Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/README-checkpoint.md +59 -0
- .ipynb_checkpoints/trainer_log-checkpoint.jsonl +156 -0
- .ipynb_checkpoints/training_loss-checkpoint.png +0 -0
- README.md +59 -0
- all_results.json +8 -0
- config.json +31 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +197 -0
- train_results.json +8 -0
- trainer_log.jsonl +156 -0
- trainer_state.json +1085 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Zyphra/ZR1-1.5B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Zyphra/ZR1-1.5B](https://huggingface.co/Zyphra/ZR1-1.5B) on the svg dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 7e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 5.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.45.2
|
| 57 |
+
- Pytorch 2.7.0+cu126
|
| 58 |
+
- Datasets 2.21.0
|
| 59 |
+
- Tokenizers 0.20.3
|
.ipynb_checkpoints/trainer_log-checkpoint.jsonl
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 745, "loss": 2.2902, "lr": 4.666666666666666e-06, "epoch": 0.03350083752093802, "percentage": 0.67, "elapsed_time": "0:00:49", "remaining_time": "2:02:13"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 745, "loss": 1.4714, "lr": 9.333333333333333e-06, "epoch": 0.06700167504187604, "percentage": 1.34, "elapsed_time": "0:01:29", "remaining_time": "1:49:03"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 745, "loss": 0.8749, "lr": 1.4e-05, "epoch": 0.10050251256281408, "percentage": 2.01, "elapsed_time": "0:02:08", "remaining_time": "1:44:36"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 745, "loss": 0.7402, "lr": 1.8666666666666665e-05, "epoch": 0.13400335008375208, "percentage": 2.68, "elapsed_time": "0:02:48", "remaining_time": "1:41:53"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 745, "loss": 0.6662, "lr": 2.333333333333333e-05, "epoch": 0.16750418760469013, "percentage": 3.36, "elapsed_time": "0:03:26", "remaining_time": "1:39:04"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 745, "loss": 0.6202, "lr": 2.8e-05, "epoch": 0.20100502512562815, "percentage": 4.03, "elapsed_time": "0:04:13", "remaining_time": "1:40:45"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 745, "loss": 0.6055, "lr": 3.266666666666666e-05, "epoch": 0.23450586264656617, "percentage": 4.7, "elapsed_time": "0:04:50", "remaining_time": "1:38:03"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 745, "loss": 0.6467, "lr": 3.733333333333333e-05, "epoch": 0.26800670016750416, "percentage": 5.37, "elapsed_time": "0:05:32", "remaining_time": "1:37:35"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 745, "loss": 0.6908, "lr": 4.2e-05, "epoch": 0.3015075376884422, "percentage": 6.04, "elapsed_time": "0:06:10", "remaining_time": "1:36:09"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 745, "loss": 0.6715, "lr": 4.666666666666666e-05, "epoch": 0.33500837520938026, "percentage": 6.71, "elapsed_time": "0:06:54", "remaining_time": "1:36:03"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 745, "loss": 0.6929, "lr": 5.1333333333333325e-05, "epoch": 0.3685092127303183, "percentage": 7.38, "elapsed_time": "0:07:42", "remaining_time": "1:36:39"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 745, "loss": 0.6122, "lr": 5.6e-05, "epoch": 0.4020100502512563, "percentage": 8.05, "elapsed_time": "0:08:23", "remaining_time": "1:35:47"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 745, "loss": 0.5965, "lr": 6.0666666666666666e-05, "epoch": 0.4355108877721943, "percentage": 8.72, "elapsed_time": "0:08:56", "remaining_time": "1:33:30"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 745, "loss": 0.6156, "lr": 6.533333333333333e-05, "epoch": 0.46901172529313234, "percentage": 9.4, "elapsed_time": "0:09:36", "remaining_time": "1:32:41"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 745, "loss": 0.6128, "lr": 7e-05, "epoch": 0.5025125628140703, "percentage": 10.07, "elapsed_time": "0:10:13", "remaining_time": "1:31:22"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 745, "loss": 0.6462, "lr": 6.999038147884355e-05, "epoch": 0.5360134003350083, "percentage": 10.74, "elapsed_time": "0:11:01", "remaining_time": "1:31:39"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 745, "loss": 0.6145, "lr": 6.99615312019999e-05, "epoch": 0.5695142378559463, "percentage": 11.41, "elapsed_time": "0:11:43", "remaining_time": "1:30:59"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 745, "loss": 0.5769, "lr": 6.991346502644035e-05, "epoch": 0.6030150753768844, "percentage": 12.08, "elapsed_time": "0:12:22", "remaining_time": "1:30:05"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 745, "loss": 0.6176, "lr": 6.984620937076643e-05, "epoch": 0.6365159128978225, "percentage": 12.75, "elapsed_time": "0:13:04", "remaining_time": "1:29:28"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 745, "loss": 0.5512, "lr": 6.975980120068939e-05, "epoch": 0.6700167504187605, "percentage": 13.42, "elapsed_time": "0:13:52", "remaining_time": "1:29:29"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 745, "loss": 0.6277, "lr": 6.965428800871278e-05, "epoch": 0.7035175879396985, "percentage": 14.09, "elapsed_time": "0:14:31", "remaining_time": "1:28:33"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 745, "loss": 0.6424, "lr": 6.952972778802912e-05, "epoch": 0.7370184254606366, "percentage": 14.77, "elapsed_time": "0:15:14", "remaining_time": "1:27:58"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 745, "loss": 0.6046, "lr": 6.938618900064515e-05, "epoch": 0.7705192629815746, "percentage": 15.44, "elapsed_time": "0:15:58", "remaining_time": "1:27:32"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 745, "loss": 0.618, "lr": 6.922375053975308e-05, "epoch": 0.8040201005025126, "percentage": 16.11, "elapsed_time": "0:16:35", "remaining_time": "1:26:23"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 745, "loss": 0.6257, "lr": 6.904250168636844e-05, "epoch": 0.8375209380234506, "percentage": 16.78, "elapsed_time": "0:17:19", "remaining_time": "1:25:54"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 745, "loss": 0.5944, "lr": 6.884254206025877e-05, "epoch": 0.8710217755443886, "percentage": 17.45, "elapsed_time": "0:18:04", "remaining_time": "1:25:31"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 745, "loss": 0.5749, "lr": 6.86239815651894e-05, "epoch": 0.9045226130653267, "percentage": 18.12, "elapsed_time": "0:18:38", "remaining_time": "1:24:14"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 745, "loss": 0.5728, "lr": 6.838694032851726e-05, "epoch": 0.9380234505862647, "percentage": 18.79, "elapsed_time": "0:19:19", "remaining_time": "1:23:30"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 745, "loss": 0.6186, "lr": 6.813154863516519e-05, "epoch": 0.9715242881072027, "percentage": 19.46, "elapsed_time": "0:20:09", "remaining_time": "1:23:23"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 745, "loss": 0.5516, "lr": 6.785794685601351e-05, "epoch": 1.0050251256281406, "percentage": 20.13, "elapsed_time": "0:20:47", "remaining_time": "1:22:27"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 745, "loss": 0.4678, "lr": 6.756628537074802e-05, "epoch": 1.0385259631490786, "percentage": 20.81, "elapsed_time": "0:21:35", "remaining_time": "1:22:09"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 745, "loss": 0.508, "lr": 6.725672448520679e-05, "epoch": 1.0720268006700167, "percentage": 21.48, "elapsed_time": "0:22:23", "remaining_time": "1:21:52"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 745, "loss": 0.48, "lr": 6.692943434327137e-05, "epoch": 1.1055276381909547, "percentage": 22.15, "elapsed_time": "0:23:11", "remaining_time": "1:21:31"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 745, "loss": 0.4675, "lr": 6.65845948333506e-05, "epoch": 1.1390284757118927, "percentage": 22.82, "elapsed_time": "0:23:48", "remaining_time": "1:20:31"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 745, "loss": 0.4949, "lr": 6.622239548950852e-05, "epoch": 1.1725293132328307, "percentage": 23.49, "elapsed_time": "0:24:31", "remaining_time": "1:19:52"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 745, "loss": 0.5078, "lr": 6.584303538729098e-05, "epoch": 1.2060301507537687, "percentage": 24.16, "elapsed_time": "0:25:15", "remaining_time": "1:19:16"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 745, "loss": 0.4654, "lr": 6.544672303430766e-05, "epoch": 1.2395309882747068, "percentage": 24.83, "elapsed_time": "0:25:54", "remaining_time": "1:18:26"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 745, "loss": 0.4841, "lr": 6.503367625563004e-05, "epoch": 1.2730318257956448, "percentage": 25.5, "elapsed_time": "0:26:35", "remaining_time": "1:17:40"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 745, "loss": 0.5139, "lr": 6.46041220740684e-05, "epoch": 1.3065326633165828, "percentage": 26.17, "elapsed_time": "0:27:14", "remaining_time": "1:16:50"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 745, "loss": 0.4688, "lr": 6.41582965853932e-05, "epoch": 1.3400335008375208, "percentage": 26.85, "elapsed_time": "0:28:02", "remaining_time": "1:16:23"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 745, "loss": 0.4757, "lr": 6.369644482856986e-05, "epoch": 1.3735343383584588, "percentage": 27.52, "elapsed_time": "0:28:42", "remaining_time": "1:15:36"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 745, "loss": 0.4656, "lr": 6.321882065107803e-05, "epoch": 1.4070351758793969, "percentage": 28.19, "elapsed_time": "0:29:19", "remaining_time": "1:14:42"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 745, "loss": 0.4519, "lr": 6.272568656938952e-05, "epoch": 1.4405360134003349, "percentage": 28.86, "elapsed_time": "0:30:00", "remaining_time": "1:13:58"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 745, "loss": 0.4843, "lr": 6.221731362468132e-05, "epoch": 1.474036850921273, "percentage": 29.53, "elapsed_time": "0:30:42", "remaining_time": "1:13:17"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 745, "loss": 0.4852, "lr": 6.169398123386336e-05, "epoch": 1.507537688442211, "percentage": 30.2, "elapsed_time": "0:31:26", "remaining_time": "1:12:40"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 745, "loss": 0.4833, "lr": 6.115597703600269e-05, "epoch": 1.541038525963149, "percentage": 30.87, "elapsed_time": "0:32:02", "remaining_time": "1:11:44"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 745, "loss": 0.493, "lr": 6.060359673422841e-05, "epoch": 1.574539363484087, "percentage": 31.54, "elapsed_time": "0:32:48", "remaining_time": "1:11:11"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 745, "loss": 0.4667, "lr": 6.003714393320446e-05, "epoch": 1.608040201005025, "percentage": 32.21, "elapsed_time": "0:33:27", "remaining_time": "1:10:23"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 745, "loss": 0.4988, "lr": 5.945692997225945e-05, "epoch": 1.641541038525963, "percentage": 32.89, "elapsed_time": "0:34:06", "remaining_time": "1:09:36"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 745, "loss": 0.4782, "lr": 5.8863273754265325e-05, "epoch": 1.675041876046901, "percentage": 33.56, "elapsed_time": "0:34:43", "remaining_time": "1:08:46"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 745, "loss": 0.4822, "lr": 5.825650157035876e-05, "epoch": 1.708542713567839, "percentage": 34.23, "elapsed_time": "0:35:21", "remaining_time": "1:07:56"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 745, "loss": 0.4345, "lr": 5.763694692060194e-05, "epoch": 1.742043551088777, "percentage": 34.9, "elapsed_time": "0:35:55", "remaining_time": "1:06:59"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 745, "loss": 0.488, "lr": 5.700495033068097e-05, "epoch": 1.775544388609715, "percentage": 35.57, "elapsed_time": "0:36:42", "remaining_time": "1:06:30"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 745, "loss": 0.5029, "lr": 5.636085916474272e-05, "epoch": 1.809045226130653, "percentage": 36.24, "elapsed_time": "0:37:25", "remaining_time": "1:05:50"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 745, "loss": 0.4689, "lr": 5.570502743447328e-05, "epoch": 1.8425460636515911, "percentage": 36.91, "elapsed_time": "0:38:06", "remaining_time": "1:05:07"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 745, "loss": 0.4732, "lr": 5.503781560452251e-05, "epoch": 1.8760469011725294, "percentage": 37.58, "elapsed_time": "0:38:45", "remaining_time": "1:04:22"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 745, "loss": 0.4228, "lr": 5.435959039438197e-05, "epoch": 1.9095477386934674, "percentage": 38.26, "elapsed_time": "0:39:25", "remaining_time": "1:03:37"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 745, "loss": 0.5041, "lr": 5.367072457682496e-05, "epoch": 1.9430485762144054, "percentage": 38.93, "elapsed_time": "0:40:08", "remaining_time": "1:02:58"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 745, "loss": 0.4211, "lr": 5.297159677301946e-05, "epoch": 1.9765494137353434, "percentage": 39.6, "elapsed_time": "0:40:45", "remaining_time": "1:02:10"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 745, "loss": 0.4343, "lr": 5.226259124442675e-05, "epoch": 2.0100502512562812, "percentage": 40.27, "elapsed_time": "0:41:26", "remaining_time": "1:01:28"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 745, "loss": 0.3459, "lr": 5.1544097681599774e-05, "epoch": 2.0435510887772192, "percentage": 40.94, "elapsed_time": "0:42:04", "remaining_time": "1:00:41"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 745, "loss": 0.3323, "lr": 5.081651098999768e-05, "epoch": 2.0770519262981573, "percentage": 41.61, "elapsed_time": "0:42:44", "remaining_time": "0:59:59"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 745, "loss": 0.3071, "lr": 5.008023107293396e-05, "epoch": 2.1105527638190953, "percentage": 42.28, "elapsed_time": "0:43:25", "remaining_time": "0:59:16"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 745, "loss": 0.3019, "lr": 4.9335662611777724e-05, "epoch": 2.1440536013400333, "percentage": 42.95, "elapsed_time": "0:44:07", "remaining_time": "0:58:36"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 745, "loss": 0.3203, "lr": 4.8583214843528736e-05, "epoch": 2.1775544388609713, "percentage": 43.62, "elapsed_time": "0:44:49", "remaining_time": "0:57:55"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 745, "loss": 0.3302, "lr": 4.7823301335888614e-05, "epoch": 2.2110552763819094, "percentage": 44.3, "elapsed_time": "0:45:25", "remaining_time": "0:57:07"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 745, "loss": 0.3386, "lr": 4.7056339759951644e-05, "epoch": 2.2445561139028474, "percentage": 44.97, "elapsed_time": "0:46:06", "remaining_time": "0:56:25"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 745, "loss": 0.3379, "lr": 4.6282751660640375e-05, "epoch": 2.2780569514237854, "percentage": 45.64, "elapsed_time": "0:46:44", "remaining_time": "0:55:40"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 745, "loss": 0.3163, "lr": 4.550296222501192e-05, "epoch": 2.3115577889447234, "percentage": 46.31, "elapsed_time": "0:47:22", "remaining_time": "0:54:55"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 745, "loss": 0.3086, "lr": 4.471740004856251e-05, "epoch": 2.3450586264656614, "percentage": 46.98, "elapsed_time": "0:47:56", "remaining_time": "0:54:06"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 745, "loss": 0.319, "lr": 4.392649689965867e-05, "epoch": 2.3785594639865995, "percentage": 47.65, "elapsed_time": "0:48:34", "remaining_time": "0:53:22"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 745, "loss": 0.3321, "lr": 4.313068748222441e-05, "epoch": 2.4120603015075375, "percentage": 48.32, "elapsed_time": "0:49:18", "remaining_time": "0:52:44"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 745, "loss": 0.3348, "lr": 4.233040919681506e-05, "epoch": 2.4455611390284755, "percentage": 48.99, "elapsed_time": "0:50:03", "remaining_time": "0:52:07"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 745, "loss": 0.3189, "lr": 4.152610190020884e-05, "epoch": 2.4790619765494135, "percentage": 49.66, "elapsed_time": "0:50:43", "remaining_time": "0:51:25"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 745, "loss": 0.332, "lr": 4.071820766364855e-05, "epoch": 2.5125628140703515, "percentage": 50.34, "elapsed_time": "0:51:25", "remaining_time": "0:50:44"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 745, "loss": 0.339, "lr": 3.990717052986601e-05, "epoch": 2.5460636515912896, "percentage": 51.01, "elapsed_time": "0:52:03", "remaining_time": "0:50:00"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 745, "loss": 0.3473, "lr": 3.909343626902289e-05, "epoch": 2.5795644891122276, "percentage": 51.68, "elapsed_time": "0:52:41", "remaining_time": "0:49:16"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 745, "loss": 0.3431, "lr": 3.8277452133702276e-05, "epoch": 2.6130653266331656, "percentage": 52.35, "elapsed_time": "0:53:28", "remaining_time": "0:48:40"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 745, "loss": 0.3689, "lr": 3.745966661308525e-05, "epoch": 2.6465661641541036, "percentage": 53.02, "elapsed_time": "0:54:14", "remaining_time": "0:48:04"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 745, "loss": 0.3166, "lr": 3.66405291864479e-05, "epoch": 2.6800670016750416, "percentage": 53.69, "elapsed_time": "0:55:01", "remaining_time": "0:47:27"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 745, "loss": 0.3638, "lr": 3.5820490076114116e-05, "epoch": 2.7135678391959797, "percentage": 54.36, "elapsed_time": "0:55:45", "remaining_time": "0:46:48"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 745, "loss": 0.3503, "lr": 3.5e-05, "epoch": 2.7470686767169177, "percentage": 55.03, "elapsed_time": "0:56:27", "remaining_time": "0:46:07"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 745, "loss": 0.367, "lr": 3.4179509923885885e-05, "epoch": 2.7805695142378557, "percentage": 55.7, "elapsed_time": "0:57:11", "remaining_time": "0:45:28"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 745, "loss": 0.3212, "lr": 3.335947081355209e-05, "epoch": 2.8140703517587937, "percentage": 56.38, "elapsed_time": "0:57:49", "remaining_time": "0:44:44"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 745, "loss": 0.3311, "lr": 3.254033338691476e-05, "epoch": 2.8475711892797317, "percentage": 57.05, "elapsed_time": "0:58:34", "remaining_time": "0:44:05"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 745, "loss": 0.3207, "lr": 3.1722547866297724e-05, "epoch": 2.8810720268006698, "percentage": 57.72, "elapsed_time": "0:59:18", "remaining_time": "0:43:26"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 745, "loss": 0.3208, "lr": 3.090656373097711e-05, "epoch": 2.914572864321608, "percentage": 58.39, "elapsed_time": "1:00:04", "remaining_time": "0:42:48"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 745, "loss": 0.3018, "lr": 3.0092829470133993e-05, "epoch": 2.948073701842546, "percentage": 59.06, "elapsed_time": "1:00:43", "remaining_time": "0:42:05"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 745, "loss": 0.3235, "lr": 2.9281792336351436e-05, "epoch": 2.981574539363484, "percentage": 59.73, "elapsed_time": "1:01:21", "remaining_time": "0:41:21"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 745, "loss": 0.2668, "lr": 2.8473898099791164e-05, "epoch": 3.0150753768844223, "percentage": 60.4, "elapsed_time": "1:02:00", "remaining_time": "0:40:39"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 745, "loss": 0.2008, "lr": 2.7669590803184948e-05, "epoch": 3.0485762144053603, "percentage": 61.07, "elapsed_time": "1:02:38", "remaining_time": "0:39:55"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 745, "loss": 0.184, "lr": 2.686931251777559e-05, "epoch": 3.0820770519262983, "percentage": 61.74, "elapsed_time": "1:03:16", "remaining_time": "0:39:12"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 745, "loss": 0.2065, "lr": 2.6073503100341324e-05, "epoch": 3.1155778894472363, "percentage": 62.42, "elapsed_time": "1:03:58", "remaining_time": "0:38:31"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 745, "loss": 0.2146, "lr": 2.5282599951437474e-05, "epoch": 3.1490787269681744, "percentage": 63.09, "elapsed_time": "1:04:50", "remaining_time": "0:37:56"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 745, "loss": 0.2227, "lr": 2.449703777498808e-05, "epoch": 3.1825795644891124, "percentage": 63.76, "elapsed_time": "1:05:39", "remaining_time": "0:37:19"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 745, "loss": 0.1902, "lr": 2.371724833935962e-05, "epoch": 3.2160804020100504, "percentage": 64.43, "elapsed_time": "1:06:16", "remaining_time": "0:36:35"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 745, "loss": 0.1713, "lr": 2.2943660240048347e-05, "epoch": 3.2495812395309884, "percentage": 65.1, "elapsed_time": "1:06:54", "remaining_time": "0:35:52"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 745, "loss": 0.2053, "lr": 2.217669866411138e-05, "epoch": 3.2830820770519265, "percentage": 65.77, "elapsed_time": "1:07:38", "remaining_time": "0:35:11"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 745, "loss": 0.2057, "lr": 2.141678515647125e-05, "epoch": 3.3165829145728645, "percentage": 66.44, "elapsed_time": "1:08:17", "remaining_time": "0:34:29"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 745, "loss": 0.1915, "lr": 2.066433738822227e-05, "epoch": 3.3500837520938025, "percentage": 67.11, "elapsed_time": "1:09:01", "remaining_time": "0:33:49"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 745, "loss": 0.1961, "lr": 1.9919768927066035e-05, "epoch": 3.3835845896147405, "percentage": 67.79, "elapsed_time": "1:09:45", "remaining_time": "0:33:09"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 745, "loss": 0.1746, "lr": 1.918348901000232e-05, "epoch": 3.4170854271356785, "percentage": 68.46, "elapsed_time": "1:10:26", "remaining_time": "0:32:27"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 745, "loss": 0.2121, "lr": 1.845590231840021e-05, "epoch": 3.4505862646566166, "percentage": 69.13, "elapsed_time": "1:11:12", "remaining_time": "0:31:48"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 745, "loss": 0.1668, "lr": 1.7737408755573246e-05, "epoch": 3.4840871021775546, "percentage": 69.8, "elapsed_time": "1:11:47", "remaining_time": "0:31:03"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 745, "loss": 0.1703, "lr": 1.7028403226980523e-05, "epoch": 3.5175879396984926, "percentage": 70.47, "elapsed_time": "1:12:25", "remaining_time": "0:30:20"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 745, "loss": 0.1795, "lr": 1.6329275423175046e-05, "epoch": 3.5510887772194306, "percentage": 71.14, "elapsed_time": "1:13:04", "remaining_time": "0:29:38"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 745, "loss": 0.1748, "lr": 1.564040960561802e-05, "epoch": 3.5845896147403686, "percentage": 71.81, "elapsed_time": "1:13:38", "remaining_time": "0:28:54"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 745, "loss": 0.1798, "lr": 1.496218439547749e-05, "epoch": 3.6180904522613067, "percentage": 72.48, "elapsed_time": "1:14:12", "remaining_time": "0:28:10"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 745, "loss": 0.1689, "lr": 1.4294972565526714e-05, "epoch": 3.6515912897822447, "percentage": 73.15, "elapsed_time": "1:14:49", "remaining_time": "0:27:27"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 745, "loss": 0.2217, "lr": 1.3639140835257279e-05, "epoch": 3.6850921273031827, "percentage": 73.83, "elapsed_time": "1:15:35", "remaining_time": "0:26:47"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 745, "loss": 0.1921, "lr": 1.2995049669319036e-05, "epoch": 3.7185929648241207, "percentage": 74.5, "elapsed_time": "1:16:18", "remaining_time": "0:26:07"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 745, "loss": 0.2058, "lr": 1.2363053079398044e-05, "epoch": 3.7520938023450587, "percentage": 75.17, "elapsed_time": "1:17:04", "remaining_time": "0:25:27"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 745, "loss": 0.1807, "lr": 1.1743498429641242e-05, "epoch": 3.7855946398659968, "percentage": 75.84, "elapsed_time": "1:17:45", "remaining_time": "0:24:46"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 745, "loss": 0.1845, "lr": 1.1136726245734674e-05, "epoch": 3.819095477386935, "percentage": 76.51, "elapsed_time": "1:18:28", "remaining_time": "0:24:05"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 745, "loss": 0.1853, "lr": 1.0543070027740541e-05, "epoch": 3.852596314907873, "percentage": 77.18, "elapsed_time": "1:19:07", "remaining_time": "0:23:23"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 745, "loss": 0.1912, "lr": 9.962856066795543e-06, "epoch": 3.886097152428811, "percentage": 77.85, "elapsed_time": "1:19:47", "remaining_time": "0:22:42"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 745, "loss": 0.1815, "lr": 9.396403265771593e-06, "epoch": 3.919597989949749, "percentage": 78.52, "elapsed_time": "1:20:26", "remaining_time": "0:21:59"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 745, "loss": 0.2068, "lr": 8.844022963997302e-06, "epoch": 3.953098827470687, "percentage": 79.19, "elapsed_time": "1:21:13", "remaining_time": "0:21:20"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 745, "loss": 0.1852, "lr": 8.306018766136634e-06, "epoch": 3.986599664991625, "percentage": 79.87, "elapsed_time": "1:21:49", "remaining_time": "0:20:37"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 745, "loss": 0.1656, "lr": 7.782686375318677e-06, "epoch": 4.0201005025125625, "percentage": 80.54, "elapsed_time": "1:22:35", "remaining_time": "0:19:57"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 745, "loss": 0.1076, "lr": 7.2743134306104725e-06, "epoch": 4.0536013400335005, "percentage": 81.21, "elapsed_time": "1:23:16", "remaining_time": "0:19:16"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 745, "loss": 0.141, "lr": 6.781179348921959e-06, "epoch": 4.0871021775544385, "percentage": 81.88, "elapsed_time": "1:24:07", "remaining_time": "0:18:37"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 745, "loss": 0.1196, "lr": 6.303555171430139e-06, "epoch": 4.1206030150753765, "percentage": 82.55, "elapsed_time": "1:24:50", "remaining_time": "0:17:56"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 745, "loss": 0.1039, "lr": 5.8417034146068e-06, "epoch": 4.1541038525963145, "percentage": 83.22, "elapsed_time": "1:25:27", "remaining_time": "0:17:13"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 745, "loss": 0.1461, "lr": 5.3958779259315894e-06, "epoch": 4.187604690117253, "percentage": 83.89, "elapsed_time": "1:26:14", "remaining_time": "0:16:33"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 745, "loss": 0.1088, "lr": 4.966323744369957e-06, "epoch": 4.221105527638191, "percentage": 84.56, "elapsed_time": "1:26:55", "remaining_time": "0:15:52"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 745, "loss": 0.0861, "lr": 4.553276965692342e-06, "epoch": 4.254606365159129, "percentage": 85.23, "elapsed_time": "1:27:31", "remaining_time": "0:15:09"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 745, "loss": 0.113, "lr": 4.15696461270901e-06, "epoch": 4.288107202680067, "percentage": 85.91, "elapsed_time": "1:28:16", "remaining_time": "0:14:28"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 745, "loss": 0.1051, "lr": 3.7776045104914728e-06, "epoch": 4.321608040201005, "percentage": 86.58, "elapsed_time": "1:28:58", "remaining_time": "0:13:47"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 745, "loss": 0.0947, "lr": 3.4154051666494086e-06, "epoch": 4.355108877721943, "percentage": 87.25, "elapsed_time": "1:29:36", "remaining_time": "0:13:05"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 745, "loss": 0.1155, "lr": 3.070565656728618e-06, "epoch": 4.388609715242881, "percentage": 87.92, "elapsed_time": "1:30:22", "remaining_time": "0:12:25"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 745, "loss": 0.0996, "lr": 2.7432755147931913e-06, "epoch": 4.422110552763819, "percentage": 88.59, "elapsed_time": "1:31:05", "remaining_time": "0:11:43"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 745, "loss": 0.09, "lr": 2.4337146292519717e-06, "epoch": 4.455611390284757, "percentage": 89.26, "elapsed_time": "1:31:40", "remaining_time": "0:11:01"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 745, "loss": 0.0998, "lr": 2.1420531439864768e-06, "epoch": 4.489112227805695, "percentage": 89.93, "elapsed_time": "1:32:19", "remaining_time": "0:10:20"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 745, "loss": 0.1131, "lr": 1.868451364834806e-06, "epoch": 4.522613065326633, "percentage": 90.6, "elapsed_time": "1:33:07", "remaining_time": "0:09:39"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 745, "loss": 0.0996, "lr": 1.6130596714827338e-06, "epoch": 4.556113902847571, "percentage": 91.28, "elapsed_time": "1:33:46", "remaining_time": "0:08:57"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 745, "loss": 0.0913, "lr": 1.3760184348105974e-06, "epoch": 4.589614740368509, "percentage": 91.95, "elapsed_time": "1:34:18", "remaining_time": "0:08:15"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 745, "loss": 0.1163, "lr": 1.1574579397412277e-06, "epoch": 4.623115577889447, "percentage": 92.62, "elapsed_time": "1:34:59", "remaining_time": "0:07:34"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 745, "loss": 0.0988, "lr": 9.574983136315444e-07, "epoch": 4.656616415410385, "percentage": 93.29, "elapsed_time": "1:35:36", "remaining_time": "0:06:52"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 745, "loss": 0.137, "lr": 7.762494602469205e-07, "epoch": 4.690117252931323, "percentage": 93.96, "elapsed_time": "1:36:25", "remaining_time": "0:06:11"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 745, "loss": 0.0944, "lr": 6.138109993548362e-07, "epoch": 4.723618090452261, "percentage": 94.63, "elapsed_time": "1:36:59", "remaining_time": "0:05:30"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 745, "loss": 0.1124, "lr": 4.7027221197087516e-07, "epoch": 4.757118927973199, "percentage": 95.3, "elapsed_time": "1:37:43", "remaining_time": "0:04:49"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 745, "loss": 0.1061, "lr": 3.457119912872169e-07, "epoch": 4.790619765494137, "percentage": 95.97, "elapsed_time": "1:38:21", "remaining_time": "0:04:07"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 745, "loss": 0.088, "lr": 2.401987993106058e-07, "epoch": 4.824120603015075, "percentage": 96.64, "elapsed_time": "1:39:01", "remaining_time": "0:03:26"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 745, "loss": 0.1112, "lr": 1.5379062923356667e-07, "epoch": 4.857621440536013, "percentage": 97.32, "elapsed_time": "1:39:42", "remaining_time": "0:02:45"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 745, "loss": 0.1014, "lr": 8.6534973559646e-08, "epoch": 4.891122278056951, "percentage": 97.99, "elapsed_time": "1:40:22", "remaining_time": "0:02:03"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 745, "loss": 0.1203, "lr": 3.846879800010194e-08, "epoch": 4.924623115577889, "percentage": 98.66, "elapsed_time": "1:41:05", "remaining_time": "0:01:22"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 745, "loss": 0.1164, "lr": 9.618521156443681e-09, "epoch": 4.958123953098827, "percentage": 99.33, "elapsed_time": "1:41:48", "remaining_time": "0:00:41"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 745, "loss": 0.1109, "lr": 0.0, "epoch": 4.991624790619765, "percentage": 100.0, "elapsed_time": "1:42:24", "remaining_time": "0:00:00"}
|
| 150 |
+
{"current_steps": 745, "total_steps": 745, "epoch": 4.991624790619765, "percentage": 100.0, "elapsed_time": "1:42:41", "remaining_time": "0:00:00"}
|
| 151 |
+
{"current_steps": 750, "total_steps": 1043, "loss": 0.6377, "lr": 1.554286006542546e-05, "epoch": 5.033500837520938, "percentage": 71.91, "elapsed_time": "0:00:35", "remaining_time": "0:00:13"}
|
| 152 |
+
{"current_steps": 755, "total_steps": 1043, "loss": 0.9747, "lr": 1.5058408052431222e-05, "epoch": 5.067001675041876, "percentage": 72.39, "elapsed_time": "0:01:15", "remaining_time": "0:00:28"}
|
| 153 |
+
{"current_steps": 760, "total_steps": 1043, "loss": 0.8049, "lr": 1.4579548253061636e-05, "epoch": 5.100502512562814, "percentage": 72.87, "elapsed_time": "0:02:01", "remaining_time": "0:00:45"}
|
| 154 |
+
{"current_steps": 765, "total_steps": 1043, "loss": 0.6952, "lr": 1.4106414953802022e-05, "epoch": 5.134003350083752, "percentage": 73.35, "elapsed_time": "0:02:36", "remaining_time": "0:00:56"}
|
| 155 |
+
{"current_steps": 770, "total_steps": 1043, "loss": 0.7622, "lr": 1.3639140835257279e-05, "epoch": 5.16750418760469, "percentage": 73.83, "elapsed_time": "0:03:18", "remaining_time": "0:01:10"}
|
| 156 |
+
{"current_steps": 775, "total_steps": 1043, "loss": 0.7505, "lr": 1.3177856934944328e-05, "epoch": 5.201005025125628, "percentage": 74.3, "elapsed_time": "0:03:53", "remaining_time": "0:01:20"}
|
.ipynb_checkpoints/training_loss-checkpoint.png
ADDED
|
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Zyphra/ZR1-1.5B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Zyphra/ZR1-1.5B](https://huggingface.co/Zyphra/ZR1-1.5B) on the svg dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 7e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 5.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.45.2
|
| 57 |
+
- Pytorch 2.7.0+cu126
|
| 58 |
+
- Datasets 2.21.0
|
| 59 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.991624790619765,
|
| 3 |
+
"total_flos": 1.7623459714564096e+16,
|
| 4 |
+
"train_loss": 0.3653655869448745,
|
| 5 |
+
"train_runtime": 6161.9443,
|
| 6 |
+
"train_samples_per_second": 1.938,
|
| 7 |
+
"train_steps_per_second": 0.121
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.45.2",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.45.2"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be34476618948b5ab0a68bdfdeb0a1b887d2b41a764816d50ed9e993931dbfb6
|
| 3 |
+
size 3554214752
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"padding_side": "right",
|
| 192 |
+
"sp_model_kwargs": {},
|
| 193 |
+
"split_special_tokens": false,
|
| 194 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 195 |
+
"unk_token": null,
|
| 196 |
+
"use_default_system_prompt": false
|
| 197 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.991624790619765,
|
| 3 |
+
"total_flos": 1.7623459714564096e+16,
|
| 4 |
+
"train_loss": 0.3653655869448745,
|
| 5 |
+
"train_runtime": 6161.9443,
|
| 6 |
+
"train_samples_per_second": 1.938,
|
| 7 |
+
"train_steps_per_second": 0.121
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 745, "loss": 2.2902, "lr": 4.666666666666666e-06, "epoch": 0.03350083752093802, "percentage": 0.67, "elapsed_time": "0:00:49", "remaining_time": "2:02:13"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 745, "loss": 1.4714, "lr": 9.333333333333333e-06, "epoch": 0.06700167504187604, "percentage": 1.34, "elapsed_time": "0:01:29", "remaining_time": "1:49:03"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 745, "loss": 0.8749, "lr": 1.4e-05, "epoch": 0.10050251256281408, "percentage": 2.01, "elapsed_time": "0:02:08", "remaining_time": "1:44:36"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 745, "loss": 0.7402, "lr": 1.8666666666666665e-05, "epoch": 0.13400335008375208, "percentage": 2.68, "elapsed_time": "0:02:48", "remaining_time": "1:41:53"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 745, "loss": 0.6662, "lr": 2.333333333333333e-05, "epoch": 0.16750418760469013, "percentage": 3.36, "elapsed_time": "0:03:26", "remaining_time": "1:39:04"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 745, "loss": 0.6202, "lr": 2.8e-05, "epoch": 0.20100502512562815, "percentage": 4.03, "elapsed_time": "0:04:13", "remaining_time": "1:40:45"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 745, "loss": 0.6055, "lr": 3.266666666666666e-05, "epoch": 0.23450586264656617, "percentage": 4.7, "elapsed_time": "0:04:50", "remaining_time": "1:38:03"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 745, "loss": 0.6467, "lr": 3.733333333333333e-05, "epoch": 0.26800670016750416, "percentage": 5.37, "elapsed_time": "0:05:32", "remaining_time": "1:37:35"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 745, "loss": 0.6908, "lr": 4.2e-05, "epoch": 0.3015075376884422, "percentage": 6.04, "elapsed_time": "0:06:10", "remaining_time": "1:36:09"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 745, "loss": 0.6715, "lr": 4.666666666666666e-05, "epoch": 0.33500837520938026, "percentage": 6.71, "elapsed_time": "0:06:54", "remaining_time": "1:36:03"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 745, "loss": 0.6929, "lr": 5.1333333333333325e-05, "epoch": 0.3685092127303183, "percentage": 7.38, "elapsed_time": "0:07:42", "remaining_time": "1:36:39"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 745, "loss": 0.6122, "lr": 5.6e-05, "epoch": 0.4020100502512563, "percentage": 8.05, "elapsed_time": "0:08:23", "remaining_time": "1:35:47"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 745, "loss": 0.5965, "lr": 6.0666666666666666e-05, "epoch": 0.4355108877721943, "percentage": 8.72, "elapsed_time": "0:08:56", "remaining_time": "1:33:30"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 745, "loss": 0.6156, "lr": 6.533333333333333e-05, "epoch": 0.46901172529313234, "percentage": 9.4, "elapsed_time": "0:09:36", "remaining_time": "1:32:41"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 745, "loss": 0.6128, "lr": 7e-05, "epoch": 0.5025125628140703, "percentage": 10.07, "elapsed_time": "0:10:13", "remaining_time": "1:31:22"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 745, "loss": 0.6462, "lr": 6.999038147884355e-05, "epoch": 0.5360134003350083, "percentage": 10.74, "elapsed_time": "0:11:01", "remaining_time": "1:31:39"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 745, "loss": 0.6145, "lr": 6.99615312019999e-05, "epoch": 0.5695142378559463, "percentage": 11.41, "elapsed_time": "0:11:43", "remaining_time": "1:30:59"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 745, "loss": 0.5769, "lr": 6.991346502644035e-05, "epoch": 0.6030150753768844, "percentage": 12.08, "elapsed_time": "0:12:22", "remaining_time": "1:30:05"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 745, "loss": 0.6176, "lr": 6.984620937076643e-05, "epoch": 0.6365159128978225, "percentage": 12.75, "elapsed_time": "0:13:04", "remaining_time": "1:29:28"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 745, "loss": 0.5512, "lr": 6.975980120068939e-05, "epoch": 0.6700167504187605, "percentage": 13.42, "elapsed_time": "0:13:52", "remaining_time": "1:29:29"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 745, "loss": 0.6277, "lr": 6.965428800871278e-05, "epoch": 0.7035175879396985, "percentage": 14.09, "elapsed_time": "0:14:31", "remaining_time": "1:28:33"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 745, "loss": 0.6424, "lr": 6.952972778802912e-05, "epoch": 0.7370184254606366, "percentage": 14.77, "elapsed_time": "0:15:14", "remaining_time": "1:27:58"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 745, "loss": 0.6046, "lr": 6.938618900064515e-05, "epoch": 0.7705192629815746, "percentage": 15.44, "elapsed_time": "0:15:58", "remaining_time": "1:27:32"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 745, "loss": 0.618, "lr": 6.922375053975308e-05, "epoch": 0.8040201005025126, "percentage": 16.11, "elapsed_time": "0:16:35", "remaining_time": "1:26:23"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 745, "loss": 0.6257, "lr": 6.904250168636844e-05, "epoch": 0.8375209380234506, "percentage": 16.78, "elapsed_time": "0:17:19", "remaining_time": "1:25:54"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 745, "loss": 0.5944, "lr": 6.884254206025877e-05, "epoch": 0.8710217755443886, "percentage": 17.45, "elapsed_time": "0:18:04", "remaining_time": "1:25:31"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 745, "loss": 0.5749, "lr": 6.86239815651894e-05, "epoch": 0.9045226130653267, "percentage": 18.12, "elapsed_time": "0:18:38", "remaining_time": "1:24:14"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 745, "loss": 0.5728, "lr": 6.838694032851726e-05, "epoch": 0.9380234505862647, "percentage": 18.79, "elapsed_time": "0:19:19", "remaining_time": "1:23:30"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 745, "loss": 0.6186, "lr": 6.813154863516519e-05, "epoch": 0.9715242881072027, "percentage": 19.46, "elapsed_time": "0:20:09", "remaining_time": "1:23:23"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 745, "loss": 0.5516, "lr": 6.785794685601351e-05, "epoch": 1.0050251256281406, "percentage": 20.13, "elapsed_time": "0:20:47", "remaining_time": "1:22:27"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 745, "loss": 0.4678, "lr": 6.756628537074802e-05, "epoch": 1.0385259631490786, "percentage": 20.81, "elapsed_time": "0:21:35", "remaining_time": "1:22:09"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 745, "loss": 0.508, "lr": 6.725672448520679e-05, "epoch": 1.0720268006700167, "percentage": 21.48, "elapsed_time": "0:22:23", "remaining_time": "1:21:52"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 745, "loss": 0.48, "lr": 6.692943434327137e-05, "epoch": 1.1055276381909547, "percentage": 22.15, "elapsed_time": "0:23:11", "remaining_time": "1:21:31"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 745, "loss": 0.4675, "lr": 6.65845948333506e-05, "epoch": 1.1390284757118927, "percentage": 22.82, "elapsed_time": "0:23:48", "remaining_time": "1:20:31"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 745, "loss": 0.4949, "lr": 6.622239548950852e-05, "epoch": 1.1725293132328307, "percentage": 23.49, "elapsed_time": "0:24:31", "remaining_time": "1:19:52"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 745, "loss": 0.5078, "lr": 6.584303538729098e-05, "epoch": 1.2060301507537687, "percentage": 24.16, "elapsed_time": "0:25:15", "remaining_time": "1:19:16"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 745, "loss": 0.4654, "lr": 6.544672303430766e-05, "epoch": 1.2395309882747068, "percentage": 24.83, "elapsed_time": "0:25:54", "remaining_time": "1:18:26"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 745, "loss": 0.4841, "lr": 6.503367625563004e-05, "epoch": 1.2730318257956448, "percentage": 25.5, "elapsed_time": "0:26:35", "remaining_time": "1:17:40"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 745, "loss": 0.5139, "lr": 6.46041220740684e-05, "epoch": 1.3065326633165828, "percentage": 26.17, "elapsed_time": "0:27:14", "remaining_time": "1:16:50"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 745, "loss": 0.4688, "lr": 6.41582965853932e-05, "epoch": 1.3400335008375208, "percentage": 26.85, "elapsed_time": "0:28:02", "remaining_time": "1:16:23"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 745, "loss": 0.4757, "lr": 6.369644482856986e-05, "epoch": 1.3735343383584588, "percentage": 27.52, "elapsed_time": "0:28:42", "remaining_time": "1:15:36"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 745, "loss": 0.4656, "lr": 6.321882065107803e-05, "epoch": 1.4070351758793969, "percentage": 28.19, "elapsed_time": "0:29:19", "remaining_time": "1:14:42"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 745, "loss": 0.4519, "lr": 6.272568656938952e-05, "epoch": 1.4405360134003349, "percentage": 28.86, "elapsed_time": "0:30:00", "remaining_time": "1:13:58"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 745, "loss": 0.4843, "lr": 6.221731362468132e-05, "epoch": 1.474036850921273, "percentage": 29.53, "elapsed_time": "0:30:42", "remaining_time": "1:13:17"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 745, "loss": 0.4852, "lr": 6.169398123386336e-05, "epoch": 1.507537688442211, "percentage": 30.2, "elapsed_time": "0:31:26", "remaining_time": "1:12:40"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 745, "loss": 0.4833, "lr": 6.115597703600269e-05, "epoch": 1.541038525963149, "percentage": 30.87, "elapsed_time": "0:32:02", "remaining_time": "1:11:44"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 745, "loss": 0.493, "lr": 6.060359673422841e-05, "epoch": 1.574539363484087, "percentage": 31.54, "elapsed_time": "0:32:48", "remaining_time": "1:11:11"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 745, "loss": 0.4667, "lr": 6.003714393320446e-05, "epoch": 1.608040201005025, "percentage": 32.21, "elapsed_time": "0:33:27", "remaining_time": "1:10:23"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 745, "loss": 0.4988, "lr": 5.945692997225945e-05, "epoch": 1.641541038525963, "percentage": 32.89, "elapsed_time": "0:34:06", "remaining_time": "1:09:36"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 745, "loss": 0.4782, "lr": 5.8863273754265325e-05, "epoch": 1.675041876046901, "percentage": 33.56, "elapsed_time": "0:34:43", "remaining_time": "1:08:46"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 745, "loss": 0.4822, "lr": 5.825650157035876e-05, "epoch": 1.708542713567839, "percentage": 34.23, "elapsed_time": "0:35:21", "remaining_time": "1:07:56"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 745, "loss": 0.4345, "lr": 5.763694692060194e-05, "epoch": 1.742043551088777, "percentage": 34.9, "elapsed_time": "0:35:55", "remaining_time": "1:06:59"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 745, "loss": 0.488, "lr": 5.700495033068097e-05, "epoch": 1.775544388609715, "percentage": 35.57, "elapsed_time": "0:36:42", "remaining_time": "1:06:30"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 745, "loss": 0.5029, "lr": 5.636085916474272e-05, "epoch": 1.809045226130653, "percentage": 36.24, "elapsed_time": "0:37:25", "remaining_time": "1:05:50"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 745, "loss": 0.4689, "lr": 5.570502743447328e-05, "epoch": 1.8425460636515911, "percentage": 36.91, "elapsed_time": "0:38:06", "remaining_time": "1:05:07"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 745, "loss": 0.4732, "lr": 5.503781560452251e-05, "epoch": 1.8760469011725294, "percentage": 37.58, "elapsed_time": "0:38:45", "remaining_time": "1:04:22"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 745, "loss": 0.4228, "lr": 5.435959039438197e-05, "epoch": 1.9095477386934674, "percentage": 38.26, "elapsed_time": "0:39:25", "remaining_time": "1:03:37"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 745, "loss": 0.5041, "lr": 5.367072457682496e-05, "epoch": 1.9430485762144054, "percentage": 38.93, "elapsed_time": "0:40:08", "remaining_time": "1:02:58"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 745, "loss": 0.4211, "lr": 5.297159677301946e-05, "epoch": 1.9765494137353434, "percentage": 39.6, "elapsed_time": "0:40:45", "remaining_time": "1:02:10"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 745, "loss": 0.4343, "lr": 5.226259124442675e-05, "epoch": 2.0100502512562812, "percentage": 40.27, "elapsed_time": "0:41:26", "remaining_time": "1:01:28"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 745, "loss": 0.3459, "lr": 5.1544097681599774e-05, "epoch": 2.0435510887772192, "percentage": 40.94, "elapsed_time": "0:42:04", "remaining_time": "1:00:41"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 745, "loss": 0.3323, "lr": 5.081651098999768e-05, "epoch": 2.0770519262981573, "percentage": 41.61, "elapsed_time": "0:42:44", "remaining_time": "0:59:59"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 745, "loss": 0.3071, "lr": 5.008023107293396e-05, "epoch": 2.1105527638190953, "percentage": 42.28, "elapsed_time": "0:43:25", "remaining_time": "0:59:16"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 745, "loss": 0.3019, "lr": 4.9335662611777724e-05, "epoch": 2.1440536013400333, "percentage": 42.95, "elapsed_time": "0:44:07", "remaining_time": "0:58:36"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 745, "loss": 0.3203, "lr": 4.8583214843528736e-05, "epoch": 2.1775544388609713, "percentage": 43.62, "elapsed_time": "0:44:49", "remaining_time": "0:57:55"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 745, "loss": 0.3302, "lr": 4.7823301335888614e-05, "epoch": 2.2110552763819094, "percentage": 44.3, "elapsed_time": "0:45:25", "remaining_time": "0:57:07"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 745, "loss": 0.3386, "lr": 4.7056339759951644e-05, "epoch": 2.2445561139028474, "percentage": 44.97, "elapsed_time": "0:46:06", "remaining_time": "0:56:25"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 745, "loss": 0.3379, "lr": 4.6282751660640375e-05, "epoch": 2.2780569514237854, "percentage": 45.64, "elapsed_time": "0:46:44", "remaining_time": "0:55:40"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 745, "loss": 0.3163, "lr": 4.550296222501192e-05, "epoch": 2.3115577889447234, "percentage": 46.31, "elapsed_time": "0:47:22", "remaining_time": "0:54:55"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 745, "loss": 0.3086, "lr": 4.471740004856251e-05, "epoch": 2.3450586264656614, "percentage": 46.98, "elapsed_time": "0:47:56", "remaining_time": "0:54:06"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 745, "loss": 0.319, "lr": 4.392649689965867e-05, "epoch": 2.3785594639865995, "percentage": 47.65, "elapsed_time": "0:48:34", "remaining_time": "0:53:22"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 745, "loss": 0.3321, "lr": 4.313068748222441e-05, "epoch": 2.4120603015075375, "percentage": 48.32, "elapsed_time": "0:49:18", "remaining_time": "0:52:44"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 745, "loss": 0.3348, "lr": 4.233040919681506e-05, "epoch": 2.4455611390284755, "percentage": 48.99, "elapsed_time": "0:50:03", "remaining_time": "0:52:07"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 745, "loss": 0.3189, "lr": 4.152610190020884e-05, "epoch": 2.4790619765494135, "percentage": 49.66, "elapsed_time": "0:50:43", "remaining_time": "0:51:25"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 745, "loss": 0.332, "lr": 4.071820766364855e-05, "epoch": 2.5125628140703515, "percentage": 50.34, "elapsed_time": "0:51:25", "remaining_time": "0:50:44"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 745, "loss": 0.339, "lr": 3.990717052986601e-05, "epoch": 2.5460636515912896, "percentage": 51.01, "elapsed_time": "0:52:03", "remaining_time": "0:50:00"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 745, "loss": 0.3473, "lr": 3.909343626902289e-05, "epoch": 2.5795644891122276, "percentage": 51.68, "elapsed_time": "0:52:41", "remaining_time": "0:49:16"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 745, "loss": 0.3431, "lr": 3.8277452133702276e-05, "epoch": 2.6130653266331656, "percentage": 52.35, "elapsed_time": "0:53:28", "remaining_time": "0:48:40"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 745, "loss": 0.3689, "lr": 3.745966661308525e-05, "epoch": 2.6465661641541036, "percentage": 53.02, "elapsed_time": "0:54:14", "remaining_time": "0:48:04"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 745, "loss": 0.3166, "lr": 3.66405291864479e-05, "epoch": 2.6800670016750416, "percentage": 53.69, "elapsed_time": "0:55:01", "remaining_time": "0:47:27"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 745, "loss": 0.3638, "lr": 3.5820490076114116e-05, "epoch": 2.7135678391959797, "percentage": 54.36, "elapsed_time": "0:55:45", "remaining_time": "0:46:48"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 745, "loss": 0.3503, "lr": 3.5e-05, "epoch": 2.7470686767169177, "percentage": 55.03, "elapsed_time": "0:56:27", "remaining_time": "0:46:07"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 745, "loss": 0.367, "lr": 3.4179509923885885e-05, "epoch": 2.7805695142378557, "percentage": 55.7, "elapsed_time": "0:57:11", "remaining_time": "0:45:28"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 745, "loss": 0.3212, "lr": 3.335947081355209e-05, "epoch": 2.8140703517587937, "percentage": 56.38, "elapsed_time": "0:57:49", "remaining_time": "0:44:44"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 745, "loss": 0.3311, "lr": 3.254033338691476e-05, "epoch": 2.8475711892797317, "percentage": 57.05, "elapsed_time": "0:58:34", "remaining_time": "0:44:05"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 745, "loss": 0.3207, "lr": 3.1722547866297724e-05, "epoch": 2.8810720268006698, "percentage": 57.72, "elapsed_time": "0:59:18", "remaining_time": "0:43:26"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 745, "loss": 0.3208, "lr": 3.090656373097711e-05, "epoch": 2.914572864321608, "percentage": 58.39, "elapsed_time": "1:00:04", "remaining_time": "0:42:48"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 745, "loss": 0.3018, "lr": 3.0092829470133993e-05, "epoch": 2.948073701842546, "percentage": 59.06, "elapsed_time": "1:00:43", "remaining_time": "0:42:05"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 745, "loss": 0.3235, "lr": 2.9281792336351436e-05, "epoch": 2.981574539363484, "percentage": 59.73, "elapsed_time": "1:01:21", "remaining_time": "0:41:21"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 745, "loss": 0.2668, "lr": 2.8473898099791164e-05, "epoch": 3.0150753768844223, "percentage": 60.4, "elapsed_time": "1:02:00", "remaining_time": "0:40:39"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 745, "loss": 0.2008, "lr": 2.7669590803184948e-05, "epoch": 3.0485762144053603, "percentage": 61.07, "elapsed_time": "1:02:38", "remaining_time": "0:39:55"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 745, "loss": 0.184, "lr": 2.686931251777559e-05, "epoch": 3.0820770519262983, "percentage": 61.74, "elapsed_time": "1:03:16", "remaining_time": "0:39:12"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 745, "loss": 0.2065, "lr": 2.6073503100341324e-05, "epoch": 3.1155778894472363, "percentage": 62.42, "elapsed_time": "1:03:58", "remaining_time": "0:38:31"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 745, "loss": 0.2146, "lr": 2.5282599951437474e-05, "epoch": 3.1490787269681744, "percentage": 63.09, "elapsed_time": "1:04:50", "remaining_time": "0:37:56"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 745, "loss": 0.2227, "lr": 2.449703777498808e-05, "epoch": 3.1825795644891124, "percentage": 63.76, "elapsed_time": "1:05:39", "remaining_time": "0:37:19"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 745, "loss": 0.1902, "lr": 2.371724833935962e-05, "epoch": 3.2160804020100504, "percentage": 64.43, "elapsed_time": "1:06:16", "remaining_time": "0:36:35"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 745, "loss": 0.1713, "lr": 2.2943660240048347e-05, "epoch": 3.2495812395309884, "percentage": 65.1, "elapsed_time": "1:06:54", "remaining_time": "0:35:52"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 745, "loss": 0.2053, "lr": 2.217669866411138e-05, "epoch": 3.2830820770519265, "percentage": 65.77, "elapsed_time": "1:07:38", "remaining_time": "0:35:11"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 745, "loss": 0.2057, "lr": 2.141678515647125e-05, "epoch": 3.3165829145728645, "percentage": 66.44, "elapsed_time": "1:08:17", "remaining_time": "0:34:29"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 745, "loss": 0.1915, "lr": 2.066433738822227e-05, "epoch": 3.3500837520938025, "percentage": 67.11, "elapsed_time": "1:09:01", "remaining_time": "0:33:49"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 745, "loss": 0.1961, "lr": 1.9919768927066035e-05, "epoch": 3.3835845896147405, "percentage": 67.79, "elapsed_time": "1:09:45", "remaining_time": "0:33:09"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 745, "loss": 0.1746, "lr": 1.918348901000232e-05, "epoch": 3.4170854271356785, "percentage": 68.46, "elapsed_time": "1:10:26", "remaining_time": "0:32:27"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 745, "loss": 0.2121, "lr": 1.845590231840021e-05, "epoch": 3.4505862646566166, "percentage": 69.13, "elapsed_time": "1:11:12", "remaining_time": "0:31:48"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 745, "loss": 0.1668, "lr": 1.7737408755573246e-05, "epoch": 3.4840871021775546, "percentage": 69.8, "elapsed_time": "1:11:47", "remaining_time": "0:31:03"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 745, "loss": 0.1703, "lr": 1.7028403226980523e-05, "epoch": 3.5175879396984926, "percentage": 70.47, "elapsed_time": "1:12:25", "remaining_time": "0:30:20"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 745, "loss": 0.1795, "lr": 1.6329275423175046e-05, "epoch": 3.5510887772194306, "percentage": 71.14, "elapsed_time": "1:13:04", "remaining_time": "0:29:38"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 745, "loss": 0.1748, "lr": 1.564040960561802e-05, "epoch": 3.5845896147403686, "percentage": 71.81, "elapsed_time": "1:13:38", "remaining_time": "0:28:54"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 745, "loss": 0.1798, "lr": 1.496218439547749e-05, "epoch": 3.6180904522613067, "percentage": 72.48, "elapsed_time": "1:14:12", "remaining_time": "0:28:10"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 745, "loss": 0.1689, "lr": 1.4294972565526714e-05, "epoch": 3.6515912897822447, "percentage": 73.15, "elapsed_time": "1:14:49", "remaining_time": "0:27:27"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 745, "loss": 0.2217, "lr": 1.3639140835257279e-05, "epoch": 3.6850921273031827, "percentage": 73.83, "elapsed_time": "1:15:35", "remaining_time": "0:26:47"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 745, "loss": 0.1921, "lr": 1.2995049669319036e-05, "epoch": 3.7185929648241207, "percentage": 74.5, "elapsed_time": "1:16:18", "remaining_time": "0:26:07"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 745, "loss": 0.2058, "lr": 1.2363053079398044e-05, "epoch": 3.7520938023450587, "percentage": 75.17, "elapsed_time": "1:17:04", "remaining_time": "0:25:27"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 745, "loss": 0.1807, "lr": 1.1743498429641242e-05, "epoch": 3.7855946398659968, "percentage": 75.84, "elapsed_time": "1:17:45", "remaining_time": "0:24:46"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 745, "loss": 0.1845, "lr": 1.1136726245734674e-05, "epoch": 3.819095477386935, "percentage": 76.51, "elapsed_time": "1:18:28", "remaining_time": "0:24:05"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 745, "loss": 0.1853, "lr": 1.0543070027740541e-05, "epoch": 3.852596314907873, "percentage": 77.18, "elapsed_time": "1:19:07", "remaining_time": "0:23:23"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 745, "loss": 0.1912, "lr": 9.962856066795543e-06, "epoch": 3.886097152428811, "percentage": 77.85, "elapsed_time": "1:19:47", "remaining_time": "0:22:42"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 745, "loss": 0.1815, "lr": 9.396403265771593e-06, "epoch": 3.919597989949749, "percentage": 78.52, "elapsed_time": "1:20:26", "remaining_time": "0:21:59"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 745, "loss": 0.2068, "lr": 8.844022963997302e-06, "epoch": 3.953098827470687, "percentage": 79.19, "elapsed_time": "1:21:13", "remaining_time": "0:21:20"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 745, "loss": 0.1852, "lr": 8.306018766136634e-06, "epoch": 3.986599664991625, "percentage": 79.87, "elapsed_time": "1:21:49", "remaining_time": "0:20:37"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 745, "loss": 0.1656, "lr": 7.782686375318677e-06, "epoch": 4.0201005025125625, "percentage": 80.54, "elapsed_time": "1:22:35", "remaining_time": "0:19:57"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 745, "loss": 0.1076, "lr": 7.2743134306104725e-06, "epoch": 4.0536013400335005, "percentage": 81.21, "elapsed_time": "1:23:16", "remaining_time": "0:19:16"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 745, "loss": 0.141, "lr": 6.781179348921959e-06, "epoch": 4.0871021775544385, "percentage": 81.88, "elapsed_time": "1:24:07", "remaining_time": "0:18:37"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 745, "loss": 0.1196, "lr": 6.303555171430139e-06, "epoch": 4.1206030150753765, "percentage": 82.55, "elapsed_time": "1:24:50", "remaining_time": "0:17:56"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 745, "loss": 0.1039, "lr": 5.8417034146068e-06, "epoch": 4.1541038525963145, "percentage": 83.22, "elapsed_time": "1:25:27", "remaining_time": "0:17:13"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 745, "loss": 0.1461, "lr": 5.3958779259315894e-06, "epoch": 4.187604690117253, "percentage": 83.89, "elapsed_time": "1:26:14", "remaining_time": "0:16:33"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 745, "loss": 0.1088, "lr": 4.966323744369957e-06, "epoch": 4.221105527638191, "percentage": 84.56, "elapsed_time": "1:26:55", "remaining_time": "0:15:52"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 745, "loss": 0.0861, "lr": 4.553276965692342e-06, "epoch": 4.254606365159129, "percentage": 85.23, "elapsed_time": "1:27:31", "remaining_time": "0:15:09"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 745, "loss": 0.113, "lr": 4.15696461270901e-06, "epoch": 4.288107202680067, "percentage": 85.91, "elapsed_time": "1:28:16", "remaining_time": "0:14:28"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 745, "loss": 0.1051, "lr": 3.7776045104914728e-06, "epoch": 4.321608040201005, "percentage": 86.58, "elapsed_time": "1:28:58", "remaining_time": "0:13:47"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 745, "loss": 0.0947, "lr": 3.4154051666494086e-06, "epoch": 4.355108877721943, "percentage": 87.25, "elapsed_time": "1:29:36", "remaining_time": "0:13:05"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 745, "loss": 0.1155, "lr": 3.070565656728618e-06, "epoch": 4.388609715242881, "percentage": 87.92, "elapsed_time": "1:30:22", "remaining_time": "0:12:25"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 745, "loss": 0.0996, "lr": 2.7432755147931913e-06, "epoch": 4.422110552763819, "percentage": 88.59, "elapsed_time": "1:31:05", "remaining_time": "0:11:43"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 745, "loss": 0.09, "lr": 2.4337146292519717e-06, "epoch": 4.455611390284757, "percentage": 89.26, "elapsed_time": "1:31:40", "remaining_time": "0:11:01"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 745, "loss": 0.0998, "lr": 2.1420531439864768e-06, "epoch": 4.489112227805695, "percentage": 89.93, "elapsed_time": "1:32:19", "remaining_time": "0:10:20"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 745, "loss": 0.1131, "lr": 1.868451364834806e-06, "epoch": 4.522613065326633, "percentage": 90.6, "elapsed_time": "1:33:07", "remaining_time": "0:09:39"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 745, "loss": 0.0996, "lr": 1.6130596714827338e-06, "epoch": 4.556113902847571, "percentage": 91.28, "elapsed_time": "1:33:46", "remaining_time": "0:08:57"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 745, "loss": 0.0913, "lr": 1.3760184348105974e-06, "epoch": 4.589614740368509, "percentage": 91.95, "elapsed_time": "1:34:18", "remaining_time": "0:08:15"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 745, "loss": 0.1163, "lr": 1.1574579397412277e-06, "epoch": 4.623115577889447, "percentage": 92.62, "elapsed_time": "1:34:59", "remaining_time": "0:07:34"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 745, "loss": 0.0988, "lr": 9.574983136315444e-07, "epoch": 4.656616415410385, "percentage": 93.29, "elapsed_time": "1:35:36", "remaining_time": "0:06:52"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 745, "loss": 0.137, "lr": 7.762494602469205e-07, "epoch": 4.690117252931323, "percentage": 93.96, "elapsed_time": "1:36:25", "remaining_time": "0:06:11"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 745, "loss": 0.0944, "lr": 6.138109993548362e-07, "epoch": 4.723618090452261, "percentage": 94.63, "elapsed_time": "1:36:59", "remaining_time": "0:05:30"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 745, "loss": 0.1124, "lr": 4.7027221197087516e-07, "epoch": 4.757118927973199, "percentage": 95.3, "elapsed_time": "1:37:43", "remaining_time": "0:04:49"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 745, "loss": 0.1061, "lr": 3.457119912872169e-07, "epoch": 4.790619765494137, "percentage": 95.97, "elapsed_time": "1:38:21", "remaining_time": "0:04:07"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 745, "loss": 0.088, "lr": 2.401987993106058e-07, "epoch": 4.824120603015075, "percentage": 96.64, "elapsed_time": "1:39:01", "remaining_time": "0:03:26"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 745, "loss": 0.1112, "lr": 1.5379062923356667e-07, "epoch": 4.857621440536013, "percentage": 97.32, "elapsed_time": "1:39:42", "remaining_time": "0:02:45"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 745, "loss": 0.1014, "lr": 8.6534973559646e-08, "epoch": 4.891122278056951, "percentage": 97.99, "elapsed_time": "1:40:22", "remaining_time": "0:02:03"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 745, "loss": 0.1203, "lr": 3.846879800010194e-08, "epoch": 4.924623115577889, "percentage": 98.66, "elapsed_time": "1:41:05", "remaining_time": "0:01:22"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 745, "loss": 0.1164, "lr": 9.618521156443681e-09, "epoch": 4.958123953098827, "percentage": 99.33, "elapsed_time": "1:41:48", "remaining_time": "0:00:41"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 745, "loss": 0.1109, "lr": 0.0, "epoch": 4.991624790619765, "percentage": 100.0, "elapsed_time": "1:42:24", "remaining_time": "0:00:00"}
|
| 150 |
+
{"current_steps": 745, "total_steps": 745, "epoch": 4.991624790619765, "percentage": 100.0, "elapsed_time": "1:42:41", "remaining_time": "0:00:00"}
|
| 151 |
+
{"current_steps": 750, "total_steps": 1043, "loss": 0.6377, "lr": 1.554286006542546e-05, "epoch": 5.033500837520938, "percentage": 71.91, "elapsed_time": "0:00:35", "remaining_time": "0:00:13"}
|
| 152 |
+
{"current_steps": 755, "total_steps": 1043, "loss": 0.9747, "lr": 1.5058408052431222e-05, "epoch": 5.067001675041876, "percentage": 72.39, "elapsed_time": "0:01:15", "remaining_time": "0:00:28"}
|
| 153 |
+
{"current_steps": 760, "total_steps": 1043, "loss": 0.8049, "lr": 1.4579548253061636e-05, "epoch": 5.100502512562814, "percentage": 72.87, "elapsed_time": "0:02:01", "remaining_time": "0:00:45"}
|
| 154 |
+
{"current_steps": 765, "total_steps": 1043, "loss": 0.6952, "lr": 1.4106414953802022e-05, "epoch": 5.134003350083752, "percentage": 73.35, "elapsed_time": "0:02:36", "remaining_time": "0:00:56"}
|
| 155 |
+
{"current_steps": 770, "total_steps": 1043, "loss": 0.7622, "lr": 1.3639140835257279e-05, "epoch": 5.16750418760469, "percentage": 73.83, "elapsed_time": "0:03:18", "remaining_time": "0:01:10"}
|
| 156 |
+
{"current_steps": 775, "total_steps": 1043, "loss": 0.7505, "lr": 1.3177856934944328e-05, "epoch": 5.201005025125628, "percentage": 74.3, "elapsed_time": "0:03:53", "remaining_time": "0:01:20"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1085 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.991624790619765,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 745,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03350083752093802,
|
| 13 |
+
"grad_norm": 34.80492705959525,
|
| 14 |
+
"learning_rate": 4.666666666666666e-06,
|
| 15 |
+
"loss": 2.2902,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06700167504187604,
|
| 20 |
+
"grad_norm": 5.166739007826064,
|
| 21 |
+
"learning_rate": 9.333333333333333e-06,
|
| 22 |
+
"loss": 1.4714,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10050251256281408,
|
| 27 |
+
"grad_norm": 1.5785465668605727,
|
| 28 |
+
"learning_rate": 1.4e-05,
|
| 29 |
+
"loss": 0.8749,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13400335008375208,
|
| 34 |
+
"grad_norm": 1.3017705727363509,
|
| 35 |
+
"learning_rate": 1.8666666666666665e-05,
|
| 36 |
+
"loss": 0.7402,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16750418760469013,
|
| 41 |
+
"grad_norm": 1.138970566043088,
|
| 42 |
+
"learning_rate": 2.333333333333333e-05,
|
| 43 |
+
"loss": 0.6662,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20100502512562815,
|
| 48 |
+
"grad_norm": 0.9803236376080032,
|
| 49 |
+
"learning_rate": 2.8e-05,
|
| 50 |
+
"loss": 0.6202,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23450586264656617,
|
| 55 |
+
"grad_norm": 0.9449083039125502,
|
| 56 |
+
"learning_rate": 3.266666666666666e-05,
|
| 57 |
+
"loss": 0.6055,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.26800670016750416,
|
| 62 |
+
"grad_norm": 0.8953629097401007,
|
| 63 |
+
"learning_rate": 3.733333333333333e-05,
|
| 64 |
+
"loss": 0.6467,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3015075376884422,
|
| 69 |
+
"grad_norm": 0.9236842543856943,
|
| 70 |
+
"learning_rate": 4.2e-05,
|
| 71 |
+
"loss": 0.6908,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33500837520938026,
|
| 76 |
+
"grad_norm": 0.9183798107767142,
|
| 77 |
+
"learning_rate": 4.666666666666666e-05,
|
| 78 |
+
"loss": 0.6715,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3685092127303183,
|
| 83 |
+
"grad_norm": 0.7864209322814975,
|
| 84 |
+
"learning_rate": 5.1333333333333325e-05,
|
| 85 |
+
"loss": 0.6929,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4020100502512563,
|
| 90 |
+
"grad_norm": 0.9247238376379071,
|
| 91 |
+
"learning_rate": 5.6e-05,
|
| 92 |
+
"loss": 0.6122,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4355108877721943,
|
| 97 |
+
"grad_norm": 0.8059080906969511,
|
| 98 |
+
"learning_rate": 6.0666666666666666e-05,
|
| 99 |
+
"loss": 0.5965,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.46901172529313234,
|
| 104 |
+
"grad_norm": 0.7752380679588927,
|
| 105 |
+
"learning_rate": 6.533333333333333e-05,
|
| 106 |
+
"loss": 0.6156,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5025125628140703,
|
| 111 |
+
"grad_norm": 0.836562944289899,
|
| 112 |
+
"learning_rate": 7e-05,
|
| 113 |
+
"loss": 0.6128,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5360134003350083,
|
| 118 |
+
"grad_norm": 0.6742631276517493,
|
| 119 |
+
"learning_rate": 6.999038147884355e-05,
|
| 120 |
+
"loss": 0.6462,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5695142378559463,
|
| 125 |
+
"grad_norm": 0.7016185858163685,
|
| 126 |
+
"learning_rate": 6.99615312019999e-05,
|
| 127 |
+
"loss": 0.6145,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6030150753768844,
|
| 132 |
+
"grad_norm": 0.586004493971468,
|
| 133 |
+
"learning_rate": 6.991346502644035e-05,
|
| 134 |
+
"loss": 0.5769,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6365159128978225,
|
| 139 |
+
"grad_norm": 0.7512234937648998,
|
| 140 |
+
"learning_rate": 6.984620937076643e-05,
|
| 141 |
+
"loss": 0.6176,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6700167504187605,
|
| 146 |
+
"grad_norm": 0.7807494669009042,
|
| 147 |
+
"learning_rate": 6.975980120068939e-05,
|
| 148 |
+
"loss": 0.5512,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7035175879396985,
|
| 153 |
+
"grad_norm": 0.7219132421334526,
|
| 154 |
+
"learning_rate": 6.965428800871278e-05,
|
| 155 |
+
"loss": 0.6277,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7370184254606366,
|
| 160 |
+
"grad_norm": 0.685078863769536,
|
| 161 |
+
"learning_rate": 6.952972778802912e-05,
|
| 162 |
+
"loss": 0.6424,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7705192629815746,
|
| 167 |
+
"grad_norm": 0.7067972863218654,
|
| 168 |
+
"learning_rate": 6.938618900064515e-05,
|
| 169 |
+
"loss": 0.6046,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8040201005025126,
|
| 174 |
+
"grad_norm": 0.7730157743669701,
|
| 175 |
+
"learning_rate": 6.922375053975308e-05,
|
| 176 |
+
"loss": 0.618,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8375209380234506,
|
| 181 |
+
"grad_norm": 0.6356848020377898,
|
| 182 |
+
"learning_rate": 6.904250168636844e-05,
|
| 183 |
+
"loss": 0.6257,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8710217755443886,
|
| 188 |
+
"grad_norm": 0.5858577306342904,
|
| 189 |
+
"learning_rate": 6.884254206025877e-05,
|
| 190 |
+
"loss": 0.5944,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9045226130653267,
|
| 195 |
+
"grad_norm": 0.682378985400794,
|
| 196 |
+
"learning_rate": 6.86239815651894e-05,
|
| 197 |
+
"loss": 0.5749,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9380234505862647,
|
| 202 |
+
"grad_norm": 0.6412387913789104,
|
| 203 |
+
"learning_rate": 6.838694032851726e-05,
|
| 204 |
+
"loss": 0.5728,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9715242881072027,
|
| 209 |
+
"grad_norm": 0.6438809607143741,
|
| 210 |
+
"learning_rate": 6.813154863516519e-05,
|
| 211 |
+
"loss": 0.6186,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0050251256281406,
|
| 216 |
+
"grad_norm": 0.5932818990093398,
|
| 217 |
+
"learning_rate": 6.785794685601351e-05,
|
| 218 |
+
"loss": 0.5516,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0385259631490786,
|
| 223 |
+
"grad_norm": 0.5354668533855788,
|
| 224 |
+
"learning_rate": 6.756628537074802e-05,
|
| 225 |
+
"loss": 0.4678,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0720268006700167,
|
| 230 |
+
"grad_norm": 0.6020045809658352,
|
| 231 |
+
"learning_rate": 6.725672448520679e-05,
|
| 232 |
+
"loss": 0.508,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.1055276381909547,
|
| 237 |
+
"grad_norm": 0.5557624061583789,
|
| 238 |
+
"learning_rate": 6.692943434327137e-05,
|
| 239 |
+
"loss": 0.48,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.1390284757118927,
|
| 244 |
+
"grad_norm": 0.6336589932582405,
|
| 245 |
+
"learning_rate": 6.65845948333506e-05,
|
| 246 |
+
"loss": 0.4675,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.1725293132328307,
|
| 251 |
+
"grad_norm": 0.6253236726963862,
|
| 252 |
+
"learning_rate": 6.622239548950852e-05,
|
| 253 |
+
"loss": 0.4949,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.2060301507537687,
|
| 258 |
+
"grad_norm": 0.6769604583507771,
|
| 259 |
+
"learning_rate": 6.584303538729098e-05,
|
| 260 |
+
"loss": 0.5078,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.2395309882747068,
|
| 265 |
+
"grad_norm": 0.6676634293567288,
|
| 266 |
+
"learning_rate": 6.544672303430766e-05,
|
| 267 |
+
"loss": 0.4654,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.2730318257956448,
|
| 272 |
+
"grad_norm": 0.610563567985976,
|
| 273 |
+
"learning_rate": 6.503367625563004e-05,
|
| 274 |
+
"loss": 0.4841,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.3065326633165828,
|
| 279 |
+
"grad_norm": 0.5952739520163685,
|
| 280 |
+
"learning_rate": 6.46041220740684e-05,
|
| 281 |
+
"loss": 0.5139,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.3400335008375208,
|
| 286 |
+
"grad_norm": 0.6025159887498315,
|
| 287 |
+
"learning_rate": 6.41582965853932e-05,
|
| 288 |
+
"loss": 0.4688,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.3735343383584588,
|
| 293 |
+
"grad_norm": 0.6170155658637507,
|
| 294 |
+
"learning_rate": 6.369644482856986e-05,
|
| 295 |
+
"loss": 0.4757,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.4070351758793969,
|
| 300 |
+
"grad_norm": 0.5923141190268442,
|
| 301 |
+
"learning_rate": 6.321882065107803e-05,
|
| 302 |
+
"loss": 0.4656,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.4405360134003349,
|
| 307 |
+
"grad_norm": 0.6413156056735193,
|
| 308 |
+
"learning_rate": 6.272568656938952e-05,
|
| 309 |
+
"loss": 0.4519,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.474036850921273,
|
| 314 |
+
"grad_norm": 0.5901693653221566,
|
| 315 |
+
"learning_rate": 6.221731362468132e-05,
|
| 316 |
+
"loss": 0.4843,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.507537688442211,
|
| 321 |
+
"grad_norm": 0.5757281238838933,
|
| 322 |
+
"learning_rate": 6.169398123386336e-05,
|
| 323 |
+
"loss": 0.4852,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.541038525963149,
|
| 328 |
+
"grad_norm": 0.6061306875552653,
|
| 329 |
+
"learning_rate": 6.115597703600269e-05,
|
| 330 |
+
"loss": 0.4833,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.574539363484087,
|
| 335 |
+
"grad_norm": 0.560733023318414,
|
| 336 |
+
"learning_rate": 6.060359673422841e-05,
|
| 337 |
+
"loss": 0.493,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.608040201005025,
|
| 342 |
+
"grad_norm": 0.5873453423744714,
|
| 343 |
+
"learning_rate": 6.003714393320446e-05,
|
| 344 |
+
"loss": 0.4667,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.641541038525963,
|
| 349 |
+
"grad_norm": 0.48650490973913996,
|
| 350 |
+
"learning_rate": 5.945692997225945e-05,
|
| 351 |
+
"loss": 0.4988,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.675041876046901,
|
| 356 |
+
"grad_norm": 0.6031605899864272,
|
| 357 |
+
"learning_rate": 5.8863273754265325e-05,
|
| 358 |
+
"loss": 0.4782,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.708542713567839,
|
| 363 |
+
"grad_norm": 0.6625359418264612,
|
| 364 |
+
"learning_rate": 5.825650157035876e-05,
|
| 365 |
+
"loss": 0.4822,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.742043551088777,
|
| 370 |
+
"grad_norm": 0.634540799056585,
|
| 371 |
+
"learning_rate": 5.763694692060194e-05,
|
| 372 |
+
"loss": 0.4345,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.775544388609715,
|
| 377 |
+
"grad_norm": 0.5136795866997242,
|
| 378 |
+
"learning_rate": 5.700495033068097e-05,
|
| 379 |
+
"loss": 0.488,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.809045226130653,
|
| 384 |
+
"grad_norm": 1.0558474931218984,
|
| 385 |
+
"learning_rate": 5.636085916474272e-05,
|
| 386 |
+
"loss": 0.5029,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.8425460636515911,
|
| 391 |
+
"grad_norm": 0.6029696403679754,
|
| 392 |
+
"learning_rate": 5.570502743447328e-05,
|
| 393 |
+
"loss": 0.4689,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.8760469011725294,
|
| 398 |
+
"grad_norm": 0.508735151914748,
|
| 399 |
+
"learning_rate": 5.503781560452251e-05,
|
| 400 |
+
"loss": 0.4732,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.9095477386934674,
|
| 405 |
+
"grad_norm": 0.4922081091170513,
|
| 406 |
+
"learning_rate": 5.435959039438197e-05,
|
| 407 |
+
"loss": 0.4228,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.9430485762144054,
|
| 412 |
+
"grad_norm": 0.5692349121238272,
|
| 413 |
+
"learning_rate": 5.367072457682496e-05,
|
| 414 |
+
"loss": 0.5041,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.9765494137353434,
|
| 419 |
+
"grad_norm": 0.5499011241481202,
|
| 420 |
+
"learning_rate": 5.297159677301946e-05,
|
| 421 |
+
"loss": 0.4211,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.0100502512562812,
|
| 426 |
+
"grad_norm": 0.4700172084890638,
|
| 427 |
+
"learning_rate": 5.226259124442675e-05,
|
| 428 |
+
"loss": 0.4343,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.0435510887772192,
|
| 433 |
+
"grad_norm": 0.5923162312303414,
|
| 434 |
+
"learning_rate": 5.1544097681599774e-05,
|
| 435 |
+
"loss": 0.3459,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.0770519262981573,
|
| 440 |
+
"grad_norm": 0.5743684360604622,
|
| 441 |
+
"learning_rate": 5.081651098999768e-05,
|
| 442 |
+
"loss": 0.3323,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.1105527638190953,
|
| 447 |
+
"grad_norm": 0.5107020853019847,
|
| 448 |
+
"learning_rate": 5.008023107293396e-05,
|
| 449 |
+
"loss": 0.3071,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.1440536013400333,
|
| 454 |
+
"grad_norm": 0.5905967863566861,
|
| 455 |
+
"learning_rate": 4.9335662611777724e-05,
|
| 456 |
+
"loss": 0.3019,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.1775544388609713,
|
| 461 |
+
"grad_norm": 0.5453801034033648,
|
| 462 |
+
"learning_rate": 4.8583214843528736e-05,
|
| 463 |
+
"loss": 0.3203,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.2110552763819094,
|
| 468 |
+
"grad_norm": 0.5408639551482948,
|
| 469 |
+
"learning_rate": 4.7823301335888614e-05,
|
| 470 |
+
"loss": 0.3302,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.2445561139028474,
|
| 475 |
+
"grad_norm": 0.6455049625826139,
|
| 476 |
+
"learning_rate": 4.7056339759951644e-05,
|
| 477 |
+
"loss": 0.3386,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.2780569514237854,
|
| 482 |
+
"grad_norm": 0.6356725684457077,
|
| 483 |
+
"learning_rate": 4.6282751660640375e-05,
|
| 484 |
+
"loss": 0.3379,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.3115577889447234,
|
| 489 |
+
"grad_norm": 0.6791610312742078,
|
| 490 |
+
"learning_rate": 4.550296222501192e-05,
|
| 491 |
+
"loss": 0.3163,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.3450586264656614,
|
| 496 |
+
"grad_norm": 0.6048103944990366,
|
| 497 |
+
"learning_rate": 4.471740004856251e-05,
|
| 498 |
+
"loss": 0.3086,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.3785594639865995,
|
| 503 |
+
"grad_norm": 0.5826236844965245,
|
| 504 |
+
"learning_rate": 4.392649689965867e-05,
|
| 505 |
+
"loss": 0.319,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.4120603015075375,
|
| 510 |
+
"grad_norm": 0.5363148860382632,
|
| 511 |
+
"learning_rate": 4.313068748222441e-05,
|
| 512 |
+
"loss": 0.3321,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.4455611390284755,
|
| 517 |
+
"grad_norm": 0.5795578225039034,
|
| 518 |
+
"learning_rate": 4.233040919681506e-05,
|
| 519 |
+
"loss": 0.3348,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.4790619765494135,
|
| 524 |
+
"grad_norm": 0.5425776591836236,
|
| 525 |
+
"learning_rate": 4.152610190020884e-05,
|
| 526 |
+
"loss": 0.3189,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.5125628140703515,
|
| 531 |
+
"grad_norm": 0.49573135271387697,
|
| 532 |
+
"learning_rate": 4.071820766364855e-05,
|
| 533 |
+
"loss": 0.332,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.5460636515912896,
|
| 538 |
+
"grad_norm": 0.6002144021182374,
|
| 539 |
+
"learning_rate": 3.990717052986601e-05,
|
| 540 |
+
"loss": 0.339,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.5795644891122276,
|
| 545 |
+
"grad_norm": 0.5460358347561705,
|
| 546 |
+
"learning_rate": 3.909343626902289e-05,
|
| 547 |
+
"loss": 0.3473,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.6130653266331656,
|
| 552 |
+
"grad_norm": 0.6297236065331678,
|
| 553 |
+
"learning_rate": 3.8277452133702276e-05,
|
| 554 |
+
"loss": 0.3431,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.6465661641541036,
|
| 559 |
+
"grad_norm": 0.5645857704777305,
|
| 560 |
+
"learning_rate": 3.745966661308525e-05,
|
| 561 |
+
"loss": 0.3689,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.6800670016750416,
|
| 566 |
+
"grad_norm": 0.557220947816843,
|
| 567 |
+
"learning_rate": 3.66405291864479e-05,
|
| 568 |
+
"loss": 0.3166,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.7135678391959797,
|
| 573 |
+
"grad_norm": 0.6472130522027957,
|
| 574 |
+
"learning_rate": 3.5820490076114116e-05,
|
| 575 |
+
"loss": 0.3638,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.7470686767169177,
|
| 580 |
+
"grad_norm": 0.5745436996559928,
|
| 581 |
+
"learning_rate": 3.5e-05,
|
| 582 |
+
"loss": 0.3503,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.7805695142378557,
|
| 587 |
+
"grad_norm": 0.5690252846719771,
|
| 588 |
+
"learning_rate": 3.4179509923885885e-05,
|
| 589 |
+
"loss": 0.367,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.8140703517587937,
|
| 594 |
+
"grad_norm": 0.605864059693205,
|
| 595 |
+
"learning_rate": 3.335947081355209e-05,
|
| 596 |
+
"loss": 0.3212,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.8475711892797317,
|
| 601 |
+
"grad_norm": 0.7553823444249659,
|
| 602 |
+
"learning_rate": 3.254033338691476e-05,
|
| 603 |
+
"loss": 0.3311,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.8810720268006698,
|
| 608 |
+
"grad_norm": 0.49908316950166315,
|
| 609 |
+
"learning_rate": 3.1722547866297724e-05,
|
| 610 |
+
"loss": 0.3207,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.914572864321608,
|
| 615 |
+
"grad_norm": 0.57944604992337,
|
| 616 |
+
"learning_rate": 3.090656373097711e-05,
|
| 617 |
+
"loss": 0.3208,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.948073701842546,
|
| 622 |
+
"grad_norm": 0.5704240451777757,
|
| 623 |
+
"learning_rate": 3.0092829470133993e-05,
|
| 624 |
+
"loss": 0.3018,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.981574539363484,
|
| 629 |
+
"grad_norm": 0.6417293058476662,
|
| 630 |
+
"learning_rate": 2.9281792336351436e-05,
|
| 631 |
+
"loss": 0.3235,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.0150753768844223,
|
| 636 |
+
"grad_norm": 0.5108169382866715,
|
| 637 |
+
"learning_rate": 2.8473898099791164e-05,
|
| 638 |
+
"loss": 0.2668,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.0485762144053603,
|
| 643 |
+
"grad_norm": 0.5219067974535717,
|
| 644 |
+
"learning_rate": 2.7669590803184948e-05,
|
| 645 |
+
"loss": 0.2008,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.0820770519262983,
|
| 650 |
+
"grad_norm": 0.711253666063413,
|
| 651 |
+
"learning_rate": 2.686931251777559e-05,
|
| 652 |
+
"loss": 0.184,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.1155778894472363,
|
| 657 |
+
"grad_norm": 0.538965162397822,
|
| 658 |
+
"learning_rate": 2.6073503100341324e-05,
|
| 659 |
+
"loss": 0.2065,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.1490787269681744,
|
| 664 |
+
"grad_norm": 0.567905876332219,
|
| 665 |
+
"learning_rate": 2.5282599951437474e-05,
|
| 666 |
+
"loss": 0.2146,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.1825795644891124,
|
| 671 |
+
"grad_norm": 0.5780027289698754,
|
| 672 |
+
"learning_rate": 2.449703777498808e-05,
|
| 673 |
+
"loss": 0.2227,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.2160804020100504,
|
| 678 |
+
"grad_norm": 0.5457253123626112,
|
| 679 |
+
"learning_rate": 2.371724833935962e-05,
|
| 680 |
+
"loss": 0.1902,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.2495812395309884,
|
| 685 |
+
"grad_norm": 0.5603871012904064,
|
| 686 |
+
"learning_rate": 2.2943660240048347e-05,
|
| 687 |
+
"loss": 0.1713,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.2830820770519265,
|
| 692 |
+
"grad_norm": 0.5372790107076946,
|
| 693 |
+
"learning_rate": 2.217669866411138e-05,
|
| 694 |
+
"loss": 0.2053,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.3165829145728645,
|
| 699 |
+
"grad_norm": 0.5631904884303854,
|
| 700 |
+
"learning_rate": 2.141678515647125e-05,
|
| 701 |
+
"loss": 0.2057,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.3500837520938025,
|
| 706 |
+
"grad_norm": 0.5888366952300346,
|
| 707 |
+
"learning_rate": 2.066433738822227e-05,
|
| 708 |
+
"loss": 0.1915,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.3835845896147405,
|
| 713 |
+
"grad_norm": 0.5843810943110128,
|
| 714 |
+
"learning_rate": 1.9919768927066035e-05,
|
| 715 |
+
"loss": 0.1961,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.4170854271356785,
|
| 720 |
+
"grad_norm": 0.4969351695968504,
|
| 721 |
+
"learning_rate": 1.918348901000232e-05,
|
| 722 |
+
"loss": 0.1746,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.4505862646566166,
|
| 727 |
+
"grad_norm": 0.5944802718765301,
|
| 728 |
+
"learning_rate": 1.845590231840021e-05,
|
| 729 |
+
"loss": 0.2121,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.4840871021775546,
|
| 734 |
+
"grad_norm": 0.5464534791859954,
|
| 735 |
+
"learning_rate": 1.7737408755573246e-05,
|
| 736 |
+
"loss": 0.1668,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 3.5175879396984926,
|
| 741 |
+
"grad_norm": 0.6179461018939855,
|
| 742 |
+
"learning_rate": 1.7028403226980523e-05,
|
| 743 |
+
"loss": 0.1703,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.5510887772194306,
|
| 748 |
+
"grad_norm": 0.5786220911700548,
|
| 749 |
+
"learning_rate": 1.6329275423175046e-05,
|
| 750 |
+
"loss": 0.1795,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.5845896147403686,
|
| 755 |
+
"grad_norm": 0.5296237476248948,
|
| 756 |
+
"learning_rate": 1.564040960561802e-05,
|
| 757 |
+
"loss": 0.1748,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.6180904522613067,
|
| 762 |
+
"grad_norm": 0.6010522801331311,
|
| 763 |
+
"learning_rate": 1.496218439547749e-05,
|
| 764 |
+
"loss": 0.1798,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.6515912897822447,
|
| 769 |
+
"grad_norm": 0.5121930967444979,
|
| 770 |
+
"learning_rate": 1.4294972565526714e-05,
|
| 771 |
+
"loss": 0.1689,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 3.6850921273031827,
|
| 776 |
+
"grad_norm": 0.5388169858543181,
|
| 777 |
+
"learning_rate": 1.3639140835257279e-05,
|
| 778 |
+
"loss": 0.2217,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.7185929648241207,
|
| 783 |
+
"grad_norm": 0.5590769251207034,
|
| 784 |
+
"learning_rate": 1.2995049669319036e-05,
|
| 785 |
+
"loss": 0.1921,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.7520938023450587,
|
| 790 |
+
"grad_norm": 0.5388887860292118,
|
| 791 |
+
"learning_rate": 1.2363053079398044e-05,
|
| 792 |
+
"loss": 0.2058,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.7855946398659968,
|
| 797 |
+
"grad_norm": 0.5382683416376374,
|
| 798 |
+
"learning_rate": 1.1743498429641242e-05,
|
| 799 |
+
"loss": 0.1807,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.819095477386935,
|
| 804 |
+
"grad_norm": 0.5787044255728166,
|
| 805 |
+
"learning_rate": 1.1136726245734674e-05,
|
| 806 |
+
"loss": 0.1845,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.852596314907873,
|
| 811 |
+
"grad_norm": 0.5410043026171784,
|
| 812 |
+
"learning_rate": 1.0543070027740541e-05,
|
| 813 |
+
"loss": 0.1853,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 3.886097152428811,
|
| 818 |
+
"grad_norm": 0.5914102230648232,
|
| 819 |
+
"learning_rate": 9.962856066795543e-06,
|
| 820 |
+
"loss": 0.1912,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 3.919597989949749,
|
| 825 |
+
"grad_norm": 0.5706083963862681,
|
| 826 |
+
"learning_rate": 9.396403265771593e-06,
|
| 827 |
+
"loss": 0.1815,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.953098827470687,
|
| 832 |
+
"grad_norm": 0.5594124582309807,
|
| 833 |
+
"learning_rate": 8.844022963997302e-06,
|
| 834 |
+
"loss": 0.2068,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 3.986599664991625,
|
| 839 |
+
"grad_norm": 0.5768228859947889,
|
| 840 |
+
"learning_rate": 8.306018766136634e-06,
|
| 841 |
+
"loss": 0.1852,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.0201005025125625,
|
| 846 |
+
"grad_norm": 0.3902254725833821,
|
| 847 |
+
"learning_rate": 7.782686375318677e-06,
|
| 848 |
+
"loss": 0.1656,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.0536013400335005,
|
| 853 |
+
"grad_norm": 0.41369592272807765,
|
| 854 |
+
"learning_rate": 7.2743134306104725e-06,
|
| 855 |
+
"loss": 0.1076,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.0871021775544385,
|
| 860 |
+
"grad_norm": 0.4560022947735015,
|
| 861 |
+
"learning_rate": 6.781179348921959e-06,
|
| 862 |
+
"loss": 0.141,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.1206030150753765,
|
| 867 |
+
"grad_norm": 0.48760650704072855,
|
| 868 |
+
"learning_rate": 6.303555171430139e-06,
|
| 869 |
+
"loss": 0.1196,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.1541038525963145,
|
| 874 |
+
"grad_norm": 0.5471898279104627,
|
| 875 |
+
"learning_rate": 5.8417034146068e-06,
|
| 876 |
+
"loss": 0.1039,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 4.187604690117253,
|
| 881 |
+
"grad_norm": 0.5423741826689038,
|
| 882 |
+
"learning_rate": 5.3958779259315894e-06,
|
| 883 |
+
"loss": 0.1461,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.221105527638191,
|
| 888 |
+
"grad_norm": 0.43964572959248005,
|
| 889 |
+
"learning_rate": 4.966323744369957e-06,
|
| 890 |
+
"loss": 0.1088,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 4.254606365159129,
|
| 895 |
+
"grad_norm": 0.49143575899849606,
|
| 896 |
+
"learning_rate": 4.553276965692342e-06,
|
| 897 |
+
"loss": 0.0861,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.288107202680067,
|
| 902 |
+
"grad_norm": 0.4688041566562614,
|
| 903 |
+
"learning_rate": 4.15696461270901e-06,
|
| 904 |
+
"loss": 0.113,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.321608040201005,
|
| 909 |
+
"grad_norm": 0.4823371709827415,
|
| 910 |
+
"learning_rate": 3.7776045104914728e-06,
|
| 911 |
+
"loss": 0.1051,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 4.355108877721943,
|
| 916 |
+
"grad_norm": 0.4401168066047478,
|
| 917 |
+
"learning_rate": 3.4154051666494086e-06,
|
| 918 |
+
"loss": 0.0947,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 4.388609715242881,
|
| 923 |
+
"grad_norm": 0.5155747285843881,
|
| 924 |
+
"learning_rate": 3.070565656728618e-06,
|
| 925 |
+
"loss": 0.1155,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.422110552763819,
|
| 930 |
+
"grad_norm": 0.46337786766594463,
|
| 931 |
+
"learning_rate": 2.7432755147931913e-06,
|
| 932 |
+
"loss": 0.0996,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 4.455611390284757,
|
| 937 |
+
"grad_norm": 0.47230762831912765,
|
| 938 |
+
"learning_rate": 2.4337146292519717e-06,
|
| 939 |
+
"loss": 0.09,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 4.489112227805695,
|
| 944 |
+
"grad_norm": 0.5036731266630834,
|
| 945 |
+
"learning_rate": 2.1420531439864768e-06,
|
| 946 |
+
"loss": 0.0998,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.522613065326633,
|
| 951 |
+
"grad_norm": 0.45421524222792464,
|
| 952 |
+
"learning_rate": 1.868451364834806e-06,
|
| 953 |
+
"loss": 0.1131,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.556113902847571,
|
| 958 |
+
"grad_norm": 0.46661240509380125,
|
| 959 |
+
"learning_rate": 1.6130596714827338e-06,
|
| 960 |
+
"loss": 0.0996,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 4.589614740368509,
|
| 965 |
+
"grad_norm": 0.674781968177737,
|
| 966 |
+
"learning_rate": 1.3760184348105974e-06,
|
| 967 |
+
"loss": 0.0913,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.623115577889447,
|
| 972 |
+
"grad_norm": 0.5301911498015647,
|
| 973 |
+
"learning_rate": 1.1574579397412277e-06,
|
| 974 |
+
"loss": 0.1163,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 4.656616415410385,
|
| 979 |
+
"grad_norm": 0.4612822009249947,
|
| 980 |
+
"learning_rate": 9.574983136315444e-07,
|
| 981 |
+
"loss": 0.0988,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 4.690117252931323,
|
| 986 |
+
"grad_norm": 0.45438592797164,
|
| 987 |
+
"learning_rate": 7.762494602469205e-07,
|
| 988 |
+
"loss": 0.137,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 4.723618090452261,
|
| 993 |
+
"grad_norm": 0.44432567702142994,
|
| 994 |
+
"learning_rate": 6.138109993548362e-07,
|
| 995 |
+
"loss": 0.0944,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.757118927973199,
|
| 1000 |
+
"grad_norm": 0.47142059755521903,
|
| 1001 |
+
"learning_rate": 4.7027221197087516e-07,
|
| 1002 |
+
"loss": 0.1124,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 4.790619765494137,
|
| 1007 |
+
"grad_norm": 0.46965730517790255,
|
| 1008 |
+
"learning_rate": 3.457119912872169e-07,
|
| 1009 |
+
"loss": 0.1061,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 4.824120603015075,
|
| 1014 |
+
"grad_norm": 0.4745040542942461,
|
| 1015 |
+
"learning_rate": 2.401987993106058e-07,
|
| 1016 |
+
"loss": 0.088,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.857621440536013,
|
| 1021 |
+
"grad_norm": 0.38238464661360244,
|
| 1022 |
+
"learning_rate": 1.5379062923356667e-07,
|
| 1023 |
+
"loss": 0.1112,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 4.891122278056951,
|
| 1028 |
+
"grad_norm": 0.47237914614668175,
|
| 1029 |
+
"learning_rate": 8.6534973559646e-08,
|
| 1030 |
+
"loss": 0.1014,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 4.924623115577889,
|
| 1035 |
+
"grad_norm": 0.43186793603609225,
|
| 1036 |
+
"learning_rate": 3.846879800010194e-08,
|
| 1037 |
+
"loss": 0.1203,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 4.958123953098827,
|
| 1042 |
+
"grad_norm": 0.45563313559521235,
|
| 1043 |
+
"learning_rate": 9.618521156443681e-09,
|
| 1044 |
+
"loss": 0.1164,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 4.991624790619765,
|
| 1049 |
+
"grad_norm": 0.5086839154828875,
|
| 1050 |
+
"learning_rate": 0.0,
|
| 1051 |
+
"loss": 0.1109,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 4.991624790619765,
|
| 1056 |
+
"step": 745,
|
| 1057 |
+
"total_flos": 1.7623459714564096e+16,
|
| 1058 |
+
"train_loss": 0.3653655869448745,
|
| 1059 |
+
"train_runtime": 6161.9443,
|
| 1060 |
+
"train_samples_per_second": 1.938,
|
| 1061 |
+
"train_steps_per_second": 0.121
|
| 1062 |
+
}
|
| 1063 |
+
],
|
| 1064 |
+
"logging_steps": 5,
|
| 1065 |
+
"max_steps": 745,
|
| 1066 |
+
"num_input_tokens_seen": 0,
|
| 1067 |
+
"num_train_epochs": 5,
|
| 1068 |
+
"save_steps": 1000,
|
| 1069 |
+
"stateful_callbacks": {
|
| 1070 |
+
"TrainerControl": {
|
| 1071 |
+
"args": {
|
| 1072 |
+
"should_epoch_stop": false,
|
| 1073 |
+
"should_evaluate": false,
|
| 1074 |
+
"should_log": false,
|
| 1075 |
+
"should_save": true,
|
| 1076 |
+
"should_training_stop": true
|
| 1077 |
+
},
|
| 1078 |
+
"attributes": {}
|
| 1079 |
+
}
|
| 1080 |
+
},
|
| 1081 |
+
"total_flos": 1.7623459714564096e+16,
|
| 1082 |
+
"train_batch_size": 2,
|
| 1083 |
+
"trial_name": null,
|
| 1084 |
+
"trial_params": null
|
| 1085 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3166d6edc93d8f50696e54c59b9835aa2feb43e78005c9cb34b1ac17fbbb0f2a
|
| 3 |
+
size 7761
|
training_loss.png
ADDED
|