514851485149e-06, | |
| "loss": 0.5094, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.132013201320133e-06, | |
| "loss": 0.5208, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.115511551155116e-06, | |
| "loss": 0.4969, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.0990099009901e-06, | |
| "loss": 0.4974, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.082508250825083e-06, | |
| "loss": 0.4893, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.066006600660066e-06, | |
| "loss": 0.5605, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.04950495049505e-06, | |
| "loss": 0.5285, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.033003300330034e-06, | |
| "loss": 0.5375, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.0165016501650164e-06, | |
| "loss": 0.4906, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5413, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.9834983498349835e-06, | |
| "loss": 0.5934, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.9669966996699675e-06, | |
| "loss": 0.5093, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.950495049504951e-06, | |
| "loss": 0.5305, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.933993399339934e-06, | |
| "loss": 0.5534, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.917491749174918e-06, | |
| "loss": 0.54, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.900990099009901e-06, | |
| "loss": 0.5404, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.884488448844885e-06, | |
| "loss": 0.5408, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.867986798679869e-06, | |
| "loss": 0.4956, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.851485148514852e-06, | |
| "loss": 0.5042, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.834983498349836e-06, | |
| "loss": 0.5014, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.818481848184819e-06, | |
| "loss": 0.5651, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.801980198019802e-06, | |
| "loss": 0.5257, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.785478547854786e-06, | |
| "loss": 0.5143, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.768976897689769e-06, | |
| "loss": 0.4706, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.7524752475247525e-06, | |
| "loss": 0.4911, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.7359735973597365e-06, | |
| "loss": 0.4994, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.71947194719472e-06, | |
| "loss": 0.5162, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.702970297029703e-06, | |
| "loss": 0.4987, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.686468646864687e-06, | |
| "loss": 0.4791, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.66996699669967e-06, | |
| "loss": 0.5449, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.653465346534654e-06, | |
| "loss": 0.4738, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.636963696369637e-06, | |
| "loss": 0.5353, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.620462046204621e-06, | |
| "loss": 0.5287, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.603960396039605e-06, | |
| "loss": 0.5528, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.587458745874588e-06, | |
| "loss": 0.5267, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.570957095709571e-06, | |
| "loss": 0.4881, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.554455445544555e-06, | |
| "loss": 0.5573, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.537953795379538e-06, | |
| "loss": 0.52, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.5214521452145214e-06, | |
| "loss": 0.503, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.5049504950495054e-06, | |
| "loss": 0.5097, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.4884488448844886e-06, | |
| "loss": 0.5514, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.4719471947194725e-06, | |
| "loss": 0.526, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.455445544554456e-06, | |
| "loss": 0.5, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.438943894389439e-06, | |
| "loss": 0.4736, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.422442244224423e-06, | |
| "loss": 0.4961, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.405940594059406e-06, | |
| "loss": 0.5664, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.38943894389439e-06, | |
| "loss": 0.5631, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.372937293729374e-06, | |
| "loss": 0.494, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.356435643564357e-06, | |
| "loss": 0.5277, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.33993399339934e-06, | |
| "loss": 0.5417, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.323432343234324e-06, | |
| "loss": 0.5174, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.306930693069307e-06, | |
| "loss": 0.4929, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.29042904290429e-06, | |
| "loss": 0.4719, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.273927392739274e-06, | |
| "loss": 0.4924, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.2574257425742575e-06, | |
| "loss": 0.4951, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.2409240924092415e-06, | |
| "loss": 0.471, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.224422442244225e-06, | |
| "loss": 0.5077, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.207920792079208e-06, | |
| "loss": 0.5385, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.191419141914192e-06, | |
| "loss": 0.504, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.174917491749175e-06, | |
| "loss": 0.4735, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.158415841584159e-06, | |
| "loss": 0.449, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.141914191419143e-06, | |
| "loss": 0.5192, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.125412541254126e-06, | |
| "loss": 0.5347, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1250, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |