Upload folder using huggingface_hub
Browse files- lr6e-4_total_batch_size61440_baseline_seed1339/args.json +1 -0
- lr6e-4_total_batch_size61440_baseline_seed1339/dataloader_08749.pt +3 -0
- lr6e-4_total_batch_size61440_baseline_seed1339/log2.txt +1054 -0
- lr6e-4_total_batch_size61440_baseline_seed1339/model_08749.pt +3 -0
- lr6e-4_total_batch_size61440_baseline_seed1339/optimizer_08749.pt +3 -0
lr6e-4_total_batch_size61440_baseline_seed1339/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "wider_is_better_11/lr6e-4_total_batch_size61440_baseline_seed1339", "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": 1339, "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": 0.0006, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "6e-4_61440", "n_embd": 256}
|
lr6e-4_total_batch_size61440_baseline_seed1339/dataloader_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:953385078aa3787b69fc6857dfd48b0a2cd2f4d27c6f8892e01211aca53d07f5
|
| 3 |
+
size 964
|
lr6e-4_total_batch_size61440_baseline_seed1339/log2.txt
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_steps: 8750
|
| 2 |
+
0 val loss 11.2592
|
| 3 |
+
0 val perplexity 77590.4141
|
| 4 |
+
0 train 11.272774 (lr=1.2000e-06) (hash(x)=150724848)
|
| 5 |
+
10 train 10.348531 (lr=1.3200e-05) (hash(x)=149663361)
|
| 6 |
+
20 train 9.881202 (lr=2.5200e-05) (hash(x)=153483789)
|
| 7 |
+
30 train 9.705391 (lr=3.7200e-05) (hash(x)=145733176)
|
| 8 |
+
40 train 9.268219 (lr=4.9200e-05) (hash(x)=145287265)
|
| 9 |
+
50 train 8.903151 (lr=6.1200e-05) (hash(x)=149217061)
|
| 10 |
+
60 train 8.471861 (lr=7.3200e-05) (hash(x)=150157569)
|
| 11 |
+
70 train 8.082783 (lr=8.5200e-05) (hash(x)=140292841)
|
| 12 |
+
80 train 7.880149 (lr=9.7200e-05) (hash(x)=152157598)
|
| 13 |
+
90 train 7.629221 (lr=1.0920e-04) (hash(x)=149756968)
|
| 14 |
+
100 val loss 7.5905
|
| 15 |
+
100 val perplexity 1979.2290
|
| 16 |
+
100 train 7.560264 (lr=1.2120e-04) (hash(x)=149910534)
|
| 17 |
+
110 train 7.479685 (lr=1.3320e-04) (hash(x)=159020328)
|
| 18 |
+
120 train 7.438631 (lr=1.4520e-04) (hash(x)=150731273)
|
| 19 |
+
130 train 7.267333 (lr=1.5720e-04) (hash(x)=156727355)
|
| 20 |
+
140 train 7.303560 (lr=1.6920e-04) (hash(x)=166473281)
|
| 21 |
+
150 train 6.991832 (lr=1.8120e-04) (hash(x)=142185643)
|
| 22 |
+
160 train 6.989021 (lr=1.9320e-04) (hash(x)=151371145)
|
| 23 |
+
170 train 7.010696 (lr=2.0520e-04) (hash(x)=151601659)
|
| 24 |
+
180 train 6.841847 (lr=2.1720e-04) (hash(x)=153368917)
|
| 25 |
+
190 train 6.697760 (lr=2.2920e-04) (hash(x)=145008196)
|
| 26 |
+
200 val loss 6.8087
|
| 27 |
+
200 val perplexity 905.6707
|
| 28 |
+
200 train 6.711312 (lr=2.4120e-04) (hash(x)=148123706)
|
| 29 |
+
210 train 6.587342 (lr=2.5320e-04) (hash(x)=145714762)
|
| 30 |
+
220 train 6.576862 (lr=2.6520e-04) (hash(x)=150622583)
|
| 31 |
+
230 train 6.375014 (lr=2.7720e-04) (hash(x)=146512648)
|
| 32 |
+
240 train 6.406185 (lr=2.8920e-04) (hash(x)=151535384)
|
| 33 |
+
250 train 6.314778 (lr=3.0120e-04) (hash(x)=149952383)
|
| 34 |
+
260 train 6.231345 (lr=3.1320e-04) (hash(x)=148726088)
|
| 35 |
+
270 train 6.193257 (lr=3.2520e-04) (hash(x)=152776695)
|
| 36 |
+
280 train 6.235998 (lr=3.3720e-04) (hash(x)=157260375)
|
| 37 |
+
290 train 6.272188 (lr=3.4920e-04) (hash(x)=151559106)
|
| 38 |
+
300 val loss 6.3377
|
| 39 |
+
300 val perplexity 565.4866
|
| 40 |
+
300 train 6.081059 (lr=3.6120e-04) (hash(x)=146678221)
|
| 41 |
+
310 train 6.176166 (lr=3.7320e-04) (hash(x)=156713527)
|
| 42 |
+
320 train 6.220588 (lr=3.8520e-04) (hash(x)=144947971)
|
| 43 |
+
330 train 6.391332 (lr=3.9720e-04) (hash(x)=158684944)
|
| 44 |
+
340 train 6.256314 (lr=4.0920e-04) (hash(x)=162318756)
|
| 45 |
+
350 train 6.058861 (lr=4.2120e-04) (hash(x)=156180736)
|
| 46 |
+
360 train 6.249966 (lr=4.3320e-04) (hash(x)=178373797)
|
| 47 |
+
370 train 6.135502 (lr=4.4520e-04) (hash(x)=154389449)
|
| 48 |
+
380 train 5.965200 (lr=4.5720e-04) (hash(x)=150369080)
|
| 49 |
+
390 train 6.098134 (lr=4.6920e-04) (hash(x)=159840654)
|
| 50 |
+
400 val loss 5.9844
|
| 51 |
+
400 val perplexity 397.2034
|
| 52 |
+
400 train 5.886833 (lr=4.8120e-04) (hash(x)=151700982)
|
| 53 |
+
410 train 5.883242 (lr=4.9320e-04) (hash(x)=160467274)
|
| 54 |
+
420 train 5.801489 (lr=5.0520e-04) (hash(x)=148930522)
|
| 55 |
+
430 train 6.008842 (lr=5.1720e-04) (hash(x)=154565303)
|
| 56 |
+
440 train 5.968906 (lr=5.2920e-04) (hash(x)=148079227)
|
| 57 |
+
450 train 5.706450 (lr=5.4120e-04) (hash(x)=147288467)
|
| 58 |
+
460 train 5.724346 (lr=5.5320e-04) (hash(x)=145272617)
|
| 59 |
+
470 train 5.727170 (lr=5.6520e-04) (hash(x)=123126729)
|
| 60 |
+
480 train 5.695118 (lr=5.7720e-04) (hash(x)=156287490)
|
| 61 |
+
490 train 5.821955 (lr=5.8920e-04) (hash(x)=161700145)
|
| 62 |
+
500 val loss 5.7330
|
| 63 |
+
500 val perplexity 308.9048
|
| 64 |
+
500 train 5.843773 (lr=6.0000e-04) (hash(x)=156182087)
|
| 65 |
+
510 train 5.446055 (lr=6.0000e-04) (hash(x)=131674504)
|
| 66 |
+
520 train 5.762048 (lr=5.9999e-04) (hash(x)=162758254)
|
| 67 |
+
530 train 5.569715 (lr=5.9998e-04) (hash(x)=133510409)
|
| 68 |
+
540 train 5.574682 (lr=5.9997e-04) (hash(x)=157363914)
|
| 69 |
+
550 train 5.495609 (lr=5.9995e-04) (hash(x)=147861550)
|
| 70 |
+
560 train 5.445497 (lr=5.9993e-04) (hash(x)=149449280)
|
| 71 |
+
570 train 5.451368 (lr=5.9990e-04) (hash(x)=143899904)
|
| 72 |
+
580 train 5.428978 (lr=5.9987e-04) (hash(x)=149266312)
|
| 73 |
+
590 train 5.653462 (lr=5.9984e-04) (hash(x)=164352774)
|
| 74 |
+
600 val loss 5.5497
|
| 75 |
+
600 val perplexity 257.1707
|
| 76 |
+
600 train 5.425047 (lr=5.9980e-04) (hash(x)=149318660)
|
| 77 |
+
610 train 5.324417 (lr=5.9976e-04) (hash(x)=146101781)
|
| 78 |
+
620 train 5.280165 (lr=5.9972e-04) (hash(x)=137184623)
|
| 79 |
+
630 train 5.170963 (lr=5.9967e-04) (hash(x)=145791873)
|
| 80 |
+
640 train 5.191816 (lr=5.9962e-04) (hash(x)=143999212)
|
| 81 |
+
650 train 5.296673 (lr=5.9956e-04) (hash(x)=151631103)
|
| 82 |
+
660 train 5.056845 (lr=5.9950e-04) (hash(x)=138360108)
|
| 83 |
+
670 train 5.425130 (lr=5.9943e-04) (hash(x)=156637679)
|
| 84 |
+
680 train 5.071157 (lr=5.9937e-04) (hash(x)=143752601)
|
| 85 |
+
690 train 5.232902 (lr=5.9929e-04) (hash(x)=158368903)
|
| 86 |
+
700 val loss 5.4376
|
| 87 |
+
700 val perplexity 229.8988
|
| 88 |
+
700 train 5.435502 (lr=5.9922e-04) (hash(x)=150482428)
|
| 89 |
+
710 train 5.390243 (lr=5.9914e-04) (hash(x)=158085060)
|
| 90 |
+
720 train 5.451671 (lr=5.9905e-04) (hash(x)=159461069)
|
| 91 |
+
730 train 5.295540 (lr=5.9897e-04) (hash(x)=148795562)
|
| 92 |
+
740 train 5.311264 (lr=5.9887e-04) (hash(x)=149967984)
|
| 93 |
+
750 train 5.293331 (lr=5.9878e-04) (hash(x)=144458617)
|
| 94 |
+
760 train 5.335251 (lr=5.9868e-04) (hash(x)=155106202)
|
| 95 |
+
770 train 5.139704 (lr=5.9857e-04) (hash(x)=144506191)
|
| 96 |
+
780 train 5.283480 (lr=5.9847e-04) (hash(x)=155825158)
|
| 97 |
+
790 train 5.339315 (lr=5.9836e-04) (hash(x)=158835381)
|
| 98 |
+
800 val loss 5.2758
|
| 99 |
+
800 val perplexity 195.5408
|
| 100 |
+
800 train 5.221201 (lr=5.9824e-04) (hash(x)=143268605)
|
| 101 |
+
810 train 5.131927 (lr=5.9812e-04) (hash(x)=139072755)
|
| 102 |
+
820 train 5.289010 (lr=5.9800e-04) (hash(x)=179384792)
|
| 103 |
+
830 train 5.067116 (lr=5.9787e-04) (hash(x)=151086962)
|
| 104 |
+
840 train 5.661775 (lr=5.9774e-04) (hash(x)=142711393)
|
| 105 |
+
850 train 5.152798 (lr=5.9761e-04) (hash(x)=150817011)
|
| 106 |
+
860 train 5.079017 (lr=5.9747e-04) (hash(x)=138495801)
|
| 107 |
+
870 train 5.115953 (lr=5.9732e-04) (hash(x)=155474016)
|
| 108 |
+
880 train 5.142139 (lr=5.9718e-04) (hash(x)=151951501)
|
| 109 |
+
890 train 5.010257 (lr=5.9703e-04) (hash(x)=143699524)
|
| 110 |
+
900 val loss 5.1649
|
| 111 |
+
900 val perplexity 175.0215
|
| 112 |
+
900 train 5.159478 (lr=5.9687e-04) (hash(x)=152322423)
|
| 113 |
+
910 train 5.104273 (lr=5.9672e-04) (hash(x)=151010509)
|
| 114 |
+
920 train 4.893851 (lr=5.9655e-04) (hash(x)=148720342)
|
| 115 |
+
930 train 4.846943 (lr=5.9639e-04) (hash(x)=125869480)
|
| 116 |
+
940 train 5.102963 (lr=5.9622e-04) (hash(x)=150349503)
|
| 117 |
+
950 train 4.882380 (lr=5.9605e-04) (hash(x)=143574126)
|
| 118 |
+
960 train 5.064518 (lr=5.9587e-04) (hash(x)=146292562)
|
| 119 |
+
970 train 5.011444 (lr=5.9569e-04) (hash(x)=162256596)
|
| 120 |
+
980 train 4.948880 (lr=5.9550e-04) (hash(x)=137640259)
|
| 121 |
+
990 train 4.855735 (lr=5.9531e-04) (hash(x)=141767794)
|
| 122 |
+
1000 val loss 5.1091
|
| 123 |
+
1000 val perplexity 165.5265
|
| 124 |
+
1000 train 5.042518 (lr=5.9512e-04) (hash(x)=147904298)
|
| 125 |
+
1010 train 4.974709 (lr=5.9492e-04) (hash(x)=162239186)
|
| 126 |
+
1020 train 4.734469 (lr=5.9472e-04) (hash(x)=140706537)
|
| 127 |
+
1030 train 4.853150 (lr=5.9452e-04) (hash(x)=155556720)
|
| 128 |
+
1040 train 4.743192 (lr=5.9431e-04) (hash(x)=144746445)
|
| 129 |
+
1050 train 4.839166 (lr=5.9410e-04) (hash(x)=144719400)
|
| 130 |
+
1060 train 4.652897 (lr=5.9388e-04) (hash(x)=153065665)
|
| 131 |
+
1070 train 4.803423 (lr=5.9366e-04) (hash(x)=136468722)
|
| 132 |
+
1080 train 4.792062 (lr=5.9344e-04) (hash(x)=157674756)
|
| 133 |
+
1090 train 4.941757 (lr=5.9321e-04) (hash(x)=155882884)
|
| 134 |
+
1100 val loss 5.0126
|
| 135 |
+
1100 val perplexity 150.2885
|
| 136 |
+
1100 train 5.242490 (lr=5.9298e-04) (hash(x)=154343147)
|
| 137 |
+
1110 train 5.006681 (lr=5.9275e-04) (hash(x)=158582939)
|
| 138 |
+
1120 train 4.827847 (lr=5.9251e-04) (hash(x)=162479784)
|
| 139 |
+
1130 train 5.024753 (lr=5.9227e-04) (hash(x)=155704345)
|
| 140 |
+
1140 train 4.898115 (lr=5.9202e-04) (hash(x)=146934299)
|
| 141 |
+
1150 train 4.857088 (lr=5.9177e-04) (hash(x)=154372635)
|
| 142 |
+
1160 train 4.816307 (lr=5.9152e-04) (hash(x)=145536832)
|
| 143 |
+
1170 train 5.123067 (lr=5.9126e-04) (hash(x)=158785901)
|
| 144 |
+
1180 train 4.930710 (lr=5.9100e-04) (hash(x)=158271614)
|
| 145 |
+
1190 train 4.950810 (lr=5.9073e-04) (hash(x)=157365589)
|
| 146 |
+
1200 val loss 4.9073
|
| 147 |
+
1200 val perplexity 135.2674
|
| 148 |
+
1200 train 4.956767 (lr=5.9046e-04) (hash(x)=141843115)
|
| 149 |
+
1210 train 4.872190 (lr=5.9019e-04) (hash(x)=146807973)
|
| 150 |
+
1220 train 4.841632 (lr=5.8992e-04) (hash(x)=144149947)
|
| 151 |
+
1230 train 4.780746 (lr=5.8963e-04) (hash(x)=147869063)
|
| 152 |
+
1240 train 4.859216 (lr=5.8935e-04) (hash(x)=152217389)
|
| 153 |
+
1250 train 4.843330 (lr=5.8906e-04) (hash(x)=149417679)
|
| 154 |
+
1260 train 4.890008 (lr=5.8877e-04) (hash(x)=144029489)
|
| 155 |
+
1270 train 4.985224 (lr=5.8848e-04) (hash(x)=154328303)
|
| 156 |
+
1280 train 4.849533 (lr=5.8818e-04) (hash(x)=151625838)
|
| 157 |
+
1290 train 4.716599 (lr=5.8787e-04) (hash(x)=140270541)
|
| 158 |
+
1300 val loss 4.8360
|
| 159 |
+
1300 val perplexity 125.9631
|
| 160 |
+
1300 train 4.773347 (lr=5.8757e-04) (hash(x)=145279030)
|
| 161 |
+
1310 train 4.799668 (lr=5.8726e-04) (hash(x)=140279630)
|
| 162 |
+
1320 train 4.521388 (lr=5.8694e-04) (hash(x)=133642994)
|
| 163 |
+
1330 train 4.691833 (lr=5.8663e-04) (hash(x)=146634776)
|
| 164 |
+
1340 train 4.794439 (lr=5.8630e-04) (hash(x)=155919973)
|
| 165 |
+
1350 train 4.814174 (lr=5.8598e-04) (hash(x)=146363911)
|
| 166 |
+
1360 train 4.686668 (lr=5.8565e-04) (hash(x)=150613636)
|
| 167 |
+
1370 train 4.676257 (lr=5.8532e-04) (hash(x)=148536643)
|
| 168 |
+
1380 train 4.686653 (lr=5.8498e-04) (hash(x)=152803906)
|
| 169 |
+
1390 train 4.633714 (lr=5.8464e-04) (hash(x)=150383305)
|
| 170 |
+
1400 val loss 4.7960
|
| 171 |
+
1400 val perplexity 121.0193
|
| 172 |
+
1400 train 4.692439 (lr=5.8430e-04) (hash(x)=152507639)
|
| 173 |
+
1410 train 4.454031 (lr=5.8395e-04) (hash(x)=161841408)
|
| 174 |
+
1420 train 4.586825 (lr=5.8360e-04) (hash(x)=167824828)
|
| 175 |
+
1430 train 4.542679 (lr=5.8324e-04) (hash(x)=147696374)
|
| 176 |
+
1440 train 4.496708 (lr=5.8289e-04) (hash(x)=150085494)
|
| 177 |
+
1450 train 4.447160 (lr=5.8252e-04) (hash(x)=139296191)
|
| 178 |
+
1460 train 4.371064 (lr=5.8216e-04) (hash(x)=142956546)
|
| 179 |
+
1470 train 4.450001 (lr=5.8179e-04) (hash(x)=155908628)
|
| 180 |
+
1480 train 4.425796 (lr=5.8142e-04) (hash(x)=150893345)
|
| 181 |
+
1490 train 4.445243 (lr=5.8104e-04) (hash(x)=143548902)
|
| 182 |
+
1500 val loss 4.7301
|
| 183 |
+
1500 val perplexity 113.3080
|
| 184 |
+
1500 train 4.701874 (lr=5.8066e-04) (hash(x)=148473774)
|
| 185 |
+
1510 train 4.771822 (lr=5.8028e-04) (hash(x)=161631000)
|
| 186 |
+
1520 train 4.712205 (lr=5.7989e-04) (hash(x)=166217855)
|
| 187 |
+
1530 train 4.657665 (lr=5.7950e-04) (hash(x)=149440046)
|
| 188 |
+
1540 train 4.601507 (lr=5.7910e-04) (hash(x)=155013278)
|
| 189 |
+
1550 train 4.617747 (lr=5.7870e-04) (hash(x)=154130527)
|
| 190 |
+
1560 train 4.660770 (lr=5.7830e-04) (hash(x)=152138735)
|
| 191 |
+
1570 train 4.563497 (lr=5.7790e-04) (hash(x)=148128305)
|
| 192 |
+
1580 train 4.708984 (lr=5.7749e-04) (hash(x)=157176546)
|
| 193 |
+
1590 train 4.805791 (lr=5.7707e-04) (hash(x)=152935467)
|
| 194 |
+
1600 val loss 4.6581
|
| 195 |
+
1600 val perplexity 105.4339
|
| 196 |
+
1600 train 4.635081 (lr=5.7666e-04) (hash(x)=151117002)
|
| 197 |
+
1610 train 4.615851 (lr=5.7624e-04) (hash(x)=149883384)
|
| 198 |
+
1620 train 4.683335 (lr=5.7581e-04) (hash(x)=145015354)
|
| 199 |
+
1630 train 4.592213 (lr=5.7539e-04) (hash(x)=146717645)
|
| 200 |
+
1640 train 4.804672 (lr=5.7496e-04) (hash(x)=156372727)
|
| 201 |
+
1650 train 4.707918 (lr=5.7452e-04) (hash(x)=140261555)
|
| 202 |
+
1660 train 4.537348 (lr=5.7408e-04) (hash(x)=150088650)
|
| 203 |
+
1670 train 4.458913 (lr=5.7364e-04) (hash(x)=135943513)
|
| 204 |
+
1680 train 4.689734 (lr=5.7320e-04) (hash(x)=153529653)
|
| 205 |
+
1690 train 4.733294 (lr=5.7275e-04) (hash(x)=148930360)
|
| 206 |
+
1700 val loss 4.6493
|
| 207 |
+
1700 val perplexity 104.5153
|
| 208 |
+
1700 train 4.629510 (lr=5.7230e-04) (hash(x)=138011335)
|
| 209 |
+
1710 train 4.586173 (lr=5.7184e-04) (hash(x)=141383599)
|
| 210 |
+
1720 train 4.764947 (lr=5.7138e-04) (hash(x)=161449652)
|
| 211 |
+
1730 train 4.559359 (lr=5.7092e-04) (hash(x)=153923561)
|
| 212 |
+
1740 train 4.498707 (lr=5.7045e-04) (hash(x)=146043253)
|
| 213 |
+
1750 train 4.524877 (lr=5.6999e-04) (hash(x)=155720883)
|
| 214 |
+
1760 train 4.497934 (lr=5.6951e-04) (hash(x)=148222148)
|
| 215 |
+
1770 train 4.568258 (lr=5.6904e-04) (hash(x)=155712380)
|
| 216 |
+
1780 train 4.451543 (lr=5.6856e-04) (hash(x)=149767859)
|
| 217 |
+
1790 train 4.688375 (lr=5.6807e-04) (hash(x)=167214230)
|
| 218 |
+
1800 val loss 4.6062
|
| 219 |
+
1800 val perplexity 100.1025
|
| 220 |
+
1800 train 4.582571 (lr=5.6759e-04) (hash(x)=171180926)
|
| 221 |
+
1810 train 4.596643 (lr=5.6710e-04) (hash(x)=162375834)
|
| 222 |
+
1820 train 4.715477 (lr=5.6660e-04) (hash(x)=151495752)
|
| 223 |
+
1830 train 4.626053 (lr=5.6611e-04) (hash(x)=146532257)
|
| 224 |
+
1840 train 4.706219 (lr=5.6561e-04) (hash(x)=145694434)
|
| 225 |
+
1850 train 4.594100 (lr=5.6510e-04) (hash(x)=144823488)
|
| 226 |
+
1860 train 4.681180 (lr=5.6459e-04) (hash(x)=149836286)
|
| 227 |
+
1870 train 4.653625 (lr=5.6408e-04) (hash(x)=143935049)
|
| 228 |
+
1880 train 4.677234 (lr=5.6357e-04) (hash(x)=151786371)
|
| 229 |
+
1890 train 4.573680 (lr=5.6305e-04) (hash(x)=152892567)
|
| 230 |
+
1900 val loss 4.5636
|
| 231 |
+
1900 val perplexity 95.9250
|
| 232 |
+
1900 train 4.604174 (lr=5.6253e-04) (hash(x)=141769419)
|
| 233 |
+
1910 train 4.637553 (lr=5.6201e-04) (hash(x)=156914416)
|
| 234 |
+
1920 train 4.478181 (lr=5.6148e-04) (hash(x)=151573900)
|
| 235 |
+
1930 train 4.578133 (lr=5.6095e-04) (hash(x)=145121701)
|
| 236 |
+
1940 train 4.518665 (lr=5.6041e-04) (hash(x)=150896348)
|
| 237 |
+
1950 train 4.629759 (lr=5.5988e-04) (hash(x)=168797189)
|
| 238 |
+
1960 train 4.501838 (lr=5.5934e-04) (hash(x)=146711430)
|
| 239 |
+
1970 train 4.357291 (lr=5.5879e-04) (hash(x)=152180946)
|
| 240 |
+
1980 train 4.480283 (lr=5.5824e-04) (hash(x)=155542268)
|
| 241 |
+
1990 train 4.446460 (lr=5.5769e-04) (hash(x)=144668660)
|
| 242 |
+
2000 val loss 4.5288
|
| 243 |
+
2000 val perplexity 92.6475
|
| 244 |
+
2000 train 4.521599 (lr=5.5714e-04) (hash(x)=151963443)
|
| 245 |
+
2010 train 4.511193 (lr=5.5658e-04) (hash(x)=150810352)
|
| 246 |
+
2020 train 4.513572 (lr=5.5602e-04) (hash(x)=157539832)
|
| 247 |
+
2030 train 4.734151 (lr=5.5546e-04) (hash(x)=137858786)
|
| 248 |
+
2040 train 4.464633 (lr=5.5489e-04) (hash(x)=154270900)
|
| 249 |
+
2050 train 4.326408 (lr=5.5432e-04) (hash(x)=156252579)
|
| 250 |
+
2060 train 4.255533 (lr=5.5374e-04) (hash(x)=143285549)
|
| 251 |
+
2070 train 4.466375 (lr=5.5317e-04) (hash(x)=150542438)
|
| 252 |
+
2080 train 4.391304 (lr=5.5259e-04) (hash(x)=146290330)
|
| 253 |
+
2090 train 4.477229 (lr=5.5200e-04) (hash(x)=146486756)
|
| 254 |
+
2100 val loss 4.5450
|
| 255 |
+
2100 val perplexity 94.1638
|
| 256 |
+
2100 train 4.485621 (lr=5.5142e-04) (hash(x)=162947470)
|
| 257 |
+
2110 train 4.384953 (lr=5.5083e-04) (hash(x)=150305391)
|
| 258 |
+
2120 train 4.541253 (lr=5.5023e-04) (hash(x)=156452783)
|
| 259 |
+
2130 train 4.524720 (lr=5.4964e-04) (hash(x)=167481875)
|
| 260 |
+
2140 train 4.491261 (lr=5.4904e-04) (hash(x)=141782256)
|
| 261 |
+
2150 train 4.525728 (lr=5.4843e-04) (hash(x)=145035419)
|
| 262 |
+
2160 train 4.574007 (lr=5.4783e-04) (hash(x)=142000400)
|
| 263 |
+
2170 train 4.530458 (lr=5.4722e-04) (hash(x)=144229380)
|
| 264 |
+
2180 train 4.579500 (lr=5.4661e-04) (hash(x)=166204176)
|
| 265 |
+
2190 train 4.506018 (lr=5.4599e-04) (hash(x)=150712057)
|
| 266 |
+
2200 val loss 4.4805
|
| 267 |
+
2200 val perplexity 88.2752
|
| 268 |
+
2200 train 4.396422 (lr=5.4537e-04) (hash(x)=154954810)
|
| 269 |
+
2210 train 4.591577 (lr=5.4475e-04) (hash(x)=155668760)
|
| 270 |
+
2220 train 4.421214 (lr=5.4413e-04) (hash(x)=144834708)
|
| 271 |
+
2230 train 4.412834 (lr=5.4350e-04) (hash(x)=159744566)
|
| 272 |
+
2240 train 4.380198 (lr=5.4287e-04) (hash(x)=158543377)
|
| 273 |
+
2250 train 4.391350 (lr=5.4223e-04) (hash(x)=151004281)
|
| 274 |
+
2260 train 4.494900 (lr=5.4160e-04) (hash(x)=151242482)
|
| 275 |
+
2270 train 4.444022 (lr=5.4096e-04) (hash(x)=152056559)
|
| 276 |
+
2280 train 4.370753 (lr=5.4031e-04) (hash(x)=148864076)
|
| 277 |
+
2290 train 4.498991 (lr=5.3967e-04) (hash(x)=144294586)
|
| 278 |
+
2300 val loss 4.4655
|
| 279 |
+
2300 val perplexity 86.9604
|
| 280 |
+
2300 train 4.405931 (lr=5.3902e-04) (hash(x)=151878111)
|
| 281 |
+
2310 train 4.409058 (lr=5.3837e-04) (hash(x)=154139457)
|
| 282 |
+
2320 train 4.342014 (lr=5.3771e-04) (hash(x)=155571592)
|
| 283 |
+
2330 train 4.381868 (lr=5.3705e-04) (hash(x)=154823764)
|
| 284 |
+
2340 train 4.436868 (lr=5.3639e-04) (hash(x)=153252177)
|
| 285 |
+
2350 train 4.370737 (lr=5.3573e-04) (hash(x)=136051830)
|
| 286 |
+
2360 train 4.414216 (lr=5.3506e-04) (hash(x)=153814175)
|
| 287 |
+
2370 train 4.416036 (lr=5.3439e-04) (hash(x)=146391078)
|
| 288 |
+
2380 train 4.382503 (lr=5.3372e-04) (hash(x)=150782698)
|
| 289 |
+
2390 train 4.449402 (lr=5.3304e-04) (hash(x)=142752256)
|
| 290 |
+
2400 val loss 4.4705
|
| 291 |
+
2400 val perplexity 87.4020
|
| 292 |
+
2400 train 4.350583 (lr=5.3236e-04) (hash(x)=158661057)
|
| 293 |
+
2410 train 4.422263 (lr=5.3168e-04) (hash(x)=153611303)
|
| 294 |
+
2420 train 4.598189 (lr=5.3099e-04) (hash(x)=159508684)
|
| 295 |
+
2430 train 4.392899 (lr=5.3030e-04) (hash(x)=149501192)
|
| 296 |
+
2440 train 4.059241 (lr=5.2961e-04) (hash(x)=181177177)
|
| 297 |
+
2450 train 4.527268 (lr=5.2892e-04) (hash(x)=163664732)
|
| 298 |
+
2460 train 4.213627 (lr=5.2822e-04) (hash(x)=194527955)
|
| 299 |
+
2470 train 4.437664 (lr=5.2752e-04) (hash(x)=158088521)
|
| 300 |
+
2480 train 4.392514 (lr=5.2682e-04) (hash(x)=152865678)
|
| 301 |
+
2490 train 4.382834 (lr=5.2612e-04) (hash(x)=165703871)
|
| 302 |
+
2500 val loss 4.4230
|
| 303 |
+
2500 val perplexity 83.3499
|
| 304 |
+
2500 train 4.470942 (lr=5.2541e-04) (hash(x)=150925584)
|
| 305 |
+
2510 train 4.375011 (lr=5.2470e-04) (hash(x)=144406177)
|
| 306 |
+
2520 train 4.262231 (lr=5.2398e-04) (hash(x)=120133043)
|
| 307 |
+
2530 train 4.474709 (lr=5.2327e-04) (hash(x)=167900247)
|
| 308 |
+
2540 train 4.356240 (lr=5.2255e-04) (hash(x)=162599203)
|
| 309 |
+
2550 train 4.412279 (lr=5.2183e-04) (hash(x)=149328180)
|
| 310 |
+
2560 train 4.310459 (lr=5.2110e-04) (hash(x)=150049968)
|
| 311 |
+
2570 train 4.448700 (lr=5.2037e-04) (hash(x)=162876159)
|
| 312 |
+
2580 train 4.271173 (lr=5.1964e-04) (hash(x)=148260649)
|
| 313 |
+
2590 train 4.409980 (lr=5.1891e-04) (hash(x)=148998018)
|
| 314 |
+
2600 val loss 4.4101
|
| 315 |
+
2600 val perplexity 82.2796
|
| 316 |
+
2600 train 4.329995 (lr=5.1817e-04) (hash(x)=144515755)
|
| 317 |
+
2610 train 4.448966 (lr=5.1743e-04) (hash(x)=154455224)
|
| 318 |
+
2620 train 4.250093 (lr=5.1669e-04) (hash(x)=142920048)
|
| 319 |
+
2630 train 4.402009 (lr=5.1595e-04) (hash(x)=143931236)
|
| 320 |
+
2640 train 4.257731 (lr=5.1520e-04) (hash(x)=150983323)
|
| 321 |
+
2650 train 4.360910 (lr=5.1445e-04) (hash(x)=139360405)
|
| 322 |
+
2660 train 4.264170 (lr=5.1370e-04) (hash(x)=148850470)
|
| 323 |
+
2670 train 4.520264 (lr=5.1295e-04) (hash(x)=149929606)
|
| 324 |
+
2680 train 4.494000 (lr=5.1219e-04) (hash(x)=151673000)
|
| 325 |
+
2690 train 4.364605 (lr=5.1143e-04) (hash(x)=140631266)
|
| 326 |
+
2700 val loss 4.4025
|
| 327 |
+
2700 val perplexity 81.6556
|
| 328 |
+
2700 train 4.338117 (lr=5.1067e-04) (hash(x)=153109144)
|
| 329 |
+
2710 train 4.218790 (lr=5.0990e-04) (hash(x)=135332836)
|
| 330 |
+
2720 train 4.582860 (lr=5.0913e-04) (hash(x)=131611182)
|
| 331 |
+
2730 train 4.410504 (lr=5.0836e-04) (hash(x)=142909388)
|
| 332 |
+
2740 train 4.445091 (lr=5.0759e-04) (hash(x)=145593419)
|
| 333 |
+
2750 train 4.332325 (lr=5.0681e-04) (hash(x)=158225769)
|
| 334 |
+
2760 train 4.313293 (lr=5.0603e-04) (hash(x)=170509938)
|
| 335 |
+
2770 train 4.324759 (lr=5.0525e-04) (hash(x)=150785805)
|
| 336 |
+
2780 train 4.269176 (lr=5.0447e-04) (hash(x)=167281736)
|
| 337 |
+
2790 train 4.455155 (lr=5.0368e-04) (hash(x)=161660187)
|
| 338 |
+
2800 val loss 4.3755
|
| 339 |
+
2800 val perplexity 79.4785
|
| 340 |
+
2800 train 4.408805 (lr=5.0290e-04) (hash(x)=151152897)
|
| 341 |
+
2810 train 4.374192 (lr=5.0210e-04) (hash(x)=143172067)
|
| 342 |
+
2820 train 4.388582 (lr=5.0131e-04) (hash(x)=141569169)
|
| 343 |
+
2830 train 4.267646 (lr=5.0052e-04) (hash(x)=159709681)
|
| 344 |
+
2840 train 4.329834 (lr=4.9972e-04) (hash(x)=162552294)
|
| 345 |
+
2850 train 4.443244 (lr=4.9892e-04) (hash(x)=146762690)
|
| 346 |
+
2860 train 4.316198 (lr=4.9811e-04) (hash(x)=145729422)
|
| 347 |
+
2870 train 4.388108 (lr=4.9731e-04) (hash(x)=144360628)
|
| 348 |
+
2880 train 4.203232 (lr=4.9650e-04) (hash(x)=147737098)
|
| 349 |
+
2890 train 4.314510 (lr=4.9569e-04) (hash(x)=146849057)
|
| 350 |
+
2900 val loss 4.3576
|
| 351 |
+
2900 val perplexity 78.0701
|
| 352 |
+
2900 train 4.378337 (lr=4.9487e-04) (hash(x)=145800210)
|
| 353 |
+
2910 train 4.185465 (lr=4.9406e-04) (hash(x)=147316313)
|
| 354 |
+
2920 train 4.234604 (lr=4.9324e-04) (hash(x)=152595415)
|
| 355 |
+
2930 train 4.399158 (lr=4.9242e-04) (hash(x)=156542647)
|
| 356 |
+
2940 train 4.257132 (lr=4.9160e-04) (hash(x)=141183896)
|
| 357 |
+
2950 train 4.358592 (lr=4.9077e-04) (hash(x)=156329036)
|
| 358 |
+
2960 train 4.397128 (lr=4.8995e-04) (hash(x)=156717793)
|
| 359 |
+
2970 train 4.259643 (lr=4.8912e-04) (hash(x)=143949931)
|
| 360 |
+
2980 train 4.325744 (lr=4.8829e-04) (hash(x)=155067290)
|
| 361 |
+
2990 train 4.290055 (lr=4.8745e-04) (hash(x)=148774729)
|
| 362 |
+
3000 val loss 4.3704
|
| 363 |
+
3000 val perplexity 79.0792
|
| 364 |
+
3000 train 4.270265 (lr=4.8662e-04) (hash(x)=141997485)
|
| 365 |
+
3010 train 4.238098 (lr=4.8578e-04) (hash(x)=160762953)
|
| 366 |
+
3020 train 4.209878 (lr=4.8494e-04) (hash(x)=170341665)
|
| 367 |
+
3030 train 4.473457 (lr=4.8409e-04) (hash(x)=150722836)
|
| 368 |
+
3040 train 4.265443 (lr=4.8325e-04) (hash(x)=154243307)
|
| 369 |
+
3050 train 4.313826 (lr=4.8240e-04) (hash(x)=146077234)
|
| 370 |
+
3060 train 4.266632 (lr=4.8155e-04) (hash(x)=152125542)
|
| 371 |
+
3070 train 4.449606 (lr=4.8070e-04) (hash(x)=144149387)
|
| 372 |
+
3080 train 4.279145 (lr=4.7984e-04) (hash(x)=147508712)
|
| 373 |
+
3090 train 4.274778 (lr=4.7899e-04) (hash(x)=143583369)
|
| 374 |
+
3100 val loss 4.3284
|
| 375 |
+
3100 val perplexity 75.8227
|
| 376 |
+
3100 train 4.305622 (lr=4.7813e-04) (hash(x)=154049740)
|
| 377 |
+
3110 train 4.365994 (lr=4.7727e-04) (hash(x)=147054835)
|
| 378 |
+
3120 train 4.347172 (lr=4.7641e-04) (hash(x)=152468568)
|
| 379 |
+
3130 train 4.287776 (lr=4.7554e-04) (hash(x)=151635194)
|
| 380 |
+
3140 train 4.255615 (lr=4.7467e-04) (hash(x)=150396274)
|
| 381 |
+
3150 train 4.307040 (lr=4.7380e-04) (hash(x)=141306267)
|
| 382 |
+
3160 train 4.250585 (lr=4.7293e-04) (hash(x)=151110762)
|
| 383 |
+
3170 train 4.344000 (lr=4.7206e-04) (hash(x)=146518875)
|
| 384 |
+
3180 train 4.218246 (lr=4.7118e-04) (hash(x)=139914401)
|
| 385 |
+
3190 train 4.226621 (lr=4.7031e-04) (hash(x)=161631880)
|
| 386 |
+
3200 val loss 4.3408
|
| 387 |
+
3200 val perplexity 76.7651
|
| 388 |
+
3200 train 4.252343 (lr=4.6943e-04) (hash(x)=150471842)
|
| 389 |
+
3210 train 4.312123 (lr=4.6855e-04) (hash(x)=147355138)
|
| 390 |
+
3220 train 4.111239 (lr=4.6766e-04) (hash(x)=138879678)
|
| 391 |
+
3230 train 4.218341 (lr=4.6678e-04) (hash(x)=123929679)
|
| 392 |
+
3240 train 4.286832 (lr=4.6589e-04) (hash(x)=157263734)
|
| 393 |
+
3250 train 4.294387 (lr=4.6500e-04) (hash(x)=148065539)
|
| 394 |
+
3260 train 4.213184 (lr=4.6411e-04) (hash(x)=138020742)
|
| 395 |
+
3270 train 4.077530 (lr=4.6322e-04) (hash(x)=142053611)
|
| 396 |
+
3280 train 4.233654 (lr=4.6232e-04) (hash(x)=155444784)
|
| 397 |
+
3290 train 4.061300 (lr=4.6142e-04) (hash(x)=148500315)
|
| 398 |
+
3300 val loss 4.3312
|
| 399 |
+
3300 val perplexity 76.0333
|
| 400 |
+
3300 train 4.298663 (lr=4.6052e-04) (hash(x)=149048126)
|
| 401 |
+
3310 train 4.245136 (lr=4.5962e-04) (hash(x)=141680674)
|
| 402 |
+
3320 train 4.189808 (lr=4.5872e-04) (hash(x)=143310642)
|
| 403 |
+
3330 train 4.290866 (lr=4.5782e-04) (hash(x)=149891496)
|
| 404 |
+
3340 train 4.248428 (lr=4.5691e-04) (hash(x)=151244609)
|
| 405 |
+
3350 train 4.260502 (lr=4.5600e-04) (hash(x)=157158479)
|
| 406 |
+
3360 train 4.115778 (lr=4.5509e-04) (hash(x)=151709876)
|
| 407 |
+
3370 train 4.266237 (lr=4.5418e-04) (hash(x)=145297090)
|
| 408 |
+
3380 train 4.285998 (lr=4.5326e-04) (hash(x)=154767881)
|
| 409 |
+
3390 train 4.260479 (lr=4.5235e-04) (hash(x)=152600366)
|
| 410 |
+
3400 val loss 4.3074
|
| 411 |
+
3400 val perplexity 74.2492
|
| 412 |
+
3400 train 4.491827 (lr=4.5143e-04) (hash(x)=161261339)
|
| 413 |
+
3410 train 4.242117 (lr=4.5051e-04) (hash(x)=146859162)
|
| 414 |
+
3420 train 4.334076 (lr=4.4959e-04) (hash(x)=149276224)
|
| 415 |
+
3430 train 4.361734 (lr=4.4867e-04) (hash(x)=155866933)
|
| 416 |
+
3440 train 4.214377 (lr=4.4774e-04) (hash(x)=143191904)
|
| 417 |
+
3450 train 4.436650 (lr=4.4682e-04) (hash(x)=156910661)
|
| 418 |
+
3460 train 4.225041 (lr=4.4589e-04) (hash(x)=140850879)
|
| 419 |
+
3470 train 4.445935 (lr=4.4496e-04) (hash(x)=162140445)
|
| 420 |
+
3480 train 4.190761 (lr=4.4403e-04) (hash(x)=145607495)
|
| 421 |
+
3490 train 4.205517 (lr=4.4310e-04) (hash(x)=152496121)
|
| 422 |
+
3500 val loss 4.3006
|
| 423 |
+
3500 val perplexity 73.7430
|
| 424 |
+
3500 train 4.175681 (lr=4.4216e-04) (hash(x)=157495564)
|
| 425 |
+
3510 train 4.298810 (lr=4.4123e-04) (hash(x)=147657004)
|
| 426 |
+
3520 train 4.267686 (lr=4.4029e-04) (hash(x)=152978060)
|
| 427 |
+
3530 train 4.205024 (lr=4.3935e-04) (hash(x)=146800180)
|
| 428 |
+
3540 train 4.279503 (lr=4.3841e-04) (hash(x)=195450444)
|
| 429 |
+
3550 train 4.260127 (lr=4.3747e-04) (hash(x)=151114129)
|
| 430 |
+
3560 train 4.244706 (lr=4.3652e-04) (hash(x)=143833190)
|
| 431 |
+
3570 train 4.051334 (lr=4.3558e-04) (hash(x)=146039971)
|
| 432 |
+
3580 train 4.116214 (lr=4.3463e-04) (hash(x)=145172249)
|
| 433 |
+
3590 train 4.035852 (lr=4.3368e-04) (hash(x)=159164125)
|
| 434 |
+
3600 val loss 4.2968
|
| 435 |
+
3600 val perplexity 73.4613
|
| 436 |
+
3600 train 4.271433 (lr=4.3273e-04) (hash(x)=144352932)
|
| 437 |
+
3610 train 4.239083 (lr=4.3178e-04) (hash(x)=150550670)
|
| 438 |
+
3620 train 4.367783 (lr=4.3083e-04) (hash(x)=147170125)
|
| 439 |
+
3630 train 4.166487 (lr=4.2987e-04) (hash(x)=139473935)
|
| 440 |
+
3640 train 4.158472 (lr=4.2892e-04) (hash(x)=159294424)
|
| 441 |
+
3650 train 4.276155 (lr=4.2796e-04) (hash(x)=145943278)
|
| 442 |
+
3660 train 4.334130 (lr=4.2700e-04) (hash(x)=141647872)
|
| 443 |
+
3670 train 4.305375 (lr=4.2604e-04) (hash(x)=147109351)
|
| 444 |
+
3680 train 4.328221 (lr=4.2508e-04) (hash(x)=140683368)
|
| 445 |
+
3690 train 4.245663 (lr=4.2411e-04) (hash(x)=156276284)
|
| 446 |
+
3700 val loss 4.2802
|
| 447 |
+
3700 val perplexity 72.2530
|
| 448 |
+
3700 train 4.196733 (lr=4.2315e-04) (hash(x)=149389012)
|
| 449 |
+
3710 train 4.326389 (lr=4.2218e-04) (hash(x)=142107929)
|
| 450 |
+
3720 train 4.301076 (lr=4.2122e-04) (hash(x)=147828843)
|
| 451 |
+
3730 train 4.365184 (lr=4.2025e-04) (hash(x)=141784679)
|
| 452 |
+
3740 train 4.265013 (lr=4.1928e-04) (hash(x)=153375464)
|
| 453 |
+
3750 train 4.203296 (lr=4.1831e-04) (hash(x)=153716001)
|
| 454 |
+
3760 train 4.164290 (lr=4.1734e-04) (hash(x)=146848822)
|
| 455 |
+
3770 train 4.123320 (lr=4.1636e-04) (hash(x)=148396782)
|
| 456 |
+
3780 train 4.191072 (lr=4.1539e-04) (hash(x)=153563244)
|
| 457 |
+
3790 train 4.104450 (lr=4.1441e-04) (hash(x)=160808734)
|
| 458 |
+
3800 val loss 4.2704
|
| 459 |
+
3800 val perplexity 71.5513
|
| 460 |
+
3800 train 4.292404 (lr=4.1343e-04) (hash(x)=146607620)
|
| 461 |
+
3810 train 4.258980 (lr=4.1246e-04) (hash(x)=152580677)
|
| 462 |
+
3820 train 4.617507 (lr=4.1148e-04) (hash(x)=144860879)
|
| 463 |
+
3830 train 4.278432 (lr=4.1050e-04) (hash(x)=162099851)
|
| 464 |
+
3840 train 4.239708 (lr=4.0951e-04) (hash(x)=159506855)
|
| 465 |
+
3850 train 4.164797 (lr=4.0853e-04) (hash(x)=140022686)
|
| 466 |
+
3860 train 4.237893 (lr=4.0755e-04) (hash(x)=152137850)
|
| 467 |
+
3870 train 4.356323 (lr=4.0656e-04) (hash(x)=142666785)
|
| 468 |
+
3880 train 4.204819 (lr=4.0557e-04) (hash(x)=148285868)
|
| 469 |
+
3890 train 4.171728 (lr=4.0459e-04) (hash(x)=147910067)
|
| 470 |
+
3900 val loss 4.2705
|
| 471 |
+
3900 val perplexity 71.5566
|
| 472 |
+
3900 train 4.208207 (lr=4.0360e-04) (hash(x)=143754617)
|
| 473 |
+
3910 train 4.207408 (lr=4.0261e-04) (hash(x)=154779949)
|
| 474 |
+
3920 train 4.047403 (lr=4.0162e-04) (hash(x)=137824061)
|
| 475 |
+
3930 train 4.017090 (lr=4.0063e-04) (hash(x)=136933373)
|
| 476 |
+
3940 train 4.094826 (lr=3.9963e-04) (hash(x)=164054337)
|
| 477 |
+
3950 train 4.318359 (lr=3.9864e-04) (hash(x)=155752984)
|
| 478 |
+
3960 train 4.403209 (lr=3.9764e-04) (hash(x)=160957673)
|
| 479 |
+
3970 train 4.272636 (lr=3.9665e-04) (hash(x)=157158690)
|
| 480 |
+
3980 train 4.278957 (lr=3.9565e-04) (hash(x)=153282027)
|
| 481 |
+
3990 train 4.304569 (lr=3.9465e-04) (hash(x)=152183510)
|
| 482 |
+
4000 val loss 4.2443
|
| 483 |
+
4000 val perplexity 69.7064
|
| 484 |
+
4000 train 4.196175 (lr=3.9365e-04) (hash(x)=156930722)
|
| 485 |
+
4010 train 4.187428 (lr=3.9266e-04) (hash(x)=150798740)
|
| 486 |
+
4020 train 4.405786 (lr=3.9165e-04) (hash(x)=142632400)
|
| 487 |
+
4030 train 4.304651 (lr=3.9065e-04) (hash(x)=173326287)
|
| 488 |
+
4040 train 4.197855 (lr=3.8965e-04) (hash(x)=128797443)
|
| 489 |
+
4050 train 4.192305 (lr=3.8865e-04) (hash(x)=146937792)
|
| 490 |
+
4060 train 4.300669 (lr=3.8764e-04) (hash(x)=164579030)
|
| 491 |
+
4070 train 4.162514 (lr=3.8664e-04) (hash(x)=149459820)
|
| 492 |
+
4080 train 4.134852 (lr=3.8563e-04) (hash(x)=160159595)
|
| 493 |
+
4090 train 4.076524 (lr=3.8463e-04) (hash(x)=141507853)
|
| 494 |
+
4100 val loss 4.2426
|
| 495 |
+
4100 val perplexity 69.5908
|
| 496 |
+
4100 train 4.212006 (lr=3.8362e-04) (hash(x)=147500519)
|
| 497 |
+
4110 train 4.189104 (lr=3.8261e-04) (hash(x)=153297081)
|
| 498 |
+
4120 train 4.196279 (lr=3.8160e-04) (hash(x)=142560288)
|
| 499 |
+
4130 train 4.212025 (lr=3.8059e-04) (hash(x)=153380118)
|
| 500 |
+
4140 train 4.117969 (lr=3.7958e-04) (hash(x)=143150720)
|
| 501 |
+
4150 train 4.160090 (lr=3.7857e-04) (hash(x)=143459564)
|
| 502 |
+
4160 train 4.192156 (lr=3.7756e-04) (hash(x)=153955741)
|
| 503 |
+
4170 train 4.297305 (lr=3.7655e-04) (hash(x)=152199253)
|
| 504 |
+
4180 train 4.064004 (lr=3.7553e-04) (hash(x)=165957668)
|
| 505 |
+
4190 train 4.118344 (lr=3.7452e-04) (hash(x)=144866923)
|
| 506 |
+
4200 val loss 4.2466
|
| 507 |
+
4200 val perplexity 69.8644
|
| 508 |
+
4200 train 4.116647 (lr=3.7351e-04) (hash(x)=143232237)
|
| 509 |
+
4210 train 4.033844 (lr=3.7249e-04) (hash(x)=151907163)
|
| 510 |
+
4220 train 4.135174 (lr=3.7148e-04) (hash(x)=145917587)
|
| 511 |
+
4230 train 3.967760 (lr=3.7046e-04) (hash(x)=147258846)
|
| 512 |
+
4240 train 4.124782 (lr=3.6944e-04) (hash(x)=143449843)
|
| 513 |
+
4250 train 4.085752 (lr=3.6843e-04) (hash(x)=184883715)
|
| 514 |
+
4260 train 4.176322 (lr=3.6741e-04) (hash(x)=156958761)
|
| 515 |
+
4270 train 4.250105 (lr=3.6639e-04) (hash(x)=168870544)
|
| 516 |
+
4280 train 4.175034 (lr=3.6537e-04) (hash(x)=179446735)
|
| 517 |
+
4290 train 4.219192 (lr=3.6435e-04) (hash(x)=145649386)
|
| 518 |
+
4300 val loss 4.2332
|
| 519 |
+
4300 val perplexity 68.9401
|
| 520 |
+
4300 train 4.066499 (lr=3.6333e-04) (hash(x)=146811670)
|
| 521 |
+
4310 train 4.336442 (lr=3.6231e-04) (hash(x)=151907075)
|
| 522 |
+
4320 train 4.138725 (lr=3.6129e-04) (hash(x)=138628365)
|
| 523 |
+
4330 train 4.197901 (lr=3.6027e-04) (hash(x)=151608240)
|
| 524 |
+
4340 train 4.128697 (lr=3.5925e-04) (hash(x)=160111319)
|
| 525 |
+
4350 train 4.278884 (lr=3.5822e-04) (hash(x)=144958652)
|
| 526 |
+
4360 train 4.068399 (lr=3.5720e-04) (hash(x)=149176222)
|
| 527 |
+
4370 train 4.125728 (lr=3.5618e-04) (hash(x)=216221371)
|
| 528 |
+
4380 train 4.071362 (lr=3.5515e-04) (hash(x)=141760648)
|
| 529 |
+
4390 train 4.159255 (lr=3.5413e-04) (hash(x)=151710283)
|
| 530 |
+
4400 val loss 4.2200
|
| 531 |
+
4400 val perplexity 68.0334
|
| 532 |
+
4400 train 4.280020 (lr=3.5311e-04) (hash(x)=158418746)
|
| 533 |
+
4410 train 4.136970 (lr=3.5208e-04) (hash(x)=142331301)
|
| 534 |
+
4420 train 4.217907 (lr=3.5106e-04) (hash(x)=146507180)
|
| 535 |
+
4430 train 4.309099 (lr=3.5003e-04) (hash(x)=166506937)
|
| 536 |
+
4440 train 4.245703 (lr=3.4901e-04) (hash(x)=151209447)
|
| 537 |
+
4450 train 4.208759 (lr=3.4798e-04) (hash(x)=149186822)
|
| 538 |
+
4460 train 4.195794 (lr=3.4695e-04) (hash(x)=144348412)
|
| 539 |
+
4470 train 4.081789 (lr=3.4593e-04) (hash(x)=156494284)
|
| 540 |
+
4480 train 4.115552 (lr=3.4490e-04) (hash(x)=147238744)
|
| 541 |
+
4490 train 4.059175 (lr=3.4387e-04) (hash(x)=150746185)
|
| 542 |
+
4500 val loss 4.2153
|
| 543 |
+
4500 val perplexity 67.7136
|
| 544 |
+
4500 train 4.153756 (lr=3.4285e-04) (hash(x)=156695778)
|
| 545 |
+
4510 train 3.995005 (lr=3.4182e-04) (hash(x)=135988958)
|
| 546 |
+
4520 train 4.163864 (lr=3.4079e-04) (hash(x)=148272110)
|
| 547 |
+
4530 train 4.080733 (lr=3.3977e-04) (hash(x)=136459794)
|
| 548 |
+
4540 train 4.115305 (lr=3.3874e-04) (hash(x)=147624954)
|
| 549 |
+
4550 train 4.115876 (lr=3.3771e-04) (hash(x)=154947199)
|
| 550 |
+
4560 train 4.174077 (lr=3.3668e-04) (hash(x)=147869166)
|
| 551 |
+
4570 train 4.023650 (lr=3.3565e-04) (hash(x)=148415463)
|
| 552 |
+
4580 train 4.192674 (lr=3.3463e-04) (hash(x)=152104066)
|
| 553 |
+
4590 train 4.090989 (lr=3.3360e-04) (hash(x)=147060040)
|
| 554 |
+
4600 val loss 4.2122
|
| 555 |
+
4600 val perplexity 67.5075
|
| 556 |
+
4600 train 4.163352 (lr=3.3257e-04) (hash(x)=147791497)
|
| 557 |
+
4610 train 4.362179 (lr=3.3154e-04) (hash(x)=155595556)
|
| 558 |
+
4620 train 4.207492 (lr=3.3051e-04) (hash(x)=147178858)
|
| 559 |
+
4630 train 4.258422 (lr=3.2949e-04) (hash(x)=152617112)
|
| 560 |
+
4640 train 4.267780 (lr=3.2846e-04) (hash(x)=161766869)
|
| 561 |
+
4650 train 4.242554 (lr=3.2743e-04) (hash(x)=158075561)
|
| 562 |
+
4660 train 4.279838 (lr=3.2640e-04) (hash(x)=145360002)
|
| 563 |
+
4670 train 4.162302 (lr=3.2537e-04) (hash(x)=144538791)
|
| 564 |
+
4680 train 4.194803 (lr=3.2435e-04) (hash(x)=142711273)
|
| 565 |
+
4690 train 4.356268 (lr=3.2332e-04) (hash(x)=193907362)
|
| 566 |
+
4700 val loss 4.1921
|
| 567 |
+
4700 val perplexity 66.1593
|
| 568 |
+
4700 train 4.161912 (lr=3.2229e-04) (hash(x)=155533088)
|
| 569 |
+
4710 train 4.120488 (lr=3.2126e-04) (hash(x)=148618528)
|
| 570 |
+
4720 train 4.228819 (lr=3.2023e-04) (hash(x)=150502624)
|
| 571 |
+
4730 train 4.103030 (lr=3.1921e-04) (hash(x)=189205847)
|
| 572 |
+
4740 train 4.159419 (lr=3.1818e-04) (hash(x)=167322800)
|
| 573 |
+
4750 train 4.279221 (lr=3.1715e-04) (hash(x)=162169095)
|
| 574 |
+
4760 train 3.984187 (lr=3.1613e-04) (hash(x)=143459469)
|
| 575 |
+
4770 train 4.055861 (lr=3.1510e-04) (hash(x)=144386593)
|
| 576 |
+
4780 train 4.026664 (lr=3.1407e-04) (hash(x)=143721184)
|
| 577 |
+
4790 train 4.094540 (lr=3.1305e-04) (hash(x)=146077222)
|
| 578 |
+
4800 val loss 4.1973
|
| 579 |
+
4800 val perplexity 66.5080
|
| 580 |
+
4800 train 4.074190 (lr=3.1202e-04) (hash(x)=138350044)
|
| 581 |
+
4810 train 4.074332 (lr=3.1099e-04) (hash(x)=154960112)
|
| 582 |
+
4820 train 3.985426 (lr=3.0997e-04) (hash(x)=146950685)
|
| 583 |
+
4830 train 3.986783 (lr=3.0894e-04) (hash(x)=140224554)
|
| 584 |
+
4840 train 3.984618 (lr=3.0792e-04) (hash(x)=156640495)
|
| 585 |
+
4850 train 4.193567 (lr=3.0689e-04) (hash(x)=153409150)
|
| 586 |
+
4860 train 4.110546 (lr=3.0587e-04) (hash(x)=151647700)
|
| 587 |
+
4870 train 4.507183 (lr=3.0485e-04) (hash(x)=155465603)
|
| 588 |
+
4880 train 4.350823 (lr=3.0382e-04) (hash(x)=153404400)
|
| 589 |
+
4890 train 4.237038 (lr=3.0280e-04) (hash(x)=170409281)
|
| 590 |
+
4900 val loss 4.1829
|
| 591 |
+
4900 val perplexity 65.5532
|
| 592 |
+
4900 train 4.104501 (lr=3.0178e-04) (hash(x)=143735284)
|
| 593 |
+
4910 train 4.239965 (lr=3.0075e-04) (hash(x)=150784329)
|
| 594 |
+
4920 train 4.126100 (lr=2.9973e-04) (hash(x)=152353574)
|
| 595 |
+
4930 train 4.079868 (lr=2.9871e-04) (hash(x)=152677008)
|
| 596 |
+
4940 train 4.157333 (lr=2.9769e-04) (hash(x)=140553861)
|
| 597 |
+
4950 train 4.247647 (lr=2.9667e-04) (hash(x)=152869181)
|
| 598 |
+
4960 train 4.198486 (lr=2.9565e-04) (hash(x)=153011079)
|
| 599 |
+
4970 train 4.151272 (lr=2.9463e-04) (hash(x)=152796617)
|
| 600 |
+
4980 train 4.263351 (lr=2.9361e-04) (hash(x)=146868417)
|
| 601 |
+
4990 train 4.140583 (lr=2.9259e-04) (hash(x)=140168188)
|
| 602 |
+
5000 val loss 4.1718
|
| 603 |
+
5000 val perplexity 64.8329
|
| 604 |
+
5000 train 4.124722 (lr=2.9157e-04) (hash(x)=154976463)
|
| 605 |
+
5010 train 4.190895 (lr=2.9056e-04) (hash(x)=148582690)
|
| 606 |
+
5020 train 4.192195 (lr=2.8954e-04) (hash(x)=166715464)
|
| 607 |
+
5030 train 4.154720 (lr=2.8852e-04) (hash(x)=150616397)
|
| 608 |
+
5040 train 4.201216 (lr=2.8751e-04) (hash(x)=150775548)
|
| 609 |
+
5050 train 4.184381 (lr=2.8649e-04) (hash(x)=150575367)
|
| 610 |
+
5060 train 4.107418 (lr=2.8548e-04) (hash(x)=152352082)
|
| 611 |
+
5070 train 4.150015 (lr=2.8447e-04) (hash(x)=150269272)
|
| 612 |
+
5080 train 4.204904 (lr=2.8345e-04) (hash(x)=146499361)
|
| 613 |
+
5090 train 3.890438 (lr=2.8244e-04) (hash(x)=148734454)
|
| 614 |
+
5100 val loss 4.1734
|
| 615 |
+
5100 val perplexity 64.9384
|
| 616 |
+
5100 train 4.077798 (lr=2.8143e-04) (hash(x)=149894982)
|
| 617 |
+
5110 train 4.130024 (lr=2.8042e-04) (hash(x)=154487751)
|
| 618 |
+
5120 train 4.074249 (lr=2.7941e-04) (hash(x)=144169582)
|
| 619 |
+
5130 train 4.052025 (lr=2.7840e-04) (hash(x)=152217630)
|
| 620 |
+
5140 train 4.084290 (lr=2.7739e-04) (hash(x)=158233831)
|
| 621 |
+
5150 train 4.140765 (lr=2.7638e-04) (hash(x)=142746426)
|
| 622 |
+
5160 train 4.132466 (lr=2.7537e-04) (hash(x)=139184458)
|
| 623 |
+
5170 train 4.219120 (lr=2.7437e-04) (hash(x)=140624857)
|
| 624 |
+
5180 train 3.941659 (lr=2.7336e-04) (hash(x)=154107423)
|
| 625 |
+
5190 train 3.882357 (lr=2.7236e-04) (hash(x)=144892610)
|
| 626 |
+
5200 val loss 4.1729
|
| 627 |
+
5200 val perplexity 64.9035
|
| 628 |
+
5200 train 3.836998 (lr=2.7135e-04) (hash(x)=159326689)
|
| 629 |
+
5210 train 3.999723 (lr=2.7035e-04) (hash(x)=151186017)
|
| 630 |
+
5220 train 3.814011 (lr=2.6935e-04) (hash(x)=148996819)
|
| 631 |
+
5230 train 3.761153 (lr=2.6835e-04) (hash(x)=150829917)
|
| 632 |
+
5240 train 3.874853 (lr=2.6734e-04) (hash(x)=152758972)
|
| 633 |
+
5250 train 3.841526 (lr=2.6635e-04) (hash(x)=154345903)
|
| 634 |
+
5260 train 3.839329 (lr=2.6535e-04) (hash(x)=150134947)
|
| 635 |
+
5270 train 3.933956 (lr=2.6435e-04) (hash(x)=149689310)
|
| 636 |
+
5280 train 4.160221 (lr=2.6335e-04) (hash(x)=147662223)
|
| 637 |
+
5290 train 4.229419 (lr=2.6236e-04) (hash(x)=165770608)
|
| 638 |
+
5300 val loss 4.1613
|
| 639 |
+
5300 val perplexity 64.1526
|
| 640 |
+
5300 train 4.209962 (lr=2.6136e-04) (hash(x)=159484800)
|
| 641 |
+
5310 train 4.250412 (lr=2.6037e-04) (hash(x)=152672536)
|
| 642 |
+
5320 train 4.067711 (lr=2.5937e-04) (hash(x)=152728812)
|
| 643 |
+
5330 train 4.014211 (lr=2.5838e-04) (hash(x)=152778685)
|
| 644 |
+
5340 train 4.104506 (lr=2.5739e-04) (hash(x)=149818849)
|
| 645 |
+
5350 train 4.043990 (lr=2.5640e-04) (hash(x)=168239739)
|
| 646 |
+
5360 train 4.186938 (lr=2.5541e-04) (hash(x)=139859423)
|
| 647 |
+
5370 train 4.012883 (lr=2.5443e-04) (hash(x)=139315327)
|
| 648 |
+
5380 train 4.216764 (lr=2.5344e-04) (hash(x)=163068509)
|
| 649 |
+
5390 train 4.173079 (lr=2.5245e-04) (hash(x)=147645415)
|
| 650 |
+
5400 val loss 4.1419
|
| 651 |
+
5400 val perplexity 62.9238
|
| 652 |
+
5400 train 4.131252 (lr=2.5147e-04) (hash(x)=140385615)
|
| 653 |
+
5410 train 3.990021 (lr=2.5049e-04) (hash(x)=151381862)
|
| 654 |
+
5420 train 4.146679 (lr=2.4950e-04) (hash(x)=152445092)
|
| 655 |
+
5430 train 4.156535 (lr=2.4852e-04) (hash(x)=142454479)
|
| 656 |
+
5440 train 4.111445 (lr=2.4754e-04) (hash(x)=151308771)
|
| 657 |
+
5450 train 3.961064 (lr=2.4657e-04) (hash(x)=150886070)
|
| 658 |
+
5460 train 4.065333 (lr=2.4559e-04) (hash(x)=146080408)
|
| 659 |
+
5470 train 4.092682 (lr=2.4461e-04) (hash(x)=149828857)
|
| 660 |
+
5480 train 4.064167 (lr=2.4364e-04) (hash(x)=139922034)
|
| 661 |
+
5490 train 4.013615 (lr=2.4266e-04) (hash(x)=150262276)
|
| 662 |
+
5500 val loss 4.1429
|
| 663 |
+
5500 val perplexity 62.9838
|
| 664 |
+
5500 train 3.983670 (lr=2.4169e-04) (hash(x)=148498335)
|
| 665 |
+
5510 train 4.095223 (lr=2.4072e-04) (hash(x)=157036224)
|
| 666 |
+
5520 train 3.978663 (lr=2.3975e-04) (hash(x)=134093409)
|
| 667 |
+
5530 train 4.008155 (lr=2.3878e-04) (hash(x)=153126250)
|
| 668 |
+
5540 train 4.013888 (lr=2.3782e-04) (hash(x)=136170985)
|
| 669 |
+
5550 train 4.001459 (lr=2.3685e-04) (hash(x)=152841201)
|
| 670 |
+
5560 train 4.100555 (lr=2.3589e-04) (hash(x)=147439014)
|
| 671 |
+
5570 train 4.017499 (lr=2.3492e-04) (hash(x)=143476132)
|
| 672 |
+
5580 train 3.789842 (lr=2.3396e-04) (hash(x)=139503437)
|
| 673 |
+
5590 train 3.834293 (lr=2.3300e-04) (hash(x)=131664955)
|
| 674 |
+
5600 val loss 4.1513
|
| 675 |
+
5600 val perplexity 63.5171
|
| 676 |
+
5600 train 3.930974 (lr=2.3204e-04) (hash(x)=151907614)
|
| 677 |
+
5610 train 3.818095 (lr=2.3108e-04) (hash(x)=157132674)
|
| 678 |
+
5620 train 4.014812 (lr=2.3013e-04) (hash(x)=146793775)
|
| 679 |
+
5630 train 3.964301 (lr=2.2917e-04) (hash(x)=147237910)
|
| 680 |
+
5640 train 3.873759 (lr=2.2822e-04) (hash(x)=141120024)
|
| 681 |
+
5650 train 3.853304 (lr=2.2727e-04) (hash(x)=144275645)
|
| 682 |
+
5660 train 3.882977 (lr=2.2632e-04) (hash(x)=159088002)
|
| 683 |
+
5670 train 3.939816 (lr=2.2537e-04) (hash(x)=147224479)
|
| 684 |
+
5680 train 4.283384 (lr=2.2442e-04) (hash(x)=147208743)
|
| 685 |
+
5690 train 4.087255 (lr=2.2348e-04) (hash(x)=154384701)
|
| 686 |
+
5700 val loss 4.1429
|
| 687 |
+
5700 val perplexity 62.9852
|
| 688 |
+
5700 train 4.122369 (lr=2.2253e-04) (hash(x)=155192267)
|
| 689 |
+
5710 train 4.061213 (lr=2.2159e-04) (hash(x)=148458753)
|
| 690 |
+
5720 train 4.166955 (lr=2.2065e-04) (hash(x)=159947204)
|
| 691 |
+
5730 train 4.161260 (lr=2.1971e-04) (hash(x)=150746366)
|
| 692 |
+
5740 train 4.148029 (lr=2.1877e-04) (hash(x)=155201884)
|
| 693 |
+
5750 train 4.150617 (lr=2.1784e-04) (hash(x)=156432008)
|
| 694 |
+
5760 train 4.132886 (lr=2.1690e-04) (hash(x)=185977746)
|
| 695 |
+
5770 train 4.132131 (lr=2.1597e-04) (hash(x)=133620000)
|
| 696 |
+
5780 train 4.140632 (lr=2.1504e-04) (hash(x)=153778044)
|
| 697 |
+
5790 train 3.990527 (lr=2.1411e-04) (hash(x)=147713822)
|
| 698 |
+
5800 val loss 4.1225
|
| 699 |
+
5800 val perplexity 61.7122
|
| 700 |
+
5800 train 4.144154 (lr=2.1318e-04) (hash(x)=153132158)
|
| 701 |
+
5810 train 4.095840 (lr=2.1226e-04) (hash(x)=144293895)
|
| 702 |
+
5820 train 4.077534 (lr=2.1133e-04) (hash(x)=151500590)
|
| 703 |
+
5830 train 4.025883 (lr=2.1041e-04) (hash(x)=139308707)
|
| 704 |
+
5840 train 4.143580 (lr=2.0949e-04) (hash(x)=153591278)
|
| 705 |
+
5850 train 4.122774 (lr=2.0857e-04) (hash(x)=146077037)
|
| 706 |
+
5860 train 4.084943 (lr=2.0765e-04) (hash(x)=149160733)
|
| 707 |
+
5870 train 4.069598 (lr=2.0674e-04) (hash(x)=138482476)
|
| 708 |
+
5880 train 4.084016 (lr=2.0582e-04) (hash(x)=152173137)
|
| 709 |
+
5890 train 4.054162 (lr=2.0491e-04) (hash(x)=142387057)
|
| 710 |
+
5900 val loss 4.1294
|
| 711 |
+
5900 val perplexity 62.1406
|
| 712 |
+
5900 train 4.130868 (lr=2.0400e-04) (hash(x)=161446764)
|
| 713 |
+
5910 train 4.006062 (lr=2.0309e-04) (hash(x)=144512138)
|
| 714 |
+
5920 train 4.065510 (lr=2.0218e-04) (hash(x)=152555618)
|
| 715 |
+
5930 train 4.024787 (lr=2.0128e-04) (hash(x)=146129367)
|
| 716 |
+
5940 train 3.964532 (lr=2.0038e-04) (hash(x)=154607527)
|
| 717 |
+
5950 train 4.052170 (lr=1.9948e-04) (hash(x)=143827143)
|
| 718 |
+
5960 train 4.181569 (lr=1.9858e-04) (hash(x)=151168510)
|
| 719 |
+
5970 train 3.971842 (lr=1.9768e-04) (hash(x)=158961574)
|
| 720 |
+
5980 train 3.800040 (lr=1.9678e-04) (hash(x)=148757787)
|
| 721 |
+
5990 train 4.304749 (lr=1.9589e-04) (hash(x)=161719494)
|
| 722 |
+
6000 val loss 4.1289
|
| 723 |
+
6000 val perplexity 62.1090
|
| 724 |
+
6000 train 3.803596 (lr=1.9500e-04) (hash(x)=151512446)
|
| 725 |
+
6010 train 3.928452 (lr=1.9411e-04) (hash(x)=173500735)
|
| 726 |
+
6020 train 4.054879 (lr=1.9322e-04) (hash(x)=157621031)
|
| 727 |
+
6030 train 3.941328 (lr=1.9234e-04) (hash(x)=142662684)
|
| 728 |
+
6040 train 3.926851 (lr=1.9145e-04) (hash(x)=146180940)
|
| 729 |
+
6050 train 3.845347 (lr=1.9057e-04) (hash(x)=147654412)
|
| 730 |
+
6060 train 3.725557 (lr=1.8969e-04) (hash(x)=156393157)
|
| 731 |
+
6070 train 4.119762 (lr=1.8882e-04) (hash(x)=156947300)
|
| 732 |
+
6080 train 4.114617 (lr=1.8794e-04) (hash(x)=163108626)
|
| 733 |
+
6090 train 4.212381 (lr=1.8707e-04) (hash(x)=158654713)
|
| 734 |
+
6100 val loss 4.1114
|
| 735 |
+
6100 val perplexity 61.0335
|
| 736 |
+
6100 train 3.941209 (lr=1.8620e-04) (hash(x)=188094053)
|
| 737 |
+
6110 train 4.104810 (lr=1.8533e-04) (hash(x)=145132600)
|
| 738 |
+
6120 train 3.973321 (lr=1.8446e-04) (hash(x)=146999707)
|
| 739 |
+
6130 train 4.207595 (lr=1.8359e-04) (hash(x)=145719530)
|
| 740 |
+
6140 train 4.146309 (lr=1.8273e-04) (hash(x)=153230722)
|
| 741 |
+
6150 train 4.078898 (lr=1.8187e-04) (hash(x)=147455934)
|
| 742 |
+
6160 train 4.128797 (lr=1.8101e-04) (hash(x)=146596242)
|
| 743 |
+
6170 train 4.223723 (lr=1.8016e-04) (hash(x)=152029855)
|
| 744 |
+
6180 train 4.086768 (lr=1.7930e-04) (hash(x)=151480034)
|
| 745 |
+
6190 train 4.021400 (lr=1.7845e-04) (hash(x)=147381047)
|
| 746 |
+
6200 val loss 4.0979
|
| 747 |
+
6200 val perplexity 60.2145
|
| 748 |
+
6200 train 4.008654 (lr=1.7760e-04) (hash(x)=149389789)
|
| 749 |
+
6210 train 4.056643 (lr=1.7675e-04) (hash(x)=154894138)
|
| 750 |
+
6220 train 4.092628 (lr=1.7591e-04) (hash(x)=150074302)
|
| 751 |
+
6230 train 3.964304 (lr=1.7506e-04) (hash(x)=142881794)
|
| 752 |
+
6240 train 3.946099 (lr=1.7422e-04) (hash(x)=164747461)
|
| 753 |
+
6250 train 4.111120 (lr=1.7338e-04) (hash(x)=158378292)
|
| 754 |
+
6260 train 4.119335 (lr=1.7255e-04) (hash(x)=147675938)
|
| 755 |
+
6270 train 4.062585 (lr=1.7171e-04) (hash(x)=148197228)
|
| 756 |
+
6280 train 4.023065 (lr=1.7088e-04) (hash(x)=135296747)
|
| 757 |
+
6290 train 4.102140 (lr=1.7005e-04) (hash(x)=156439346)
|
| 758 |
+
6300 val loss 4.0971
|
| 759 |
+
6300 val perplexity 60.1641
|
| 760 |
+
6300 train 3.917470 (lr=1.6923e-04) (hash(x)=138212820)
|
| 761 |
+
6310 train 4.217722 (lr=1.6840e-04) (hash(x)=165985336)
|
| 762 |
+
6320 train 4.081685 (lr=1.6758e-04) (hash(x)=145921897)
|
| 763 |
+
6330 train 4.295026 (lr=1.6676e-04) (hash(x)=145502689)
|
| 764 |
+
6340 train 4.025110 (lr=1.6594e-04) (hash(x)=141704937)
|
| 765 |
+
6350 train 4.083145 (lr=1.6513e-04) (hash(x)=161789400)
|
| 766 |
+
6360 train 3.802051 (lr=1.6431e-04) (hash(x)=145457780)
|
| 767 |
+
6370 train 4.056484 (lr=1.6350e-04) (hash(x)=171628530)
|
| 768 |
+
6380 train 3.849670 (lr=1.6269e-04) (hash(x)=153467923)
|
| 769 |
+
6390 train 4.222523 (lr=1.6189e-04) (hash(x)=158066904)
|
| 770 |
+
6400 val loss 4.1026
|
| 771 |
+
6400 val perplexity 60.4967
|
| 772 |
+
6400 train 3.873353 (lr=1.6108e-04) (hash(x)=146535423)
|
| 773 |
+
6410 train 3.737594 (lr=1.6028e-04) (hash(x)=147264155)
|
| 774 |
+
6420 train 3.840661 (lr=1.5948e-04) (hash(x)=145595485)
|
| 775 |
+
6430 train 3.986471 (lr=1.5869e-04) (hash(x)=146929074)
|
| 776 |
+
6440 train 3.911173 (lr=1.5790e-04) (hash(x)=147290878)
|
| 777 |
+
6450 train 4.010109 (lr=1.5710e-04) (hash(x)=141154205)
|
| 778 |
+
6460 train 3.855596 (lr=1.5632e-04) (hash(x)=154360901)
|
| 779 |
+
6470 train 4.191347 (lr=1.5553e-04) (hash(x)=146350558)
|
| 780 |
+
6480 train 4.154114 (lr=1.5475e-04) (hash(x)=153927683)
|
| 781 |
+
6490 train 4.065804 (lr=1.5397e-04) (hash(x)=149337047)
|
| 782 |
+
6500 val loss 4.0905
|
| 783 |
+
6500 val perplexity 59.7677
|
| 784 |
+
6500 train 3.990298 (lr=1.5319e-04) (hash(x)=145950843)
|
| 785 |
+
6510 train 4.055512 (lr=1.5241e-04) (hash(x)=142577653)
|
| 786 |
+
6520 train 4.114680 (lr=1.5164e-04) (hash(x)=165060689)
|
| 787 |
+
6530 train 3.950322 (lr=1.5087e-04) (hash(x)=148367505)
|
| 788 |
+
6540 train 4.050065 (lr=1.5010e-04) (hash(x)=154313651)
|
| 789 |
+
6550 train 3.966772 (lr=1.4933e-04) (hash(x)=147477315)
|
| 790 |
+
6560 train 4.057713 (lr=1.4857e-04) (hash(x)=139825403)
|
| 791 |
+
6570 train 4.073455 (lr=1.4781e-04) (hash(x)=141482518)
|
| 792 |
+
6580 train 4.111005 (lr=1.4705e-04) (hash(x)=144968144)
|
| 793 |
+
6590 train 4.052938 (lr=1.4630e-04) (hash(x)=154319720)
|
| 794 |
+
6600 val loss 4.0872
|
| 795 |
+
6600 val perplexity 59.5708
|
| 796 |
+
6600 train 4.098924 (lr=1.4555e-04) (hash(x)=141162902)
|
| 797 |
+
6610 train 4.064279 (lr=1.4480e-04) (hash(x)=159490449)
|
| 798 |
+
6620 train 3.944865 (lr=1.4405e-04) (hash(x)=151189772)
|
| 799 |
+
6630 train 3.929213 (lr=1.4331e-04) (hash(x)=148451651)
|
| 800 |
+
6640 train 4.048608 (lr=1.4257e-04) (hash(x)=152815550)
|
| 801 |
+
6650 train 3.899125 (lr=1.4183e-04) (hash(x)=144316094)
|
| 802 |
+
6660 train 4.218923 (lr=1.4109e-04) (hash(x)=143951240)
|
| 803 |
+
6670 train 3.841168 (lr=1.4036e-04) (hash(x)=143203472)
|
| 804 |
+
6680 train 3.883866 (lr=1.3963e-04) (hash(x)=132063806)
|
| 805 |
+
6690 train 3.975191 (lr=1.3890e-04) (hash(x)=140739750)
|
| 806 |
+
6700 val loss 4.0906
|
| 807 |
+
6700 val perplexity 59.7781
|
| 808 |
+
6700 train 4.037490 (lr=1.3817e-04) (hash(x)=153018737)
|
| 809 |
+
6710 train 3.898584 (lr=1.3745e-04) (hash(x)=140107197)
|
| 810 |
+
6720 train 4.004174 (lr=1.3673e-04) (hash(x)=144396559)
|
| 811 |
+
6730 train 3.850376 (lr=1.3602e-04) (hash(x)=148038991)
|
| 812 |
+
6740 train 4.063259 (lr=1.3530e-04) (hash(x)=145504746)
|
| 813 |
+
6750 train 4.052204 (lr=1.3459e-04) (hash(x)=119579094)
|
| 814 |
+
6760 train 4.065996 (lr=1.3388e-04) (hash(x)=161725430)
|
| 815 |
+
6770 train 4.082900 (lr=1.3318e-04) (hash(x)=153646966)
|
| 816 |
+
6780 train 4.088391 (lr=1.3248e-04) (hash(x)=153838463)
|
| 817 |
+
6790 train 4.215812 (lr=1.3178e-04) (hash(x)=157891196)
|
| 818 |
+
6800 val loss 4.0746
|
| 819 |
+
6800 val perplexity 58.8259
|
| 820 |
+
6800 train 3.928339 (lr=1.3108e-04) (hash(x)=155640155)
|
| 821 |
+
6810 train 4.126523 (lr=1.3039e-04) (hash(x)=154913809)
|
| 822 |
+
6820 train 4.039434 (lr=1.2970e-04) (hash(x)=159412493)
|
| 823 |
+
6830 train 3.998991 (lr=1.2901e-04) (hash(x)=144756549)
|
| 824 |
+
6840 train 4.210915 (lr=1.2832e-04) (hash(x)=143824638)
|
| 825 |
+
6850 train 4.539484 (lr=1.2764e-04) (hash(x)=117180982)
|
| 826 |
+
6860 train 4.055289 (lr=1.2696e-04) (hash(x)=141887150)
|
| 827 |
+
6870 train 4.125406 (lr=1.2628e-04) (hash(x)=140094872)
|
| 828 |
+
6880 train 3.961360 (lr=1.2561e-04) (hash(x)=141479953)
|
| 829 |
+
6890 train 4.027465 (lr=1.2494e-04) (hash(x)=153166840)
|
| 830 |
+
6900 val loss 4.0723
|
| 831 |
+
6900 val perplexity 58.6907
|
| 832 |
+
6900 train 4.051608 (lr=1.2427e-04) (hash(x)=153722115)
|
| 833 |
+
6910 train 4.156342 (lr=1.2361e-04) (hash(x)=149578602)
|
| 834 |
+
6920 train 4.013233 (lr=1.2295e-04) (hash(x)=149925108)
|
| 835 |
+
6930 train 3.959399 (lr=1.2229e-04) (hash(x)=148589489)
|
| 836 |
+
6940 train 3.865299 (lr=1.2163e-04) (hash(x)=144243794)
|
| 837 |
+
6950 train 3.951268 (lr=1.2098e-04) (hash(x)=157743480)
|
| 838 |
+
6960 train 3.939175 (lr=1.2033e-04) (hash(x)=139858247)
|
| 839 |
+
6970 train 3.865141 (lr=1.1969e-04) (hash(x)=148727536)
|
| 840 |
+
6980 train 3.978397 (lr=1.1904e-04) (hash(x)=153382595)
|
| 841 |
+
6990 train 4.121367 (lr=1.1840e-04) (hash(x)=147529919)
|
| 842 |
+
7000 val loss 4.0668
|
| 843 |
+
7000 val perplexity 58.3719
|
| 844 |
+
7000 train 4.085890 (lr=1.1777e-04) (hash(x)=146953450)
|
| 845 |
+
7010 train 3.999857 (lr=1.1713e-04) (hash(x)=134561015)
|
| 846 |
+
7020 train 4.108835 (lr=1.1650e-04) (hash(x)=148433515)
|
| 847 |
+
7030 train 3.959126 (lr=1.1587e-04) (hash(x)=140394326)
|
| 848 |
+
7040 train 3.971859 (lr=1.1525e-04) (hash(x)=136740763)
|
| 849 |
+
7050 train 3.811120 (lr=1.1463e-04) (hash(x)=148637938)
|
| 850 |
+
7060 train 3.966332 (lr=1.1401e-04) (hash(x)=147262147)
|
| 851 |
+
7070 train 3.942297 (lr=1.1339e-04) (hash(x)=140191039)
|
| 852 |
+
7080 train 3.959689 (lr=1.1278e-04) (hash(x)=148223305)
|
| 853 |
+
7090 train 3.878488 (lr=1.1217e-04) (hash(x)=139984988)
|
| 854 |
+
7100 val loss 4.0709
|
| 855 |
+
7100 val perplexity 58.6080
|
| 856 |
+
7100 train 3.991115 (lr=1.1157e-04) (hash(x)=137663885)
|
| 857 |
+
7110 train 3.870194 (lr=1.1096e-04) (hash(x)=150955021)
|
| 858 |
+
7120 train 3.781229 (lr=1.1036e-04) (hash(x)=148585682)
|
| 859 |
+
7130 train 3.980319 (lr=1.0977e-04) (hash(x)=146055548)
|
| 860 |
+
7140 train 4.023724 (lr=1.0917e-04) (hash(x)=155723541)
|
| 861 |
+
7150 train 4.093482 (lr=1.0858e-04) (hash(x)=140465834)
|
| 862 |
+
7160 train 4.069212 (lr=1.0800e-04) (hash(x)=163246922)
|
| 863 |
+
7170 train 3.923124 (lr=1.0741e-04) (hash(x)=150754166)
|
| 864 |
+
7180 train 4.459840 (lr=1.0683e-04) (hash(x)=142844151)
|
| 865 |
+
7190 train 4.051715 (lr=1.0626e-04) (hash(x)=145167470)
|
| 866 |
+
7200 val loss 4.0558
|
| 867 |
+
7200 val perplexity 57.7315
|
| 868 |
+
7200 train 4.245859 (lr=1.0568e-04) (hash(x)=146172950)
|
| 869 |
+
7210 train 4.069397 (lr=1.0511e-04) (hash(x)=143155287)
|
| 870 |
+
7220 train 4.012595 (lr=1.0454e-04) (hash(x)=151976669)
|
| 871 |
+
7230 train 4.131927 (lr=1.0398e-04) (hash(x)=145979940)
|
| 872 |
+
7240 train 4.099851 (lr=1.0342e-04) (hash(x)=155656034)
|
| 873 |
+
7250 train 4.103560 (lr=1.0286e-04) (hash(x)=135610136)
|
| 874 |
+
7260 train 4.178649 (lr=1.0231e-04) (hash(x)=148133023)
|
| 875 |
+
7270 train 4.054573 (lr=1.0176e-04) (hash(x)=148006681)
|
| 876 |
+
7280 train 4.087193 (lr=1.0121e-04) (hash(x)=151397627)
|
| 877 |
+
7290 train 4.051458 (lr=1.0066e-04) (hash(x)=141696871)
|
| 878 |
+
7300 val loss 4.0521
|
| 879 |
+
7300 val perplexity 57.5208
|
| 880 |
+
7300 train 3.987123 (lr=1.0012e-04) (hash(x)=150018163)
|
| 881 |
+
7310 train 4.026327 (lr=9.9586e-05) (hash(x)=154900050)
|
| 882 |
+
7320 train 3.923479 (lr=9.9052e-05) (hash(x)=142608283)
|
| 883 |
+
7330 train 4.023843 (lr=9.8521e-05) (hash(x)=148977837)
|
| 884 |
+
7340 train 4.039836 (lr=9.7993e-05) (hash(x)=141676907)
|
| 885 |
+
7350 train 3.929224 (lr=9.7469e-05) (hash(x)=147846997)
|
| 886 |
+
7360 train 4.172251 (lr=9.6948e-05) (hash(x)=143252181)
|
| 887 |
+
7370 train 3.990706 (lr=9.6431e-05) (hash(x)=155081717)
|
| 888 |
+
7380 train 4.076017 (lr=9.5917e-05) (hash(x)=149678451)
|
| 889 |
+
7390 train 3.903874 (lr=9.5406e-05) (hash(x)=159341637)
|
| 890 |
+
7400 val loss 4.0528
|
| 891 |
+
7400 val perplexity 57.5576
|
| 892 |
+
7400 train 4.190771 (lr=9.4899e-05) (hash(x)=145351166)
|
| 893 |
+
7410 train 4.010730 (lr=9.4395e-05) (hash(x)=162274009)
|
| 894 |
+
7420 train 3.855141 (lr=9.3894e-05) (hash(x)=143254858)
|
| 895 |
+
7430 train 3.970327 (lr=9.3397e-05) (hash(x)=143049884)
|
| 896 |
+
7440 train 3.891670 (lr=9.2904e-05) (hash(x)=141768538)
|
| 897 |
+
7450 train 3.909357 (lr=9.2413e-05) (hash(x)=139895310)
|
| 898 |
+
7460 train 3.787262 (lr=9.1927e-05) (hash(x)=155900365)
|
| 899 |
+
7470 train 3.772058 (lr=9.1443e-05) (hash(x)=145048215)
|
| 900 |
+
7480 train 3.908541 (lr=9.0964e-05) (hash(x)=136992624)
|
| 901 |
+
7490 train 4.018570 (lr=9.0487e-05) (hash(x)=141424789)
|
| 902 |
+
7500 val loss 4.0561
|
| 903 |
+
7500 val perplexity 57.7496
|
| 904 |
+
7500 train 3.868097 (lr=9.0014e-05) (hash(x)=145292116)
|
| 905 |
+
7510 train 3.908433 (lr=8.9545e-05) (hash(x)=144818029)
|
| 906 |
+
7520 train 4.077182 (lr=8.9079e-05) (hash(x)=152903515)
|
| 907 |
+
7530 train 4.084540 (lr=8.8617e-05) (hash(x)=156934724)
|
| 908 |
+
7540 train 4.309597 (lr=8.8158e-05) (hash(x)=156695926)
|
| 909 |
+
7550 train 4.071164 (lr=8.7702e-05) (hash(x)=149115609)
|
| 910 |
+
7560 train 4.053979 (lr=8.7251e-05) (hash(x)=143974224)
|
| 911 |
+
7570 train 4.006804 (lr=8.6802e-05) (hash(x)=148204424)
|
| 912 |
+
7580 train 4.087867 (lr=8.6357e-05) (hash(x)=150177910)
|
| 913 |
+
7590 train 4.101072 (lr=8.5916e-05) (hash(x)=140325629)
|
| 914 |
+
7600 val loss 4.0446
|
| 915 |
+
7600 val perplexity 57.0909
|
| 916 |
+
7600 train 3.985204 (lr=8.5478e-05) (hash(x)=150235132)
|
| 917 |
+
7610 train 4.110114 (lr=8.5044e-05) (hash(x)=157594837)
|
| 918 |
+
7620 train 4.119292 (lr=8.4613e-05) (hash(x)=146696749)
|
| 919 |
+
7630 train 4.158076 (lr=8.4186e-05) (hash(x)=148463580)
|
| 920 |
+
7640 train 3.973668 (lr=8.3763e-05) (hash(x)=140271046)
|
| 921 |
+
7650 train 4.038039 (lr=8.3343e-05) (hash(x)=159952319)
|
| 922 |
+
7660 train 4.034402 (lr=8.2926e-05) (hash(x)=146307392)
|
| 923 |
+
7670 train 3.989335 (lr=8.2514e-05) (hash(x)=145027988)
|
| 924 |
+
7680 train 4.054815 (lr=8.2104e-05) (hash(x)=147729698)
|
| 925 |
+
7690 train 4.038677 (lr=8.1699e-05) (hash(x)=143401210)
|
| 926 |
+
7700 val loss 4.0396
|
| 927 |
+
7700 val perplexity 56.8057
|
| 928 |
+
7700 train 3.969559 (lr=8.1297e-05) (hash(x)=154543455)
|
| 929 |
+
7710 train 4.043605 (lr=8.0898e-05) (hash(x)=151600456)
|
| 930 |
+
7720 train 3.959592 (lr=8.0503e-05) (hash(x)=165913803)
|
| 931 |
+
7730 train 3.830664 (lr=8.0112e-05) (hash(x)=144942059)
|
| 932 |
+
7740 train 4.057778 (lr=7.9725e-05) (hash(x)=150302103)
|
| 933 |
+
7750 train 4.001315 (lr=7.9341e-05) (hash(x)=155782458)
|
| 934 |
+
7760 train 4.029814 (lr=7.8960e-05) (hash(x)=147824384)
|
| 935 |
+
7770 train 4.042323 (lr=7.8584e-05) (hash(x)=149177657)
|
| 936 |
+
7780 train 4.068219 (lr=7.8211e-05) (hash(x)=164446738)
|
| 937 |
+
7790 train 3.872403 (lr=7.7841e-05) (hash(x)=146417077)
|
| 938 |
+
7800 val loss 4.0418
|
| 939 |
+
7800 val perplexity 56.9286
|
| 940 |
+
7800 train 4.019204 (lr=7.7476e-05) (hash(x)=142456852)
|
| 941 |
+
7810 train 3.718816 (lr=7.7114e-05) (hash(x)=146221807)
|
| 942 |
+
7820 train 3.913092 (lr=7.6755e-05) (hash(x)=154136533)
|
| 943 |
+
7830 train 3.827279 (lr=7.6400e-05) (hash(x)=147492735)
|
| 944 |
+
7840 train 3.978069 (lr=7.6049e-05) (hash(x)=143481291)
|
| 945 |
+
7850 train 3.808123 (lr=7.5702e-05) (hash(x)=136749307)
|
| 946 |
+
7860 train 3.832468 (lr=7.5358e-05) (hash(x)=128985347)
|
| 947 |
+
7870 train 3.735158 (lr=7.5018e-05) (hash(x)=152897363)
|
| 948 |
+
7880 train 3.940140 (lr=7.4682e-05) (hash(x)=151460360)
|
| 949 |
+
7890 train 3.758469 (lr=7.4350e-05) (hash(x)=137481738)
|
| 950 |
+
7900 val loss 4.0428
|
| 951 |
+
7900 val perplexity 56.9839
|
| 952 |
+
7900 train 3.836514 (lr=7.4021e-05) (hash(x)=147363479)
|
| 953 |
+
7910 train 4.058046 (lr=7.3696e-05) (hash(x)=151165744)
|
| 954 |
+
7920 train 4.230208 (lr=7.3374e-05) (hash(x)=146214226)
|
| 955 |
+
7930 train 4.041663 (lr=7.3056e-05) (hash(x)=154457502)
|
| 956 |
+
7940 train 3.949116 (lr=7.2742e-05) (hash(x)=162025201)
|
| 957 |
+
7950 train 3.940442 (lr=7.2432e-05) (hash(x)=156488145)
|
| 958 |
+
7960 train 4.217037 (lr=7.2126e-05) (hash(x)=154011584)
|
| 959 |
+
7970 train 4.064871 (lr=7.1823e-05) (hash(x)=145330320)
|
| 960 |
+
7980 train 3.970730 (lr=7.1524e-05) (hash(x)=148216312)
|
| 961 |
+
7990 train 3.905138 (lr=7.1228e-05) (hash(x)=156819091)
|
| 962 |
+
8000 val loss 4.0332
|
| 963 |
+
8000 val perplexity 56.4407
|
| 964 |
+
8000 train 4.066167 (lr=7.0937e-05) (hash(x)=156122973)
|
| 965 |
+
8010 train 4.008729 (lr=7.0649e-05) (hash(x)=146933088)
|
| 966 |
+
8020 train 4.105101 (lr=7.0365e-05) (hash(x)=151650746)
|
| 967 |
+
8030 train 4.029701 (lr=7.0085e-05) (hash(x)=140692373)
|
| 968 |
+
8040 train 4.217567 (lr=6.9808e-05) (hash(x)=147850094)
|
| 969 |
+
8050 train 4.041002 (lr=6.9536e-05) (hash(x)=144454109)
|
| 970 |
+
8060 train 3.900548 (lr=6.9267e-05) (hash(x)=152205124)
|
| 971 |
+
8070 train 4.119748 (lr=6.9002e-05) (hash(x)=148918066)
|
| 972 |
+
8080 train 4.046878 (lr=6.8740e-05) (hash(x)=146481024)
|
| 973 |
+
8090 train 4.087018 (lr=6.8483e-05) (hash(x)=168785549)
|
| 974 |
+
8100 val loss 4.0309
|
| 975 |
+
8100 val perplexity 56.3093
|
| 976 |
+
8100 train 4.111370 (lr=6.8229e-05) (hash(x)=156153179)
|
| 977 |
+
8110 train 4.061481 (lr=6.7979e-05) (hash(x)=150498601)
|
| 978 |
+
8120 train 4.070875 (lr=6.7733e-05) (hash(x)=142002714)
|
| 979 |
+
8130 train 3.953250 (lr=6.7490e-05) (hash(x)=138450483)
|
| 980 |
+
8140 train 4.037171 (lr=6.7252e-05) (hash(x)=145306351)
|
| 981 |
+
8150 train 3.917471 (lr=6.7017e-05) (hash(x)=172502865)
|
| 982 |
+
8160 train 4.017513 (lr=6.6786e-05) (hash(x)=156689649)
|
| 983 |
+
8170 train 3.935237 (lr=6.6559e-05) (hash(x)=143766932)
|
| 984 |
+
8180 train 4.074619 (lr=6.6335e-05) (hash(x)=150361321)
|
| 985 |
+
8190 train 3.908869 (lr=6.6116e-05) (hash(x)=152664241)
|
| 986 |
+
8200 val loss 4.0305
|
| 987 |
+
8200 val perplexity 56.2880
|
| 988 |
+
8200 train 4.183567 (lr=6.5900e-05) (hash(x)=146430698)
|
| 989 |
+
8210 train 3.867009 (lr=6.5688e-05) (hash(x)=167362078)
|
| 990 |
+
8220 train 4.093256 (lr=6.5480e-05) (hash(x)=157650942)
|
| 991 |
+
8230 train 3.901181 (lr=6.5276e-05) (hash(x)=142102044)
|
| 992 |
+
8240 train 3.941739 (lr=6.5076e-05) (hash(x)=153405900)
|
| 993 |
+
8250 train 3.893206 (lr=6.4879e-05) (hash(x)=140222909)
|
| 994 |
+
8260 train 4.024216 (lr=6.4687e-05) (hash(x)=137981854)
|
| 995 |
+
8270 train 3.940482 (lr=6.4498e-05) (hash(x)=147576272)
|
| 996 |
+
8280 train 3.954591 (lr=6.4313e-05) (hash(x)=157988195)
|
| 997 |
+
8290 train 4.008123 (lr=6.4132e-05) (hash(x)=145715681)
|
| 998 |
+
8300 val loss 4.0318
|
| 999 |
+
8300 val perplexity 56.3649
|
| 1000 |
+
8300 train 3.955391 (lr=6.3954e-05) (hash(x)=143507257)
|
| 1001 |
+
8310 train 4.012368 (lr=6.3781e-05) (hash(x)=148930064)
|
| 1002 |
+
8320 train 3.940289 (lr=6.3612e-05) (hash(x)=144134805)
|
| 1003 |
+
8330 train 4.057148 (lr=6.3446e-05) (hash(x)=148418079)
|
| 1004 |
+
8340 train 3.786915 (lr=6.3284e-05) (hash(x)=166518807)
|
| 1005 |
+
8350 train 4.088065 (lr=6.3126e-05) (hash(x)=140042036)
|
| 1006 |
+
8360 train 3.959472 (lr=6.2972e-05) (hash(x)=151427074)
|
| 1007 |
+
8370 train 4.044179 (lr=6.2822e-05) (hash(x)=158389185)
|
| 1008 |
+
8380 train 3.948700 (lr=6.2676e-05) (hash(x)=148193308)
|
| 1009 |
+
8390 train 4.018093 (lr=6.2533e-05) (hash(x)=144289008)
|
| 1010 |
+
8400 val loss 4.0231
|
| 1011 |
+
8400 val perplexity 55.8756
|
| 1012 |
+
8400 train 3.730502 (lr=6.2395e-05) (hash(x)=166272643)
|
| 1013 |
+
8410 train 3.945931 (lr=6.2260e-05) (hash(x)=162244433)
|
| 1014 |
+
8420 train 3.980301 (lr=6.2129e-05) (hash(x)=149271299)
|
| 1015 |
+
8430 train 4.122830 (lr=6.2002e-05) (hash(x)=154135338)
|
| 1016 |
+
8440 train 4.166543 (lr=6.1879e-05) (hash(x)=149661838)
|
| 1017 |
+
8450 train 4.001691 (lr=6.1760e-05) (hash(x)=142205056)
|
| 1018 |
+
8460 train 3.936829 (lr=6.1645e-05) (hash(x)=166652398)
|
| 1019 |
+
8470 train 4.108621 (lr=6.1533e-05) (hash(x)=149029710)
|
| 1020 |
+
8480 train 3.878456 (lr=6.1426e-05) (hash(x)=154217415)
|
| 1021 |
+
8490 train 3.956630 (lr=6.1322e-05) (hash(x)=151526557)
|
| 1022 |
+
8500 val loss 4.0245
|
| 1023 |
+
8500 val perplexity 55.9505
|
| 1024 |
+
8500 train 3.953250 (lr=6.1223e-05) (hash(x)=143887848)
|
| 1025 |
+
8510 train 3.933973 (lr=6.1127e-05) (hash(x)=152324645)
|
| 1026 |
+
8520 train 3.669834 (lr=6.1035e-05) (hash(x)=145124959)
|
| 1027 |
+
8530 train 3.988543 (lr=6.0947e-05) (hash(x)=186319340)
|
| 1028 |
+
8540 train 3.998351 (lr=6.0863e-05) (hash(x)=147388339)
|
| 1029 |
+
8550 train 4.030067 (lr=6.0783e-05) (hash(x)=150118928)
|
| 1030 |
+
8560 train 4.035618 (lr=6.0706e-05) (hash(x)=153985286)
|
| 1031 |
+
8570 train 3.982238 (lr=6.0634e-05) (hash(x)=149582799)
|
| 1032 |
+
8580 train 3.983272 (lr=6.0566e-05) (hash(x)=156867870)
|
| 1033 |
+
8590 train 3.867692 (lr=6.0501e-05) (hash(x)=148773298)
|
| 1034 |
+
8600 val loss 4.0264
|
| 1035 |
+
8600 val perplexity 56.0602
|
| 1036 |
+
8600 train 3.975746 (lr=6.0440e-05) (hash(x)=156900341)
|
| 1037 |
+
8610 train 4.127031 (lr=6.0384e-05) (hash(x)=156790089)
|
| 1038 |
+
8620 train 3.927780 (lr=6.0331e-05) (hash(x)=154680805)
|
| 1039 |
+
8630 train 3.971957 (lr=6.0282e-05) (hash(x)=138107873)
|
| 1040 |
+
8640 train 4.058555 (lr=6.0237e-05) (hash(x)=142554243)
|
| 1041 |
+
8650 train 3.861350 (lr=6.0196e-05) (hash(x)=134360956)
|
| 1042 |
+
8660 train 3.940917 (lr=6.0159e-05) (hash(x)=128599610)
|
| 1043 |
+
8670 train 3.970823 (lr=6.0125e-05) (hash(x)=159628945)
|
| 1044 |
+
8680 train 3.998497 (lr=6.0096e-05) (hash(x)=143161532)
|
| 1045 |
+
8690 train 4.033208 (lr=6.0070e-05) (hash(x)=140104912)
|
| 1046 |
+
8700 val loss 4.0187
|
| 1047 |
+
8700 val perplexity 55.6291
|
| 1048 |
+
8700 train 4.209576 (lr=6.0049e-05) (hash(x)=146417632)
|
| 1049 |
+
8710 train 4.181637 (lr=6.0031e-05) (hash(x)=153671695)
|
| 1050 |
+
8720 train 4.049231 (lr=6.0018e-05) (hash(x)=141680750)
|
| 1051 |
+
8730 train 3.930593 (lr=6.0008e-05) (hash(x)=147279231)
|
| 1052 |
+
8740 train 4.216293 (lr=6.0002e-05) (hash(x)=129729371)
|
| 1053 |
+
8749 val loss 4.0193
|
| 1054 |
+
8749 val perplexity 55.6630
|
lr6e-4_total_batch_size61440_baseline_seed1339/model_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ceb2613f6f378609f0a5aaa260de28c00cb0c688169a9a2036966df5a5dd8b82
|
| 3 |
+
size 92843394
|
lr6e-4_total_batch_size61440_baseline_seed1339/optimizer_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9789733031cde5e1b8a9b52a97f37623631b6b70ac5db1debe0274e14ae8edd7
|
| 3 |
+
size 179406214
|