Upload folder using huggingface_hub
Browse files- lr2e-4_total_batch_size61440_baseline_seed1340/args.json +1 -0
- lr2e-4_total_batch_size61440_baseline_seed1340/dataloader_08749.pt +3 -0
- lr2e-4_total_batch_size61440_baseline_seed1340/log2.txt +1054 -0
- lr2e-4_total_batch_size61440_baseline_seed1340/model_08749.pt +3 -0
- lr2e-4_total_batch_size61440_baseline_seed1340/optimizer_08749.pt +3 -0
lr2e-4_total_batch_size61440_baseline_seed1340/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "wider_is_better_11/lr2e-4_total_batch_size61440_baseline_seed1340", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 4, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 8750, "warmup_steps": 500, "group": "wider_is_better_11", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1340, "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": 256, "batch_size": 120, "total_batch_size": 61440, "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": false, "mup_enable_coord_check_logging": false, "max_lr": 0.0002, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "2e-4_61440", "n_embd": 256}
|
lr2e-4_total_batch_size61440_baseline_seed1340/dataloader_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:953385078aa3787b69fc6857dfd48b0a2cd2f4d27c6f8892e01211aca53d07f5
|
| 3 |
+
size 964
|
lr2e-4_total_batch_size61440_baseline_seed1340/log2.txt
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_steps: 8750
|
| 2 |
+
0 val loss 11.2465
|
| 3 |
+
0 val perplexity 76608.0938
|
| 4 |
+
0 train 11.254622 (lr=4.0000e-07) (hash(x)=164406924)
|
| 5 |
+
10 train 10.826647 (lr=4.4000e-06) (hash(x)=152008797)
|
| 6 |
+
20 train 10.252349 (lr=8.4000e-06) (hash(x)=153494457)
|
| 7 |
+
30 train 9.874741 (lr=1.2400e-05) (hash(x)=137328499)
|
| 8 |
+
40 train 9.867218 (lr=1.6400e-05) (hash(x)=159333245)
|
| 9 |
+
50 train 9.683481 (lr=2.0400e-05) (hash(x)=177407419)
|
| 10 |
+
60 train 9.519449 (lr=2.4400e-05) (hash(x)=127877799)
|
| 11 |
+
70 train 9.238721 (lr=2.8400e-05) (hash(x)=140873918)
|
| 12 |
+
80 train 9.098090 (lr=3.2400e-05) (hash(x)=160249377)
|
| 13 |
+
90 train 8.800228 (lr=3.6400e-05) (hash(x)=154282910)
|
| 14 |
+
100 val loss 8.5390
|
| 15 |
+
100 val perplexity 5110.0830
|
| 16 |
+
100 train 8.487245 (lr=4.0400e-05) (hash(x)=144903932)
|
| 17 |
+
110 train 8.311394 (lr=4.4400e-05) (hash(x)=151685723)
|
| 18 |
+
120 train 8.024857 (lr=4.8400e-05) (hash(x)=152347864)
|
| 19 |
+
130 train 7.880245 (lr=5.2400e-05) (hash(x)=152230926)
|
| 20 |
+
140 train 7.691835 (lr=5.6400e-05) (hash(x)=142121048)
|
| 21 |
+
150 train 7.718791 (lr=6.0400e-05) (hash(x)=173839165)
|
| 22 |
+
160 train 7.478759 (lr=6.4400e-05) (hash(x)=158755931)
|
| 23 |
+
170 train 7.346524 (lr=6.8400e-05) (hash(x)=151645697)
|
| 24 |
+
180 train 7.614252 (lr=7.2400e-05) (hash(x)=179696111)
|
| 25 |
+
190 train 7.256871 (lr=7.6400e-05) (hash(x)=150511423)
|
| 26 |
+
200 val loss 7.3076
|
| 27 |
+
200 val perplexity 1491.5831
|
| 28 |
+
200 train 7.426102 (lr=8.0400e-05) (hash(x)=167734596)
|
| 29 |
+
210 train 7.037323 (lr=8.4400e-05) (hash(x)=133157560)
|
| 30 |
+
220 train 7.290061 (lr=8.8400e-05) (hash(x)=152234670)
|
| 31 |
+
230 train 7.111869 (lr=9.2400e-05) (hash(x)=160995039)
|
| 32 |
+
240 train 6.985393 (lr=9.6400e-05) (hash(x)=139367591)
|
| 33 |
+
250 train 7.149043 (lr=1.0040e-04) (hash(x)=153224076)
|
| 34 |
+
260 train 7.063549 (lr=1.0440e-04) (hash(x)=156667529)
|
| 35 |
+
270 train 6.926666 (lr=1.0840e-04) (hash(x)=133883725)
|
| 36 |
+
280 train 6.748665 (lr=1.1240e-04) (hash(x)=151939311)
|
| 37 |
+
290 train 6.800394 (lr=1.1640e-04) (hash(x)=150290478)
|
| 38 |
+
300 val loss 6.8028
|
| 39 |
+
300 val perplexity 900.3564
|
| 40 |
+
300 train 6.743678 (lr=1.2040e-04) (hash(x)=149619098)
|
| 41 |
+
310 train 6.627342 (lr=1.2440e-04) (hash(x)=142344072)
|
| 42 |
+
320 train 6.714992 (lr=1.2840e-04) (hash(x)=151878766)
|
| 43 |
+
330 train 6.567842 (lr=1.3240e-04) (hash(x)=136419763)
|
| 44 |
+
340 train 6.680336 (lr=1.3640e-04) (hash(x)=160761498)
|
| 45 |
+
350 train 6.533365 (lr=1.4040e-04) (hash(x)=146539909)
|
| 46 |
+
360 train 6.600818 (lr=1.4440e-04) (hash(x)=143063312)
|
| 47 |
+
370 train 6.488721 (lr=1.4840e-04) (hash(x)=153705818)
|
| 48 |
+
380 train 6.402529 (lr=1.5240e-04) (hash(x)=149579175)
|
| 49 |
+
390 train 6.342468 (lr=1.5640e-04) (hash(x)=150904406)
|
| 50 |
+
400 val loss 6.4480
|
| 51 |
+
400 val perplexity 631.4080
|
| 52 |
+
400 train 6.285553 (lr=1.6040e-04) (hash(x)=153710890)
|
| 53 |
+
410 train 6.206480 (lr=1.6440e-04) (hash(x)=138302968)
|
| 54 |
+
420 train 6.188835 (lr=1.6840e-04) (hash(x)=141112989)
|
| 55 |
+
430 train 6.267785 (lr=1.7240e-04) (hash(x)=149846944)
|
| 56 |
+
440 train 6.286611 (lr=1.7640e-04) (hash(x)=157683479)
|
| 57 |
+
450 train 6.294905 (lr=1.8040e-04) (hash(x)=155873620)
|
| 58 |
+
460 train 6.475963 (lr=1.8440e-04) (hash(x)=152133659)
|
| 59 |
+
470 train 6.218535 (lr=1.8840e-04) (hash(x)=158095308)
|
| 60 |
+
480 train 6.087288 (lr=1.9240e-04) (hash(x)=148422063)
|
| 61 |
+
490 train 6.233428 (lr=1.9640e-04) (hash(x)=145665071)
|
| 62 |
+
500 val loss 6.1992
|
| 63 |
+
500 val perplexity 492.3375
|
| 64 |
+
500 train 6.214863 (lr=2.0000e-04) (hash(x)=145450636)
|
| 65 |
+
510 train 6.142928 (lr=2.0000e-04) (hash(x)=148375186)
|
| 66 |
+
520 train 6.186651 (lr=2.0000e-04) (hash(x)=144256573)
|
| 67 |
+
530 train 6.169929 (lr=1.9999e-04) (hash(x)=141443048)
|
| 68 |
+
540 train 6.053875 (lr=1.9999e-04) (hash(x)=149347480)
|
| 69 |
+
550 train 6.136587 (lr=1.9998e-04) (hash(x)=154123388)
|
| 70 |
+
560 train 6.078873 (lr=1.9998e-04) (hash(x)=143045783)
|
| 71 |
+
570 train 5.966445 (lr=1.9997e-04) (hash(x)=157244060)
|
| 72 |
+
580 train 5.967642 (lr=1.9996e-04) (hash(x)=158018166)
|
| 73 |
+
590 train 6.036210 (lr=1.9995e-04) (hash(x)=153794251)
|
| 74 |
+
600 val loss 5.9815
|
| 75 |
+
600 val perplexity 396.0463
|
| 76 |
+
600 train 5.947205 (lr=1.9993e-04) (hash(x)=145249251)
|
| 77 |
+
610 train 5.980606 (lr=1.9992e-04) (hash(x)=150377688)
|
| 78 |
+
620 train 5.930734 (lr=1.9991e-04) (hash(x)=134768519)
|
| 79 |
+
630 train 5.872939 (lr=1.9989e-04) (hash(x)=141559208)
|
| 80 |
+
640 train 5.875177 (lr=1.9987e-04) (hash(x)=148444988)
|
| 81 |
+
650 train 5.866013 (lr=1.9985e-04) (hash(x)=148937127)
|
| 82 |
+
660 train 5.768834 (lr=1.9983e-04) (hash(x)=145121305)
|
| 83 |
+
670 train 5.870611 (lr=1.9981e-04) (hash(x)=156860740)
|
| 84 |
+
680 train 5.684099 (lr=1.9979e-04) (hash(x)=137272598)
|
| 85 |
+
690 train 5.678128 (lr=1.9976e-04) (hash(x)=139021179)
|
| 86 |
+
700 val loss 5.8063
|
| 87 |
+
700 val perplexity 332.3801
|
| 88 |
+
700 train 5.997221 (lr=1.9974e-04) (hash(x)=150475545)
|
| 89 |
+
710 train 5.751516 (lr=1.9971e-04) (hash(x)=148476077)
|
| 90 |
+
720 train 5.666198 (lr=1.9968e-04) (hash(x)=143328717)
|
| 91 |
+
730 train 5.549758 (lr=1.9966e-04) (hash(x)=137342488)
|
| 92 |
+
740 train 5.661616 (lr=1.9962e-04) (hash(x)=149452392)
|
| 93 |
+
750 train 5.652436 (lr=1.9959e-04) (hash(x)=154653428)
|
| 94 |
+
760 train 5.769066 (lr=1.9956e-04) (hash(x)=153305312)
|
| 95 |
+
770 train 5.635132 (lr=1.9952e-04) (hash(x)=153862299)
|
| 96 |
+
780 train 5.631968 (lr=1.9949e-04) (hash(x)=151035519)
|
| 97 |
+
790 train 5.715518 (lr=1.9945e-04) (hash(x)=145990773)
|
| 98 |
+
800 val loss 5.6773
|
| 99 |
+
800 val perplexity 292.1676
|
| 100 |
+
800 train 5.687585 (lr=1.9941e-04) (hash(x)=144483776)
|
| 101 |
+
810 train 5.595492 (lr=1.9937e-04) (hash(x)=142045737)
|
| 102 |
+
820 train 5.735525 (lr=1.9933e-04) (hash(x)=157946886)
|
| 103 |
+
830 train 5.585011 (lr=1.9929e-04) (hash(x)=150425385)
|
| 104 |
+
840 train 5.621552 (lr=1.9925e-04) (hash(x)=144514796)
|
| 105 |
+
850 train 5.654304 (lr=1.9920e-04) (hash(x)=157395496)
|
| 106 |
+
860 train 5.642696 (lr=1.9916e-04) (hash(x)=151365298)
|
| 107 |
+
870 train 5.670675 (lr=1.9911e-04) (hash(x)=151437005)
|
| 108 |
+
880 train 5.575616 (lr=1.9906e-04) (hash(x)=151935250)
|
| 109 |
+
890 train 5.614539 (lr=1.9901e-04) (hash(x)=159838534)
|
| 110 |
+
900 val loss 5.5691
|
| 111 |
+
900 val perplexity 262.2056
|
| 112 |
+
900 train 5.629570 (lr=1.9896e-04) (hash(x)=157916369)
|
| 113 |
+
910 train 5.615073 (lr=1.9891e-04) (hash(x)=165272484)
|
| 114 |
+
920 train 5.455021 (lr=1.9885e-04) (hash(x)=145383083)
|
| 115 |
+
930 train 5.475767 (lr=1.9880e-04) (hash(x)=152078393)
|
| 116 |
+
940 train 5.601940 (lr=1.9874e-04) (hash(x)=151846396)
|
| 117 |
+
950 train 5.529554 (lr=1.9868e-04) (hash(x)=166073923)
|
| 118 |
+
960 train 5.503806 (lr=1.9862e-04) (hash(x)=136782937)
|
| 119 |
+
970 train 5.455806 (lr=1.9856e-04) (hash(x)=146747407)
|
| 120 |
+
980 train 5.512696 (lr=1.9850e-04) (hash(x)=171270168)
|
| 121 |
+
990 train 5.490362 (lr=1.9844e-04) (hash(x)=141668491)
|
| 122 |
+
1000 val loss 5.4922
|
| 123 |
+
1000 val perplexity 242.7847
|
| 124 |
+
1000 train 5.434521 (lr=1.9837e-04) (hash(x)=154856891)
|
| 125 |
+
1010 train 5.449195 (lr=1.9831e-04) (hash(x)=145288527)
|
| 126 |
+
1020 train 5.350771 (lr=1.9824e-04) (hash(x)=144618667)
|
| 127 |
+
1030 train 5.570031 (lr=1.9817e-04) (hash(x)=139276042)
|
| 128 |
+
1040 train 5.262878 (lr=1.9810e-04) (hash(x)=147217952)
|
| 129 |
+
1050 train 5.391931 (lr=1.9803e-04) (hash(x)=151925203)
|
| 130 |
+
1060 train 5.348153 (lr=1.9796e-04) (hash(x)=147473652)
|
| 131 |
+
1070 train 5.316768 (lr=1.9789e-04) (hash(x)=145345524)
|
| 132 |
+
1080 train 5.225784 (lr=1.9781e-04) (hash(x)=155595779)
|
| 133 |
+
1090 train 5.294695 (lr=1.9774e-04) (hash(x)=147405225)
|
| 134 |
+
1100 val loss 5.4074
|
| 135 |
+
1100 val perplexity 223.0456
|
| 136 |
+
1100 train 5.088440 (lr=1.9766e-04) (hash(x)=136191502)
|
| 137 |
+
1110 train 5.299249 (lr=1.9758e-04) (hash(x)=151847694)
|
| 138 |
+
1120 train 5.427071 (lr=1.9750e-04) (hash(x)=144828302)
|
| 139 |
+
1130 train 5.440718 (lr=1.9742e-04) (hash(x)=153817096)
|
| 140 |
+
1140 train 5.517003 (lr=1.9734e-04) (hash(x)=166352243)
|
| 141 |
+
1150 train 5.527533 (lr=1.9726e-04) (hash(x)=153273362)
|
| 142 |
+
1160 train 5.432720 (lr=1.9717e-04) (hash(x)=178082599)
|
| 143 |
+
1170 train 5.190054 (lr=1.9709e-04) (hash(x)=149460553)
|
| 144 |
+
1180 train 5.425666 (lr=1.9700e-04) (hash(x)=151910947)
|
| 145 |
+
1190 train 5.283683 (lr=1.9691e-04) (hash(x)=147115336)
|
| 146 |
+
1200 val loss 5.3325
|
| 147 |
+
1200 val perplexity 206.9522
|
| 148 |
+
1200 train 5.318884 (lr=1.9682e-04) (hash(x)=148021541)
|
| 149 |
+
1210 train 5.229850 (lr=1.9673e-04) (hash(x)=151495989)
|
| 150 |
+
1220 train 5.362013 (lr=1.9664e-04) (hash(x)=156983220)
|
| 151 |
+
1230 train 5.552077 (lr=1.9654e-04) (hash(x)=147788187)
|
| 152 |
+
1240 train 5.387790 (lr=1.9645e-04) (hash(x)=171125590)
|
| 153 |
+
1250 train 5.294948 (lr=1.9635e-04) (hash(x)=141356608)
|
| 154 |
+
1260 train 5.323934 (lr=1.9626e-04) (hash(x)=150132098)
|
| 155 |
+
1270 train 5.239218 (lr=1.9616e-04) (hash(x)=147917245)
|
| 156 |
+
1280 train 5.324166 (lr=1.9606e-04) (hash(x)=148900016)
|
| 157 |
+
1290 train 5.326596 (lr=1.9596e-04) (hash(x)=144978605)
|
| 158 |
+
1300 val loss 5.2617
|
| 159 |
+
1300 val perplexity 192.8019
|
| 160 |
+
1300 train 5.211295 (lr=1.9586e-04) (hash(x)=146005217)
|
| 161 |
+
1310 train 5.246667 (lr=1.9575e-04) (hash(x)=144892309)
|
| 162 |
+
1320 train 5.247231 (lr=1.9565e-04) (hash(x)=165903661)
|
| 163 |
+
1330 train 5.286109 (lr=1.9554e-04) (hash(x)=168489989)
|
| 164 |
+
1340 train 5.411146 (lr=1.9543e-04) (hash(x)=176281294)
|
| 165 |
+
1350 train 5.143373 (lr=1.9533e-04) (hash(x)=144511718)
|
| 166 |
+
1360 train 5.221279 (lr=1.9522e-04) (hash(x)=144362722)
|
| 167 |
+
1370 train 5.099247 (lr=1.9511e-04) (hash(x)=139964999)
|
| 168 |
+
1380 train 5.163990 (lr=1.9499e-04) (hash(x)=193332654)
|
| 169 |
+
1390 train 5.145540 (lr=1.9488e-04) (hash(x)=138180866)
|
| 170 |
+
1400 val loss 5.2146
|
| 171 |
+
1400 val perplexity 183.9324
|
| 172 |
+
1400 train 5.170571 (lr=1.9477e-04) (hash(x)=146019502)
|
| 173 |
+
1410 train 5.261338 (lr=1.9465e-04) (hash(x)=153245388)
|
| 174 |
+
1420 train 5.126568 (lr=1.9453e-04) (hash(x)=149839636)
|
| 175 |
+
1430 train 5.207678 (lr=1.9441e-04) (hash(x)=142844796)
|
| 176 |
+
1440 train 5.501095 (lr=1.9430e-04) (hash(x)=159787060)
|
| 177 |
+
1450 train 5.181979 (lr=1.9417e-04) (hash(x)=146496200)
|
| 178 |
+
1460 train 5.111094 (lr=1.9405e-04) (hash(x)=164169521)
|
| 179 |
+
1470 train 5.136604 (lr=1.9393e-04) (hash(x)=150906386)
|
| 180 |
+
1480 train 5.144449 (lr=1.9381e-04) (hash(x)=148916053)
|
| 181 |
+
1490 train 5.094568 (lr=1.9368e-04) (hash(x)=148746554)
|
| 182 |
+
1500 val loss 5.2017
|
| 183 |
+
1500 val perplexity 181.5760
|
| 184 |
+
1500 train 5.148333 (lr=1.9355e-04) (hash(x)=150127281)
|
| 185 |
+
1510 train 5.366138 (lr=1.9343e-04) (hash(x)=149760530)
|
| 186 |
+
1520 train 5.199327 (lr=1.9330e-04) (hash(x)=144237370)
|
| 187 |
+
1530 train 4.980842 (lr=1.9317e-04) (hash(x)=132692898)
|
| 188 |
+
1540 train 4.950060 (lr=1.9303e-04) (hash(x)=150979737)
|
| 189 |
+
1550 train 5.120465 (lr=1.9290e-04) (hash(x)=142022255)
|
| 190 |
+
1560 train 5.076756 (lr=1.9277e-04) (hash(x)=135769745)
|
| 191 |
+
1570 train 4.964491 (lr=1.9263e-04) (hash(x)=162241131)
|
| 192 |
+
1580 train 5.085033 (lr=1.9250e-04) (hash(x)=166874637)
|
| 193 |
+
1590 train 4.995204 (lr=1.9236e-04) (hash(x)=157401041)
|
| 194 |
+
1600 val loss 5.0976
|
| 195 |
+
1600 val perplexity 163.6229
|
| 196 |
+
1600 train 5.042225 (lr=1.9222e-04) (hash(x)=154120875)
|
| 197 |
+
1610 train 5.040401 (lr=1.9208e-04) (hash(x)=149407490)
|
| 198 |
+
1620 train 4.957605 (lr=1.9194e-04) (hash(x)=144479755)
|
| 199 |
+
1630 train 5.084030 (lr=1.9180e-04) (hash(x)=170907716)
|
| 200 |
+
1640 train 4.739767 (lr=1.9165e-04) (hash(x)=151914010)
|
| 201 |
+
1650 train 4.964855 (lr=1.9151e-04) (hash(x)=149843610)
|
| 202 |
+
1660 train 4.888924 (lr=1.9136e-04) (hash(x)=133217001)
|
| 203 |
+
1670 train 4.878605 (lr=1.9121e-04) (hash(x)=168227774)
|
| 204 |
+
1680 train 4.847594 (lr=1.9107e-04) (hash(x)=157093189)
|
| 205 |
+
1690 train 4.697741 (lr=1.9092e-04) (hash(x)=154989819)
|
| 206 |
+
1700 val loss 5.0617
|
| 207 |
+
1700 val perplexity 157.8595
|
| 208 |
+
1700 train 5.191277 (lr=1.9077e-04) (hash(x)=155797680)
|
| 209 |
+
1710 train 4.933702 (lr=1.9061e-04) (hash(x)=166050772)
|
| 210 |
+
1720 train 4.797922 (lr=1.9046e-04) (hash(x)=151663443)
|
| 211 |
+
1730 train 5.047015 (lr=1.9031e-04) (hash(x)=152112619)
|
| 212 |
+
1740 train 4.969186 (lr=1.9015e-04) (hash(x)=156132679)
|
| 213 |
+
1750 train 4.804039 (lr=1.9000e-04) (hash(x)=149044477)
|
| 214 |
+
1760 train 4.946286 (lr=1.8984e-04) (hash(x)=142924719)
|
| 215 |
+
1770 train 4.901054 (lr=1.8968e-04) (hash(x)=153467406)
|
| 216 |
+
1780 train 4.965936 (lr=1.8952e-04) (hash(x)=148889581)
|
| 217 |
+
1790 train 4.909609 (lr=1.8936e-04) (hash(x)=164831182)
|
| 218 |
+
1800 val loss 4.9933
|
| 219 |
+
1800 val perplexity 147.4198
|
| 220 |
+
1800 train 4.926932 (lr=1.8920e-04) (hash(x)=156809396)
|
| 221 |
+
1810 train 5.048708 (lr=1.8903e-04) (hash(x)=149245741)
|
| 222 |
+
1820 train 4.925602 (lr=1.8887e-04) (hash(x)=146865466)
|
| 223 |
+
1830 train 4.982058 (lr=1.8870e-04) (hash(x)=148068618)
|
| 224 |
+
1840 train 4.868454 (lr=1.8854e-04) (hash(x)=150088183)
|
| 225 |
+
1850 train 4.902516 (lr=1.8837e-04) (hash(x)=146695082)
|
| 226 |
+
1860 train 4.917751 (lr=1.8820e-04) (hash(x)=169008624)
|
| 227 |
+
1870 train 4.801825 (lr=1.8803e-04) (hash(x)=148645124)
|
| 228 |
+
1880 train 4.920990 (lr=1.8786e-04) (hash(x)=139701422)
|
| 229 |
+
1890 train 4.922510 (lr=1.8768e-04) (hash(x)=156374257)
|
| 230 |
+
1900 val loss 4.9479
|
| 231 |
+
1900 val perplexity 140.8855
|
| 232 |
+
1900 train 4.831605 (lr=1.8751e-04) (hash(x)=144640294)
|
| 233 |
+
1910 train 5.001435 (lr=1.8734e-04) (hash(x)=147484985)
|
| 234 |
+
1920 train 4.867589 (lr=1.8716e-04) (hash(x)=142317889)
|
| 235 |
+
1930 train 4.819494 (lr=1.8698e-04) (hash(x)=144906216)
|
| 236 |
+
1940 train 4.923316 (lr=1.8680e-04) (hash(x)=165332621)
|
| 237 |
+
1950 train 4.846935 (lr=1.8663e-04) (hash(x)=145701919)
|
| 238 |
+
1960 train 4.769879 (lr=1.8645e-04) (hash(x)=146414118)
|
| 239 |
+
1970 train 4.954073 (lr=1.8626e-04) (hash(x)=146766958)
|
| 240 |
+
1980 train 4.852221 (lr=1.8608e-04) (hash(x)=148146847)
|
| 241 |
+
1990 train 4.645075 (lr=1.8590e-04) (hash(x)=159684604)
|
| 242 |
+
2000 val loss 4.9172
|
| 243 |
+
2000 val perplexity 136.6220
|
| 244 |
+
2000 train 4.738275 (lr=1.8571e-04) (hash(x)=162831106)
|
| 245 |
+
2010 train 4.750999 (lr=1.8553e-04) (hash(x)=150583346)
|
| 246 |
+
2020 train 4.734468 (lr=1.8534e-04) (hash(x)=142779458)
|
| 247 |
+
2030 train 4.698251 (lr=1.8515e-04) (hash(x)=143755114)
|
| 248 |
+
2040 train 4.621077 (lr=1.8496e-04) (hash(x)=147324095)
|
| 249 |
+
2050 train 4.754095 (lr=1.8477e-04) (hash(x)=141727373)
|
| 250 |
+
2060 train 4.814393 (lr=1.8458e-04) (hash(x)=162053052)
|
| 251 |
+
2070 train 4.853208 (lr=1.8439e-04) (hash(x)=162596975)
|
| 252 |
+
2080 train 4.811847 (lr=1.8420e-04) (hash(x)=161242340)
|
| 253 |
+
2090 train 4.729753 (lr=1.8400e-04) (hash(x)=148583522)
|
| 254 |
+
2100 val loss 4.9048
|
| 255 |
+
2100 val perplexity 134.9424
|
| 256 |
+
2100 train 4.824936 (lr=1.8381e-04) (hash(x)=158239484)
|
| 257 |
+
2110 train 4.718829 (lr=1.8361e-04) (hash(x)=152610058)
|
| 258 |
+
2120 train 4.745886 (lr=1.8341e-04) (hash(x)=146582203)
|
| 259 |
+
2130 train 4.501572 (lr=1.8321e-04) (hash(x)=146686436)
|
| 260 |
+
2140 train 4.904179 (lr=1.8301e-04) (hash(x)=142827295)
|
| 261 |
+
2150 train 4.816408 (lr=1.8281e-04) (hash(x)=150747398)
|
| 262 |
+
2160 train 5.080038 (lr=1.8261e-04) (hash(x)=150777134)
|
| 263 |
+
2170 train 4.763044 (lr=1.8241e-04) (hash(x)=157002856)
|
| 264 |
+
2180 train 4.811253 (lr=1.8220e-04) (hash(x)=150442337)
|
| 265 |
+
2190 train 4.765451 (lr=1.8200e-04) (hash(x)=150799081)
|
| 266 |
+
2200 val loss 4.8247
|
| 267 |
+
2200 val perplexity 124.5457
|
| 268 |
+
2200 train 4.709141 (lr=1.8179e-04) (hash(x)=140504180)
|
| 269 |
+
2210 train 4.812778 (lr=1.8158e-04) (hash(x)=149088475)
|
| 270 |
+
2220 train 4.813722 (lr=1.8138e-04) (hash(x)=155180847)
|
| 271 |
+
2230 train 4.736659 (lr=1.8117e-04) (hash(x)=159347164)
|
| 272 |
+
2240 train 4.879557 (lr=1.8096e-04) (hash(x)=153574288)
|
| 273 |
+
2250 train 4.804108 (lr=1.8074e-04) (hash(x)=142603512)
|
| 274 |
+
2260 train 4.826382 (lr=1.8053e-04) (hash(x)=142953831)
|
| 275 |
+
2270 train 4.717840 (lr=1.8032e-04) (hash(x)=137642681)
|
| 276 |
+
2280 train 4.762791 (lr=1.8010e-04) (hash(x)=158106614)
|
| 277 |
+
2290 train 4.751254 (lr=1.7989e-04) (hash(x)=160787891)
|
| 278 |
+
2300 val loss 4.7812
|
| 279 |
+
2300 val perplexity 119.2487
|
| 280 |
+
2300 train 4.829497 (lr=1.7967e-04) (hash(x)=142234024)
|
| 281 |
+
2310 train 4.740950 (lr=1.7946e-04) (hash(x)=138192210)
|
| 282 |
+
2320 train 4.760793 (lr=1.7924e-04) (hash(x)=147727662)
|
| 283 |
+
2330 train 4.746098 (lr=1.7902e-04) (hash(x)=169324653)
|
| 284 |
+
2340 train 4.788718 (lr=1.7880e-04) (hash(x)=145350355)
|
| 285 |
+
2350 train 4.813288 (lr=1.7858e-04) (hash(x)=156909016)
|
| 286 |
+
2360 train 4.713846 (lr=1.7835e-04) (hash(x)=144559543)
|
| 287 |
+
2370 train 4.677996 (lr=1.7813e-04) (hash(x)=153212312)
|
| 288 |
+
2380 train 4.653701 (lr=1.7791e-04) (hash(x)=131816284)
|
| 289 |
+
2390 train 4.726965 (lr=1.7768e-04) (hash(x)=165818309)
|
| 290 |
+
2400 val loss 4.7544
|
| 291 |
+
2400 val perplexity 116.0940
|
| 292 |
+
2400 train 4.775056 (lr=1.7745e-04) (hash(x)=143091562)
|
| 293 |
+
2410 train 4.666837 (lr=1.7723e-04) (hash(x)=154010697)
|
| 294 |
+
2420 train 4.614624 (lr=1.7700e-04) (hash(x)=144844001)
|
| 295 |
+
2430 train 4.779184 (lr=1.7677e-04) (hash(x)=156389834)
|
| 296 |
+
2440 train 4.503231 (lr=1.7654e-04) (hash(x)=162425919)
|
| 297 |
+
2450 train 4.733906 (lr=1.7631e-04) (hash(x)=154200479)
|
| 298 |
+
2460 train 4.626272 (lr=1.7607e-04) (hash(x)=159066617)
|
| 299 |
+
2470 train 4.467434 (lr=1.7584e-04) (hash(x)=148278058)
|
| 300 |
+
2480 train 4.444224 (lr=1.7561e-04) (hash(x)=165598522)
|
| 301 |
+
2490 train 4.759528 (lr=1.7537e-04) (hash(x)=141306086)
|
| 302 |
+
2500 val loss 4.7653
|
| 303 |
+
2500 val perplexity 117.3720
|
| 304 |
+
2500 train 4.605213 (lr=1.7514e-04) (hash(x)=149857456)
|
| 305 |
+
2510 train 4.579810 (lr=1.7490e-04) (hash(x)=150368907)
|
| 306 |
+
2520 train 4.549736 (lr=1.7466e-04) (hash(x)=153394920)
|
| 307 |
+
2530 train 4.523377 (lr=1.7442e-04) (hash(x)=159740116)
|
| 308 |
+
2540 train 4.667135 (lr=1.7418e-04) (hash(x)=161620367)
|
| 309 |
+
2550 train 4.730655 (lr=1.7394e-04) (hash(x)=147223658)
|
| 310 |
+
2560 train 4.814854 (lr=1.7370e-04) (hash(x)=158146613)
|
| 311 |
+
2570 train 4.720209 (lr=1.7346e-04) (hash(x)=136375336)
|
| 312 |
+
2580 train 4.754598 (lr=1.7321e-04) (hash(x)=149298016)
|
| 313 |
+
2590 train 4.670939 (lr=1.7297e-04) (hash(x)=150720933)
|
| 314 |
+
2600 val loss 4.6914
|
| 315 |
+
2600 val perplexity 109.0005
|
| 316 |
+
2600 train 4.778792 (lr=1.7272e-04) (hash(x)=146191551)
|
| 317 |
+
2610 train 4.616460 (lr=1.7248e-04) (hash(x)=151413395)
|
| 318 |
+
2620 train 4.819472 (lr=1.7223e-04) (hash(x)=162094106)
|
| 319 |
+
2630 train 4.702490 (lr=1.7198e-04) (hash(x)=150608302)
|
| 320 |
+
2640 train 4.574631 (lr=1.7173e-04) (hash(x)=146115160)
|
| 321 |
+
2650 train 4.684813 (lr=1.7148e-04) (hash(x)=138242788)
|
| 322 |
+
2660 train 4.908566 (lr=1.7123e-04) (hash(x)=159921837)
|
| 323 |
+
2670 train 4.504551 (lr=1.7098e-04) (hash(x)=137205989)
|
| 324 |
+
2680 train 4.535458 (lr=1.7073e-04) (hash(x)=158608524)
|
| 325 |
+
2690 train 4.587166 (lr=1.7048e-04) (hash(x)=153322085)
|
| 326 |
+
2700 val loss 4.6600
|
| 327 |
+
2700 val perplexity 105.6352
|
| 328 |
+
2700 train 4.591282 (lr=1.7022e-04) (hash(x)=145375752)
|
| 329 |
+
2710 train 4.599703 (lr=1.6997e-04) (hash(x)=145036398)
|
| 330 |
+
2720 train 4.641655 (lr=1.6971e-04) (hash(x)=140064355)
|
| 331 |
+
2730 train 4.634297 (lr=1.6945e-04) (hash(x)=148983355)
|
| 332 |
+
2740 train 4.551638 (lr=1.6920e-04) (hash(x)=147636026)
|
| 333 |
+
2750 train 4.618248 (lr=1.6894e-04) (hash(x)=151763585)
|
| 334 |
+
2760 train 4.552727 (lr=1.6868e-04) (hash(x)=178033416)
|
| 335 |
+
2770 train 4.506301 (lr=1.6842e-04) (hash(x)=147097669)
|
| 336 |
+
2780 train 4.459331 (lr=1.6816e-04) (hash(x)=140475447)
|
| 337 |
+
2790 train 4.569263 (lr=1.6789e-04) (hash(x)=141135962)
|
| 338 |
+
2800 val loss 4.6456
|
| 339 |
+
2800 val perplexity 104.1223
|
| 340 |
+
2800 train 4.496553 (lr=1.6763e-04) (hash(x)=151568014)
|
| 341 |
+
2810 train 5.160812 (lr=1.6737e-04) (hash(x)=170629615)
|
| 342 |
+
2820 train 4.549790 (lr=1.6710e-04) (hash(x)=151858146)
|
| 343 |
+
2830 train 4.451913 (lr=1.6684e-04) (hash(x)=152170305)
|
| 344 |
+
2840 train 4.387339 (lr=1.6657e-04) (hash(x)=150705881)
|
| 345 |
+
2850 train 4.456629 (lr=1.6631e-04) (hash(x)=146997394)
|
| 346 |
+
2860 train 4.407030 (lr=1.6604e-04) (hash(x)=159749180)
|
| 347 |
+
2870 train 4.303867 (lr=1.6577e-04) (hash(x)=147618423)
|
| 348 |
+
2880 train 4.490003 (lr=1.6550e-04) (hash(x)=140778993)
|
| 349 |
+
2890 train 4.395747 (lr=1.6523e-04) (hash(x)=150735837)
|
| 350 |
+
2900 val loss 4.6339
|
| 351 |
+
2900 val perplexity 102.9121
|
| 352 |
+
2900 train 4.412498 (lr=1.6496e-04) (hash(x)=149366597)
|
| 353 |
+
2910 train 4.557461 (lr=1.6469e-04) (hash(x)=181602500)
|
| 354 |
+
2920 train 4.515381 (lr=1.6441e-04) (hash(x)=148080200)
|
| 355 |
+
2930 train 4.356223 (lr=1.6414e-04) (hash(x)=150629961)
|
| 356 |
+
2940 train 4.520838 (lr=1.6387e-04) (hash(x)=155786888)
|
| 357 |
+
2950 train 4.523497 (lr=1.6359e-04) (hash(x)=148553059)
|
| 358 |
+
2960 train 4.633657 (lr=1.6332e-04) (hash(x)=158494862)
|
| 359 |
+
2970 train 4.743243 (lr=1.6304e-04) (hash(x)=147684099)
|
| 360 |
+
2980 train 4.499400 (lr=1.6276e-04) (hash(x)=159008790)
|
| 361 |
+
2990 train 4.648293 (lr=1.6248e-04) (hash(x)=148288782)
|
| 362 |
+
3000 val loss 4.5884
|
| 363 |
+
3000 val perplexity 98.3382
|
| 364 |
+
3000 train 4.529827 (lr=1.6221e-04) (hash(x)=150464442)
|
| 365 |
+
3010 train 4.597640 (lr=1.6193e-04) (hash(x)=148665916)
|
| 366 |
+
3020 train 4.551066 (lr=1.6165e-04) (hash(x)=159788454)
|
| 367 |
+
3030 train 4.639585 (lr=1.6136e-04) (hash(x)=170224765)
|
| 368 |
+
3040 train 4.488675 (lr=1.6108e-04) (hash(x)=139746299)
|
| 369 |
+
3050 train 4.563065 (lr=1.6080e-04) (hash(x)=173491884)
|
| 370 |
+
3060 train 4.542188 (lr=1.6052e-04) (hash(x)=146098725)
|
| 371 |
+
3070 train 4.516827 (lr=1.6023e-04) (hash(x)=154713525)
|
| 372 |
+
3080 train 4.567209 (lr=1.5995e-04) (hash(x)=151206978)
|
| 373 |
+
3090 train 4.600539 (lr=1.5966e-04) (hash(x)=144250687)
|
| 374 |
+
3100 val loss 4.5911
|
| 375 |
+
3100 val perplexity 98.6010
|
| 376 |
+
3100 train 4.642585 (lr=1.5938e-04) (hash(x)=182449036)
|
| 377 |
+
3110 train 4.432832 (lr=1.5909e-04) (hash(x)=145504538)
|
| 378 |
+
3120 train 4.466027 (lr=1.5880e-04) (hash(x)=147948751)
|
| 379 |
+
3130 train 4.407699 (lr=1.5851e-04) (hash(x)=144547711)
|
| 380 |
+
3140 train 4.552614 (lr=1.5822e-04) (hash(x)=158622029)
|
| 381 |
+
3150 train 4.502462 (lr=1.5793e-04) (hash(x)=155949476)
|
| 382 |
+
3160 train 4.488748 (lr=1.5764e-04) (hash(x)=129245664)
|
| 383 |
+
3170 train 4.519265 (lr=1.5735e-04) (hash(x)=157162959)
|
| 384 |
+
3180 train 4.581204 (lr=1.5706e-04) (hash(x)=163102434)
|
| 385 |
+
3190 train 4.583764 (lr=1.5677e-04) (hash(x)=155952009)
|
| 386 |
+
3200 val loss 4.5658
|
| 387 |
+
3200 val perplexity 96.1440
|
| 388 |
+
3200 train 4.508083 (lr=1.5648e-04) (hash(x)=140141286)
|
| 389 |
+
3210 train 4.488015 (lr=1.5618e-04) (hash(x)=148811694)
|
| 390 |
+
3220 train 4.440585 (lr=1.5589e-04) (hash(x)=143433404)
|
| 391 |
+
3230 train 4.494131 (lr=1.5559e-04) (hash(x)=150525065)
|
| 392 |
+
3240 train 4.415021 (lr=1.5530e-04) (hash(x)=152014854)
|
| 393 |
+
3250 train 4.268109 (lr=1.5500e-04) (hash(x)=144716153)
|
| 394 |
+
3260 train 4.593725 (lr=1.5470e-04) (hash(x)=145324818)
|
| 395 |
+
3270 train 4.542977 (lr=1.5441e-04) (hash(x)=154930419)
|
| 396 |
+
3280 train 4.519682 (lr=1.5411e-04) (hash(x)=144649958)
|
| 397 |
+
3290 train 4.517303 (lr=1.5381e-04) (hash(x)=156496147)
|
| 398 |
+
3300 val loss 4.5475
|
| 399 |
+
3300 val perplexity 94.3956
|
| 400 |
+
3300 train 4.465536 (lr=1.5351e-04) (hash(x)=148099414)
|
| 401 |
+
3310 train 4.538521 (lr=1.5321e-04) (hash(x)=141081470)
|
| 402 |
+
3320 train 4.500180 (lr=1.5291e-04) (hash(x)=151572529)
|
| 403 |
+
3330 train 4.454835 (lr=1.5261e-04) (hash(x)=146887343)
|
| 404 |
+
3340 train 4.489556 (lr=1.5230e-04) (hash(x)=148612634)
|
| 405 |
+
3350 train 4.447524 (lr=1.5200e-04) (hash(x)=145218304)
|
| 406 |
+
3360 train 4.379771 (lr=1.5170e-04) (hash(x)=146893345)
|
| 407 |
+
3370 train 4.467313 (lr=1.5139e-04) (hash(x)=159302018)
|
| 408 |
+
3380 train 4.524377 (lr=1.5109e-04) (hash(x)=164117611)
|
| 409 |
+
3390 train 4.393842 (lr=1.5078e-04) (hash(x)=142401925)
|
| 410 |
+
3400 val loss 4.5303
|
| 411 |
+
3400 val perplexity 92.7899
|
| 412 |
+
3400 train 4.375565 (lr=1.5048e-04) (hash(x)=142633951)
|
| 413 |
+
3410 train 4.503698 (lr=1.5017e-04) (hash(x)=148491904)
|
| 414 |
+
3420 train 4.543382 (lr=1.4986e-04) (hash(x)=144013244)
|
| 415 |
+
3430 train 4.369911 (lr=1.4956e-04) (hash(x)=146939843)
|
| 416 |
+
3440 train 4.392822 (lr=1.4925e-04) (hash(x)=161055964)
|
| 417 |
+
3450 train 4.298733 (lr=1.4894e-04) (hash(x)=134825681)
|
| 418 |
+
3460 train 4.469254 (lr=1.4863e-04) (hash(x)=145087511)
|
| 419 |
+
3470 train 4.287777 (lr=1.4832e-04) (hash(x)=144200286)
|
| 420 |
+
3480 train 4.351079 (lr=1.4801e-04) (hash(x)=157605428)
|
| 421 |
+
3490 train 4.521192 (lr=1.4770e-04) (hash(x)=153636990)
|
| 422 |
+
3500 val loss 4.5270
|
| 423 |
+
3500 val perplexity 92.4793
|
| 424 |
+
3500 train 4.377568 (lr=1.4739e-04) (hash(x)=148368965)
|
| 425 |
+
3510 train 4.266108 (lr=1.4708e-04) (hash(x)=144775557)
|
| 426 |
+
3520 train 4.448303 (lr=1.4676e-04) (hash(x)=151539855)
|
| 427 |
+
3530 train 4.481318 (lr=1.4645e-04) (hash(x)=168384321)
|
| 428 |
+
3540 train 4.620030 (lr=1.4614e-04) (hash(x)=155671447)
|
| 429 |
+
3550 train 4.641882 (lr=1.4582e-04) (hash(x)=157403334)
|
| 430 |
+
3560 train 4.404396 (lr=1.4551e-04) (hash(x)=139495714)
|
| 431 |
+
3570 train 4.561201 (lr=1.4519e-04) (hash(x)=147685555)
|
| 432 |
+
3580 train 4.676671 (lr=1.4488e-04) (hash(x)=154209753)
|
| 433 |
+
3590 train 4.321961 (lr=1.4456e-04) (hash(x)=166864372)
|
| 434 |
+
3600 val loss 4.5037
|
| 435 |
+
3600 val perplexity 90.3527
|
| 436 |
+
3600 train 4.424910 (lr=1.4424e-04) (hash(x)=152372067)
|
| 437 |
+
3610 train 4.668788 (lr=1.4393e-04) (hash(x)=156579291)
|
| 438 |
+
3620 train 4.273847 (lr=1.4361e-04) (hash(x)=152969451)
|
| 439 |
+
3630 train 4.251420 (lr=1.4329e-04) (hash(x)=164428105)
|
| 440 |
+
3640 train 4.437449 (lr=1.4297e-04) (hash(x)=153325907)
|
| 441 |
+
3650 train 4.398088 (lr=1.4265e-04) (hash(x)=159197101)
|
| 442 |
+
3660 train 4.380780 (lr=1.4233e-04) (hash(x)=157503290)
|
| 443 |
+
3670 train 4.308009 (lr=1.4201e-04) (hash(x)=149036650)
|
| 444 |
+
3680 train 4.307835 (lr=1.4169e-04) (hash(x)=144525088)
|
| 445 |
+
3690 train 4.427937 (lr=1.4137e-04) (hash(x)=143154211)
|
| 446 |
+
3700 val loss 4.4952
|
| 447 |
+
3700 val perplexity 89.5846
|
| 448 |
+
3700 train 4.435429 (lr=1.4105e-04) (hash(x)=168885609)
|
| 449 |
+
3710 train 4.377898 (lr=1.4073e-04) (hash(x)=148815644)
|
| 450 |
+
3720 train 4.312550 (lr=1.4041e-04) (hash(x)=153279629)
|
| 451 |
+
3730 train 4.327567 (lr=1.4008e-04) (hash(x)=148181200)
|
| 452 |
+
3740 train 4.290925 (lr=1.3976e-04) (hash(x)=151357364)
|
| 453 |
+
3750 train 4.263413 (lr=1.3944e-04) (hash(x)=145269246)
|
| 454 |
+
3760 train 4.349578 (lr=1.3911e-04) (hash(x)=148923398)
|
| 455 |
+
3770 train 4.351328 (lr=1.3879e-04) (hash(x)=141205226)
|
| 456 |
+
3780 train 4.228529 (lr=1.3846e-04) (hash(x)=146180296)
|
| 457 |
+
3790 train 4.312975 (lr=1.3814e-04) (hash(x)=169790000)
|
| 458 |
+
3800 val loss 4.4879
|
| 459 |
+
3800 val perplexity 88.9316
|
| 460 |
+
3800 train 4.338605 (lr=1.3781e-04) (hash(x)=141633734)
|
| 461 |
+
3810 train 4.479588 (lr=1.3749e-04) (hash(x)=156306070)
|
| 462 |
+
3820 train 4.473075 (lr=1.3716e-04) (hash(x)=158769870)
|
| 463 |
+
3830 train 4.441172 (lr=1.3683e-04) (hash(x)=165301927)
|
| 464 |
+
3840 train 4.468076 (lr=1.3650e-04) (hash(x)=147025475)
|
| 465 |
+
3850 train 4.395224 (lr=1.3618e-04) (hash(x)=141223580)
|
| 466 |
+
3860 train 4.391093 (lr=1.3585e-04) (hash(x)=139668795)
|
| 467 |
+
3870 train 4.491822 (lr=1.3552e-04) (hash(x)=155839599)
|
| 468 |
+
3880 train 4.547165 (lr=1.3519e-04) (hash(x)=150635541)
|
| 469 |
+
3890 train 4.553460 (lr=1.3486e-04) (hash(x)=153702524)
|
| 470 |
+
3900 val loss 4.4667
|
| 471 |
+
3900 val perplexity 87.0676
|
| 472 |
+
3900 train 4.362882 (lr=1.3453e-04) (hash(x)=153141007)
|
| 473 |
+
3910 train 4.434646 (lr=1.3420e-04) (hash(x)=145483115)
|
| 474 |
+
3920 train 4.242191 (lr=1.3387e-04) (hash(x)=147480523)
|
| 475 |
+
3930 train 4.414628 (lr=1.3354e-04) (hash(x)=146229467)
|
| 476 |
+
3940 train 4.395383 (lr=1.3321e-04) (hash(x)=151376187)
|
| 477 |
+
3950 train 4.375435 (lr=1.3288e-04) (hash(x)=153745186)
|
| 478 |
+
3960 train 4.328387 (lr=1.3255e-04) (hash(x)=147595615)
|
| 479 |
+
3970 train 4.457239 (lr=1.3222e-04) (hash(x)=157979848)
|
| 480 |
+
3980 train 4.318165 (lr=1.3188e-04) (hash(x)=153714091)
|
| 481 |
+
3990 train 4.356363 (lr=1.3155e-04) (hash(x)=155637629)
|
| 482 |
+
4000 val loss 4.4596
|
| 483 |
+
4000 val perplexity 86.4571
|
| 484 |
+
4000 train 4.382516 (lr=1.3122e-04) (hash(x)=160577202)
|
| 485 |
+
4010 train 4.290060 (lr=1.3089e-04) (hash(x)=147432640)
|
| 486 |
+
4020 train 4.239993 (lr=1.3055e-04) (hash(x)=135542902)
|
| 487 |
+
4030 train 4.387903 (lr=1.3022e-04) (hash(x)=143137909)
|
| 488 |
+
4040 train 4.380359 (lr=1.2988e-04) (hash(x)=148269908)
|
| 489 |
+
4050 train 4.274552 (lr=1.2955e-04) (hash(x)=141954182)
|
| 490 |
+
4060 train 4.361626 (lr=1.2921e-04) (hash(x)=157035179)
|
| 491 |
+
4070 train 4.079983 (lr=1.2888e-04) (hash(x)=151361423)
|
| 492 |
+
4080 train 4.201018 (lr=1.2854e-04) (hash(x)=144373988)
|
| 493 |
+
4090 train 4.417612 (lr=1.2821e-04) (hash(x)=156461428)
|
| 494 |
+
4100 val loss 4.4503
|
| 495 |
+
4100 val perplexity 85.6567
|
| 496 |
+
4100 train 4.530666 (lr=1.2787e-04) (hash(x)=153858169)
|
| 497 |
+
4110 train 4.500566 (lr=1.2754e-04) (hash(x)=165506959)
|
| 498 |
+
4120 train 4.504848 (lr=1.2720e-04) (hash(x)=158709009)
|
| 499 |
+
4130 train 4.580986 (lr=1.2686e-04) (hash(x)=151836522)
|
| 500 |
+
4140 train 4.357361 (lr=1.2653e-04) (hash(x)=152917389)
|
| 501 |
+
4150 train 4.386983 (lr=1.2619e-04) (hash(x)=146973868)
|
| 502 |
+
4160 train 4.496432 (lr=1.2585e-04) (hash(x)=157875887)
|
| 503 |
+
4170 train 4.742476 (lr=1.2552e-04) (hash(x)=167933111)
|
| 504 |
+
4180 train 4.375991 (lr=1.2518e-04) (hash(x)=161938168)
|
| 505 |
+
4190 train 4.345077 (lr=1.2484e-04) (hash(x)=158102630)
|
| 506 |
+
4200 val loss 4.4341
|
| 507 |
+
4200 val perplexity 84.2766
|
| 508 |
+
4200 train 4.449669 (lr=1.2450e-04) (hash(x)=155889149)
|
| 509 |
+
4210 train 4.521132 (lr=1.2416e-04) (hash(x)=131046288)
|
| 510 |
+
4220 train 4.282924 (lr=1.2383e-04) (hash(x)=149423408)
|
| 511 |
+
4230 train 4.382806 (lr=1.2349e-04) (hash(x)=150033580)
|
| 512 |
+
4240 train 4.280843 (lr=1.2315e-04) (hash(x)=137509644)
|
| 513 |
+
4250 train 4.445551 (lr=1.2281e-04) (hash(x)=161159362)
|
| 514 |
+
4260 train 4.352830 (lr=1.2247e-04) (hash(x)=148117355)
|
| 515 |
+
4270 train 4.281821 (lr=1.2213e-04) (hash(x)=147315384)
|
| 516 |
+
4280 train 4.344691 (lr=1.2179e-04) (hash(x)=156577316)
|
| 517 |
+
4290 train 4.518243 (lr=1.2145e-04) (hash(x)=161553761)
|
| 518 |
+
4300 val loss 4.4260
|
| 519 |
+
4300 val perplexity 83.5934
|
| 520 |
+
4300 train 4.186801 (lr=1.2111e-04) (hash(x)=152294662)
|
| 521 |
+
4310 train 4.212661 (lr=1.2077e-04) (hash(x)=144616611)
|
| 522 |
+
4320 train 4.355005 (lr=1.2043e-04) (hash(x)=154134591)
|
| 523 |
+
4330 train 4.227376 (lr=1.2009e-04) (hash(x)=159947834)
|
| 524 |
+
4340 train 4.215275 (lr=1.1975e-04) (hash(x)=156261313)
|
| 525 |
+
4350 train 4.319102 (lr=1.1941e-04) (hash(x)=141245643)
|
| 526 |
+
4360 train 4.286971 (lr=1.1907e-04) (hash(x)=157291204)
|
| 527 |
+
4370 train 4.312543 (lr=1.1873e-04) (hash(x)=142877676)
|
| 528 |
+
4380 train 4.360546 (lr=1.1838e-04) (hash(x)=155174402)
|
| 529 |
+
4390 train 4.218593 (lr=1.1804e-04) (hash(x)=154675451)
|
| 530 |
+
4400 val loss 4.4208
|
| 531 |
+
4400 val perplexity 83.1620
|
| 532 |
+
4400 train 4.376889 (lr=1.1770e-04) (hash(x)=141804386)
|
| 533 |
+
4410 train 4.593949 (lr=1.1736e-04) (hash(x)=163930619)
|
| 534 |
+
4420 train 4.471976 (lr=1.1702e-04) (hash(x)=139437472)
|
| 535 |
+
4430 train 4.396026 (lr=1.1668e-04) (hash(x)=142474831)
|
| 536 |
+
4440 train 4.431621 (lr=1.1634e-04) (hash(x)=150102428)
|
| 537 |
+
4450 train 4.400961 (lr=1.1599e-04) (hash(x)=135805460)
|
| 538 |
+
4460 train 4.354246 (lr=1.1565e-04) (hash(x)=154732100)
|
| 539 |
+
4470 train 4.366503 (lr=1.1531e-04) (hash(x)=148554435)
|
| 540 |
+
4480 train 4.305525 (lr=1.1497e-04) (hash(x)=142410065)
|
| 541 |
+
4490 train 4.344002 (lr=1.1462e-04) (hash(x)=148108338)
|
| 542 |
+
4500 val loss 4.4016
|
| 543 |
+
4500 val perplexity 81.5842
|
| 544 |
+
4500 train 4.241544 (lr=1.1428e-04) (hash(x)=151095242)
|
| 545 |
+
4510 train 4.255592 (lr=1.1394e-04) (hash(x)=154911617)
|
| 546 |
+
4520 train 4.286982 (lr=1.1360e-04) (hash(x)=150858662)
|
| 547 |
+
4530 train 4.244315 (lr=1.1326e-04) (hash(x)=146850830)
|
| 548 |
+
4540 train 4.300093 (lr=1.1291e-04) (hash(x)=153506103)
|
| 549 |
+
4550 train 4.320744 (lr=1.1257e-04) (hash(x)=157068400)
|
| 550 |
+
4560 train 4.401394 (lr=1.1223e-04) (hash(x)=163640327)
|
| 551 |
+
4570 train 4.449715 (lr=1.1188e-04) (hash(x)=158962962)
|
| 552 |
+
4580 train 4.299818 (lr=1.1154e-04) (hash(x)=143454481)
|
| 553 |
+
4590 train 4.314882 (lr=1.1120e-04) (hash(x)=155380269)
|
| 554 |
+
4600 val loss 4.4230
|
| 555 |
+
4600 val perplexity 83.3462
|
| 556 |
+
4600 train 4.438488 (lr=1.1086e-04) (hash(x)=156414699)
|
| 557 |
+
4610 train 4.287294 (lr=1.1051e-04) (hash(x)=153520595)
|
| 558 |
+
4620 train 4.293586 (lr=1.1017e-04) (hash(x)=151287061)
|
| 559 |
+
4630 train 4.119936 (lr=1.0983e-04) (hash(x)=144972877)
|
| 560 |
+
4640 train 4.253728 (lr=1.0949e-04) (hash(x)=152031134)
|
| 561 |
+
4650 train 4.403440 (lr=1.0914e-04) (hash(x)=155348609)
|
| 562 |
+
4660 train 4.176124 (lr=1.0880e-04) (hash(x)=144855343)
|
| 563 |
+
4670 train 4.341481 (lr=1.0846e-04) (hash(x)=159247995)
|
| 564 |
+
4680 train 4.217478 (lr=1.0812e-04) (hash(x)=133146878)
|
| 565 |
+
4690 train 4.440002 (lr=1.0777e-04) (hash(x)=148797338)
|
| 566 |
+
4700 val loss 4.3902
|
| 567 |
+
4700 val perplexity 80.6551
|
| 568 |
+
4700 train 4.350540 (lr=1.0743e-04) (hash(x)=161556686)
|
| 569 |
+
4710 train 4.526335 (lr=1.0709e-04) (hash(x)=142528636)
|
| 570 |
+
4720 train 4.455257 (lr=1.0674e-04) (hash(x)=148322603)
|
| 571 |
+
4730 train 4.387408 (lr=1.0640e-04) (hash(x)=145051555)
|
| 572 |
+
4740 train 4.299163 (lr=1.0606e-04) (hash(x)=146193153)
|
| 573 |
+
4750 train 4.497538 (lr=1.0572e-04) (hash(x)=165802167)
|
| 574 |
+
4760 train 4.434232 (lr=1.0538e-04) (hash(x)=158948628)
|
| 575 |
+
4770 train 4.480371 (lr=1.0503e-04) (hash(x)=156177788)
|
| 576 |
+
4780 train 4.324424 (lr=1.0469e-04) (hash(x)=175446069)
|
| 577 |
+
4790 train 4.352595 (lr=1.0435e-04) (hash(x)=141100706)
|
| 578 |
+
4800 val loss 4.3843
|
| 579 |
+
4800 val perplexity 80.1789
|
| 580 |
+
4800 train 4.266932 (lr=1.0401e-04) (hash(x)=149000293)
|
| 581 |
+
4810 train 4.195770 (lr=1.0366e-04) (hash(x)=135891778)
|
| 582 |
+
4820 train 4.250564 (lr=1.0332e-04) (hash(x)=145474733)
|
| 583 |
+
4830 train 4.313738 (lr=1.0298e-04) (hash(x)=145187742)
|
| 584 |
+
4840 train 4.361818 (lr=1.0264e-04) (hash(x)=157685237)
|
| 585 |
+
4850 train 4.176809 (lr=1.0230e-04) (hash(x)=128599506)
|
| 586 |
+
4860 train 4.276623 (lr=1.0196e-04) (hash(x)=142067051)
|
| 587 |
+
4870 train 4.233524 (lr=1.0162e-04) (hash(x)=156215711)
|
| 588 |
+
4880 train 4.439707 (lr=1.0127e-04) (hash(x)=150456895)
|
| 589 |
+
4890 train 4.055364 (lr=1.0093e-04) (hash(x)=141647202)
|
| 590 |
+
4900 val loss 4.3750
|
| 591 |
+
4900 val perplexity 79.4364
|
| 592 |
+
4900 train 4.114244 (lr=1.0059e-04) (hash(x)=154349989)
|
| 593 |
+
4910 train 4.146536 (lr=1.0025e-04) (hash(x)=151563396)
|
| 594 |
+
4920 train 4.162678 (lr=9.9911e-05) (hash(x)=138868314)
|
| 595 |
+
4930 train 4.303694 (lr=9.9571e-05) (hash(x)=148533460)
|
| 596 |
+
4940 train 4.283459 (lr=9.9230e-05) (hash(x)=144892493)
|
| 597 |
+
4950 train 4.315923 (lr=9.8890e-05) (hash(x)=170326431)
|
| 598 |
+
4960 train 4.331150 (lr=9.8550e-05) (hash(x)=163312680)
|
| 599 |
+
4970 train 4.292846 (lr=9.8210e-05) (hash(x)=184352734)
|
| 600 |
+
4980 train 4.353080 (lr=9.7870e-05) (hash(x)=140363733)
|
| 601 |
+
4990 train 4.256046 (lr=9.7531e-05) (hash(x)=147794873)
|
| 602 |
+
5000 val loss 4.3665
|
| 603 |
+
5000 val perplexity 78.7687
|
| 604 |
+
5000 train 4.329332 (lr=9.7192e-05) (hash(x)=131475967)
|
| 605 |
+
5010 train 4.447375 (lr=9.6853e-05) (hash(x)=139560000)
|
| 606 |
+
5020 train 4.353000 (lr=9.6514e-05) (hash(x)=160128701)
|
| 607 |
+
5030 train 4.479330 (lr=9.6175e-05) (hash(x)=154698531)
|
| 608 |
+
5040 train 4.424429 (lr=9.5836e-05) (hash(x)=153833791)
|
| 609 |
+
5050 train 4.353383 (lr=9.5498e-05) (hash(x)=145953388)
|
| 610 |
+
5060 train 4.675714 (lr=9.5160e-05) (hash(x)=134297881)
|
| 611 |
+
5070 train 4.351737 (lr=9.4822e-05) (hash(x)=159987550)
|
| 612 |
+
5080 train 4.346187 (lr=9.4484e-05) (hash(x)=147699302)
|
| 613 |
+
5090 train 4.053625 (lr=9.4147e-05) (hash(x)=140534876)
|
| 614 |
+
5100 val loss 4.3604
|
| 615 |
+
5100 val perplexity 78.2883
|
| 616 |
+
5100 train 4.271592 (lr=9.3809e-05) (hash(x)=149717902)
|
| 617 |
+
5110 train 4.199753 (lr=9.3472e-05) (hash(x)=147648148)
|
| 618 |
+
5120 train 4.204808 (lr=9.3136e-05) (hash(x)=170962791)
|
| 619 |
+
5130 train 4.262938 (lr=9.2799e-05) (hash(x)=139633288)
|
| 620 |
+
5140 train 4.425567 (lr=9.2463e-05) (hash(x)=160163221)
|
| 621 |
+
5150 train 4.258599 (lr=9.2127e-05) (hash(x)=146625393)
|
| 622 |
+
5160 train 4.316090 (lr=9.1791e-05) (hash(x)=147399092)
|
| 623 |
+
5170 train 4.145160 (lr=9.1456e-05) (hash(x)=147172792)
|
| 624 |
+
5180 train 4.254137 (lr=9.1120e-05) (hash(x)=140600568)
|
| 625 |
+
5190 train 4.188149 (lr=9.0785e-05) (hash(x)=152423962)
|
| 626 |
+
5200 val loss 4.3585
|
| 627 |
+
5200 val perplexity 78.1364
|
| 628 |
+
5200 train 4.281057 (lr=9.0451e-05) (hash(x)=151407999)
|
| 629 |
+
5210 train 4.237440 (lr=9.0116e-05) (hash(x)=154874903)
|
| 630 |
+
5220 train 4.064445 (lr=8.9782e-05) (hash(x)=154133697)
|
| 631 |
+
5230 train 4.256553 (lr=8.9448e-05) (hash(x)=148148721)
|
| 632 |
+
5240 train 4.217537 (lr=8.9115e-05) (hash(x)=149681665)
|
| 633 |
+
5250 train 4.181986 (lr=8.8782e-05) (hash(x)=150136904)
|
| 634 |
+
5260 train 4.294079 (lr=8.8449e-05) (hash(x)=149261170)
|
| 635 |
+
5270 train 4.282716 (lr=8.8116e-05) (hash(x)=155540595)
|
| 636 |
+
5280 train 4.294362 (lr=8.7784e-05) (hash(x)=141973714)
|
| 637 |
+
5290 train 4.713636 (lr=8.7452e-05) (hash(x)=146827439)
|
| 638 |
+
5300 val loss 4.3474
|
| 639 |
+
5300 val perplexity 77.2795
|
| 640 |
+
5300 train 4.307263 (lr=8.7120e-05) (hash(x)=168602728)
|
| 641 |
+
5310 train 4.285343 (lr=8.6789e-05) (hash(x)=144035757)
|
| 642 |
+
5320 train 4.352224 (lr=8.6458e-05) (hash(x)=143287560)
|
| 643 |
+
5330 train 4.296372 (lr=8.6127e-05) (hash(x)=142461814)
|
| 644 |
+
5340 train 4.317139 (lr=8.5797e-05) (hash(x)=149905536)
|
| 645 |
+
5350 train 4.410029 (lr=8.5467e-05) (hash(x)=134597061)
|
| 646 |
+
5360 train 4.455861 (lr=8.5138e-05) (hash(x)=156520228)
|
| 647 |
+
5370 train 4.342811 (lr=8.4809e-05) (hash(x)=152690323)
|
| 648 |
+
5380 train 4.287538 (lr=8.4480e-05) (hash(x)=140092622)
|
| 649 |
+
5390 train 4.258121 (lr=8.4151e-05) (hash(x)=153504017)
|
| 650 |
+
5400 val loss 4.3346
|
| 651 |
+
5400 val perplexity 76.2978
|
| 652 |
+
5400 train 4.286188 (lr=8.3823e-05) (hash(x)=158344511)
|
| 653 |
+
5410 train 4.200195 (lr=8.3495e-05) (hash(x)=149681960)
|
| 654 |
+
5420 train 4.251153 (lr=8.3168e-05) (hash(x)=143459968)
|
| 655 |
+
5430 train 4.172085 (lr=8.2841e-05) (hash(x)=134759020)
|
| 656 |
+
5440 train 4.164204 (lr=8.2515e-05) (hash(x)=164760471)
|
| 657 |
+
5450 train 4.213181 (lr=8.2188e-05) (hash(x)=148551310)
|
| 658 |
+
5460 train 4.343667 (lr=8.1863e-05) (hash(x)=155464239)
|
| 659 |
+
5470 train 4.161403 (lr=8.1537e-05) (hash(x)=147309485)
|
| 660 |
+
5480 train 4.116476 (lr=8.1212e-05) (hash(x)=163937590)
|
| 661 |
+
5490 train 4.375223 (lr=8.0888e-05) (hash(x)=142830147)
|
| 662 |
+
5500 val loss 4.3310
|
| 663 |
+
5500 val perplexity 76.0234
|
| 664 |
+
5500 train 4.241357 (lr=8.0564e-05) (hash(x)=148350057)
|
| 665 |
+
5510 train 4.194294 (lr=8.0240e-05) (hash(x)=149007838)
|
| 666 |
+
5520 train 4.163612 (lr=7.9917e-05) (hash(x)=158176239)
|
| 667 |
+
5530 train 4.294765 (lr=7.9594e-05) (hash(x)=156395740)
|
| 668 |
+
5540 train 4.431059 (lr=7.9272e-05) (hash(x)=152453211)
|
| 669 |
+
5550 train 4.133646 (lr=7.8950e-05) (hash(x)=144447218)
|
| 670 |
+
5560 train 4.324423 (lr=7.8629e-05) (hash(x)=153858804)
|
| 671 |
+
5570 train 4.156987 (lr=7.8308e-05) (hash(x)=133929681)
|
| 672 |
+
5580 train 4.419901 (lr=7.7987e-05) (hash(x)=159170988)
|
| 673 |
+
5590 train 4.347997 (lr=7.7667e-05) (hash(x)=144978886)
|
| 674 |
+
5600 val loss 4.3231
|
| 675 |
+
5600 val perplexity 75.4191
|
| 676 |
+
5600 train 4.365823 (lr=7.7347e-05) (hash(x)=153847323)
|
| 677 |
+
5610 train 4.313200 (lr=7.7028e-05) (hash(x)=145553636)
|
| 678 |
+
5620 train 5.422201 (lr=7.6710e-05) (hash(x)=153712417)
|
| 679 |
+
5630 train 4.340506 (lr=7.6391e-05) (hash(x)=148397520)
|
| 680 |
+
5640 train 4.277450 (lr=7.6074e-05) (hash(x)=149424351)
|
| 681 |
+
5650 train 4.373177 (lr=7.5756e-05) (hash(x)=140531069)
|
| 682 |
+
5660 train 4.307762 (lr=7.5440e-05) (hash(x)=144904009)
|
| 683 |
+
5670 train 4.176829 (lr=7.5124e-05) (hash(x)=162469666)
|
| 684 |
+
5680 train 4.290189 (lr=7.4808e-05) (hash(x)=149254569)
|
| 685 |
+
5690 train 4.214894 (lr=7.4493e-05) (hash(x)=146949494)
|
| 686 |
+
5700 val loss 4.3171
|
| 687 |
+
5700 val perplexity 74.9727
|
| 688 |
+
5700 train 4.268072 (lr=7.4178e-05) (hash(x)=156607405)
|
| 689 |
+
5710 train 4.129677 (lr=7.3864e-05) (hash(x)=146349425)
|
| 690 |
+
5720 train 4.291361 (lr=7.3550e-05) (hash(x)=160347239)
|
| 691 |
+
5730 train 4.213557 (lr=7.3237e-05) (hash(x)=153785045)
|
| 692 |
+
5740 train 4.227172 (lr=7.2925e-05) (hash(x)=135967367)
|
| 693 |
+
5750 train 4.189945 (lr=7.2613e-05) (hash(x)=140181987)
|
| 694 |
+
5760 train 4.345820 (lr=7.2301e-05) (hash(x)=153217075)
|
| 695 |
+
5770 train 4.210167 (lr=7.1990e-05) (hash(x)=146360100)
|
| 696 |
+
5780 train 4.234823 (lr=7.1680e-05) (hash(x)=161111351)
|
| 697 |
+
5790 train 4.188477 (lr=7.1370e-05) (hash(x)=147891055)
|
| 698 |
+
5800 val loss 4.3141
|
| 699 |
+
5800 val perplexity 74.7453
|
| 700 |
+
5800 train 4.046721 (lr=7.1061e-05) (hash(x)=145115031)
|
| 701 |
+
5810 train 4.088463 (lr=7.0752e-05) (hash(x)=153661465)
|
| 702 |
+
5820 train 4.171758 (lr=7.0444e-05) (hash(x)=148264581)
|
| 703 |
+
5830 train 4.308817 (lr=7.0136e-05) (hash(x)=171144748)
|
| 704 |
+
5840 train 4.222538 (lr=6.9829e-05) (hash(x)=157863238)
|
| 705 |
+
5850 train 4.152556 (lr=6.9523e-05) (hash(x)=144669655)
|
| 706 |
+
5860 train 4.062222 (lr=6.9217e-05) (hash(x)=154948909)
|
| 707 |
+
5870 train 4.230974 (lr=6.8912e-05) (hash(x)=158981837)
|
| 708 |
+
5880 train 4.268141 (lr=6.8607e-05) (hash(x)=151102851)
|
| 709 |
+
5890 train 4.473804 (lr=6.8303e-05) (hash(x)=153490628)
|
| 710 |
+
5900 val loss 4.3051
|
| 711 |
+
5900 val perplexity 74.0780
|
| 712 |
+
5900 train 4.257727 (lr=6.8000e-05) (hash(x)=141584622)
|
| 713 |
+
5910 train 4.146469 (lr=6.7697e-05) (hash(x)=142896324)
|
| 714 |
+
5920 train 4.434845 (lr=6.7395e-05) (hash(x)=148264764)
|
| 715 |
+
5930 train 4.304631 (lr=6.7093e-05) (hash(x)=153157848)
|
| 716 |
+
5940 train 4.285012 (lr=6.6792e-05) (hash(x)=151086429)
|
| 717 |
+
5950 train 4.254316 (lr=6.6492e-05) (hash(x)=146009598)
|
| 718 |
+
5960 train 4.373035 (lr=6.6192e-05) (hash(x)=149488374)
|
| 719 |
+
5970 train 4.191684 (lr=6.5893e-05) (hash(x)=149307478)
|
| 720 |
+
5980 train 3.968511 (lr=6.5595e-05) (hash(x)=156742339)
|
| 721 |
+
5990 train 4.237554 (lr=6.5297e-05) (hash(x)=164296391)
|
| 722 |
+
6000 val loss 4.2998
|
| 723 |
+
6000 val perplexity 73.6864
|
| 724 |
+
6000 train 4.321777 (lr=6.5000e-05) (hash(x)=146613857)
|
| 725 |
+
6010 train 4.194132 (lr=6.4704e-05) (hash(x)=149742104)
|
| 726 |
+
6020 train 4.141329 (lr=6.4408e-05) (hash(x)=145645994)
|
| 727 |
+
6030 train 4.225548 (lr=6.4113e-05) (hash(x)=156324150)
|
| 728 |
+
6040 train 4.405778 (lr=6.3818e-05) (hash(x)=154655300)
|
| 729 |
+
6050 train 4.267885 (lr=6.3524e-05) (hash(x)=153714860)
|
| 730 |
+
6060 train 4.207855 (lr=6.3231e-05) (hash(x)=139981556)
|
| 731 |
+
6070 train 4.042480 (lr=6.2939e-05) (hash(x)=158753458)
|
| 732 |
+
6080 train 4.204513 (lr=6.2647e-05) (hash(x)=152559930)
|
| 733 |
+
6090 train 4.186002 (lr=6.2356e-05) (hash(x)=137128715)
|
| 734 |
+
6100 val loss 4.2985
|
| 735 |
+
6100 val perplexity 73.5868
|
| 736 |
+
6100 train 4.209692 (lr=6.2065e-05) (hash(x)=144621768)
|
| 737 |
+
6110 train 4.206194 (lr=6.1776e-05) (hash(x)=155614333)
|
| 738 |
+
6120 train 4.178743 (lr=6.1487e-05) (hash(x)=145682343)
|
| 739 |
+
6130 train 4.096683 (lr=6.1198e-05) (hash(x)=142909600)
|
| 740 |
+
6140 train 4.124542 (lr=6.0911e-05) (hash(x)=152993494)
|
| 741 |
+
6150 train 4.016838 (lr=6.0624e-05) (hash(x)=157151527)
|
| 742 |
+
6160 train 4.172402 (lr=6.0338e-05) (hash(x)=150653611)
|
| 743 |
+
6170 train 4.416188 (lr=6.0052e-05) (hash(x)=165237934)
|
| 744 |
+
6180 train 4.260923 (lr=5.9767e-05) (hash(x)=155730197)
|
| 745 |
+
6190 train 4.274584 (lr=5.9483e-05) (hash(x)=149687169)
|
| 746 |
+
6200 val loss 4.2964
|
| 747 |
+
6200 val perplexity 73.4338
|
| 748 |
+
6200 train 4.281773 (lr=5.9200e-05) (hash(x)=146521760)
|
| 749 |
+
6210 train 4.274331 (lr=5.8918e-05) (hash(x)=141008090)
|
| 750 |
+
6220 train 4.251613 (lr=5.8636e-05) (hash(x)=143407095)
|
| 751 |
+
6230 train 4.384538 (lr=5.8355e-05) (hash(x)=152947604)
|
| 752 |
+
6240 train 4.696904 (lr=5.8074e-05) (hash(x)=153876740)
|
| 753 |
+
6250 train 4.328625 (lr=5.7795e-05) (hash(x)=144250615)
|
| 754 |
+
6260 train 4.331225 (lr=5.7516e-05) (hash(x)=155236959)
|
| 755 |
+
6270 train 4.276639 (lr=5.7238e-05) (hash(x)=139785369)
|
| 756 |
+
6280 train 4.232081 (lr=5.6961e-05) (hash(x)=165036565)
|
| 757 |
+
6290 train 4.232760 (lr=5.6684e-05) (hash(x)=144585028)
|
| 758 |
+
6300 val loss 4.2847
|
| 759 |
+
6300 val perplexity 72.5785
|
| 760 |
+
6300 train 4.109934 (lr=5.6409e-05) (hash(x)=161378136)
|
| 761 |
+
6310 train 4.156933 (lr=5.6134e-05) (hash(x)=148483421)
|
| 762 |
+
6320 train 4.205138 (lr=5.5859e-05) (hash(x)=149835040)
|
| 763 |
+
6330 train 4.117356 (lr=5.5586e-05) (hash(x)=149459414)
|
| 764 |
+
6340 train 4.151870 (lr=5.5313e-05) (hash(x)=154290067)
|
| 765 |
+
6350 train 4.250857 (lr=5.5042e-05) (hash(x)=147407391)
|
| 766 |
+
6360 train 4.173744 (lr=5.4771e-05) (hash(x)=146317149)
|
| 767 |
+
6370 train 4.077678 (lr=5.4500e-05) (hash(x)=141970628)
|
| 768 |
+
6380 train 4.110469 (lr=5.4231e-05) (hash(x)=139170535)
|
| 769 |
+
6390 train 4.306239 (lr=5.3963e-05) (hash(x)=148905963)
|
| 770 |
+
6400 val loss 4.2837
|
| 771 |
+
6400 val perplexity 72.5100
|
| 772 |
+
6400 train 4.113089 (lr=5.3695e-05) (hash(x)=141624235)
|
| 773 |
+
6410 train 4.109133 (lr=5.3428e-05) (hash(x)=150520968)
|
| 774 |
+
6420 train 4.003477 (lr=5.3162e-05) (hash(x)=155019129)
|
| 775 |
+
6430 train 4.055148 (lr=5.2896e-05) (hash(x)=150031836)
|
| 776 |
+
6440 train 4.026678 (lr=5.2632e-05) (hash(x)=112835661)
|
| 777 |
+
6450 train 4.023211 (lr=5.2368e-05) (hash(x)=141072709)
|
| 778 |
+
6460 train 4.179096 (lr=5.2105e-05) (hash(x)=153933796)
|
| 779 |
+
6470 train 4.231690 (lr=5.1843e-05) (hash(x)=153315715)
|
| 780 |
+
6480 train 4.305419 (lr=5.1582e-05) (hash(x)=158089228)
|
| 781 |
+
6490 train 4.154889 (lr=5.1322e-05) (hash(x)=149471788)
|
| 782 |
+
6500 val loss 4.2800
|
| 783 |
+
6500 val perplexity 72.2400
|
| 784 |
+
6500 train 4.270938 (lr=5.1063e-05) (hash(x)=151197095)
|
| 785 |
+
6510 train 4.236389 (lr=5.0804e-05) (hash(x)=165554266)
|
| 786 |
+
6520 train 4.401155 (lr=5.0546e-05) (hash(x)=157822242)
|
| 787 |
+
6530 train 4.335565 (lr=5.0289e-05) (hash(x)=156267861)
|
| 788 |
+
6540 train 4.246706 (lr=5.0033e-05) (hash(x)=145825803)
|
| 789 |
+
6550 train 4.325245 (lr=4.9778e-05) (hash(x)=151303683)
|
| 790 |
+
6560 train 4.398297 (lr=4.9524e-05) (hash(x)=150786942)
|
| 791 |
+
6570 train 4.210903 (lr=4.9271e-05) (hash(x)=146237093)
|
| 792 |
+
6580 train 4.166203 (lr=4.9018e-05) (hash(x)=147063866)
|
| 793 |
+
6590 train 4.394531 (lr=4.8767e-05) (hash(x)=130513396)
|
| 794 |
+
6600 val loss 4.2795
|
| 795 |
+
6600 val perplexity 72.2013
|
| 796 |
+
6600 train 4.299331 (lr=4.8516e-05) (hash(x)=153269571)
|
| 797 |
+
6610 train 4.361736 (lr=4.8266e-05) (hash(x)=150340530)
|
| 798 |
+
6620 train 4.254641 (lr=4.8017e-05) (hash(x)=153843616)
|
| 799 |
+
6630 train 4.314037 (lr=4.7769e-05) (hash(x)=144540858)
|
| 800 |
+
6640 train 4.117453 (lr=4.7522e-05) (hash(x)=153330434)
|
| 801 |
+
6650 train 4.133489 (lr=4.7276e-05) (hash(x)=146851492)
|
| 802 |
+
6660 train 4.149190 (lr=4.7030e-05) (hash(x)=153601788)
|
| 803 |
+
6670 train 4.185151 (lr=4.6786e-05) (hash(x)=140005742)
|
| 804 |
+
6680 train 4.039562 (lr=4.6542e-05) (hash(x)=154102392)
|
| 805 |
+
6690 train 4.045180 (lr=4.6300e-05) (hash(x)=152774975)
|
| 806 |
+
6700 val loss 4.2746
|
| 807 |
+
6700 val perplexity 71.8506
|
| 808 |
+
6700 train 4.252868 (lr=4.6058e-05) (hash(x)=146111181)
|
| 809 |
+
6710 train 4.200380 (lr=4.5817e-05) (hash(x)=143988017)
|
| 810 |
+
6720 train 4.190205 (lr=4.5578e-05) (hash(x)=146073959)
|
| 811 |
+
6730 train 4.442221 (lr=4.5339e-05) (hash(x)=152642956)
|
| 812 |
+
6740 train 4.329429 (lr=4.5101e-05) (hash(x)=146964363)
|
| 813 |
+
6750 train 4.132747 (lr=4.4864e-05) (hash(x)=162251871)
|
| 814 |
+
6760 train 4.505999 (lr=4.4628e-05) (hash(x)=171122166)
|
| 815 |
+
6770 train 4.245312 (lr=4.4393e-05) (hash(x)=135199617)
|
| 816 |
+
6780 train 4.236043 (lr=4.4159e-05) (hash(x)=160480410)
|
| 817 |
+
6790 train 4.364385 (lr=4.3926e-05) (hash(x)=151933948)
|
| 818 |
+
6800 val loss 4.2652
|
| 819 |
+
6800 val perplexity 71.1773
|
| 820 |
+
6800 train 4.275690 (lr=4.3693e-05) (hash(x)=147269760)
|
| 821 |
+
6810 train 4.344633 (lr=4.3462e-05) (hash(x)=156710316)
|
| 822 |
+
6820 train 4.353480 (lr=4.3232e-05) (hash(x)=157300754)
|
| 823 |
+
6830 train 4.165288 (lr=4.3002e-05) (hash(x)=133838057)
|
| 824 |
+
6840 train 4.357896 (lr=4.2774e-05) (hash(x)=143518263)
|
| 825 |
+
6850 train 4.424093 (lr=4.2547e-05) (hash(x)=160328446)
|
| 826 |
+
6860 train 4.249020 (lr=4.2320e-05) (hash(x)=142143427)
|
| 827 |
+
6870 train 4.313288 (lr=4.2095e-05) (hash(x)=149045075)
|
| 828 |
+
6880 train 4.236265 (lr=4.1870e-05) (hash(x)=150708270)
|
| 829 |
+
6890 train 4.254002 (lr=4.1647e-05) (hash(x)=153066841)
|
| 830 |
+
6900 val loss 4.2641
|
| 831 |
+
6900 val perplexity 71.0984
|
| 832 |
+
6900 train 4.342815 (lr=4.1425e-05) (hash(x)=152912762)
|
| 833 |
+
6910 train 4.196371 (lr=4.1203e-05) (hash(x)=148346240)
|
| 834 |
+
6920 train 4.320452 (lr=4.0983e-05) (hash(x)=152806752)
|
| 835 |
+
6930 train 4.279309 (lr=4.0763e-05) (hash(x)=161831829)
|
| 836 |
+
6940 train 4.191529 (lr=4.0545e-05) (hash(x)=149483673)
|
| 837 |
+
6950 train 4.170962 (lr=4.0327e-05) (hash(x)=119634555)
|
| 838 |
+
6960 train 4.099692 (lr=4.0111e-05) (hash(x)=144709540)
|
| 839 |
+
6970 train 4.110287 (lr=3.9895e-05) (hash(x)=141277017)
|
| 840 |
+
6980 train 4.171920 (lr=3.9681e-05) (hash(x)=140618792)
|
| 841 |
+
6990 train 4.168587 (lr=3.9468e-05) (hash(x)=157443505)
|
| 842 |
+
7000 val loss 4.2615
|
| 843 |
+
7000 val perplexity 70.9192
|
| 844 |
+
7000 train 4.396641 (lr=3.9255e-05) (hash(x)=165412343)
|
| 845 |
+
7010 train 4.035657 (lr=3.9044e-05) (hash(x)=140746035)
|
| 846 |
+
7020 train 4.080826 (lr=3.8834e-05) (hash(x)=141101046)
|
| 847 |
+
7030 train 4.236568 (lr=3.8624e-05) (hash(x)=152098342)
|
| 848 |
+
7040 train 4.100988 (lr=3.8416e-05) (hash(x)=169244968)
|
| 849 |
+
7050 train 4.223993 (lr=3.8209e-05) (hash(x)=149886680)
|
| 850 |
+
7060 train 4.375239 (lr=3.8003e-05) (hash(x)=144670487)
|
| 851 |
+
7070 train 4.410848 (lr=3.7798e-05) (hash(x)=148774474)
|
| 852 |
+
7080 train 4.245543 (lr=3.7593e-05) (hash(x)=155096286)
|
| 853 |
+
7090 train 4.212723 (lr=3.7390e-05) (hash(x)=145048246)
|
| 854 |
+
7100 val loss 4.2502
|
| 855 |
+
7100 val perplexity 70.1214
|
| 856 |
+
7100 train 4.360320 (lr=3.7188e-05) (hash(x)=162866028)
|
| 857 |
+
7110 train 4.223542 (lr=3.6988e-05) (hash(x)=162308558)
|
| 858 |
+
7120 train 4.196485 (lr=3.6788e-05) (hash(x)=153468309)
|
| 859 |
+
7130 train 4.214267 (lr=3.6589e-05) (hash(x)=144522880)
|
| 860 |
+
7140 train 4.365647 (lr=3.6391e-05) (hash(x)=153055749)
|
| 861 |
+
7150 train 4.184833 (lr=3.6195e-05) (hash(x)=171163513)
|
| 862 |
+
7160 train 4.263638 (lr=3.5999e-05) (hash(x)=138563864)
|
| 863 |
+
7170 train 4.389495 (lr=3.5804e-05) (hash(x)=166996657)
|
| 864 |
+
7180 train 4.086361 (lr=3.5611e-05) (hash(x)=154809376)
|
| 865 |
+
7190 train 4.167136 (lr=3.5419e-05) (hash(x)=147988525)
|
| 866 |
+
7200 val loss 4.2505
|
| 867 |
+
7200 val perplexity 70.1407
|
| 868 |
+
7200 train 4.219349 (lr=3.5227e-05) (hash(x)=142998115)
|
| 869 |
+
7210 train 4.196731 (lr=3.5037e-05) (hash(x)=145518575)
|
| 870 |
+
7220 train 4.222198 (lr=3.4848e-05) (hash(x)=145758781)
|
| 871 |
+
7230 train 4.321281 (lr=3.4660e-05) (hash(x)=148909637)
|
| 872 |
+
7240 train 4.176664 (lr=3.4473e-05) (hash(x)=144422691)
|
| 873 |
+
7250 train 4.048461 (lr=3.4287e-05) (hash(x)=140396153)
|
| 874 |
+
7260 train 4.280532 (lr=3.4102e-05) (hash(x)=153619124)
|
| 875 |
+
7270 train 4.188111 (lr=3.3919e-05) (hash(x)=161980521)
|
| 876 |
+
7280 train 3.993474 (lr=3.3736e-05) (hash(x)=135160527)
|
| 877 |
+
7290 train 4.135906 (lr=3.3555e-05) (hash(x)=167156181)
|
| 878 |
+
7300 val loss 4.2497
|
| 879 |
+
7300 val perplexity 70.0817
|
| 880 |
+
7300 train 4.067224 (lr=3.3375e-05) (hash(x)=145486999)
|
| 881 |
+
7310 train 4.153581 (lr=3.3195e-05) (hash(x)=155013351)
|
| 882 |
+
7320 train 4.212828 (lr=3.3017e-05) (hash(x)=169616991)
|
| 883 |
+
7330 train 4.077139 (lr=3.2840e-05) (hash(x)=146516856)
|
| 884 |
+
7340 train 4.406440 (lr=3.2664e-05) (hash(x)=171918417)
|
| 885 |
+
7350 train 4.420859 (lr=3.2490e-05) (hash(x)=160511891)
|
| 886 |
+
7360 train 4.275684 (lr=3.2316e-05) (hash(x)=150280167)
|
| 887 |
+
7370 train 4.342896 (lr=3.2144e-05) (hash(x)=151373787)
|
| 888 |
+
7380 train 4.448463 (lr=3.1972e-05) (hash(x)=163311616)
|
| 889 |
+
7390 train 4.448496 (lr=3.1802e-05) (hash(x)=164418521)
|
| 890 |
+
7400 val loss 4.2412
|
| 891 |
+
7400 val perplexity 69.4915
|
| 892 |
+
7400 train 4.191174 (lr=3.1633e-05) (hash(x)=155325873)
|
| 893 |
+
7410 train 4.246516 (lr=3.1465e-05) (hash(x)=135020608)
|
| 894 |
+
7420 train 4.108366 (lr=3.1298e-05) (hash(x)=142812793)
|
| 895 |
+
7430 train 4.257035 (lr=3.1132e-05) (hash(x)=149463283)
|
| 896 |
+
7440 train 4.209622 (lr=3.0968e-05) (hash(x)=170512352)
|
| 897 |
+
7450 train 4.187057 (lr=3.0804e-05) (hash(x)=146253806)
|
| 898 |
+
7460 train 4.831943 (lr=3.0642e-05) (hash(x)=133479853)
|
| 899 |
+
7470 train 4.187799 (lr=3.0481e-05) (hash(x)=138198949)
|
| 900 |
+
7480 train 4.173747 (lr=3.0321e-05) (hash(x)=143831431)
|
| 901 |
+
7490 train 4.331958 (lr=3.0162e-05) (hash(x)=148147144)
|
| 902 |
+
7500 val loss 4.2405
|
| 903 |
+
7500 val perplexity 69.4427
|
| 904 |
+
7500 train 4.232979 (lr=3.0005e-05) (hash(x)=145131256)
|
| 905 |
+
7510 train 4.278220 (lr=2.9848e-05) (hash(x)=150932291)
|
| 906 |
+
7520 train 4.246240 (lr=2.9693e-05) (hash(x)=147605934)
|
| 907 |
+
7530 train 4.193724 (lr=2.9539e-05) (hash(x)=154343507)
|
| 908 |
+
7540 train 4.311944 (lr=2.9386e-05) (hash(x)=148440064)
|
| 909 |
+
7550 train 4.123746 (lr=2.9234e-05) (hash(x)=140505990)
|
| 910 |
+
7560 train 4.126618 (lr=2.9084e-05) (hash(x)=177438878)
|
| 911 |
+
7570 train 4.184727 (lr=2.8934e-05) (hash(x)=154527960)
|
| 912 |
+
7580 train 4.280052 (lr=2.8786e-05) (hash(x)=153793091)
|
| 913 |
+
7590 train 4.108408 (lr=2.8639e-05) (hash(x)=163097232)
|
| 914 |
+
7600 val loss 4.2470
|
| 915 |
+
7600 val perplexity 69.8981
|
| 916 |
+
7600 train 4.228789 (lr=2.8493e-05) (hash(x)=144008365)
|
| 917 |
+
7610 train 4.215824 (lr=2.8348e-05) (hash(x)=139649886)
|
| 918 |
+
7620 train 4.155736 (lr=2.8204e-05) (hash(x)=145452123)
|
| 919 |
+
7630 train 4.182721 (lr=2.8062e-05) (hash(x)=132477285)
|
| 920 |
+
7640 train 4.102047 (lr=2.7921e-05) (hash(x)=139030720)
|
| 921 |
+
7650 train 4.240751 (lr=2.7781e-05) (hash(x)=157466085)
|
| 922 |
+
7660 train 4.256503 (lr=2.7642e-05) (hash(x)=153638385)
|
| 923 |
+
7670 train 4.304187 (lr=2.7505e-05) (hash(x)=154823094)
|
| 924 |
+
7680 train 4.217982 (lr=2.7368e-05) (hash(x)=153107930)
|
| 925 |
+
7690 train 4.191523 (lr=2.7233e-05) (hash(x)=153681916)
|
| 926 |
+
7700 val loss 4.2344
|
| 927 |
+
7700 val perplexity 69.0204
|
| 928 |
+
7700 train 4.507432 (lr=2.7099e-05) (hash(x)=148848532)
|
| 929 |
+
7710 train 4.232899 (lr=2.6966e-05) (hash(x)=156640791)
|
| 930 |
+
7720 train 4.459990 (lr=2.6834e-05) (hash(x)=152573035)
|
| 931 |
+
7730 train 4.299294 (lr=2.6704e-05) (hash(x)=147536091)
|
| 932 |
+
7740 train 4.495372 (lr=2.6575e-05) (hash(x)=175687483)
|
| 933 |
+
7750 train 4.221022 (lr=2.6447e-05) (hash(x)=143775898)
|
| 934 |
+
7760 train 4.247890 (lr=2.6320e-05) (hash(x)=146986193)
|
| 935 |
+
7770 train 4.158616 (lr=2.6195e-05) (hash(x)=160924293)
|
| 936 |
+
7780 train 4.196349 (lr=2.6070e-05) (hash(x)=132579169)
|
| 937 |
+
7790 train 4.429517 (lr=2.5947e-05) (hash(x)=147474225)
|
| 938 |
+
7800 val loss 4.2340
|
| 939 |
+
7800 val perplexity 68.9898
|
| 940 |
+
7800 train 4.267305 (lr=2.5825e-05) (hash(x)=150391642)
|
| 941 |
+
7810 train 4.448611 (lr=2.5705e-05) (hash(x)=156984481)
|
| 942 |
+
7820 train 4.152966 (lr=2.5585e-05) (hash(x)=139652488)
|
| 943 |
+
7830 train 4.177397 (lr=2.5467e-05) (hash(x)=169033643)
|
| 944 |
+
7840 train 4.150917 (lr=2.5350e-05) (hash(x)=152645857)
|
| 945 |
+
7850 train 4.286904 (lr=2.5234e-05) (hash(x)=150228075)
|
| 946 |
+
7860 train 4.208807 (lr=2.5119e-05) (hash(x)=178788133)
|
| 947 |
+
7870 train 4.182274 (lr=2.5006e-05) (hash(x)=149891068)
|
| 948 |
+
7880 train 4.136569 (lr=2.4894e-05) (hash(x)=157461488)
|
| 949 |
+
7890 train 4.092426 (lr=2.4783e-05) (hash(x)=142502446)
|
| 950 |
+
7900 val loss 4.2344
|
| 951 |
+
7900 val perplexity 69.0175
|
| 952 |
+
7900 train 4.020327 (lr=2.4674e-05) (hash(x)=152191414)
|
| 953 |
+
7910 train 4.207443 (lr=2.4565e-05) (hash(x)=151329539)
|
| 954 |
+
7920 train 4.086550 (lr=2.4458e-05) (hash(x)=134143115)
|
| 955 |
+
7930 train 4.097367 (lr=2.4352e-05) (hash(x)=155536160)
|
| 956 |
+
7940 train 4.159870 (lr=2.4247e-05) (hash(x)=146709034)
|
| 957 |
+
7950 train 4.246765 (lr=2.4144e-05) (hash(x)=141966330)
|
| 958 |
+
7960 train 4.230599 (lr=2.4042e-05) (hash(x)=152102296)
|
| 959 |
+
7970 train 4.396601 (lr=2.3941e-05) (hash(x)=150272684)
|
| 960 |
+
7980 train 4.365520 (lr=2.3841e-05) (hash(x)=150251784)
|
| 961 |
+
7990 train 4.355377 (lr=2.3743e-05) (hash(x)=151226159)
|
| 962 |
+
8000 val loss 4.2291
|
| 963 |
+
8000 val perplexity 68.6540
|
| 964 |
+
8000 train 4.263064 (lr=2.3646e-05) (hash(x)=159755587)
|
| 965 |
+
8010 train 4.256445 (lr=2.3550e-05) (hash(x)=137607202)
|
| 966 |
+
8020 train 4.254905 (lr=2.3455e-05) (hash(x)=149574886)
|
| 967 |
+
8030 train 4.172956 (lr=2.3362e-05) (hash(x)=151690927)
|
| 968 |
+
8040 train 4.189911 (lr=2.3269e-05) (hash(x)=151181288)
|
| 969 |
+
8050 train 4.318566 (lr=2.3179e-05) (hash(x)=150465993)
|
| 970 |
+
8060 train 4.315163 (lr=2.3089e-05) (hash(x)=134201020)
|
| 971 |
+
8070 train 4.207779 (lr=2.3001e-05) (hash(x)=157696045)
|
| 972 |
+
8080 train 4.216081 (lr=2.2913e-05) (hash(x)=135581816)
|
| 973 |
+
8090 train 4.149670 (lr=2.2828e-05) (hash(x)=153898278)
|
| 974 |
+
8100 val loss 4.2264
|
| 975 |
+
8100 val perplexity 68.4727
|
| 976 |
+
8100 train 4.267791 (lr=2.2743e-05) (hash(x)=156664468)
|
| 977 |
+
8110 train 4.381624 (lr=2.2660e-05) (hash(x)=161572593)
|
| 978 |
+
8120 train 4.114841 (lr=2.2578e-05) (hash(x)=154381651)
|
| 979 |
+
8130 train 4.384490 (lr=2.2497e-05) (hash(x)=149810514)
|
| 980 |
+
8140 train 4.220920 (lr=2.2417e-05) (hash(x)=145085369)
|
| 981 |
+
8150 train 4.074906 (lr=2.2339e-05) (hash(x)=149020616)
|
| 982 |
+
8160 train 3.969363 (lr=2.2262e-05) (hash(x)=146450644)
|
| 983 |
+
8170 train 4.176548 (lr=2.2186e-05) (hash(x)=148094499)
|
| 984 |
+
8180 train 4.032140 (lr=2.2112e-05) (hash(x)=140810897)
|
| 985 |
+
8190 train 4.138612 (lr=2.2039e-05) (hash(x)=142960309)
|
| 986 |
+
8200 val loss 4.2278
|
| 987 |
+
8200 val perplexity 68.5653
|
| 988 |
+
8200 train 4.164021 (lr=2.1967e-05) (hash(x)=139457379)
|
| 989 |
+
8210 train 4.159283 (lr=2.1896e-05) (hash(x)=145575125)
|
| 990 |
+
8220 train 3.960563 (lr=2.1827e-05) (hash(x)=152836922)
|
| 991 |
+
8230 train 4.046914 (lr=2.1759e-05) (hash(x)=135086706)
|
| 992 |
+
8240 train 4.022552 (lr=2.1692e-05) (hash(x)=153448613)
|
| 993 |
+
8250 train 3.976381 (lr=2.1626e-05) (hash(x)=138041222)
|
| 994 |
+
8260 train 4.052716 (lr=2.1562e-05) (hash(x)=158857968)
|
| 995 |
+
8270 train 4.056579 (lr=2.1499e-05) (hash(x)=157265315)
|
| 996 |
+
8280 train 3.894977 (lr=2.1438e-05) (hash(x)=136059191)
|
| 997 |
+
8290 train 3.988907 (lr=2.1377e-05) (hash(x)=162526712)
|
| 998 |
+
8300 val loss 4.2325
|
| 999 |
+
8300 val perplexity 68.8870
|
| 1000 |
+
8300 train 4.043128 (lr=2.1318e-05) (hash(x)=145478564)
|
| 1001 |
+
8310 train 3.717913 (lr=2.1260e-05) (hash(x)=157367549)
|
| 1002 |
+
8320 train 4.090946 (lr=2.1204e-05) (hash(x)=156085849)
|
| 1003 |
+
8330 train 4.374941 (lr=2.1149e-05) (hash(x)=154822719)
|
| 1004 |
+
8340 train 4.099777 (lr=2.1095e-05) (hash(x)=159688342)
|
| 1005 |
+
8350 train 4.210627 (lr=2.1042e-05) (hash(x)=144133822)
|
| 1006 |
+
8360 train 4.174705 (lr=2.0991e-05) (hash(x)=154155471)
|
| 1007 |
+
8370 train 4.176700 (lr=2.0941e-05) (hash(x)=157077804)
|
| 1008 |
+
8380 train 4.182048 (lr=2.0892e-05) (hash(x)=147796790)
|
| 1009 |
+
8390 train 4.174019 (lr=2.0844e-05) (hash(x)=145208254)
|
| 1010 |
+
8400 val loss 4.2231
|
| 1011 |
+
8400 val perplexity 68.2451
|
| 1012 |
+
8400 train 4.132093 (lr=2.0798e-05) (hash(x)=154982769)
|
| 1013 |
+
8410 train 4.323674 (lr=2.0753e-05) (hash(x)=138073867)
|
| 1014 |
+
8420 train 4.367599 (lr=2.0710e-05) (hash(x)=159521725)
|
| 1015 |
+
8430 train 4.296305 (lr=2.0667e-05) (hash(x)=149988578)
|
| 1016 |
+
8440 train 4.257502 (lr=2.0626e-05) (hash(x)=149457063)
|
| 1017 |
+
8450 train 4.116613 (lr=2.0587e-05) (hash(x)=134678896)
|
| 1018 |
+
8460 train 4.176216 (lr=2.0548e-05) (hash(x)=146122249)
|
| 1019 |
+
8470 train 4.194399 (lr=2.0511e-05) (hash(x)=141393319)
|
| 1020 |
+
8480 train 4.212975 (lr=2.0475e-05) (hash(x)=165396836)
|
| 1021 |
+
8490 train 4.301051 (lr=2.0441e-05) (hash(x)=140043806)
|
| 1022 |
+
8500 val loss 4.2206
|
| 1023 |
+
8500 val perplexity 68.0735
|
| 1024 |
+
8500 train 4.244764 (lr=2.0408e-05) (hash(x)=145798118)
|
| 1025 |
+
8510 train 4.188856 (lr=2.0376e-05) (hash(x)=150358299)
|
| 1026 |
+
8520 train 4.093578 (lr=2.0345e-05) (hash(x)=152572913)
|
| 1027 |
+
8530 train 4.160171 (lr=2.0316e-05) (hash(x)=148669229)
|
| 1028 |
+
8540 train 4.196958 (lr=2.0288e-05) (hash(x)=147078347)
|
| 1029 |
+
8550 train 4.168790 (lr=2.0261e-05) (hash(x)=146715166)
|
| 1030 |
+
8560 train 4.141449 (lr=2.0235e-05) (hash(x)=143176392)
|
| 1031 |
+
8570 train 4.262403 (lr=2.0211e-05) (hash(x)=153825484)
|
| 1032 |
+
8580 train 4.287475 (lr=2.0189e-05) (hash(x)=163379045)
|
| 1033 |
+
8590 train 4.061338 (lr=2.0167e-05) (hash(x)=140050873)
|
| 1034 |
+
8600 val loss 4.2223
|
| 1035 |
+
8600 val perplexity 68.1883
|
| 1036 |
+
8600 train 4.155617 (lr=2.0147e-05) (hash(x)=143231551)
|
| 1037 |
+
8610 train 4.018944 (lr=2.0128e-05) (hash(x)=164291360)
|
| 1038 |
+
8620 train 4.060422 (lr=2.0110e-05) (hash(x)=159122123)
|
| 1039 |
+
8630 train 4.019196 (lr=2.0094e-05) (hash(x)=140041695)
|
| 1040 |
+
8640 train 4.040040 (lr=2.0079e-05) (hash(x)=146010790)
|
| 1041 |
+
8650 train 3.966620 (lr=2.0065e-05) (hash(x)=146882123)
|
| 1042 |
+
8660 train 3.781430 (lr=2.0053e-05) (hash(x)=144933705)
|
| 1043 |
+
8670 train 4.017633 (lr=2.0042e-05) (hash(x)=145580075)
|
| 1044 |
+
8680 train 4.054173 (lr=2.0032e-05) (hash(x)=160982926)
|
| 1045 |
+
8690 train 3.944473 (lr=2.0023e-05) (hash(x)=140047108)
|
| 1046 |
+
8700 val loss 4.2296
|
| 1047 |
+
8700 val perplexity 68.6911
|
| 1048 |
+
8700 train 4.070146 (lr=2.0016e-05) (hash(x)=154780112)
|
| 1049 |
+
8710 train 4.149293 (lr=2.0010e-05) (hash(x)=157568560)
|
| 1050 |
+
8720 train 4.193864 (lr=2.0006e-05) (hash(x)=159587459)
|
| 1051 |
+
8730 train 4.188174 (lr=2.0003e-05) (hash(x)=152918103)
|
| 1052 |
+
8740 train 4.183417 (lr=2.0001e-05) (hash(x)=156928586)
|
| 1053 |
+
8749 val loss 4.2193
|
| 1054 |
+
8749 val perplexity 67.9865
|
lr2e-4_total_batch_size61440_baseline_seed1340/model_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a83c9fa13a91f1a01b461c9a6fcdd1853fbf4a4a716a6b93ff47d11576a92974
|
| 3 |
+
size 92843394
|
lr2e-4_total_batch_size61440_baseline_seed1340/optimizer_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23ae4ef8b5056115a6a5b066f00da545480cfabac0633a9fea73247a75410214
|
| 3 |
+
size 179406214
|