Upload folder using huggingface_hub
Browse files- lr8e-4_total_batch_size61440_baseline_seed1340/args.json +1 -0
- lr8e-4_total_batch_size61440_baseline_seed1340/dataloader_08749.pt +3 -0
- lr8e-4_total_batch_size61440_baseline_seed1340/log2.txt +1054 -0
- lr8e-4_total_batch_size61440_baseline_seed1340/model_08749.pt +3 -0
- lr8e-4_total_batch_size61440_baseline_seed1340/optimizer_08749.pt +3 -0
lr8e-4_total_batch_size61440_baseline_seed1340/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "wider_is_better_11/lr8e-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": 0.0008, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "8e-4_61440", "n_embd": 256}
|
lr8e-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
|
lr8e-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 76607.9531
|
| 4 |
+
0 train 11.254622 (lr=1.6000e-06) (hash(x)=164406924)
|
| 5 |
+
10 train 10.403351 (lr=1.7600e-05) (hash(x)=152008797)
|
| 6 |
+
20 train 9.868977 (lr=3.3600e-05) (hash(x)=153494457)
|
| 7 |
+
30 train 9.439003 (lr=4.9600e-05) (hash(x)=137328499)
|
| 8 |
+
40 train 9.154652 (lr=6.5600e-05) (hash(x)=159333245)
|
| 9 |
+
50 train 8.698051 (lr=8.1600e-05) (hash(x)=177407419)
|
| 10 |
+
60 train 8.108204 (lr=9.7600e-05) (hash(x)=127877799)
|
| 11 |
+
70 train 7.771571 (lr=1.1360e-04) (hash(x)=140873918)
|
| 12 |
+
80 train 7.731904 (lr=1.2960e-04) (hash(x)=160249377)
|
| 13 |
+
90 train 7.585963 (lr=1.4560e-04) (hash(x)=154282910)
|
| 14 |
+
100 val loss 7.5267
|
| 15 |
+
100 val perplexity 1856.9932
|
| 16 |
+
100 train 7.433286 (lr=1.6160e-04) (hash(x)=144903932)
|
| 17 |
+
110 train 7.439407 (lr=1.7760e-04) (hash(x)=151685723)
|
| 18 |
+
120 train 7.209979 (lr=1.9360e-04) (hash(x)=152347864)
|
| 19 |
+
130 train 7.200047 (lr=2.0960e-04) (hash(x)=152230926)
|
| 20 |
+
140 train 7.039568 (lr=2.2560e-04) (hash(x)=142121048)
|
| 21 |
+
150 train 7.147993 (lr=2.4160e-04) (hash(x)=173839165)
|
| 22 |
+
160 train 6.931983 (lr=2.5760e-04) (hash(x)=158755931)
|
| 23 |
+
170 train 6.753846 (lr=2.7360e-04) (hash(x)=151645697)
|
| 24 |
+
180 train 7.072424 (lr=2.8960e-04) (hash(x)=179696111)
|
| 25 |
+
190 train 6.703321 (lr=3.0560e-04) (hash(x)=150511423)
|
| 26 |
+
200 val loss 6.7542
|
| 27 |
+
200 val perplexity 857.6615
|
| 28 |
+
200 train 6.878301 (lr=3.2160e-04) (hash(x)=167734596)
|
| 29 |
+
210 train 6.442939 (lr=3.3760e-04) (hash(x)=133157560)
|
| 30 |
+
220 train 6.690583 (lr=3.5360e-04) (hash(x)=152234670)
|
| 31 |
+
230 train 6.510370 (lr=3.6960e-04) (hash(x)=160995039)
|
| 32 |
+
240 train 6.399655 (lr=3.8560e-04) (hash(x)=139367591)
|
| 33 |
+
250 train 6.569918 (lr=4.0160e-04) (hash(x)=153224076)
|
| 34 |
+
260 train 6.472605 (lr=4.1760e-04) (hash(x)=156667529)
|
| 35 |
+
270 train 6.388954 (lr=4.3360e-04) (hash(x)=133883725)
|
| 36 |
+
280 train 6.184897 (lr=4.4960e-04) (hash(x)=151939311)
|
| 37 |
+
290 train 6.241949 (lr=4.6560e-04) (hash(x)=150290478)
|
| 38 |
+
300 val loss 6.2475
|
| 39 |
+
300 val perplexity 516.7203
|
| 40 |
+
300 train 6.209776 (lr=4.8160e-04) (hash(x)=149619098)
|
| 41 |
+
310 train 6.118904 (lr=4.9760e-04) (hash(x)=142344072)
|
| 42 |
+
320 train 6.189412 (lr=5.1360e-04) (hash(x)=151878766)
|
| 43 |
+
330 train 6.037600 (lr=5.2960e-04) (hash(x)=136419763)
|
| 44 |
+
340 train 6.145535 (lr=5.4560e-04) (hash(x)=160761498)
|
| 45 |
+
350 train 6.016574 (lr=5.6160e-04) (hash(x)=146539909)
|
| 46 |
+
360 train 6.113569 (lr=5.7760e-04) (hash(x)=143063312)
|
| 47 |
+
370 train 5.972857 (lr=5.9360e-04) (hash(x)=153705818)
|
| 48 |
+
380 train 5.882222 (lr=6.0960e-04) (hash(x)=149579175)
|
| 49 |
+
390 train 5.831676 (lr=6.2560e-04) (hash(x)=150904406)
|
| 50 |
+
400 val loss 5.9268
|
| 51 |
+
400 val perplexity 374.9491
|
| 52 |
+
400 train 5.795779 (lr=6.4160e-04) (hash(x)=153710890)
|
| 53 |
+
410 train 5.692109 (lr=6.5760e-04) (hash(x)=138302968)
|
| 54 |
+
420 train 5.692981 (lr=6.7360e-04) (hash(x)=141112989)
|
| 55 |
+
430 train 5.750648 (lr=6.8960e-04) (hash(x)=149846944)
|
| 56 |
+
440 train 5.743404 (lr=7.0560e-04) (hash(x)=157683479)
|
| 57 |
+
450 train 5.747998 (lr=7.2160e-04) (hash(x)=155873620)
|
| 58 |
+
460 train 5.953325 (lr=7.3760e-04) (hash(x)=152133659)
|
| 59 |
+
470 train 5.708988 (lr=7.5360e-04) (hash(x)=158095308)
|
| 60 |
+
480 train 5.579508 (lr=7.6960e-04) (hash(x)=148422063)
|
| 61 |
+
490 train 5.766305 (lr=7.8560e-04) (hash(x)=145665071)
|
| 62 |
+
500 val loss 5.7229
|
| 63 |
+
500 val perplexity 305.7949
|
| 64 |
+
500 train 5.692929 (lr=8.0000e-04) (hash(x)=145450636)
|
| 65 |
+
510 train 5.697438 (lr=8.0000e-04) (hash(x)=148375186)
|
| 66 |
+
520 train 5.714912 (lr=7.9999e-04) (hash(x)=144256573)
|
| 67 |
+
530 train 5.765066 (lr=7.9998e-04) (hash(x)=141443048)
|
| 68 |
+
540 train 5.584963 (lr=7.9996e-04) (hash(x)=149347480)
|
| 69 |
+
550 train 5.667272 (lr=7.9993e-04) (hash(x)=154123388)
|
| 70 |
+
560 train 5.640288 (lr=7.9991e-04) (hash(x)=143045783)
|
| 71 |
+
570 train 5.503636 (lr=7.9987e-04) (hash(x)=157244060)
|
| 72 |
+
580 train 5.495625 (lr=7.9983e-04) (hash(x)=158018166)
|
| 73 |
+
590 train 5.568650 (lr=7.9979e-04) (hash(x)=153794251)
|
| 74 |
+
600 val loss 5.5449
|
| 75 |
+
600 val perplexity 255.9347
|
| 76 |
+
600 train 5.487761 (lr=7.9974e-04) (hash(x)=145249251)
|
| 77 |
+
610 train 5.555068 (lr=7.9968e-04) (hash(x)=150377688)
|
| 78 |
+
620 train 5.509329 (lr=7.9962e-04) (hash(x)=134768519)
|
| 79 |
+
630 train 5.423077 (lr=7.9956e-04) (hash(x)=141559208)
|
| 80 |
+
640 train 5.397127 (lr=7.9949e-04) (hash(x)=148444988)
|
| 81 |
+
650 train 5.408972 (lr=7.9941e-04) (hash(x)=148937127)
|
| 82 |
+
660 train 5.298910 (lr=7.9933e-04) (hash(x)=145121305)
|
| 83 |
+
670 train 5.437715 (lr=7.9925e-04) (hash(x)=156860740)
|
| 84 |
+
680 train 5.224507 (lr=7.9915e-04) (hash(x)=137272598)
|
| 85 |
+
690 train 5.228613 (lr=7.9906e-04) (hash(x)=139021179)
|
| 86 |
+
700 val loss 5.3565
|
| 87 |
+
700 val perplexity 211.9827
|
| 88 |
+
700 train 5.517815 (lr=7.9896e-04) (hash(x)=150475545)
|
| 89 |
+
710 train 5.306555 (lr=7.9885e-04) (hash(x)=148476077)
|
| 90 |
+
720 train 5.197684 (lr=7.9874e-04) (hash(x)=143328717)
|
| 91 |
+
730 train 5.128149 (lr=7.9862e-04) (hash(x)=137342488)
|
| 92 |
+
740 train 5.202574 (lr=7.9850e-04) (hash(x)=149452392)
|
| 93 |
+
750 train 5.188231 (lr=7.9837e-04) (hash(x)=154653428)
|
| 94 |
+
760 train 5.320519 (lr=7.9824e-04) (hash(x)=153305312)
|
| 95 |
+
770 train 5.169168 (lr=7.9810e-04) (hash(x)=153862299)
|
| 96 |
+
780 train 5.183595 (lr=7.9796e-04) (hash(x)=151035519)
|
| 97 |
+
790 train 5.272301 (lr=7.9781e-04) (hash(x)=145990773)
|
| 98 |
+
800 val loss 5.2334
|
| 99 |
+
800 val perplexity 187.4342
|
| 100 |
+
800 train 5.242605 (lr=7.9765e-04) (hash(x)=144483776)
|
| 101 |
+
810 train 5.147661 (lr=7.9749e-04) (hash(x)=142045737)
|
| 102 |
+
820 train 5.270576 (lr=7.9733e-04) (hash(x)=157946886)
|
| 103 |
+
830 train 5.146349 (lr=7.9716e-04) (hash(x)=150425385)
|
| 104 |
+
840 train 5.186336 (lr=7.9699e-04) (hash(x)=144514796)
|
| 105 |
+
850 train 5.230666 (lr=7.9681e-04) (hash(x)=157395496)
|
| 106 |
+
860 train 5.188850 (lr=7.9662e-04) (hash(x)=151365298)
|
| 107 |
+
870 train 5.209791 (lr=7.9643e-04) (hash(x)=151437005)
|
| 108 |
+
880 train 5.125273 (lr=7.9624e-04) (hash(x)=151935250)
|
| 109 |
+
890 train 5.171317 (lr=7.9604e-04) (hash(x)=159838534)
|
| 110 |
+
900 val loss 5.1185
|
| 111 |
+
900 val perplexity 167.0831
|
| 112 |
+
900 train 5.096739 (lr=7.9583e-04) (hash(x)=157916369)
|
| 113 |
+
910 train 5.220689 (lr=7.9562e-04) (hash(x)=165272484)
|
| 114 |
+
920 train 5.051099 (lr=7.9541e-04) (hash(x)=145383083)
|
| 115 |
+
930 train 5.021815 (lr=7.9518e-04) (hash(x)=152078393)
|
| 116 |
+
940 train 5.160800 (lr=7.9496e-04) (hash(x)=151846396)
|
| 117 |
+
950 train 5.079991 (lr=7.9473e-04) (hash(x)=166073923)
|
| 118 |
+
960 train 5.027879 (lr=7.9449e-04) (hash(x)=136782937)
|
| 119 |
+
970 train 5.002523 (lr=7.9425e-04) (hash(x)=146747407)
|
| 120 |
+
980 train 5.018802 (lr=7.9400e-04) (hash(x)=171270168)
|
| 121 |
+
990 train 5.032642 (lr=7.9375e-04) (hash(x)=141668491)
|
| 122 |
+
1000 val loss 5.0419
|
| 123 |
+
1000 val perplexity 154.7682
|
| 124 |
+
1000 train 4.942974 (lr=7.9349e-04) (hash(x)=154856891)
|
| 125 |
+
1010 train 5.023415 (lr=7.9323e-04) (hash(x)=145288527)
|
| 126 |
+
1020 train 4.891458 (lr=7.9297e-04) (hash(x)=144618667)
|
| 127 |
+
1030 train 5.122633 (lr=7.9269e-04) (hash(x)=139276042)
|
| 128 |
+
1040 train 4.822103 (lr=7.9242e-04) (hash(x)=147217952)
|
| 129 |
+
1050 train 4.909261 (lr=7.9213e-04) (hash(x)=151925203)
|
| 130 |
+
1060 train 4.889205 (lr=7.9185e-04) (hash(x)=147473652)
|
| 131 |
+
1070 train 4.843236 (lr=7.9155e-04) (hash(x)=145345524)
|
| 132 |
+
1080 train 4.721206 (lr=7.9126e-04) (hash(x)=155595779)
|
| 133 |
+
1090 train 4.774611 (lr=7.9095e-04) (hash(x)=147405225)
|
| 134 |
+
1100 val loss 4.9275
|
| 135 |
+
1100 val perplexity 138.0355
|
| 136 |
+
1100 train 4.630736 (lr=7.9064e-04) (hash(x)=136191502)
|
| 137 |
+
1110 train 4.868481 (lr=7.9033e-04) (hash(x)=151847694)
|
| 138 |
+
1120 train 4.962811 (lr=7.9001e-04) (hash(x)=144828302)
|
| 139 |
+
1130 train 4.973944 (lr=7.8969e-04) (hash(x)=153817096)
|
| 140 |
+
1140 train 5.029817 (lr=7.8936e-04) (hash(x)=166352243)
|
| 141 |
+
1150 train 5.074063 (lr=7.8903e-04) (hash(x)=153273362)
|
| 142 |
+
1160 train 4.891214 (lr=7.8869e-04) (hash(x)=178082599)
|
| 143 |
+
1170 train 4.706911 (lr=7.8835e-04) (hash(x)=149460553)
|
| 144 |
+
1180 train 4.890978 (lr=7.8800e-04) (hash(x)=151910947)
|
| 145 |
+
1190 train 4.809578 (lr=7.8764e-04) (hash(x)=147115336)
|
| 146 |
+
1200 val loss 4.8477
|
| 147 |
+
1200 val perplexity 127.4472
|
| 148 |
+
1200 train 4.877482 (lr=7.8729e-04) (hash(x)=148021541)
|
| 149 |
+
1210 train 4.768750 (lr=7.8692e-04) (hash(x)=151495989)
|
| 150 |
+
1220 train 4.880058 (lr=7.8655e-04) (hash(x)=156983220)
|
| 151 |
+
1230 train 4.935190 (lr=7.8618e-04) (hash(x)=147788187)
|
| 152 |
+
1240 train 4.916607 (lr=7.8580e-04) (hash(x)=171125590)
|
| 153 |
+
1250 train 4.835770 (lr=7.8542e-04) (hash(x)=141356608)
|
| 154 |
+
1260 train 4.869235 (lr=7.8503e-04) (hash(x)=150132098)
|
| 155 |
+
1270 train 4.739377 (lr=7.8464e-04) (hash(x)=147917245)
|
| 156 |
+
1280 train 4.835557 (lr=7.8424e-04) (hash(x)=148900016)
|
| 157 |
+
1290 train 4.795037 (lr=7.8383e-04) (hash(x)=144978605)
|
| 158 |
+
1300 val loss 4.7704
|
| 159 |
+
1300 val perplexity 117.9618
|
| 160 |
+
1300 train 4.727566 (lr=7.8342e-04) (hash(x)=146005217)
|
| 161 |
+
1310 train 4.730542 (lr=7.8301e-04) (hash(x)=144892309)
|
| 162 |
+
1320 train 4.810223 (lr=7.8259e-04) (hash(x)=165903661)
|
| 163 |
+
1330 train 4.754246 (lr=7.8217e-04) (hash(x)=168489989)
|
| 164 |
+
1340 train 4.920579 (lr=7.8174e-04) (hash(x)=176281294)
|
| 165 |
+
1350 train 4.715534 (lr=7.8131e-04) (hash(x)=144511718)
|
| 166 |
+
1360 train 4.766327 (lr=7.8087e-04) (hash(x)=144362722)
|
| 167 |
+
1370 train 4.656821 (lr=7.8042e-04) (hash(x)=139964999)
|
| 168 |
+
1380 train 4.687278 (lr=7.7998e-04) (hash(x)=193332654)
|
| 169 |
+
1390 train 4.714314 (lr=7.7952e-04) (hash(x)=138180866)
|
| 170 |
+
1400 val loss 4.7345
|
| 171 |
+
1400 val perplexity 113.8102
|
| 172 |
+
1400 train 4.719286 (lr=7.7906e-04) (hash(x)=146019502)
|
| 173 |
+
1410 train 4.751299 (lr=7.7860e-04) (hash(x)=153245388)
|
| 174 |
+
1420 train 4.651731 (lr=7.7813e-04) (hash(x)=149839636)
|
| 175 |
+
1430 train 4.751934 (lr=7.7766e-04) (hash(x)=142844796)
|
| 176 |
+
1440 train 4.976958 (lr=7.7718e-04) (hash(x)=159787060)
|
| 177 |
+
1450 train 4.693465 (lr=7.7670e-04) (hash(x)=146496200)
|
| 178 |
+
1460 train 4.615085 (lr=7.7621e-04) (hash(x)=164169521)
|
| 179 |
+
1470 train 4.659662 (lr=7.7572e-04) (hash(x)=150906386)
|
| 180 |
+
1480 train 4.679850 (lr=7.7522e-04) (hash(x)=148916053)
|
| 181 |
+
1490 train 4.613160 (lr=7.7472e-04) (hash(x)=148746554)
|
| 182 |
+
1500 val loss 4.7497
|
| 183 |
+
1500 val perplexity 115.5447
|
| 184 |
+
1500 train 4.710093 (lr=7.7421e-04) (hash(x)=150127281)
|
| 185 |
+
1510 train 4.875929 (lr=7.7370e-04) (hash(x)=149760530)
|
| 186 |
+
1520 train 4.708329 (lr=7.7318e-04) (hash(x)=144237370)
|
| 187 |
+
1530 train 4.524237 (lr=7.7266e-04) (hash(x)=132692898)
|
| 188 |
+
1540 train 4.510156 (lr=7.7214e-04) (hash(x)=150979737)
|
| 189 |
+
1550 train 4.708315 (lr=7.7160e-04) (hash(x)=142022255)
|
| 190 |
+
1560 train 4.633008 (lr=7.7107e-04) (hash(x)=135769745)
|
| 191 |
+
1570 train 4.496590 (lr=7.7053e-04) (hash(x)=162241131)
|
| 192 |
+
1580 train 4.591646 (lr=7.6998e-04) (hash(x)=166874637)
|
| 193 |
+
1590 train 4.558323 (lr=7.6943e-04) (hash(x)=157401041)
|
| 194 |
+
1600 val loss 4.6503
|
| 195 |
+
1600 val perplexity 104.6158
|
| 196 |
+
1600 train 4.591084 (lr=7.6888e-04) (hash(x)=154120875)
|
| 197 |
+
1610 train 4.559020 (lr=7.6832e-04) (hash(x)=149407490)
|
| 198 |
+
1620 train 4.525401 (lr=7.6775e-04) (hash(x)=144479755)
|
| 199 |
+
1630 train 4.602766 (lr=7.6718e-04) (hash(x)=170907716)
|
| 200 |
+
1640 train 4.240652 (lr=7.6661e-04) (hash(x)=151914010)
|
| 201 |
+
1650 train 4.549155 (lr=7.6603e-04) (hash(x)=149843610)
|
| 202 |
+
1660 train 4.444502 (lr=7.6545e-04) (hash(x)=133217001)
|
| 203 |
+
1670 train 4.400337 (lr=7.6486e-04) (hash(x)=168227774)
|
| 204 |
+
1680 train 4.357891 (lr=7.6426e-04) (hash(x)=157093189)
|
| 205 |
+
1690 train 4.199286 (lr=7.6367e-04) (hash(x)=154989819)
|
| 206 |
+
1700 val loss 4.6285
|
| 207 |
+
1700 val perplexity 102.3628
|
| 208 |
+
1700 train 4.723501 (lr=7.6306e-04) (hash(x)=155797680)
|
| 209 |
+
1710 train 4.406520 (lr=7.6246e-04) (hash(x)=166050772)
|
| 210 |
+
1720 train 4.370466 (lr=7.6184e-04) (hash(x)=151663443)
|
| 211 |
+
1730 train 4.605211 (lr=7.6123e-04) (hash(x)=152112619)
|
| 212 |
+
1740 train 4.541809 (lr=7.6061e-04) (hash(x)=156132679)
|
| 213 |
+
1750 train 4.385110 (lr=7.5998e-04) (hash(x)=149044477)
|
| 214 |
+
1760 train 4.568919 (lr=7.5935e-04) (hash(x)=142924719)
|
| 215 |
+
1770 train 4.461357 (lr=7.5872e-04) (hash(x)=153467406)
|
| 216 |
+
1780 train 4.542307 (lr=7.5808e-04) (hash(x)=148889581)
|
| 217 |
+
1790 train 4.487999 (lr=7.5743e-04) (hash(x)=164831182)
|
| 218 |
+
1800 val loss 4.5634
|
| 219 |
+
1800 val perplexity 95.9069
|
| 220 |
+
1800 train 4.488400 (lr=7.5678e-04) (hash(x)=156809396)
|
| 221 |
+
1810 train 4.583954 (lr=7.5613e-04) (hash(x)=149245741)
|
| 222 |
+
1820 train 4.536496 (lr=7.5547e-04) (hash(x)=146865466)
|
| 223 |
+
1830 train 4.607292 (lr=7.5481e-04) (hash(x)=148068618)
|
| 224 |
+
1840 train 4.442547 (lr=7.5414e-04) (hash(x)=150088183)
|
| 225 |
+
1850 train 4.528140 (lr=7.5347e-04) (hash(x)=146695082)
|
| 226 |
+
1860 train 4.454133 (lr=7.5279e-04) (hash(x)=169008624)
|
| 227 |
+
1870 train 4.399381 (lr=7.5211e-04) (hash(x)=148645124)
|
| 228 |
+
1880 train 4.554943 (lr=7.5143e-04) (hash(x)=139701422)
|
| 229 |
+
1890 train 4.520085 (lr=7.5074e-04) (hash(x)=156374257)
|
| 230 |
+
1900 val loss 4.5413
|
| 231 |
+
1900 val perplexity 93.8098
|
| 232 |
+
1900 train 4.468108 (lr=7.5004e-04) (hash(x)=144640294)
|
| 233 |
+
1910 train 4.617693 (lr=7.4934e-04) (hash(x)=147484985)
|
| 234 |
+
1920 train 4.462884 (lr=7.4864e-04) (hash(x)=142317889)
|
| 235 |
+
1930 train 4.455640 (lr=7.4793e-04) (hash(x)=144906216)
|
| 236 |
+
1940 train 4.495804 (lr=7.4722e-04) (hash(x)=165332621)
|
| 237 |
+
1950 train 4.480155 (lr=7.4650e-04) (hash(x)=145701919)
|
| 238 |
+
1960 train 4.377773 (lr=7.4578e-04) (hash(x)=146414118)
|
| 239 |
+
1970 train 4.549281 (lr=7.4505e-04) (hash(x)=146766958)
|
| 240 |
+
1980 train 4.467148 (lr=7.4432e-04) (hash(x)=148146847)
|
| 241 |
+
1990 train 4.222916 (lr=7.4359e-04) (hash(x)=159684604)
|
| 242 |
+
2000 val loss 4.5393
|
| 243 |
+
2000 val perplexity 93.6256
|
| 244 |
+
2000 train 4.372840 (lr=7.4285e-04) (hash(x)=162831106)
|
| 245 |
+
2010 train 4.392554 (lr=7.4211e-04) (hash(x)=150583346)
|
| 246 |
+
2020 train 4.344497 (lr=7.4136e-04) (hash(x)=142779458)
|
| 247 |
+
2030 train 4.326798 (lr=7.4061e-04) (hash(x)=143755114)
|
| 248 |
+
2040 train 4.237622 (lr=7.3985e-04) (hash(x)=147324095)
|
| 249 |
+
2050 train 4.332928 (lr=7.3909e-04) (hash(x)=141727373)
|
| 250 |
+
2060 train 4.418235 (lr=7.3833e-04) (hash(x)=162053052)
|
| 251 |
+
2070 train 4.464035 (lr=7.3756e-04) (hash(x)=162596975)
|
| 252 |
+
2080 train 4.385101 (lr=7.3678e-04) (hash(x)=161242340)
|
| 253 |
+
2090 train 4.371880 (lr=7.3600e-04) (hash(x)=148583522)
|
| 254 |
+
2100 val loss 4.5540
|
| 255 |
+
2100 val perplexity 95.0149
|
| 256 |
+
2100 train 4.437373 (lr=7.3522e-04) (hash(x)=158239484)
|
| 257 |
+
2110 train 4.354429 (lr=7.3444e-04) (hash(x)=152610058)
|
| 258 |
+
2120 train 4.409340 (lr=7.3364e-04) (hash(x)=146582203)
|
| 259 |
+
2130 train 4.129742 (lr=7.3285e-04) (hash(x)=146686436)
|
| 260 |
+
2140 train 4.537238 (lr=7.3205e-04) (hash(x)=142827295)
|
| 261 |
+
2150 train 4.455830 (lr=7.3125e-04) (hash(x)=150747398)
|
| 262 |
+
2160 train 4.733751 (lr=7.3044e-04) (hash(x)=150777134)
|
| 263 |
+
2170 train 4.413770 (lr=7.2963e-04) (hash(x)=157002856)
|
| 264 |
+
2180 train 4.465530 (lr=7.2881e-04) (hash(x)=150442337)
|
| 265 |
+
2190 train 4.423717 (lr=7.2799e-04) (hash(x)=150799081)
|
| 266 |
+
2200 val loss 4.4807
|
| 267 |
+
2200 val perplexity 88.2965
|
| 268 |
+
2200 train 4.362355 (lr=7.2716e-04) (hash(x)=140504180)
|
| 269 |
+
2210 train 4.492737 (lr=7.2634e-04) (hash(x)=149088475)
|
| 270 |
+
2220 train 4.455531 (lr=7.2550e-04) (hash(x)=155180847)
|
| 271 |
+
2230 train 4.377587 (lr=7.2467e-04) (hash(x)=159347164)
|
| 272 |
+
2240 train 4.543031 (lr=7.2382e-04) (hash(x)=153574288)
|
| 273 |
+
2250 train 4.486637 (lr=7.2298e-04) (hash(x)=142603512)
|
| 274 |
+
2260 train 4.500721 (lr=7.2213e-04) (hash(x)=142953831)
|
| 275 |
+
2270 train 4.397542 (lr=7.2128e-04) (hash(x)=137642681)
|
| 276 |
+
2280 train 4.408342 (lr=7.2042e-04) (hash(x)=158106614)
|
| 277 |
+
2290 train 4.403256 (lr=7.1956e-04) (hash(x)=160787891)
|
| 278 |
+
2300 val loss 4.4439
|
| 279 |
+
2300 val perplexity 85.1104
|
| 280 |
+
2300 train 4.512861 (lr=7.1869e-04) (hash(x)=142234024)
|
| 281 |
+
2310 train 4.417135 (lr=7.1782e-04) (hash(x)=138192210)
|
| 282 |
+
2320 train 4.441013 (lr=7.1695e-04) (hash(x)=147727662)
|
| 283 |
+
2330 train 4.380257 (lr=7.1607e-04) (hash(x)=169324653)
|
| 284 |
+
2340 train 4.493105 (lr=7.1519e-04) (hash(x)=145350355)
|
| 285 |
+
2350 train 4.494195 (lr=7.1430e-04) (hash(x)=156909016)
|
| 286 |
+
2360 train 4.408182 (lr=7.1341e-04) (hash(x)=144559543)
|
| 287 |
+
2370 train 4.400643 (lr=7.1252e-04) (hash(x)=153212312)
|
| 288 |
+
2380 train 4.370908 (lr=7.1162e-04) (hash(x)=131816284)
|
| 289 |
+
2390 train 4.426950 (lr=7.1072e-04) (hash(x)=165818309)
|
| 290 |
+
2400 val loss 4.4459
|
| 291 |
+
2400 val perplexity 85.2803
|
| 292 |
+
2400 train 4.459247 (lr=7.0981e-04) (hash(x)=143091562)
|
| 293 |
+
2410 train 4.344828 (lr=7.0890e-04) (hash(x)=154010697)
|
| 294 |
+
2420 train 4.326580 (lr=7.0799e-04) (hash(x)=144844001)
|
| 295 |
+
2430 train 4.488793 (lr=7.0707e-04) (hash(x)=156389834)
|
| 296 |
+
2440 train 4.171124 (lr=7.0615e-04) (hash(x)=162425919)
|
| 297 |
+
2450 train 4.425237 (lr=7.0523e-04) (hash(x)=154200479)
|
| 298 |
+
2460 train 4.354559 (lr=7.0430e-04) (hash(x)=159066617)
|
| 299 |
+
2470 train 4.158089 (lr=7.0337e-04) (hash(x)=148278058)
|
| 300 |
+
2480 train 4.122016 (lr=7.0243e-04) (hash(x)=165598522)
|
| 301 |
+
2490 train 4.438636 (lr=7.0149e-04) (hash(x)=141306086)
|
| 302 |
+
2500 val loss 4.4752
|
| 303 |
+
2500 val perplexity 87.8132
|
| 304 |
+
2500 train 4.294726 (lr=7.0054e-04) (hash(x)=149857456)
|
| 305 |
+
2510 train 4.284560 (lr=6.9960e-04) (hash(x)=150368907)
|
| 306 |
+
2520 train 4.236595 (lr=6.9864e-04) (hash(x)=153394920)
|
| 307 |
+
2530 train 4.216421 (lr=6.9769e-04) (hash(x)=159740116)
|
| 308 |
+
2540 train 4.369461 (lr=6.9673e-04) (hash(x)=161620367)
|
| 309 |
+
2550 train 4.451651 (lr=6.9577e-04) (hash(x)=147223658)
|
| 310 |
+
2560 train 4.545908 (lr=6.9480e-04) (hash(x)=158146613)
|
| 311 |
+
2570 train 4.444758 (lr=6.9383e-04) (hash(x)=136375336)
|
| 312 |
+
2580 train 4.481951 (lr=6.9286e-04) (hash(x)=149298016)
|
| 313 |
+
2590 train 4.405572 (lr=6.9188e-04) (hash(x)=150720933)
|
| 314 |
+
2600 val loss 4.4096
|
| 315 |
+
2600 val perplexity 82.2385
|
| 316 |
+
2600 train 4.510528 (lr=6.9090e-04) (hash(x)=146191551)
|
| 317 |
+
2610 train 4.317633 (lr=6.8991e-04) (hash(x)=151413395)
|
| 318 |
+
2620 train 4.533701 (lr=6.8892e-04) (hash(x)=162094106)
|
| 319 |
+
2630 train 4.404751 (lr=6.8793e-04) (hash(x)=150608302)
|
| 320 |
+
2640 train 4.319120 (lr=6.8694e-04) (hash(x)=146115160)
|
| 321 |
+
2650 train 4.413404 (lr=6.8594e-04) (hash(x)=138242788)
|
| 322 |
+
2660 train 4.600614 (lr=6.8493e-04) (hash(x)=159921837)
|
| 323 |
+
2670 train 4.239727 (lr=6.8393e-04) (hash(x)=137205989)
|
| 324 |
+
2680 train 4.257802 (lr=6.8292e-04) (hash(x)=158608524)
|
| 325 |
+
2690 train 4.291055 (lr=6.8190e-04) (hash(x)=153322085)
|
| 326 |
+
2700 val loss 4.3896
|
| 327 |
+
2700 val perplexity 80.6121
|
| 328 |
+
2700 train 4.331791 (lr=6.8089e-04) (hash(x)=145375752)
|
| 329 |
+
2710 train 4.348867 (lr=6.7987e-04) (hash(x)=145036398)
|
| 330 |
+
2720 train 4.369700 (lr=6.7884e-04) (hash(x)=140064355)
|
| 331 |
+
2730 train 4.403379 (lr=6.7782e-04) (hash(x)=148983355)
|
| 332 |
+
2740 train 4.296770 (lr=6.7678e-04) (hash(x)=147636026)
|
| 333 |
+
2750 train 4.354241 (lr=6.7575e-04) (hash(x)=151763585)
|
| 334 |
+
2760 train 4.278496 (lr=6.7471e-04) (hash(x)=178033416)
|
| 335 |
+
2770 train 4.243112 (lr=6.7367e-04) (hash(x)=147097669)
|
| 336 |
+
2780 train 4.208759 (lr=6.7263e-04) (hash(x)=140475447)
|
| 337 |
+
2790 train 4.322309 (lr=6.7158e-04) (hash(x)=141135962)
|
| 338 |
+
2800 val loss 4.3828
|
| 339 |
+
2800 val perplexity 80.0634
|
| 340 |
+
2800 train 4.221279 (lr=6.7053e-04) (hash(x)=151568014)
|
| 341 |
+
2810 train 4.934597 (lr=6.6947e-04) (hash(x)=170629615)
|
| 342 |
+
2820 train 4.303170 (lr=6.6841e-04) (hash(x)=151858146)
|
| 343 |
+
2830 train 4.210390 (lr=6.6735e-04) (hash(x)=152170305)
|
| 344 |
+
2840 train 4.129820 (lr=6.6629e-04) (hash(x)=150705881)
|
| 345 |
+
2850 train 4.163996 (lr=6.6522e-04) (hash(x)=146997394)
|
| 346 |
+
2860 train 4.152957 (lr=6.6415e-04) (hash(x)=159749180)
|
| 347 |
+
2870 train 4.034689 (lr=6.6308e-04) (hash(x)=147618423)
|
| 348 |
+
2880 train 4.229532 (lr=6.6200e-04) (hash(x)=140778993)
|
| 349 |
+
2890 train 4.103230 (lr=6.6092e-04) (hash(x)=150735837)
|
| 350 |
+
2900 val loss 4.3834
|
| 351 |
+
2900 val perplexity 80.1119
|
| 352 |
+
2900 train 4.162219 (lr=6.5983e-04) (hash(x)=149366597)
|
| 353 |
+
2910 train 4.283740 (lr=6.5875e-04) (hash(x)=181602500)
|
| 354 |
+
2920 train 4.244694 (lr=6.5766e-04) (hash(x)=148080200)
|
| 355 |
+
2930 train 4.081357 (lr=6.5656e-04) (hash(x)=150629961)
|
| 356 |
+
2940 train 4.262661 (lr=6.5547e-04) (hash(x)=155786888)
|
| 357 |
+
2950 train 4.263927 (lr=6.5437e-04) (hash(x)=148553059)
|
| 358 |
+
2960 train 4.380385 (lr=6.5326e-04) (hash(x)=158494862)
|
| 359 |
+
2970 train 4.492483 (lr=6.5216e-04) (hash(x)=147684099)
|
| 360 |
+
2980 train 4.263389 (lr=6.5105e-04) (hash(x)=159008790)
|
| 361 |
+
2990 train 4.413972 (lr=6.4994e-04) (hash(x)=148288782)
|
| 362 |
+
3000 val loss 4.3429
|
| 363 |
+
3000 val perplexity 76.9281
|
| 364 |
+
3000 train 4.276694 (lr=6.4882e-04) (hash(x)=150464442)
|
| 365 |
+
3010 train 4.349776 (lr=6.4770e-04) (hash(x)=148665916)
|
| 366 |
+
3020 train 4.292125 (lr=6.4658e-04) (hash(x)=159788454)
|
| 367 |
+
3030 train 4.379039 (lr=6.4546e-04) (hash(x)=170224765)
|
| 368 |
+
3040 train 4.265642 (lr=6.4433e-04) (hash(x)=139746299)
|
| 369 |
+
3050 train 4.342177 (lr=6.4320e-04) (hash(x)=173491884)
|
| 370 |
+
3060 train 4.319968 (lr=6.4207e-04) (hash(x)=146098725)
|
| 371 |
+
3070 train 4.291288 (lr=6.4093e-04) (hash(x)=154713525)
|
| 372 |
+
3080 train 4.318592 (lr=6.3979e-04) (hash(x)=151206978)
|
| 373 |
+
3090 train 4.356441 (lr=6.3865e-04) (hash(x)=144250687)
|
| 374 |
+
3100 val loss 4.3596
|
| 375 |
+
3100 val perplexity 78.2258
|
| 376 |
+
3100 train 4.395173 (lr=6.3750e-04) (hash(x)=182449036)
|
| 377 |
+
3110 train 4.214971 (lr=6.3636e-04) (hash(x)=145504538)
|
| 378 |
+
3120 train 4.246961 (lr=6.3521e-04) (hash(x)=147948751)
|
| 379 |
+
3130 train 4.192139 (lr=6.3405e-04) (hash(x)=144547711)
|
| 380 |
+
3140 train 4.310242 (lr=6.3290e-04) (hash(x)=158622029)
|
| 381 |
+
3150 train 4.271168 (lr=6.3174e-04) (hash(x)=155949476)
|
| 382 |
+
3160 train 4.276151 (lr=6.3058e-04) (hash(x)=129245664)
|
| 383 |
+
3170 train 4.289102 (lr=6.2941e-04) (hash(x)=157162959)
|
| 384 |
+
3180 train 4.353170 (lr=6.2825e-04) (hash(x)=163102434)
|
| 385 |
+
3190 train 4.390101 (lr=6.2708e-04) (hash(x)=155952009)
|
| 386 |
+
3200 val loss 4.3352
|
| 387 |
+
3200 val perplexity 76.3420
|
| 388 |
+
3200 train 4.271265 (lr=6.2590e-04) (hash(x)=140141286)
|
| 389 |
+
3210 train 4.270248 (lr=6.2473e-04) (hash(x)=148811694)
|
| 390 |
+
3220 train 4.210612 (lr=6.2355e-04) (hash(x)=143433404)
|
| 391 |
+
3230 train 4.263620 (lr=6.2237e-04) (hash(x)=150525065)
|
| 392 |
+
3240 train 4.156843 (lr=6.2119e-04) (hash(x)=152014854)
|
| 393 |
+
3250 train 4.045469 (lr=6.2000e-04) (hash(x)=144716153)
|
| 394 |
+
3260 train 4.375982 (lr=6.1881e-04) (hash(x)=145324818)
|
| 395 |
+
3270 train 4.309959 (lr=6.1762e-04) (hash(x)=154930419)
|
| 396 |
+
3280 train 4.306784 (lr=6.1643e-04) (hash(x)=144649958)
|
| 397 |
+
3290 train 4.294215 (lr=6.1523e-04) (hash(x)=156496147)
|
| 398 |
+
3300 val loss 4.3204
|
| 399 |
+
3300 val perplexity 75.2181
|
| 400 |
+
3300 train 4.240705 (lr=6.1403e-04) (hash(x)=148099414)
|
| 401 |
+
3310 train 4.302856 (lr=6.1283e-04) (hash(x)=141081470)
|
| 402 |
+
3320 train 4.276582 (lr=6.1163e-04) (hash(x)=151572529)
|
| 403 |
+
3330 train 4.232923 (lr=6.1042e-04) (hash(x)=146887343)
|
| 404 |
+
3340 train 4.273978 (lr=6.0921e-04) (hash(x)=148612634)
|
| 405 |
+
3350 train 4.232584 (lr=6.0800e-04) (hash(x)=145218304)
|
| 406 |
+
3360 train 4.165869 (lr=6.0679e-04) (hash(x)=146893345)
|
| 407 |
+
3370 train 4.241447 (lr=6.0557e-04) (hash(x)=159302018)
|
| 408 |
+
3380 train 4.306074 (lr=6.0435e-04) (hash(x)=164117611)
|
| 409 |
+
3390 train 4.181183 (lr=6.0313e-04) (hash(x)=142401925)
|
| 410 |
+
3400 val loss 4.3082
|
| 411 |
+
3400 val perplexity 74.3046
|
| 412 |
+
3400 train 4.163392 (lr=6.0191e-04) (hash(x)=142633951)
|
| 413 |
+
3410 train 4.288529 (lr=6.0068e-04) (hash(x)=148491904)
|
| 414 |
+
3420 train 4.335003 (lr=5.9945e-04) (hash(x)=144013244)
|
| 415 |
+
3430 train 4.146573 (lr=5.9822e-04) (hash(x)=146939843)
|
| 416 |
+
3440 train 4.175786 (lr=5.9699e-04) (hash(x)=161055964)
|
| 417 |
+
3450 train 4.076260 (lr=5.9576e-04) (hash(x)=134825681)
|
| 418 |
+
3460 train 4.268161 (lr=5.9452e-04) (hash(x)=145087511)
|
| 419 |
+
3470 train 4.089385 (lr=5.9328e-04) (hash(x)=144200286)
|
| 420 |
+
3480 train 4.130699 (lr=5.9204e-04) (hash(x)=157605428)
|
| 421 |
+
3490 train 4.316826 (lr=5.9080e-04) (hash(x)=153636990)
|
| 422 |
+
3500 val loss 4.3115
|
| 423 |
+
3500 val perplexity 74.5501
|
| 424 |
+
3500 train 4.169837 (lr=5.8955e-04) (hash(x)=148368965)
|
| 425 |
+
3510 train 4.075866 (lr=5.8830e-04) (hash(x)=144775557)
|
| 426 |
+
3520 train 4.250553 (lr=5.8705e-04) (hash(x)=151539855)
|
| 427 |
+
3530 train 4.262748 (lr=5.8580e-04) (hash(x)=168384321)
|
| 428 |
+
3540 train 4.407971 (lr=5.8454e-04) (hash(x)=155671447)
|
| 429 |
+
3550 train 4.441235 (lr=5.8329e-04) (hash(x)=157403334)
|
| 430 |
+
3560 train 4.209557 (lr=5.8203e-04) (hash(x)=139495714)
|
| 431 |
+
3570 train 4.347342 (lr=5.8077e-04) (hash(x)=147685555)
|
| 432 |
+
3580 train 4.472521 (lr=5.7951e-04) (hash(x)=154209753)
|
| 433 |
+
3590 train 4.086065 (lr=5.7824e-04) (hash(x)=166864372)
|
| 434 |
+
3600 val loss 4.2907
|
| 435 |
+
3600 val perplexity 73.0203
|
| 436 |
+
3600 train 4.200510 (lr=5.7697e-04) (hash(x)=152372067)
|
| 437 |
+
3610 train 4.481126 (lr=5.7571e-04) (hash(x)=156579291)
|
| 438 |
+
3620 train 4.064327 (lr=5.7443e-04) (hash(x)=152969451)
|
| 439 |
+
3630 train 4.037411 (lr=5.7316e-04) (hash(x)=164428105)
|
| 440 |
+
3640 train 4.215364 (lr=5.7189e-04) (hash(x)=153325907)
|
| 441 |
+
3650 train 4.196020 (lr=5.7061e-04) (hash(x)=159197101)
|
| 442 |
+
3660 train 4.183208 (lr=5.6933e-04) (hash(x)=157503290)
|
| 443 |
+
3670 train 4.105588 (lr=5.6805e-04) (hash(x)=149036650)
|
| 444 |
+
3680 train 4.110247 (lr=5.6677e-04) (hash(x)=144525088)
|
| 445 |
+
3690 train 4.224317 (lr=5.6549e-04) (hash(x)=143154211)
|
| 446 |
+
3700 val loss 4.2872
|
| 447 |
+
3700 val perplexity 72.7606
|
| 448 |
+
3700 train 4.217520 (lr=5.6420e-04) (hash(x)=168885609)
|
| 449 |
+
3710 train 4.182745 (lr=5.6291e-04) (hash(x)=148815644)
|
| 450 |
+
3720 train 4.113211 (lr=5.6162e-04) (hash(x)=153279629)
|
| 451 |
+
3730 train 4.131580 (lr=5.6033e-04) (hash(x)=148181200)
|
| 452 |
+
3740 train 4.099375 (lr=5.5904e-04) (hash(x)=151357364)
|
| 453 |
+
3750 train 4.063350 (lr=5.5774e-04) (hash(x)=145269246)
|
| 454 |
+
3760 train 4.141498 (lr=5.5645e-04) (hash(x)=148923398)
|
| 455 |
+
3770 train 4.138111 (lr=5.5515e-04) (hash(x)=141205226)
|
| 456 |
+
3780 train 4.027296 (lr=5.5385e-04) (hash(x)=146180296)
|
| 457 |
+
3790 train 4.098681 (lr=5.5255e-04) (hash(x)=169790000)
|
| 458 |
+
3800 val loss 4.2884
|
| 459 |
+
3800 val perplexity 72.8520
|
| 460 |
+
3800 train 4.140154 (lr=5.5125e-04) (hash(x)=141633734)
|
| 461 |
+
3810 train 4.264968 (lr=5.4994e-04) (hash(x)=156306070)
|
| 462 |
+
3820 train 4.257529 (lr=5.4864e-04) (hash(x)=158769870)
|
| 463 |
+
3830 train 4.221703 (lr=5.4733e-04) (hash(x)=165301927)
|
| 464 |
+
3840 train 4.261649 (lr=5.4602e-04) (hash(x)=147025475)
|
| 465 |
+
3850 train 4.204757 (lr=5.4471e-04) (hash(x)=141223580)
|
| 466 |
+
3860 train 4.229239 (lr=5.4340e-04) (hash(x)=139668795)
|
| 467 |
+
3870 train 4.290291 (lr=5.4208e-04) (hash(x)=155839599)
|
| 468 |
+
3880 train 4.349567 (lr=5.4077e-04) (hash(x)=150635541)
|
| 469 |
+
3890 train 4.344969 (lr=5.3945e-04) (hash(x)=153702524)
|
| 470 |
+
3900 val loss 4.2637
|
| 471 |
+
3900 val perplexity 71.0743
|
| 472 |
+
3900 train 4.167935 (lr=5.3813e-04) (hash(x)=153141007)
|
| 473 |
+
3910 train 4.255192 (lr=5.3681e-04) (hash(x)=145483115)
|
| 474 |
+
3920 train 4.044975 (lr=5.3549e-04) (hash(x)=147480523)
|
| 475 |
+
3930 train 4.221537 (lr=5.3417e-04) (hash(x)=146229467)
|
| 476 |
+
3940 train 4.202239 (lr=5.3284e-04) (hash(x)=151376187)
|
| 477 |
+
3950 train 4.170072 (lr=5.3152e-04) (hash(x)=153745186)
|
| 478 |
+
3960 train 4.128955 (lr=5.3019e-04) (hash(x)=147595615)
|
| 479 |
+
3970 train 4.266096 (lr=5.2886e-04) (hash(x)=157979848)
|
| 480 |
+
3980 train 4.131737 (lr=5.2754e-04) (hash(x)=153714091)
|
| 481 |
+
3990 train 4.166999 (lr=5.2620e-04) (hash(x)=155637629)
|
| 482 |
+
4000 val loss 4.2596
|
| 483 |
+
4000 val perplexity 70.7806
|
| 484 |
+
4000 train 4.197123 (lr=5.2487e-04) (hash(x)=160577202)
|
| 485 |
+
4010 train 4.104901 (lr=5.2354e-04) (hash(x)=147432640)
|
| 486 |
+
4020 train 4.067557 (lr=5.2221e-04) (hash(x)=135542902)
|
| 487 |
+
4030 train 4.200021 (lr=5.2087e-04) (hash(x)=143137909)
|
| 488 |
+
4040 train 4.196943 (lr=5.1953e-04) (hash(x)=148269908)
|
| 489 |
+
4050 train 4.077495 (lr=5.1820e-04) (hash(x)=141954182)
|
| 490 |
+
4060 train 4.168184 (lr=5.1686e-04) (hash(x)=157035179)
|
| 491 |
+
4070 train 3.890860 (lr=5.1552e-04) (hash(x)=151361423)
|
| 492 |
+
4080 train 4.016812 (lr=5.1418e-04) (hash(x)=144373988)
|
| 493 |
+
4090 train 4.229814 (lr=5.1284e-04) (hash(x)=156461428)
|
| 494 |
+
4100 val loss 4.2536
|
| 495 |
+
4100 val perplexity 70.3554
|
| 496 |
+
4100 train 4.337818 (lr=5.1149e-04) (hash(x)=153858169)
|
| 497 |
+
4110 train 4.302637 (lr=5.1015e-04) (hash(x)=165506959)
|
| 498 |
+
4120 train 4.307225 (lr=5.0880e-04) (hash(x)=158709009)
|
| 499 |
+
4130 train 4.383077 (lr=5.0746e-04) (hash(x)=151836522)
|
| 500 |
+
4140 train 4.145933 (lr=5.0611e-04) (hash(x)=152917389)
|
| 501 |
+
4150 train 4.194824 (lr=5.0476e-04) (hash(x)=146973868)
|
| 502 |
+
4160 train 4.292345 (lr=5.0341e-04) (hash(x)=157875887)
|
| 503 |
+
4170 train 4.574834 (lr=5.0206e-04) (hash(x)=167933111)
|
| 504 |
+
4180 train 4.161945 (lr=5.0071e-04) (hash(x)=161938168)
|
| 505 |
+
4190 train 4.143842 (lr=4.9936e-04) (hash(x)=158102630)
|
| 506 |
+
4200 val loss 4.2357
|
| 507 |
+
4200 val perplexity 69.1110
|
| 508 |
+
4200 train 4.255004 (lr=4.9801e-04) (hash(x)=155889149)
|
| 509 |
+
4210 train 4.343439 (lr=4.9665e-04) (hash(x)=131046288)
|
| 510 |
+
4220 train 4.102593 (lr=4.9530e-04) (hash(x)=149423408)
|
| 511 |
+
4230 train 4.191511 (lr=4.9395e-04) (hash(x)=150033580)
|
| 512 |
+
4240 train 4.084181 (lr=4.9259e-04) (hash(x)=137509644)
|
| 513 |
+
4250 train 4.258571 (lr=4.9123e-04) (hash(x)=161159362)
|
| 514 |
+
4260 train 4.159616 (lr=4.8988e-04) (hash(x)=148117355)
|
| 515 |
+
4270 train 4.094699 (lr=4.8852e-04) (hash(x)=147315384)
|
| 516 |
+
4280 train 4.150157 (lr=4.8716e-04) (hash(x)=156577316)
|
| 517 |
+
4290 train 4.340037 (lr=4.8580e-04) (hash(x)=161553761)
|
| 518 |
+
4300 val loss 4.2312
|
| 519 |
+
4300 val perplexity 68.7999
|
| 520 |
+
4300 train 3.985034 (lr=4.8444e-04) (hash(x)=152294662)
|
| 521 |
+
4310 train 4.017335 (lr=4.8308e-04) (hash(x)=144616611)
|
| 522 |
+
4320 train 4.176939 (lr=4.8172e-04) (hash(x)=154134591)
|
| 523 |
+
4330 train 4.037823 (lr=4.8036e-04) (hash(x)=159947834)
|
| 524 |
+
4340 train 4.018911 (lr=4.7899e-04) (hash(x)=156261313)
|
| 525 |
+
4350 train 4.131335 (lr=4.7763e-04) (hash(x)=141245643)
|
| 526 |
+
4360 train 4.101488 (lr=4.7627e-04) (hash(x)=157291204)
|
| 527 |
+
4370 train 4.132045 (lr=4.7490e-04) (hash(x)=142877676)
|
| 528 |
+
4380 train 4.179982 (lr=4.7354e-04) (hash(x)=155174402)
|
| 529 |
+
4390 train 4.027390 (lr=4.7217e-04) (hash(x)=154675451)
|
| 530 |
+
4400 val loss 4.2285
|
| 531 |
+
4400 val perplexity 68.6117
|
| 532 |
+
4400 train 4.197064 (lr=4.7081e-04) (hash(x)=141804386)
|
| 533 |
+
4410 train 4.414270 (lr=4.6944e-04) (hash(x)=163930619)
|
| 534 |
+
4420 train 4.285137 (lr=4.6807e-04) (hash(x)=139437472)
|
| 535 |
+
4430 train 4.228657 (lr=4.6671e-04) (hash(x)=142474831)
|
| 536 |
+
4440 train 4.242911 (lr=4.6534e-04) (hash(x)=150102428)
|
| 537 |
+
4450 train 4.209610 (lr=4.6397e-04) (hash(x)=135805460)
|
| 538 |
+
4460 train 4.174462 (lr=4.6260e-04) (hash(x)=154732100)
|
| 539 |
+
4470 train 4.177282 (lr=4.6124e-04) (hash(x)=148554435)
|
| 540 |
+
4480 train 4.120358 (lr=4.5987e-04) (hash(x)=142410065)
|
| 541 |
+
4490 train 4.150236 (lr=4.5850e-04) (hash(x)=148108338)
|
| 542 |
+
4500 val loss 4.2082
|
| 543 |
+
4500 val perplexity 67.2346
|
| 544 |
+
4500 train 4.047217 (lr=4.5713e-04) (hash(x)=151095242)
|
| 545 |
+
4510 train 4.058399 (lr=4.5576e-04) (hash(x)=154911617)
|
| 546 |
+
4520 train 4.106719 (lr=4.5439e-04) (hash(x)=150858662)
|
| 547 |
+
4530 train 4.055121 (lr=4.5302e-04) (hash(x)=146850830)
|
| 548 |
+
4540 train 4.116180 (lr=4.5165e-04) (hash(x)=153506103)
|
| 549 |
+
4550 train 4.117402 (lr=4.5028e-04) (hash(x)=157068400)
|
| 550 |
+
4560 train 4.200628 (lr=4.4891e-04) (hash(x)=163640327)
|
| 551 |
+
4570 train 4.254792 (lr=4.4754e-04) (hash(x)=158962962)
|
| 552 |
+
4580 train 4.123038 (lr=4.4617e-04) (hash(x)=143454481)
|
| 553 |
+
4590 train 4.127841 (lr=4.4480e-04) (hash(x)=155380269)
|
| 554 |
+
4600 val loss 4.2468
|
| 555 |
+
4600 val perplexity 69.8807
|
| 556 |
+
4600 train 4.274385 (lr=4.4343e-04) (hash(x)=156414699)
|
| 557 |
+
4610 train 4.101875 (lr=4.4206e-04) (hash(x)=153520595)
|
| 558 |
+
4620 train 4.126172 (lr=4.4069e-04) (hash(x)=151287061)
|
| 559 |
+
4630 train 3.953681 (lr=4.3931e-04) (hash(x)=144972877)
|
| 560 |
+
4640 train 4.076117 (lr=4.3794e-04) (hash(x)=152031134)
|
| 561 |
+
4650 train 4.214238 (lr=4.3657e-04) (hash(x)=155348609)
|
| 562 |
+
4660 train 3.999416 (lr=4.3520e-04) (hash(x)=144855343)
|
| 563 |
+
4670 train 4.153498 (lr=4.3383e-04) (hash(x)=159247995)
|
| 564 |
+
4680 train 4.042363 (lr=4.3246e-04) (hash(x)=133146878)
|
| 565 |
+
4690 train 4.272006 (lr=4.3109e-04) (hash(x)=148797338)
|
| 566 |
+
4700 val loss 4.2037
|
| 567 |
+
4700 val perplexity 66.9357
|
| 568 |
+
4700 train 4.158514 (lr=4.2972e-04) (hash(x)=161556686)
|
| 569 |
+
4710 train 4.343598 (lr=4.2835e-04) (hash(x)=142528636)
|
| 570 |
+
4720 train 4.275161 (lr=4.2698e-04) (hash(x)=148322603)
|
| 571 |
+
4730 train 4.187306 (lr=4.2561e-04) (hash(x)=145051555)
|
| 572 |
+
4740 train 4.103632 (lr=4.2424e-04) (hash(x)=146193153)
|
| 573 |
+
4750 train 4.299421 (lr=4.2287e-04) (hash(x)=165802167)
|
| 574 |
+
4760 train 4.241821 (lr=4.2150e-04) (hash(x)=158948628)
|
| 575 |
+
4770 train 4.297499 (lr=4.2013e-04) (hash(x)=156177788)
|
| 576 |
+
4780 train 4.148581 (lr=4.1876e-04) (hash(x)=175446069)
|
| 577 |
+
4790 train 4.170279 (lr=4.1740e-04) (hash(x)=141100706)
|
| 578 |
+
4800 val loss 4.1999
|
| 579 |
+
4800 val perplexity 66.6807
|
| 580 |
+
4800 train 4.087453 (lr=4.1603e-04) (hash(x)=149000293)
|
| 581 |
+
4810 train 4.022676 (lr=4.1466e-04) (hash(x)=135891778)
|
| 582 |
+
4820 train 4.074157 (lr=4.1329e-04) (hash(x)=145474733)
|
| 583 |
+
4830 train 4.132744 (lr=4.1193e-04) (hash(x)=145187742)
|
| 584 |
+
4840 train 4.176939 (lr=4.1056e-04) (hash(x)=157685237)
|
| 585 |
+
4850 train 4.014524 (lr=4.0919e-04) (hash(x)=128599506)
|
| 586 |
+
4860 train 4.106462 (lr=4.0783e-04) (hash(x)=142067051)
|
| 587 |
+
4870 train 4.060631 (lr=4.0646e-04) (hash(x)=156215711)
|
| 588 |
+
4880 train 4.241800 (lr=4.0510e-04) (hash(x)=150456895)
|
| 589 |
+
4890 train 3.870941 (lr=4.0373e-04) (hash(x)=141647202)
|
| 590 |
+
4900 val loss 4.1891
|
| 591 |
+
4900 val perplexity 65.9613
|
| 592 |
+
4900 train 3.934667 (lr=4.0237e-04) (hash(x)=154349989)
|
| 593 |
+
4910 train 3.962008 (lr=4.0101e-04) (hash(x)=151563396)
|
| 594 |
+
4920 train 3.985592 (lr=3.9964e-04) (hash(x)=138868314)
|
| 595 |
+
4930 train 4.125028 (lr=3.9828e-04) (hash(x)=148533460)
|
| 596 |
+
4940 train 4.120391 (lr=3.9692e-04) (hash(x)=144892493)
|
| 597 |
+
4950 train 4.139394 (lr=3.9556e-04) (hash(x)=170326431)
|
| 598 |
+
4960 train 4.133707 (lr=3.9420e-04) (hash(x)=163312680)
|
| 599 |
+
4970 train 4.099628 (lr=3.9284e-04) (hash(x)=184352734)
|
| 600 |
+
4980 train 4.171930 (lr=3.9148e-04) (hash(x)=140363733)
|
| 601 |
+
4990 train 4.072880 (lr=3.9012e-04) (hash(x)=147794873)
|
| 602 |
+
5000 val loss 4.1830
|
| 603 |
+
5000 val perplexity 65.5644
|
| 604 |
+
5000 train 4.167898 (lr=3.8877e-04) (hash(x)=131475967)
|
| 605 |
+
5010 train 4.271088 (lr=3.8741e-04) (hash(x)=139560000)
|
| 606 |
+
5020 train 4.173810 (lr=3.8605e-04) (hash(x)=160128701)
|
| 607 |
+
5030 train 4.287411 (lr=3.8470e-04) (hash(x)=154698531)
|
| 608 |
+
5040 train 4.248640 (lr=3.8335e-04) (hash(x)=153833791)
|
| 609 |
+
5050 train 4.170629 (lr=3.8199e-04) (hash(x)=145953388)
|
| 610 |
+
5060 train 4.517692 (lr=3.8064e-04) (hash(x)=134297881)
|
| 611 |
+
5070 train 4.169985 (lr=3.7929e-04) (hash(x)=159987550)
|
| 612 |
+
5080 train 4.168464 (lr=3.7794e-04) (hash(x)=147699302)
|
| 613 |
+
5090 train 3.886464 (lr=3.7659e-04) (hash(x)=140534876)
|
| 614 |
+
5100 val loss 4.1779
|
| 615 |
+
5100 val perplexity 65.2258
|
| 616 |
+
5100 train 4.094859 (lr=3.7524e-04) (hash(x)=149717902)
|
| 617 |
+
5110 train 4.011804 (lr=3.7389e-04) (hash(x)=147648148)
|
| 618 |
+
5120 train 4.026576 (lr=3.7254e-04) (hash(x)=170962791)
|
| 619 |
+
5130 train 4.078098 (lr=3.7120e-04) (hash(x)=139633288)
|
| 620 |
+
5140 train 4.241095 (lr=3.6985e-04) (hash(x)=160163221)
|
| 621 |
+
5150 train 4.080642 (lr=3.6851e-04) (hash(x)=146625393)
|
| 622 |
+
5160 train 4.141926 (lr=3.6716e-04) (hash(x)=147399092)
|
| 623 |
+
5170 train 3.977932 (lr=3.6582e-04) (hash(x)=147172792)
|
| 624 |
+
5180 train 4.083449 (lr=3.6448e-04) (hash(x)=140600568)
|
| 625 |
+
5190 train 4.010283 (lr=3.6314e-04) (hash(x)=152423962)
|
| 626 |
+
5200 val loss 4.1738
|
| 627 |
+
5200 val perplexity 64.9593
|
| 628 |
+
5200 train 4.113544 (lr=3.6180e-04) (hash(x)=151407999)
|
| 629 |
+
5210 train 4.060960 (lr=3.6047e-04) (hash(x)=154874903)
|
| 630 |
+
5220 train 3.878493 (lr=3.5913e-04) (hash(x)=154133697)
|
| 631 |
+
5230 train 4.058887 (lr=3.5779e-04) (hash(x)=148148721)
|
| 632 |
+
5240 train 4.048518 (lr=3.5646e-04) (hash(x)=149681665)
|
| 633 |
+
5250 train 4.019365 (lr=3.5513e-04) (hash(x)=150136904)
|
| 634 |
+
5260 train 4.124552 (lr=3.5380e-04) (hash(x)=149261170)
|
| 635 |
+
5270 train 4.098753 (lr=3.5246e-04) (hash(x)=155540595)
|
| 636 |
+
5280 train 4.112729 (lr=3.5114e-04) (hash(x)=141973714)
|
| 637 |
+
5290 train 4.549044 (lr=3.4981e-04) (hash(x)=146827439)
|
| 638 |
+
5300 val loss 4.1624
|
| 639 |
+
5300 val perplexity 64.2232
|
| 640 |
+
5300 train 4.121033 (lr=3.4848e-04) (hash(x)=168602728)
|
| 641 |
+
5310 train 4.109458 (lr=3.4716e-04) (hash(x)=144035757)
|
| 642 |
+
5320 train 4.164502 (lr=3.4583e-04) (hash(x)=143287560)
|
| 643 |
+
5330 train 4.103524 (lr=3.4451e-04) (hash(x)=142461814)
|
| 644 |
+
5340 train 4.138205 (lr=3.4319e-04) (hash(x)=149905536)
|
| 645 |
+
5350 train 4.240426 (lr=3.4187e-04) (hash(x)=134597061)
|
| 646 |
+
5360 train 4.260373 (lr=3.4055e-04) (hash(x)=156520228)
|
| 647 |
+
5370 train 4.166106 (lr=3.3923e-04) (hash(x)=152690323)
|
| 648 |
+
5380 train 4.114301 (lr=3.3792e-04) (hash(x)=140092622)
|
| 649 |
+
5390 train 4.074981 (lr=3.3660e-04) (hash(x)=153504017)
|
| 650 |
+
5400 val loss 4.1477
|
| 651 |
+
5400 val perplexity 63.2883
|
| 652 |
+
5400 train 4.093682 (lr=3.3529e-04) (hash(x)=158344511)
|
| 653 |
+
5410 train 4.028800 (lr=3.3398e-04) (hash(x)=149681960)
|
| 654 |
+
5420 train 4.079967 (lr=3.3267e-04) (hash(x)=143459968)
|
| 655 |
+
5430 train 3.996368 (lr=3.3136e-04) (hash(x)=134759020)
|
| 656 |
+
5440 train 3.970869 (lr=3.3006e-04) (hash(x)=164760471)
|
| 657 |
+
5450 train 4.027930 (lr=3.2875e-04) (hash(x)=148551310)
|
| 658 |
+
5460 train 4.165794 (lr=3.2745e-04) (hash(x)=155464239)
|
| 659 |
+
5470 train 3.976872 (lr=3.2615e-04) (hash(x)=147309485)
|
| 660 |
+
5480 train 3.932474 (lr=3.2485e-04) (hash(x)=163937590)
|
| 661 |
+
5490 train 4.215070 (lr=3.2355e-04) (hash(x)=142830147)
|
| 662 |
+
5500 val loss 4.1447
|
| 663 |
+
5500 val perplexity 63.1018
|
| 664 |
+
5500 train 4.041501 (lr=3.2226e-04) (hash(x)=148350057)
|
| 665 |
+
5510 train 4.018369 (lr=3.2096e-04) (hash(x)=149007838)
|
| 666 |
+
5520 train 3.987614 (lr=3.1967e-04) (hash(x)=158176239)
|
| 667 |
+
5530 train 4.085081 (lr=3.1838e-04) (hash(x)=156395740)
|
| 668 |
+
5540 train 4.269013 (lr=3.1709e-04) (hash(x)=152453211)
|
| 669 |
+
5550 train 3.966241 (lr=3.1580e-04) (hash(x)=144447218)
|
| 670 |
+
5560 train 4.153876 (lr=3.1451e-04) (hash(x)=153858804)
|
| 671 |
+
5570 train 3.975330 (lr=3.1323e-04) (hash(x)=133929681)
|
| 672 |
+
5580 train 4.230175 (lr=3.1195e-04) (hash(x)=159170988)
|
| 673 |
+
5590 train 4.166400 (lr=3.1067e-04) (hash(x)=144978886)
|
| 674 |
+
5600 val loss 4.1395
|
| 675 |
+
5600 val perplexity 62.7716
|
| 676 |
+
5600 train 4.180494 (lr=3.0939e-04) (hash(x)=153847323)
|
| 677 |
+
5610 train 4.129622 (lr=3.0811e-04) (hash(x)=145553636)
|
| 678 |
+
5620 train 5.283006 (lr=3.0684e-04) (hash(x)=153712417)
|
| 679 |
+
5630 train 4.160687 (lr=3.0557e-04) (hash(x)=148397520)
|
| 680 |
+
5640 train 4.106377 (lr=3.0429e-04) (hash(x)=149424351)
|
| 681 |
+
5650 train 4.192017 (lr=3.0303e-04) (hash(x)=140531069)
|
| 682 |
+
5660 train 4.134145 (lr=3.0176e-04) (hash(x)=144904009)
|
| 683 |
+
5670 train 3.978693 (lr=3.0049e-04) (hash(x)=162469666)
|
| 684 |
+
5680 train 4.111402 (lr=2.9923e-04) (hash(x)=149254569)
|
| 685 |
+
5690 train 4.030644 (lr=2.9797e-04) (hash(x)=146949494)
|
| 686 |
+
5700 val loss 4.1318
|
| 687 |
+
5700 val perplexity 62.2899
|
| 688 |
+
5700 train 4.090963 (lr=2.9671e-04) (hash(x)=156607405)
|
| 689 |
+
5710 train 3.940398 (lr=2.9546e-04) (hash(x)=146349425)
|
| 690 |
+
5720 train 4.115198 (lr=2.9420e-04) (hash(x)=160347239)
|
| 691 |
+
5730 train 4.043807 (lr=2.9295e-04) (hash(x)=153785045)
|
| 692 |
+
5740 train 4.048010 (lr=2.9170e-04) (hash(x)=135967367)
|
| 693 |
+
5750 train 4.020603 (lr=2.9045e-04) (hash(x)=140181987)
|
| 694 |
+
5760 train 4.170301 (lr=2.8920e-04) (hash(x)=153217075)
|
| 695 |
+
5770 train 4.040683 (lr=2.8796e-04) (hash(x)=146360100)
|
| 696 |
+
5780 train 4.062373 (lr=2.8672e-04) (hash(x)=161111351)
|
| 697 |
+
5790 train 3.995572 (lr=2.8548e-04) (hash(x)=147891055)
|
| 698 |
+
5800 val loss 4.1293
|
| 699 |
+
5800 val perplexity 62.1330
|
| 700 |
+
5800 train 3.867943 (lr=2.8424e-04) (hash(x)=145115031)
|
| 701 |
+
5810 train 3.911765 (lr=2.8301e-04) (hash(x)=153661465)
|
| 702 |
+
5820 train 4.009286 (lr=2.8178e-04) (hash(x)=148264581)
|
| 703 |
+
5830 train 4.105780 (lr=2.8055e-04) (hash(x)=171144748)
|
| 704 |
+
5840 train 4.037564 (lr=2.7932e-04) (hash(x)=157863238)
|
| 705 |
+
5850 train 3.976783 (lr=2.7809e-04) (hash(x)=144669655)
|
| 706 |
+
5860 train 3.887782 (lr=2.7687e-04) (hash(x)=154948909)
|
| 707 |
+
5870 train 4.053301 (lr=2.7565e-04) (hash(x)=158981837)
|
| 708 |
+
5880 train 4.102110 (lr=2.7443e-04) (hash(x)=151102851)
|
| 709 |
+
5890 train 4.291588 (lr=2.7321e-04) (hash(x)=153490628)
|
| 710 |
+
5900 val loss 4.1200
|
| 711 |
+
5900 val perplexity 61.5616
|
| 712 |
+
5900 train 4.085109 (lr=2.7200e-04) (hash(x)=141584622)
|
| 713 |
+
5910 train 3.965896 (lr=2.7079e-04) (hash(x)=142896324)
|
| 714 |
+
5920 train 4.256884 (lr=2.6958e-04) (hash(x)=148264764)
|
| 715 |
+
5930 train 4.115695 (lr=2.6837e-04) (hash(x)=153157848)
|
| 716 |
+
5940 train 4.092025 (lr=2.6717e-04) (hash(x)=151086429)
|
| 717 |
+
5950 train 4.073498 (lr=2.6597e-04) (hash(x)=146009598)
|
| 718 |
+
5960 train 4.175600 (lr=2.6477e-04) (hash(x)=149488374)
|
| 719 |
+
5970 train 4.019866 (lr=2.6357e-04) (hash(x)=149307478)
|
| 720 |
+
5980 train 3.781977 (lr=2.6238e-04) (hash(x)=156742339)
|
| 721 |
+
5990 train 4.043467 (lr=2.6119e-04) (hash(x)=164296391)
|
| 722 |
+
6000 val loss 4.1115
|
| 723 |
+
6000 val perplexity 61.0411
|
| 724 |
+
6000 train 4.145084 (lr=2.6000e-04) (hash(x)=146613857)
|
| 725 |
+
6010 train 4.018159 (lr=2.5881e-04) (hash(x)=149742104)
|
| 726 |
+
6020 train 3.962527 (lr=2.5763e-04) (hash(x)=145645994)
|
| 727 |
+
6030 train 4.046016 (lr=2.5645e-04) (hash(x)=156324150)
|
| 728 |
+
6040 train 4.222361 (lr=2.5527e-04) (hash(x)=154655300)
|
| 729 |
+
6050 train 4.085439 (lr=2.5410e-04) (hash(x)=153714860)
|
| 730 |
+
6060 train 4.041783 (lr=2.5292e-04) (hash(x)=139981556)
|
| 731 |
+
6070 train 3.864680 (lr=2.5175e-04) (hash(x)=158753458)
|
| 732 |
+
6080 train 4.033009 (lr=2.5059e-04) (hash(x)=152559930)
|
| 733 |
+
6090 train 4.000428 (lr=2.4942e-04) (hash(x)=137128715)
|
| 734 |
+
6100 val loss 4.1123
|
| 735 |
+
6100 val perplexity 61.0880
|
| 736 |
+
6100 train 4.019367 (lr=2.4826e-04) (hash(x)=144621768)
|
| 737 |
+
6110 train 4.023533 (lr=2.4710e-04) (hash(x)=155614333)
|
| 738 |
+
6120 train 4.006380 (lr=2.4595e-04) (hash(x)=145682343)
|
| 739 |
+
6130 train 3.914570 (lr=2.4479e-04) (hash(x)=142909600)
|
| 740 |
+
6140 train 3.943367 (lr=2.4364e-04) (hash(x)=152993494)
|
| 741 |
+
6150 train 3.831490 (lr=2.4250e-04) (hash(x)=157151527)
|
| 742 |
+
6160 train 3.979619 (lr=2.4135e-04) (hash(x)=150653611)
|
| 743 |
+
6170 train 4.241260 (lr=2.4021e-04) (hash(x)=165237934)
|
| 744 |
+
6180 train 4.084354 (lr=2.3907e-04) (hash(x)=155730197)
|
| 745 |
+
6190 train 4.098281 (lr=2.3793e-04) (hash(x)=149687169)
|
| 746 |
+
6200 val loss 4.1127
|
| 747 |
+
6200 val perplexity 61.1091
|
| 748 |
+
6200 train 4.095367 (lr=2.3680e-04) (hash(x)=146521760)
|
| 749 |
+
6210 train 4.108415 (lr=2.3567e-04) (hash(x)=141008090)
|
| 750 |
+
6220 train 4.062373 (lr=2.3454e-04) (hash(x)=143407095)
|
| 751 |
+
6230 train 4.196450 (lr=2.3342e-04) (hash(x)=152947604)
|
| 752 |
+
6240 train 4.505361 (lr=2.3230e-04) (hash(x)=153876740)
|
| 753 |
+
6250 train 4.151809 (lr=2.3118e-04) (hash(x)=144250615)
|
| 754 |
+
6260 train 4.140716 (lr=2.3006e-04) (hash(x)=155236959)
|
| 755 |
+
6270 train 4.118550 (lr=2.2895e-04) (hash(x)=139785369)
|
| 756 |
+
6280 train 4.034225 (lr=2.2784e-04) (hash(x)=165036565)
|
| 757 |
+
6290 train 4.068254 (lr=2.2674e-04) (hash(x)=144585028)
|
| 758 |
+
6300 val loss 4.0962
|
| 759 |
+
6300 val perplexity 60.1101
|
| 760 |
+
6300 train 3.925282 (lr=2.2563e-04) (hash(x)=161378136)
|
| 761 |
+
6310 train 3.975079 (lr=2.2453e-04) (hash(x)=148483421)
|
| 762 |
+
6320 train 4.015523 (lr=2.2344e-04) (hash(x)=149835040)
|
| 763 |
+
6330 train 3.933032 (lr=2.2234e-04) (hash(x)=149459414)
|
| 764 |
+
6340 train 3.966676 (lr=2.2125e-04) (hash(x)=154290067)
|
| 765 |
+
6350 train 4.060078 (lr=2.2017e-04) (hash(x)=147407391)
|
| 766 |
+
6360 train 3.994248 (lr=2.1908e-04) (hash(x)=146317149)
|
| 767 |
+
6370 train 3.898934 (lr=2.1800e-04) (hash(x)=141970628)
|
| 768 |
+
6380 train 3.933867 (lr=2.1692e-04) (hash(x)=139170535)
|
| 769 |
+
6390 train 4.129155 (lr=2.1585e-04) (hash(x)=148905963)
|
| 770 |
+
6400 val loss 4.0970
|
| 771 |
+
6400 val perplexity 60.1566
|
| 772 |
+
6400 train 3.924435 (lr=2.1478e-04) (hash(x)=141624235)
|
| 773 |
+
6410 train 3.926183 (lr=2.1371e-04) (hash(x)=150520968)
|
| 774 |
+
6420 train 3.817674 (lr=2.1265e-04) (hash(x)=155019129)
|
| 775 |
+
6430 train 3.879323 (lr=2.1159e-04) (hash(x)=150031836)
|
| 776 |
+
6440 train 3.837521 (lr=2.1053e-04) (hash(x)=112835661)
|
| 777 |
+
6450 train 3.843982 (lr=2.0947e-04) (hash(x)=141072709)
|
| 778 |
+
6460 train 3.982452 (lr=2.0842e-04) (hash(x)=153933796)
|
| 779 |
+
6470 train 4.041571 (lr=2.0737e-04) (hash(x)=153315715)
|
| 780 |
+
6480 train 4.108235 (lr=2.0633e-04) (hash(x)=158089228)
|
| 781 |
+
6490 train 3.965218 (lr=2.0529e-04) (hash(x)=149471788)
|
| 782 |
+
6500 val loss 4.0934
|
| 783 |
+
6500 val perplexity 59.9419
|
| 784 |
+
6500 train 4.100058 (lr=2.0425e-04) (hash(x)=151197095)
|
| 785 |
+
6510 train 4.049337 (lr=2.0322e-04) (hash(x)=165554266)
|
| 786 |
+
6520 train 4.220020 (lr=2.0218e-04) (hash(x)=157822242)
|
| 787 |
+
6530 train 4.153152 (lr=2.0116e-04) (hash(x)=156267861)
|
| 788 |
+
6540 train 4.063520 (lr=2.0013e-04) (hash(x)=145825803)
|
| 789 |
+
6550 train 4.144500 (lr=1.9911e-04) (hash(x)=151303683)
|
| 790 |
+
6560 train 4.201071 (lr=1.9810e-04) (hash(x)=150786942)
|
| 791 |
+
6570 train 4.016315 (lr=1.9708e-04) (hash(x)=146237093)
|
| 792 |
+
6580 train 3.989436 (lr=1.9607e-04) (hash(x)=147063866)
|
| 793 |
+
6590 train 4.218430 (lr=1.9507e-04) (hash(x)=130513396)
|
| 794 |
+
6600 val loss 4.0895
|
| 795 |
+
6600 val perplexity 59.7122
|
| 796 |
+
6600 train 4.109011 (lr=1.9406e-04) (hash(x)=153269571)
|
| 797 |
+
6610 train 4.177717 (lr=1.9306e-04) (hash(x)=150340530)
|
| 798 |
+
6620 train 4.066791 (lr=1.9207e-04) (hash(x)=153843616)
|
| 799 |
+
6630 train 4.131222 (lr=1.9108e-04) (hash(x)=144540858)
|
| 800 |
+
6640 train 3.927896 (lr=1.9009e-04) (hash(x)=153330434)
|
| 801 |
+
6650 train 3.938975 (lr=1.8910e-04) (hash(x)=146851492)
|
| 802 |
+
6660 train 3.961146 (lr=1.8812e-04) (hash(x)=153601788)
|
| 803 |
+
6670 train 3.995249 (lr=1.8714e-04) (hash(x)=140005742)
|
| 804 |
+
6680 train 3.858025 (lr=1.8617e-04) (hash(x)=154102392)
|
| 805 |
+
6690 train 3.862147 (lr=1.8520e-04) (hash(x)=152774975)
|
| 806 |
+
6700 val loss 4.0877
|
| 807 |
+
6700 val perplexity 59.6009
|
| 808 |
+
6700 train 4.065046 (lr=1.8423e-04) (hash(x)=146111181)
|
| 809 |
+
6710 train 4.014231 (lr=1.8327e-04) (hash(x)=143988017)
|
| 810 |
+
6720 train 4.001183 (lr=1.8231e-04) (hash(x)=146073959)
|
| 811 |
+
6730 train 4.255454 (lr=1.8136e-04) (hash(x)=152642956)
|
| 812 |
+
6740 train 4.142077 (lr=1.8040e-04) (hash(x)=146964363)
|
| 813 |
+
6750 train 3.936705 (lr=1.7946e-04) (hash(x)=162251871)
|
| 814 |
+
6760 train 4.288689 (lr=1.7851e-04) (hash(x)=171122166)
|
| 815 |
+
6770 train 4.061587 (lr=1.7757e-04) (hash(x)=135199617)
|
| 816 |
+
6780 train 4.032383 (lr=1.7663e-04) (hash(x)=160480410)
|
| 817 |
+
6790 train 4.180742 (lr=1.7570e-04) (hash(x)=151933948)
|
| 818 |
+
6800 val loss 4.0727
|
| 819 |
+
6800 val perplexity 58.7151
|
| 820 |
+
6800 train 4.071478 (lr=1.7477e-04) (hash(x)=147269760)
|
| 821 |
+
6810 train 4.142908 (lr=1.7385e-04) (hash(x)=156710316)
|
| 822 |
+
6820 train 4.167407 (lr=1.7293e-04) (hash(x)=157300754)
|
| 823 |
+
6830 train 3.968544 (lr=1.7201e-04) (hash(x)=133838057)
|
| 824 |
+
6840 train 4.165523 (lr=1.7110e-04) (hash(x)=143518263)
|
| 825 |
+
6850 train 4.232651 (lr=1.7019e-04) (hash(x)=160328446)
|
| 826 |
+
6860 train 4.067945 (lr=1.6928e-04) (hash(x)=142143427)
|
| 827 |
+
6870 train 4.127422 (lr=1.6838e-04) (hash(x)=149045075)
|
| 828 |
+
6880 train 4.037887 (lr=1.6748e-04) (hash(x)=150708270)
|
| 829 |
+
6890 train 4.039498 (lr=1.6659e-04) (hash(x)=153066841)
|
| 830 |
+
6900 val loss 4.0709
|
| 831 |
+
6900 val perplexity 58.6113
|
| 832 |
+
6900 train 4.150796 (lr=1.6570e-04) (hash(x)=152912762)
|
| 833 |
+
6910 train 3.991377 (lr=1.6481e-04) (hash(x)=148346240)
|
| 834 |
+
6920 train 4.112321 (lr=1.6393e-04) (hash(x)=152806752)
|
| 835 |
+
6930 train 4.095747 (lr=1.6305e-04) (hash(x)=161831829)
|
| 836 |
+
6940 train 4.010226 (lr=1.6218e-04) (hash(x)=149483673)
|
| 837 |
+
6950 train 3.990258 (lr=1.6131e-04) (hash(x)=119634555)
|
| 838 |
+
6960 train 3.909781 (lr=1.6044e-04) (hash(x)=144709540)
|
| 839 |
+
6970 train 3.941809 (lr=1.5958e-04) (hash(x)=141277017)
|
| 840 |
+
6980 train 3.994755 (lr=1.5872e-04) (hash(x)=140618792)
|
| 841 |
+
6990 train 3.973725 (lr=1.5787e-04) (hash(x)=157443505)
|
| 842 |
+
7000 val loss 4.0699
|
| 843 |
+
7000 val perplexity 58.5540
|
| 844 |
+
7000 train 4.211453 (lr=1.5702e-04) (hash(x)=165412343)
|
| 845 |
+
7010 train 3.857019 (lr=1.5618e-04) (hash(x)=140746035)
|
| 846 |
+
7020 train 3.902428 (lr=1.5533e-04) (hash(x)=141101046)
|
| 847 |
+
7030 train 4.042645 (lr=1.5450e-04) (hash(x)=152098342)
|
| 848 |
+
7040 train 3.900831 (lr=1.5366e-04) (hash(x)=169244968)
|
| 849 |
+
7050 train 4.025446 (lr=1.5284e-04) (hash(x)=149886680)
|
| 850 |
+
7060 train 4.192437 (lr=1.5201e-04) (hash(x)=144670487)
|
| 851 |
+
7070 train 4.215551 (lr=1.5119e-04) (hash(x)=148774474)
|
| 852 |
+
7080 train 4.048332 (lr=1.5037e-04) (hash(x)=155096286)
|
| 853 |
+
7090 train 4.019391 (lr=1.4956e-04) (hash(x)=145048246)
|
| 854 |
+
7100 val loss 4.0556
|
| 855 |
+
7100 val perplexity 57.7220
|
| 856 |
+
7100 train 4.162021 (lr=1.4875e-04) (hash(x)=162866028)
|
| 857 |
+
7110 train 4.033250 (lr=1.4795e-04) (hash(x)=162308558)
|
| 858 |
+
7120 train 3.996074 (lr=1.4715e-04) (hash(x)=153468309)
|
| 859 |
+
7130 train 4.026896 (lr=1.4636e-04) (hash(x)=144522880)
|
| 860 |
+
7140 train 4.171306 (lr=1.4556e-04) (hash(x)=153055749)
|
| 861 |
+
7150 train 3.984723 (lr=1.4478e-04) (hash(x)=171163513)
|
| 862 |
+
7160 train 4.063915 (lr=1.4400e-04) (hash(x)=138563864)
|
| 863 |
+
7170 train 4.198422 (lr=1.4322e-04) (hash(x)=166996657)
|
| 864 |
+
7180 train 3.894148 (lr=1.4244e-04) (hash(x)=154809376)
|
| 865 |
+
7190 train 3.980723 (lr=1.4167e-04) (hash(x)=147988525)
|
| 866 |
+
7200 val loss 4.0552
|
| 867 |
+
7200 val perplexity 57.6953
|
| 868 |
+
7200 train 4.023038 (lr=1.4091e-04) (hash(x)=142998115)
|
| 869 |
+
7210 train 4.007470 (lr=1.4015e-04) (hash(x)=145518575)
|
| 870 |
+
7220 train 4.037627 (lr=1.3939e-04) (hash(x)=145758781)
|
| 871 |
+
7230 train 4.144683 (lr=1.3864e-04) (hash(x)=148909637)
|
| 872 |
+
7240 train 4.000212 (lr=1.3789e-04) (hash(x)=144422691)
|
| 873 |
+
7250 train 3.846135 (lr=1.3715e-04) (hash(x)=140396153)
|
| 874 |
+
7260 train 4.084816 (lr=1.3641e-04) (hash(x)=153619124)
|
| 875 |
+
7270 train 3.990026 (lr=1.3568e-04) (hash(x)=161980521)
|
| 876 |
+
7280 train 3.819988 (lr=1.3495e-04) (hash(x)=135160527)
|
| 877 |
+
7290 train 3.953932 (lr=1.3422e-04) (hash(x)=167156181)
|
| 878 |
+
7300 val loss 4.0550
|
| 879 |
+
7300 val perplexity 57.6829
|
| 880 |
+
7300 train 3.889663 (lr=1.3350e-04) (hash(x)=145486999)
|
| 881 |
+
7310 train 3.960577 (lr=1.3278e-04) (hash(x)=155013351)
|
| 882 |
+
7320 train 4.004139 (lr=1.3207e-04) (hash(x)=169616991)
|
| 883 |
+
7330 train 3.890252 (lr=1.3136e-04) (hash(x)=146516856)
|
| 884 |
+
7340 train 4.210858 (lr=1.3066e-04) (hash(x)=171918417)
|
| 885 |
+
7350 train 4.222839 (lr=1.2996e-04) (hash(x)=160511891)
|
| 886 |
+
7360 train 4.070906 (lr=1.2926e-04) (hash(x)=150280167)
|
| 887 |
+
7370 train 4.147654 (lr=1.2857e-04) (hash(x)=151373787)
|
| 888 |
+
7380 train 4.246967 (lr=1.2789e-04) (hash(x)=163311616)
|
| 889 |
+
7390 train 4.233782 (lr=1.2721e-04) (hash(x)=164418521)
|
| 890 |
+
7400 val loss 4.0432
|
| 891 |
+
7400 val perplexity 57.0093
|
| 892 |
+
7400 train 3.998075 (lr=1.2653e-04) (hash(x)=155325873)
|
| 893 |
+
7410 train 4.055531 (lr=1.2586e-04) (hash(x)=135020608)
|
| 894 |
+
7420 train 3.943713 (lr=1.2519e-04) (hash(x)=142812793)
|
| 895 |
+
7430 train 4.056371 (lr=1.2453e-04) (hash(x)=149463283)
|
| 896 |
+
7440 train 4.016263 (lr=1.2387e-04) (hash(x)=170512352)
|
| 897 |
+
7450 train 3.993564 (lr=1.2322e-04) (hash(x)=146253806)
|
| 898 |
+
7460 train 4.654219 (lr=1.2257e-04) (hash(x)=133479853)
|
| 899 |
+
7470 train 4.002298 (lr=1.2192e-04) (hash(x)=138198949)
|
| 900 |
+
7480 train 3.980343 (lr=1.2128e-04) (hash(x)=143831431)
|
| 901 |
+
7490 train 4.143089 (lr=1.2065e-04) (hash(x)=148147144)
|
| 902 |
+
7500 val loss 4.0429
|
| 903 |
+
7500 val perplexity 56.9901
|
| 904 |
+
7500 train 4.045605 (lr=1.2002e-04) (hash(x)=145131256)
|
| 905 |
+
7510 train 4.081214 (lr=1.1939e-04) (hash(x)=150932291)
|
| 906 |
+
7520 train 4.041511 (lr=1.1877e-04) (hash(x)=147605934)
|
| 907 |
+
7530 train 3.996105 (lr=1.1816e-04) (hash(x)=154343507)
|
| 908 |
+
7540 train 4.132847 (lr=1.1754e-04) (hash(x)=148440064)
|
| 909 |
+
7550 train 3.938812 (lr=1.1694e-04) (hash(x)=140505990)
|
| 910 |
+
7560 train 3.922266 (lr=1.1633e-04) (hash(x)=177438878)
|
| 911 |
+
7570 train 4.001867 (lr=1.1574e-04) (hash(x)=154527960)
|
| 912 |
+
7580 train 4.090985 (lr=1.1514e-04) (hash(x)=153793091)
|
| 913 |
+
7590 train 3.910792 (lr=1.1455e-04) (hash(x)=163097232)
|
| 914 |
+
7600 val loss 4.0522
|
| 915 |
+
7600 val perplexity 57.5267
|
| 916 |
+
7600 train 4.042652 (lr=1.1397e-04) (hash(x)=144008365)
|
| 917 |
+
7610 train 4.032667 (lr=1.1339e-04) (hash(x)=139649886)
|
| 918 |
+
7620 train 3.979476 (lr=1.1282e-04) (hash(x)=145452123)
|
| 919 |
+
7630 train 3.996011 (lr=1.1225e-04) (hash(x)=132477285)
|
| 920 |
+
7640 train 3.912077 (lr=1.1168e-04) (hash(x)=139030720)
|
| 921 |
+
7650 train 4.040545 (lr=1.1112e-04) (hash(x)=157466085)
|
| 922 |
+
7660 train 4.055116 (lr=1.1057e-04) (hash(x)=153638385)
|
| 923 |
+
7670 train 4.101335 (lr=1.1002e-04) (hash(x)=154823094)
|
| 924 |
+
7680 train 4.008807 (lr=1.0947e-04) (hash(x)=153107930)
|
| 925 |
+
7690 train 3.999007 (lr=1.0893e-04) (hash(x)=153681916)
|
| 926 |
+
7700 val loss 4.0351
|
| 927 |
+
7700 val perplexity 56.5501
|
| 928 |
+
7700 train 4.314200 (lr=1.0840e-04) (hash(x)=148848532)
|
| 929 |
+
7710 train 4.039814 (lr=1.0786e-04) (hash(x)=156640791)
|
| 930 |
+
7720 train 4.270339 (lr=1.0734e-04) (hash(x)=152573035)
|
| 931 |
+
7730 train 4.111857 (lr=1.0682e-04) (hash(x)=147536091)
|
| 932 |
+
7740 train 4.281199 (lr=1.0630e-04) (hash(x)=175687483)
|
| 933 |
+
7750 train 4.021767 (lr=1.0579e-04) (hash(x)=143775898)
|
| 934 |
+
7760 train 4.044106 (lr=1.0528e-04) (hash(x)=146986193)
|
| 935 |
+
7770 train 3.960701 (lr=1.0478e-04) (hash(x)=160924293)
|
| 936 |
+
7780 train 4.009738 (lr=1.0428e-04) (hash(x)=132579169)
|
| 937 |
+
7790 train 4.225746 (lr=1.0379e-04) (hash(x)=147474225)
|
| 938 |
+
7800 val loss 4.0338
|
| 939 |
+
7800 val perplexity 56.4751
|
| 940 |
+
7800 train 4.070296 (lr=1.0330e-04) (hash(x)=150391642)
|
| 941 |
+
7810 train 4.240418 (lr=1.0282e-04) (hash(x)=156984481)
|
| 942 |
+
7820 train 3.954861 (lr=1.0234e-04) (hash(x)=139652488)
|
| 943 |
+
7830 train 3.973538 (lr=1.0187e-04) (hash(x)=169033643)
|
| 944 |
+
7840 train 3.948540 (lr=1.0140e-04) (hash(x)=152645857)
|
| 945 |
+
7850 train 4.096553 (lr=1.0094e-04) (hash(x)=150228075)
|
| 946 |
+
7860 train 4.015212 (lr=1.0048e-04) (hash(x)=178788133)
|
| 947 |
+
7870 train 4.004895 (lr=1.0002e-04) (hash(x)=149891068)
|
| 948 |
+
7880 train 3.945235 (lr=9.9576e-05) (hash(x)=157461488)
|
| 949 |
+
7890 train 3.909171 (lr=9.9133e-05) (hash(x)=142502446)
|
| 950 |
+
7900 val loss 4.0353
|
| 951 |
+
7900 val perplexity 56.5587
|
| 952 |
+
7900 train 3.841818 (lr=9.8694e-05) (hash(x)=152191414)
|
| 953 |
+
7910 train 4.029228 (lr=9.8261e-05) (hash(x)=151329539)
|
| 954 |
+
7920 train 3.905884 (lr=9.7832e-05) (hash(x)=134143115)
|
| 955 |
+
7930 train 3.911115 (lr=9.7408e-05) (hash(x)=155536160)
|
| 956 |
+
7940 train 3.972835 (lr=9.6990e-05) (hash(x)=146709034)
|
| 957 |
+
7950 train 4.055519 (lr=9.6576e-05) (hash(x)=141966330)
|
| 958 |
+
7960 train 4.027141 (lr=9.6167e-05) (hash(x)=152102296)
|
| 959 |
+
7970 train 4.198737 (lr=9.5764e-05) (hash(x)=150272684)
|
| 960 |
+
7980 train 4.170050 (lr=9.5365e-05) (hash(x)=150251784)
|
| 961 |
+
7990 train 4.157490 (lr=9.4971e-05) (hash(x)=151226159)
|
| 962 |
+
8000 val loss 4.0288
|
| 963 |
+
8000 val perplexity 56.1923
|
| 964 |
+
8000 train 4.056860 (lr=9.4583e-05) (hash(x)=159755587)
|
| 965 |
+
8010 train 4.059852 (lr=9.4199e-05) (hash(x)=137607202)
|
| 966 |
+
8020 train 4.054667 (lr=9.3820e-05) (hash(x)=149574886)
|
| 967 |
+
8030 train 3.968499 (lr=9.3446e-05) (hash(x)=151690927)
|
| 968 |
+
8040 train 3.989096 (lr=9.3078e-05) (hash(x)=151181288)
|
| 969 |
+
8050 train 4.102449 (lr=9.2714e-05) (hash(x)=150465993)
|
| 970 |
+
8060 train 4.126997 (lr=9.2356e-05) (hash(x)=134201020)
|
| 971 |
+
8070 train 4.016723 (lr=9.2002e-05) (hash(x)=157696045)
|
| 972 |
+
8080 train 4.022478 (lr=9.1654e-05) (hash(x)=135581816)
|
| 973 |
+
8090 train 3.951553 (lr=9.1310e-05) (hash(x)=153898278)
|
| 974 |
+
8100 val loss 4.0254
|
| 975 |
+
8100 val perplexity 56.0010
|
| 976 |
+
8100 train 4.071581 (lr=9.0972e-05) (hash(x)=156664468)
|
| 977 |
+
8110 train 4.173835 (lr=9.0638e-05) (hash(x)=161572593)
|
| 978 |
+
8120 train 3.923417 (lr=9.0310e-05) (hash(x)=154381651)
|
| 979 |
+
8130 train 4.184300 (lr=8.9987e-05) (hash(x)=149810514)
|
| 980 |
+
8140 train 4.037950 (lr=8.9669e-05) (hash(x)=145085369)
|
| 981 |
+
8150 train 3.896777 (lr=8.9356e-05) (hash(x)=149020616)
|
| 982 |
+
8160 train 3.779180 (lr=8.9048e-05) (hash(x)=146450644)
|
| 983 |
+
8170 train 3.979685 (lr=8.8745e-05) (hash(x)=148094499)
|
| 984 |
+
8180 train 3.846212 (lr=8.8447e-05) (hash(x)=140810897)
|
| 985 |
+
8190 train 3.955846 (lr=8.8154e-05) (hash(x)=142960309)
|
| 986 |
+
8200 val loss 4.0263
|
| 987 |
+
8200 val perplexity 56.0558
|
| 988 |
+
8200 train 3.989845 (lr=8.7867e-05) (hash(x)=139457379)
|
| 989 |
+
8210 train 3.969254 (lr=8.7584e-05) (hash(x)=145575125)
|
| 990 |
+
8220 train 3.766742 (lr=8.7307e-05) (hash(x)=152836922)
|
| 991 |
+
8230 train 3.852656 (lr=8.7035e-05) (hash(x)=135086706)
|
| 992 |
+
8240 train 3.822788 (lr=8.6768e-05) (hash(x)=153448613)
|
| 993 |
+
8250 train 3.786960 (lr=8.6506e-05) (hash(x)=138041222)
|
| 994 |
+
8260 train 3.844816 (lr=8.6249e-05) (hash(x)=158857968)
|
| 995 |
+
8270 train 3.861579 (lr=8.5997e-05) (hash(x)=157265315)
|
| 996 |
+
8280 train 3.699619 (lr=8.5750e-05) (hash(x)=136059191)
|
| 997 |
+
8290 train 3.771731 (lr=8.5509e-05) (hash(x)=162526712)
|
| 998 |
+
8300 val loss 4.0331
|
| 999 |
+
8300 val perplexity 56.4341
|
| 1000 |
+
8300 train 3.853588 (lr=8.5273e-05) (hash(x)=145478564)
|
| 1001 |
+
8310 train 3.498652 (lr=8.5041e-05) (hash(x)=157367549)
|
| 1002 |
+
8320 train 3.892195 (lr=8.4815e-05) (hash(x)=156085849)
|
| 1003 |
+
8330 train 4.177628 (lr=8.4594e-05) (hash(x)=154822719)
|
| 1004 |
+
8340 train 3.892810 (lr=8.4379e-05) (hash(x)=159688342)
|
| 1005 |
+
8350 train 4.026961 (lr=8.4168e-05) (hash(x)=144133822)
|
| 1006 |
+
8360 train 3.965671 (lr=8.3963e-05) (hash(x)=154155471)
|
| 1007 |
+
8370 train 3.969778 (lr=8.3762e-05) (hash(x)=157077804)
|
| 1008 |
+
8380 train 3.977879 (lr=8.3567e-05) (hash(x)=147796790)
|
| 1009 |
+
8390 train 3.983309 (lr=8.3377e-05) (hash(x)=145208254)
|
| 1010 |
+
8400 val loss 4.0212
|
| 1011 |
+
8400 val perplexity 55.7665
|
| 1012 |
+
8400 train 3.936470 (lr=8.3193e-05) (hash(x)=154982769)
|
| 1013 |
+
8410 train 4.127687 (lr=8.3013e-05) (hash(x)=138073867)
|
| 1014 |
+
8420 train 4.170509 (lr=8.2839e-05) (hash(x)=159521725)
|
| 1015 |
+
8430 train 4.096187 (lr=8.2669e-05) (hash(x)=149988578)
|
| 1016 |
+
8440 train 4.064534 (lr=8.2505e-05) (hash(x)=149457063)
|
| 1017 |
+
8450 train 3.931552 (lr=8.2347e-05) (hash(x)=134678896)
|
| 1018 |
+
8460 train 3.979403 (lr=8.2193e-05) (hash(x)=146122249)
|
| 1019 |
+
8470 train 4.000155 (lr=8.2044e-05) (hash(x)=141393319)
|
| 1020 |
+
8480 train 4.029669 (lr=8.1901e-05) (hash(x)=165396836)
|
| 1021 |
+
8490 train 4.098529 (lr=8.1763e-05) (hash(x)=140043806)
|
| 1022 |
+
8500 val loss 4.0175
|
| 1023 |
+
8500 val perplexity 55.5628
|
| 1024 |
+
8500 train 4.053110 (lr=8.1630e-05) (hash(x)=145798118)
|
| 1025 |
+
8510 train 4.001561 (lr=8.1502e-05) (hash(x)=150358299)
|
| 1026 |
+
8520 train 3.894746 (lr=8.1380e-05) (hash(x)=152572913)
|
| 1027 |
+
8530 train 3.967403 (lr=8.1263e-05) (hash(x)=148669229)
|
| 1028 |
+
8540 train 3.993587 (lr=8.1150e-05) (hash(x)=147078347)
|
| 1029 |
+
8550 train 3.978547 (lr=8.1044e-05) (hash(x)=146715166)
|
| 1030 |
+
8560 train 3.950264 (lr=8.0942e-05) (hash(x)=143176392)
|
| 1031 |
+
8570 train 4.067235 (lr=8.0845e-05) (hash(x)=153825484)
|
| 1032 |
+
8580 train 4.096317 (lr=8.0754e-05) (hash(x)=163379045)
|
| 1033 |
+
8590 train 3.885189 (lr=8.0668e-05) (hash(x)=140050873)
|
| 1034 |
+
8600 val loss 4.0200
|
| 1035 |
+
8600 val perplexity 55.7025
|
| 1036 |
+
8600 train 3.957555 (lr=8.0587e-05) (hash(x)=143231551)
|
| 1037 |
+
8610 train 3.812697 (lr=8.0511e-05) (hash(x)=164291360)
|
| 1038 |
+
8620 train 3.844626 (lr=8.0441e-05) (hash(x)=159122123)
|
| 1039 |
+
8630 train 3.817628 (lr=8.0376e-05) (hash(x)=140041695)
|
| 1040 |
+
8640 train 3.849620 (lr=8.0316e-05) (hash(x)=146010790)
|
| 1041 |
+
8650 train 3.763236 (lr=8.0261e-05) (hash(x)=146882123)
|
| 1042 |
+
8660 train 3.575861 (lr=8.0211e-05) (hash(x)=144933705)
|
| 1043 |
+
8670 train 3.803743 (lr=8.0167e-05) (hash(x)=145580075)
|
| 1044 |
+
8680 train 3.850536 (lr=8.0128e-05) (hash(x)=160982926)
|
| 1045 |
+
8690 train 3.727633 (lr=8.0094e-05) (hash(x)=140047108)
|
| 1046 |
+
8700 val loss 4.0299
|
| 1047 |
+
8700 val perplexity 56.2546
|
| 1048 |
+
8700 train 3.854482 (lr=8.0065e-05) (hash(x)=154780112)
|
| 1049 |
+
8710 train 3.940895 (lr=8.0042e-05) (hash(x)=157568560)
|
| 1050 |
+
8720 train 3.983122 (lr=8.0023e-05) (hash(x)=159587459)
|
| 1051 |
+
8730 train 3.986237 (lr=8.0010e-05) (hash(x)=152918103)
|
| 1052 |
+
8740 train 3.984485 (lr=8.0003e-05) (hash(x)=156928586)
|
| 1053 |
+
8749 val loss 4.0185
|
| 1054 |
+
8749 val perplexity 55.6157
|
lr8e-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 sha256:0a0f1619dd8d4621d4f83155177dfe843d66005c298d6eb6c6a08a9de2201267
|
| 3 |
+
size 92843394
|
lr8e-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 sha256:6ca2a073f94983c8a04cf45dec16b670ace74b0893e4ee7e6a2edb9d37e71b14
|
| 3 |
+
size 179406214
|