Upload folder using huggingface_hub
Browse files- lr3e-3_total_batch_size20480_seq_len128/args.json +1 -0
- lr3e-3_total_batch_size20480_seq_len128/dataloader_00999.pt +3 -0
- lr3e-3_total_batch_size20480_seq_len128/log2.txt +1043 -0
- lr3e-3_total_batch_size20480_seq_len128/model_00999.pt +3 -0
- lr3e-3_total_batch_size20480_seq_len128/optimizer_00999.pt +3 -0
lr3e-3_total_batch_size20480_seq_len128/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr3e-3_total_batch_size20480_seq_len128", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 2, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": null, "group": "proxy_model_sweep_2", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1337, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "none", "selection_head_linear_combo_scale": 1.0, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 128, "batch_size": null, "total_batch_size": 20480, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": null, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": true, "mup_enable_coord_check_logging": false, "max_lr": 0.003, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128}
|
lr3e-3_total_batch_size20480_seq_len128/dataloader_00999.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8513131d2bf732f8f6d97ff82d32c505b2a2f3f9f2247bac315bb09ce0e1f97
|
| 3 |
+
size 964
|
lr3e-3_total_batch_size20480_seq_len128/log2.txt
ADDED
|
@@ -0,0 +1,1043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_steps: 1000
|
| 2 |
+
0 val loss 11.6870
|
| 3 |
+
0 val perplexity 119016.5000
|
| 4 |
+
0 train 11.700421 (lr=1.0490e-05) (hash(x)=5113283)
|
| 5 |
+
1 train 11.648456 (lr=2.0979e-05) (hash(x)=5534142)
|
| 6 |
+
2 train 11.602330 (lr=3.1469e-05) (hash(x)=6763231)
|
| 7 |
+
3 train 11.491509 (lr=4.1958e-05) (hash(x)=6328012)
|
| 8 |
+
4 train 11.341316 (lr=5.2448e-05) (hash(x)=7052161)
|
| 9 |
+
5 train 11.175173 (lr=6.2937e-05) (hash(x)=5556098)
|
| 10 |
+
6 train 11.032974 (lr=7.3427e-05) (hash(x)=4696943)
|
| 11 |
+
7 train 10.814923 (lr=8.3916e-05) (hash(x)=6219138)
|
| 12 |
+
8 train 10.684901 (lr=9.4406e-05) (hash(x)=6049878)
|
| 13 |
+
9 train 10.583606 (lr=1.0490e-04) (hash(x)=5491972)
|
| 14 |
+
10 train 10.493355 (lr=1.1538e-04) (hash(x)=8075458)
|
| 15 |
+
11 train 10.414818 (lr=1.2587e-04) (hash(x)=5917741)
|
| 16 |
+
12 train 10.358828 (lr=1.3636e-04) (hash(x)=5750403)
|
| 17 |
+
13 train 10.337406 (lr=1.4685e-04) (hash(x)=6112458)
|
| 18 |
+
14 train 10.285822 (lr=1.5734e-04) (hash(x)=5806490)
|
| 19 |
+
15 train 10.207575 (lr=1.6783e-04) (hash(x)=6568379)
|
| 20 |
+
16 train 10.129399 (lr=1.7832e-04) (hash(x)=7212403)
|
| 21 |
+
17 train 10.103264 (lr=1.8881e-04) (hash(x)=7386082)
|
| 22 |
+
18 train 10.044456 (lr=1.9930e-04) (hash(x)=6359743)
|
| 23 |
+
19 train 9.966672 (lr=2.0979e-04) (hash(x)=6151674)
|
| 24 |
+
20 train 9.941641 (lr=2.2028e-04) (hash(x)=7168704)
|
| 25 |
+
21 train 9.868073 (lr=2.3077e-04) (hash(x)=7859060)
|
| 26 |
+
22 train 9.735929 (lr=2.4126e-04) (hash(x)=6976239)
|
| 27 |
+
23 train 9.671158 (lr=2.5175e-04) (hash(x)=6391506)
|
| 28 |
+
24 train 9.610453 (lr=2.6224e-04) (hash(x)=5245999)
|
| 29 |
+
25 train 9.476439 (lr=2.7273e-04) (hash(x)=5985675)
|
| 30 |
+
26 train 9.301088 (lr=2.8322e-04) (hash(x)=4355733)
|
| 31 |
+
27 train 9.446084 (lr=2.9371e-04) (hash(x)=6984772)
|
| 32 |
+
28 train 9.152047 (lr=3.0420e-04) (hash(x)=6244096)
|
| 33 |
+
29 train 9.096377 (lr=3.1469e-04) (hash(x)=6603717)
|
| 34 |
+
30 train 8.818591 (lr=3.2517e-04) (hash(x)=5669522)
|
| 35 |
+
31 train 8.722396 (lr=3.3566e-04) (hash(x)=6190579)
|
| 36 |
+
32 train 8.726132 (lr=3.4615e-04) (hash(x)=4912983)
|
| 37 |
+
33 train 8.496450 (lr=3.5664e-04) (hash(x)=7276303)
|
| 38 |
+
34 train 8.489619 (lr=3.6713e-04) (hash(x)=5479947)
|
| 39 |
+
35 train 8.599414 (lr=3.7762e-04) (hash(x)=6630378)
|
| 40 |
+
36 train 8.411640 (lr=3.8811e-04) (hash(x)=8097010)
|
| 41 |
+
37 train 8.563215 (lr=3.9860e-04) (hash(x)=9989744)
|
| 42 |
+
38 train 8.356658 (lr=4.0909e-04) (hash(x)=6694932)
|
| 43 |
+
39 train 8.169016 (lr=4.1958e-04) (hash(x)=6317894)
|
| 44 |
+
40 train 7.956865 (lr=4.3007e-04) (hash(x)=5046327)
|
| 45 |
+
41 train 8.047102 (lr=4.4056e-04) (hash(x)=7947703)
|
| 46 |
+
42 train 7.794744 (lr=4.5105e-04) (hash(x)=5916068)
|
| 47 |
+
43 train 7.911313 (lr=4.6154e-04) (hash(x)=5777498)
|
| 48 |
+
44 train 7.929577 (lr=4.7203e-04) (hash(x)=5753092)
|
| 49 |
+
45 train 7.780885 (lr=4.8252e-04) (hash(x)=7723226)
|
| 50 |
+
46 train 7.912669 (lr=4.9301e-04) (hash(x)=7007016)
|
| 51 |
+
47 train 7.663750 (lr=5.0350e-04) (hash(x)=6491229)
|
| 52 |
+
48 train 7.892894 (lr=5.1399e-04) (hash(x)=6390752)
|
| 53 |
+
49 train 8.178432 (lr=5.2448e-04) (hash(x)=6019389)
|
| 54 |
+
50 val loss 7.8372
|
| 55 |
+
50 val perplexity 2533.0796
|
| 56 |
+
50 train 7.923337 (lr=5.3497e-04) (hash(x)=7662067)
|
| 57 |
+
51 train 7.874187 (lr=5.4545e-04) (hash(x)=4648609)
|
| 58 |
+
52 train 7.782726 (lr=5.5594e-04) (hash(x)=4725966)
|
| 59 |
+
53 train 7.740320 (lr=5.6643e-04) (hash(x)=5558355)
|
| 60 |
+
54 train 7.881777 (lr=5.7692e-04) (hash(x)=6524933)
|
| 61 |
+
55 train 7.796289 (lr=5.8741e-04) (hash(x)=6369326)
|
| 62 |
+
56 train 7.866249 (lr=5.9790e-04) (hash(x)=6022625)
|
| 63 |
+
57 train 7.750662 (lr=6.0839e-04) (hash(x)=4906853)
|
| 64 |
+
58 train 7.529279 (lr=6.1888e-04) (hash(x)=5589269)
|
| 65 |
+
59 train 7.745609 (lr=6.2937e-04) (hash(x)=6437376)
|
| 66 |
+
60 train 7.999413 (lr=6.3986e-04) (hash(x)=7304892)
|
| 67 |
+
61 train 7.953251 (lr=6.5035e-04) (hash(x)=7084093)
|
| 68 |
+
62 train 7.933053 (lr=6.6084e-04) (hash(x)=5908178)
|
| 69 |
+
63 train 7.794608 (lr=6.7133e-04) (hash(x)=7048804)
|
| 70 |
+
64 train 7.846518 (lr=6.8182e-04) (hash(x)=6085549)
|
| 71 |
+
65 train 7.951125 (lr=6.9231e-04) (hash(x)=5752594)
|
| 72 |
+
66 train 7.743689 (lr=7.0280e-04) (hash(x)=7662769)
|
| 73 |
+
67 train 7.689874 (lr=7.1329e-04) (hash(x)=6393520)
|
| 74 |
+
68 train 7.911360 (lr=7.2378e-04) (hash(x)=5942867)
|
| 75 |
+
69 train 9.864039 (lr=7.3427e-04) (hash(x)=6793550)
|
| 76 |
+
70 train 10.147027 (lr=7.4476e-04) (hash(x)=7105976)
|
| 77 |
+
71 train 7.971744 (lr=7.5524e-04) (hash(x)=6581348)
|
| 78 |
+
72 train 7.811897 (lr=7.6573e-04) (hash(x)=5555598)
|
| 79 |
+
73 train 7.870414 (lr=7.7622e-04) (hash(x)=6235837)
|
| 80 |
+
74 train 7.773763 (lr=7.8671e-04) (hash(x)=5591770)
|
| 81 |
+
75 train 8.146915 (lr=7.9720e-04) (hash(x)=7083021)
|
| 82 |
+
76 train 7.906426 (lr=8.0769e-04) (hash(x)=7281348)
|
| 83 |
+
77 train 8.095078 (lr=8.1818e-04) (hash(x)=6155821)
|
| 84 |
+
78 train 7.841678 (lr=8.2867e-04) (hash(x)=5736241)
|
| 85 |
+
79 train 7.795271 (lr=8.3916e-04) (hash(x)=5657123)
|
| 86 |
+
80 train 7.932291 (lr=8.4965e-04) (hash(x)=6452095)
|
| 87 |
+
81 train 7.729075 (lr=8.6014e-04) (hash(x)=5312267)
|
| 88 |
+
82 train 7.459696 (lr=8.7063e-04) (hash(x)=5434493)
|
| 89 |
+
83 train 7.851946 (lr=8.8112e-04) (hash(x)=6830813)
|
| 90 |
+
84 train 7.559114 (lr=8.9161e-04) (hash(x)=4752771)
|
| 91 |
+
85 train 7.804661 (lr=9.0210e-04) (hash(x)=6424933)
|
| 92 |
+
86 train 7.766463 (lr=9.1259e-04) (hash(x)=5786517)
|
| 93 |
+
87 train 7.905903 (lr=9.2308e-04) (hash(x)=6680023)
|
| 94 |
+
88 train 7.821273 (lr=9.3357e-04) (hash(x)=6474729)
|
| 95 |
+
89 train 7.790932 (lr=9.4406e-04) (hash(x)=7523279)
|
| 96 |
+
90 train 7.628687 (lr=9.5455e-04) (hash(x)=5508768)
|
| 97 |
+
91 train 7.938216 (lr=9.6503e-04) (hash(x)=6635925)
|
| 98 |
+
92 train 7.743244 (lr=9.7552e-04) (hash(x)=6663801)
|
| 99 |
+
93 train 7.712664 (lr=9.8601e-04) (hash(x)=5869441)
|
| 100 |
+
94 train 7.847742 (lr=9.9650e-04) (hash(x)=6698878)
|
| 101 |
+
95 train 7.709070 (lr=1.0070e-03) (hash(x)=6349004)
|
| 102 |
+
96 train 7.750356 (lr=1.0175e-03) (hash(x)=4986137)
|
| 103 |
+
97 train 7.539471 (lr=1.0280e-03) (hash(x)=6008454)
|
| 104 |
+
98 train 7.622161 (lr=1.0385e-03) (hash(x)=6550770)
|
| 105 |
+
99 train 7.807179 (lr=1.0490e-03) (hash(x)=7682741)
|
| 106 |
+
100 val loss 7.7642
|
| 107 |
+
100 val perplexity 2354.7844
|
| 108 |
+
100 train 7.861078 (lr=1.0594e-03) (hash(x)=7892158)
|
| 109 |
+
101 train 7.728724 (lr=1.0699e-03) (hash(x)=7794028)
|
| 110 |
+
102 train 7.733254 (lr=1.0804e-03) (hash(x)=7093523)
|
| 111 |
+
103 train 7.825886 (lr=1.0909e-03) (hash(x)=6166062)
|
| 112 |
+
104 train 7.791701 (lr=1.1014e-03) (hash(x)=6645781)
|
| 113 |
+
105 train 7.720055 (lr=1.1119e-03) (hash(x)=4811192)
|
| 114 |
+
106 train 7.675869 (lr=1.1224e-03) (hash(x)=5970866)
|
| 115 |
+
107 train 7.692483 (lr=1.1329e-03) (hash(x)=7822680)
|
| 116 |
+
108 train 7.660205 (lr=1.1434e-03) (hash(x)=6317317)
|
| 117 |
+
109 train 7.796702 (lr=1.1538e-03) (hash(x)=6431409)
|
| 118 |
+
110 train 7.781823 (lr=1.1643e-03) (hash(x)=6653337)
|
| 119 |
+
111 train 7.730199 (lr=1.1748e-03) (hash(x)=5323032)
|
| 120 |
+
112 train 7.600882 (lr=1.1853e-03) (hash(x)=5125339)
|
| 121 |
+
113 train 7.527102 (lr=1.1958e-03) (hash(x)=7363286)
|
| 122 |
+
114 train 7.979993 (lr=1.2063e-03) (hash(x)=7670050)
|
| 123 |
+
115 train 7.721940 (lr=1.2168e-03) (hash(x)=5616075)
|
| 124 |
+
116 train 7.773359 (lr=1.2273e-03) (hash(x)=6593764)
|
| 125 |
+
117 train 7.811423 (lr=1.2378e-03) (hash(x)=5672608)
|
| 126 |
+
118 train 7.650008 (lr=1.2483e-03) (hash(x)=6828653)
|
| 127 |
+
119 train 7.630859 (lr=1.2587e-03) (hash(x)=6839867)
|
| 128 |
+
120 train 7.819833 (lr=1.2692e-03) (hash(x)=8426992)
|
| 129 |
+
121 train 7.488562 (lr=1.2797e-03) (hash(x)=4916928)
|
| 130 |
+
122 train 7.673828 (lr=1.2902e-03) (hash(x)=6484050)
|
| 131 |
+
123 train 7.781674 (lr=1.3007e-03) (hash(x)=8353379)
|
| 132 |
+
124 train 7.722819 (lr=1.3112e-03) (hash(x)=6552510)
|
| 133 |
+
125 train 7.699184 (lr=1.3217e-03) (hash(x)=4838871)
|
| 134 |
+
126 train 7.466110 (lr=1.3322e-03) (hash(x)=3021697)
|
| 135 |
+
127 train 7.618384 (lr=1.3427e-03) (hash(x)=6795665)
|
| 136 |
+
128 train 7.642485 (lr=1.3531e-03) (hash(x)=5486935)
|
| 137 |
+
129 train 7.827383 (lr=1.3636e-03) (hash(x)=6678038)
|
| 138 |
+
130 train 7.860967 (lr=1.3741e-03) (hash(x)=6657714)
|
| 139 |
+
131 train 7.704404 (lr=1.3846e-03) (hash(x)=6112215)
|
| 140 |
+
132 train 7.764118 (lr=1.3951e-03) (hash(x)=8353143)
|
| 141 |
+
133 train 7.768530 (lr=1.4056e-03) (hash(x)=5915361)
|
| 142 |
+
134 train 7.698390 (lr=1.4161e-03) (hash(x)=6254885)
|
| 143 |
+
135 train 7.704067 (lr=1.4266e-03) (hash(x)=5771588)
|
| 144 |
+
136 train 7.662247 (lr=1.4371e-03) (hash(x)=5561507)
|
| 145 |
+
137 train 7.601452 (lr=1.4476e-03) (hash(x)=5688829)
|
| 146 |
+
138 train 7.594398 (lr=1.4580e-03) (hash(x)=5371951)
|
| 147 |
+
139 train 7.745932 (lr=1.4685e-03) (hash(x)=5443305)
|
| 148 |
+
140 train 7.731729 (lr=1.4790e-03) (hash(x)=5016757)
|
| 149 |
+
141 train 7.729746 (lr=1.4895e-03) (hash(x)=6901933)
|
| 150 |
+
142 train 7.701281 (lr=1.5000e-03) (hash(x)=6019085)
|
| 151 |
+
143 train 7.548456 (lr=1.5105e-03) (hash(x)=4294425)
|
| 152 |
+
144 train 7.677052 (lr=1.5210e-03) (hash(x)=6095229)
|
| 153 |
+
145 train 7.477534 (lr=1.5315e-03) (hash(x)=4363941)
|
| 154 |
+
146 train 7.580789 (lr=1.5420e-03) (hash(x)=4693798)
|
| 155 |
+
147 train 8.169653 (lr=1.5524e-03) (hash(x)=5486335)
|
| 156 |
+
148 train 7.896008 (lr=1.5629e-03) (hash(x)=7907450)
|
| 157 |
+
149 train 7.772290 (lr=1.5734e-03) (hash(x)=7295165)
|
| 158 |
+
150 val loss 7.6660
|
| 159 |
+
150 val perplexity 2134.4456
|
| 160 |
+
150 train 7.715491 (lr=1.5839e-03) (hash(x)=6814026)
|
| 161 |
+
151 train 7.763258 (lr=1.5944e-03) (hash(x)=6267424)
|
| 162 |
+
152 train 7.830932 (lr=1.6049e-03) (hash(x)=8086437)
|
| 163 |
+
153 train 7.823525 (lr=1.6154e-03) (hash(x)=5270452)
|
| 164 |
+
154 train 7.678262 (lr=1.6259e-03) (hash(x)=6420820)
|
| 165 |
+
155 train 7.582094 (lr=1.6364e-03) (hash(x)=6305297)
|
| 166 |
+
156 train 7.737405 (lr=1.6469e-03) (hash(x)=7889849)
|
| 167 |
+
157 train 8.125040 (lr=1.6573e-03) (hash(x)=6040077)
|
| 168 |
+
158 train 8.112333 (lr=1.6678e-03) (hash(x)=5652497)
|
| 169 |
+
159 train 7.713661 (lr=1.6783e-03) (hash(x)=7130251)
|
| 170 |
+
160 train 7.557770 (lr=1.6888e-03) (hash(x)=6610177)
|
| 171 |
+
161 train 7.581771 (lr=1.6993e-03) (hash(x)=6508350)
|
| 172 |
+
162 train 7.757425 (lr=1.7098e-03) (hash(x)=6994983)
|
| 173 |
+
163 train 7.710099 (lr=1.7203e-03) (hash(x)=5859576)
|
| 174 |
+
164 train 7.245765 (lr=1.7308e-03) (hash(x)=5487065)
|
| 175 |
+
165 train 7.513906 (lr=1.7413e-03) (hash(x)=4892065)
|
| 176 |
+
166 train 7.420795 (lr=1.7517e-03) (hash(x)=4933674)
|
| 177 |
+
167 train 7.709130 (lr=1.7622e-03) (hash(x)=7317289)
|
| 178 |
+
168 train 7.824700 (lr=1.7727e-03) (hash(x)=6811522)
|
| 179 |
+
169 train 7.671185 (lr=1.7832e-03) (hash(x)=5510218)
|
| 180 |
+
170 train 7.831715 (lr=1.7937e-03) (hash(x)=7304235)
|
| 181 |
+
171 train 7.971092 (lr=1.8042e-03) (hash(x)=6752265)
|
| 182 |
+
172 train 7.655431 (lr=1.8147e-03) (hash(x)=5994476)
|
| 183 |
+
173 train 7.588530 (lr=1.8252e-03) (hash(x)=6530867)
|
| 184 |
+
174 train 7.720550 (lr=1.8357e-03) (hash(x)=5746260)
|
| 185 |
+
175 train 7.652929 (lr=1.8462e-03) (hash(x)=5790078)
|
| 186 |
+
176 train 7.671865 (lr=1.8566e-03) (hash(x)=6430135)
|
| 187 |
+
177 train 7.730179 (lr=1.8671e-03) (hash(x)=7614023)
|
| 188 |
+
178 train 7.726293 (lr=1.8776e-03) (hash(x)=5244861)
|
| 189 |
+
179 train 7.705664 (lr=1.8881e-03) (hash(x)=5245146)
|
| 190 |
+
180 train 7.596778 (lr=1.8986e-03) (hash(x)=6415565)
|
| 191 |
+
181 train 7.667508 (lr=1.9091e-03) (hash(x)=5786972)
|
| 192 |
+
182 train 7.687834 (lr=1.9196e-03) (hash(x)=6131703)
|
| 193 |
+
183 train 7.716973 (lr=1.9301e-03) (hash(x)=6346459)
|
| 194 |
+
184 train 7.761470 (lr=1.9406e-03) (hash(x)=6504131)
|
| 195 |
+
185 train 7.744598 (lr=1.9510e-03) (hash(x)=5209234)
|
| 196 |
+
186 train 7.709203 (lr=1.9615e-03) (hash(x)=6163272)
|
| 197 |
+
187 train 7.701839 (lr=1.9720e-03) (hash(x)=5676768)
|
| 198 |
+
188 train 7.766649 (lr=1.9825e-03) (hash(x)=6090561)
|
| 199 |
+
189 train 7.919727 (lr=1.9930e-03) (hash(x)=5863092)
|
| 200 |
+
190 train 7.815581 (lr=2.0035e-03) (hash(x)=7201312)
|
| 201 |
+
191 train 7.872892 (lr=2.0140e-03) (hash(x)=7019489)
|
| 202 |
+
192 train 7.670346 (lr=2.0245e-03) (hash(x)=6225608)
|
| 203 |
+
193 train 7.728556 (lr=2.0350e-03) (hash(x)=5483019)
|
| 204 |
+
194 train 7.667670 (lr=2.0455e-03) (hash(x)=5903258)
|
| 205 |
+
195 train 7.715605 (lr=2.0559e-03) (hash(x)=5968716)
|
| 206 |
+
196 train 7.696278 (lr=2.0664e-03) (hash(x)=5778017)
|
| 207 |
+
197 train 7.446229 (lr=2.0769e-03) (hash(x)=7780194)
|
| 208 |
+
198 train 7.623067 (lr=2.0874e-03) (hash(x)=6140998)
|
| 209 |
+
199 train 7.617758 (lr=2.0979e-03) (hash(x)=3784321)
|
| 210 |
+
200 val loss 7.6227
|
| 211 |
+
200 val perplexity 2044.1687
|
| 212 |
+
200 train 7.632349 (lr=2.1084e-03) (hash(x)=5860821)
|
| 213 |
+
201 train 7.667895 (lr=2.1189e-03) (hash(x)=7774109)
|
| 214 |
+
202 train 7.860171 (lr=2.1294e-03) (hash(x)=7997664)
|
| 215 |
+
203 train 7.817795 (lr=2.1399e-03) (hash(x)=6576749)
|
| 216 |
+
204 train 7.770859 (lr=2.1503e-03) (hash(x)=7266655)
|
| 217 |
+
205 train 7.753757 (lr=2.1608e-03) (hash(x)=7072404)
|
| 218 |
+
206 train 7.659934 (lr=2.1713e-03) (hash(x)=6626459)
|
| 219 |
+
207 train 7.685405 (lr=2.1818e-03) (hash(x)=6556025)
|
| 220 |
+
208 train 7.673626 (lr=2.1923e-03) (hash(x)=5942129)
|
| 221 |
+
209 train 7.783625 (lr=2.2028e-03) (hash(x)=7325027)
|
| 222 |
+
210 train 7.812902 (lr=2.2133e-03) (hash(x)=7322467)
|
| 223 |
+
211 train 7.734835 (lr=2.2238e-03) (hash(x)=6373412)
|
| 224 |
+
212 train 7.536884 (lr=2.2343e-03) (hash(x)=7332255)
|
| 225 |
+
213 train 7.799944 (lr=2.2448e-03) (hash(x)=5262868)
|
| 226 |
+
214 train 7.522233 (lr=2.2552e-03) (hash(x)=5688247)
|
| 227 |
+
215 train 7.675527 (lr=2.2657e-03) (hash(x)=8055563)
|
| 228 |
+
216 train 7.716257 (lr=2.2762e-03) (hash(x)=5352405)
|
| 229 |
+
217 train 7.777974 (lr=2.2867e-03) (hash(x)=5932790)
|
| 230 |
+
218 train 7.738881 (lr=2.2972e-03) (hash(x)=6249312)
|
| 231 |
+
219 train 7.696980 (lr=2.3077e-03) (hash(x)=5680154)
|
| 232 |
+
220 train 7.798860 (lr=2.3182e-03) (hash(x)=8156280)
|
| 233 |
+
221 train 7.721104 (lr=2.3287e-03) (hash(x)=5914217)
|
| 234 |
+
222 train 7.588368 (lr=2.3392e-03) (hash(x)=7120215)
|
| 235 |
+
223 train 7.730671 (lr=2.3497e-03) (hash(x)=6424128)
|
| 236 |
+
224 train 7.495186 (lr=2.3601e-03) (hash(x)=4390027)
|
| 237 |
+
225 train 7.705771 (lr=2.3706e-03) (hash(x)=7804089)
|
| 238 |
+
226 train 7.736785 (lr=2.3811e-03) (hash(x)=7130267)
|
| 239 |
+
227 train 7.513812 (lr=2.3916e-03) (hash(x)=6490149)
|
| 240 |
+
228 train 7.674036 (lr=2.4021e-03) (hash(x)=9276378)
|
| 241 |
+
229 train 7.717918 (lr=2.4126e-03) (hash(x)=6283540)
|
| 242 |
+
230 train 7.685045 (lr=2.4231e-03) (hash(x)=5781680)
|
| 243 |
+
231 train 7.627794 (lr=2.4336e-03) (hash(x)=5728337)
|
| 244 |
+
232 train 7.604231 (lr=2.4441e-03) (hash(x)=6278202)
|
| 245 |
+
233 train 7.694215 (lr=2.4545e-03) (hash(x)=7400272)
|
| 246 |
+
234 train 7.662181 (lr=2.4650e-03) (hash(x)=5795128)
|
| 247 |
+
235 train 7.656936 (lr=2.4755e-03) (hash(x)=6473432)
|
| 248 |
+
236 train 7.650620 (lr=2.4860e-03) (hash(x)=5201502)
|
| 249 |
+
237 train 7.835255 (lr=2.4965e-03) (hash(x)=6922646)
|
| 250 |
+
238 train 7.572138 (lr=2.5070e-03) (hash(x)=5484641)
|
| 251 |
+
239 train 7.644621 (lr=2.5175e-03) (hash(x)=7277141)
|
| 252 |
+
240 train 7.632049 (lr=2.5280e-03) (hash(x)=5604614)
|
| 253 |
+
241 train 7.708956 (lr=2.5385e-03) (hash(x)=7443124)
|
| 254 |
+
242 train 7.720611 (lr=2.5490e-03) (hash(x)=5601968)
|
| 255 |
+
243 train 7.620909 (lr=2.5594e-03) (hash(x)=5632735)
|
| 256 |
+
244 train 7.618441 (lr=2.5699e-03) (hash(x)=5594810)
|
| 257 |
+
245 train 7.467982 (lr=2.5804e-03) (hash(x)=5881015)
|
| 258 |
+
246 train 7.612959 (lr=2.5909e-03) (hash(x)=6865361)
|
| 259 |
+
247 train 7.708794 (lr=2.6014e-03) (hash(x)=5809411)
|
| 260 |
+
248 train 7.693843 (lr=2.6119e-03) (hash(x)=6293025)
|
| 261 |
+
249 train 7.642121 (lr=2.6224e-03) (hash(x)=7232964)
|
| 262 |
+
250 val loss 7.6851
|
| 263 |
+
250 val perplexity 2175.6370
|
| 264 |
+
250 train 7.620738 (lr=2.6329e-03) (hash(x)=5646619)
|
| 265 |
+
251 train 7.678328 (lr=2.6434e-03) (hash(x)=6171829)
|
| 266 |
+
252 train 7.766405 (lr=2.6538e-03) (hash(x)=7787552)
|
| 267 |
+
253 train 7.687263 (lr=2.6643e-03) (hash(x)=5884456)
|
| 268 |
+
254 train 7.706809 (lr=2.6748e-03) (hash(x)=6752162)
|
| 269 |
+
255 train 7.637703 (lr=2.6853e-03) (hash(x)=5077031)
|
| 270 |
+
256 train 7.767127 (lr=2.6958e-03) (hash(x)=6883481)
|
| 271 |
+
257 train 7.686365 (lr=2.7063e-03) (hash(x)=6248895)
|
| 272 |
+
258 train 7.568206 (lr=2.7168e-03) (hash(x)=6636615)
|
| 273 |
+
259 train 7.748939 (lr=2.7273e-03) (hash(x)=6918004)
|
| 274 |
+
260 train 7.660208 (lr=2.7378e-03) (hash(x)=7302874)
|
| 275 |
+
261 train 7.757563 (lr=2.7483e-03) (hash(x)=6482466)
|
| 276 |
+
262 train 7.597752 (lr=2.7587e-03) (hash(x)=7298317)
|
| 277 |
+
263 train 7.640695 (lr=2.7692e-03) (hash(x)=6588573)
|
| 278 |
+
264 train 7.663079 (lr=2.7797e-03) (hash(x)=6229630)
|
| 279 |
+
265 train 7.712162 (lr=2.7902e-03) (hash(x)=6136939)
|
| 280 |
+
266 train 7.500829 (lr=2.8007e-03) (hash(x)=6394645)
|
| 281 |
+
267 train 7.733948 (lr=2.8112e-03) (hash(x)=7040157)
|
| 282 |
+
268 train 7.792384 (lr=2.8217e-03) (hash(x)=7041858)
|
| 283 |
+
269 train 7.718139 (lr=2.8322e-03) (hash(x)=6455595)
|
| 284 |
+
270 train 7.688664 (lr=2.8427e-03) (hash(x)=6480443)
|
| 285 |
+
271 train 7.847613 (lr=2.8531e-03) (hash(x)=4122983)
|
| 286 |
+
272 train 7.705967 (lr=2.8636e-03) (hash(x)=7672190)
|
| 287 |
+
273 train 7.780782 (lr=2.8741e-03) (hash(x)=4724052)
|
| 288 |
+
274 train 7.748899 (lr=2.8846e-03) (hash(x)=6654267)
|
| 289 |
+
275 train 7.779582 (lr=2.8951e-03) (hash(x)=6820797)
|
| 290 |
+
276 train 7.836013 (lr=2.9056e-03) (hash(x)=6458662)
|
| 291 |
+
277 train 8.147118 (lr=2.9161e-03) (hash(x)=7477594)
|
| 292 |
+
278 train 7.887693 (lr=2.9266e-03) (hash(x)=5876574)
|
| 293 |
+
279 train 7.646071 (lr=2.9371e-03) (hash(x)=6146305)
|
| 294 |
+
280 train 7.829340 (lr=2.9476e-03) (hash(x)=6162080)
|
| 295 |
+
281 train 7.781260 (lr=2.9580e-03) (hash(x)=6814831)
|
| 296 |
+
282 train 7.876835 (lr=2.9685e-03) (hash(x)=7138295)
|
| 297 |
+
283 train 7.670539 (lr=2.9790e-03) (hash(x)=5548298)
|
| 298 |
+
284 train 7.762685 (lr=2.9895e-03) (hash(x)=6265078)
|
| 299 |
+
285 train 8.112201 (lr=3.0000e-03) (hash(x)=7609416)
|
| 300 |
+
286 train 7.840725 (lr=3.0000e-03) (hash(x)=6909367)
|
| 301 |
+
287 train 7.926526 (lr=3.0000e-03) (hash(x)=7574342)
|
| 302 |
+
288 train 7.721856 (lr=2.9999e-03) (hash(x)=8859748)
|
| 303 |
+
289 train 7.671402 (lr=2.9999e-03) (hash(x)=5906937)
|
| 304 |
+
290 train 7.687088 (lr=2.9998e-03) (hash(x)=7243024)
|
| 305 |
+
291 train 7.792162 (lr=2.9997e-03) (hash(x)=8013471)
|
| 306 |
+
292 train 7.728837 (lr=2.9995e-03) (hash(x)=5659461)
|
| 307 |
+
293 train 7.738378 (lr=2.9994e-03) (hash(x)=6146213)
|
| 308 |
+
294 train 7.758625 (lr=2.9992e-03) (hash(x)=6602917)
|
| 309 |
+
295 train 7.726678 (lr=2.9989e-03) (hash(x)=6709902)
|
| 310 |
+
296 train 7.828316 (lr=2.9987e-03) (hash(x)=8154341)
|
| 311 |
+
297 train 7.975238 (lr=2.9984e-03) (hash(x)=6402571)
|
| 312 |
+
298 train 7.745817 (lr=2.9981e-03) (hash(x)=5605466)
|
| 313 |
+
299 train 7.702537 (lr=2.9978e-03) (hash(x)=7683614)
|
| 314 |
+
300 val loss 7.7148
|
| 315 |
+
300 val perplexity 2241.2197
|
| 316 |
+
300 train 7.783172 (lr=2.9974e-03) (hash(x)=5421572)
|
| 317 |
+
301 train 7.629285 (lr=2.9971e-03) (hash(x)=5453026)
|
| 318 |
+
302 train 7.685293 (lr=2.9967e-03) (hash(x)=6437746)
|
| 319 |
+
303 train 7.568858 (lr=2.9962e-03) (hash(x)=6260017)
|
| 320 |
+
304 train 7.658658 (lr=2.9958e-03) (hash(x)=6119053)
|
| 321 |
+
305 train 7.817883 (lr=2.9953e-03) (hash(x)=6591466)
|
| 322 |
+
306 train 7.743184 (lr=2.9948e-03) (hash(x)=5652701)
|
| 323 |
+
307 train 7.736233 (lr=2.9942e-03) (hash(x)=5501472)
|
| 324 |
+
308 train 7.913201 (lr=2.9937e-03) (hash(x)=6160695)
|
| 325 |
+
309 train 7.691071 (lr=2.9931e-03) (hash(x)=5871698)
|
| 326 |
+
310 train 7.688094 (lr=2.9925e-03) (hash(x)=7301184)
|
| 327 |
+
311 train 7.602130 (lr=2.9918e-03) (hash(x)=4282052)
|
| 328 |
+
312 train 7.738359 (lr=2.9912e-03) (hash(x)=5679330)
|
| 329 |
+
313 train 7.641282 (lr=2.9905e-03) (hash(x)=7824660)
|
| 330 |
+
314 train 7.676686 (lr=2.9898e-03) (hash(x)=4857318)
|
| 331 |
+
315 train 7.662409 (lr=2.9890e-03) (hash(x)=5954950)
|
| 332 |
+
316 train 7.787707 (lr=2.9883e-03) (hash(x)=5758178)
|
| 333 |
+
317 train 7.824773 (lr=2.9875e-03) (hash(x)=5484656)
|
| 334 |
+
318 train 7.837453 (lr=2.9866e-03) (hash(x)=6818913)
|
| 335 |
+
319 train 7.964227 (lr=2.9858e-03) (hash(x)=7031328)
|
| 336 |
+
320 train 7.812165 (lr=2.9849e-03) (hash(x)=6837621)
|
| 337 |
+
321 train 7.816828 (lr=2.9840e-03) (hash(x)=9157069)
|
| 338 |
+
322 train 8.013040 (lr=2.9831e-03) (hash(x)=6509536)
|
| 339 |
+
323 train 7.737958 (lr=2.9821e-03) (hash(x)=5996883)
|
| 340 |
+
324 train 7.957640 (lr=2.9812e-03) (hash(x)=6850868)
|
| 341 |
+
325 train 7.920590 (lr=2.9802e-03) (hash(x)=7645447)
|
| 342 |
+
326 train 7.923620 (lr=2.9791e-03) (hash(x)=6717515)
|
| 343 |
+
327 train 7.987480 (lr=2.9781e-03) (hash(x)=6336164)
|
| 344 |
+
328 train 7.736178 (lr=2.9770e-03) (hash(x)=6897445)
|
| 345 |
+
329 train 7.656796 (lr=2.9759e-03) (hash(x)=5224240)
|
| 346 |
+
330 train 7.795270 (lr=2.9748e-03) (hash(x)=6612945)
|
| 347 |
+
331 train 8.244423 (lr=2.9736e-03) (hash(x)=5447801)
|
| 348 |
+
332 train 7.783621 (lr=2.9724e-03) (hash(x)=7308579)
|
| 349 |
+
333 train 7.651783 (lr=2.9712e-03) (hash(x)=4155598)
|
| 350 |
+
334 train 7.707504 (lr=2.9700e-03) (hash(x)=6106773)
|
| 351 |
+
335 train 7.753897 (lr=2.9687e-03) (hash(x)=7482744)
|
| 352 |
+
336 train 7.794834 (lr=2.9675e-03) (hash(x)=6310687)
|
| 353 |
+
337 train 7.666138 (lr=2.9662e-03) (hash(x)=4733414)
|
| 354 |
+
338 train 7.788680 (lr=2.9648e-03) (hash(x)=6979734)
|
| 355 |
+
339 train 7.597414 (lr=2.9635e-03) (hash(x)=7806284)
|
| 356 |
+
340 train 7.601125 (lr=2.9621e-03) (hash(x)=5080536)
|
| 357 |
+
341 train 7.852858 (lr=2.9607e-03) (hash(x)=7236478)
|
| 358 |
+
342 train 7.770869 (lr=2.9592e-03) (hash(x)=6619318)
|
| 359 |
+
343 train 7.629714 (lr=2.9578e-03) (hash(x)=4656255)
|
| 360 |
+
344 train 7.626460 (lr=2.9563e-03) (hash(x)=5546888)
|
| 361 |
+
345 train 7.953907 (lr=2.9548e-03) (hash(x)=9298325)
|
| 362 |
+
346 train 7.713796 (lr=2.9532e-03) (hash(x)=5994232)
|
| 363 |
+
347 train 7.704513 (lr=2.9517e-03) (hash(x)=6287524)
|
| 364 |
+
348 train 7.781829 (lr=2.9501e-03) (hash(x)=6200049)
|
| 365 |
+
349 train 7.707115 (lr=2.9485e-03) (hash(x)=7895970)
|
| 366 |
+
350 val loss 7.6625
|
| 367 |
+
350 val perplexity 2127.1697
|
| 368 |
+
350 train 7.633056 (lr=2.9468e-03) (hash(x)=6051847)
|
| 369 |
+
351 train 7.769653 (lr=2.9452e-03) (hash(x)=8847992)
|
| 370 |
+
352 train 8.056492 (lr=2.9435e-03) (hash(x)=5123883)
|
| 371 |
+
353 train 7.740765 (lr=2.9418e-03) (hash(x)=6338998)
|
| 372 |
+
354 train 7.758173 (lr=2.9400e-03) (hash(x)=5765866)
|
| 373 |
+
355 train 8.060540 (lr=2.9383e-03) (hash(x)=7104011)
|
| 374 |
+
356 train 7.874704 (lr=2.9365e-03) (hash(x)=7438267)
|
| 375 |
+
357 train 7.669201 (lr=2.9347e-03) (hash(x)=5573214)
|
| 376 |
+
358 train 7.887046 (lr=2.9328e-03) (hash(x)=6897283)
|
| 377 |
+
359 train 7.698498 (lr=2.9310e-03) (hash(x)=6882897)
|
| 378 |
+
360 train 7.846356 (lr=2.9291e-03) (hash(x)=5343615)
|
| 379 |
+
361 train 7.732404 (lr=2.9272e-03) (hash(x)=5854242)
|
| 380 |
+
362 train 7.663037 (lr=2.9252e-03) (hash(x)=6317324)
|
| 381 |
+
363 train 7.612657 (lr=2.9233e-03) (hash(x)=6972494)
|
| 382 |
+
364 train 7.670935 (lr=2.9213e-03) (hash(x)=5661167)
|
| 383 |
+
365 train 7.700908 (lr=2.9193e-03) (hash(x)=6796805)
|
| 384 |
+
366 train 7.570414 (lr=2.9172e-03) (hash(x)=5817209)
|
| 385 |
+
367 train 7.607064 (lr=2.9152e-03) (hash(x)=6139120)
|
| 386 |
+
368 train 7.757494 (lr=2.9131e-03) (hash(x)=6121296)
|
| 387 |
+
369 train 7.716562 (lr=2.9110e-03) (hash(x)=6486796)
|
| 388 |
+
370 train 7.652543 (lr=2.9088e-03) (hash(x)=5514645)
|
| 389 |
+
371 train 7.562969 (lr=2.9067e-03) (hash(x)=5578797)
|
| 390 |
+
372 train 7.640291 (lr=2.9045e-03) (hash(x)=7651738)
|
| 391 |
+
373 train 7.822971 (lr=2.9023e-03) (hash(x)=6895326)
|
| 392 |
+
374 train 7.826408 (lr=2.9001e-03) (hash(x)=5490256)
|
| 393 |
+
375 train 7.669705 (lr=2.8978e-03) (hash(x)=7783160)
|
| 394 |
+
376 train 7.868746 (lr=2.8955e-03) (hash(x)=5608424)
|
| 395 |
+
377 train 7.616645 (lr=2.8932e-03) (hash(x)=4867625)
|
| 396 |
+
378 train 7.535501 (lr=2.8909e-03) (hash(x)=4655472)
|
| 397 |
+
379 train 7.664939 (lr=2.8885e-03) (hash(x)=6631123)
|
| 398 |
+
380 train 7.403232 (lr=2.8862e-03) (hash(x)=5751990)
|
| 399 |
+
381 train 7.724658 (lr=2.8838e-03) (hash(x)=6710965)
|
| 400 |
+
382 train 7.697394 (lr=2.8813e-03) (hash(x)=5293800)
|
| 401 |
+
383 train 7.670368 (lr=2.8789e-03) (hash(x)=6294657)
|
| 402 |
+
384 train 7.807682 (lr=2.8764e-03) (hash(x)=6999538)
|
| 403 |
+
385 train 7.777709 (lr=2.8739e-03) (hash(x)=5443606)
|
| 404 |
+
386 train 7.767588 (lr=2.8714e-03) (hash(x)=5650401)
|
| 405 |
+
387 train 7.775039 (lr=2.8689e-03) (hash(x)=7035770)
|
| 406 |
+
388 train 7.714263 (lr=2.8663e-03) (hash(x)=6678271)
|
| 407 |
+
389 train 7.924842 (lr=2.8637e-03) (hash(x)=4899541)
|
| 408 |
+
390 train 7.713251 (lr=2.8611e-03) (hash(x)=5359260)
|
| 409 |
+
391 train 7.752142 (lr=2.8585e-03) (hash(x)=6227120)
|
| 410 |
+
392 train 7.823219 (lr=2.8558e-03) (hash(x)=6643916)
|
| 411 |
+
393 train 7.851696 (lr=2.8531e-03) (hash(x)=5981648)
|
| 412 |
+
394 train 7.841235 (lr=2.8504e-03) (hash(x)=6467540)
|
| 413 |
+
395 train 7.806389 (lr=2.8477e-03) (hash(x)=5558993)
|
| 414 |
+
396 train 7.953036 (lr=2.8449e-03) (hash(x)=6698959)
|
| 415 |
+
397 train 7.713658 (lr=2.8422e-03) (hash(x)=7015671)
|
| 416 |
+
398 train 7.750506 (lr=2.8394e-03) (hash(x)=6800890)
|
| 417 |
+
399 train 7.905320 (lr=2.8365e-03) (hash(x)=5931234)
|
| 418 |
+
400 val loss 7.8011
|
| 419 |
+
400 val perplexity 2443.2805
|
| 420 |
+
400 train 7.729572 (lr=2.8337e-03) (hash(x)=3995070)
|
| 421 |
+
401 train 7.721914 (lr=2.8308e-03) (hash(x)=4582159)
|
| 422 |
+
402 train 7.857014 (lr=2.8279e-03) (hash(x)=7081906)
|
| 423 |
+
403 train 7.797179 (lr=2.8250e-03) (hash(x)=5029472)
|
| 424 |
+
404 train 7.779564 (lr=2.8221e-03) (hash(x)=3946232)
|
| 425 |
+
405 train 7.708671 (lr=2.8191e-03) (hash(x)=5434102)
|
| 426 |
+
406 train 8.424617 (lr=2.8162e-03) (hash(x)=5340646)
|
| 427 |
+
407 train 7.648555 (lr=2.8131e-03) (hash(x)=6810638)
|
| 428 |
+
408 train 7.840656 (lr=2.8101e-03) (hash(x)=6768026)
|
| 429 |
+
409 train 7.868793 (lr=2.8071e-03) (hash(x)=6521562)
|
| 430 |
+
410 train 7.863975 (lr=2.8040e-03) (hash(x)=4429434)
|
| 431 |
+
411 train 7.945518 (lr=2.8009e-03) (hash(x)=7226932)
|
| 432 |
+
412 train 7.723341 (lr=2.7978e-03) (hash(x)=5065932)
|
| 433 |
+
413 train 7.881609 (lr=2.7947e-03) (hash(x)=6957849)
|
| 434 |
+
414 train 7.922746 (lr=2.7915e-03) (hash(x)=6431457)
|
| 435 |
+
415 train 7.997596 (lr=2.7883e-03) (hash(x)=5334281)
|
| 436 |
+
416 train 7.999408 (lr=2.7851e-03) (hash(x)=5471747)
|
| 437 |
+
417 train 8.103524 (lr=2.7819e-03) (hash(x)=5887983)
|
| 438 |
+
418 train 7.996161 (lr=2.7786e-03) (hash(x)=5075909)
|
| 439 |
+
419 train 7.792341 (lr=2.7754e-03) (hash(x)=6393576)
|
| 440 |
+
420 train 7.938378 (lr=2.7721e-03) (hash(x)=6608979)
|
| 441 |
+
421 train 8.275102 (lr=2.7688e-03) (hash(x)=5057959)
|
| 442 |
+
422 train 8.249427 (lr=2.7654e-03) (hash(x)=6414858)
|
| 443 |
+
423 train 8.018306 (lr=2.7621e-03) (hash(x)=8595271)
|
| 444 |
+
424 train 7.903035 (lr=2.7587e-03) (hash(x)=6500949)
|
| 445 |
+
425 train 8.053634 (lr=2.7553e-03) (hash(x)=8395167)
|
| 446 |
+
426 train 8.171664 (lr=2.7519e-03) (hash(x)=6288420)
|
| 447 |
+
427 train 8.028038 (lr=2.7484e-03) (hash(x)=7634417)
|
| 448 |
+
428 train 7.902526 (lr=2.7450e-03) (hash(x)=6795561)
|
| 449 |
+
429 train 7.781545 (lr=2.7415e-03) (hash(x)=5257771)
|
| 450 |
+
430 train 7.895492 (lr=2.7380e-03) (hash(x)=7506860)
|
| 451 |
+
431 train 7.966156 (lr=2.7344e-03) (hash(x)=7674238)
|
| 452 |
+
432 train 8.062552 (lr=2.7309e-03) (hash(x)=5353794)
|
| 453 |
+
433 train 8.043380 (lr=2.7273e-03) (hash(x)=5300555)
|
| 454 |
+
434 train 7.732123 (lr=2.7237e-03) (hash(x)=5564419)
|
| 455 |
+
435 train 7.954382 (lr=2.7201e-03) (hash(x)=6066139)
|
| 456 |
+
436 train 7.914176 (lr=2.7165e-03) (hash(x)=6863709)
|
| 457 |
+
437 train 7.927457 (lr=2.7128e-03) (hash(x)=6688212)
|
| 458 |
+
438 train 8.113889 (lr=2.7092e-03) (hash(x)=7095090)
|
| 459 |
+
439 train 8.155068 (lr=2.7055e-03) (hash(x)=6642404)
|
| 460 |
+
440 train 7.900812 (lr=2.7018e-03) (hash(x)=6539227)
|
| 461 |
+
441 train 7.901281 (lr=2.6980e-03) (hash(x)=4961570)
|
| 462 |
+
442 train 7.847559 (lr=2.6943e-03) (hash(x)=6606391)
|
| 463 |
+
443 train 7.667533 (lr=2.6905e-03) (hash(x)=5105190)
|
| 464 |
+
444 train 8.176149 (lr=2.6867e-03) (hash(x)=5695997)
|
| 465 |
+
445 train 7.932266 (lr=2.6829e-03) (hash(x)=7155991)
|
| 466 |
+
446 train 7.933327 (lr=2.6791e-03) (hash(x)=7249727)
|
| 467 |
+
447 train 7.926046 (lr=2.6752e-03) (hash(x)=5132972)
|
| 468 |
+
448 train 7.935805 (lr=2.6713e-03) (hash(x)=5381802)
|
| 469 |
+
449 train 7.973014 (lr=2.6674e-03) (hash(x)=6269946)
|
| 470 |
+
450 val loss 7.9383
|
| 471 |
+
450 val perplexity 2802.6472
|
| 472 |
+
450 train 7.944842 (lr=2.6635e-03) (hash(x)=4976762)
|
| 473 |
+
451 train 8.006948 (lr=2.6596e-03) (hash(x)=5396133)
|
| 474 |
+
452 train 7.989438 (lr=2.6556e-03) (hash(x)=6173473)
|
| 475 |
+
453 train 7.997161 (lr=2.6517e-03) (hash(x)=6394083)
|
| 476 |
+
454 train 8.010630 (lr=2.6477e-03) (hash(x)=6436030)
|
| 477 |
+
455 train 7.917981 (lr=2.6437e-03) (hash(x)=5237804)
|
| 478 |
+
456 train 7.868698 (lr=2.6396e-03) (hash(x)=6540397)
|
| 479 |
+
457 train 8.089856 (lr=2.6356e-03) (hash(x)=5216638)
|
| 480 |
+
458 train 7.983370 (lr=2.6315e-03) (hash(x)=5750537)
|
| 481 |
+
459 train 7.943202 (lr=2.6274e-03) (hash(x)=6735565)
|
| 482 |
+
460 train 7.976765 (lr=2.6233e-03) (hash(x)=7297488)
|
| 483 |
+
461 train 8.166513 (lr=2.6192e-03) (hash(x)=5983575)
|
| 484 |
+
462 train 8.007421 (lr=2.6150e-03) (hash(x)=4808543)
|
| 485 |
+
463 train 8.073018 (lr=2.6109e-03) (hash(x)=5831619)
|
| 486 |
+
464 train 7.890032 (lr=2.6067e-03) (hash(x)=6280052)
|
| 487 |
+
465 train 7.881892 (lr=2.6025e-03) (hash(x)=9109083)
|
| 488 |
+
466 train 8.133326 (lr=2.5983e-03) (hash(x)=5848604)
|
| 489 |
+
467 train 8.054812 (lr=2.5940e-03) (hash(x)=6912967)
|
| 490 |
+
468 train 8.200366 (lr=2.5898e-03) (hash(x)=6615365)
|
| 491 |
+
469 train 8.259668 (lr=2.5855e-03) (hash(x)=5965674)
|
| 492 |
+
470 train 8.095193 (lr=2.5812e-03) (hash(x)=6879965)
|
| 493 |
+
471 train 8.095140 (lr=2.5769e-03) (hash(x)=5822533)
|
| 494 |
+
472 train 7.966299 (lr=2.5726e-03) (hash(x)=5794462)
|
| 495 |
+
473 train 8.030313 (lr=2.5682e-03) (hash(x)=5268216)
|
| 496 |
+
474 train 7.873148 (lr=2.5639e-03) (hash(x)=7058396)
|
| 497 |
+
475 train 7.960652 (lr=2.5595e-03) (hash(x)=6531900)
|
| 498 |
+
476 train 7.949832 (lr=2.5551e-03) (hash(x)=5878912)
|
| 499 |
+
477 train 7.775286 (lr=2.5507e-03) (hash(x)=5426499)
|
| 500 |
+
478 train 7.951344 (lr=2.5462e-03) (hash(x)=8107004)
|
| 501 |
+
479 train 8.597595 (lr=2.5418e-03) (hash(x)=7455372)
|
| 502 |
+
480 train 8.484189 (lr=2.5373e-03) (hash(x)=7727959)
|
| 503 |
+
481 train 8.422830 (lr=2.5328e-03) (hash(x)=8319119)
|
| 504 |
+
482 train 8.377604 (lr=2.5283e-03) (hash(x)=7581656)
|
| 505 |
+
483 train 8.430602 (lr=2.5238e-03) (hash(x)=7592128)
|
| 506 |
+
484 train 8.436010 (lr=2.5193e-03) (hash(x)=10506633)
|
| 507 |
+
485 train 8.412131 (lr=2.5147e-03) (hash(x)=8704170)
|
| 508 |
+
486 train 8.266512 (lr=2.5102e-03) (hash(x)=7461138)
|
| 509 |
+
487 train 8.173214 (lr=2.5056e-03) (hash(x)=7165037)
|
| 510 |
+
488 train 8.125466 (lr=2.5010e-03) (hash(x)=4976998)
|
| 511 |
+
489 train 7.863452 (lr=2.4963e-03) (hash(x)=7678000)
|
| 512 |
+
490 train 7.880426 (lr=2.4917e-03) (hash(x)=6299409)
|
| 513 |
+
491 train 7.912982 (lr=2.4871e-03) (hash(x)=7414788)
|
| 514 |
+
492 train 7.945197 (lr=2.4824e-03) (hash(x)=5063061)
|
| 515 |
+
493 train 7.891151 (lr=2.4777e-03) (hash(x)=7326216)
|
| 516 |
+
494 train 8.001021 (lr=2.4730e-03) (hash(x)=7492012)
|
| 517 |
+
495 train 7.946517 (lr=2.4683e-03) (hash(x)=5857162)
|
| 518 |
+
496 train 7.742063 (lr=2.4636e-03) (hash(x)=6169001)
|
| 519 |
+
497 train 9.323244 (lr=2.4588e-03) (hash(x)=14715669)
|
| 520 |
+
498 train 11.585467 (lr=2.4540e-03) (hash(x)=18256706)
|
| 521 |
+
499 train 11.505814 (lr=2.4493e-03) (hash(x)=16950560)
|
| 522 |
+
500 val loss 7.9923
|
| 523 |
+
500 val perplexity 2958.0181
|
| 524 |
+
500 train 8.598713 (lr=2.4445e-03) (hash(x)=6113563)
|
| 525 |
+
501 train 7.678519 (lr=2.4397e-03) (hash(x)=6159125)
|
| 526 |
+
502 train 7.969828 (lr=2.4348e-03) (hash(x)=5482303)
|
| 527 |
+
503 train 7.944439 (lr=2.4300e-03) (hash(x)=5908442)
|
| 528 |
+
504 train 7.774529 (lr=2.4251e-03) (hash(x)=4985045)
|
| 529 |
+
505 train 7.677323 (lr=2.4203e-03) (hash(x)=6668887)
|
| 530 |
+
506 train 7.788567 (lr=2.4154e-03) (hash(x)=6123910)
|
| 531 |
+
507 train 7.998281 (lr=2.4105e-03) (hash(x)=7662975)
|
| 532 |
+
508 train 8.016782 (lr=2.4056e-03) (hash(x)=7191898)
|
| 533 |
+
509 train 7.777871 (lr=2.4006e-03) (hash(x)=6669539)
|
| 534 |
+
510 train 7.794437 (lr=2.3957e-03) (hash(x)=6557481)
|
| 535 |
+
511 train 7.741953 (lr=2.3907e-03) (hash(x)=5015998)
|
| 536 |
+
512 train 7.873833 (lr=2.3858e-03) (hash(x)=4964540)
|
| 537 |
+
513 train 7.804757 (lr=2.3808e-03) (hash(x)=5458386)
|
| 538 |
+
514 train 8.057392 (lr=2.3758e-03) (hash(x)=6077616)
|
| 539 |
+
515 train 7.841374 (lr=2.3708e-03) (hash(x)=4849847)
|
| 540 |
+
516 train 7.810348 (lr=2.3657e-03) (hash(x)=5431422)
|
| 541 |
+
517 train 7.937412 (lr=2.3607e-03) (hash(x)=5125562)
|
| 542 |
+
518 train 7.879202 (lr=2.3556e-03) (hash(x)=5587715)
|
| 543 |
+
519 train 7.989350 (lr=2.3506e-03) (hash(x)=6012047)
|
| 544 |
+
520 train 7.872843 (lr=2.3455e-03) (hash(x)=5668436)
|
| 545 |
+
521 train 7.925120 (lr=2.3404e-03) (hash(x)=6079364)
|
| 546 |
+
522 train 8.085070 (lr=2.3353e-03) (hash(x)=5200504)
|
| 547 |
+
523 train 7.750674 (lr=2.3301e-03) (hash(x)=6030395)
|
| 548 |
+
524 train 7.994751 (lr=2.3250e-03) (hash(x)=6855319)
|
| 549 |
+
525 train 7.724610 (lr=2.3198e-03) (hash(x)=6781762)
|
| 550 |
+
526 train 7.858620 (lr=2.3147e-03) (hash(x)=6717939)
|
| 551 |
+
527 train 7.841614 (lr=2.3095e-03) (hash(x)=5238325)
|
| 552 |
+
528 train 7.739461 (lr=2.3043e-03) (hash(x)=5808069)
|
| 553 |
+
529 train 8.022832 (lr=2.2991e-03) (hash(x)=8611144)
|
| 554 |
+
530 train 7.778861 (lr=2.2939e-03) (hash(x)=6028738)
|
| 555 |
+
531 train 7.774855 (lr=2.2887e-03) (hash(x)=6901605)
|
| 556 |
+
532 train 7.729041 (lr=2.2834e-03) (hash(x)=6723307)
|
| 557 |
+
533 train 7.801713 (lr=2.2782e-03) (hash(x)=5499337)
|
| 558 |
+
534 train 7.761014 (lr=2.2729e-03) (hash(x)=6586372)
|
| 559 |
+
535 train 7.874071 (lr=2.2676e-03) (hash(x)=7134874)
|
| 560 |
+
536 train 7.772084 (lr=2.2624e-03) (hash(x)=8415623)
|
| 561 |
+
537 train 7.804130 (lr=2.2571e-03) (hash(x)=6149038)
|
| 562 |
+
538 train 7.834948 (lr=2.2517e-03) (hash(x)=6078325)
|
| 563 |
+
539 train 7.808557 (lr=2.2464e-03) (hash(x)=6609760)
|
| 564 |
+
540 train 7.700895 (lr=2.2411e-03) (hash(x)=6185253)
|
| 565 |
+
541 train 8.098028 (lr=2.2357e-03) (hash(x)=6652627)
|
| 566 |
+
542 train 7.866323 (lr=2.2304e-03) (hash(x)=7758536)
|
| 567 |
+
543 train 7.853946 (lr=2.2250e-03) (hash(x)=8618579)
|
| 568 |
+
544 train 7.824872 (lr=2.2196e-03) (hash(x)=6710226)
|
| 569 |
+
545 train 7.689782 (lr=2.2142e-03) (hash(x)=5896892)
|
| 570 |
+
546 train 7.695562 (lr=2.2088e-03) (hash(x)=6332995)
|
| 571 |
+
547 train 8.089109 (lr=2.2034e-03) (hash(x)=8945854)
|
| 572 |
+
548 train 7.645922 (lr=2.1980e-03) (hash(x)=4329129)
|
| 573 |
+
549 train 7.714274 (lr=2.1926e-03) (hash(x)=6775103)
|
| 574 |
+
550 val loss 7.7371
|
| 575 |
+
550 val perplexity 2291.8955
|
| 576 |
+
550 train 7.809414 (lr=2.1871e-03) (hash(x)=4465735)
|
| 577 |
+
551 train 7.704854 (lr=2.1817e-03) (hash(x)=6200024)
|
| 578 |
+
552 train 7.674021 (lr=2.1762e-03) (hash(x)=5520748)
|
| 579 |
+
553 train 7.686450 (lr=2.1707e-03) (hash(x)=5238139)
|
| 580 |
+
554 train 7.948024 (lr=2.1653e-03) (hash(x)=7639817)
|
| 581 |
+
555 train 7.674497 (lr=2.1598e-03) (hash(x)=5780948)
|
| 582 |
+
556 train 7.809311 (lr=2.1542e-03) (hash(x)=6733444)
|
| 583 |
+
557 train 7.760883 (lr=2.1487e-03) (hash(x)=6168407)
|
| 584 |
+
558 train 7.792346 (lr=2.1432e-03) (hash(x)=6680197)
|
| 585 |
+
559 train 7.708677 (lr=2.1377e-03) (hash(x)=3775881)
|
| 586 |
+
560 train 7.542058 (lr=2.1321e-03) (hash(x)=5784096)
|
| 587 |
+
561 train 7.974462 (lr=2.1266e-03) (hash(x)=6848709)
|
| 588 |
+
562 train 8.006401 (lr=2.1210e-03) (hash(x)=7449019)
|
| 589 |
+
563 train 8.100924 (lr=2.1154e-03) (hash(x)=6478113)
|
| 590 |
+
564 train 7.741627 (lr=2.1099e-03) (hash(x)=5925744)
|
| 591 |
+
565 train 7.798370 (lr=2.1043e-03) (hash(x)=6483914)
|
| 592 |
+
566 train 7.719404 (lr=2.0987e-03) (hash(x)=6010847)
|
| 593 |
+
567 train 7.807489 (lr=2.0931e-03) (hash(x)=5927795)
|
| 594 |
+
568 train 7.792548 (lr=2.0875e-03) (hash(x)=5896332)
|
| 595 |
+
569 train 7.763503 (lr=2.0818e-03) (hash(x)=8438033)
|
| 596 |
+
570 train 7.838992 (lr=2.0762e-03) (hash(x)=6081660)
|
| 597 |
+
571 train 7.772511 (lr=2.0706e-03) (hash(x)=5684788)
|
| 598 |
+
572 train 7.681820 (lr=2.0649e-03) (hash(x)=6272055)
|
| 599 |
+
573 train 7.640155 (lr=2.0593e-03) (hash(x)=5710182)
|
| 600 |
+
574 train 7.744366 (lr=2.0536e-03) (hash(x)=6219616)
|
| 601 |
+
575 train 7.731422 (lr=2.0479e-03) (hash(x)=6160063)
|
| 602 |
+
576 train 7.743604 (lr=2.0422e-03) (hash(x)=5710809)
|
| 603 |
+
577 train 7.576396 (lr=2.0366e-03) (hash(x)=5955100)
|
| 604 |
+
578 train 7.616704 (lr=2.0309e-03) (hash(x)=5356088)
|
| 605 |
+
579 train 7.678293 (lr=2.0252e-03) (hash(x)=6672309)
|
| 606 |
+
580 train 7.871900 (lr=2.0194e-03) (hash(x)=5841684)
|
| 607 |
+
581 train 8.198613 (lr=2.0137e-03) (hash(x)=9001564)
|
| 608 |
+
582 train 8.703930 (lr=2.0080e-03) (hash(x)=6897178)
|
| 609 |
+
583 train 7.881172 (lr=2.0023e-03) (hash(x)=5454654)
|
| 610 |
+
584 train 7.689722 (lr=1.9965e-03) (hash(x)=6391454)
|
| 611 |
+
585 train 7.760036 (lr=1.9908e-03) (hash(x)=5174062)
|
| 612 |
+
586 train 7.865849 (lr=1.9850e-03) (hash(x)=5197924)
|
| 613 |
+
587 train 7.974902 (lr=1.9793e-03) (hash(x)=6199203)
|
| 614 |
+
588 train 7.830613 (lr=1.9735e-03) (hash(x)=5786498)
|
| 615 |
+
589 train 7.862635 (lr=1.9677e-03) (hash(x)=8352747)
|
| 616 |
+
590 train 8.096232 (lr=1.9620e-03) (hash(x)=4829700)
|
| 617 |
+
591 train 7.609157 (lr=1.9562e-03) (hash(x)=4547106)
|
| 618 |
+
592 train 7.931683 (lr=1.9504e-03) (hash(x)=7686831)
|
| 619 |
+
593 train 7.834821 (lr=1.9446e-03) (hash(x)=6433099)
|
| 620 |
+
594 train 7.736665 (lr=1.9388e-03) (hash(x)=4826460)
|
| 621 |
+
595 train 7.856832 (lr=1.9330e-03) (hash(x)=6424428)
|
| 622 |
+
596 train 7.744674 (lr=1.9272e-03) (hash(x)=6073605)
|
| 623 |
+
597 train 8.010549 (lr=1.9214e-03) (hash(x)=5975712)
|
| 624 |
+
598 train 7.597208 (lr=1.9156e-03) (hash(x)=7030029)
|
| 625 |
+
599 train 7.850381 (lr=1.9097e-03) (hash(x)=5458532)
|
| 626 |
+
600 val loss 7.8050
|
| 627 |
+
600 val perplexity 2452.8469
|
| 628 |
+
600 train 7.737244 (lr=1.9039e-03) (hash(x)=7823919)
|
| 629 |
+
601 train 8.143096 (lr=1.8981e-03) (hash(x)=7002774)
|
| 630 |
+
602 train 7.982004 (lr=1.8922e-03) (hash(x)=7056399)
|
| 631 |
+
603 train 8.169475 (lr=1.8864e-03) (hash(x)=8206173)
|
| 632 |
+
604 train 7.984448 (lr=1.8805e-03) (hash(x)=8034846)
|
| 633 |
+
605 train 8.210122 (lr=1.8747e-03) (hash(x)=7784971)
|
| 634 |
+
606 train 8.455732 (lr=1.8688e-03) (hash(x)=7118076)
|
| 635 |
+
607 train 7.696686 (lr=1.8629e-03) (hash(x)=6001843)
|
| 636 |
+
608 train 7.811610 (lr=1.8571e-03) (hash(x)=5582437)
|
| 637 |
+
609 train 7.915626 (lr=1.8512e-03) (hash(x)=5698642)
|
| 638 |
+
610 train 7.810270 (lr=1.8453e-03) (hash(x)=6615301)
|
| 639 |
+
611 train 7.849596 (lr=1.8395e-03) (hash(x)=6600751)
|
| 640 |
+
612 train 7.812829 (lr=1.8336e-03) (hash(x)=6880955)
|
| 641 |
+
613 train 7.871310 (lr=1.8277e-03) (hash(x)=5804610)
|
| 642 |
+
614 train 7.721910 (lr=1.8218e-03) (hash(x)=6263347)
|
| 643 |
+
615 train 7.704498 (lr=1.8159e-03) (hash(x)=5162652)
|
| 644 |
+
616 train 7.714991 (lr=1.8100e-03) (hash(x)=6055710)
|
| 645 |
+
617 train 7.678866 (lr=1.8041e-03) (hash(x)=5297006)
|
| 646 |
+
618 train 7.712785 (lr=1.7982e-03) (hash(x)=5923648)
|
| 647 |
+
619 train 7.789293 (lr=1.7923e-03) (hash(x)=6728323)
|
| 648 |
+
620 train 7.809510 (lr=1.7864e-03) (hash(x)=6660239)
|
| 649 |
+
621 train 7.755341 (lr=1.7805e-03) (hash(x)=3964882)
|
| 650 |
+
622 train 7.824354 (lr=1.7746e-03) (hash(x)=5868942)
|
| 651 |
+
623 train 7.733279 (lr=1.7686e-03) (hash(x)=6735993)
|
| 652 |
+
624 train 7.965105 (lr=1.7627e-03) (hash(x)=5926190)
|
| 653 |
+
625 train 7.723885 (lr=1.7568e-03) (hash(x)=5150316)
|
| 654 |
+
626 train 7.748303 (lr=1.7509e-03) (hash(x)=7571467)
|
| 655 |
+
627 train 7.623729 (lr=1.7450e-03) (hash(x)=5220448)
|
| 656 |
+
628 train 7.666851 (lr=1.7390e-03) (hash(x)=6790397)
|
| 657 |
+
629 train 8.094706 (lr=1.7331e-03) (hash(x)=6971289)
|
| 658 |
+
630 train 8.032075 (lr=1.7272e-03) (hash(x)=7123359)
|
| 659 |
+
631 train 7.846966 (lr=1.7212e-03) (hash(x)=5012069)
|
| 660 |
+
632 train 7.789418 (lr=1.7153e-03) (hash(x)=6183574)
|
| 661 |
+
633 train 7.699522 (lr=1.7094e-03) (hash(x)=6576136)
|
| 662 |
+
634 train 7.766065 (lr=1.7034e-03) (hash(x)=6157346)
|
| 663 |
+
635 train 7.748011 (lr=1.6975e-03) (hash(x)=6077647)
|
| 664 |
+
636 train 7.959746 (lr=1.6916e-03) (hash(x)=8369488)
|
| 665 |
+
637 train 7.770888 (lr=1.6856e-03) (hash(x)=6032381)
|
| 666 |
+
638 train 7.699530 (lr=1.6797e-03) (hash(x)=5924756)
|
| 667 |
+
639 train 7.721142 (lr=1.6738e-03) (hash(x)=8410716)
|
| 668 |
+
640 train 7.728985 (lr=1.6678e-03) (hash(x)=5803440)
|
| 669 |
+
641 train 7.794473 (lr=1.6619e-03) (hash(x)=6212516)
|
| 670 |
+
642 train 7.875453 (lr=1.6559e-03) (hash(x)=7165945)
|
| 671 |
+
643 train 7.586662 (lr=1.6500e-03) (hash(x)=5298545)
|
| 672 |
+
644 train 7.807044 (lr=1.6441e-03) (hash(x)=6281739)
|
| 673 |
+
645 train 7.799070 (lr=1.6381e-03) (hash(x)=5779073)
|
| 674 |
+
646 train 7.660677 (lr=1.6322e-03) (hash(x)=5090107)
|
| 675 |
+
647 train 7.747698 (lr=1.6262e-03) (hash(x)=6340947)
|
| 676 |
+
648 train 7.520845 (lr=1.6203e-03) (hash(x)=4741418)
|
| 677 |
+
649 train 7.467843 (lr=1.6144e-03) (hash(x)=6530441)
|
| 678 |
+
650 val loss 7.7629
|
| 679 |
+
650 val perplexity 2351.6338
|
| 680 |
+
650 train 7.972628 (lr=1.6084e-03) (hash(x)=6396041)
|
| 681 |
+
651 train 7.677337 (lr=1.6025e-03) (hash(x)=7818007)
|
| 682 |
+
652 train 7.657900 (lr=1.5966e-03) (hash(x)=6478457)
|
| 683 |
+
653 train 7.741147 (lr=1.5906e-03) (hash(x)=6277435)
|
| 684 |
+
654 train 7.690449 (lr=1.5847e-03) (hash(x)=6042369)
|
| 685 |
+
655 train 7.692099 (lr=1.5788e-03) (hash(x)=6226320)
|
| 686 |
+
656 train 7.694995 (lr=1.5728e-03) (hash(x)=5826883)
|
| 687 |
+
657 train 7.791507 (lr=1.5669e-03) (hash(x)=5463751)
|
| 688 |
+
658 train 7.761098 (lr=1.5610e-03) (hash(x)=6433080)
|
| 689 |
+
659 train 7.616423 (lr=1.5550e-03) (hash(x)=6579329)
|
| 690 |
+
660 train 7.607751 (lr=1.5491e-03) (hash(x)=4724703)
|
| 691 |
+
661 train 7.910522 (lr=1.5432e-03) (hash(x)=6660540)
|
| 692 |
+
662 train 7.749463 (lr=1.5373e-03) (hash(x)=5918756)
|
| 693 |
+
663 train 7.701428 (lr=1.5314e-03) (hash(x)=6491272)
|
| 694 |
+
664 train 7.631092 (lr=1.5254e-03) (hash(x)=5452863)
|
| 695 |
+
665 train 7.807280 (lr=1.5195e-03) (hash(x)=6766947)
|
| 696 |
+
666 train 8.081844 (lr=1.5136e-03) (hash(x)=7459504)
|
| 697 |
+
667 train 7.823114 (lr=1.5077e-03) (hash(x)=3721218)
|
| 698 |
+
668 train 7.956896 (lr=1.5018e-03) (hash(x)=7929571)
|
| 699 |
+
669 train 7.701605 (lr=1.4959e-03) (hash(x)=5229898)
|
| 700 |
+
670 train 7.722555 (lr=1.4900e-03) (hash(x)=6083090)
|
| 701 |
+
671 train 7.603117 (lr=1.4841e-03) (hash(x)=6054428)
|
| 702 |
+
672 train 7.728995 (lr=1.4782e-03) (hash(x)=6072563)
|
| 703 |
+
673 train 7.896479 (lr=1.4723e-03) (hash(x)=6290464)
|
| 704 |
+
674 train 7.950490 (lr=1.4664e-03) (hash(x)=6314742)
|
| 705 |
+
675 train 7.621716 (lr=1.4605e-03) (hash(x)=6904498)
|
| 706 |
+
676 train 7.732175 (lr=1.4547e-03) (hash(x)=5378107)
|
| 707 |
+
677 train 7.837443 (lr=1.4488e-03) (hash(x)=7765805)
|
| 708 |
+
678 train 7.693831 (lr=1.4429e-03) (hash(x)=5871280)
|
| 709 |
+
679 train 7.818718 (lr=1.4371e-03) (hash(x)=6543764)
|
| 710 |
+
680 train 7.768837 (lr=1.4312e-03) (hash(x)=7369665)
|
| 711 |
+
681 train 7.800853 (lr=1.4253e-03) (hash(x)=7204955)
|
| 712 |
+
682 train 7.765916 (lr=1.4195e-03) (hash(x)=5856543)
|
| 713 |
+
683 train 7.634814 (lr=1.4136e-03) (hash(x)=4423711)
|
| 714 |
+
684 train 7.615927 (lr=1.4078e-03) (hash(x)=5818153)
|
| 715 |
+
685 train 7.729960 (lr=1.4019e-03) (hash(x)=5343477)
|
| 716 |
+
686 train 7.862391 (lr=1.3961e-03) (hash(x)=6581702)
|
| 717 |
+
687 train 7.739387 (lr=1.3903e-03) (hash(x)=6595856)
|
| 718 |
+
688 train 7.707435 (lr=1.3844e-03) (hash(x)=5325378)
|
| 719 |
+
689 train 7.593647 (lr=1.3786e-03) (hash(x)=7229015)
|
| 720 |
+
690 train 7.778830 (lr=1.3728e-03) (hash(x)=5918186)
|
| 721 |
+
691 train 7.672666 (lr=1.3670e-03) (hash(x)=5916034)
|
| 722 |
+
692 train 7.652022 (lr=1.3612e-03) (hash(x)=5280722)
|
| 723 |
+
693 train 8.022188 (lr=1.3554e-03) (hash(x)=6939521)
|
| 724 |
+
694 train 7.780650 (lr=1.3496e-03) (hash(x)=5172566)
|
| 725 |
+
695 train 7.668669 (lr=1.3438e-03) (hash(x)=5492185)
|
| 726 |
+
696 train 7.530053 (lr=1.3380e-03) (hash(x)=5779011)
|
| 727 |
+
697 train 7.806943 (lr=1.3323e-03) (hash(x)=6898006)
|
| 728 |
+
698 train 7.649033 (lr=1.3265e-03) (hash(x)=5779217)
|
| 729 |
+
699 train 7.519248 (lr=1.3207e-03) (hash(x)=5462008)
|
| 730 |
+
700 val loss 7.7573
|
| 731 |
+
700 val perplexity 2338.6721
|
| 732 |
+
700 train 7.608866 (lr=1.3150e-03) (hash(x)=6243843)
|
| 733 |
+
701 train 7.664562 (lr=1.3092e-03) (hash(x)=7821902)
|
| 734 |
+
702 train 7.759399 (lr=1.3035e-03) (hash(x)=5222501)
|
| 735 |
+
703 train 7.725120 (lr=1.2977e-03) (hash(x)=6608108)
|
| 736 |
+
704 train 7.830003 (lr=1.2920e-03) (hash(x)=7602879)
|
| 737 |
+
705 train 7.744042 (lr=1.2863e-03) (hash(x)=6295394)
|
| 738 |
+
706 train 7.720629 (lr=1.2806e-03) (hash(x)=6579907)
|
| 739 |
+
707 train 7.618686 (lr=1.2748e-03) (hash(x)=6803449)
|
| 740 |
+
708 train 7.697527 (lr=1.2691e-03) (hash(x)=5413733)
|
| 741 |
+
709 train 7.682727 (lr=1.2634e-03) (hash(x)=7444134)
|
| 742 |
+
710 train 7.778391 (lr=1.2578e-03) (hash(x)=7028652)
|
| 743 |
+
711 train 7.619783 (lr=1.2521e-03) (hash(x)=5361923)
|
| 744 |
+
712 train 7.714285 (lr=1.2464e-03) (hash(x)=5478293)
|
| 745 |
+
713 train 7.666296 (lr=1.2407e-03) (hash(x)=7803039)
|
| 746 |
+
714 train 7.873608 (lr=1.2351e-03) (hash(x)=6469017)
|
| 747 |
+
715 train 7.756383 (lr=1.2294e-03) (hash(x)=7042578)
|
| 748 |
+
716 train 7.805631 (lr=1.2238e-03) (hash(x)=6927957)
|
| 749 |
+
717 train 7.658313 (lr=1.2182e-03) (hash(x)=6647007)
|
| 750 |
+
718 train 7.626003 (lr=1.2125e-03) (hash(x)=6230888)
|
| 751 |
+
719 train 7.867710 (lr=1.2069e-03) (hash(x)=6303658)
|
| 752 |
+
720 train 7.879463 (lr=1.2013e-03) (hash(x)=6769880)
|
| 753 |
+
721 train 7.752194 (lr=1.1957e-03) (hash(x)=6158927)
|
| 754 |
+
722 train 7.750047 (lr=1.1901e-03) (hash(x)=5991631)
|
| 755 |
+
723 train 7.639153 (lr=1.1846e-03) (hash(x)=6419656)
|
| 756 |
+
724 train 7.682890 (lr=1.1790e-03) (hash(x)=7739209)
|
| 757 |
+
725 train 7.577069 (lr=1.1734e-03) (hash(x)=7891271)
|
| 758 |
+
726 train 7.858076 (lr=1.1679e-03) (hash(x)=7171433)
|
| 759 |
+
727 train 7.661083 (lr=1.1623e-03) (hash(x)=7099888)
|
| 760 |
+
728 train 7.706316 (lr=1.1568e-03) (hash(x)=6103730)
|
| 761 |
+
729 train 7.850070 (lr=1.1513e-03) (hash(x)=6352424)
|
| 762 |
+
730 train 7.735737 (lr=1.1458e-03) (hash(x)=4893671)
|
| 763 |
+
731 train 7.715113 (lr=1.1402e-03) (hash(x)=5863145)
|
| 764 |
+
732 train 7.823025 (lr=1.1347e-03) (hash(x)=5502233)
|
| 765 |
+
733 train 7.668149 (lr=1.1293e-03) (hash(x)=6844597)
|
| 766 |
+
734 train 7.700110 (lr=1.1238e-03) (hash(x)=6744526)
|
| 767 |
+
735 train 7.816046 (lr=1.1183e-03) (hash(x)=6009861)
|
| 768 |
+
736 train 7.730307 (lr=1.1129e-03) (hash(x)=6152358)
|
| 769 |
+
737 train 7.641603 (lr=1.1074e-03) (hash(x)=5374957)
|
| 770 |
+
738 train 7.698134 (lr=1.1020e-03) (hash(x)=6495309)
|
| 771 |
+
739 train 7.831391 (lr=1.0966e-03) (hash(x)=3923225)
|
| 772 |
+
740 train 7.642580 (lr=1.0912e-03) (hash(x)=6255243)
|
| 773 |
+
741 train 7.729340 (lr=1.0858e-03) (hash(x)=5848862)
|
| 774 |
+
742 train 7.830632 (lr=1.0804e-03) (hash(x)=4535000)
|
| 775 |
+
743 train 7.688915 (lr=1.0750e-03) (hash(x)=4440634)
|
| 776 |
+
744 train 7.650380 (lr=1.0696e-03) (hash(x)=5222077)
|
| 777 |
+
745 train 7.661867 (lr=1.0643e-03) (hash(x)=4788998)
|
| 778 |
+
746 train 7.659130 (lr=1.0589e-03) (hash(x)=6108350)
|
| 779 |
+
747 train 7.556808 (lr=1.0536e-03) (hash(x)=7378165)
|
| 780 |
+
748 train 7.655461 (lr=1.0483e-03) (hash(x)=5475646)
|
| 781 |
+
749 train 7.684846 (lr=1.0429e-03) (hash(x)=4771243)
|
| 782 |
+
750 val loss 7.7446
|
| 783 |
+
750 val perplexity 2309.0671
|
| 784 |
+
750 train 7.546549 (lr=1.0376e-03) (hash(x)=6668088)
|
| 785 |
+
751 train 7.782291 (lr=1.0324e-03) (hash(x)=5716089)
|
| 786 |
+
752 train 7.754150 (lr=1.0271e-03) (hash(x)=6991946)
|
| 787 |
+
753 train 7.649727 (lr=1.0218e-03) (hash(x)=7991009)
|
| 788 |
+
754 train 7.750846 (lr=1.0166e-03) (hash(x)=6037018)
|
| 789 |
+
755 train 7.760281 (lr=1.0113e-03) (hash(x)=5348607)
|
| 790 |
+
756 train 7.875297 (lr=1.0061e-03) (hash(x)=5190526)
|
| 791 |
+
757 train 7.791673 (lr=1.0009e-03) (hash(x)=6036146)
|
| 792 |
+
758 train 7.639391 (lr=9.9568e-04) (hash(x)=5329783)
|
| 793 |
+
759 train 7.736132 (lr=9.9049e-04) (hash(x)=6658718)
|
| 794 |
+
760 train 7.628929 (lr=9.8531e-04) (hash(x)=4820939)
|
| 795 |
+
761 train 7.576667 (lr=9.8015e-04) (hash(x)=6176253)
|
| 796 |
+
762 train 7.576687 (lr=9.7500e-04) (hash(x)=5316750)
|
| 797 |
+
763 train 7.659533 (lr=9.6986e-04) (hash(x)=4542895)
|
| 798 |
+
764 train 7.536968 (lr=9.6474e-04) (hash(x)=5395673)
|
| 799 |
+
765 train 7.587499 (lr=9.5963e-04) (hash(x)=5549073)
|
| 800 |
+
766 train 7.839692 (lr=9.5453e-04) (hash(x)=5233723)
|
| 801 |
+
767 train 7.864366 (lr=9.4944e-04) (hash(x)=5342783)
|
| 802 |
+
768 train 7.814504 (lr=9.4437e-04) (hash(x)=5552448)
|
| 803 |
+
769 train 7.966274 (lr=9.3932e-04) (hash(x)=6549546)
|
| 804 |
+
770 train 7.629685 (lr=9.3427e-04) (hash(x)=3816493)
|
| 805 |
+
771 train 7.701268 (lr=9.2924e-04) (hash(x)=6170599)
|
| 806 |
+
772 train 8.166368 (lr=9.2423e-04) (hash(x)=6708759)
|
| 807 |
+
773 train 7.812929 (lr=9.1923e-04) (hash(x)=8483134)
|
| 808 |
+
774 train 8.372843 (lr=9.1424e-04) (hash(x)=5583732)
|
| 809 |
+
775 train 7.799413 (lr=9.0927e-04) (hash(x)=4865036)
|
| 810 |
+
776 train 7.704354 (lr=9.0431e-04) (hash(x)=7234336)
|
| 811 |
+
777 train 7.665652 (lr=8.9936e-04) (hash(x)=4433890)
|
| 812 |
+
778 train 7.969852 (lr=8.9443e-04) (hash(x)=7484636)
|
| 813 |
+
779 train 8.454505 (lr=8.8952e-04) (hash(x)=6738597)
|
| 814 |
+
780 train 7.688463 (lr=8.8462e-04) (hash(x)=6752421)
|
| 815 |
+
781 train 7.865383 (lr=8.7973e-04) (hash(x)=5459620)
|
| 816 |
+
782 train 7.794898 (lr=8.7486e-04) (hash(x)=6718131)
|
| 817 |
+
783 train 7.777268 (lr=8.7001e-04) (hash(x)=4604074)
|
| 818 |
+
784 train 7.632578 (lr=8.6516e-04) (hash(x)=5946124)
|
| 819 |
+
785 train 7.862961 (lr=8.6034e-04) (hash(x)=8045501)
|
| 820 |
+
786 train 8.002986 (lr=8.5553e-04) (hash(x)=5712725)
|
| 821 |
+
787 train 7.726302 (lr=8.5073e-04) (hash(x)=6176464)
|
| 822 |
+
788 train 7.806107 (lr=8.4596e-04) (hash(x)=6276702)
|
| 823 |
+
789 train 7.621425 (lr=8.4119e-04) (hash(x)=6127317)
|
| 824 |
+
790 train 7.731322 (lr=8.3644e-04) (hash(x)=7221374)
|
| 825 |
+
791 train 7.723422 (lr=8.3171e-04) (hash(x)=5571462)
|
| 826 |
+
792 train 7.708071 (lr=8.2699e-04) (hash(x)=7518021)
|
| 827 |
+
793 train 7.732567 (lr=8.2229e-04) (hash(x)=6640755)
|
| 828 |
+
794 train 7.818214 (lr=8.1761e-04) (hash(x)=6870405)
|
| 829 |
+
795 train 7.785426 (lr=8.1294e-04) (hash(x)=6147295)
|
| 830 |
+
796 train 7.666309 (lr=8.0829e-04) (hash(x)=6782583)
|
| 831 |
+
797 train 7.766424 (lr=8.0365e-04) (hash(x)=6120461)
|
| 832 |
+
798 train 7.702960 (lr=7.9903e-04) (hash(x)=5893870)
|
| 833 |
+
799 train 7.636458 (lr=7.9443e-04) (hash(x)=5123928)
|
| 834 |
+
800 val loss 7.7189
|
| 835 |
+
800 val perplexity 2250.5442
|
| 836 |
+
800 train 7.693479 (lr=7.8984e-04) (hash(x)=7037251)
|
| 837 |
+
801 train 7.702105 (lr=7.8527e-04) (hash(x)=5428813)
|
| 838 |
+
802 train 7.605880 (lr=7.8072e-04) (hash(x)=5550387)
|
| 839 |
+
803 train 7.726039 (lr=7.7618e-04) (hash(x)=6448586)
|
| 840 |
+
804 train 7.836322 (lr=7.7167e-04) (hash(x)=5916934)
|
| 841 |
+
805 train 7.794024 (lr=7.6716e-04) (hash(x)=8116987)
|
| 842 |
+
806 train 7.768242 (lr=7.6268e-04) (hash(x)=6210899)
|
| 843 |
+
807 train 7.869483 (lr=7.5821e-04) (hash(x)=5974342)
|
| 844 |
+
808 train 7.886734 (lr=7.5376e-04) (hash(x)=7236199)
|
| 845 |
+
809 train 7.820665 (lr=7.4933e-04) (hash(x)=5261336)
|
| 846 |
+
810 train 7.649134 (lr=7.4491e-04) (hash(x)=6310720)
|
| 847 |
+
811 train 7.690774 (lr=7.4051e-04) (hash(x)=5307056)
|
| 848 |
+
812 train 7.530347 (lr=7.3613e-04) (hash(x)=7356633)
|
| 849 |
+
813 train 7.639516 (lr=7.3177e-04) (hash(x)=5865119)
|
| 850 |
+
814 train 7.559615 (lr=7.2742e-04) (hash(x)=5979205)
|
| 851 |
+
815 train 7.690104 (lr=7.2309e-04) (hash(x)=6672380)
|
| 852 |
+
816 train 7.690113 (lr=7.1878e-04) (hash(x)=5565030)
|
| 853 |
+
817 train 7.665623 (lr=7.1449e-04) (hash(x)=6886810)
|
| 854 |
+
818 train 7.717739 (lr=7.1022e-04) (hash(x)=5926478)
|
| 855 |
+
819 train 7.886773 (lr=7.0596e-04) (hash(x)=6564071)
|
| 856 |
+
820 train 7.555373 (lr=7.0173e-04) (hash(x)=5024280)
|
| 857 |
+
821 train 7.568484 (lr=6.9751e-04) (hash(x)=7705089)
|
| 858 |
+
822 train 7.549848 (lr=6.9331e-04) (hash(x)=4037371)
|
| 859 |
+
823 train 7.644377 (lr=6.8913e-04) (hash(x)=5773073)
|
| 860 |
+
824 train 7.650955 (lr=6.8496e-04) (hash(x)=7158139)
|
| 861 |
+
825 train 7.496713 (lr=6.8082e-04) (hash(x)=5905976)
|
| 862 |
+
826 train 7.935842 (lr=6.7669e-04) (hash(x)=13897369)
|
| 863 |
+
827 train 9.065568 (lr=6.7259e-04) (hash(x)=6936653)
|
| 864 |
+
828 train 7.685574 (lr=6.6850e-04) (hash(x)=6592246)
|
| 865 |
+
829 train 7.650198 (lr=6.6443e-04) (hash(x)=6592773)
|
| 866 |
+
830 train 7.721585 (lr=6.6038e-04) (hash(x)=5461178)
|
| 867 |
+
831 train 7.512312 (lr=6.5635e-04) (hash(x)=6796551)
|
| 868 |
+
832 train 7.708601 (lr=6.5234e-04) (hash(x)=4721691)
|
| 869 |
+
833 train 7.635646 (lr=6.4835e-04) (hash(x)=6151589)
|
| 870 |
+
834 train 7.783632 (lr=6.4437e-04) (hash(x)=7008995)
|
| 871 |
+
835 train 8.044557 (lr=6.4042e-04) (hash(x)=7045164)
|
| 872 |
+
836 train 7.694743 (lr=6.3649e-04) (hash(x)=6614221)
|
| 873 |
+
837 train 7.741001 (lr=6.3257e-04) (hash(x)=6650506)
|
| 874 |
+
838 train 7.584609 (lr=6.2868e-04) (hash(x)=6363762)
|
| 875 |
+
839 train 7.705591 (lr=6.2480e-04) (hash(x)=7839748)
|
| 876 |
+
840 train 7.630804 (lr=6.2095e-04) (hash(x)=5124077)
|
| 877 |
+
841 train 8.054181 (lr=6.1711e-04) (hash(x)=6028671)
|
| 878 |
+
842 train 7.554688 (lr=6.1330e-04) (hash(x)=5427175)
|
| 879 |
+
843 train 7.825301 (lr=6.0950e-04) (hash(x)=6118408)
|
| 880 |
+
844 train 7.664781 (lr=6.0573e-04) (hash(x)=6022552)
|
| 881 |
+
845 train 7.648100 (lr=6.0198e-04) (hash(x)=5757526)
|
| 882 |
+
846 train 8.100301 (lr=5.9824e-04) (hash(x)=6476549)
|
| 883 |
+
847 train 7.494151 (lr=5.9453e-04) (hash(x)=6030172)
|
| 884 |
+
848 train 7.786404 (lr=5.9083e-04) (hash(x)=5917229)
|
| 885 |
+
849 train 7.899832 (lr=5.8716e-04) (hash(x)=6719882)
|
| 886 |
+
850 val loss 7.7071
|
| 887 |
+
850 val perplexity 2223.9949
|
| 888 |
+
850 train 7.746506 (lr=5.8351e-04) (hash(x)=5441498)
|
| 889 |
+
851 train 7.653311 (lr=5.7988e-04) (hash(x)=5028050)
|
| 890 |
+
852 train 7.693791 (lr=5.7627e-04) (hash(x)=8487491)
|
| 891 |
+
853 train 7.688711 (lr=5.7268e-04) (hash(x)=5682910)
|
| 892 |
+
854 train 7.864785 (lr=5.6911e-04) (hash(x)=6781362)
|
| 893 |
+
855 train 7.677633 (lr=5.6556e-04) (hash(x)=5747891)
|
| 894 |
+
856 train 7.728158 (lr=5.6203e-04) (hash(x)=7627661)
|
| 895 |
+
857 train 7.398406 (lr=5.5853e-04) (hash(x)=5734208)
|
| 896 |
+
858 train 7.535101 (lr=5.5504e-04) (hash(x)=6162015)
|
| 897 |
+
859 train 7.759229 (lr=5.5158e-04) (hash(x)=7024381)
|
| 898 |
+
860 train 7.900477 (lr=5.4813e-04) (hash(x)=5198498)
|
| 899 |
+
861 train 7.872756 (lr=5.4471e-04) (hash(x)=7814361)
|
| 900 |
+
862 train 7.786388 (lr=5.4131e-04) (hash(x)=7394995)
|
| 901 |
+
863 train 7.723223 (lr=5.3793e-04) (hash(x)=5765893)
|
| 902 |
+
864 train 7.529533 (lr=5.3458e-04) (hash(x)=4990435)
|
| 903 |
+
865 train 7.621973 (lr=5.3124e-04) (hash(x)=5572048)
|
| 904 |
+
866 train 7.808869 (lr=5.2793e-04) (hash(x)=7093293)
|
| 905 |
+
867 train 7.701506 (lr=5.2464e-04) (hash(x)=5610058)
|
| 906 |
+
868 train 7.610654 (lr=5.2137e-04) (hash(x)=6771468)
|
| 907 |
+
869 train 7.614294 (lr=5.1812e-04) (hash(x)=4459483)
|
| 908 |
+
870 train 7.531222 (lr=5.1489e-04) (hash(x)=4926546)
|
| 909 |
+
871 train 7.655554 (lr=5.1169e-04) (hash(x)=6758411)
|
| 910 |
+
872 train 7.589464 (lr=5.0851e-04) (hash(x)=7394277)
|
| 911 |
+
873 train 7.726064 (lr=5.0534e-04) (hash(x)=6701381)
|
| 912 |
+
874 train 8.026758 (lr=5.0221e-04) (hash(x)=8120966)
|
| 913 |
+
875 train 7.588314 (lr=4.9909e-04) (hash(x)=5416400)
|
| 914 |
+
876 train 7.609078 (lr=4.9600e-04) (hash(x)=6292778)
|
| 915 |
+
877 train 7.524262 (lr=4.9293e-04) (hash(x)=5919569)
|
| 916 |
+
878 train 7.842921 (lr=4.8988e-04) (hash(x)=7561740)
|
| 917 |
+
879 train 7.611346 (lr=4.8685e-04) (hash(x)=5282870)
|
| 918 |
+
880 train 7.612226 (lr=4.8385e-04) (hash(x)=5473238)
|
| 919 |
+
881 train 7.519906 (lr=4.8087e-04) (hash(x)=8072181)
|
| 920 |
+
882 train 7.548308 (lr=4.7791e-04) (hash(x)=6757322)
|
| 921 |
+
883 train 7.529226 (lr=4.7497e-04) (hash(x)=7996770)
|
| 922 |
+
884 train 7.588312 (lr=4.7206e-04) (hash(x)=3181021)
|
| 923 |
+
885 train 7.610131 (lr=4.6917e-04) (hash(x)=5093519)
|
| 924 |
+
886 train 7.599638 (lr=4.6630e-04) (hash(x)=5391352)
|
| 925 |
+
887 train 7.642168 (lr=4.6346e-04) (hash(x)=6270917)
|
| 926 |
+
888 train 7.650049 (lr=4.6063e-04) (hash(x)=5818195)
|
| 927 |
+
889 train 7.375628 (lr=4.5783e-04) (hash(x)=5852780)
|
| 928 |
+
890 train 7.306717 (lr=4.5506e-04) (hash(x)=5777928)
|
| 929 |
+
891 train 7.517593 (lr=4.5231e-04) (hash(x)=5327728)
|
| 930 |
+
892 train 7.565458 (lr=4.4958e-04) (hash(x)=7651281)
|
| 931 |
+
893 train 7.717712 (lr=4.4687e-04) (hash(x)=6260765)
|
| 932 |
+
894 train 7.621277 (lr=4.4419e-04) (hash(x)=6265102)
|
| 933 |
+
895 train 7.790190 (lr=4.4153e-04) (hash(x)=6212894)
|
| 934 |
+
896 train 7.579635 (lr=4.3889e-04) (hash(x)=6901967)
|
| 935 |
+
897 train 7.616450 (lr=4.3628e-04) (hash(x)=6724010)
|
| 936 |
+
898 train 7.616309 (lr=4.3369e-04) (hash(x)=6299033)
|
| 937 |
+
899 train 7.756639 (lr=4.3113e-04) (hash(x)=6059934)
|
| 938 |
+
900 val loss 7.6898
|
| 939 |
+
900 val perplexity 2185.8826
|
| 940 |
+
900 train 7.497322 (lr=4.2858e-04) (hash(x)=6029696)
|
| 941 |
+
901 train 7.426641 (lr=4.2607e-04) (hash(x)=5587382)
|
| 942 |
+
902 train 7.630977 (lr=4.2357e-04) (hash(x)=5890076)
|
| 943 |
+
903 train 7.569328 (lr=4.2110e-04) (hash(x)=7274108)
|
| 944 |
+
904 train 7.642725 (lr=4.1865e-04) (hash(x)=7975528)
|
| 945 |
+
905 train 7.667113 (lr=4.1623e-04) (hash(x)=6085396)
|
| 946 |
+
906 train 7.563230 (lr=4.1383e-04) (hash(x)=6724496)
|
| 947 |
+
907 train 7.567484 (lr=4.1146e-04) (hash(x)=4784666)
|
| 948 |
+
908 train 7.576261 (lr=4.0910e-04) (hash(x)=7193845)
|
| 949 |
+
909 train 7.719419 (lr=4.0678e-04) (hash(x)=6288638)
|
| 950 |
+
910 train 7.692960 (lr=4.0447e-04) (hash(x)=5685285)
|
| 951 |
+
911 train 7.666305 (lr=4.0220e-04) (hash(x)=7714288)
|
| 952 |
+
912 train 7.747677 (lr=3.9994e-04) (hash(x)=5983679)
|
| 953 |
+
913 train 7.705470 (lr=3.9771e-04) (hash(x)=5534748)
|
| 954 |
+
914 train 7.656706 (lr=3.9550e-04) (hash(x)=6545471)
|
| 955 |
+
915 train 7.647849 (lr=3.9332e-04) (hash(x)=6361270)
|
| 956 |
+
916 train 7.651623 (lr=3.9116e-04) (hash(x)=6257744)
|
| 957 |
+
917 train 7.653042 (lr=3.8903e-04) (hash(x)=4682956)
|
| 958 |
+
918 train 7.536811 (lr=3.8692e-04) (hash(x)=4521756)
|
| 959 |
+
919 train 7.683554 (lr=3.8484e-04) (hash(x)=7568935)
|
| 960 |
+
920 train 7.620051 (lr=3.8277e-04) (hash(x)=7969353)
|
| 961 |
+
921 train 7.775512 (lr=3.8074e-04) (hash(x)=7973311)
|
| 962 |
+
922 train 7.513662 (lr=3.7873e-04) (hash(x)=4843937)
|
| 963 |
+
923 train 7.645644 (lr=3.7674e-04) (hash(x)=6987352)
|
| 964 |
+
924 train 7.716321 (lr=3.7478e-04) (hash(x)=7179418)
|
| 965 |
+
925 train 7.418215 (lr=3.7284e-04) (hash(x)=5413904)
|
| 966 |
+
926 train 7.781198 (lr=3.7093e-04) (hash(x)=6028105)
|
| 967 |
+
927 train 7.721332 (lr=3.6904e-04) (hash(x)=6732924)
|
| 968 |
+
928 train 7.630275 (lr=3.6718e-04) (hash(x)=4547651)
|
| 969 |
+
929 train 7.767948 (lr=3.6534e-04) (hash(x)=6219754)
|
| 970 |
+
930 train 7.586576 (lr=3.6353e-04) (hash(x)=7465186)
|
| 971 |
+
931 train 7.708647 (lr=3.6174e-04) (hash(x)=6839070)
|
| 972 |
+
932 train 7.599780 (lr=3.5998e-04) (hash(x)=5390324)
|
| 973 |
+
933 train 7.540503 (lr=3.5824e-04) (hash(x)=6090120)
|
| 974 |
+
934 train 8.092051 (lr=3.5653e-04) (hash(x)=7123181)
|
| 975 |
+
935 train 7.824137 (lr=3.5484e-04) (hash(x)=7115176)
|
| 976 |
+
936 train 7.840931 (lr=3.5317e-04) (hash(x)=7016990)
|
| 977 |
+
937 train 7.606159 (lr=3.5154e-04) (hash(x)=4989299)
|
| 978 |
+
938 train 7.635037 (lr=3.4992e-04) (hash(x)=6783311)
|
| 979 |
+
939 train 7.605995 (lr=3.4833e-04) (hash(x)=7497590)
|
| 980 |
+
940 train 7.803225 (lr=3.4677e-04) (hash(x)=6767514)
|
| 981 |
+
941 train 7.577324 (lr=3.4523e-04) (hash(x)=3977557)
|
| 982 |
+
942 train 7.673528 (lr=3.4372e-04) (hash(x)=4806492)
|
| 983 |
+
943 train 7.605245 (lr=3.4224e-04) (hash(x)=5524165)
|
| 984 |
+
944 train 7.674973 (lr=3.4077e-04) (hash(x)=4930752)
|
| 985 |
+
945 train 7.645176 (lr=3.3934e-04) (hash(x)=5124936)
|
| 986 |
+
946 train 7.545757 (lr=3.3793e-04) (hash(x)=6877351)
|
| 987 |
+
947 train 7.793520 (lr=3.3654e-04) (hash(x)=5522119)
|
| 988 |
+
948 train 7.619642 (lr=3.3518e-04) (hash(x)=6183512)
|
| 989 |
+
949 train 7.531892 (lr=3.3385e-04) (hash(x)=5030865)
|
| 990 |
+
950 val loss 7.6693
|
| 991 |
+
950 val perplexity 2141.6748
|
| 992 |
+
950 train 7.626034 (lr=3.3254e-04) (hash(x)=6619812)
|
| 993 |
+
951 train 7.628423 (lr=3.3125e-04) (hash(x)=6411783)
|
| 994 |
+
952 train 7.648422 (lr=3.3000e-04) (hash(x)=6748982)
|
| 995 |
+
953 train 7.528099 (lr=3.2876e-04) (hash(x)=6581937)
|
| 996 |
+
954 train 7.662632 (lr=3.2756e-04) (hash(x)=7881022)
|
| 997 |
+
955 train 7.622310 (lr=3.2638e-04) (hash(x)=5116910)
|
| 998 |
+
956 train 7.402312 (lr=3.2522e-04) (hash(x)=4880833)
|
| 999 |
+
957 train 7.445642 (lr=3.2409e-04) (hash(x)=7353459)
|
| 1000 |
+
958 train 7.529793 (lr=3.2299e-04) (hash(x)=4951302)
|
| 1001 |
+
959 train 7.449977 (lr=3.2191e-04) (hash(x)=6344535)
|
| 1002 |
+
960 train 8.022265 (lr=3.2085e-04) (hash(x)=7411763)
|
| 1003 |
+
961 train 7.606797 (lr=3.1983e-04) (hash(x)=5840169)
|
| 1004 |
+
962 train 7.669691 (lr=3.1883e-04) (hash(x)=5784788)
|
| 1005 |
+
963 train 7.503743 (lr=3.1785e-04) (hash(x)=6754290)
|
| 1006 |
+
964 train 7.788940 (lr=3.1690e-04) (hash(x)=6369963)
|
| 1007 |
+
965 train 7.825077 (lr=3.1598e-04) (hash(x)=6484573)
|
| 1008 |
+
966 train 7.465019 (lr=3.1508e-04) (hash(x)=6516338)
|
| 1009 |
+
967 train 7.505771 (lr=3.1421e-04) (hash(x)=5260125)
|
| 1010 |
+
968 train 7.605400 (lr=3.1336e-04) (hash(x)=5781624)
|
| 1011 |
+
969 train 7.429417 (lr=3.1254e-04) (hash(x)=4881179)
|
| 1012 |
+
970 train 7.543368 (lr=3.1174e-04) (hash(x)=6707821)
|
| 1013 |
+
971 train 7.668115 (lr=3.1098e-04) (hash(x)=5001634)
|
| 1014 |
+
972 train 7.527225 (lr=3.1023e-04) (hash(x)=4402949)
|
| 1015 |
+
973 train 7.552583 (lr=3.0952e-04) (hash(x)=7424810)
|
| 1016 |
+
974 train 7.377101 (lr=3.0882e-04) (hash(x)=4814803)
|
| 1017 |
+
975 train 7.317751 (lr=3.0816e-04) (hash(x)=5176431)
|
| 1018 |
+
976 train 7.517481 (lr=3.0752e-04) (hash(x)=5769393)
|
| 1019 |
+
977 train 7.466238 (lr=3.0691e-04) (hash(x)=5421624)
|
| 1020 |
+
978 train 7.668548 (lr=3.0632e-04) (hash(x)=5999773)
|
| 1021 |
+
979 train 7.464861 (lr=3.0576e-04) (hash(x)=5674439)
|
| 1022 |
+
980 train 7.529809 (lr=3.0522e-04) (hash(x)=6345351)
|
| 1023 |
+
981 train 7.470555 (lr=3.0471e-04) (hash(x)=5819157)
|
| 1024 |
+
982 train 7.667230 (lr=3.0423e-04) (hash(x)=11159355)
|
| 1025 |
+
983 train 7.651269 (lr=3.0377e-04) (hash(x)=6506856)
|
| 1026 |
+
984 train 7.550761 (lr=3.0334e-04) (hash(x)=6331023)
|
| 1027 |
+
985 train 7.446228 (lr=3.0294e-04) (hash(x)=6119124)
|
| 1028 |
+
986 train 7.646875 (lr=3.0256e-04) (hash(x)=8142528)
|
| 1029 |
+
987 train 7.805590 (lr=3.0221e-04) (hash(x)=6241669)
|
| 1030 |
+
988 train 7.469787 (lr=3.0188e-04) (hash(x)=3852991)
|
| 1031 |
+
989 train 7.245332 (lr=3.0158e-04) (hash(x)=4992756)
|
| 1032 |
+
990 train 7.870277 (lr=3.0131e-04) (hash(x)=7097145)
|
| 1033 |
+
991 train 7.664296 (lr=3.0106e-04) (hash(x)=7277927)
|
| 1034 |
+
992 train 7.733374 (lr=3.0084e-04) (hash(x)=5661400)
|
| 1035 |
+
993 train 7.671187 (lr=3.0064e-04) (hash(x)=6622097)
|
| 1036 |
+
994 train 7.763366 (lr=3.0047e-04) (hash(x)=5016804)
|
| 1037 |
+
995 train 7.836728 (lr=3.0033e-04) (hash(x)=7026582)
|
| 1038 |
+
996 train 7.639297 (lr=3.0021e-04) (hash(x)=5639136)
|
| 1039 |
+
997 train 7.818308 (lr=3.0012e-04) (hash(x)=5840987)
|
| 1040 |
+
998 train 7.442023 (lr=3.0005e-04) (hash(x)=5265410)
|
| 1041 |
+
999 val loss 7.6574
|
| 1042 |
+
999 val perplexity 2116.2170
|
| 1043 |
+
999 train 7.426812 (lr=3.0001e-04) (hash(x)=4351074)
|
lr3e-3_total_batch_size20480_seq_len128/model_00999.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0feb000846e4a55ca04000ed370702db2d2c70ffa53489bc0993bb8db79d859
|
| 3 |
+
size 36163010
|
lr3e-3_total_batch_size20480_seq_len128/optimizer_00999.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6270b6c88175c4bbf6227b5e0847218f6c39a18e81fd9c47078ae504fb3bdcc3
|
| 3 |
+
size 70764358
|