Upload folder using huggingface_hub
Browse files- lr12e-4_total_batch_size61440_baseline_seed1338/args.json +1 -0
- lr12e-4_total_batch_size61440_baseline_seed1338/dataloader_08749.pt +3 -0
- lr12e-4_total_batch_size61440_baseline_seed1338/log2.txt +1054 -0
- lr12e-4_total_batch_size61440_baseline_seed1338/model_08749.pt +3 -0
- lr12e-4_total_batch_size61440_baseline_seed1338/optimizer_08749.pt +3 -0
lr12e-4_total_batch_size61440_baseline_seed1338/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "wider_is_better_11/lr12e-4_total_batch_size61440_baseline_seed1338", "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": 1338, "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": 0.0012, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "12e-4_61440", "n_embd": 256}
|
lr12e-4_total_batch_size61440_baseline_seed1338/dataloader_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:953385078aa3787b69fc6857dfd48b0a2cd2f4d27c6f8892e01211aca53d07f5
|
| 3 |
+
size 964
|
lr12e-4_total_batch_size61440_baseline_seed1338/log2.txt
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_steps: 8750
|
| 2 |
+
0 val loss 11.2202
|
| 3 |
+
0 val perplexity 74626.3672
|
| 4 |
+
0 train 11.227304 (lr=2.4000e-06) (hash(x)=150327452)
|
| 5 |
+
10 train 10.043566 (lr=2.6400e-05) (hash(x)=165603215)
|
| 6 |
+
20 train 9.636700 (lr=5.0400e-05) (hash(x)=142061326)
|
| 7 |
+
30 train 9.137615 (lr=7.4400e-05) (hash(x)=147690730)
|
| 8 |
+
40 train 8.636971 (lr=9.8400e-05) (hash(x)=160872542)
|
| 9 |
+
50 train 8.102778 (lr=1.2240e-04) (hash(x)=166441190)
|
| 10 |
+
60 train 7.762578 (lr=1.4640e-04) (hash(x)=140536766)
|
| 11 |
+
70 train 7.608108 (lr=1.7040e-04) (hash(x)=146052944)
|
| 12 |
+
80 train 7.523576 (lr=1.9440e-04) (hash(x)=140542391)
|
| 13 |
+
90 train 7.393627 (lr=2.1840e-04) (hash(x)=147098660)
|
| 14 |
+
100 val loss 7.3900
|
| 15 |
+
100 val perplexity 1619.7013
|
| 16 |
+
100 train 7.370001 (lr=2.4240e-04) (hash(x)=166780046)
|
| 17 |
+
110 train 7.116112 (lr=2.6640e-04) (hash(x)=143376584)
|
| 18 |
+
120 train 7.048679 (lr=2.9040e-04) (hash(x)=145337630)
|
| 19 |
+
130 train 7.007643 (lr=3.1440e-04) (hash(x)=147524744)
|
| 20 |
+
140 train 6.912862 (lr=3.3840e-04) (hash(x)=155587442)
|
| 21 |
+
150 train 6.776953 (lr=3.6240e-04) (hash(x)=159835303)
|
| 22 |
+
160 train 6.616092 (lr=3.8640e-04) (hash(x)=142171630)
|
| 23 |
+
170 train 6.505166 (lr=4.1040e-04) (hash(x)=136930463)
|
| 24 |
+
180 train 6.489495 (lr=4.3440e-04) (hash(x)=153579148)
|
| 25 |
+
190 train 6.374035 (lr=4.5840e-04) (hash(x)=140352771)
|
| 26 |
+
200 val loss 6.5638
|
| 27 |
+
200 val perplexity 708.9832
|
| 28 |
+
200 train 6.277971 (lr=4.8240e-04) (hash(x)=155040610)
|
| 29 |
+
210 train 6.226378 (lr=5.0640e-04) (hash(x)=141273862)
|
| 30 |
+
220 train 6.454213 (lr=5.3040e-04) (hash(x)=165326618)
|
| 31 |
+
230 train 6.204575 (lr=5.5440e-04) (hash(x)=150122120)
|
| 32 |
+
240 train 5.976537 (lr=5.7840e-04) (hash(x)=143024679)
|
| 33 |
+
250 train 5.992911 (lr=6.0240e-04) (hash(x)=130190460)
|
| 34 |
+
260 train 6.094464 (lr=6.2640e-04) (hash(x)=151890219)
|
| 35 |
+
270 train 5.866133 (lr=6.5040e-04) (hash(x)=143685291)
|
| 36 |
+
280 train 6.176681 (lr=6.7440e-04) (hash(x)=137108194)
|
| 37 |
+
290 train 6.306267 (lr=6.9840e-04) (hash(x)=157920866)
|
| 38 |
+
300 val loss 6.1215
|
| 39 |
+
300 val perplexity 455.5549
|
| 40 |
+
300 train 6.045178 (lr=7.2240e-04) (hash(x)=155504036)
|
| 41 |
+
310 train 6.151872 (lr=7.4640e-04) (hash(x)=144551186)
|
| 42 |
+
320 train 6.130730 (lr=7.7040e-04) (hash(x)=161180086)
|
| 43 |
+
330 train 5.899500 (lr=7.9440e-04) (hash(x)=141651471)
|
| 44 |
+
340 train 6.012617 (lr=8.1840e-04) (hash(x)=157490741)
|
| 45 |
+
350 train 5.987797 (lr=8.4240e-04) (hash(x)=137347213)
|
| 46 |
+
360 train 6.264895 (lr=8.6640e-04) (hash(x)=171273659)
|
| 47 |
+
370 train 5.856385 (lr=8.9040e-04) (hash(x)=152118871)
|
| 48 |
+
380 train 5.850949 (lr=9.1440e-04) (hash(x)=161338097)
|
| 49 |
+
390 train 5.942008 (lr=9.3840e-04) (hash(x)=152404537)
|
| 50 |
+
400 val loss 5.7993
|
| 51 |
+
400 val perplexity 330.0540
|
| 52 |
+
400 train 5.634412 (lr=9.6240e-04) (hash(x)=143823248)
|
| 53 |
+
410 train 5.877761 (lr=9.8640e-04) (hash(x)=161686752)
|
| 54 |
+
420 train 5.616230 (lr=1.0104e-03) (hash(x)=155391312)
|
| 55 |
+
430 train 5.537411 (lr=1.0344e-03) (hash(x)=142145507)
|
| 56 |
+
440 train 5.684703 (lr=1.0584e-03) (hash(x)=121931091)
|
| 57 |
+
450 train 5.608408 (lr=1.0824e-03) (hash(x)=156260416)
|
| 58 |
+
460 train 5.773273 (lr=1.1064e-03) (hash(x)=169781623)
|
| 59 |
+
470 train 5.545495 (lr=1.1304e-03) (hash(x)=150131545)
|
| 60 |
+
480 train 5.562218 (lr=1.1544e-03) (hash(x)=150443184)
|
| 61 |
+
490 train 5.567348 (lr=1.1784e-03) (hash(x)=149368198)
|
| 62 |
+
500 val loss 5.5877
|
| 63 |
+
500 val perplexity 267.1292
|
| 64 |
+
500 train 5.467353 (lr=1.2000e-03) (hash(x)=143734685)
|
| 65 |
+
510 train 5.486808 (lr=1.2000e-03) (hash(x)=148943891)
|
| 66 |
+
520 train 5.501876 (lr=1.2000e-03) (hash(x)=149070354)
|
| 67 |
+
530 train 5.482356 (lr=1.2000e-03) (hash(x)=153601219)
|
| 68 |
+
540 train 5.500357 (lr=1.1999e-03) (hash(x)=174970654)
|
| 69 |
+
550 train 5.427029 (lr=1.1999e-03) (hash(x)=160013925)
|
| 70 |
+
560 train 5.269190 (lr=1.1999e-03) (hash(x)=152096988)
|
| 71 |
+
570 train 5.401695 (lr=1.1998e-03) (hash(x)=157203924)
|
| 72 |
+
580 train 5.165419 (lr=1.1997e-03) (hash(x)=138582113)
|
| 73 |
+
590 train 5.183616 (lr=1.1997e-03) (hash(x)=157451775)
|
| 74 |
+
600 val loss 5.4083
|
| 75 |
+
600 val perplexity 223.2439
|
| 76 |
+
600 train 5.102455 (lr=1.1996e-03) (hash(x)=150678249)
|
| 77 |
+
610 train 5.143948 (lr=1.1995e-03) (hash(x)=150248072)
|
| 78 |
+
620 train 5.054785 (lr=1.1994e-03) (hash(x)=148286909)
|
| 79 |
+
630 train 5.013937 (lr=1.1993e-03) (hash(x)=141197178)
|
| 80 |
+
640 train 5.090557 (lr=1.1992e-03) (hash(x)=144988391)
|
| 81 |
+
650 train 5.010117 (lr=1.1991e-03) (hash(x)=149073315)
|
| 82 |
+
660 train 4.951813 (lr=1.1990e-03) (hash(x)=145239943)
|
| 83 |
+
670 train 4.977932 (lr=1.1989e-03) (hash(x)=146657426)
|
| 84 |
+
680 train 5.228216 (lr=1.1987e-03) (hash(x)=142323429)
|
| 85 |
+
690 train 5.218717 (lr=1.1986e-03) (hash(x)=142724342)
|
| 86 |
+
700 val loss 5.2487
|
| 87 |
+
700 val perplexity 190.3157
|
| 88 |
+
700 train 5.108372 (lr=1.1984e-03) (hash(x)=175802021)
|
| 89 |
+
710 train 5.183319 (lr=1.1983e-03) (hash(x)=148902690)
|
| 90 |
+
720 train 5.251441 (lr=1.1981e-03) (hash(x)=155151320)
|
| 91 |
+
730 train 5.105034 (lr=1.1979e-03) (hash(x)=142078914)
|
| 92 |
+
740 train 5.253070 (lr=1.1977e-03) (hash(x)=155634484)
|
| 93 |
+
750 train 5.213976 (lr=1.1976e-03) (hash(x)=171034639)
|
| 94 |
+
760 train 5.188686 (lr=1.1974e-03) (hash(x)=142470148)
|
| 95 |
+
770 train 5.133727 (lr=1.1971e-03) (hash(x)=156024448)
|
| 96 |
+
780 train 5.058815 (lr=1.1969e-03) (hash(x)=151369417)
|
| 97 |
+
790 train 4.996135 (lr=1.1967e-03) (hash(x)=139260056)
|
| 98 |
+
800 val loss 5.0863
|
| 99 |
+
800 val perplexity 161.7937
|
| 100 |
+
800 train 5.186707 (lr=1.1965e-03) (hash(x)=158681215)
|
| 101 |
+
810 train 4.993236 (lr=1.1962e-03) (hash(x)=144884161)
|
| 102 |
+
820 train 5.036819 (lr=1.1960e-03) (hash(x)=146977514)
|
| 103 |
+
830 train 4.926033 (lr=1.1957e-03) (hash(x)=148983636)
|
| 104 |
+
840 train 4.951172 (lr=1.1955e-03) (hash(x)=157824542)
|
| 105 |
+
850 train 4.933328 (lr=1.1952e-03) (hash(x)=152116061)
|
| 106 |
+
860 train 5.026952 (lr=1.1949e-03) (hash(x)=153743703)
|
| 107 |
+
870 train 5.163640 (lr=1.1946e-03) (hash(x)=149913335)
|
| 108 |
+
880 train 4.928003 (lr=1.1944e-03) (hash(x)=151096434)
|
| 109 |
+
890 train 4.897477 (lr=1.1941e-03) (hash(x)=145848702)
|
| 110 |
+
900 val loss 4.9619
|
| 111 |
+
900 val perplexity 142.8654
|
| 112 |
+
900 train 4.891966 (lr=1.1937e-03) (hash(x)=146108145)
|
| 113 |
+
910 train 4.848469 (lr=1.1934e-03) (hash(x)=146903806)
|
| 114 |
+
920 train 4.789801 (lr=1.1931e-03) (hash(x)=149225019)
|
| 115 |
+
930 train 4.743031 (lr=1.1928e-03) (hash(x)=146110422)
|
| 116 |
+
940 train 4.824255 (lr=1.1924e-03) (hash(x)=161333614)
|
| 117 |
+
950 train 4.727974 (lr=1.1921e-03) (hash(x)=147598108)
|
| 118 |
+
960 train 4.878925 (lr=1.1917e-03) (hash(x)=158133101)
|
| 119 |
+
970 train 4.677869 (lr=1.1914e-03) (hash(x)=152199591)
|
| 120 |
+
980 train 4.652217 (lr=1.1910e-03) (hash(x)=152359036)
|
| 121 |
+
990 train 4.695938 (lr=1.1906e-03) (hash(x)=145166335)
|
| 122 |
+
1000 val loss 4.8978
|
| 123 |
+
1000 val perplexity 133.9969
|
| 124 |
+
1000 train 4.600762 (lr=1.1902e-03) (hash(x)=154996086)
|
| 125 |
+
1010 train 4.550015 (lr=1.1898e-03) (hash(x)=149406975)
|
| 126 |
+
1020 train 4.658103 (lr=1.1894e-03) (hash(x)=144618270)
|
| 127 |
+
1030 train 4.511468 (lr=1.1890e-03) (hash(x)=148306536)
|
| 128 |
+
1040 train 4.550925 (lr=1.1886e-03) (hash(x)=151643553)
|
| 129 |
+
1050 train 4.511025 (lr=1.1882e-03) (hash(x)=153396183)
|
| 130 |
+
1060 train 4.497548 (lr=1.1878e-03) (hash(x)=157501787)
|
| 131 |
+
1070 train 4.709174 (lr=1.1873e-03) (hash(x)=153277507)
|
| 132 |
+
1080 train 4.777462 (lr=1.1869e-03) (hash(x)=156232389)
|
| 133 |
+
1090 train 4.725815 (lr=1.1864e-03) (hash(x)=150673143)
|
| 134 |
+
1100 val loss 4.8155
|
| 135 |
+
1100 val perplexity 123.4037
|
| 136 |
+
1100 train 4.796827 (lr=1.1860e-03) (hash(x)=153885445)
|
| 137 |
+
1110 train 4.806124 (lr=1.1855e-03) (hash(x)=143951073)
|
| 138 |
+
1120 train 5.213799 (lr=1.1850e-03) (hash(x)=151626904)
|
| 139 |
+
1130 train 4.778947 (lr=1.1845e-03) (hash(x)=144013074)
|
| 140 |
+
1140 train 4.723954 (lr=1.1840e-03) (hash(x)=149948988)
|
| 141 |
+
1150 train 4.779643 (lr=1.1835e-03) (hash(x)=159666385)
|
| 142 |
+
1160 train 4.754763 (lr=1.1830e-03) (hash(x)=146889587)
|
| 143 |
+
1170 train 4.807662 (lr=1.1825e-03) (hash(x)=151746917)
|
| 144 |
+
1180 train 4.825612 (lr=1.1820e-03) (hash(x)=154396948)
|
| 145 |
+
1190 train 4.787005 (lr=1.1815e-03) (hash(x)=148201222)
|
| 146 |
+
1200 val loss 4.7552
|
| 147 |
+
1200 val perplexity 116.1909
|
| 148 |
+
1200 train 4.763546 (lr=1.1809e-03) (hash(x)=142353087)
|
| 149 |
+
1210 train 4.770575 (lr=1.1804e-03) (hash(x)=146779775)
|
| 150 |
+
1220 train 4.829851 (lr=1.1798e-03) (hash(x)=155864740)
|
| 151 |
+
1230 train 4.882763 (lr=1.1793e-03) (hash(x)=129826485)
|
| 152 |
+
1240 train 4.740846 (lr=1.1787e-03) (hash(x)=108599491)
|
| 153 |
+
1250 train 4.614779 (lr=1.1781e-03) (hash(x)=146491718)
|
| 154 |
+
1260 train 4.698064 (lr=1.1775e-03) (hash(x)=141897382)
|
| 155 |
+
1270 train 4.663107 (lr=1.1770e-03) (hash(x)=144830380)
|
| 156 |
+
1280 train 4.727241 (lr=1.1764e-03) (hash(x)=157677763)
|
| 157 |
+
1290 train 4.556900 (lr=1.1757e-03) (hash(x)=143611746)
|
| 158 |
+
1300 val loss 4.7126
|
| 159 |
+
1300 val perplexity 111.3461
|
| 160 |
+
1300 train 4.591140 (lr=1.1751e-03) (hash(x)=150750353)
|
| 161 |
+
1310 train 4.816674 (lr=1.1745e-03) (hash(x)=152850907)
|
| 162 |
+
1320 train 4.734184 (lr=1.1739e-03) (hash(x)=148575395)
|
| 163 |
+
1330 train 4.483955 (lr=1.1733e-03) (hash(x)=157113001)
|
| 164 |
+
1340 train 4.533743 (lr=1.1726e-03) (hash(x)=137400723)
|
| 165 |
+
1350 train 4.584448 (lr=1.1720e-03) (hash(x)=129849193)
|
| 166 |
+
1360 train 4.578285 (lr=1.1713e-03) (hash(x)=144176797)
|
| 167 |
+
1370 train 4.409174 (lr=1.1706e-03) (hash(x)=144550831)
|
| 168 |
+
1380 train 4.371612 (lr=1.1700e-03) (hash(x)=144171821)
|
| 169 |
+
1390 train 4.321939 (lr=1.1693e-03) (hash(x)=146110449)
|
| 170 |
+
1400 val loss 4.6774
|
| 171 |
+
1400 val perplexity 107.4898
|
| 172 |
+
1400 train 4.401787 (lr=1.1686e-03) (hash(x)=152767913)
|
| 173 |
+
1410 train 4.403412 (lr=1.1679e-03) (hash(x)=148110947)
|
| 174 |
+
1420 train 4.286788 (lr=1.1672e-03) (hash(x)=153477905)
|
| 175 |
+
1430 train 4.183553 (lr=1.1665e-03) (hash(x)=147227598)
|
| 176 |
+
1440 train 4.400781 (lr=1.1658e-03) (hash(x)=146280368)
|
| 177 |
+
1450 train 4.368161 (lr=1.1650e-03) (hash(x)=146531140)
|
| 178 |
+
1460 train 4.206741 (lr=1.1643e-03) (hash(x)=151573873)
|
| 179 |
+
1470 train 4.696241 (lr=1.1636e-03) (hash(x)=155559275)
|
| 180 |
+
1480 train 4.593302 (lr=1.1628e-03) (hash(x)=140584826)
|
| 181 |
+
1490 train 4.554906 (lr=1.1621e-03) (hash(x)=165070637)
|
| 182 |
+
1500 val loss 4.6558
|
| 183 |
+
1500 val perplexity 105.1893
|
| 184 |
+
1500 train 4.668531 (lr=1.1613e-03) (hash(x)=151562048)
|
| 185 |
+
1510 train 4.452632 (lr=1.1606e-03) (hash(x)=147770607)
|
| 186 |
+
1520 train 4.532268 (lr=1.1598e-03) (hash(x)=156486153)
|
| 187 |
+
1530 train 4.493896 (lr=1.1590e-03) (hash(x)=140244564)
|
| 188 |
+
1540 train 4.546974 (lr=1.1582e-03) (hash(x)=151627549)
|
| 189 |
+
1550 train 4.587705 (lr=1.1574e-03) (hash(x)=146001424)
|
| 190 |
+
1560 train 4.663332 (lr=1.1566e-03) (hash(x)=184266264)
|
| 191 |
+
1570 train 4.564212 (lr=1.1558e-03) (hash(x)=145002091)
|
| 192 |
+
1580 train 4.456964 (lr=1.1550e-03) (hash(x)=132216826)
|
| 193 |
+
1590 train 4.628085 (lr=1.1541e-03) (hash(x)=160975703)
|
| 194 |
+
1600 val loss 4.6063
|
| 195 |
+
1600 val perplexity 100.1180
|
| 196 |
+
1600 train 4.765093 (lr=1.1533e-03) (hash(x)=166486165)
|
| 197 |
+
1610 train 4.643884 (lr=1.1525e-03) (hash(x)=149601833)
|
| 198 |
+
1620 train 4.528735 (lr=1.1516e-03) (hash(x)=157815188)
|
| 199 |
+
1630 train 4.552350 (lr=1.1508e-03) (hash(x)=144234679)
|
| 200 |
+
1640 train 4.681679 (lr=1.1499e-03) (hash(x)=160054560)
|
| 201 |
+
1650 train 4.501699 (lr=1.1490e-03) (hash(x)=141061333)
|
| 202 |
+
1660 train 4.623842 (lr=1.1482e-03) (hash(x)=148064219)
|
| 203 |
+
1670 train 4.454599 (lr=1.1473e-03) (hash(x)=162799669)
|
| 204 |
+
1680 train 4.499043 (lr=1.1464e-03) (hash(x)=147474277)
|
| 205 |
+
1690 train 4.575129 (lr=1.1455e-03) (hash(x)=142369299)
|
| 206 |
+
1700 val loss 4.5886
|
| 207 |
+
1700 val perplexity 98.3532
|
| 208 |
+
1700 train 4.345064 (lr=1.1446e-03) (hash(x)=130835396)
|
| 209 |
+
1710 train 4.678625 (lr=1.1437e-03) (hash(x)=153173892)
|
| 210 |
+
1720 train 4.337577 (lr=1.1428e-03) (hash(x)=148451191)
|
| 211 |
+
1730 train 4.452821 (lr=1.1418e-03) (hash(x)=145047239)
|
| 212 |
+
1740 train 4.360914 (lr=1.1409e-03) (hash(x)=147187109)
|
| 213 |
+
1750 train 4.466157 (lr=1.1400e-03) (hash(x)=149493155)
|
| 214 |
+
1760 train 4.417027 (lr=1.1390e-03) (hash(x)=147647531)
|
| 215 |
+
1770 train 4.648774 (lr=1.1381e-03) (hash(x)=153677279)
|
| 216 |
+
1780 train 4.483948 (lr=1.1371e-03) (hash(x)=144314015)
|
| 217 |
+
1790 train 4.498517 (lr=1.1361e-03) (hash(x)=176962883)
|
| 218 |
+
1800 val loss 4.5503
|
| 219 |
+
1800 val perplexity 94.6609
|
| 220 |
+
1800 train 4.595906 (lr=1.1352e-03) (hash(x)=158851816)
|
| 221 |
+
1810 train 4.173228 (lr=1.1342e-03) (hash(x)=175415447)
|
| 222 |
+
1820 train 4.475898 (lr=1.1332e-03) (hash(x)=169829733)
|
| 223 |
+
1830 train 4.460073 (lr=1.1322e-03) (hash(x)=154116106)
|
| 224 |
+
1840 train 4.296570 (lr=1.1312e-03) (hash(x)=150168406)
|
| 225 |
+
1850 train 4.301556 (lr=1.1302e-03) (hash(x)=145782493)
|
| 226 |
+
1860 train 4.281737 (lr=1.1292e-03) (hash(x)=158111664)
|
| 227 |
+
1870 train 4.217637 (lr=1.1282e-03) (hash(x)=154837061)
|
| 228 |
+
1880 train 4.173563 (lr=1.1271e-03) (hash(x)=151363745)
|
| 229 |
+
1890 train 4.295354 (lr=1.1261e-03) (hash(x)=161283557)
|
| 230 |
+
1900 val loss 4.5415
|
| 231 |
+
1900 val perplexity 93.8312
|
| 232 |
+
1900 train 4.543294 (lr=1.1251e-03) (hash(x)=153313879)
|
| 233 |
+
1910 train 4.361296 (lr=1.1240e-03) (hash(x)=152272272)
|
| 234 |
+
1920 train 4.424660 (lr=1.1230e-03) (hash(x)=153648837)
|
| 235 |
+
1930 train 4.535228 (lr=1.1219e-03) (hash(x)=150161694)
|
| 236 |
+
1940 train 4.411074 (lr=1.1208e-03) (hash(x)=151235093)
|
| 237 |
+
1950 train 4.459749 (lr=1.1198e-03) (hash(x)=140582058)
|
| 238 |
+
1960 train 4.409209 (lr=1.1187e-03) (hash(x)=125616059)
|
| 239 |
+
1970 train 4.538680 (lr=1.1176e-03) (hash(x)=154353968)
|
| 240 |
+
1980 train 4.553346 (lr=1.1165e-03) (hash(x)=156063143)
|
| 241 |
+
1990 train 4.572001 (lr=1.1154e-03) (hash(x)=160927289)
|
| 242 |
+
2000 val loss 4.4972
|
| 243 |
+
2000 val perplexity 89.7687
|
| 244 |
+
2000 train 4.490731 (lr=1.1143e-03) (hash(x)=158245023)
|
| 245 |
+
2010 train 4.534901 (lr=1.1132e-03) (hash(x)=157096661)
|
| 246 |
+
2020 train 4.750103 (lr=1.1120e-03) (hash(x)=144994302)
|
| 247 |
+
2030 train 4.442916 (lr=1.1109e-03) (hash(x)=145742929)
|
| 248 |
+
2040 train 4.454543 (lr=1.1098e-03) (hash(x)=156958528)
|
| 249 |
+
2050 train 4.973023 (lr=1.1086e-03) (hash(x)=135313020)
|
| 250 |
+
2060 train 4.604349 (lr=1.1075e-03) (hash(x)=147309332)
|
| 251 |
+
2070 train 4.389680 (lr=1.1063e-03) (hash(x)=161720962)
|
| 252 |
+
2080 train 4.575774 (lr=1.1052e-03) (hash(x)=167204793)
|
| 253 |
+
2090 train 4.479274 (lr=1.1040e-03) (hash(x)=141325510)
|
| 254 |
+
2100 val loss 4.4712
|
| 255 |
+
2100 val perplexity 87.4634
|
| 256 |
+
2100 train 4.296272 (lr=1.1028e-03) (hash(x)=157204896)
|
| 257 |
+
2110 train 4.258873 (lr=1.1017e-03) (hash(x)=143077993)
|
| 258 |
+
2120 train 4.460779 (lr=1.1005e-03) (hash(x)=159032689)
|
| 259 |
+
2130 train 4.347858 (lr=1.0993e-03) (hash(x)=149513855)
|
| 260 |
+
2140 train 4.262276 (lr=1.0981e-03) (hash(x)=151678267)
|
| 261 |
+
2150 train 4.351796 (lr=1.0969e-03) (hash(x)=141309246)
|
| 262 |
+
2160 train 4.453807 (lr=1.0957e-03) (hash(x)=153935732)
|
| 263 |
+
2170 train 4.353261 (lr=1.0944e-03) (hash(x)=150668875)
|
| 264 |
+
2180 train 4.359627 (lr=1.0932e-03) (hash(x)=142033123)
|
| 265 |
+
2190 train 4.400106 (lr=1.0920e-03) (hash(x)=157015026)
|
| 266 |
+
2200 val loss 4.4628
|
| 267 |
+
2200 val perplexity 86.7335
|
| 268 |
+
2200 train 4.274426 (lr=1.0907e-03) (hash(x)=137541932)
|
| 269 |
+
2210 train 4.199095 (lr=1.0895e-03) (hash(x)=144424504)
|
| 270 |
+
2220 train 4.124374 (lr=1.0883e-03) (hash(x)=151015810)
|
| 271 |
+
2230 train 4.203579 (lr=1.0870e-03) (hash(x)=160707806)
|
| 272 |
+
2240 train 4.210435 (lr=1.0857e-03) (hash(x)=151874110)
|
| 273 |
+
2250 train 4.183490 (lr=1.0845e-03) (hash(x)=157341469)
|
| 274 |
+
2260 train 4.003013 (lr=1.0832e-03) (hash(x)=144563224)
|
| 275 |
+
2270 train 4.157713 (lr=1.0819e-03) (hash(x)=144878459)
|
| 276 |
+
2280 train 4.229084 (lr=1.0806e-03) (hash(x)=158331565)
|
| 277 |
+
2290 train 4.253307 (lr=1.0793e-03) (hash(x)=146875132)
|
| 278 |
+
2300 val loss 4.4501
|
| 279 |
+
2300 val perplexity 85.6350
|
| 280 |
+
2300 train 4.393061 (lr=1.0780e-03) (hash(x)=150149692)
|
| 281 |
+
2310 train 4.391582 (lr=1.0767e-03) (hash(x)=141206538)
|
| 282 |
+
2320 train 4.429655 (lr=1.0754e-03) (hash(x)=136219115)
|
| 283 |
+
2330 train 4.461800 (lr=1.0741e-03) (hash(x)=148496500)
|
| 284 |
+
2340 train 4.440364 (lr=1.0728e-03) (hash(x)=161388511)
|
| 285 |
+
2350 train 4.292878 (lr=1.0715e-03) (hash(x)=149433185)
|
| 286 |
+
2360 train 4.511472 (lr=1.0701e-03) (hash(x)=154659203)
|
| 287 |
+
2370 train 4.496448 (lr=1.0688e-03) (hash(x)=145696996)
|
| 288 |
+
2380 train 4.307777 (lr=1.0674e-03) (hash(x)=139915095)
|
| 289 |
+
2390 train 4.428535 (lr=1.0661e-03) (hash(x)=150567584)
|
| 290 |
+
2400 val loss 4.4305
|
| 291 |
+
2400 val perplexity 83.9713
|
| 292 |
+
2400 train 4.344971 (lr=1.0647e-03) (hash(x)=151730720)
|
| 293 |
+
2410 train 4.384171 (lr=1.0634e-03) (hash(x)=153136544)
|
| 294 |
+
2420 train 4.342879 (lr=1.0620e-03) (hash(x)=151004677)
|
| 295 |
+
2430 train 4.369178 (lr=1.0606e-03) (hash(x)=167118859)
|
| 296 |
+
2440 train 4.382798 (lr=1.0592e-03) (hash(x)=145433453)
|
| 297 |
+
2450 train 4.411444 (lr=1.0578e-03) (hash(x)=150913293)
|
| 298 |
+
2460 train 4.379098 (lr=1.0564e-03) (hash(x)=145674639)
|
| 299 |
+
2470 train 4.484651 (lr=1.0550e-03) (hash(x)=151022749)
|
| 300 |
+
2480 train 4.338229 (lr=1.0536e-03) (hash(x)=136621037)
|
| 301 |
+
2490 train 4.387036 (lr=1.0522e-03) (hash(x)=158100672)
|
| 302 |
+
2500 val loss 4.3958
|
| 303 |
+
2500 val perplexity 81.1121
|
| 304 |
+
2500 train 4.404529 (lr=1.0508e-03) (hash(x)=143406752)
|
| 305 |
+
2510 train 4.324270 (lr=1.0494e-03) (hash(x)=142664084)
|
| 306 |
+
2520 train 4.380427 (lr=1.0480e-03) (hash(x)=132174378)
|
| 307 |
+
2530 train 4.392709 (lr=1.0465e-03) (hash(x)=140760293)
|
| 308 |
+
2540 train 4.338997 (lr=1.0451e-03) (hash(x)=154863398)
|
| 309 |
+
2550 train 4.273774 (lr=1.0437e-03) (hash(x)=153042049)
|
| 310 |
+
2560 train 4.214525 (lr=1.0422e-03) (hash(x)=145339170)
|
| 311 |
+
2570 train 4.364367 (lr=1.0407e-03) (hash(x)=157656357)
|
| 312 |
+
2580 train 4.352256 (lr=1.0393e-03) (hash(x)=147899462)
|
| 313 |
+
2590 train 4.328138 (lr=1.0378e-03) (hash(x)=142812892)
|
| 314 |
+
2600 val loss 4.4162
|
| 315 |
+
2600 val perplexity 82.7770
|
| 316 |
+
2600 train 4.286908 (lr=1.0363e-03) (hash(x)=157272496)
|
| 317 |
+
2610 train 4.072866 (lr=1.0349e-03) (hash(x)=148923594)
|
| 318 |
+
2620 train 4.002738 (lr=1.0334e-03) (hash(x)=164654807)
|
| 319 |
+
2630 train 4.191705 (lr=1.0319e-03) (hash(x)=136419327)
|
| 320 |
+
2640 train 4.165152 (lr=1.0304e-03) (hash(x)=153420840)
|
| 321 |
+
2650 train 3.994519 (lr=1.0289e-03) (hash(x)=153693827)
|
| 322 |
+
2660 train 4.158392 (lr=1.0274e-03) (hash(x)=145574165)
|
| 323 |
+
2670 train 4.192242 (lr=1.0259e-03) (hash(x)=153894843)
|
| 324 |
+
2680 train 4.051522 (lr=1.0244e-03) (hash(x)=132234446)
|
| 325 |
+
2690 train 4.122947 (lr=1.0229e-03) (hash(x)=153430212)
|
| 326 |
+
2700 val loss 4.3959
|
| 327 |
+
2700 val perplexity 81.1200
|
| 328 |
+
2700 train 4.300157 (lr=1.0213e-03) (hash(x)=155342327)
|
| 329 |
+
2710 train 4.306634 (lr=1.0198e-03) (hash(x)=145797023)
|
| 330 |
+
2720 train 4.458131 (lr=1.0183e-03) (hash(x)=149220870)
|
| 331 |
+
2730 train 4.363703 (lr=1.0167e-03) (hash(x)=134069562)
|
| 332 |
+
2740 train 4.370448 (lr=1.0152e-03) (hash(x)=141560499)
|
| 333 |
+
2750 train 4.390449 (lr=1.0136e-03) (hash(x)=146000524)
|
| 334 |
+
2760 train 4.278594 (lr=1.0121e-03) (hash(x)=164710665)
|
| 335 |
+
2770 train 4.165776 (lr=1.0105e-03) (hash(x)=151199094)
|
| 336 |
+
2780 train 4.367261 (lr=1.0089e-03) (hash(x)=138625404)
|
| 337 |
+
2790 train 4.621789 (lr=1.0074e-03) (hash(x)=162766112)
|
| 338 |
+
2800 val loss 4.3641
|
| 339 |
+
2800 val perplexity 78.5808
|
| 340 |
+
2800 train 4.323768 (lr=1.0058e-03) (hash(x)=140626679)
|
| 341 |
+
2810 train 4.412624 (lr=1.0042e-03) (hash(x)=144248544)
|
| 342 |
+
2820 train 4.328740 (lr=1.0026e-03) (hash(x)=139378481)
|
| 343 |
+
2830 train 4.260414 (lr=1.0010e-03) (hash(x)=150173403)
|
| 344 |
+
2840 train 4.557928 (lr=9.9943e-04) (hash(x)=160168705)
|
| 345 |
+
2850 train 4.342053 (lr=9.9783e-04) (hash(x)=149480059)
|
| 346 |
+
2860 train 4.387614 (lr=9.9622e-04) (hash(x)=155559096)
|
| 347 |
+
2870 train 4.321328 (lr=9.9461e-04) (hash(x)=158825683)
|
| 348 |
+
2880 train 4.494553 (lr=9.9300e-04) (hash(x)=152129048)
|
| 349 |
+
2890 train 4.169604 (lr=9.9138e-04) (hash(x)=157866544)
|
| 350 |
+
2900 val loss 4.3438
|
| 351 |
+
2900 val perplexity 77.0015
|
| 352 |
+
2900 train 4.296373 (lr=9.8975e-04) (hash(x)=144953350)
|
| 353 |
+
2910 train 4.504882 (lr=9.8812e-04) (hash(x)=154103497)
|
| 354 |
+
2920 train 4.216828 (lr=9.8648e-04) (hash(x)=144467854)
|
| 355 |
+
2930 train 4.148761 (lr=9.8484e-04) (hash(x)=153784048)
|
| 356 |
+
2940 train 4.436899 (lr=9.8320e-04) (hash(x)=154774534)
|
| 357 |
+
2950 train 4.294656 (lr=9.8155e-04) (hash(x)=143988507)
|
| 358 |
+
2960 train 4.174391 (lr=9.7989e-04) (hash(x)=159552857)
|
| 359 |
+
2970 train 4.477135 (lr=9.7824e-04) (hash(x)=175539144)
|
| 360 |
+
2980 train 4.359574 (lr=9.7657e-04) (hash(x)=158172686)
|
| 361 |
+
2990 train 4.235113 (lr=9.7490e-04) (hash(x)=147553039)
|
| 362 |
+
3000 val loss 4.3513
|
| 363 |
+
3000 val perplexity 77.5777
|
| 364 |
+
3000 train 4.159828 (lr=9.7323e-04) (hash(x)=172449837)
|
| 365 |
+
3010 train 4.044053 (lr=9.7155e-04) (hash(x)=153285123)
|
| 366 |
+
3020 train 4.219427 (lr=9.6987e-04) (hash(x)=145307252)
|
| 367 |
+
3030 train 4.279302 (lr=9.6819e-04) (hash(x)=147739766)
|
| 368 |
+
3040 train 4.000305 (lr=9.6649e-04) (hash(x)=154414400)
|
| 369 |
+
3050 train 4.080393 (lr=9.6480e-04) (hash(x)=150696487)
|
| 370 |
+
3060 train 4.082495 (lr=9.6310e-04) (hash(x)=154543441)
|
| 371 |
+
3070 train 3.860185 (lr=9.6140e-04) (hash(x)=170733242)
|
| 372 |
+
3080 train 4.214581 (lr=9.5969e-04) (hash(x)=161914669)
|
| 373 |
+
3090 train 4.109222 (lr=9.5797e-04) (hash(x)=156125491)
|
| 374 |
+
3100 val loss 4.3696
|
| 375 |
+
3100 val perplexity 79.0094
|
| 376 |
+
3100 train 3.998011 (lr=9.5626e-04) (hash(x)=141710086)
|
| 377 |
+
3110 train 4.304519 (lr=9.5454e-04) (hash(x)=154547635)
|
| 378 |
+
3120 train 4.154260 (lr=9.5281e-04) (hash(x)=151747171)
|
| 379 |
+
3130 train 4.436217 (lr=9.5108e-04) (hash(x)=160311353)
|
| 380 |
+
3140 train 4.548502 (lr=9.4935e-04) (hash(x)=157233821)
|
| 381 |
+
3150 train 4.365603 (lr=9.4761e-04) (hash(x)=153016810)
|
| 382 |
+
3160 train 4.332740 (lr=9.4587e-04) (hash(x)=157289875)
|
| 383 |
+
3170 train 4.331023 (lr=9.4412e-04) (hash(x)=157459484)
|
| 384 |
+
3180 train 4.254135 (lr=9.4237e-04) (hash(x)=162037435)
|
| 385 |
+
3190 train 4.350301 (lr=9.4061e-04) (hash(x)=159360169)
|
| 386 |
+
3200 val loss 4.3145
|
| 387 |
+
3200 val perplexity 74.7736
|
| 388 |
+
3200 train 4.234976 (lr=9.3885e-04) (hash(x)=151299772)
|
| 389 |
+
3210 train 4.460176 (lr=9.3709e-04) (hash(x)=183865364)
|
| 390 |
+
3220 train 4.207427 (lr=9.3532e-04) (hash(x)=139622592)
|
| 391 |
+
3230 train 4.163662 (lr=9.3355e-04) (hash(x)=147102655)
|
| 392 |
+
3240 train 4.222013 (lr=9.3178e-04) (hash(x)=161870696)
|
| 393 |
+
3250 train 4.371922 (lr=9.3000e-04) (hash(x)=152692231)
|
| 394 |
+
3260 train 4.115882 (lr=9.2822e-04) (hash(x)=149990134)
|
| 395 |
+
3270 train 4.093308 (lr=9.2643e-04) (hash(x)=134848432)
|
| 396 |
+
3280 train 4.153458 (lr=9.2464e-04) (hash(x)=138519418)
|
| 397 |
+
3290 train 4.282721 (lr=9.2285e-04) (hash(x)=139301249)
|
| 398 |
+
3300 val loss 4.3173
|
| 399 |
+
3300 val perplexity 74.9867
|
| 400 |
+
3300 train 4.125478 (lr=9.2105e-04) (hash(x)=146473110)
|
| 401 |
+
3310 train 4.189485 (lr=9.1925e-04) (hash(x)=144833685)
|
| 402 |
+
3320 train 4.094378 (lr=9.1744e-04) (hash(x)=148953545)
|
| 403 |
+
3330 train 4.326285 (lr=9.1563e-04) (hash(x)=161302371)
|
| 404 |
+
3340 train 4.256340 (lr=9.1382e-04) (hash(x)=144215411)
|
| 405 |
+
3350 train 4.429482 (lr=9.1200e-04) (hash(x)=157713664)
|
| 406 |
+
3360 train 4.297342 (lr=9.1018e-04) (hash(x)=150813928)
|
| 407 |
+
3370 train 4.281432 (lr=9.0836e-04) (hash(x)=150889463)
|
| 408 |
+
3380 train 4.331371 (lr=9.0653e-04) (hash(x)=156631928)
|
| 409 |
+
3390 train 4.360106 (lr=9.0470e-04) (hash(x)=136001579)
|
| 410 |
+
3400 val loss 4.2940
|
| 411 |
+
3400 val perplexity 73.2568
|
| 412 |
+
3400 train 4.436232 (lr=9.0286e-04) (hash(x)=153954157)
|
| 413 |
+
3410 train 4.221395 (lr=9.0102e-04) (hash(x)=150012477)
|
| 414 |
+
3420 train 4.581305 (lr=8.9918e-04) (hash(x)=160878899)
|
| 415 |
+
3430 train 4.612657 (lr=8.9734e-04) (hash(x)=128131106)
|
| 416 |
+
3440 train 4.534104 (lr=8.9549e-04) (hash(x)=149611866)
|
| 417 |
+
3450 train 4.167780 (lr=8.9364e-04) (hash(x)=166942460)
|
| 418 |
+
3460 train 4.323987 (lr=8.9178e-04) (hash(x)=150498414)
|
| 419 |
+
3470 train 4.462865 (lr=8.8992e-04) (hash(x)=144342279)
|
| 420 |
+
3480 train 4.300633 (lr=8.8806e-04) (hash(x)=148891764)
|
| 421 |
+
3490 train 4.269976 (lr=8.8619e-04) (hash(x)=157308188)
|
| 422 |
+
3500 val loss 4.2842
|
| 423 |
+
3500 val perplexity 72.5478
|
| 424 |
+
3500 train 4.176987 (lr=8.8432e-04) (hash(x)=153717336)
|
| 425 |
+
3510 train 4.202427 (lr=8.8245e-04) (hash(x)=156083924)
|
| 426 |
+
3520 train 4.189377 (lr=8.8058e-04) (hash(x)=144234966)
|
| 427 |
+
3530 train 4.271102 (lr=8.7870e-04) (hash(x)=150184381)
|
| 428 |
+
3540 train 4.159916 (lr=8.7682e-04) (hash(x)=143011198)
|
| 429 |
+
3550 train 4.309648 (lr=8.7493e-04) (hash(x)=148764613)
|
| 430 |
+
3560 train 4.065536 (lr=8.7304e-04) (hash(x)=150625329)
|
| 431 |
+
3570 train 4.178932 (lr=8.7115e-04) (hash(x)=143981302)
|
| 432 |
+
3580 train 4.233986 (lr=8.6926e-04) (hash(x)=154989703)
|
| 433 |
+
3590 train 4.360559 (lr=8.6736e-04) (hash(x)=146602526)
|
| 434 |
+
3600 val loss 4.2800
|
| 435 |
+
3600 val perplexity 72.2440
|
| 436 |
+
3600 train 4.064428 (lr=8.6546e-04) (hash(x)=144965161)
|
| 437 |
+
3610 train 4.059069 (lr=8.6356e-04) (hash(x)=159452243)
|
| 438 |
+
3620 train 4.043866 (lr=8.6165e-04) (hash(x)=144904300)
|
| 439 |
+
3630 train 3.954698 (lr=8.5974e-04) (hash(x)=127790212)
|
| 440 |
+
3640 train 4.194890 (lr=8.5783e-04) (hash(x)=150863158)
|
| 441 |
+
3650 train 4.157388 (lr=8.5592e-04) (hash(x)=145691635)
|
| 442 |
+
3660 train 4.139422 (lr=8.5400e-04) (hash(x)=150631264)
|
| 443 |
+
3670 train 4.114650 (lr=8.5208e-04) (hash(x)=148646259)
|
| 444 |
+
3680 train 4.082514 (lr=8.5015e-04) (hash(x)=139317386)
|
| 445 |
+
3690 train 4.190567 (lr=8.4823e-04) (hash(x)=142206916)
|
| 446 |
+
3700 val loss 4.2943
|
| 447 |
+
3700 val perplexity 73.2790
|
| 448 |
+
3700 train 4.196024 (lr=8.4630e-04) (hash(x)=125969741)
|
| 449 |
+
3710 train 4.042959 (lr=8.4437e-04) (hash(x)=157183915)
|
| 450 |
+
3720 train 4.028553 (lr=8.4243e-04) (hash(x)=150434369)
|
| 451 |
+
3730 train 4.225134 (lr=8.4050e-04) (hash(x)=160911722)
|
| 452 |
+
3740 train 4.114355 (lr=8.3856e-04) (hash(x)=163306921)
|
| 453 |
+
3750 train 4.235348 (lr=8.3662e-04) (hash(x)=149156876)
|
| 454 |
+
3760 train 4.377959 (lr=8.3467e-04) (hash(x)=156015970)
|
| 455 |
+
3770 train 4.317109 (lr=8.3273e-04) (hash(x)=148222322)
|
| 456 |
+
3780 train 4.422432 (lr=8.3078e-04) (hash(x)=172040174)
|
| 457 |
+
3790 train 4.326936 (lr=8.2882e-04) (hash(x)=151593070)
|
| 458 |
+
3800 val loss 4.2642
|
| 459 |
+
3800 val perplexity 71.1065
|
| 460 |
+
3800 train 4.083686 (lr=8.2687e-04) (hash(x)=155070487)
|
| 461 |
+
3810 train 4.273068 (lr=8.2491e-04) (hash(x)=137073164)
|
| 462 |
+
3820 train 4.172925 (lr=8.2295e-04) (hash(x)=147761510)
|
| 463 |
+
3830 train 4.094745 (lr=8.2099e-04) (hash(x)=154763021)
|
| 464 |
+
3840 train 4.139504 (lr=8.1903e-04) (hash(x)=149622435)
|
| 465 |
+
3850 train 4.249288 (lr=8.1706e-04) (hash(x)=150779423)
|
| 466 |
+
3860 train 4.222582 (lr=8.1509e-04) (hash(x)=139445120)
|
| 467 |
+
3870 train 4.202474 (lr=8.1312e-04) (hash(x)=151884947)
|
| 468 |
+
3880 train 4.204114 (lr=8.1115e-04) (hash(x)=139795201)
|
| 469 |
+
3890 train 4.248280 (lr=8.0917e-04) (hash(x)=155589956)
|
| 470 |
+
3900 val loss 4.2508
|
| 471 |
+
3900 val perplexity 70.1599
|
| 472 |
+
3900 train 4.178463 (lr=8.0720e-04) (hash(x)=149444644)
|
| 473 |
+
3910 train 4.172431 (lr=8.0522e-04) (hash(x)=148538323)
|
| 474 |
+
3920 train 4.290403 (lr=8.0324e-04) (hash(x)=144026925)
|
| 475 |
+
3930 train 4.173790 (lr=8.0125e-04) (hash(x)=155311200)
|
| 476 |
+
3940 train 4.146957 (lr=7.9927e-04) (hash(x)=142410034)
|
| 477 |
+
3950 train 4.129738 (lr=7.9728e-04) (hash(x)=145986075)
|
| 478 |
+
3960 train 4.034800 (lr=7.9529e-04) (hash(x)=156197753)
|
| 479 |
+
3970 train 4.181997 (lr=7.9330e-04) (hash(x)=146981564)
|
| 480 |
+
3980 train 4.496729 (lr=7.9130e-04) (hash(x)=145361976)
|
| 481 |
+
3990 train 4.223596 (lr=7.8931e-04) (hash(x)=149344475)
|
| 482 |
+
4000 val loss 4.2467
|
| 483 |
+
4000 val perplexity 69.8764
|
| 484 |
+
4000 train 4.105182 (lr=7.8731e-04) (hash(x)=151663033)
|
| 485 |
+
4010 train 3.988441 (lr=7.8531e-04) (hash(x)=140915499)
|
| 486 |
+
4020 train 4.213029 (lr=7.8331e-04) (hash(x)=159979134)
|
| 487 |
+
4030 train 4.134548 (lr=7.8131e-04) (hash(x)=163081433)
|
| 488 |
+
4040 train 4.006662 (lr=7.7930e-04) (hash(x)=144890231)
|
| 489 |
+
4050 train 4.182634 (lr=7.7730e-04) (hash(x)=138242368)
|
| 490 |
+
4060 train 4.075220 (lr=7.7529e-04) (hash(x)=144438406)
|
| 491 |
+
4070 train 3.954852 (lr=7.7328e-04) (hash(x)=159294906)
|
| 492 |
+
4080 train 4.015694 (lr=7.7127e-04) (hash(x)=143676301)
|
| 493 |
+
4090 train 4.250175 (lr=7.6925e-04) (hash(x)=147875296)
|
| 494 |
+
4100 val loss 4.2620
|
| 495 |
+
4100 val perplexity 70.9517
|
| 496 |
+
4100 train 4.315056 (lr=7.6724e-04) (hash(x)=143688282)
|
| 497 |
+
4110 train 4.075085 (lr=7.6522e-04) (hash(x)=150086777)
|
| 498 |
+
4120 train 4.032660 (lr=7.6321e-04) (hash(x)=154624391)
|
| 499 |
+
4130 train 4.213395 (lr=7.6119e-04) (hash(x)=141163032)
|
| 500 |
+
4140 train 4.237598 (lr=7.5917e-04) (hash(x)=151038180)
|
| 501 |
+
4150 train 4.318644 (lr=7.5714e-04) (hash(x)=144718421)
|
| 502 |
+
4160 train 4.235207 (lr=7.5512e-04) (hash(x)=154277459)
|
| 503 |
+
4170 train 4.392091 (lr=7.5309e-04) (hash(x)=143765173)
|
| 504 |
+
4180 train 4.264243 (lr=7.5107e-04) (hash(x)=161013425)
|
| 505 |
+
4190 train 4.223252 (lr=7.4904e-04) (hash(x)=161666854)
|
| 506 |
+
4200 val loss 4.2255
|
| 507 |
+
4200 val perplexity 68.4074
|
| 508 |
+
4200 train 4.133971 (lr=7.4701e-04) (hash(x)=163361651)
|
| 509 |
+
4210 train 4.468192 (lr=7.4498e-04) (hash(x)=153491528)
|
| 510 |
+
4220 train 4.265892 (lr=7.4295e-04) (hash(x)=164410385)
|
| 511 |
+
4230 train 4.208070 (lr=7.4092e-04) (hash(x)=175191816)
|
| 512 |
+
4240 train 4.080769 (lr=7.3888e-04) (hash(x)=133924818)
|
| 513 |
+
4250 train 4.309552 (lr=7.3685e-04) (hash(x)=152932845)
|
| 514 |
+
4260 train 4.178353 (lr=7.3481e-04) (hash(x)=141987318)
|
| 515 |
+
4270 train 4.271982 (lr=7.3278e-04) (hash(x)=142521279)
|
| 516 |
+
4280 train 4.136922 (lr=7.3074e-04) (hash(x)=147707669)
|
| 517 |
+
4290 train 4.203806 (lr=7.2870e-04) (hash(x)=152245539)
|
| 518 |
+
4300 val loss 4.2116
|
| 519 |
+
4300 val perplexity 67.4657
|
| 520 |
+
4300 train 4.095089 (lr=7.2666e-04) (hash(x)=153619361)
|
| 521 |
+
4310 train 4.300336 (lr=7.2462e-04) (hash(x)=142614473)
|
| 522 |
+
4320 train 4.120403 (lr=7.2258e-04) (hash(x)=142689858)
|
| 523 |
+
4330 train 4.145303 (lr=7.2053e-04) (hash(x)=140837891)
|
| 524 |
+
4340 train 4.131041 (lr=7.1849e-04) (hash(x)=131790760)
|
| 525 |
+
4350 train 4.295598 (lr=7.1645e-04) (hash(x)=147186292)
|
| 526 |
+
4360 train 4.107206 (lr=7.1440e-04) (hash(x)=148140562)
|
| 527 |
+
4370 train 4.216874 (lr=7.1235e-04) (hash(x)=156409913)
|
| 528 |
+
4380 train 4.127831 (lr=7.1031e-04) (hash(x)=145126034)
|
| 529 |
+
4390 train 4.075968 (lr=7.0826e-04) (hash(x)=147368423)
|
| 530 |
+
4400 val loss 4.2152
|
| 531 |
+
4400 val perplexity 67.7103
|
| 532 |
+
4400 train 4.556031 (lr=7.0621e-04) (hash(x)=168527064)
|
| 533 |
+
4410 train 4.068285 (lr=7.0416e-04) (hash(x)=150152773)
|
| 534 |
+
4420 train 4.158576 (lr=7.0211e-04) (hash(x)=155472304)
|
| 535 |
+
4430 train 4.092190 (lr=7.0006e-04) (hash(x)=147299265)
|
| 536 |
+
4440 train 4.066811 (lr=6.9801e-04) (hash(x)=140659522)
|
| 537 |
+
4450 train 4.112331 (lr=6.9596e-04) (hash(x)=147169111)
|
| 538 |
+
4460 train 4.180674 (lr=6.9391e-04) (hash(x)=144098557)
|
| 539 |
+
4470 train 3.938227 (lr=6.9185e-04) (hash(x)=161957507)
|
| 540 |
+
4480 train 3.965213 (lr=6.8980e-04) (hash(x)=154064204)
|
| 541 |
+
4490 train 4.099475 (lr=6.8775e-04) (hash(x)=153999958)
|
| 542 |
+
4500 val loss 4.2288
|
| 543 |
+
4500 val perplexity 68.6346
|
| 544 |
+
4500 train 4.256774 (lr=6.8569e-04) (hash(x)=125588037)
|
| 545 |
+
4510 train 4.055616 (lr=6.8364e-04) (hash(x)=142522186)
|
| 546 |
+
4520 train 3.900446 (lr=6.8159e-04) (hash(x)=152736893)
|
| 547 |
+
4530 train 4.130034 (lr=6.7953e-04) (hash(x)=148091275)
|
| 548 |
+
4540 train 4.244890 (lr=6.7748e-04) (hash(x)=147663019)
|
| 549 |
+
4550 train 4.328283 (lr=6.7542e-04) (hash(x)=151491857)
|
| 550 |
+
4560 train 4.210903 (lr=6.7336e-04) (hash(x)=161757513)
|
| 551 |
+
4570 train 4.201483 (lr=6.7131e-04) (hash(x)=165448260)
|
| 552 |
+
4580 train 4.340016 (lr=6.6925e-04) (hash(x)=151620292)
|
| 553 |
+
4590 train 4.416916 (lr=6.6720e-04) (hash(x)=161877852)
|
| 554 |
+
4600 val loss 4.1902
|
| 555 |
+
4600 val perplexity 66.0328
|
| 556 |
+
4600 train 4.167441 (lr=6.6514e-04) (hash(x)=143710941)
|
| 557 |
+
4610 train 4.261973 (lr=6.6308e-04) (hash(x)=152244871)
|
| 558 |
+
4620 train 4.211172 (lr=6.6103e-04) (hash(x)=161268167)
|
| 559 |
+
4630 train 4.200485 (lr=6.5897e-04) (hash(x)=153904677)
|
| 560 |
+
4640 train 4.161034 (lr=6.5692e-04) (hash(x)=152593758)
|
| 561 |
+
4650 train 4.312203 (lr=6.5486e-04) (hash(x)=159047122)
|
| 562 |
+
4660 train 4.382846 (lr=6.5280e-04) (hash(x)=167370244)
|
| 563 |
+
4670 train 4.153875 (lr=6.5075e-04) (hash(x)=140357684)
|
| 564 |
+
4680 train 4.305804 (lr=6.4869e-04) (hash(x)=140547853)
|
| 565 |
+
4690 train 4.487305 (lr=6.4664e-04) (hash(x)=143000949)
|
| 566 |
+
4700 val loss 4.1850
|
| 567 |
+
4700 val perplexity 65.6936
|
| 568 |
+
4700 train 4.115927 (lr=6.4458e-04) (hash(x)=150952742)
|
| 569 |
+
4710 train 4.170420 (lr=6.4252e-04) (hash(x)=157964406)
|
| 570 |
+
4720 train 4.058089 (lr=6.4047e-04) (hash(x)=147653608)
|
| 571 |
+
4730 train 4.135849 (lr=6.3841e-04) (hash(x)=165545764)
|
| 572 |
+
4740 train 4.119219 (lr=6.3636e-04) (hash(x)=146744631)
|
| 573 |
+
4750 train 4.199740 (lr=6.3431e-04) (hash(x)=153635164)
|
| 574 |
+
4760 train 4.248627 (lr=6.3225e-04) (hash(x)=153217508)
|
| 575 |
+
4770 train 4.288467 (lr=6.3020e-04) (hash(x)=169622743)
|
| 576 |
+
4780 train 4.120420 (lr=6.2815e-04) (hash(x)=138018297)
|
| 577 |
+
4790 train 3.994079 (lr=6.2609e-04) (hash(x)=156067303)
|
| 578 |
+
4800 val loss 4.1827
|
| 579 |
+
4800 val perplexity 65.5400
|
| 580 |
+
4800 train 4.170136 (lr=6.2404e-04) (hash(x)=145323659)
|
| 581 |
+
4810 train 4.055809 (lr=6.2199e-04) (hash(x)=152587772)
|
| 582 |
+
4820 train 4.278728 (lr=6.1994e-04) (hash(x)=148481485)
|
| 583 |
+
4830 train 4.043983 (lr=6.1789e-04) (hash(x)=154219664)
|
| 584 |
+
4840 train 3.925792 (lr=6.1584e-04) (hash(x)=156853645)
|
| 585 |
+
4850 train 4.012112 (lr=6.1379e-04) (hash(x)=152329702)
|
| 586 |
+
4860 train 4.010230 (lr=6.1174e-04) (hash(x)=136684779)
|
| 587 |
+
4870 train 4.073963 (lr=6.0969e-04) (hash(x)=143260367)
|
| 588 |
+
4880 train 4.031417 (lr=6.0765e-04) (hash(x)=150910947)
|
| 589 |
+
4890 train 4.057988 (lr=6.0560e-04) (hash(x)=179249925)
|
| 590 |
+
4900 val loss 4.1904
|
| 591 |
+
4900 val perplexity 66.0507
|
| 592 |
+
4900 train 4.210465 (lr=6.0355e-04) (hash(x)=153151397)
|
| 593 |
+
4910 train 4.165105 (lr=6.0151e-04) (hash(x)=144101891)
|
| 594 |
+
4920 train 4.056757 (lr=5.9947e-04) (hash(x)=144994952)
|
| 595 |
+
4930 train 4.347969 (lr=5.9742e-04) (hash(x)=155390878)
|
| 596 |
+
4940 train 4.122891 (lr=5.9538e-04) (hash(x)=141359221)
|
| 597 |
+
4950 train 4.029159 (lr=5.9334e-04) (hash(x)=151570011)
|
| 598 |
+
4960 train 4.246418 (lr=5.9130e-04) (hash(x)=146918855)
|
| 599 |
+
4970 train 4.180827 (lr=5.8926e-04) (hash(x)=148647362)
|
| 600 |
+
4980 train 4.138757 (lr=5.8722e-04) (hash(x)=159753562)
|
| 601 |
+
4990 train 4.087659 (lr=5.8519e-04) (hash(x)=147683447)
|
| 602 |
+
5000 val loss 4.1796
|
| 603 |
+
5000 val perplexity 65.3408
|
| 604 |
+
5000 train 4.228114 (lr=5.8315e-04) (hash(x)=143182059)
|
| 605 |
+
5010 train 4.035646 (lr=5.8112e-04) (hash(x)=138657407)
|
| 606 |
+
5020 train 4.143503 (lr=5.7908e-04) (hash(x)=151830497)
|
| 607 |
+
5030 train 4.137726 (lr=5.7705e-04) (hash(x)=147727694)
|
| 608 |
+
5040 train 3.978547 (lr=5.7502e-04) (hash(x)=151957014)
|
| 609 |
+
5050 train 4.242515 (lr=5.7299e-04) (hash(x)=147828693)
|
| 610 |
+
5060 train 4.299127 (lr=5.7096e-04) (hash(x)=158589700)
|
| 611 |
+
5070 train 4.184930 (lr=5.6893e-04) (hash(x)=155662163)
|
| 612 |
+
5080 train 4.301843 (lr=5.6691e-04) (hash(x)=157797383)
|
| 613 |
+
5090 train 4.167457 (lr=5.6488e-04) (hash(x)=153848957)
|
| 614 |
+
5100 val loss 4.1660
|
| 615 |
+
5100 val perplexity 64.4543
|
| 616 |
+
5100 train 4.121503 (lr=5.6286e-04) (hash(x)=170083586)
|
| 617 |
+
5110 train 4.041676 (lr=5.6083e-04) (hash(x)=153800138)
|
| 618 |
+
5120 train 4.135445 (lr=5.5881e-04) (hash(x)=153526228)
|
| 619 |
+
5130 train 4.150413 (lr=5.5679e-04) (hash(x)=158650342)
|
| 620 |
+
5140 train 4.145401 (lr=5.5478e-04) (hash(x)=153163034)
|
| 621 |
+
5150 train 4.135987 (lr=5.5276e-04) (hash(x)=155281294)
|
| 622 |
+
5160 train 4.114844 (lr=5.5075e-04) (hash(x)=147731627)
|
| 623 |
+
5170 train 4.095918 (lr=5.4873e-04) (hash(x)=146388976)
|
| 624 |
+
5180 train 4.305400 (lr=5.4672e-04) (hash(x)=140323065)
|
| 625 |
+
5190 train 4.210309 (lr=5.4471e-04) (hash(x)=150406523)
|
| 626 |
+
5200 val loss 4.1596
|
| 627 |
+
5200 val perplexity 64.0464
|
| 628 |
+
5200 train 4.020193 (lr=5.4270e-04) (hash(x)=149363919)
|
| 629 |
+
5210 train 4.163621 (lr=5.4070e-04) (hash(x)=164390214)
|
| 630 |
+
5220 train 4.120431 (lr=5.3869e-04) (hash(x)=153652984)
|
| 631 |
+
5230 train 4.082411 (lr=5.3669e-04) (hash(x)=139542770)
|
| 632 |
+
5240 train 3.968673 (lr=5.3469e-04) (hash(x)=140115288)
|
| 633 |
+
5250 train 4.099965 (lr=5.3269e-04) (hash(x)=142158900)
|
| 634 |
+
5260 train 4.019733 (lr=5.3069e-04) (hash(x)=156019449)
|
| 635 |
+
5270 train 4.140660 (lr=5.2870e-04) (hash(x)=150776850)
|
| 636 |
+
5280 train 4.089438 (lr=5.2670e-04) (hash(x)=151358692)
|
| 637 |
+
5290 train 4.054388 (lr=5.2471e-04) (hash(x)=137112863)
|
| 638 |
+
5300 val loss 4.1555
|
| 639 |
+
5300 val perplexity 63.7854
|
| 640 |
+
5300 train 3.986618 (lr=5.2272e-04) (hash(x)=152033784)
|
| 641 |
+
5310 train 4.026261 (lr=5.2073e-04) (hash(x)=147785712)
|
| 642 |
+
5320 train 4.163860 (lr=5.1875e-04) (hash(x)=156426339)
|
| 643 |
+
5330 train 4.113514 (lr=5.1676e-04) (hash(x)=161907693)
|
| 644 |
+
5340 train 4.182077 (lr=5.1478e-04) (hash(x)=156414094)
|
| 645 |
+
5350 train 4.205866 (lr=5.1280e-04) (hash(x)=141712428)
|
| 646 |
+
5360 train 4.164051 (lr=5.1083e-04) (hash(x)=156873601)
|
| 647 |
+
5370 train 4.137769 (lr=5.0885e-04) (hash(x)=149863781)
|
| 648 |
+
5380 train 4.133194 (lr=5.0688e-04) (hash(x)=148183971)
|
| 649 |
+
5390 train 4.098209 (lr=5.0491e-04) (hash(x)=151542334)
|
| 650 |
+
5400 val loss 4.1334
|
| 651 |
+
5400 val perplexity 62.3881
|
| 652 |
+
5400 train 4.381930 (lr=5.0294e-04) (hash(x)=154614289)
|
| 653 |
+
5410 train 4.121605 (lr=5.0097e-04) (hash(x)=169124671)
|
| 654 |
+
5420 train 4.142497 (lr=4.9901e-04) (hash(x)=159963738)
|
| 655 |
+
5430 train 4.107469 (lr=4.9705e-04) (hash(x)=155162691)
|
| 656 |
+
5440 train 4.140220 (lr=4.9509e-04) (hash(x)=135981908)
|
| 657 |
+
5450 train 4.226433 (lr=4.9313e-04) (hash(x)=145055580)
|
| 658 |
+
5460 train 4.081604 (lr=4.9118e-04) (hash(x)=150367825)
|
| 659 |
+
5470 train 4.176122 (lr=4.8922e-04) (hash(x)=151034173)
|
| 660 |
+
5480 train 4.085387 (lr=4.8727e-04) (hash(x)=155581766)
|
| 661 |
+
5490 train 4.113827 (lr=4.8533e-04) (hash(x)=136973993)
|
| 662 |
+
5500 val loss 4.1296
|
| 663 |
+
5500 val perplexity 62.1510
|
| 664 |
+
5500 train 4.282928 (lr=4.8338e-04) (hash(x)=157745174)
|
| 665 |
+
5510 train 4.238008 (lr=4.8144e-04) (hash(x)=144628894)
|
| 666 |
+
5520 train 4.126855 (lr=4.7950e-04) (hash(x)=135056684)
|
| 667 |
+
5530 train 4.105862 (lr=4.7757e-04) (hash(x)=143418640)
|
| 668 |
+
5540 train 4.087547 (lr=4.7563e-04) (hash(x)=144464984)
|
| 669 |
+
5550 train 4.292607 (lr=4.7370e-04) (hash(x)=155888745)
|
| 670 |
+
5560 train 3.955600 (lr=4.7177e-04) (hash(x)=149122683)
|
| 671 |
+
5570 train 4.004164 (lr=4.6985e-04) (hash(x)=154573954)
|
| 672 |
+
5580 train 4.104811 (lr=4.6792e-04) (hash(x)=149339361)
|
| 673 |
+
5590 train 3.999426 (lr=4.6600e-04) (hash(x)=154738453)
|
| 674 |
+
5600 val loss 4.1320
|
| 675 |
+
5600 val perplexity 62.3027
|
| 676 |
+
5600 train 4.105721 (lr=4.6408e-04) (hash(x)=147693222)
|
| 677 |
+
5610 train 3.879405 (lr=4.6217e-04) (hash(x)=142140192)
|
| 678 |
+
5620 train 4.018399 (lr=4.6026e-04) (hash(x)=148677209)
|
| 679 |
+
5630 train 4.081159 (lr=4.5835e-04) (hash(x)=143495554)
|
| 680 |
+
5640 train 4.172872 (lr=4.5644e-04) (hash(x)=153202964)
|
| 681 |
+
5650 train 4.102839 (lr=4.5454e-04) (hash(x)=168724867)
|
| 682 |
+
5660 train 4.062845 (lr=4.5264e-04) (hash(x)=142816746)
|
| 683 |
+
5670 train 4.188557 (lr=4.5074e-04) (hash(x)=164119551)
|
| 684 |
+
5680 train 4.054228 (lr=4.4885e-04) (hash(x)=157239121)
|
| 685 |
+
5690 train 4.335939 (lr=4.4696e-04) (hash(x)=144662329)
|
| 686 |
+
5700 val loss 4.1174
|
| 687 |
+
5700 val perplexity 61.3982
|
| 688 |
+
5700 train 4.048573 (lr=4.4507e-04) (hash(x)=149784627)
|
| 689 |
+
5710 train 4.018644 (lr=4.4318e-04) (hash(x)=152821162)
|
| 690 |
+
5720 train 4.226550 (lr=4.4130e-04) (hash(x)=158497530)
|
| 691 |
+
5730 train 4.222623 (lr=4.3942e-04) (hash(x)=154583914)
|
| 692 |
+
5740 train 4.044950 (lr=4.3755e-04) (hash(x)=142027172)
|
| 693 |
+
5750 train 4.280810 (lr=4.3568e-04) (hash(x)=119227402)
|
| 694 |
+
5760 train 4.131145 (lr=4.3381e-04) (hash(x)=153248187)
|
| 695 |
+
5770 train 4.002223 (lr=4.3194e-04) (hash(x)=147951994)
|
| 696 |
+
5780 train 4.026761 (lr=4.3008e-04) (hash(x)=138935284)
|
| 697 |
+
5790 train 4.103162 (lr=4.2822e-04) (hash(x)=151786681)
|
| 698 |
+
5800 val loss 4.1258
|
| 699 |
+
5800 val perplexity 61.9194
|
| 700 |
+
5800 train 4.143536 (lr=4.2636e-04) (hash(x)=158620729)
|
| 701 |
+
5810 train 4.092229 (lr=4.2451e-04) (hash(x)=178115789)
|
| 702 |
+
5820 train 4.008683 (lr=4.2266e-04) (hash(x)=149092790)
|
| 703 |
+
5830 train 4.189038 (lr=4.2082e-04) (hash(x)=148269833)
|
| 704 |
+
5840 train 4.127838 (lr=4.1898e-04) (hash(x)=163714738)
|
| 705 |
+
5850 train 4.104153 (lr=4.1714e-04) (hash(x)=144111890)
|
| 706 |
+
5860 train 4.071476 (lr=4.1530e-04) (hash(x)=170702475)
|
| 707 |
+
5870 train 4.003782 (lr=4.1347e-04) (hash(x)=155970835)
|
| 708 |
+
5880 train 4.011779 (lr=4.1164e-04) (hash(x)=146695463)
|
| 709 |
+
5890 train 4.071497 (lr=4.0982e-04) (hash(x)=151603187)
|
| 710 |
+
5900 val loss 4.1120
|
| 711 |
+
5900 val perplexity 61.0685
|
| 712 |
+
5900 train 4.088852 (lr=4.0800e-04) (hash(x)=159763910)
|
| 713 |
+
5910 train 4.131778 (lr=4.0618e-04) (hash(x)=149555230)
|
| 714 |
+
5920 train 4.139466 (lr=4.0437e-04) (hash(x)=138048333)
|
| 715 |
+
5930 train 4.033743 (lr=4.0256e-04) (hash(x)=148668256)
|
| 716 |
+
5940 train 4.177557 (lr=4.0075e-04) (hash(x)=148352543)
|
| 717 |
+
5950 train 4.190412 (lr=3.9895e-04) (hash(x)=163457488)
|
| 718 |
+
5960 train 4.257314 (lr=3.9715e-04) (hash(x)=155306804)
|
| 719 |
+
5970 train 4.116057 (lr=3.9536e-04) (hash(x)=146576143)
|
| 720 |
+
5980 train 4.117074 (lr=3.9357e-04) (hash(x)=144668956)
|
| 721 |
+
5990 train 4.086648 (lr=3.9178e-04) (hash(x)=156098617)
|
| 722 |
+
6000 val loss 4.0985
|
| 723 |
+
6000 val perplexity 60.2495
|
| 724 |
+
6000 train 4.064077 (lr=3.9000e-04) (hash(x)=147640561)
|
| 725 |
+
6010 train 4.135435 (lr=3.8822e-04) (hash(x)=161223074)
|
| 726 |
+
6020 train 4.119960 (lr=3.8645e-04) (hash(x)=156308454)
|
| 727 |
+
6030 train 4.099943 (lr=3.8468e-04) (hash(x)=142553975)
|
| 728 |
+
6040 train 4.063015 (lr=3.8291e-04) (hash(x)=142039829)
|
| 729 |
+
6050 train 4.130169 (lr=3.8115e-04) (hash(x)=156329296)
|
| 730 |
+
6060 train 4.064578 (lr=3.7939e-04) (hash(x)=148505537)
|
| 731 |
+
6070 train 3.962342 (lr=3.7763e-04) (hash(x)=151801272)
|
| 732 |
+
6080 train 4.045441 (lr=3.7588e-04) (hash(x)=159908287)
|
| 733 |
+
6090 train 4.029486 (lr=3.7413e-04) (hash(x)=148714721)
|
| 734 |
+
6100 val loss 4.0918
|
| 735 |
+
6100 val perplexity 59.8486
|
| 736 |
+
6100 train 4.096703 (lr=3.7239e-04) (hash(x)=156613394)
|
| 737 |
+
6110 train 3.953953 (lr=3.7065e-04) (hash(x)=143286705)
|
| 738 |
+
6120 train 4.165829 (lr=3.6892e-04) (hash(x)=150191141)
|
| 739 |
+
6130 train 4.043693 (lr=3.6719e-04) (hash(x)=149855624)
|
| 740 |
+
6140 train 4.027339 (lr=3.6546e-04) (hash(x)=157312372)
|
| 741 |
+
6150 train 4.157900 (lr=3.6374e-04) (hash(x)=148262730)
|
| 742 |
+
6160 train 4.065306 (lr=3.6203e-04) (hash(x)=147032785)
|
| 743 |
+
6170 train 3.995253 (lr=3.6031e-04) (hash(x)=161213064)
|
| 744 |
+
6180 train 3.867723 (lr=3.5860e-04) (hash(x)=144538373)
|
| 745 |
+
6190 train 3.920167 (lr=3.5690e-04) (hash(x)=144688493)
|
| 746 |
+
6200 val loss 4.0903
|
| 747 |
+
6200 val perplexity 59.7561
|
| 748 |
+
6200 train 4.008413 (lr=3.5520e-04) (hash(x)=186221290)
|
| 749 |
+
6210 train 4.003809 (lr=3.5351e-04) (hash(x)=139529352)
|
| 750 |
+
6220 train 4.172615 (lr=3.5181e-04) (hash(x)=138081469)
|
| 751 |
+
6230 train 4.046563 (lr=3.5013e-04) (hash(x)=152979409)
|
| 752 |
+
6240 train 4.022776 (lr=3.4845e-04) (hash(x)=157848424)
|
| 753 |
+
6250 train 3.910941 (lr=3.4677e-04) (hash(x)=150770915)
|
| 754 |
+
6260 train 4.007532 (lr=3.4510e-04) (hash(x)=153769379)
|
| 755 |
+
6270 train 3.946521 (lr=3.4343e-04) (hash(x)=153318361)
|
| 756 |
+
6280 train 3.928519 (lr=3.4176e-04) (hash(x)=143366327)
|
| 757 |
+
6290 train 4.104515 (lr=3.4011e-04) (hash(x)=160684845)
|
| 758 |
+
6300 val loss 4.0742
|
| 759 |
+
6300 val perplexity 58.8044
|
| 760 |
+
6300 train 3.985447 (lr=3.3845e-04) (hash(x)=152081419)
|
| 761 |
+
6310 train 3.951961 (lr=3.3680e-04) (hash(x)=146626797)
|
| 762 |
+
6320 train 4.130134 (lr=3.3516e-04) (hash(x)=155291923)
|
| 763 |
+
6330 train 4.008305 (lr=3.3352e-04) (hash(x)=140920951)
|
| 764 |
+
6340 train 4.083308 (lr=3.3188e-04) (hash(x)=146642359)
|
| 765 |
+
6350 train 4.065470 (lr=3.3025e-04) (hash(x)=160486550)
|
| 766 |
+
6360 train 4.015540 (lr=3.2862e-04) (hash(x)=151833082)
|
| 767 |
+
6370 train 3.996283 (lr=3.2700e-04) (hash(x)=124740362)
|
| 768 |
+
6380 train 4.157921 (lr=3.2539e-04) (hash(x)=153952434)
|
| 769 |
+
6390 train 4.194618 (lr=3.2378e-04) (hash(x)=145864314)
|
| 770 |
+
6400 val loss 4.0777
|
| 771 |
+
6400 val perplexity 59.0104
|
| 772 |
+
6400 train 4.075952 (lr=3.2217e-04) (hash(x)=154808349)
|
| 773 |
+
6410 train 4.047116 (lr=3.2057e-04) (hash(x)=155037739)
|
| 774 |
+
6420 train 3.986217 (lr=3.1897e-04) (hash(x)=151155588)
|
| 775 |
+
6430 train 3.883024 (lr=3.1738e-04) (hash(x)=146548556)
|
| 776 |
+
6440 train 4.048032 (lr=3.1579e-04) (hash(x)=152706474)
|
| 777 |
+
6450 train 4.036387 (lr=3.1421e-04) (hash(x)=154207794)
|
| 778 |
+
6460 train 3.916732 (lr=3.1263e-04) (hash(x)=141590515)
|
| 779 |
+
6470 train 3.953282 (lr=3.1106e-04) (hash(x)=157673109)
|
| 780 |
+
6480 train 3.967452 (lr=3.0949e-04) (hash(x)=155842980)
|
| 781 |
+
6490 train 4.043090 (lr=3.0793e-04) (hash(x)=143595736)
|
| 782 |
+
6500 val loss 4.0757
|
| 783 |
+
6500 val perplexity 58.8910
|
| 784 |
+
6500 train 3.994601 (lr=3.0638e-04) (hash(x)=159437208)
|
| 785 |
+
6510 train 4.009926 (lr=3.0482e-04) (hash(x)=142631317)
|
| 786 |
+
6520 train 3.735771 (lr=3.0328e-04) (hash(x)=139009211)
|
| 787 |
+
6530 train 4.083264 (lr=3.0174e-04) (hash(x)=145451137)
|
| 788 |
+
6540 train 4.031296 (lr=3.0020e-04) (hash(x)=163532779)
|
| 789 |
+
6550 train 3.940059 (lr=2.9867e-04) (hash(x)=158084674)
|
| 790 |
+
6560 train 3.928304 (lr=2.9714e-04) (hash(x)=142422592)
|
| 791 |
+
6570 train 3.841194 (lr=2.9562e-04) (hash(x)=141089289)
|
| 792 |
+
6580 train 3.942785 (lr=2.9411e-04) (hash(x)=139712979)
|
| 793 |
+
6590 train 3.847609 (lr=2.9260e-04) (hash(x)=145833805)
|
| 794 |
+
6600 val loss 4.0754
|
| 795 |
+
6600 val perplexity 58.8729
|
| 796 |
+
6600 train 3.924802 (lr=2.9109e-04) (hash(x)=157933074)
|
| 797 |
+
6610 train 3.851537 (lr=2.8960e-04) (hash(x)=142534769)
|
| 798 |
+
6620 train 3.898623 (lr=2.8810e-04) (hash(x)=138456044)
|
| 799 |
+
6630 train 4.028467 (lr=2.8661e-04) (hash(x)=145111052)
|
| 800 |
+
6640 train 3.990762 (lr=2.8513e-04) (hash(x)=166954515)
|
| 801 |
+
6650 train 3.954756 (lr=2.8365e-04) (hash(x)=146889543)
|
| 802 |
+
6660 train 3.985748 (lr=2.8218e-04) (hash(x)=143253726)
|
| 803 |
+
6670 train 3.899108 (lr=2.8072e-04) (hash(x)=144349844)
|
| 804 |
+
6680 train 4.087748 (lr=2.7925e-04) (hash(x)=139911928)
|
| 805 |
+
6690 train 4.276970 (lr=2.7780e-04) (hash(x)=143135862)
|
| 806 |
+
6700 val loss 4.0641
|
| 807 |
+
6700 val perplexity 58.2114
|
| 808 |
+
6700 train 3.992573 (lr=2.7635e-04) (hash(x)=161560240)
|
| 809 |
+
6710 train 4.085211 (lr=2.7490e-04) (hash(x)=150437730)
|
| 810 |
+
6720 train 4.184434 (lr=2.7347e-04) (hash(x)=153035304)
|
| 811 |
+
6730 train 3.974659 (lr=2.7203e-04) (hash(x)=139323796)
|
| 812 |
+
6740 train 3.981706 (lr=2.7061e-04) (hash(x)=167437923)
|
| 813 |
+
6750 train 3.943504 (lr=2.6918e-04) (hash(x)=143814596)
|
| 814 |
+
6760 train 4.016542 (lr=2.6777e-04) (hash(x)=143755031)
|
| 815 |
+
6770 train 3.962216 (lr=2.6636e-04) (hash(x)=142014038)
|
| 816 |
+
6780 train 4.024828 (lr=2.6495e-04) (hash(x)=148465062)
|
| 817 |
+
6790 train 4.054141 (lr=2.6355e-04) (hash(x)=154656877)
|
| 818 |
+
6800 val loss 4.0609
|
| 819 |
+
6800 val perplexity 58.0258
|
| 820 |
+
6800 train 4.167812 (lr=2.6216e-04) (hash(x)=155424292)
|
| 821 |
+
6810 train 3.805580 (lr=2.6077e-04) (hash(x)=147358081)
|
| 822 |
+
6820 train 3.912767 (lr=2.5939e-04) (hash(x)=145387291)
|
| 823 |
+
6830 train 3.860868 (lr=2.5801e-04) (hash(x)=146334068)
|
| 824 |
+
6840 train 3.941154 (lr=2.5664e-04) (hash(x)=139563766)
|
| 825 |
+
6850 train 3.969791 (lr=2.5528e-04) (hash(x)=139095691)
|
| 826 |
+
6860 train 3.916632 (lr=2.5392e-04) (hash(x)=142093999)
|
| 827 |
+
6870 train 4.030006 (lr=2.5257e-04) (hash(x)=148598823)
|
| 828 |
+
6880 train 4.111337 (lr=2.5122e-04) (hash(x)=146486085)
|
| 829 |
+
6890 train 3.888174 (lr=2.4988e-04) (hash(x)=165683212)
|
| 830 |
+
6900 val loss 4.0646
|
| 831 |
+
6900 val perplexity 58.2410
|
| 832 |
+
6900 train 4.098392 (lr=2.4855e-04) (hash(x)=148561470)
|
| 833 |
+
6910 train 3.789592 (lr=2.4722e-04) (hash(x)=136352432)
|
| 834 |
+
6920 train 4.164391 (lr=2.4590e-04) (hash(x)=147640094)
|
| 835 |
+
6930 train 4.053335 (lr=2.4458e-04) (hash(x)=152343827)
|
| 836 |
+
6940 train 4.030707 (lr=2.4327e-04) (hash(x)=158787971)
|
| 837 |
+
6950 train 4.301925 (lr=2.4196e-04) (hash(x)=178133125)
|
| 838 |
+
6960 train 4.095902 (lr=2.4066e-04) (hash(x)=167302853)
|
| 839 |
+
6970 train 4.026929 (lr=2.3937e-04) (hash(x)=143729435)
|
| 840 |
+
6980 train 4.123681 (lr=2.3809e-04) (hash(x)=135857879)
|
| 841 |
+
6990 train 4.072715 (lr=2.3681e-04) (hash(x)=155384510)
|
| 842 |
+
7000 val loss 4.0502
|
| 843 |
+
7000 val perplexity 57.4089
|
| 844 |
+
7000 train 4.012786 (lr=2.3553e-04) (hash(x)=141527450)
|
| 845 |
+
7010 train 4.058348 (lr=2.3426e-04) (hash(x)=148648498)
|
| 846 |
+
7020 train 3.983970 (lr=2.3300e-04) (hash(x)=148073842)
|
| 847 |
+
7030 train 4.128294 (lr=2.3175e-04) (hash(x)=160771614)
|
| 848 |
+
7040 train 3.897070 (lr=2.3050e-04) (hash(x)=148361330)
|
| 849 |
+
7050 train 3.874508 (lr=2.2925e-04) (hash(x)=151212224)
|
| 850 |
+
7060 train 4.071479 (lr=2.2802e-04) (hash(x)=155925366)
|
| 851 |
+
7070 train 3.922597 (lr=2.2679e-04) (hash(x)=149830576)
|
| 852 |
+
7080 train 3.891897 (lr=2.2556e-04) (hash(x)=144849934)
|
| 853 |
+
7090 train 3.977273 (lr=2.2434e-04) (hash(x)=150997807)
|
| 854 |
+
7100 val loss 4.0458
|
| 855 |
+
7100 val perplexity 57.1586
|
| 856 |
+
7100 train 4.019791 (lr=2.2313e-04) (hash(x)=151066339)
|
| 857 |
+
7110 train 3.923236 (lr=2.2193e-04) (hash(x)=147185781)
|
| 858 |
+
7120 train 3.971796 (lr=2.2073e-04) (hash(x)=141765575)
|
| 859 |
+
7130 train 3.986699 (lr=2.1953e-04) (hash(x)=144204513)
|
| 860 |
+
7140 train 3.810654 (lr=2.1835e-04) (hash(x)=149326253)
|
| 861 |
+
7150 train 3.975004 (lr=2.1717e-04) (hash(x)=150409811)
|
| 862 |
+
7160 train 3.864530 (lr=2.1599e-04) (hash(x)=144790348)
|
| 863 |
+
7170 train 3.986275 (lr=2.1483e-04) (hash(x)=150500939)
|
| 864 |
+
7180 train 3.806956 (lr=2.1367e-04) (hash(x)=143552103)
|
| 865 |
+
7190 train 3.854528 (lr=2.1251e-04) (hash(x)=157471075)
|
| 866 |
+
7200 val loss 4.0493
|
| 867 |
+
7200 val perplexity 57.3560
|
| 868 |
+
7200 train 3.834935 (lr=2.1136e-04) (hash(x)=155231264)
|
| 869 |
+
7210 train 3.924431 (lr=2.1022e-04) (hash(x)=150350401)
|
| 870 |
+
7220 train 3.939244 (lr=2.0909e-04) (hash(x)=151952594)
|
| 871 |
+
7230 train 4.015425 (lr=2.0796e-04) (hash(x)=145381804)
|
| 872 |
+
7240 train 3.898234 (lr=2.0684e-04) (hash(x)=142651222)
|
| 873 |
+
7250 train 4.012981 (lr=2.0572e-04) (hash(x)=136115279)
|
| 874 |
+
7260 train 4.123105 (lr=2.0461e-04) (hash(x)=154536751)
|
| 875 |
+
7270 train 4.064994 (lr=2.0351e-04) (hash(x)=148883836)
|
| 876 |
+
7280 train 3.918666 (lr=2.0242e-04) (hash(x)=150606754)
|
| 877 |
+
7290 train 4.034782 (lr=2.0133e-04) (hash(x)=165845807)
|
| 878 |
+
7300 val loss 4.0387
|
| 879 |
+
7300 val perplexity 56.7534
|
| 880 |
+
7300 train 4.108488 (lr=2.0025e-04) (hash(x)=150281149)
|
| 881 |
+
7310 train 4.057649 (lr=1.9917e-04) (hash(x)=159929281)
|
| 882 |
+
7320 train 3.883295 (lr=1.9810e-04) (hash(x)=143074269)
|
| 883 |
+
7330 train 4.044887 (lr=1.9704e-04) (hash(x)=147369269)
|
| 884 |
+
7340 train 4.100954 (lr=1.9599e-04) (hash(x)=139286601)
|
| 885 |
+
7350 train 4.001184 (lr=1.9494e-04) (hash(x)=145263048)
|
| 886 |
+
7360 train 3.858955 (lr=1.9390e-04) (hash(x)=144626817)
|
| 887 |
+
7370 train 4.058453 (lr=1.9286e-04) (hash(x)=168989813)
|
| 888 |
+
7380 train 4.028209 (lr=1.9183e-04) (hash(x)=144790656)
|
| 889 |
+
7390 train 3.840994 (lr=1.9081e-04) (hash(x)=141279761)
|
| 890 |
+
7400 val loss 4.0352
|
| 891 |
+
7400 val perplexity 56.5542
|
| 892 |
+
7400 train 3.969620 (lr=1.8980e-04) (hash(x)=148421717)
|
| 893 |
+
7410 train 3.969294 (lr=1.8879e-04) (hash(x)=141241548)
|
| 894 |
+
7420 train 4.037854 (lr=1.8779e-04) (hash(x)=162434228)
|
| 895 |
+
7430 train 3.983191 (lr=1.8679e-04) (hash(x)=156312086)
|
| 896 |
+
7440 train 3.938407 (lr=1.8581e-04) (hash(x)=139803064)
|
| 897 |
+
7450 train 3.646124 (lr=1.8483e-04) (hash(x)=156361394)
|
| 898 |
+
7460 train 3.950531 (lr=1.8385e-04) (hash(x)=141142183)
|
| 899 |
+
7470 train 3.781596 (lr=1.8289e-04) (hash(x)=156701683)
|
| 900 |
+
7480 train 3.949805 (lr=1.8193e-04) (hash(x)=148549917)
|
| 901 |
+
7490 train 3.835516 (lr=1.8097e-04) (hash(x)=143002119)
|
| 902 |
+
7500 val loss 4.0366
|
| 903 |
+
7500 val perplexity 56.6359
|
| 904 |
+
7500 train 3.840008 (lr=1.8003e-04) (hash(x)=146921118)
|
| 905 |
+
7510 train 3.845066 (lr=1.7909e-04) (hash(x)=148592146)
|
| 906 |
+
7520 train 3.993814 (lr=1.7816e-04) (hash(x)=148456120)
|
| 907 |
+
7530 train 4.156199 (lr=1.7723e-04) (hash(x)=163865945)
|
| 908 |
+
7540 train 4.048292 (lr=1.7632e-04) (hash(x)=160753039)
|
| 909 |
+
7550 train 4.053375 (lr=1.7540e-04) (hash(x)=150275989)
|
| 910 |
+
7560 train 4.077055 (lr=1.7450e-04) (hash(x)=141749735)
|
| 911 |
+
7570 train 4.046455 (lr=1.7360e-04) (hash(x)=148449999)
|
| 912 |
+
7580 train 3.924130 (lr=1.7271e-04) (hash(x)=139153889)
|
| 913 |
+
7590 train 4.044879 (lr=1.7183e-04) (hash(x)=147418540)
|
| 914 |
+
7600 val loss 4.0251
|
| 915 |
+
7600 val perplexity 55.9874
|
| 916 |
+
7600 train 4.060641 (lr=1.7096e-04) (hash(x)=150660048)
|
| 917 |
+
7610 train 4.041813 (lr=1.7009e-04) (hash(x)=155369080)
|
| 918 |
+
7620 train 3.937446 (lr=1.6923e-04) (hash(x)=151926309)
|
| 919 |
+
7630 train 4.024207 (lr=1.6837e-04) (hash(x)=149549080)
|
| 920 |
+
7640 train 3.907936 (lr=1.6753e-04) (hash(x)=140642882)
|
| 921 |
+
7650 train 4.185522 (lr=1.6669e-04) (hash(x)=140218502)
|
| 922 |
+
7660 train 4.021338 (lr=1.6585e-04) (hash(x)=153198276)
|
| 923 |
+
7670 train 3.880632 (lr=1.6503e-04) (hash(x)=150706960)
|
| 924 |
+
7680 train 4.025851 (lr=1.6421e-04) (hash(x)=152025509)
|
| 925 |
+
7690 train 3.812854 (lr=1.6340e-04) (hash(x)=147288976)
|
| 926 |
+
7700 val loss 4.0254
|
| 927 |
+
7700 val perplexity 56.0015
|
| 928 |
+
7700 train 3.920757 (lr=1.6259e-04) (hash(x)=148059852)
|
| 929 |
+
7710 train 3.743178 (lr=1.6180e-04) (hash(x)=158443334)
|
| 930 |
+
7720 train 3.847569 (lr=1.6101e-04) (hash(x)=143467085)
|
| 931 |
+
7730 train 3.803224 (lr=1.6022e-04) (hash(x)=138439550)
|
| 932 |
+
7740 train 3.934093 (lr=1.5945e-04) (hash(x)=145878152)
|
| 933 |
+
7750 train 3.786257 (lr=1.5868e-04) (hash(x)=136874128)
|
| 934 |
+
7760 train 3.813019 (lr=1.5792e-04) (hash(x)=148856154)
|
| 935 |
+
7770 train 3.843335 (lr=1.5717e-04) (hash(x)=146982119)
|
| 936 |
+
7780 train 3.943774 (lr=1.5642e-04) (hash(x)=159846779)
|
| 937 |
+
7790 train 3.626005 (lr=1.5568e-04) (hash(x)=141501838)
|
| 938 |
+
7800 val loss 4.0283
|
| 939 |
+
7800 val perplexity 56.1671
|
| 940 |
+
7800 train 3.754367 (lr=1.5495e-04) (hash(x)=148331002)
|
| 941 |
+
7810 train 4.062242 (lr=1.5423e-04) (hash(x)=150692304)
|
| 942 |
+
7820 train 3.928555 (lr=1.5351e-04) (hash(x)=156841183)
|
| 943 |
+
7830 train 3.977808 (lr=1.5280e-04) (hash(x)=139594008)
|
| 944 |
+
7840 train 3.912022 (lr=1.5210e-04) (hash(x)=149700138)
|
| 945 |
+
7850 train 3.933584 (lr=1.5140e-04) (hash(x)=149327044)
|
| 946 |
+
7860 train 4.100913 (lr=1.5072e-04) (hash(x)=148315418)
|
| 947 |
+
7870 train 4.038040 (lr=1.5004e-04) (hash(x)=153431778)
|
| 948 |
+
7880 train 3.883826 (lr=1.4936e-04) (hash(x)=145049799)
|
| 949 |
+
7890 train 4.009741 (lr=1.4870e-04) (hash(x)=150265096)
|
| 950 |
+
7900 val loss 4.0162
|
| 951 |
+
7900 val perplexity 55.4923
|
| 952 |
+
7900 train 3.838707 (lr=1.4804e-04) (hash(x)=164923883)
|
| 953 |
+
7910 train 3.895029 (lr=1.4739e-04) (hash(x)=139315738)
|
| 954 |
+
7920 train 3.954407 (lr=1.4675e-04) (hash(x)=153031394)
|
| 955 |
+
7930 train 3.742575 (lr=1.4611e-04) (hash(x)=148835859)
|
| 956 |
+
7940 train 3.871411 (lr=1.4548e-04) (hash(x)=146875217)
|
| 957 |
+
7950 train 3.946323 (lr=1.4486e-04) (hash(x)=151003885)
|
| 958 |
+
7960 train 3.857710 (lr=1.4425e-04) (hash(x)=141885471)
|
| 959 |
+
7970 train 4.061173 (lr=1.4365e-04) (hash(x)=150541583)
|
| 960 |
+
7980 train 3.761149 (lr=1.4305e-04) (hash(x)=138626492)
|
| 961 |
+
7990 train 3.946670 (lr=1.4246e-04) (hash(x)=149935635)
|
| 962 |
+
8000 val loss 4.0164
|
| 963 |
+
8000 val perplexity 55.4999
|
| 964 |
+
8000 train 3.915186 (lr=1.4187e-04) (hash(x)=143545384)
|
| 965 |
+
8010 train 3.776268 (lr=1.4130e-04) (hash(x)=144689366)
|
| 966 |
+
8020 train 3.951567 (lr=1.4073e-04) (hash(x)=151299532)
|
| 967 |
+
8030 train 3.894763 (lr=1.4017e-04) (hash(x)=131300239)
|
| 968 |
+
8040 train 3.793222 (lr=1.3962e-04) (hash(x)=146715955)
|
| 969 |
+
8050 train 3.718372 (lr=1.3907e-04) (hash(x)=135376656)
|
| 970 |
+
8060 train 3.804479 (lr=1.3853e-04) (hash(x)=141991433)
|
| 971 |
+
8070 train 3.756926 (lr=1.3800e-04) (hash(x)=140260574)
|
| 972 |
+
8080 train 3.731441 (lr=1.3748e-04) (hash(x)=151492896)
|
| 973 |
+
8090 train 3.930403 (lr=1.3697e-04) (hash(x)=143333635)
|
| 974 |
+
8100 val loss 4.0201
|
| 975 |
+
8100 val perplexity 55.7093
|
| 976 |
+
8100 train 3.816758 (lr=1.3646e-04) (hash(x)=160686959)
|
| 977 |
+
8110 train 3.815259 (lr=1.3596e-04) (hash(x)=141145704)
|
| 978 |
+
8120 train 4.051874 (lr=1.3547e-04) (hash(x)=146967795)
|
| 979 |
+
8130 train 3.884928 (lr=1.3498e-04) (hash(x)=147844486)
|
| 980 |
+
8140 train 3.935491 (lr=1.3450e-04) (hash(x)=141860136)
|
| 981 |
+
8150 train 4.069828 (lr=1.3403e-04) (hash(x)=147696006)
|
| 982 |
+
8160 train 3.974775 (lr=1.3357e-04) (hash(x)=151497110)
|
| 983 |
+
8170 train 3.975749 (lr=1.3312e-04) (hash(x)=140881859)
|
| 984 |
+
8180 train 3.920867 (lr=1.3267e-04) (hash(x)=158865574)
|
| 985 |
+
8190 train 3.881980 (lr=1.3223e-04) (hash(x)=161247161)
|
| 986 |
+
8200 val loss 4.0137
|
| 987 |
+
8200 val perplexity 55.3528
|
| 988 |
+
8200 train 3.844222 (lr=1.3180e-04) (hash(x)=156501889)
|
| 989 |
+
8210 train 3.975752 (lr=1.3138e-04) (hash(x)=158384162)
|
| 990 |
+
8220 train 4.011690 (lr=1.3096e-04) (hash(x)=154815062)
|
| 991 |
+
8230 train 3.888527 (lr=1.3055e-04) (hash(x)=145018315)
|
| 992 |
+
8240 train 3.926995 (lr=1.3015e-04) (hash(x)=161659129)
|
| 993 |
+
8250 train 3.897687 (lr=1.2976e-04) (hash(x)=139863367)
|
| 994 |
+
8260 train 3.845423 (lr=1.2937e-04) (hash(x)=149569663)
|
| 995 |
+
8270 train 3.600467 (lr=1.2900e-04) (hash(x)=162234378)
|
| 996 |
+
8280 train 3.985010 (lr=1.2863e-04) (hash(x)=144371378)
|
| 997 |
+
8290 train 3.889240 (lr=1.2826e-04) (hash(x)=148120258)
|
| 998 |
+
8300 val loss 4.0140
|
| 999 |
+
8300 val perplexity 55.3705
|
| 1000 |
+
8300 train 3.886706 (lr=1.2791e-04) (hash(x)=142716875)
|
| 1001 |
+
8310 train 3.905541 (lr=1.2756e-04) (hash(x)=166789234)
|
| 1002 |
+
8320 train 3.970407 (lr=1.2722e-04) (hash(x)=150613211)
|
| 1003 |
+
8330 train 3.851111 (lr=1.2689e-04) (hash(x)=139895391)
|
| 1004 |
+
8340 train 3.954734 (lr=1.2657e-04) (hash(x)=152011203)
|
| 1005 |
+
8350 train 3.916942 (lr=1.2625e-04) (hash(x)=156010875)
|
| 1006 |
+
8360 train 3.924271 (lr=1.2594e-04) (hash(x)=152988051)
|
| 1007 |
+
8370 train 4.091287 (lr=1.2564e-04) (hash(x)=155144327)
|
| 1008 |
+
8380 train 3.973551 (lr=1.2535e-04) (hash(x)=133642309)
|
| 1009 |
+
8390 train 4.015400 (lr=1.2507e-04) (hash(x)=149745335)
|
| 1010 |
+
8400 val loss 4.0060
|
| 1011 |
+
8400 val perplexity 54.9279
|
| 1012 |
+
8400 train 3.998825 (lr=1.2479e-04) (hash(x)=154436684)
|
| 1013 |
+
8410 train 4.044699 (lr=1.2452e-04) (hash(x)=147946630)
|
| 1014 |
+
8420 train 3.948421 (lr=1.2426e-04) (hash(x)=153947058)
|
| 1015 |
+
8430 train 4.044483 (lr=1.2400e-04) (hash(x)=159821040)
|
| 1016 |
+
8440 train 4.009828 (lr=1.2376e-04) (hash(x)=149127348)
|
| 1017 |
+
8450 train 4.017153 (lr=1.2352e-04) (hash(x)=149421871)
|
| 1018 |
+
8460 train 3.977772 (lr=1.2329e-04) (hash(x)=142621577)
|
| 1019 |
+
8470 train 3.978115 (lr=1.2307e-04) (hash(x)=148978213)
|
| 1020 |
+
8480 train 3.799624 (lr=1.2285e-04) (hash(x)=139959537)
|
| 1021 |
+
8490 train 3.888784 (lr=1.2264e-04) (hash(x)=144232498)
|
| 1022 |
+
8500 val loss 4.0050
|
| 1023 |
+
8500 val perplexity 54.8709
|
| 1024 |
+
8500 train 4.113660 (lr=1.2245e-04) (hash(x)=147965839)
|
| 1025 |
+
8510 train 3.993450 (lr=1.2225e-04) (hash(x)=147679836)
|
| 1026 |
+
8520 train 3.867264 (lr=1.2207e-04) (hash(x)=147486097)
|
| 1027 |
+
8530 train 4.011806 (lr=1.2189e-04) (hash(x)=151655265)
|
| 1028 |
+
8540 train 3.906110 (lr=1.2173e-04) (hash(x)=150866632)
|
| 1029 |
+
8550 train 4.050745 (lr=1.2157e-04) (hash(x)=144355059)
|
| 1030 |
+
8560 train 3.910684 (lr=1.2141e-04) (hash(x)=145518478)
|
| 1031 |
+
8570 train 4.055355 (lr=1.2127e-04) (hash(x)=178973323)
|
| 1032 |
+
8580 train 3.980171 (lr=1.2113e-04) (hash(x)=152773969)
|
| 1033 |
+
8590 train 3.779613 (lr=1.2100e-04) (hash(x)=141805508)
|
| 1034 |
+
8600 val loss 4.0092
|
| 1035 |
+
8600 val perplexity 55.1006
|
| 1036 |
+
8600 train 3.835459 (lr=1.2088e-04) (hash(x)=145228097)
|
| 1037 |
+
8610 train 3.849001 (lr=1.2077e-04) (hash(x)=149525694)
|
| 1038 |
+
8620 train 3.923246 (lr=1.2066e-04) (hash(x)=151651655)
|
| 1039 |
+
8630 train 4.036364 (lr=1.2056e-04) (hash(x)=144918643)
|
| 1040 |
+
8640 train 3.884690 (lr=1.2047e-04) (hash(x)=149721879)
|
| 1041 |
+
8650 train 3.963094 (lr=1.2039e-04) (hash(x)=157684127)
|
| 1042 |
+
8660 train 3.957371 (lr=1.2032e-04) (hash(x)=152426036)
|
| 1043 |
+
8670 train 3.880774 (lr=1.2025e-04) (hash(x)=141396342)
|
| 1044 |
+
8680 train 3.976223 (lr=1.2019e-04) (hash(x)=146459856)
|
| 1045 |
+
8690 train 4.052843 (lr=1.2014e-04) (hash(x)=151766124)
|
| 1046 |
+
8700 val loss 4.0002
|
| 1047 |
+
8700 val perplexity 54.6105
|
| 1048 |
+
8700 train 4.209660 (lr=1.2010e-04) (hash(x)=152910357)
|
| 1049 |
+
8710 train 4.002333 (lr=1.2006e-04) (hash(x)=149724642)
|
| 1050 |
+
8720 train 3.932195 (lr=1.2004e-04) (hash(x)=152483840)
|
| 1051 |
+
8730 train 3.913609 (lr=1.2002e-04) (hash(x)=147289415)
|
| 1052 |
+
8740 train 3.947838 (lr=1.2000e-04) (hash(x)=152254131)
|
| 1053 |
+
8749 val loss 3.9995
|
| 1054 |
+
8749 val perplexity 54.5699
|
lr12e-4_total_batch_size61440_baseline_seed1338/model_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a634f7f55483f2b0ee0f386954de6e55faff9d7eed3c70d61aab68076af47cc
|
| 3 |
+
size 92843394
|
lr12e-4_total_batch_size61440_baseline_seed1338/optimizer_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:782da4fcf2e7960138c107a5a95fb3a03d9f419408c8d4c5a217594c02709899
|
| 3 |
+
size 179406214
|