Upload folder using huggingface_hub
Browse files- lr16e-4_total_batch_size61440_baseline_seed1338/args.json +1 -0
- lr16e-4_total_batch_size61440_baseline_seed1338/dataloader_08749.pt +3 -0
- lr16e-4_total_batch_size61440_baseline_seed1338/log2.txt +1054 -0
- lr16e-4_total_batch_size61440_baseline_seed1338/model_08749.pt +3 -0
- lr16e-4_total_batch_size61440_baseline_seed1338/optimizer_08749.pt +3 -0
lr16e-4_total_batch_size61440_baseline_seed1338/args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hellaswag": true, "attention_kind": "selective", "log_dir": "wider_is_better_11/lr16e-4_total_batch_size61440_baseline_seed1338", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 4, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 8750, "warmup_steps": 500, "group": "wider_is_better_11", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1338, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "none", "selection_head_linear_combo_scale": 1.0, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 256, "batch_size": 120, "total_batch_size": 61440, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": null, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": false, "mup_enable_coord_check_logging": false, "max_lr": 0.0016, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "key": "16e-4_61440", "n_embd": 256}
|
lr16e-4_total_batch_size61440_baseline_seed1338/dataloader_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:953385078aa3787b69fc6857dfd48b0a2cd2f4d27c6f8892e01211aca53d07f5
|
| 3 |
+
size 964
|
lr16e-4_total_batch_size61440_baseline_seed1338/log2.txt
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
max_steps: 8750
|
| 2 |
+
0 val loss 11.2202
|
| 3 |
+
0 val perplexity 74626.3672
|
| 4 |
+
0 train 11.227304 (lr=3.2000e-06) (hash(x)=150327452)
|
| 5 |
+
10 train 9.972887 (lr=3.5200e-05) (hash(x)=165603215)
|
| 6 |
+
20 train 9.516108 (lr=6.7200e-05) (hash(x)=142061326)
|
| 7 |
+
30 train 8.889233 (lr=9.9200e-05) (hash(x)=147690730)
|
| 8 |
+
40 train 8.316031 (lr=1.3120e-04) (hash(x)=160872542)
|
| 9 |
+
50 train 7.841997 (lr=1.6320e-04) (hash(x)=166441190)
|
| 10 |
+
60 train 7.660695 (lr=1.9520e-04) (hash(x)=140536766)
|
| 11 |
+
70 train 7.590111 (lr=2.2720e-04) (hash(x)=146052944)
|
| 12 |
+
80 train 7.435937 (lr=2.5920e-04) (hash(x)=140542391)
|
| 13 |
+
90 train 7.297568 (lr=2.9120e-04) (hash(x)=147098660)
|
| 14 |
+
100 val loss 7.2863
|
| 15 |
+
100 val perplexity 1460.1827
|
| 16 |
+
100 train 7.253595 (lr=3.2320e-04) (hash(x)=166780046)
|
| 17 |
+
110 train 7.002010 (lr=3.5520e-04) (hash(x)=143376584)
|
| 18 |
+
120 train 6.918857 (lr=3.8720e-04) (hash(x)=145337630)
|
| 19 |
+
130 train 6.894269 (lr=4.1920e-04) (hash(x)=147524744)
|
| 20 |
+
140 train 6.784772 (lr=4.5120e-04) (hash(x)=155587442)
|
| 21 |
+
150 train 6.662381 (lr=4.8320e-04) (hash(x)=159835303)
|
| 22 |
+
160 train 6.510073 (lr=5.1520e-04) (hash(x)=142171630)
|
| 23 |
+
170 train 6.412191 (lr=5.4720e-04) (hash(x)=136930463)
|
| 24 |
+
180 train 6.380286 (lr=5.7920e-04) (hash(x)=153579148)
|
| 25 |
+
190 train 6.282069 (lr=6.1120e-04) (hash(x)=140352771)
|
| 26 |
+
200 val loss 6.4800
|
| 27 |
+
200 val perplexity 651.9868
|
| 28 |
+
200 train 6.185512 (lr=6.4320e-04) (hash(x)=155040610)
|
| 29 |
+
210 train 6.127870 (lr=6.7520e-04) (hash(x)=141273862)
|
| 30 |
+
220 train 6.341401 (lr=7.0720e-04) (hash(x)=165326618)
|
| 31 |
+
230 train 6.084839 (lr=7.3920e-04) (hash(x)=150122120)
|
| 32 |
+
240 train 5.873354 (lr=7.7120e-04) (hash(x)=143024679)
|
| 33 |
+
250 train 5.909622 (lr=8.0320e-04) (hash(x)=130190460)
|
| 34 |
+
260 train 5.988489 (lr=8.3520e-04) (hash(x)=151890219)
|
| 35 |
+
270 train 5.762166 (lr=8.6720e-04) (hash(x)=143685291)
|
| 36 |
+
280 train 6.092319 (lr=8.9920e-04) (hash(x)=137108194)
|
| 37 |
+
290 train 6.251884 (lr=9.3120e-04) (hash(x)=157920866)
|
| 38 |
+
300 val loss 6.0527
|
| 39 |
+
300 val perplexity 425.2684
|
| 40 |
+
300 train 5.970470 (lr=9.6320e-04) (hash(x)=155504036)
|
| 41 |
+
310 train 6.061251 (lr=9.9520e-04) (hash(x)=144551186)
|
| 42 |
+
320 train 6.050638 (lr=1.0272e-03) (hash(x)=161180086)
|
| 43 |
+
330 train 5.821877 (lr=1.0592e-03) (hash(x)=141651471)
|
| 44 |
+
340 train 5.936610 (lr=1.0912e-03) (hash(x)=157490741)
|
| 45 |
+
350 train 5.932688 (lr=1.1232e-03) (hash(x)=137347213)
|
| 46 |
+
360 train 6.248074 (lr=1.1552e-03) (hash(x)=171273659)
|
| 47 |
+
370 train 5.799923 (lr=1.1872e-03) (hash(x)=152118871)
|
| 48 |
+
380 train 5.777218 (lr=1.2192e-03) (hash(x)=161338097)
|
| 49 |
+
390 train 5.865106 (lr=1.2512e-03) (hash(x)=152404537)
|
| 50 |
+
400 val loss 5.7248
|
| 51 |
+
400 val perplexity 306.3653
|
| 52 |
+
400 train 5.542346 (lr=1.2832e-03) (hash(x)=143823248)
|
| 53 |
+
410 train 5.826689 (lr=1.3152e-03) (hash(x)=161686752)
|
| 54 |
+
420 train 5.554622 (lr=1.3472e-03) (hash(x)=155391312)
|
| 55 |
+
430 train 5.478610 (lr=1.3792e-03) (hash(x)=142145507)
|
| 56 |
+
440 train 5.631017 (lr=1.4112e-03) (hash(x)=121931091)
|
| 57 |
+
450 train 5.542422 (lr=1.4432e-03) (hash(x)=156260416)
|
| 58 |
+
460 train 5.681055 (lr=1.4752e-03) (hash(x)=169781623)
|
| 59 |
+
470 train 5.491864 (lr=1.5072e-03) (hash(x)=150131545)
|
| 60 |
+
480 train 5.513600 (lr=1.5392e-03) (hash(x)=150443184)
|
| 61 |
+
490 train 5.529697 (lr=1.5712e-03) (hash(x)=149368198)
|
| 62 |
+
500 val loss 5.5410
|
| 63 |
+
500 val perplexity 254.9404
|
| 64 |
+
500 train 5.415002 (lr=1.6000e-03) (hash(x)=143734685)
|
| 65 |
+
510 train 5.464277 (lr=1.6000e-03) (hash(x)=148943891)
|
| 66 |
+
520 train 5.470827 (lr=1.6000e-03) (hash(x)=149070354)
|
| 67 |
+
530 train 5.442743 (lr=1.6000e-03) (hash(x)=153601219)
|
| 68 |
+
540 train 5.434228 (lr=1.5999e-03) (hash(x)=174970654)
|
| 69 |
+
550 train 5.372306 (lr=1.5999e-03) (hash(x)=160013925)
|
| 70 |
+
560 train 5.221977 (lr=1.5998e-03) (hash(x)=152096988)
|
| 71 |
+
570 train 5.385816 (lr=1.5997e-03) (hash(x)=157203924)
|
| 72 |
+
580 train 5.122974 (lr=1.5997e-03) (hash(x)=138582113)
|
| 73 |
+
590 train 5.134297 (lr=1.5996e-03) (hash(x)=157451775)
|
| 74 |
+
600 val loss 5.3683
|
| 75 |
+
600 val perplexity 214.4945
|
| 76 |
+
600 train 5.057099 (lr=1.5995e-03) (hash(x)=150678249)
|
| 77 |
+
610 train 5.099609 (lr=1.5994e-03) (hash(x)=150248072)
|
| 78 |
+
620 train 5.006677 (lr=1.5992e-03) (hash(x)=148286909)
|
| 79 |
+
630 train 4.983775 (lr=1.5991e-03) (hash(x)=141197178)
|
| 80 |
+
640 train 5.039190 (lr=1.5990e-03) (hash(x)=144988391)
|
| 81 |
+
650 train 4.953558 (lr=1.5988e-03) (hash(x)=149073315)
|
| 82 |
+
660 train 4.898599 (lr=1.5987e-03) (hash(x)=145239943)
|
| 83 |
+
670 train 4.920674 (lr=1.5985e-03) (hash(x)=146657426)
|
| 84 |
+
680 train 5.173290 (lr=1.5983e-03) (hash(x)=142323429)
|
| 85 |
+
690 train 5.177485 (lr=1.5981e-03) (hash(x)=142724342)
|
| 86 |
+
700 val loss 5.2021
|
| 87 |
+
700 val perplexity 181.6552
|
| 88 |
+
700 train 5.132995 (lr=1.5979e-03) (hash(x)=175802021)
|
| 89 |
+
710 train 5.136622 (lr=1.5977e-03) (hash(x)=148902690)
|
| 90 |
+
720 train 5.205983 (lr=1.5975e-03) (hash(x)=155151320)
|
| 91 |
+
730 train 5.063040 (lr=1.5972e-03) (hash(x)=142078914)
|
| 92 |
+
740 train 5.207072 (lr=1.5970e-03) (hash(x)=155634484)
|
| 93 |
+
750 train 5.160653 (lr=1.5967e-03) (hash(x)=171034639)
|
| 94 |
+
760 train 5.134158 (lr=1.5965e-03) (hash(x)=142470148)
|
| 95 |
+
770 train 5.081149 (lr=1.5962e-03) (hash(x)=156024448)
|
| 96 |
+
780 train 5.006321 (lr=1.5959e-03) (hash(x)=151369417)
|
| 97 |
+
790 train 4.945127 (lr=1.5956e-03) (hash(x)=139260056)
|
| 98 |
+
800 val loss 5.0218
|
| 99 |
+
800 val perplexity 151.6873
|
| 100 |
+
800 train 5.110589 (lr=1.5953e-03) (hash(x)=158681215)
|
| 101 |
+
810 train 4.927437 (lr=1.5950e-03) (hash(x)=144884161)
|
| 102 |
+
820 train 4.976940 (lr=1.5947e-03) (hash(x)=146977514)
|
| 103 |
+
830 train 4.885663 (lr=1.5943e-03) (hash(x)=148983636)
|
| 104 |
+
840 train 4.900819 (lr=1.5940e-03) (hash(x)=157824542)
|
| 105 |
+
850 train 4.898818 (lr=1.5936e-03) (hash(x)=152116061)
|
| 106 |
+
860 train 4.979419 (lr=1.5932e-03) (hash(x)=153743703)
|
| 107 |
+
870 train 5.127135 (lr=1.5929e-03) (hash(x)=149913335)
|
| 108 |
+
880 train 4.886528 (lr=1.5925e-03) (hash(x)=151096434)
|
| 109 |
+
890 train 4.853988 (lr=1.5921e-03) (hash(x)=145848702)
|
| 110 |
+
900 val loss 4.9168
|
| 111 |
+
900 val perplexity 136.5624
|
| 112 |
+
900 train 4.855925 (lr=1.5917e-03) (hash(x)=146108145)
|
| 113 |
+
910 train 4.826305 (lr=1.5912e-03) (hash(x)=146903806)
|
| 114 |
+
920 train 4.766856 (lr=1.5908e-03) (hash(x)=149225019)
|
| 115 |
+
930 train 4.708419 (lr=1.5904e-03) (hash(x)=146110422)
|
| 116 |
+
940 train 4.792430 (lr=1.5899e-03) (hash(x)=161333614)
|
| 117 |
+
950 train 4.686063 (lr=1.5895e-03) (hash(x)=147598108)
|
| 118 |
+
960 train 4.840932 (lr=1.5890e-03) (hash(x)=158133101)
|
| 119 |
+
970 train 4.638521 (lr=1.5885e-03) (hash(x)=152199591)
|
| 120 |
+
980 train 4.610433 (lr=1.5880e-03) (hash(x)=152359036)
|
| 121 |
+
990 train 4.676208 (lr=1.5875e-03) (hash(x)=145166335)
|
| 122 |
+
1000 val loss 4.8698
|
| 123 |
+
1000 val perplexity 130.2967
|
| 124 |
+
1000 train 4.575156 (lr=1.5870e-03) (hash(x)=154996086)
|
| 125 |
+
1010 train 4.521421 (lr=1.5865e-03) (hash(x)=149406975)
|
| 126 |
+
1020 train 4.632843 (lr=1.5859e-03) (hash(x)=144618270)
|
| 127 |
+
1030 train 4.479891 (lr=1.5854e-03) (hash(x)=148306536)
|
| 128 |
+
1040 train 4.515413 (lr=1.5848e-03) (hash(x)=151643553)
|
| 129 |
+
1050 train 4.486822 (lr=1.5843e-03) (hash(x)=153396183)
|
| 130 |
+
1060 train 4.479833 (lr=1.5837e-03) (hash(x)=157501787)
|
| 131 |
+
1070 train 4.679214 (lr=1.5831e-03) (hash(x)=153277507)
|
| 132 |
+
1080 train 4.764113 (lr=1.5825e-03) (hash(x)=156232389)
|
| 133 |
+
1090 train 4.708676 (lr=1.5819e-03) (hash(x)=150673143)
|
| 134 |
+
1100 val loss 4.7879
|
| 135 |
+
1100 val perplexity 120.0531
|
| 136 |
+
1100 train 4.764720 (lr=1.5813e-03) (hash(x)=153885445)
|
| 137 |
+
1110 train 4.780037 (lr=1.5807e-03) (hash(x)=143951073)
|
| 138 |
+
1120 train 5.204698 (lr=1.5800e-03) (hash(x)=151626904)
|
| 139 |
+
1130 train 4.754672 (lr=1.5794e-03) (hash(x)=144013074)
|
| 140 |
+
1140 train 4.704170 (lr=1.5787e-03) (hash(x)=149948988)
|
| 141 |
+
1150 train 4.767950 (lr=1.5781e-03) (hash(x)=159666385)
|
| 142 |
+
1160 train 4.747581 (lr=1.5774e-03) (hash(x)=146889587)
|
| 143 |
+
1170 train 4.798748 (lr=1.5767e-03) (hash(x)=151746917)
|
| 144 |
+
1180 train 4.819768 (lr=1.5760e-03) (hash(x)=154396948)
|
| 145 |
+
1190 train 4.773929 (lr=1.5753e-03) (hash(x)=148201222)
|
| 146 |
+
1200 val loss 4.7447
|
| 147 |
+
1200 val perplexity 114.9768
|
| 148 |
+
1200 train 4.761877 (lr=1.5746e-03) (hash(x)=142353087)
|
| 149 |
+
1210 train 4.759091 (lr=1.5738e-03) (hash(x)=146779775)
|
| 150 |
+
1220 train 4.813843 (lr=1.5731e-03) (hash(x)=155864740)
|
| 151 |
+
1230 train 4.870390 (lr=1.5724e-03) (hash(x)=129826485)
|
| 152 |
+
1240 train 4.734400 (lr=1.5716e-03) (hash(x)=108599491)
|
| 153 |
+
1250 train 4.609966 (lr=1.5708e-03) (hash(x)=146491718)
|
| 154 |
+
1260 train 4.682870 (lr=1.5701e-03) (hash(x)=141897382)
|
| 155 |
+
1270 train 4.649850 (lr=1.5693e-03) (hash(x)=144830380)
|
| 156 |
+
1280 train 4.720098 (lr=1.5685e-03) (hash(x)=157677763)
|
| 157 |
+
1290 train 4.548703 (lr=1.5677e-03) (hash(x)=143611746)
|
| 158 |
+
1300 val loss 4.6979
|
| 159 |
+
1300 val perplexity 109.7178
|
| 160 |
+
1300 train 4.578378 (lr=1.5668e-03) (hash(x)=150750353)
|
| 161 |
+
1310 train 4.797231 (lr=1.5660e-03) (hash(x)=152850907)
|
| 162 |
+
1320 train 4.731252 (lr=1.5652e-03) (hash(x)=148575395)
|
| 163 |
+
1330 train 4.472525 (lr=1.5643e-03) (hash(x)=157113001)
|
| 164 |
+
1340 train 4.523620 (lr=1.5635e-03) (hash(x)=137400723)
|
| 165 |
+
1350 train 4.577045 (lr=1.5626e-03) (hash(x)=129849193)
|
| 166 |
+
1360 train 4.576400 (lr=1.5617e-03) (hash(x)=144176797)
|
| 167 |
+
1370 train 4.398354 (lr=1.5608e-03) (hash(x)=144550831)
|
| 168 |
+
1380 train 4.370352 (lr=1.5600e-03) (hash(x)=144171821)
|
| 169 |
+
1390 train 4.316359 (lr=1.5590e-03) (hash(x)=146110449)
|
| 170 |
+
1400 val loss 4.6679
|
| 171 |
+
1400 val perplexity 106.4792
|
| 172 |
+
1400 train 4.398892 (lr=1.5581e-03) (hash(x)=152767913)
|
| 173 |
+
1410 train 4.393617 (lr=1.5572e-03) (hash(x)=148110947)
|
| 174 |
+
1420 train 4.274868 (lr=1.5563e-03) (hash(x)=153477905)
|
| 175 |
+
1430 train 4.170779 (lr=1.5553e-03) (hash(x)=147227598)
|
| 176 |
+
1440 train 4.393749 (lr=1.5544e-03) (hash(x)=146280368)
|
| 177 |
+
1450 train 4.356233 (lr=1.5534e-03) (hash(x)=146531140)
|
| 178 |
+
1460 train 4.197500 (lr=1.5524e-03) (hash(x)=151573873)
|
| 179 |
+
1470 train 4.688970 (lr=1.5514e-03) (hash(x)=155559275)
|
| 180 |
+
1480 train 4.561090 (lr=1.5504e-03) (hash(x)=140584826)
|
| 181 |
+
1490 train 4.556269 (lr=1.5494e-03) (hash(x)=165070637)
|
| 182 |
+
1500 val loss 4.6568
|
| 183 |
+
1500 val perplexity 105.3020
|
| 184 |
+
1500 train 4.676044 (lr=1.5484e-03) (hash(x)=151562048)
|
| 185 |
+
1510 train 4.439283 (lr=1.5474e-03) (hash(x)=147770607)
|
| 186 |
+
1520 train 4.525732 (lr=1.5464e-03) (hash(x)=156486153)
|
| 187 |
+
1530 train 4.493170 (lr=1.5453e-03) (hash(x)=140244564)
|
| 188 |
+
1540 train 4.543811 (lr=1.5443e-03) (hash(x)=151627549)
|
| 189 |
+
1550 train 4.582613 (lr=1.5432e-03) (hash(x)=146001424)
|
| 190 |
+
1560 train 4.663486 (lr=1.5421e-03) (hash(x)=184266264)
|
| 191 |
+
1570 train 4.563400 (lr=1.5411e-03) (hash(x)=145002091)
|
| 192 |
+
1580 train 4.447846 (lr=1.5400e-03) (hash(x)=132216826)
|
| 193 |
+
1590 train 4.625302 (lr=1.5389e-03) (hash(x)=160975703)
|
| 194 |
+
1600 val loss 4.6095
|
| 195 |
+
1600 val perplexity 100.4312
|
| 196 |
+
1600 train 4.768918 (lr=1.5378e-03) (hash(x)=166486165)
|
| 197 |
+
1610 train 4.649122 (lr=1.5366e-03) (hash(x)=149601833)
|
| 198 |
+
1620 train 4.524448 (lr=1.5355e-03) (hash(x)=157815188)
|
| 199 |
+
1630 train 4.545942 (lr=1.5344e-03) (hash(x)=144234679)
|
| 200 |
+
1640 train 4.669394 (lr=1.5332e-03) (hash(x)=160054560)
|
| 201 |
+
1650 train 4.499795 (lr=1.5321e-03) (hash(x)=141061333)
|
| 202 |
+
1660 train 4.612688 (lr=1.5309e-03) (hash(x)=148064219)
|
| 203 |
+
1670 train 4.450078 (lr=1.5297e-03) (hash(x)=162799669)
|
| 204 |
+
1680 train 4.497554 (lr=1.5285e-03) (hash(x)=147474277)
|
| 205 |
+
1690 train 4.570117 (lr=1.5273e-03) (hash(x)=142369299)
|
| 206 |
+
1700 val loss 4.5872
|
| 207 |
+
1700 val perplexity 98.2144
|
| 208 |
+
1700 train 4.347134 (lr=1.5261e-03) (hash(x)=130835396)
|
| 209 |
+
1710 train 4.680794 (lr=1.5249e-03) (hash(x)=153173892)
|
| 210 |
+
1720 train 4.328899 (lr=1.5237e-03) (hash(x)=148451191)
|
| 211 |
+
1730 train 4.446330 (lr=1.5225e-03) (hash(x)=145047239)
|
| 212 |
+
1740 train 4.353974 (lr=1.5212e-03) (hash(x)=147187109)
|
| 213 |
+
1750 train 4.466566 (lr=1.5200e-03) (hash(x)=149493155)
|
| 214 |
+
1760 train 4.421374 (lr=1.5187e-03) (hash(x)=147647531)
|
| 215 |
+
1770 train 4.658438 (lr=1.5174e-03) (hash(x)=153677279)
|
| 216 |
+
1780 train 4.485175 (lr=1.5162e-03) (hash(x)=144314015)
|
| 217 |
+
1790 train 4.497335 (lr=1.5149e-03) (hash(x)=176962883)
|
| 218 |
+
1800 val loss 4.5479
|
| 219 |
+
1800 val perplexity 94.4331
|
| 220 |
+
1800 train 4.589813 (lr=1.5136e-03) (hash(x)=158851816)
|
| 221 |
+
1810 train 4.169217 (lr=1.5123e-03) (hash(x)=175415447)
|
| 222 |
+
1820 train 4.478657 (lr=1.5109e-03) (hash(x)=169829733)
|
| 223 |
+
1830 train 4.457378 (lr=1.5096e-03) (hash(x)=154116106)
|
| 224 |
+
1840 train 4.301032 (lr=1.5083e-03) (hash(x)=150168406)
|
| 225 |
+
1850 train 4.298365 (lr=1.5069e-03) (hash(x)=145782493)
|
| 226 |
+
1860 train 4.277584 (lr=1.5056e-03) (hash(x)=158111664)
|
| 227 |
+
1870 train 4.230505 (lr=1.5042e-03) (hash(x)=154837061)
|
| 228 |
+
1880 train 4.171486 (lr=1.5029e-03) (hash(x)=151363745)
|
| 229 |
+
1890 train 4.289242 (lr=1.5015e-03) (hash(x)=161283557)
|
| 230 |
+
1900 val loss 4.5416
|
| 231 |
+
1900 val perplexity 93.8427
|
| 232 |
+
1900 train 4.545915 (lr=1.5001e-03) (hash(x)=153313879)
|
| 233 |
+
1910 train 4.368105 (lr=1.4987e-03) (hash(x)=152272272)
|
| 234 |
+
1920 train 4.429684 (lr=1.4973e-03) (hash(x)=153648837)
|
| 235 |
+
1930 train 4.535322 (lr=1.4959e-03) (hash(x)=150161694)
|
| 236 |
+
1940 train 4.408885 (lr=1.4944e-03) (hash(x)=151235093)
|
| 237 |
+
1950 train 4.465991 (lr=1.4930e-03) (hash(x)=140582058)
|
| 238 |
+
1960 train 4.410006 (lr=1.4916e-03) (hash(x)=125616059)
|
| 239 |
+
1970 train 4.540657 (lr=1.4901e-03) (hash(x)=154353968)
|
| 240 |
+
1980 train 4.551030 (lr=1.4886e-03) (hash(x)=156063143)
|
| 241 |
+
1990 train 4.569766 (lr=1.4872e-03) (hash(x)=160927289)
|
| 242 |
+
2000 val loss 4.4888
|
| 243 |
+
2000 val perplexity 89.0169
|
| 244 |
+
2000 train 4.478562 (lr=1.4857e-03) (hash(x)=158245023)
|
| 245 |
+
2010 train 4.530198 (lr=1.4842e-03) (hash(x)=157096661)
|
| 246 |
+
2020 train 4.759308 (lr=1.4827e-03) (hash(x)=144994302)
|
| 247 |
+
2030 train 4.443616 (lr=1.4812e-03) (hash(x)=145742929)
|
| 248 |
+
2040 train 4.458299 (lr=1.4797e-03) (hash(x)=156958528)
|
| 249 |
+
2050 train 4.961064 (lr=1.4782e-03) (hash(x)=135313020)
|
| 250 |
+
2060 train 4.608280 (lr=1.4767e-03) (hash(x)=147309332)
|
| 251 |
+
2070 train 4.398744 (lr=1.4751e-03) (hash(x)=161720962)
|
| 252 |
+
2080 train 4.581003 (lr=1.4736e-03) (hash(x)=167204793)
|
| 253 |
+
2090 train 4.482615 (lr=1.4720e-03) (hash(x)=141325510)
|
| 254 |
+
2100 val loss 4.4758
|
| 255 |
+
2100 val perplexity 87.8612
|
| 256 |
+
2100 train 4.308885 (lr=1.4704e-03) (hash(x)=157204896)
|
| 257 |
+
2110 train 4.265119 (lr=1.4689e-03) (hash(x)=143077993)
|
| 258 |
+
2120 train 4.461938 (lr=1.4673e-03) (hash(x)=159032689)
|
| 259 |
+
2130 train 4.346468 (lr=1.4657e-03) (hash(x)=149513855)
|
| 260 |
+
2140 train 4.264449 (lr=1.4641e-03) (hash(x)=151678267)
|
| 261 |
+
2150 train 4.366063 (lr=1.4625e-03) (hash(x)=141309246)
|
| 262 |
+
2160 train 4.459674 (lr=1.4609e-03) (hash(x)=153935732)
|
| 263 |
+
2170 train 4.357332 (lr=1.4593e-03) (hash(x)=150668875)
|
| 264 |
+
2180 train 4.364537 (lr=1.4576e-03) (hash(x)=142033123)
|
| 265 |
+
2190 train 4.404786 (lr=1.4560e-03) (hash(x)=157015026)
|
| 266 |
+
2200 val loss 4.4633
|
| 267 |
+
2200 val perplexity 86.7719
|
| 268 |
+
2200 train 4.286598 (lr=1.4543e-03) (hash(x)=137541932)
|
| 269 |
+
2210 train 4.206499 (lr=1.4527e-03) (hash(x)=144424504)
|
| 270 |
+
2220 train 4.132062 (lr=1.4510e-03) (hash(x)=151015810)
|
| 271 |
+
2230 train 4.201881 (lr=1.4493e-03) (hash(x)=160707806)
|
| 272 |
+
2240 train 4.213866 (lr=1.4476e-03) (hash(x)=151874110)
|
| 273 |
+
2250 train 4.186008 (lr=1.4460e-03) (hash(x)=157341469)
|
| 274 |
+
2260 train 4.008515 (lr=1.4443e-03) (hash(x)=144563224)
|
| 275 |
+
2270 train 4.164164 (lr=1.4426e-03) (hash(x)=144878459)
|
| 276 |
+
2280 train 4.225405 (lr=1.4408e-03) (hash(x)=158331565)
|
| 277 |
+
2290 train 4.266317 (lr=1.4391e-03) (hash(x)=146875132)
|
| 278 |
+
2300 val loss 4.4551
|
| 279 |
+
2300 val perplexity 86.0660
|
| 280 |
+
2300 train 4.395679 (lr=1.4374e-03) (hash(x)=150149692)
|
| 281 |
+
2310 train 4.392414 (lr=1.4356e-03) (hash(x)=141206538)
|
| 282 |
+
2320 train 4.442695 (lr=1.4339e-03) (hash(x)=136219115)
|
| 283 |
+
2330 train 4.462418 (lr=1.4321e-03) (hash(x)=148496500)
|
| 284 |
+
2340 train 4.452066 (lr=1.4304e-03) (hash(x)=161388511)
|
| 285 |
+
2350 train 4.302850 (lr=1.4286e-03) (hash(x)=149433185)
|
| 286 |
+
2360 train 4.513514 (lr=1.4268e-03) (hash(x)=154659203)
|
| 287 |
+
2370 train 4.504569 (lr=1.4250e-03) (hash(x)=145696996)
|
| 288 |
+
2380 train 4.313843 (lr=1.4232e-03) (hash(x)=139915095)
|
| 289 |
+
2390 train 4.441415 (lr=1.4214e-03) (hash(x)=150567584)
|
| 290 |
+
2400 val loss 4.4359
|
| 291 |
+
2400 val perplexity 84.4303
|
| 292 |
+
2400 train 4.358191 (lr=1.4196e-03) (hash(x)=151730720)
|
| 293 |
+
2410 train 4.392675 (lr=1.4178e-03) (hash(x)=153136544)
|
| 294 |
+
2420 train 4.352077 (lr=1.4160e-03) (hash(x)=151004677)
|
| 295 |
+
2430 train 4.373085 (lr=1.4141e-03) (hash(x)=167118859)
|
| 296 |
+
2440 train 4.391276 (lr=1.4123e-03) (hash(x)=145433453)
|
| 297 |
+
2450 train 4.421721 (lr=1.4105e-03) (hash(x)=150913293)
|
| 298 |
+
2460 train 4.386439 (lr=1.4086e-03) (hash(x)=145674639)
|
| 299 |
+
2470 train 4.488542 (lr=1.4067e-03) (hash(x)=151022749)
|
| 300 |
+
2480 train 4.337260 (lr=1.4049e-03) (hash(x)=136621037)
|
| 301 |
+
2490 train 4.388394 (lr=1.4030e-03) (hash(x)=158100672)
|
| 302 |
+
2500 val loss 4.4006
|
| 303 |
+
2500 val perplexity 81.5001
|
| 304 |
+
2500 train 4.407022 (lr=1.4011e-03) (hash(x)=143406752)
|
| 305 |
+
2510 train 4.334888 (lr=1.3992e-03) (hash(x)=142664084)
|
| 306 |
+
2520 train 4.389374 (lr=1.3973e-03) (hash(x)=132174378)
|
| 307 |
+
2530 train 4.396482 (lr=1.3954e-03) (hash(x)=140760293)
|
| 308 |
+
2540 train 4.341993 (lr=1.3935e-03) (hash(x)=154863398)
|
| 309 |
+
2550 train 4.286408 (lr=1.3915e-03) (hash(x)=153042049)
|
| 310 |
+
2560 train 4.222927 (lr=1.3896e-03) (hash(x)=145339170)
|
| 311 |
+
2570 train 4.374972 (lr=1.3877e-03) (hash(x)=157656357)
|
| 312 |
+
2580 train 4.356512 (lr=1.3857e-03) (hash(x)=147899462)
|
| 313 |
+
2590 train 4.340437 (lr=1.3838e-03) (hash(x)=142812892)
|
| 314 |
+
2600 val loss 4.4148
|
| 315 |
+
2600 val perplexity 82.6684
|
| 316 |
+
2600 train 4.291786 (lr=1.3818e-03) (hash(x)=157272496)
|
| 317 |
+
2610 train 4.080462 (lr=1.3798e-03) (hash(x)=148923594)
|
| 318 |
+
2620 train 4.008453 (lr=1.3778e-03) (hash(x)=164654807)
|
| 319 |
+
2630 train 4.200662 (lr=1.3759e-03) (hash(x)=136419327)
|
| 320 |
+
2640 train 4.165953 (lr=1.3739e-03) (hash(x)=153420840)
|
| 321 |
+
2650 train 3.997154 (lr=1.3719e-03) (hash(x)=153693827)
|
| 322 |
+
2660 train 4.156643 (lr=1.3699e-03) (hash(x)=145574165)
|
| 323 |
+
2670 train 4.207622 (lr=1.3679e-03) (hash(x)=153894843)
|
| 324 |
+
2680 train 4.050721 (lr=1.3658e-03) (hash(x)=132234446)
|
| 325 |
+
2690 train 4.129662 (lr=1.3638e-03) (hash(x)=153430212)
|
| 326 |
+
2700 val loss 4.4035
|
| 327 |
+
2700 val perplexity 81.7395
|
| 328 |
+
2700 train 4.306398 (lr=1.3618e-03) (hash(x)=155342327)
|
| 329 |
+
2710 train 4.310942 (lr=1.3597e-03) (hash(x)=145797023)
|
| 330 |
+
2720 train 4.461793 (lr=1.3577e-03) (hash(x)=149220870)
|
| 331 |
+
2730 train 4.378531 (lr=1.3556e-03) (hash(x)=134069562)
|
| 332 |
+
2740 train 4.375551 (lr=1.3536e-03) (hash(x)=141560499)
|
| 333 |
+
2750 train 4.383879 (lr=1.3515e-03) (hash(x)=146000524)
|
| 334 |
+
2760 train 4.283324 (lr=1.3494e-03) (hash(x)=164710665)
|
| 335 |
+
2770 train 4.177800 (lr=1.3473e-03) (hash(x)=151199094)
|
| 336 |
+
2780 train 4.370714 (lr=1.3453e-03) (hash(x)=138625404)
|
| 337 |
+
2790 train 4.624011 (lr=1.3432e-03) (hash(x)=162766112)
|
| 338 |
+
2800 val loss 4.3711
|
| 339 |
+
2800 val perplexity 79.1271
|
| 340 |
+
2800 train 4.334440 (lr=1.3411e-03) (hash(x)=140626679)
|
| 341 |
+
2810 train 4.426750 (lr=1.3389e-03) (hash(x)=144248544)
|
| 342 |
+
2820 train 4.334456 (lr=1.3368e-03) (hash(x)=139378481)
|
| 343 |
+
2830 train 4.266303 (lr=1.3347e-03) (hash(x)=150173403)
|
| 344 |
+
2840 train 4.557656 (lr=1.3326e-03) (hash(x)=160168705)
|
| 345 |
+
2850 train 4.361000 (lr=1.3304e-03) (hash(x)=149480059)
|
| 346 |
+
2860 train 4.403877 (lr=1.3283e-03) (hash(x)=155559096)
|
| 347 |
+
2870 train 4.329821 (lr=1.3262e-03) (hash(x)=158825683)
|
| 348 |
+
2880 train 4.509315 (lr=1.3240e-03) (hash(x)=152129048)
|
| 349 |
+
2890 train 4.173676 (lr=1.3218e-03) (hash(x)=157866544)
|
| 350 |
+
2900 val loss 4.3501
|
| 351 |
+
2900 val perplexity 77.4855
|
| 352 |
+
2900 train 4.303938 (lr=1.3197e-03) (hash(x)=144953350)
|
| 353 |
+
2910 train 4.510077 (lr=1.3175e-03) (hash(x)=154103497)
|
| 354 |
+
2920 train 4.228721 (lr=1.3153e-03) (hash(x)=144467854)
|
| 355 |
+
2930 train 4.153110 (lr=1.3131e-03) (hash(x)=153784048)
|
| 356 |
+
2940 train 4.451362 (lr=1.3109e-03) (hash(x)=154774534)
|
| 357 |
+
2950 train 4.310647 (lr=1.3087e-03) (hash(x)=143988507)
|
| 358 |
+
2960 train 4.189782 (lr=1.3065e-03) (hash(x)=159552857)
|
| 359 |
+
2970 train 4.479873 (lr=1.3043e-03) (hash(x)=175539144)
|
| 360 |
+
2980 train 4.367302 (lr=1.3021e-03) (hash(x)=158172686)
|
| 361 |
+
2990 train 4.237266 (lr=1.2999e-03) (hash(x)=147553039)
|
| 362 |
+
3000 val loss 4.3623
|
| 363 |
+
3000 val perplexity 78.4352
|
| 364 |
+
3000 train 4.169420 (lr=1.2976e-03) (hash(x)=172449837)
|
| 365 |
+
3010 train 4.059199 (lr=1.2954e-03) (hash(x)=153285123)
|
| 366 |
+
3020 train 4.232521 (lr=1.2932e-03) (hash(x)=145307252)
|
| 367 |
+
3030 train 4.291190 (lr=1.2909e-03) (hash(x)=147739766)
|
| 368 |
+
3040 train 4.006360 (lr=1.2887e-03) (hash(x)=154414400)
|
| 369 |
+
3050 train 4.086408 (lr=1.2864e-03) (hash(x)=150696487)
|
| 370 |
+
3060 train 4.097227 (lr=1.2841e-03) (hash(x)=154543441)
|
| 371 |
+
3070 train 3.878911 (lr=1.2819e-03) (hash(x)=170733242)
|
| 372 |
+
3080 train 4.238189 (lr=1.2796e-03) (hash(x)=161914669)
|
| 373 |
+
3090 train 4.116949 (lr=1.2773e-03) (hash(x)=156125491)
|
| 374 |
+
3100 val loss 4.3764
|
| 375 |
+
3100 val perplexity 79.5494
|
| 376 |
+
3100 train 4.004492 (lr=1.2750e-03) (hash(x)=141710086)
|
| 377 |
+
3110 train 4.326313 (lr=1.2727e-03) (hash(x)=154547635)
|
| 378 |
+
3120 train 4.165356 (lr=1.2704e-03) (hash(x)=151747171)
|
| 379 |
+
3130 train 4.444594 (lr=1.2681e-03) (hash(x)=160311353)
|
| 380 |
+
3140 train 4.560120 (lr=1.2658e-03) (hash(x)=157233821)
|
| 381 |
+
3150 train 4.367349 (lr=1.2635e-03) (hash(x)=153016810)
|
| 382 |
+
3160 train 4.342836 (lr=1.2612e-03) (hash(x)=157289875)
|
| 383 |
+
3170 train 4.344308 (lr=1.2588e-03) (hash(x)=157459484)
|
| 384 |
+
3180 train 4.269902 (lr=1.2565e-03) (hash(x)=162037435)
|
| 385 |
+
3190 train 4.366226 (lr=1.2542e-03) (hash(x)=159360169)
|
| 386 |
+
3200 val loss 4.3234
|
| 387 |
+
3200 val perplexity 75.4459
|
| 388 |
+
3200 train 4.249028 (lr=1.2518e-03) (hash(x)=151299772)
|
| 389 |
+
3210 train 4.478005 (lr=1.2495e-03) (hash(x)=183865364)
|
| 390 |
+
3220 train 4.220253 (lr=1.2471e-03) (hash(x)=139622592)
|
| 391 |
+
3230 train 4.173029 (lr=1.2447e-03) (hash(x)=147102655)
|
| 392 |
+
3240 train 4.228549 (lr=1.2424e-03) (hash(x)=161870696)
|
| 393 |
+
3250 train 4.386982 (lr=1.2400e-03) (hash(x)=152692231)
|
| 394 |
+
3260 train 4.126943 (lr=1.2376e-03) (hash(x)=149990134)
|
| 395 |
+
3270 train 4.102612 (lr=1.2352e-03) (hash(x)=134848432)
|
| 396 |
+
3280 train 4.164372 (lr=1.2329e-03) (hash(x)=138519418)
|
| 397 |
+
3290 train 4.301248 (lr=1.2305e-03) (hash(x)=139301249)
|
| 398 |
+
3300 val loss 4.3291
|
| 399 |
+
3300 val perplexity 75.8753
|
| 400 |
+
3300 train 4.136382 (lr=1.2281e-03) (hash(x)=146473110)
|
| 401 |
+
3310 train 4.200676 (lr=1.2257e-03) (hash(x)=144833685)
|
| 402 |
+
3320 train 4.105077 (lr=1.2233e-03) (hash(x)=148953545)
|
| 403 |
+
3330 train 4.336022 (lr=1.2208e-03) (hash(x)=161302371)
|
| 404 |
+
3340 train 4.266917 (lr=1.2184e-03) (hash(x)=144215411)
|
| 405 |
+
3350 train 4.460447 (lr=1.2160e-03) (hash(x)=157713664)
|
| 406 |
+
3360 train 4.319351 (lr=1.2136e-03) (hash(x)=150813928)
|
| 407 |
+
3370 train 4.290013 (lr=1.2111e-03) (hash(x)=150889463)
|
| 408 |
+
3380 train 4.340569 (lr=1.2087e-03) (hash(x)=156631928)
|
| 409 |
+
3390 train 4.372313 (lr=1.2063e-03) (hash(x)=136001579)
|
| 410 |
+
3400 val loss 4.3047
|
| 411 |
+
3400 val perplexity 74.0480
|
| 412 |
+
3400 train 4.451314 (lr=1.2038e-03) (hash(x)=153954157)
|
| 413 |
+
3410 train 4.228926 (lr=1.2014e-03) (hash(x)=150012477)
|
| 414 |
+
3420 train 4.591652 (lr=1.1989e-03) (hash(x)=160878899)
|
| 415 |
+
3430 train 4.628926 (lr=1.1964e-03) (hash(x)=128131106)
|
| 416 |
+
3440 train 4.542327 (lr=1.1940e-03) (hash(x)=149611866)
|
| 417 |
+
3450 train 4.182538 (lr=1.1915e-03) (hash(x)=166942460)
|
| 418 |
+
3460 train 4.334873 (lr=1.1890e-03) (hash(x)=150498414)
|
| 419 |
+
3470 train 4.481339 (lr=1.1866e-03) (hash(x)=144342279)
|
| 420 |
+
3480 train 4.310098 (lr=1.1841e-03) (hash(x)=148891764)
|
| 421 |
+
3490 train 4.276525 (lr=1.1816e-03) (hash(x)=157308188)
|
| 422 |
+
3500 val loss 4.2948
|
| 423 |
+
3500 val perplexity 73.3210
|
| 424 |
+
3500 train 4.191946 (lr=1.1791e-03) (hash(x)=153717336)
|
| 425 |
+
3510 train 4.216006 (lr=1.1766e-03) (hash(x)=156083924)
|
| 426 |
+
3520 train 4.196649 (lr=1.1741e-03) (hash(x)=144234966)
|
| 427 |
+
3530 train 4.293768 (lr=1.1716e-03) (hash(x)=150184381)
|
| 428 |
+
3540 train 4.182832 (lr=1.1691e-03) (hash(x)=143011198)
|
| 429 |
+
3550 train 4.316899 (lr=1.1666e-03) (hash(x)=148764613)
|
| 430 |
+
3560 train 4.082632 (lr=1.1641e-03) (hash(x)=150625329)
|
| 431 |
+
3570 train 4.192494 (lr=1.1615e-03) (hash(x)=143981302)
|
| 432 |
+
3580 train 4.248079 (lr=1.1590e-03) (hash(x)=154989703)
|
| 433 |
+
3590 train 4.374173 (lr=1.1565e-03) (hash(x)=146602526)
|
| 434 |
+
3600 val loss 4.2907
|
| 435 |
+
3600 val perplexity 73.0205
|
| 436 |
+
3600 train 4.075150 (lr=1.1539e-03) (hash(x)=144965161)
|
| 437 |
+
3610 train 4.062934 (lr=1.1514e-03) (hash(x)=159452243)
|
| 438 |
+
3620 train 4.055789 (lr=1.1489e-03) (hash(x)=144904300)
|
| 439 |
+
3630 train 3.966146 (lr=1.1463e-03) (hash(x)=127790212)
|
| 440 |
+
3640 train 4.208603 (lr=1.1438e-03) (hash(x)=150863158)
|
| 441 |
+
3650 train 4.169408 (lr=1.1412e-03) (hash(x)=145691635)
|
| 442 |
+
3660 train 4.148298 (lr=1.1387e-03) (hash(x)=150631264)
|
| 443 |
+
3670 train 4.130219 (lr=1.1361e-03) (hash(x)=148646259)
|
| 444 |
+
3680 train 4.098463 (lr=1.1335e-03) (hash(x)=139317386)
|
| 445 |
+
3690 train 4.200757 (lr=1.1310e-03) (hash(x)=142206916)
|
| 446 |
+
3700 val loss 4.3036
|
| 447 |
+
3700 val perplexity 73.9631
|
| 448 |
+
3700 train 4.207170 (lr=1.1284e-03) (hash(x)=125969741)
|
| 449 |
+
3710 train 4.054093 (lr=1.1258e-03) (hash(x)=157183915)
|
| 450 |
+
3720 train 4.044124 (lr=1.1232e-03) (hash(x)=150434369)
|
| 451 |
+
3730 train 4.239077 (lr=1.1207e-03) (hash(x)=160911722)
|
| 452 |
+
3740 train 4.135977 (lr=1.1181e-03) (hash(x)=163306921)
|
| 453 |
+
3750 train 4.245700 (lr=1.1155e-03) (hash(x)=149156876)
|
| 454 |
+
3760 train 4.380814 (lr=1.1129e-03) (hash(x)=156015970)
|
| 455 |
+
3770 train 4.333178 (lr=1.1103e-03) (hash(x)=148222322)
|
| 456 |
+
3780 train 4.437116 (lr=1.1077e-03) (hash(x)=172040174)
|
| 457 |
+
3790 train 4.341127 (lr=1.1051e-03) (hash(x)=151593070)
|
| 458 |
+
3800 val loss 4.2733
|
| 459 |
+
3800 val perplexity 71.7614
|
| 460 |
+
3800 train 4.090341 (lr=1.1025e-03) (hash(x)=155070487)
|
| 461 |
+
3810 train 4.286554 (lr=1.0999e-03) (hash(x)=137073164)
|
| 462 |
+
3820 train 4.182597 (lr=1.0973e-03) (hash(x)=147761510)
|
| 463 |
+
3830 train 4.108144 (lr=1.0947e-03) (hash(x)=154763021)
|
| 464 |
+
3840 train 4.155719 (lr=1.0920e-03) (hash(x)=149622435)
|
| 465 |
+
3850 train 4.262024 (lr=1.0894e-03) (hash(x)=150779423)
|
| 466 |
+
3860 train 4.230407 (lr=1.0868e-03) (hash(x)=139445120)
|
| 467 |
+
3870 train 4.214289 (lr=1.0842e-03) (hash(x)=151884947)
|
| 468 |
+
3880 train 4.223768 (lr=1.0815e-03) (hash(x)=139795201)
|
| 469 |
+
3890 train 4.259877 (lr=1.0789e-03) (hash(x)=155589956)
|
| 470 |
+
3900 val loss 4.2648
|
| 471 |
+
3900 val perplexity 71.1531
|
| 472 |
+
3900 train 4.189574 (lr=1.0763e-03) (hash(x)=149444644)
|
| 473 |
+
3910 train 4.174083 (lr=1.0736e-03) (hash(x)=148538323)
|
| 474 |
+
3920 train 4.298960 (lr=1.0710e-03) (hash(x)=144026925)
|
| 475 |
+
3930 train 4.184155 (lr=1.0683e-03) (hash(x)=155311200)
|
| 476 |
+
3940 train 4.165025 (lr=1.0657e-03) (hash(x)=142410034)
|
| 477 |
+
3950 train 4.145735 (lr=1.0630e-03) (hash(x)=145986075)
|
| 478 |
+
3960 train 4.048140 (lr=1.0604e-03) (hash(x)=156197753)
|
| 479 |
+
3970 train 4.199309 (lr=1.0577e-03) (hash(x)=146981564)
|
| 480 |
+
3980 train 4.505698 (lr=1.0551e-03) (hash(x)=145361976)
|
| 481 |
+
3990 train 4.235699 (lr=1.0524e-03) (hash(x)=149344475)
|
| 482 |
+
4000 val loss 4.2603
|
| 483 |
+
4000 val perplexity 70.8284
|
| 484 |
+
4000 train 4.119695 (lr=1.0497e-03) (hash(x)=151663033)
|
| 485 |
+
4010 train 4.003411 (lr=1.0471e-03) (hash(x)=140915499)
|
| 486 |
+
4020 train 4.223140 (lr=1.0444e-03) (hash(x)=159979134)
|
| 487 |
+
4030 train 4.146472 (lr=1.0417e-03) (hash(x)=163081433)
|
| 488 |
+
4040 train 4.033156 (lr=1.0391e-03) (hash(x)=144890231)
|
| 489 |
+
4050 train 4.187871 (lr=1.0364e-03) (hash(x)=138242368)
|
| 490 |
+
4060 train 4.092355 (lr=1.0337e-03) (hash(x)=144438406)
|
| 491 |
+
4070 train 3.972995 (lr=1.0310e-03) (hash(x)=159294906)
|
| 492 |
+
4080 train 4.032986 (lr=1.0284e-03) (hash(x)=143676301)
|
| 493 |
+
4090 train 4.259402 (lr=1.0257e-03) (hash(x)=147875296)
|
| 494 |
+
4100 val loss 4.2758
|
| 495 |
+
4100 val perplexity 71.9386
|
| 496 |
+
4100 train 4.321385 (lr=1.0230e-03) (hash(x)=143688282)
|
| 497 |
+
4110 train 4.094481 (lr=1.0203e-03) (hash(x)=150086777)
|
| 498 |
+
4120 train 4.045703 (lr=1.0176e-03) (hash(x)=154624391)
|
| 499 |
+
4130 train 4.227767 (lr=1.0149e-03) (hash(x)=141163032)
|
| 500 |
+
4140 train 4.249865 (lr=1.0122e-03) (hash(x)=151038180)
|
| 501 |
+
4150 train 4.342282 (lr=1.0095e-03) (hash(x)=144718421)
|
| 502 |
+
4160 train 4.245982 (lr=1.0068e-03) (hash(x)=154277459)
|
| 503 |
+
4170 train 4.410131 (lr=1.0041e-03) (hash(x)=143765173)
|
| 504 |
+
4180 train 4.271582 (lr=1.0014e-03) (hash(x)=161013425)
|
| 505 |
+
4190 train 4.234535 (lr=9.9872e-04) (hash(x)=161666854)
|
| 506 |
+
4200 val loss 4.2399
|
| 507 |
+
4200 val perplexity 69.3994
|
| 508 |
+
4200 train 4.147298 (lr=9.9602e-04) (hash(x)=163361651)
|
| 509 |
+
4210 train 4.481609 (lr=9.9331e-04) (hash(x)=153491528)
|
| 510 |
+
4220 train 4.275284 (lr=9.9060e-04) (hash(x)=164410385)
|
| 511 |
+
4230 train 4.233717 (lr=9.8789e-04) (hash(x)=175191816)
|
| 512 |
+
4240 train 4.096622 (lr=9.8518e-04) (hash(x)=133924818)
|
| 513 |
+
4250 train 4.320632 (lr=9.8247e-04) (hash(x)=152932845)
|
| 514 |
+
4260 train 4.194882 (lr=9.7975e-04) (hash(x)=141987318)
|
| 515 |
+
4270 train 4.291714 (lr=9.7704e-04) (hash(x)=142521279)
|
| 516 |
+
4280 train 4.158590 (lr=9.7432e-04) (hash(x)=147707669)
|
| 517 |
+
4290 train 4.206725 (lr=9.7160e-04) (hash(x)=152245539)
|
| 518 |
+
4300 val loss 4.2259
|
| 519 |
+
4300 val perplexity 68.4342
|
| 520 |
+
4300 train 4.101810 (lr=9.6888e-04) (hash(x)=153619361)
|
| 521 |
+
4310 train 4.311889 (lr=9.6616e-04) (hash(x)=142614473)
|
| 522 |
+
4320 train 4.143874 (lr=9.6344e-04) (hash(x)=142689858)
|
| 523 |
+
4330 train 4.160812 (lr=9.6071e-04) (hash(x)=140837891)
|
| 524 |
+
4340 train 4.149849 (lr=9.5799e-04) (hash(x)=131790760)
|
| 525 |
+
4350 train 4.305469 (lr=9.5526e-04) (hash(x)=147186292)
|
| 526 |
+
4360 train 4.121147 (lr=9.5253e-04) (hash(x)=148140562)
|
| 527 |
+
4370 train 4.228862 (lr=9.4980e-04) (hash(x)=156409913)
|
| 528 |
+
4380 train 4.142556 (lr=9.4708e-04) (hash(x)=145126034)
|
| 529 |
+
4390 train 4.092573 (lr=9.4435e-04) (hash(x)=147368423)
|
| 530 |
+
4400 val loss 4.2313
|
| 531 |
+
4400 val perplexity 68.8075
|
| 532 |
+
4400 train 4.566331 (lr=9.4161e-04) (hash(x)=168527064)
|
| 533 |
+
4410 train 4.084151 (lr=9.3888e-04) (hash(x)=150152773)
|
| 534 |
+
4420 train 4.176479 (lr=9.3615e-04) (hash(x)=155472304)
|
| 535 |
+
4430 train 4.103662 (lr=9.3342e-04) (hash(x)=147299265)
|
| 536 |
+
4440 train 4.058784 (lr=9.3068e-04) (hash(x)=140659522)
|
| 537 |
+
4450 train 4.127119 (lr=9.2795e-04) (hash(x)=147169111)
|
| 538 |
+
4460 train 4.197248 (lr=9.2521e-04) (hash(x)=144098557)
|
| 539 |
+
4470 train 3.949067 (lr=9.2247e-04) (hash(x)=161957507)
|
| 540 |
+
4480 train 3.980549 (lr=9.1974e-04) (hash(x)=154064204)
|
| 541 |
+
4490 train 4.115980 (lr=9.1700e-04) (hash(x)=153999958)
|
| 542 |
+
4500 val loss 4.2432
|
| 543 |
+
4500 val perplexity 69.6283
|
| 544 |
+
4500 train 4.261584 (lr=9.1426e-04) (hash(x)=125588037)
|
| 545 |
+
4510 train 4.072170 (lr=9.1152e-04) (hash(x)=142522186)
|
| 546 |
+
4520 train 3.913814 (lr=9.0878e-04) (hash(x)=152736893)
|
| 547 |
+
4530 train 4.145648 (lr=9.0604e-04) (hash(x)=148091275)
|
| 548 |
+
4540 train 4.266252 (lr=9.0330e-04) (hash(x)=147663019)
|
| 549 |
+
4550 train 4.337443 (lr=9.0056e-04) (hash(x)=151491857)
|
| 550 |
+
4560 train 4.227212 (lr=8.9782e-04) (hash(x)=161757513)
|
| 551 |
+
4570 train 4.212447 (lr=8.9508e-04) (hash(x)=165448260)
|
| 552 |
+
4580 train 4.347905 (lr=8.9234e-04) (hash(x)=151620292)
|
| 553 |
+
4590 train 4.432113 (lr=8.8960e-04) (hash(x)=161877852)
|
| 554 |
+
4600 val loss 4.2045
|
| 555 |
+
4600 val perplexity 66.9851
|
| 556 |
+
4600 train 4.179208 (lr=8.8685e-04) (hash(x)=143710941)
|
| 557 |
+
4610 train 4.281816 (lr=8.8411e-04) (hash(x)=152244871)
|
| 558 |
+
4620 train 4.229055 (lr=8.8137e-04) (hash(x)=161268167)
|
| 559 |
+
4630 train 4.217800 (lr=8.7863e-04) (hash(x)=153904677)
|
| 560 |
+
4640 train 4.176593 (lr=8.7589e-04) (hash(x)=152593758)
|
| 561 |
+
4650 train 4.328807 (lr=8.7315e-04) (hash(x)=159047122)
|
| 562 |
+
4660 train 4.396957 (lr=8.7040e-04) (hash(x)=167370244)
|
| 563 |
+
4670 train 4.167033 (lr=8.6766e-04) (hash(x)=140357684)
|
| 564 |
+
4680 train 4.321832 (lr=8.6492e-04) (hash(x)=140547853)
|
| 565 |
+
4690 train 4.502204 (lr=8.6218e-04) (hash(x)=143000949)
|
| 566 |
+
4700 val loss 4.1974
|
| 567 |
+
4700 val perplexity 66.5150
|
| 568 |
+
4700 train 4.136136 (lr=8.5944e-04) (hash(x)=150952742)
|
| 569 |
+
4710 train 4.180377 (lr=8.5670e-04) (hash(x)=157964406)
|
| 570 |
+
4720 train 4.073139 (lr=8.5396e-04) (hash(x)=147653608)
|
| 571 |
+
4730 train 4.148001 (lr=8.5122e-04) (hash(x)=165545764)
|
| 572 |
+
4740 train 4.129364 (lr=8.4848e-04) (hash(x)=146744631)
|
| 573 |
+
4750 train 4.216397 (lr=8.4574e-04) (hash(x)=153635164)
|
| 574 |
+
4760 train 4.266573 (lr=8.4300e-04) (hash(x)=153217508)
|
| 575 |
+
4770 train 4.300474 (lr=8.4026e-04) (hash(x)=169622743)
|
| 576 |
+
4780 train 4.139132 (lr=8.3753e-04) (hash(x)=138018297)
|
| 577 |
+
4790 train 4.010749 (lr=8.3479e-04) (hash(x)=156067303)
|
| 578 |
+
4800 val loss 4.1974
|
| 579 |
+
4800 val perplexity 66.5157
|
| 580 |
+
4800 train 4.177917 (lr=8.3205e-04) (hash(x)=145323659)
|
| 581 |
+
4810 train 4.061078 (lr=8.2932e-04) (hash(x)=152587772)
|
| 582 |
+
4820 train 4.288577 (lr=8.2658e-04) (hash(x)=148481485)
|
| 583 |
+
4830 train 4.063444 (lr=8.2385e-04) (hash(x)=154219664)
|
| 584 |
+
4840 train 3.943269 (lr=8.2112e-04) (hash(x)=156853645)
|
| 585 |
+
4850 train 4.032576 (lr=8.1839e-04) (hash(x)=152329702)
|
| 586 |
+
4860 train 4.023046 (lr=8.1565e-04) (hash(x)=136684779)
|
| 587 |
+
4870 train 4.098526 (lr=8.1292e-04) (hash(x)=143260367)
|
| 588 |
+
4880 train 4.052032 (lr=8.1020e-04) (hash(x)=150910947)
|
| 589 |
+
4890 train 4.073494 (lr=8.0747e-04) (hash(x)=179249925)
|
| 590 |
+
4900 val loss 4.2033
|
| 591 |
+
4900 val perplexity 66.9095
|
| 592 |
+
4900 train 4.226156 (lr=8.0474e-04) (hash(x)=153151397)
|
| 593 |
+
4910 train 4.180113 (lr=8.0201e-04) (hash(x)=144101891)
|
| 594 |
+
4920 train 4.068473 (lr=7.9929e-04) (hash(x)=144994952)
|
| 595 |
+
4930 train 4.357684 (lr=7.9656e-04) (hash(x)=155390878)
|
| 596 |
+
4940 train 4.141274 (lr=7.9384e-04) (hash(x)=141359221)
|
| 597 |
+
4950 train 4.046164 (lr=7.9112e-04) (hash(x)=151570011)
|
| 598 |
+
4960 train 4.258111 (lr=7.8840e-04) (hash(x)=146918855)
|
| 599 |
+
4970 train 4.196177 (lr=7.8568e-04) (hash(x)=148647362)
|
| 600 |
+
4980 train 4.148799 (lr=7.8296e-04) (hash(x)=159753562)
|
| 601 |
+
4990 train 4.101168 (lr=7.8025e-04) (hash(x)=147683447)
|
| 602 |
+
5000 val loss 4.1947
|
| 603 |
+
5000 val perplexity 66.3354
|
| 604 |
+
5000 train 4.243451 (lr=7.7753e-04) (hash(x)=143182059)
|
| 605 |
+
5010 train 4.047309 (lr=7.7482e-04) (hash(x)=138657407)
|
| 606 |
+
5020 train 4.154434 (lr=7.7211e-04) (hash(x)=151830497)
|
| 607 |
+
5030 train 4.155403 (lr=7.6940e-04) (hash(x)=147727694)
|
| 608 |
+
5040 train 3.997037 (lr=7.6669e-04) (hash(x)=151957014)
|
| 609 |
+
5050 train 4.262687 (lr=7.6398e-04) (hash(x)=147828693)
|
| 610 |
+
5060 train 4.329477 (lr=7.6128e-04) (hash(x)=158589700)
|
| 611 |
+
5070 train 4.199682 (lr=7.5858e-04) (hash(x)=155662163)
|
| 612 |
+
5080 train 4.315152 (lr=7.5587e-04) (hash(x)=157797383)
|
| 613 |
+
5090 train 4.180853 (lr=7.5317e-04) (hash(x)=153848957)
|
| 614 |
+
5100 val loss 4.1798
|
| 615 |
+
5100 val perplexity 65.3550
|
| 616 |
+
5100 train 4.129765 (lr=7.5048e-04) (hash(x)=170083586)
|
| 617 |
+
5110 train 4.050482 (lr=7.4778e-04) (hash(x)=153800138)
|
| 618 |
+
5120 train 4.156245 (lr=7.4509e-04) (hash(x)=153526228)
|
| 619 |
+
5130 train 4.160551 (lr=7.4239e-04) (hash(x)=158650342)
|
| 620 |
+
5140 train 4.155452 (lr=7.3970e-04) (hash(x)=153163034)
|
| 621 |
+
5150 train 4.145086 (lr=7.3701e-04) (hash(x)=155281294)
|
| 622 |
+
5160 train 4.131432 (lr=7.3433e-04) (hash(x)=147731627)
|
| 623 |
+
5170 train 4.110987 (lr=7.3164e-04) (hash(x)=146388976)
|
| 624 |
+
5180 train 4.323846 (lr=7.2896e-04) (hash(x)=140323065)
|
| 625 |
+
5190 train 4.224886 (lr=7.2628e-04) (hash(x)=150406523)
|
| 626 |
+
5200 val loss 4.1739
|
| 627 |
+
5200 val perplexity 64.9655
|
| 628 |
+
5200 train 4.028774 (lr=7.2361e-04) (hash(x)=149363919)
|
| 629 |
+
5210 train 4.174520 (lr=7.2093e-04) (hash(x)=164390214)
|
| 630 |
+
5220 train 4.127351 (lr=7.1826e-04) (hash(x)=153652984)
|
| 631 |
+
5230 train 4.102473 (lr=7.1559e-04) (hash(x)=139542770)
|
| 632 |
+
5240 train 3.983514 (lr=7.1292e-04) (hash(x)=140115288)
|
| 633 |
+
5250 train 4.111379 (lr=7.1025e-04) (hash(x)=142158900)
|
| 634 |
+
5260 train 4.036632 (lr=7.0759e-04) (hash(x)=156019449)
|
| 635 |
+
5270 train 4.145755 (lr=7.0493e-04) (hash(x)=150776850)
|
| 636 |
+
5280 train 4.105478 (lr=7.0227e-04) (hash(x)=151358692)
|
| 637 |
+
5290 train 4.068083 (lr=6.9962e-04) (hash(x)=137112863)
|
| 638 |
+
5300 val loss 4.1712
|
| 639 |
+
5300 val perplexity 64.7923
|
| 640 |
+
5300 train 4.000528 (lr=6.9696e-04) (hash(x)=152033784)
|
| 641 |
+
5310 train 4.046142 (lr=6.9431e-04) (hash(x)=147785712)
|
| 642 |
+
5320 train 4.177117 (lr=6.9166e-04) (hash(x)=156426339)
|
| 643 |
+
5330 train 4.128112 (lr=6.8902e-04) (hash(x)=161907693)
|
| 644 |
+
5340 train 4.197877 (lr=6.8638e-04) (hash(x)=156414094)
|
| 645 |
+
5350 train 4.217412 (lr=6.8374e-04) (hash(x)=141712428)
|
| 646 |
+
5360 train 4.170516 (lr=6.8110e-04) (hash(x)=156873601)
|
| 647 |
+
5370 train 4.150231 (lr=6.7847e-04) (hash(x)=149863781)
|
| 648 |
+
5380 train 4.151899 (lr=6.7584e-04) (hash(x)=148183971)
|
| 649 |
+
5390 train 4.112661 (lr=6.7321e-04) (hash(x)=151542334)
|
| 650 |
+
5400 val loss 4.1455
|
| 651 |
+
5400 val perplexity 63.1507
|
| 652 |
+
5400 train 4.391319 (lr=6.7059e-04) (hash(x)=154614289)
|
| 653 |
+
5410 train 4.132742 (lr=6.6796e-04) (hash(x)=169124671)
|
| 654 |
+
5420 train 4.159767 (lr=6.6534e-04) (hash(x)=159963738)
|
| 655 |
+
5430 train 4.120434 (lr=6.6273e-04) (hash(x)=155162691)
|
| 656 |
+
5440 train 4.155738 (lr=6.6012e-04) (hash(x)=135981908)
|
| 657 |
+
5450 train 4.238271 (lr=6.5751e-04) (hash(x)=145055580)
|
| 658 |
+
5460 train 4.097481 (lr=6.5490e-04) (hash(x)=150367825)
|
| 659 |
+
5470 train 4.188226 (lr=6.5230e-04) (hash(x)=151034173)
|
| 660 |
+
5480 train 4.097782 (lr=6.4970e-04) (hash(x)=155581766)
|
| 661 |
+
5490 train 4.126717 (lr=6.4710e-04) (hash(x)=136973993)
|
| 662 |
+
5500 val loss 4.1405
|
| 663 |
+
5500 val perplexity 62.8314
|
| 664 |
+
5500 train 4.296653 (lr=6.4451e-04) (hash(x)=157745174)
|
| 665 |
+
5510 train 4.249143 (lr=6.4192e-04) (hash(x)=144628894)
|
| 666 |
+
5520 train 4.134798 (lr=6.3934e-04) (hash(x)=135056684)
|
| 667 |
+
5530 train 4.121049 (lr=6.3675e-04) (hash(x)=143418640)
|
| 668 |
+
5540 train 4.101325 (lr=6.3417e-04) (hash(x)=144464984)
|
| 669 |
+
5550 train 4.306342 (lr=6.3160e-04) (hash(x)=155888745)
|
| 670 |
+
5560 train 3.965852 (lr=6.2903e-04) (hash(x)=149122683)
|
| 671 |
+
5570 train 4.009026 (lr=6.2646e-04) (hash(x)=154573954)
|
| 672 |
+
5580 train 4.113039 (lr=6.2390e-04) (hash(x)=149339361)
|
| 673 |
+
5590 train 4.013528 (lr=6.2134e-04) (hash(x)=154738453)
|
| 674 |
+
5600 val loss 4.1444
|
| 675 |
+
5600 val perplexity 63.0819
|
| 676 |
+
5600 train 4.127007 (lr=6.1878e-04) (hash(x)=147693222)
|
| 677 |
+
5610 train 3.892473 (lr=6.1623e-04) (hash(x)=142140192)
|
| 678 |
+
5620 train 4.034860 (lr=6.1368e-04) (hash(x)=148677209)
|
| 679 |
+
5630 train 4.101720 (lr=6.1113e-04) (hash(x)=143495554)
|
| 680 |
+
5640 train 4.184603 (lr=6.0859e-04) (hash(x)=153202964)
|
| 681 |
+
5650 train 4.110519 (lr=6.0605e-04) (hash(x)=168724867)
|
| 682 |
+
5660 train 4.073341 (lr=6.0352e-04) (hash(x)=142816746)
|
| 683 |
+
5670 train 4.196189 (lr=6.0099e-04) (hash(x)=164119551)
|
| 684 |
+
5680 train 4.067638 (lr=5.9846e-04) (hash(x)=157239121)
|
| 685 |
+
5690 train 4.340961 (lr=5.9594e-04) (hash(x)=144662329)
|
| 686 |
+
5700 val loss 4.1286
|
| 687 |
+
5700 val perplexity 62.0893
|
| 688 |
+
5700 train 4.060287 (lr=5.9342e-04) (hash(x)=149784627)
|
| 689 |
+
5710 train 4.032685 (lr=5.9091e-04) (hash(x)=152821162)
|
| 690 |
+
5720 train 4.245067 (lr=5.8840e-04) (hash(x)=158497530)
|
| 691 |
+
5730 train 4.234516 (lr=5.8590e-04) (hash(x)=154583914)
|
| 692 |
+
5740 train 4.054588 (lr=5.8340e-04) (hash(x)=142027172)
|
| 693 |
+
5750 train 4.299486 (lr=5.8090e-04) (hash(x)=119227402)
|
| 694 |
+
5760 train 4.145566 (lr=5.7841e-04) (hash(x)=153248187)
|
| 695 |
+
5770 train 4.017678 (lr=5.7592e-04) (hash(x)=147951994)
|
| 696 |
+
5780 train 4.028544 (lr=5.7344e-04) (hash(x)=138935284)
|
| 697 |
+
5790 train 4.121736 (lr=5.7096e-04) (hash(x)=151786681)
|
| 698 |
+
5800 val loss 4.1437
|
| 699 |
+
5800 val perplexity 63.0349
|
| 700 |
+
5800 train 4.161643 (lr=5.6849e-04) (hash(x)=158620729)
|
| 701 |
+
5810 train 4.098246 (lr=5.6602e-04) (hash(x)=178115789)
|
| 702 |
+
5820 train 4.026398 (lr=5.6355e-04) (hash(x)=149092790)
|
| 703 |
+
5830 train 4.203728 (lr=5.6109e-04) (hash(x)=148269833)
|
| 704 |
+
5840 train 4.133464 (lr=5.5864e-04) (hash(x)=163714738)
|
| 705 |
+
5850 train 4.114130 (lr=5.5618e-04) (hash(x)=144111890)
|
| 706 |
+
5860 train 4.074070 (lr=5.5374e-04) (hash(x)=170702475)
|
| 707 |
+
5870 train 4.019765 (lr=5.5130e-04) (hash(x)=155970835)
|
| 708 |
+
5880 train 4.024945 (lr=5.4886e-04) (hash(x)=146695463)
|
| 709 |
+
5890 train 4.089661 (lr=5.4643e-04) (hash(x)=151603187)
|
| 710 |
+
5900 val loss 4.1251
|
| 711 |
+
5900 val perplexity 61.8761
|
| 712 |
+
5900 train 4.110221 (lr=5.4400e-04) (hash(x)=159763910)
|
| 713 |
+
5910 train 4.143404 (lr=5.4158e-04) (hash(x)=149555230)
|
| 714 |
+
5920 train 4.153804 (lr=5.3916e-04) (hash(x)=138048333)
|
| 715 |
+
5930 train 4.048625 (lr=5.3675e-04) (hash(x)=148668256)
|
| 716 |
+
5940 train 4.190791 (lr=5.3434e-04) (hash(x)=148352543)
|
| 717 |
+
5950 train 4.205280 (lr=5.3194e-04) (hash(x)=163457488)
|
| 718 |
+
5960 train 4.276459 (lr=5.2954e-04) (hash(x)=155306804)
|
| 719 |
+
5970 train 4.122219 (lr=5.2715e-04) (hash(x)=146576143)
|
| 720 |
+
5980 train 4.137489 (lr=5.2476e-04) (hash(x)=144668956)
|
| 721 |
+
5990 train 4.097038 (lr=5.2238e-04) (hash(x)=156098617)
|
| 722 |
+
6000 val loss 4.1088
|
| 723 |
+
6000 val perplexity 60.8706
|
| 724 |
+
6000 train 4.073006 (lr=5.2000e-04) (hash(x)=147640561)
|
| 725 |
+
6010 train 4.144456 (lr=5.1763e-04) (hash(x)=161223074)
|
| 726 |
+
6020 train 4.129782 (lr=5.1526e-04) (hash(x)=156308454)
|
| 727 |
+
6030 train 4.109142 (lr=5.1290e-04) (hash(x)=142553975)
|
| 728 |
+
6040 train 4.074658 (lr=5.1054e-04) (hash(x)=142039829)
|
| 729 |
+
6050 train 4.146600 (lr=5.0819e-04) (hash(x)=156329296)
|
| 730 |
+
6060 train 4.076528 (lr=5.0585e-04) (hash(x)=148505537)
|
| 731 |
+
6070 train 3.968623 (lr=5.0351e-04) (hash(x)=151801272)
|
| 732 |
+
6080 train 4.054537 (lr=5.0117e-04) (hash(x)=159908287)
|
| 733 |
+
6090 train 4.044281 (lr=4.9885e-04) (hash(x)=148714721)
|
| 734 |
+
6100 val loss 4.1038
|
| 735 |
+
6100 val perplexity 60.5726
|
| 736 |
+
6100 train 4.109980 (lr=4.9652e-04) (hash(x)=156613394)
|
| 737 |
+
6110 train 3.967459 (lr=4.9420e-04) (hash(x)=143286705)
|
| 738 |
+
6120 train 4.178342 (lr=4.9189e-04) (hash(x)=150191141)
|
| 739 |
+
6130 train 4.055149 (lr=4.8959e-04) (hash(x)=149855624)
|
| 740 |
+
6140 train 4.037532 (lr=4.8729e-04) (hash(x)=157312372)
|
| 741 |
+
6150 train 4.163954 (lr=4.8499e-04) (hash(x)=148262730)
|
| 742 |
+
6160 train 4.080248 (lr=4.8270e-04) (hash(x)=147032785)
|
| 743 |
+
6170 train 4.004763 (lr=4.8042e-04) (hash(x)=161213064)
|
| 744 |
+
6180 train 3.880142 (lr=4.7814e-04) (hash(x)=144538373)
|
| 745 |
+
6190 train 3.936374 (lr=4.7587e-04) (hash(x)=144688493)
|
| 746 |
+
6200 val loss 4.1019
|
| 747 |
+
6200 val perplexity 60.4531
|
| 748 |
+
6200 train 4.010356 (lr=4.7360e-04) (hash(x)=186221290)
|
| 749 |
+
6210 train 4.014867 (lr=4.7134e-04) (hash(x)=139529352)
|
| 750 |
+
6220 train 4.179955 (lr=4.6909e-04) (hash(x)=138081469)
|
| 751 |
+
6230 train 4.053678 (lr=4.6684e-04) (hash(x)=152979409)
|
| 752 |
+
6240 train 4.036180 (lr=4.6460e-04) (hash(x)=157848424)
|
| 753 |
+
6250 train 3.924152 (lr=4.6236e-04) (hash(x)=150770915)
|
| 754 |
+
6260 train 4.024043 (lr=4.6013e-04) (hash(x)=153769379)
|
| 755 |
+
6270 train 3.955381 (lr=4.5790e-04) (hash(x)=153318361)
|
| 756 |
+
6280 train 3.948435 (lr=4.5569e-04) (hash(x)=143366327)
|
| 757 |
+
6290 train 4.116281 (lr=4.5347e-04) (hash(x)=160684845)
|
| 758 |
+
6300 val loss 4.0853
|
| 759 |
+
6300 val perplexity 59.4595
|
| 760 |
+
6300 train 4.001014 (lr=4.5127e-04) (hash(x)=152081419)
|
| 761 |
+
6310 train 3.960897 (lr=4.4907e-04) (hash(x)=146626797)
|
| 762 |
+
6320 train 4.147958 (lr=4.4688e-04) (hash(x)=155291923)
|
| 763 |
+
6330 train 4.022735 (lr=4.4469e-04) (hash(x)=140920951)
|
| 764 |
+
6340 train 4.100725 (lr=4.4251e-04) (hash(x)=146642359)
|
| 765 |
+
6350 train 4.075447 (lr=4.4033e-04) (hash(x)=160486550)
|
| 766 |
+
6360 train 4.031275 (lr=4.3817e-04) (hash(x)=151833082)
|
| 767 |
+
6370 train 4.011332 (lr=4.3600e-04) (hash(x)=124740362)
|
| 768 |
+
6380 train 4.168252 (lr=4.3385e-04) (hash(x)=153952434)
|
| 769 |
+
6390 train 4.202826 (lr=4.3170e-04) (hash(x)=145864314)
|
| 770 |
+
6400 val loss 4.0898
|
| 771 |
+
6400 val perplexity 59.7285
|
| 772 |
+
6400 train 4.089182 (lr=4.2956e-04) (hash(x)=154808349)
|
| 773 |
+
6410 train 4.061103 (lr=4.2742e-04) (hash(x)=155037739)
|
| 774 |
+
6420 train 3.996108 (lr=4.2529e-04) (hash(x)=151155588)
|
| 775 |
+
6430 train 3.893414 (lr=4.2317e-04) (hash(x)=146548556)
|
| 776 |
+
6440 train 4.061685 (lr=4.2105e-04) (hash(x)=152706474)
|
| 777 |
+
6450 train 4.047606 (lr=4.1895e-04) (hash(x)=154207794)
|
| 778 |
+
6460 train 3.924859 (lr=4.1684e-04) (hash(x)=141590515)
|
| 779 |
+
6470 train 3.967111 (lr=4.1475e-04) (hash(x)=157673109)
|
| 780 |
+
6480 train 3.971589 (lr=4.1266e-04) (hash(x)=155842980)
|
| 781 |
+
6490 train 4.053762 (lr=4.1058e-04) (hash(x)=143595736)
|
| 782 |
+
6500 val loss 4.0874
|
| 783 |
+
6500 val perplexity 59.5838
|
| 784 |
+
6500 train 4.010974 (lr=4.0850e-04) (hash(x)=159437208)
|
| 785 |
+
6510 train 4.016948 (lr=4.0643e-04) (hash(x)=142631317)
|
| 786 |
+
6520 train 3.745801 (lr=4.0437e-04) (hash(x)=139009211)
|
| 787 |
+
6530 train 4.101014 (lr=4.0231e-04) (hash(x)=145451137)
|
| 788 |
+
6540 train 4.052980 (lr=4.0027e-04) (hash(x)=163532779)
|
| 789 |
+
6550 train 3.960567 (lr=3.9823e-04) (hash(x)=158084674)
|
| 790 |
+
6560 train 3.936872 (lr=3.9619e-04) (hash(x)=142422592)
|
| 791 |
+
6570 train 3.854061 (lr=3.9416e-04) (hash(x)=141089289)
|
| 792 |
+
6580 train 3.953637 (lr=3.9214e-04) (hash(x)=139712979)
|
| 793 |
+
6590 train 3.856697 (lr=3.9013e-04) (hash(x)=145833805)
|
| 794 |
+
6600 val loss 4.0865
|
| 795 |
+
6600 val perplexity 59.5312
|
| 796 |
+
6600 train 3.934482 (lr=3.8813e-04) (hash(x)=157933074)
|
| 797 |
+
6610 train 3.861314 (lr=3.8613e-04) (hash(x)=142534769)
|
| 798 |
+
6620 train 3.911716 (lr=3.8414e-04) (hash(x)=138456044)
|
| 799 |
+
6630 train 4.038729 (lr=3.8215e-04) (hash(x)=145111052)
|
| 800 |
+
6640 train 3.995534 (lr=3.8017e-04) (hash(x)=166954515)
|
| 801 |
+
6650 train 3.961848 (lr=3.7820e-04) (hash(x)=146889543)
|
| 802 |
+
6660 train 3.996976 (lr=3.7624e-04) (hash(x)=143253726)
|
| 803 |
+
6670 train 3.913163 (lr=3.7429e-04) (hash(x)=144349844)
|
| 804 |
+
6680 train 4.098059 (lr=3.7234e-04) (hash(x)=139911928)
|
| 805 |
+
6690 train 4.283506 (lr=3.7040e-04) (hash(x)=143135862)
|
| 806 |
+
6700 val loss 4.0738
|
| 807 |
+
6700 val perplexity 58.7791
|
| 808 |
+
6700 train 4.009466 (lr=3.6847e-04) (hash(x)=161560240)
|
| 809 |
+
6710 train 4.095942 (lr=3.6654e-04) (hash(x)=150437730)
|
| 810 |
+
6720 train 4.197622 (lr=3.6462e-04) (hash(x)=153035304)
|
| 811 |
+
6730 train 3.991101 (lr=3.6271e-04) (hash(x)=139323796)
|
| 812 |
+
6740 train 3.990134 (lr=3.6081e-04) (hash(x)=167437923)
|
| 813 |
+
6750 train 3.960217 (lr=3.5891e-04) (hash(x)=143814596)
|
| 814 |
+
6760 train 4.020265 (lr=3.5702e-04) (hash(x)=143755031)
|
| 815 |
+
6770 train 3.975055 (lr=3.5514e-04) (hash(x)=142014038)
|
| 816 |
+
6780 train 4.031541 (lr=3.5327e-04) (hash(x)=148465062)
|
| 817 |
+
6790 train 4.067742 (lr=3.5140e-04) (hash(x)=154656877)
|
| 818 |
+
6800 val loss 4.0715
|
| 819 |
+
6800 val perplexity 58.6463
|
| 820 |
+
6800 train 4.176820 (lr=3.4955e-04) (hash(x)=155424292)
|
| 821 |
+
6810 train 3.807037 (lr=3.4770e-04) (hash(x)=147358081)
|
| 822 |
+
6820 train 3.923870 (lr=3.4585e-04) (hash(x)=145387291)
|
| 823 |
+
6830 train 3.873622 (lr=3.4402e-04) (hash(x)=146334068)
|
| 824 |
+
6840 train 3.957843 (lr=3.4219e-04) (hash(x)=139563766)
|
| 825 |
+
6850 train 3.977593 (lr=3.4037e-04) (hash(x)=139095691)
|
| 826 |
+
6860 train 3.924802 (lr=3.3856e-04) (hash(x)=142093999)
|
| 827 |
+
6870 train 4.035909 (lr=3.3676e-04) (hash(x)=148598823)
|
| 828 |
+
6880 train 4.117771 (lr=3.3496e-04) (hash(x)=146486085)
|
| 829 |
+
6890 train 3.902429 (lr=3.3318e-04) (hash(x)=165683212)
|
| 830 |
+
6900 val loss 4.0728
|
| 831 |
+
6900 val perplexity 58.7210
|
| 832 |
+
6900 train 4.106917 (lr=3.3140e-04) (hash(x)=148561470)
|
| 833 |
+
6910 train 3.793993 (lr=3.2962e-04) (hash(x)=136352432)
|
| 834 |
+
6920 train 4.176646 (lr=3.2786e-04) (hash(x)=147640094)
|
| 835 |
+
6930 train 4.061341 (lr=3.2611e-04) (hash(x)=152343827)
|
| 836 |
+
6940 train 4.044687 (lr=3.2436e-04) (hash(x)=158787971)
|
| 837 |
+
6950 train 4.316038 (lr=3.2262e-04) (hash(x)=178133125)
|
| 838 |
+
6960 train 4.104434 (lr=3.2089e-04) (hash(x)=167302853)
|
| 839 |
+
6970 train 4.047144 (lr=3.1916e-04) (hash(x)=143729435)
|
| 840 |
+
6980 train 4.137383 (lr=3.1745e-04) (hash(x)=135857879)
|
| 841 |
+
6990 train 4.084717 (lr=3.1574e-04) (hash(x)=155384510)
|
| 842 |
+
7000 val loss 4.0596
|
| 843 |
+
7000 val perplexity 57.9497
|
| 844 |
+
7000 train 4.023391 (lr=3.1404e-04) (hash(x)=141527450)
|
| 845 |
+
7010 train 4.069504 (lr=3.1235e-04) (hash(x)=148648498)
|
| 846 |
+
7020 train 4.001482 (lr=3.1067e-04) (hash(x)=148073842)
|
| 847 |
+
7030 train 4.129344 (lr=3.0899e-04) (hash(x)=160771614)
|
| 848 |
+
7040 train 3.906679 (lr=3.0733e-04) (hash(x)=148361330)
|
| 849 |
+
7050 train 3.883871 (lr=3.0567e-04) (hash(x)=151212224)
|
| 850 |
+
7060 train 4.074808 (lr=3.0402e-04) (hash(x)=155925366)
|
| 851 |
+
7070 train 3.936165 (lr=3.0238e-04) (hash(x)=149830576)
|
| 852 |
+
7080 train 3.904384 (lr=3.0075e-04) (hash(x)=144849934)
|
| 853 |
+
7090 train 3.993180 (lr=2.9912e-04) (hash(x)=150997807)
|
| 854 |
+
7100 val loss 4.0543
|
| 855 |
+
7100 val perplexity 57.6421
|
| 856 |
+
7100 train 4.033813 (lr=2.9751e-04) (hash(x)=151066339)
|
| 857 |
+
7110 train 3.934469 (lr=2.9590e-04) (hash(x)=147185781)
|
| 858 |
+
7120 train 3.980731 (lr=2.9430e-04) (hash(x)=141765575)
|
| 859 |
+
7130 train 3.993372 (lr=2.9271e-04) (hash(x)=144204513)
|
| 860 |
+
7140 train 3.822274 (lr=2.9113e-04) (hash(x)=149326253)
|
| 861 |
+
7150 train 3.983820 (lr=2.8956e-04) (hash(x)=150409811)
|
| 862 |
+
7160 train 3.874244 (lr=2.8799e-04) (hash(x)=144790348)
|
| 863 |
+
7170 train 3.999096 (lr=2.8644e-04) (hash(x)=150500939)
|
| 864 |
+
7180 train 3.814944 (lr=2.8489e-04) (hash(x)=143552103)
|
| 865 |
+
7190 train 3.859600 (lr=2.8335e-04) (hash(x)=157471075)
|
| 866 |
+
7200 val loss 4.0579
|
| 867 |
+
7200 val perplexity 57.8537
|
| 868 |
+
7200 train 3.837742 (lr=2.8182e-04) (hash(x)=155231264)
|
| 869 |
+
7210 train 3.927071 (lr=2.8030e-04) (hash(x)=150350401)
|
| 870 |
+
7220 train 3.945467 (lr=2.7878e-04) (hash(x)=151952594)
|
| 871 |
+
7230 train 4.030033 (lr=2.7728e-04) (hash(x)=145381804)
|
| 872 |
+
7240 train 3.914976 (lr=2.7578e-04) (hash(x)=142651222)
|
| 873 |
+
7250 train 4.022504 (lr=2.7430e-04) (hash(x)=136115279)
|
| 874 |
+
7260 train 4.120305 (lr=2.7282e-04) (hash(x)=154536751)
|
| 875 |
+
7270 train 4.075540 (lr=2.7135e-04) (hash(x)=148883836)
|
| 876 |
+
7280 train 3.928825 (lr=2.6989e-04) (hash(x)=150606754)
|
| 877 |
+
7290 train 4.042625 (lr=2.6844e-04) (hash(x)=165845807)
|
| 878 |
+
7300 val loss 4.0463
|
| 879 |
+
7300 val perplexity 57.1863
|
| 880 |
+
7300 train 4.116895 (lr=2.6700e-04) (hash(x)=150281149)
|
| 881 |
+
7310 train 4.068338 (lr=2.6556e-04) (hash(x)=159929281)
|
| 882 |
+
7320 train 3.897439 (lr=2.6414e-04) (hash(x)=143074269)
|
| 883 |
+
7330 train 4.057128 (lr=2.6272e-04) (hash(x)=147369269)
|
| 884 |
+
7340 train 4.111042 (lr=2.6132e-04) (hash(x)=139286601)
|
| 885 |
+
7350 train 4.008691 (lr=2.5992e-04) (hash(x)=145263048)
|
| 886 |
+
7360 train 3.858882 (lr=2.5853e-04) (hash(x)=144626817)
|
| 887 |
+
7370 train 4.062269 (lr=2.5715e-04) (hash(x)=168989813)
|
| 888 |
+
7380 train 4.039978 (lr=2.5578e-04) (hash(x)=144790656)
|
| 889 |
+
7390 train 3.844556 (lr=2.5442e-04) (hash(x)=141279761)
|
| 890 |
+
7400 val loss 4.0432
|
| 891 |
+
7400 val perplexity 57.0093
|
| 892 |
+
7400 train 3.981868 (lr=2.5306e-04) (hash(x)=148421717)
|
| 893 |
+
7410 train 3.977128 (lr=2.5172e-04) (hash(x)=141241548)
|
| 894 |
+
7420 train 4.042267 (lr=2.5038e-04) (hash(x)=162434228)
|
| 895 |
+
7430 train 3.993505 (lr=2.4906e-04) (hash(x)=156312086)
|
| 896 |
+
7440 train 3.950574 (lr=2.4774e-04) (hash(x)=139803064)
|
| 897 |
+
7450 train 3.649232 (lr=2.4644e-04) (hash(x)=156361394)
|
| 898 |
+
7460 train 3.959004 (lr=2.4514e-04) (hash(x)=141142183)
|
| 899 |
+
7470 train 3.788096 (lr=2.4385e-04) (hash(x)=156701683)
|
| 900 |
+
7480 train 3.962706 (lr=2.4257e-04) (hash(x)=148549917)
|
| 901 |
+
7490 train 3.843719 (lr=2.4130e-04) (hash(x)=143002119)
|
| 902 |
+
7500 val loss 4.0448
|
| 903 |
+
7500 val perplexity 57.0980
|
| 904 |
+
7500 train 3.851630 (lr=2.4004e-04) (hash(x)=146921118)
|
| 905 |
+
7510 train 3.858370 (lr=2.3879e-04) (hash(x)=148592146)
|
| 906 |
+
7520 train 4.004126 (lr=2.3754e-04) (hash(x)=148456120)
|
| 907 |
+
7530 train 4.158412 (lr=2.3631e-04) (hash(x)=163865945)
|
| 908 |
+
7540 train 4.051578 (lr=2.3509e-04) (hash(x)=160753039)
|
| 909 |
+
7550 train 4.062814 (lr=2.3387e-04) (hash(x)=150275989)
|
| 910 |
+
7560 train 4.086408 (lr=2.3267e-04) (hash(x)=141749735)
|
| 911 |
+
7570 train 4.054147 (lr=2.3147e-04) (hash(x)=148449999)
|
| 912 |
+
7580 train 3.932919 (lr=2.3029e-04) (hash(x)=139153889)
|
| 913 |
+
7590 train 4.048338 (lr=2.2911e-04) (hash(x)=147418540)
|
| 914 |
+
7600 val loss 4.0320
|
| 915 |
+
7600 val perplexity 56.3763
|
| 916 |
+
7600 train 4.069643 (lr=2.2794e-04) (hash(x)=150660048)
|
| 917 |
+
7610 train 4.052121 (lr=2.2678e-04) (hash(x)=155369080)
|
| 918 |
+
7620 train 3.953581 (lr=2.2564e-04) (hash(x)=151926309)
|
| 919 |
+
7630 train 4.030202 (lr=2.2450e-04) (hash(x)=149549080)
|
| 920 |
+
7640 train 3.921366 (lr=2.2337e-04) (hash(x)=140642882)
|
| 921 |
+
7650 train 4.196265 (lr=2.2225e-04) (hash(x)=140218502)
|
| 922 |
+
7660 train 4.031204 (lr=2.2114e-04) (hash(x)=153198276)
|
| 923 |
+
7670 train 3.888023 (lr=2.2004e-04) (hash(x)=150706960)
|
| 924 |
+
7680 train 4.032162 (lr=2.1894e-04) (hash(x)=152025509)
|
| 925 |
+
7690 train 3.819033 (lr=2.1786e-04) (hash(x)=147288976)
|
| 926 |
+
7700 val loss 4.0332
|
| 927 |
+
7700 val perplexity 56.4415
|
| 928 |
+
7700 train 3.930063 (lr=2.1679e-04) (hash(x)=148059852)
|
| 929 |
+
7710 train 3.749929 (lr=2.1573e-04) (hash(x)=158443334)
|
| 930 |
+
7720 train 3.871289 (lr=2.1468e-04) (hash(x)=143467085)
|
| 931 |
+
7730 train 3.815771 (lr=2.1363e-04) (hash(x)=138439550)
|
| 932 |
+
7740 train 3.946394 (lr=2.1260e-04) (hash(x)=145878152)
|
| 933 |
+
7750 train 3.798604 (lr=2.1158e-04) (hash(x)=136874128)
|
| 934 |
+
7760 train 3.824095 (lr=2.1056e-04) (hash(x)=148856154)
|
| 935 |
+
7770 train 3.850093 (lr=2.0956e-04) (hash(x)=146982119)
|
| 936 |
+
7780 train 3.946401 (lr=2.0856e-04) (hash(x)=159846779)
|
| 937 |
+
7790 train 3.634008 (lr=2.0758e-04) (hash(x)=141501838)
|
| 938 |
+
7800 val loss 4.0367
|
| 939 |
+
7800 val perplexity 56.6369
|
| 940 |
+
7800 train 3.763717 (lr=2.0660e-04) (hash(x)=148331002)
|
| 941 |
+
7810 train 4.068491 (lr=2.0564e-04) (hash(x)=150692304)
|
| 942 |
+
7820 train 3.939309 (lr=2.0468e-04) (hash(x)=156841183)
|
| 943 |
+
7830 train 3.980107 (lr=2.0373e-04) (hash(x)=139594008)
|
| 944 |
+
7840 train 3.919498 (lr=2.0280e-04) (hash(x)=149700138)
|
| 945 |
+
7850 train 3.941700 (lr=2.0187e-04) (hash(x)=149327044)
|
| 946 |
+
7860 train 4.108171 (lr=2.0096e-04) (hash(x)=148315418)
|
| 947 |
+
7870 train 4.050933 (lr=2.0005e-04) (hash(x)=153431778)
|
| 948 |
+
7880 train 3.894650 (lr=1.9915e-04) (hash(x)=145049799)
|
| 949 |
+
7890 train 4.020423 (lr=1.9827e-04) (hash(x)=150265096)
|
| 950 |
+
7900 val loss 4.0240
|
| 951 |
+
7900 val perplexity 55.9238
|
| 952 |
+
7900 train 3.848468 (lr=1.9739e-04) (hash(x)=164923883)
|
| 953 |
+
7910 train 3.908226 (lr=1.9652e-04) (hash(x)=139315738)
|
| 954 |
+
7920 train 3.959571 (lr=1.9566e-04) (hash(x)=153031394)
|
| 955 |
+
7930 train 3.749157 (lr=1.9482e-04) (hash(x)=148835859)
|
| 956 |
+
7940 train 3.879015 (lr=1.9398e-04) (hash(x)=146875217)
|
| 957 |
+
7950 train 3.956004 (lr=1.9315e-04) (hash(x)=151003885)
|
| 958 |
+
7960 train 3.869174 (lr=1.9233e-04) (hash(x)=141885471)
|
| 959 |
+
7970 train 4.071434 (lr=1.9153e-04) (hash(x)=150541583)
|
| 960 |
+
7980 train 3.769432 (lr=1.9073e-04) (hash(x)=138626492)
|
| 961 |
+
7990 train 3.952919 (lr=1.8994e-04) (hash(x)=149935635)
|
| 962 |
+
8000 val loss 4.0243
|
| 963 |
+
8000 val perplexity 55.9404
|
| 964 |
+
8000 train 3.922093 (lr=1.8917e-04) (hash(x)=143545384)
|
| 965 |
+
8010 train 3.781529 (lr=1.8840e-04) (hash(x)=144689366)
|
| 966 |
+
8020 train 3.957091 (lr=1.8764e-04) (hash(x)=151299532)
|
| 967 |
+
8030 train 3.903553 (lr=1.8689e-04) (hash(x)=131300239)
|
| 968 |
+
8040 train 3.801501 (lr=1.8616e-04) (hash(x)=146715955)
|
| 969 |
+
8050 train 3.727899 (lr=1.8543e-04) (hash(x)=135376656)
|
| 970 |
+
8060 train 3.811551 (lr=1.8471e-04) (hash(x)=141991433)
|
| 971 |
+
8070 train 3.768016 (lr=1.8400e-04) (hash(x)=140260574)
|
| 972 |
+
8080 train 3.733690 (lr=1.8331e-04) (hash(x)=151492896)
|
| 973 |
+
8090 train 3.940285 (lr=1.8262e-04) (hash(x)=143333635)
|
| 974 |
+
8100 val loss 4.0283
|
| 975 |
+
8100 val perplexity 56.1633
|
| 976 |
+
8100 train 3.825931 (lr=1.8194e-04) (hash(x)=160686959)
|
| 977 |
+
8110 train 3.826274 (lr=1.8128e-04) (hash(x)=141145704)
|
| 978 |
+
8120 train 4.064416 (lr=1.8062e-04) (hash(x)=146967795)
|
| 979 |
+
8130 train 3.885343 (lr=1.7997e-04) (hash(x)=147844486)
|
| 980 |
+
8140 train 3.941893 (lr=1.7934e-04) (hash(x)=141860136)
|
| 981 |
+
8150 train 4.079678 (lr=1.7871e-04) (hash(x)=147696006)
|
| 982 |
+
8160 train 3.979321 (lr=1.7810e-04) (hash(x)=151497110)
|
| 983 |
+
8170 train 3.983521 (lr=1.7749e-04) (hash(x)=140881859)
|
| 984 |
+
8180 train 3.931177 (lr=1.7689e-04) (hash(x)=158865574)
|
| 985 |
+
8190 train 3.889834 (lr=1.7631e-04) (hash(x)=161247161)
|
| 986 |
+
8200 val loss 4.0209
|
| 987 |
+
8200 val perplexity 55.7515
|
| 988 |
+
8200 train 3.853966 (lr=1.7573e-04) (hash(x)=156501889)
|
| 989 |
+
8210 train 3.973594 (lr=1.7517e-04) (hash(x)=158384162)
|
| 990 |
+
8220 train 4.020069 (lr=1.7461e-04) (hash(x)=154815062)
|
| 991 |
+
8230 train 3.901694 (lr=1.7407e-04) (hash(x)=145018315)
|
| 992 |
+
8240 train 3.939783 (lr=1.7354e-04) (hash(x)=161659129)
|
| 993 |
+
8250 train 3.906171 (lr=1.7301e-04) (hash(x)=139863367)
|
| 994 |
+
8260 train 3.856577 (lr=1.7250e-04) (hash(x)=149569663)
|
| 995 |
+
8270 train 3.612512 (lr=1.7199e-04) (hash(x)=162234378)
|
| 996 |
+
8280 train 3.998510 (lr=1.7150e-04) (hash(x)=144371378)
|
| 997 |
+
8290 train 3.900618 (lr=1.7102e-04) (hash(x)=148120258)
|
| 998 |
+
8300 val loss 4.0212
|
| 999 |
+
8300 val perplexity 55.7700
|
| 1000 |
+
8300 train 3.891476 (lr=1.7055e-04) (hash(x)=142716875)
|
| 1001 |
+
8310 train 3.912858 (lr=1.7008e-04) (hash(x)=166789234)
|
| 1002 |
+
8320 train 3.978795 (lr=1.6963e-04) (hash(x)=150613211)
|
| 1003 |
+
8330 train 3.858101 (lr=1.6919e-04) (hash(x)=139895391)
|
| 1004 |
+
8340 train 3.967160 (lr=1.6876e-04) (hash(x)=152011203)
|
| 1005 |
+
8350 train 3.924365 (lr=1.6834e-04) (hash(x)=156010875)
|
| 1006 |
+
8360 train 3.932877 (lr=1.6793e-04) (hash(x)=152988051)
|
| 1007 |
+
8370 train 4.098442 (lr=1.6752e-04) (hash(x)=155144327)
|
| 1008 |
+
8380 train 3.971939 (lr=1.6713e-04) (hash(x)=133642309)
|
| 1009 |
+
8390 train 4.024613 (lr=1.6675e-04) (hash(x)=149745335)
|
| 1010 |
+
8400 val loss 4.0136
|
| 1011 |
+
8400 val perplexity 55.3479
|
| 1012 |
+
8400 train 4.007542 (lr=1.6639e-04) (hash(x)=154436684)
|
| 1013 |
+
8410 train 4.046245 (lr=1.6603e-04) (hash(x)=147946630)
|
| 1014 |
+
8420 train 3.959814 (lr=1.6568e-04) (hash(x)=153947058)
|
| 1015 |
+
8430 train 4.054209 (lr=1.6534e-04) (hash(x)=159821040)
|
| 1016 |
+
8440 train 4.011341 (lr=1.6501e-04) (hash(x)=149127348)
|
| 1017 |
+
8450 train 4.020397 (lr=1.6469e-04) (hash(x)=149421871)
|
| 1018 |
+
8460 train 3.992570 (lr=1.6439e-04) (hash(x)=142621577)
|
| 1019 |
+
8470 train 3.987309 (lr=1.6409e-04) (hash(x)=148978213)
|
| 1020 |
+
8480 train 3.807852 (lr=1.6380e-04) (hash(x)=139959537)
|
| 1021 |
+
8490 train 3.900011 (lr=1.6353e-04) (hash(x)=144232498)
|
| 1022 |
+
8500 val loss 4.0116
|
| 1023 |
+
8500 val perplexity 55.2336
|
| 1024 |
+
8500 train 4.118513 (lr=1.6326e-04) (hash(x)=147965839)
|
| 1025 |
+
8510 train 3.996301 (lr=1.6300e-04) (hash(x)=147679836)
|
| 1026 |
+
8520 train 3.868639 (lr=1.6276e-04) (hash(x)=147486097)
|
| 1027 |
+
8530 train 4.017868 (lr=1.6253e-04) (hash(x)=151655265)
|
| 1028 |
+
8540 train 3.915907 (lr=1.6230e-04) (hash(x)=150866632)
|
| 1029 |
+
8550 train 4.062387 (lr=1.6209e-04) (hash(x)=144355059)
|
| 1030 |
+
8560 train 3.923198 (lr=1.6188e-04) (hash(x)=145518478)
|
| 1031 |
+
8570 train 4.062747 (lr=1.6169e-04) (hash(x)=178973323)
|
| 1032 |
+
8580 train 3.990893 (lr=1.6151e-04) (hash(x)=152773969)
|
| 1033 |
+
8590 train 3.782759 (lr=1.6134e-04) (hash(x)=141805508)
|
| 1034 |
+
8600 val loss 4.0163
|
| 1035 |
+
8600 val perplexity 55.4975
|
| 1036 |
+
8600 train 3.840646 (lr=1.6117e-04) (hash(x)=145228097)
|
| 1037 |
+
8610 train 3.857193 (lr=1.6102e-04) (hash(x)=149525694)
|
| 1038 |
+
8620 train 3.927480 (lr=1.6088e-04) (hash(x)=151651655)
|
| 1039 |
+
8630 train 4.046357 (lr=1.6075e-04) (hash(x)=144918643)
|
| 1040 |
+
8640 train 3.897918 (lr=1.6063e-04) (hash(x)=149721879)
|
| 1041 |
+
8650 train 3.964263 (lr=1.6052e-04) (hash(x)=157684127)
|
| 1042 |
+
8660 train 3.969104 (lr=1.6042e-04) (hash(x)=152426036)
|
| 1043 |
+
8670 train 3.889540 (lr=1.6033e-04) (hash(x)=141396342)
|
| 1044 |
+
8680 train 3.978575 (lr=1.6026e-04) (hash(x)=146459856)
|
| 1045 |
+
8690 train 4.064189 (lr=1.6019e-04) (hash(x)=151766124)
|
| 1046 |
+
8700 val loss 4.0070
|
| 1047 |
+
8700 val perplexity 54.9826
|
| 1048 |
+
8700 train 4.220052 (lr=1.6013e-04) (hash(x)=152910357)
|
| 1049 |
+
8710 train 4.004989 (lr=1.6008e-04) (hash(x)=149724642)
|
| 1050 |
+
8720 train 3.946559 (lr=1.6005e-04) (hash(x)=152483840)
|
| 1051 |
+
8730 train 3.924124 (lr=1.6002e-04) (hash(x)=147289415)
|
| 1052 |
+
8740 train 3.959003 (lr=1.6001e-04) (hash(x)=152254131)
|
| 1053 |
+
8749 val loss 4.0056
|
| 1054 |
+
8749 val perplexity 54.9060
|
lr16e-4_total_batch_size61440_baseline_seed1338/model_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c20a788466bccde2a67c3887d5c690fd33d949dea9b4812b5a326f64507b310
|
| 3 |
+
size 92843394
|
lr16e-4_total_batch_size61440_baseline_seed1338/optimizer_08749.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d0daae3dd209136d94fe1067abea720fa99355842628448471413f7325dbb8
|
| 3 |
+
size 179406214
|