initial commit
Browse files- config.json +29 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1658 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/byt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3584,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1472,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "gated-gelu",
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"model_type": "t5",
|
| 18 |
+
"num_decoder_layers": 4,
|
| 19 |
+
"num_heads": 6,
|
| 20 |
+
"num_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"relative_attention_num_buckets": 32,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.16.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 384
|
| 29 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ddd03f204b4f64a506f89ecb254a10aaf264c21af3ce63f861b47ea968e3d9d
|
| 3 |
+
size 2397201945
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:984b01e30529132688d5db41a69859820f56c8322429d1a14139ff44a52bfb33
|
| 3 |
+
size 1198627501
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f904f92fb527f40bfc714cae2d5c061085b078f13bad2cf6c9a055cae893b74d
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85bec01659fd250d826f7d1876c2b6cdb7c16efc96e82300b5d12cd3af4d61a3
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"]}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-small", "tokenizer_class": "ByT5Tokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1658 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"global_step": 131488,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.00019997920437606474,
|
| 13 |
+
"loss": 2.1277,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.00019995840875212947,
|
| 19 |
+
"loss": 1.7025,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 0.0001999376131281942,
|
| 25 |
+
"loss": 1.5776,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 0.00019991681750425894,
|
| 31 |
+
"loss": 1.4835,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 0.00019989602188032367,
|
| 37 |
+
"loss": 1.4104,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"learning_rate": 0.00019987522625638843,
|
| 43 |
+
"loss": 1.3631,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19,
|
| 48 |
+
"learning_rate": 0.00019985443063245316,
|
| 49 |
+
"loss": 1.2903,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.21,
|
| 54 |
+
"learning_rate": 0.00019983363500851792,
|
| 55 |
+
"loss": 1.2338,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.24,
|
| 60 |
+
"learning_rate": 0.00019981283938458265,
|
| 61 |
+
"loss": 1.2018,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.27,
|
| 66 |
+
"learning_rate": 0.00019979204376064738,
|
| 67 |
+
"loss": 1.1608,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.29,
|
| 72 |
+
"learning_rate": 0.00019977124813671211,
|
| 73 |
+
"loss": 1.1202,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.32,
|
| 78 |
+
"learning_rate": 0.00019975045251277685,
|
| 79 |
+
"loss": 1.0989,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.35,
|
| 84 |
+
"learning_rate": 0.00019972965688884158,
|
| 85 |
+
"loss": 1.0627,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.37,
|
| 90 |
+
"learning_rate": 0.0001997088612649063,
|
| 91 |
+
"loss": 1.0424,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.4,
|
| 96 |
+
"learning_rate": 0.00019968806564097104,
|
| 97 |
+
"loss": 1.0196,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.43,
|
| 102 |
+
"learning_rate": 0.00019966727001703577,
|
| 103 |
+
"loss": 0.9957,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.45,
|
| 108 |
+
"learning_rate": 0.0001996464743931005,
|
| 109 |
+
"loss": 0.9923,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.48,
|
| 114 |
+
"learning_rate": 0.00019962567876916524,
|
| 115 |
+
"loss": 0.9711,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.51,
|
| 120 |
+
"learning_rate": 0.00019960488314522997,
|
| 121 |
+
"loss": 0.9457,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.53,
|
| 126 |
+
"learning_rate": 0.00019958408752129473,
|
| 127 |
+
"loss": 0.9503,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.56,
|
| 132 |
+
"learning_rate": 0.00019956329189735946,
|
| 133 |
+
"loss": 0.9184,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.59,
|
| 138 |
+
"learning_rate": 0.00019954249627342422,
|
| 139 |
+
"loss": 0.9012,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.61,
|
| 144 |
+
"learning_rate": 0.00019952170064948895,
|
| 145 |
+
"loss": 0.8869,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.64,
|
| 150 |
+
"learning_rate": 0.00019950090502555368,
|
| 151 |
+
"loss": 0.9034,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.67,
|
| 156 |
+
"learning_rate": 0.00019948010940161841,
|
| 157 |
+
"loss": 0.8827,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.69,
|
| 162 |
+
"learning_rate": 0.00019945931377768315,
|
| 163 |
+
"loss": 0.8549,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.72,
|
| 168 |
+
"learning_rate": 0.00019943851815374788,
|
| 169 |
+
"loss": 0.8701,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.75,
|
| 174 |
+
"learning_rate": 0.0001994177225298126,
|
| 175 |
+
"loss": 0.8362,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.77,
|
| 180 |
+
"learning_rate": 0.00019939692690587734,
|
| 181 |
+
"loss": 0.8444,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.8,
|
| 186 |
+
"learning_rate": 0.00019937613128194207,
|
| 187 |
+
"loss": 0.8501,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.83,
|
| 192 |
+
"learning_rate": 0.0001993553356580068,
|
| 193 |
+
"loss": 0.8297,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.85,
|
| 198 |
+
"learning_rate": 0.00019933454003407156,
|
| 199 |
+
"loss": 0.82,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.88,
|
| 204 |
+
"learning_rate": 0.0001993137444101363,
|
| 205 |
+
"loss": 0.8219,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.91,
|
| 210 |
+
"learning_rate": 0.00019929294878620103,
|
| 211 |
+
"loss": 0.8074,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.93,
|
| 216 |
+
"learning_rate": 0.00019927215316226576,
|
| 217 |
+
"loss": 0.7981,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.96,
|
| 222 |
+
"learning_rate": 0.00019925135753833052,
|
| 223 |
+
"loss": 0.7946,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.98,
|
| 228 |
+
"learning_rate": 0.00019923056191439525,
|
| 229 |
+
"loss": 0.7888,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.0,
|
| 234 |
+
"eval_bleu": 0.2617,
|
| 235 |
+
"eval_gen_len": 18.172,
|
| 236 |
+
"eval_loss": 0.6930029392242432,
|
| 237 |
+
"eval_runtime": 742.401,
|
| 238 |
+
"eval_samples_per_second": 12.652,
|
| 239 |
+
"eval_steps_per_second": 3.164,
|
| 240 |
+
"step": 18784
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.01,
|
| 244 |
+
"learning_rate": 0.00019920976629045998,
|
| 245 |
+
"loss": 0.7721,
|
| 246 |
+
"step": 19000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.04,
|
| 250 |
+
"learning_rate": 0.00019918897066652471,
|
| 251 |
+
"loss": 0.7574,
|
| 252 |
+
"step": 19500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.06,
|
| 256 |
+
"learning_rate": 0.00019916817504258945,
|
| 257 |
+
"loss": 0.7442,
|
| 258 |
+
"step": 20000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.09,
|
| 262 |
+
"learning_rate": 0.00019914737941865418,
|
| 263 |
+
"loss": 0.7454,
|
| 264 |
+
"step": 20500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.12,
|
| 268 |
+
"learning_rate": 0.0001991265837947189,
|
| 269 |
+
"loss": 0.729,
|
| 270 |
+
"step": 21000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.14,
|
| 274 |
+
"learning_rate": 0.00019910578817078364,
|
| 275 |
+
"loss": 0.7422,
|
| 276 |
+
"step": 21500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.17,
|
| 280 |
+
"learning_rate": 0.00019908499254684837,
|
| 281 |
+
"loss": 0.7405,
|
| 282 |
+
"step": 22000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.2,
|
| 286 |
+
"learning_rate": 0.00019906419692291313,
|
| 287 |
+
"loss": 0.7231,
|
| 288 |
+
"step": 22500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.22,
|
| 292 |
+
"learning_rate": 0.00019904340129897787,
|
| 293 |
+
"loss": 0.7142,
|
| 294 |
+
"step": 23000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.25,
|
| 298 |
+
"learning_rate": 0.0001990226056750426,
|
| 299 |
+
"loss": 0.7207,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.28,
|
| 304 |
+
"learning_rate": 0.00019900181005110733,
|
| 305 |
+
"loss": 0.7087,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.3,
|
| 310 |
+
"learning_rate": 0.0001989810144271721,
|
| 311 |
+
"loss": 0.7243,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.33,
|
| 316 |
+
"learning_rate": 0.00019896021880323682,
|
| 317 |
+
"loss": 0.6951,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.36,
|
| 322 |
+
"learning_rate": 0.00019893942317930155,
|
| 323 |
+
"loss": 0.7001,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.38,
|
| 328 |
+
"learning_rate": 0.00019891862755536628,
|
| 329 |
+
"loss": 0.7297,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.41,
|
| 334 |
+
"learning_rate": 0.00019889783193143102,
|
| 335 |
+
"loss": 0.7032,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.44,
|
| 340 |
+
"learning_rate": 0.00019887703630749575,
|
| 341 |
+
"loss": 0.6943,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.46,
|
| 346 |
+
"learning_rate": 0.00019885624068356048,
|
| 347 |
+
"loss": 0.6953,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.49,
|
| 352 |
+
"learning_rate": 0.0001988354450596252,
|
| 353 |
+
"loss": 0.7025,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.52,
|
| 358 |
+
"learning_rate": 0.00019881464943568994,
|
| 359 |
+
"loss": 0.6901,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.54,
|
| 364 |
+
"learning_rate": 0.0001987938538117547,
|
| 365 |
+
"loss": 0.6867,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.57,
|
| 370 |
+
"learning_rate": 0.00019877305818781943,
|
| 371 |
+
"loss": 0.6826,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.6,
|
| 376 |
+
"learning_rate": 0.00019875226256388417,
|
| 377 |
+
"loss": 0.678,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.62,
|
| 382 |
+
"learning_rate": 0.0001987314669399489,
|
| 383 |
+
"loss": 0.6763,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.65,
|
| 388 |
+
"learning_rate": 0.00019871067131601363,
|
| 389 |
+
"loss": 0.6681,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.68,
|
| 394 |
+
"learning_rate": 0.0001986898756920784,
|
| 395 |
+
"loss": 0.6792,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.7,
|
| 400 |
+
"learning_rate": 0.00019866908006814312,
|
| 401 |
+
"loss": 0.6776,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.73,
|
| 406 |
+
"learning_rate": 0.00019864828444420785,
|
| 407 |
+
"loss": 0.677,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.76,
|
| 412 |
+
"learning_rate": 0.00019862748882027258,
|
| 413 |
+
"loss": 0.6787,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.78,
|
| 418 |
+
"learning_rate": 0.00019860669319633732,
|
| 419 |
+
"loss": 0.6695,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.81,
|
| 424 |
+
"learning_rate": 0.00019858589757240205,
|
| 425 |
+
"loss": 0.6555,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.84,
|
| 430 |
+
"learning_rate": 0.00019856510194846678,
|
| 431 |
+
"loss": 0.6721,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.86,
|
| 436 |
+
"learning_rate": 0.0001985443063245315,
|
| 437 |
+
"loss": 0.6617,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.89,
|
| 442 |
+
"learning_rate": 0.00019852351070059627,
|
| 443 |
+
"loss": 0.6562,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.92,
|
| 448 |
+
"learning_rate": 0.000198502715076661,
|
| 449 |
+
"loss": 0.6496,
|
| 450 |
+
"step": 36000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.94,
|
| 454 |
+
"learning_rate": 0.00019848191945272573,
|
| 455 |
+
"loss": 0.6447,
|
| 456 |
+
"step": 36500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.97,
|
| 460 |
+
"learning_rate": 0.00019846112382879047,
|
| 461 |
+
"loss": 0.6516,
|
| 462 |
+
"step": 37000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.0,
|
| 466 |
+
"learning_rate": 0.0001984403282048552,
|
| 467 |
+
"loss": 0.6424,
|
| 468 |
+
"step": 37500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.0,
|
| 472 |
+
"eval_bleu": 0.2865,
|
| 473 |
+
"eval_gen_len": 18.082,
|
| 474 |
+
"eval_loss": 0.5811895728111267,
|
| 475 |
+
"eval_runtime": 746.9324,
|
| 476 |
+
"eval_samples_per_second": 12.575,
|
| 477 |
+
"eval_steps_per_second": 3.145,
|
| 478 |
+
"step": 37568
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.02,
|
| 482 |
+
"learning_rate": 0.00019841953258091993,
|
| 483 |
+
"loss": 0.6152,
|
| 484 |
+
"step": 38000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.05,
|
| 488 |
+
"learning_rate": 0.0001983987369569847,
|
| 489 |
+
"loss": 0.6005,
|
| 490 |
+
"step": 38500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.08,
|
| 494 |
+
"learning_rate": 0.00019837794133304942,
|
| 495 |
+
"loss": 0.5937,
|
| 496 |
+
"step": 39000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.1,
|
| 500 |
+
"learning_rate": 0.00019835714570911415,
|
| 501 |
+
"loss": 0.5997,
|
| 502 |
+
"step": 39500
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.13,
|
| 506 |
+
"learning_rate": 0.00019833635008517888,
|
| 507 |
+
"loss": 0.5995,
|
| 508 |
+
"step": 40000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.16,
|
| 512 |
+
"learning_rate": 0.00019831555446124362,
|
| 513 |
+
"loss": 0.5934,
|
| 514 |
+
"step": 40500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.18,
|
| 518 |
+
"learning_rate": 0.00019829475883730835,
|
| 519 |
+
"loss": 0.5894,
|
| 520 |
+
"step": 41000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.21,
|
| 524 |
+
"learning_rate": 0.0001982739632133731,
|
| 525 |
+
"loss": 0.5882,
|
| 526 |
+
"step": 41500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.24,
|
| 530 |
+
"learning_rate": 0.00019825316758943784,
|
| 531 |
+
"loss": 0.608,
|
| 532 |
+
"step": 42000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.26,
|
| 536 |
+
"learning_rate": 0.00019823237196550257,
|
| 537 |
+
"loss": 0.5991,
|
| 538 |
+
"step": 42500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.29,
|
| 542 |
+
"learning_rate": 0.0001982115763415673,
|
| 543 |
+
"loss": 0.5981,
|
| 544 |
+
"step": 43000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.32,
|
| 548 |
+
"learning_rate": 0.00019819078071763203,
|
| 549 |
+
"loss": 0.5962,
|
| 550 |
+
"step": 43500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.34,
|
| 554 |
+
"learning_rate": 0.00019816998509369677,
|
| 555 |
+
"loss": 0.5776,
|
| 556 |
+
"step": 44000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.37,
|
| 560 |
+
"learning_rate": 0.0001981491894697615,
|
| 561 |
+
"loss": 0.5953,
|
| 562 |
+
"step": 44500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.4,
|
| 566 |
+
"learning_rate": 0.00019812839384582626,
|
| 567 |
+
"loss": 0.6036,
|
| 568 |
+
"step": 45000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.42,
|
| 572 |
+
"learning_rate": 0.000198107598221891,
|
| 573 |
+
"loss": 0.5877,
|
| 574 |
+
"step": 45500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.45,
|
| 578 |
+
"learning_rate": 0.00019808680259795572,
|
| 579 |
+
"loss": 0.5864,
|
| 580 |
+
"step": 46000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.48,
|
| 584 |
+
"learning_rate": 0.00019806600697402045,
|
| 585 |
+
"loss": 0.579,
|
| 586 |
+
"step": 46500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.5,
|
| 590 |
+
"learning_rate": 0.00019804521135008518,
|
| 591 |
+
"loss": 0.5873,
|
| 592 |
+
"step": 47000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.53,
|
| 596 |
+
"learning_rate": 0.00019802441572614992,
|
| 597 |
+
"loss": 0.5912,
|
| 598 |
+
"step": 47500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.56,
|
| 602 |
+
"learning_rate": 0.00019800362010221468,
|
| 603 |
+
"loss": 0.592,
|
| 604 |
+
"step": 48000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.58,
|
| 608 |
+
"learning_rate": 0.0001979828244782794,
|
| 609 |
+
"loss": 0.5822,
|
| 610 |
+
"step": 48500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.61,
|
| 614 |
+
"learning_rate": 0.00019796202885434414,
|
| 615 |
+
"loss": 0.5864,
|
| 616 |
+
"step": 49000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.64,
|
| 620 |
+
"learning_rate": 0.00019794123323040887,
|
| 621 |
+
"loss": 0.5738,
|
| 622 |
+
"step": 49500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.66,
|
| 626 |
+
"learning_rate": 0.0001979204376064736,
|
| 627 |
+
"loss": 0.583,
|
| 628 |
+
"step": 50000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.69,
|
| 632 |
+
"learning_rate": 0.00019789964198253833,
|
| 633 |
+
"loss": 0.5803,
|
| 634 |
+
"step": 50500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.72,
|
| 638 |
+
"learning_rate": 0.00019787884635860307,
|
| 639 |
+
"loss": 0.5884,
|
| 640 |
+
"step": 51000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.74,
|
| 644 |
+
"learning_rate": 0.0001978580507346678,
|
| 645 |
+
"loss": 0.5938,
|
| 646 |
+
"step": 51500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.77,
|
| 650 |
+
"learning_rate": 0.00019783725511073256,
|
| 651 |
+
"loss": 0.5761,
|
| 652 |
+
"step": 52000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.79,
|
| 656 |
+
"learning_rate": 0.0001978164594867973,
|
| 657 |
+
"loss": 0.5829,
|
| 658 |
+
"step": 52500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.82,
|
| 662 |
+
"learning_rate": 0.00019779566386286202,
|
| 663 |
+
"loss": 0.5764,
|
| 664 |
+
"step": 53000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.85,
|
| 668 |
+
"learning_rate": 0.00019777486823892675,
|
| 669 |
+
"loss": 0.5707,
|
| 670 |
+
"step": 53500
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.87,
|
| 674 |
+
"learning_rate": 0.00019775407261499148,
|
| 675 |
+
"loss": 0.5836,
|
| 676 |
+
"step": 54000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9,
|
| 680 |
+
"learning_rate": 0.00019773327699105624,
|
| 681 |
+
"loss": 0.5756,
|
| 682 |
+
"step": 54500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.93,
|
| 686 |
+
"learning_rate": 0.00019771248136712098,
|
| 687 |
+
"loss": 0.5833,
|
| 688 |
+
"step": 55000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.95,
|
| 692 |
+
"learning_rate": 0.0001976916857431857,
|
| 693 |
+
"loss": 0.5638,
|
| 694 |
+
"step": 55500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.98,
|
| 698 |
+
"learning_rate": 0.00019767089011925044,
|
| 699 |
+
"loss": 0.5567,
|
| 700 |
+
"step": 56000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 3.0,
|
| 704 |
+
"eval_bleu": 0.2983,
|
| 705 |
+
"eval_gen_len": 18.1221,
|
| 706 |
+
"eval_loss": 0.5350888967514038,
|
| 707 |
+
"eval_runtime": 744.9161,
|
| 708 |
+
"eval_samples_per_second": 12.609,
|
| 709 |
+
"eval_steps_per_second": 3.153,
|
| 710 |
+
"step": 56352
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.01,
|
| 714 |
+
"learning_rate": 0.00019765009449531517,
|
| 715 |
+
"loss": 0.5522,
|
| 716 |
+
"step": 56500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 3.03,
|
| 720 |
+
"learning_rate": 0.0001976292988713799,
|
| 721 |
+
"loss": 0.513,
|
| 722 |
+
"step": 57000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 3.06,
|
| 726 |
+
"learning_rate": 0.00019760850324744463,
|
| 727 |
+
"loss": 0.5227,
|
| 728 |
+
"step": 57500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.09,
|
| 732 |
+
"learning_rate": 0.00019758770762350937,
|
| 733 |
+
"loss": 0.5269,
|
| 734 |
+
"step": 58000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.11,
|
| 738 |
+
"learning_rate": 0.0001975669119995741,
|
| 739 |
+
"loss": 0.5244,
|
| 740 |
+
"step": 58500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.14,
|
| 744 |
+
"learning_rate": 0.00019754611637563886,
|
| 745 |
+
"loss": 0.5225,
|
| 746 |
+
"step": 59000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 3.17,
|
| 750 |
+
"learning_rate": 0.0001975253207517036,
|
| 751 |
+
"loss": 0.5256,
|
| 752 |
+
"step": 59500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.19,
|
| 756 |
+
"learning_rate": 0.00019750452512776832,
|
| 757 |
+
"loss": 0.5258,
|
| 758 |
+
"step": 60000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.22,
|
| 762 |
+
"learning_rate": 0.00019748372950383305,
|
| 763 |
+
"loss": 0.5243,
|
| 764 |
+
"step": 60500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.25,
|
| 768 |
+
"learning_rate": 0.0001974629338798978,
|
| 769 |
+
"loss": 0.5217,
|
| 770 |
+
"step": 61000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 3.27,
|
| 774 |
+
"learning_rate": 0.00019744213825596254,
|
| 775 |
+
"loss": 0.5202,
|
| 776 |
+
"step": 61500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.3,
|
| 780 |
+
"learning_rate": 0.00019742134263202728,
|
| 781 |
+
"loss": 0.5272,
|
| 782 |
+
"step": 62000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 3.33,
|
| 786 |
+
"learning_rate": 0.000197400547008092,
|
| 787 |
+
"loss": 0.5183,
|
| 788 |
+
"step": 62500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.35,
|
| 792 |
+
"learning_rate": 0.00019737975138415674,
|
| 793 |
+
"loss": 0.5239,
|
| 794 |
+
"step": 63000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.38,
|
| 798 |
+
"learning_rate": 0.00019735895576022147,
|
| 799 |
+
"loss": 0.5247,
|
| 800 |
+
"step": 63500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.41,
|
| 804 |
+
"learning_rate": 0.0001973381601362862,
|
| 805 |
+
"loss": 0.531,
|
| 806 |
+
"step": 64000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.43,
|
| 810 |
+
"learning_rate": 0.00019731736451235093,
|
| 811 |
+
"loss": 0.515,
|
| 812 |
+
"step": 64500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.46,
|
| 816 |
+
"learning_rate": 0.00019729656888841567,
|
| 817 |
+
"loss": 0.5154,
|
| 818 |
+
"step": 65000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.49,
|
| 822 |
+
"learning_rate": 0.00019727577326448043,
|
| 823 |
+
"loss": 0.5252,
|
| 824 |
+
"step": 65500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.51,
|
| 828 |
+
"learning_rate": 0.00019725497764054516,
|
| 829 |
+
"loss": 0.5094,
|
| 830 |
+
"step": 66000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.54,
|
| 834 |
+
"learning_rate": 0.0001972341820166099,
|
| 835 |
+
"loss": 0.526,
|
| 836 |
+
"step": 66500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.57,
|
| 840 |
+
"learning_rate": 0.00019721338639267465,
|
| 841 |
+
"loss": 0.5175,
|
| 842 |
+
"step": 67000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.59,
|
| 846 |
+
"learning_rate": 0.00019719259076873938,
|
| 847 |
+
"loss": 0.523,
|
| 848 |
+
"step": 67500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.62,
|
| 852 |
+
"learning_rate": 0.0001971717951448041,
|
| 853 |
+
"loss": 0.514,
|
| 854 |
+
"step": 68000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.65,
|
| 858 |
+
"learning_rate": 0.00019715099952086884,
|
| 859 |
+
"loss": 0.5236,
|
| 860 |
+
"step": 68500
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.67,
|
| 864 |
+
"learning_rate": 0.00019713020389693358,
|
| 865 |
+
"loss": 0.5167,
|
| 866 |
+
"step": 69000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.7,
|
| 870 |
+
"learning_rate": 0.0001971094082729983,
|
| 871 |
+
"loss": 0.5079,
|
| 872 |
+
"step": 69500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.73,
|
| 876 |
+
"learning_rate": 0.00019708861264906304,
|
| 877 |
+
"loss": 0.5142,
|
| 878 |
+
"step": 70000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.75,
|
| 882 |
+
"learning_rate": 0.00019706781702512777,
|
| 883 |
+
"loss": 0.5186,
|
| 884 |
+
"step": 70500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.78,
|
| 888 |
+
"learning_rate": 0.0001970470214011925,
|
| 889 |
+
"loss": 0.5239,
|
| 890 |
+
"step": 71000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.81,
|
| 894 |
+
"learning_rate": 0.00019702622577725724,
|
| 895 |
+
"loss": 0.5131,
|
| 896 |
+
"step": 71500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.83,
|
| 900 |
+
"learning_rate": 0.00019700543015332197,
|
| 901 |
+
"loss": 0.519,
|
| 902 |
+
"step": 72000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.86,
|
| 906 |
+
"learning_rate": 0.00019698463452938673,
|
| 907 |
+
"loss": 0.5202,
|
| 908 |
+
"step": 72500
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.89,
|
| 912 |
+
"learning_rate": 0.00019696383890545146,
|
| 913 |
+
"loss": 0.5305,
|
| 914 |
+
"step": 73000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 3.91,
|
| 918 |
+
"learning_rate": 0.00019694304328151622,
|
| 919 |
+
"loss": 0.5042,
|
| 920 |
+
"step": 73500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.94,
|
| 924 |
+
"learning_rate": 0.00019692224765758095,
|
| 925 |
+
"loss": 0.513,
|
| 926 |
+
"step": 74000
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.97,
|
| 930 |
+
"learning_rate": 0.00019690145203364568,
|
| 931 |
+
"loss": 0.5272,
|
| 932 |
+
"step": 74500
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.99,
|
| 936 |
+
"learning_rate": 0.0001968806564097104,
|
| 937 |
+
"loss": 0.5119,
|
| 938 |
+
"step": 75000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.0,
|
| 942 |
+
"eval_bleu": 0.3043,
|
| 943 |
+
"eval_gen_len": 18.1054,
|
| 944 |
+
"eval_loss": 0.5083436965942383,
|
| 945 |
+
"eval_runtime": 750.8628,
|
| 946 |
+
"eval_samples_per_second": 12.51,
|
| 947 |
+
"eval_steps_per_second": 3.128,
|
| 948 |
+
"step": 75136
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 4.02,
|
| 952 |
+
"learning_rate": 0.00019685986078577514,
|
| 953 |
+
"loss": 0.4702,
|
| 954 |
+
"step": 75500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.05,
|
| 958 |
+
"learning_rate": 0.00019683906516183988,
|
| 959 |
+
"loss": 0.4581,
|
| 960 |
+
"step": 76000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 4.07,
|
| 964 |
+
"learning_rate": 0.0001968182695379046,
|
| 965 |
+
"loss": 0.4664,
|
| 966 |
+
"step": 76500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 4.1,
|
| 970 |
+
"learning_rate": 0.00019679747391396934,
|
| 971 |
+
"loss": 0.4596,
|
| 972 |
+
"step": 77000
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 4.13,
|
| 976 |
+
"learning_rate": 0.00019677667829003407,
|
| 977 |
+
"loss": 0.459,
|
| 978 |
+
"step": 77500
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 4.15,
|
| 982 |
+
"learning_rate": 0.0001967558826660988,
|
| 983 |
+
"loss": 0.4688,
|
| 984 |
+
"step": 78000
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.18,
|
| 988 |
+
"learning_rate": 0.00019673508704216354,
|
| 989 |
+
"loss": 0.482,
|
| 990 |
+
"step": 78500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.21,
|
| 994 |
+
"learning_rate": 0.00019671429141822827,
|
| 995 |
+
"loss": 0.4698,
|
| 996 |
+
"step": 79000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.23,
|
| 1000 |
+
"learning_rate": 0.00019669349579429303,
|
| 1001 |
+
"loss": 0.468,
|
| 1002 |
+
"step": 79500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 4.26,
|
| 1006 |
+
"learning_rate": 0.00019667270017035776,
|
| 1007 |
+
"loss": 0.4625,
|
| 1008 |
+
"step": 80000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 4.29,
|
| 1012 |
+
"learning_rate": 0.00019665190454642252,
|
| 1013 |
+
"loss": 0.4744,
|
| 1014 |
+
"step": 80500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 4.31,
|
| 1018 |
+
"learning_rate": 0.00019663110892248725,
|
| 1019 |
+
"loss": 0.4666,
|
| 1020 |
+
"step": 81000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 4.34,
|
| 1024 |
+
"learning_rate": 0.00019661031329855198,
|
| 1025 |
+
"loss": 0.4717,
|
| 1026 |
+
"step": 81500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 4.37,
|
| 1030 |
+
"learning_rate": 0.0001965895176746167,
|
| 1031 |
+
"loss": 0.4721,
|
| 1032 |
+
"step": 82000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 4.39,
|
| 1036 |
+
"learning_rate": 0.00019656872205068144,
|
| 1037 |
+
"loss": 0.4576,
|
| 1038 |
+
"step": 82500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 4.42,
|
| 1042 |
+
"learning_rate": 0.00019654792642674618,
|
| 1043 |
+
"loss": 0.4664,
|
| 1044 |
+
"step": 83000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 4.45,
|
| 1048 |
+
"learning_rate": 0.0001965271308028109,
|
| 1049 |
+
"loss": 0.4633,
|
| 1050 |
+
"step": 83500
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 4.47,
|
| 1054 |
+
"learning_rate": 0.00019650633517887564,
|
| 1055 |
+
"loss": 0.4736,
|
| 1056 |
+
"step": 84000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 4.5,
|
| 1060 |
+
"learning_rate": 0.00019648553955494037,
|
| 1061 |
+
"loss": 0.4687,
|
| 1062 |
+
"step": 84500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 4.53,
|
| 1066 |
+
"learning_rate": 0.0001964647439310051,
|
| 1067 |
+
"loss": 0.4818,
|
| 1068 |
+
"step": 85000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 4.55,
|
| 1072 |
+
"learning_rate": 0.00019644394830706984,
|
| 1073 |
+
"loss": 0.4668,
|
| 1074 |
+
"step": 85500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.58,
|
| 1078 |
+
"learning_rate": 0.0001964231526831346,
|
| 1079 |
+
"loss": 0.4745,
|
| 1080 |
+
"step": 86000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 4.6,
|
| 1084 |
+
"learning_rate": 0.00019640235705919933,
|
| 1085 |
+
"loss": 0.4686,
|
| 1086 |
+
"step": 86500
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 4.63,
|
| 1090 |
+
"learning_rate": 0.00019638156143526406,
|
| 1091 |
+
"loss": 0.4846,
|
| 1092 |
+
"step": 87000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 4.66,
|
| 1096 |
+
"learning_rate": 0.00019636076581132882,
|
| 1097 |
+
"loss": 0.4714,
|
| 1098 |
+
"step": 87500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 4.68,
|
| 1102 |
+
"learning_rate": 0.00019633997018739355,
|
| 1103 |
+
"loss": 0.4656,
|
| 1104 |
+
"step": 88000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 4.71,
|
| 1108 |
+
"learning_rate": 0.00019631917456345828,
|
| 1109 |
+
"loss": 0.4963,
|
| 1110 |
+
"step": 88500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 4.74,
|
| 1114 |
+
"learning_rate": 0.000196298378939523,
|
| 1115 |
+
"loss": 0.4754,
|
| 1116 |
+
"step": 89000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.76,
|
| 1120 |
+
"learning_rate": 0.00019627758331558774,
|
| 1121 |
+
"loss": 0.4596,
|
| 1122 |
+
"step": 89500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 4.79,
|
| 1126 |
+
"learning_rate": 0.00019625678769165248,
|
| 1127 |
+
"loss": 0.4693,
|
| 1128 |
+
"step": 90000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 4.82,
|
| 1132 |
+
"learning_rate": 0.0001962359920677172,
|
| 1133 |
+
"loss": 0.4833,
|
| 1134 |
+
"step": 90500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.84,
|
| 1138 |
+
"learning_rate": 0.00019621519644378194,
|
| 1139 |
+
"loss": 0.4847,
|
| 1140 |
+
"step": 91000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 4.87,
|
| 1144 |
+
"learning_rate": 0.00019619440081984667,
|
| 1145 |
+
"loss": 0.4752,
|
| 1146 |
+
"step": 91500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 4.9,
|
| 1150 |
+
"learning_rate": 0.0001961736051959114,
|
| 1151 |
+
"loss": 0.4805,
|
| 1152 |
+
"step": 92000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.92,
|
| 1156 |
+
"learning_rate": 0.00019615280957197614,
|
| 1157 |
+
"loss": 0.4869,
|
| 1158 |
+
"step": 92500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.95,
|
| 1162 |
+
"learning_rate": 0.0001961320139480409,
|
| 1163 |
+
"loss": 0.4731,
|
| 1164 |
+
"step": 93000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 4.98,
|
| 1168 |
+
"learning_rate": 0.00019611121832410563,
|
| 1169 |
+
"loss": 0.4624,
|
| 1170 |
+
"step": 93500
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 5.0,
|
| 1174 |
+
"eval_bleu": 0.3071,
|
| 1175 |
+
"eval_gen_len": 18.1357,
|
| 1176 |
+
"eval_loss": 0.49742114543914795,
|
| 1177 |
+
"eval_runtime": 738.3061,
|
| 1178 |
+
"eval_samples_per_second": 12.722,
|
| 1179 |
+
"eval_steps_per_second": 3.182,
|
| 1180 |
+
"step": 93920
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 5.0,
|
| 1184 |
+
"learning_rate": 0.00019609042270017039,
|
| 1185 |
+
"loss": 0.4743,
|
| 1186 |
+
"step": 94000
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 5.03,
|
| 1190 |
+
"learning_rate": 0.00019606962707623512,
|
| 1191 |
+
"loss": 0.4185,
|
| 1192 |
+
"step": 94500
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 5.06,
|
| 1196 |
+
"learning_rate": 0.00019604883145229985,
|
| 1197 |
+
"loss": 0.4121,
|
| 1198 |
+
"step": 95000
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 5.08,
|
| 1202 |
+
"learning_rate": 0.00019602803582836458,
|
| 1203 |
+
"loss": 0.4053,
|
| 1204 |
+
"step": 95500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 5.11,
|
| 1208 |
+
"learning_rate": 0.0001960072402044293,
|
| 1209 |
+
"loss": 0.4169,
|
| 1210 |
+
"step": 96000
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 5.14,
|
| 1214 |
+
"learning_rate": 0.00019598644458049405,
|
| 1215 |
+
"loss": 0.4232,
|
| 1216 |
+
"step": 96500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 5.16,
|
| 1220 |
+
"learning_rate": 0.00019596564895655878,
|
| 1221 |
+
"loss": 0.4324,
|
| 1222 |
+
"step": 97000
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 5.19,
|
| 1226 |
+
"learning_rate": 0.0001959448533326235,
|
| 1227 |
+
"loss": 0.4204,
|
| 1228 |
+
"step": 97500
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 5.22,
|
| 1232 |
+
"learning_rate": 0.00019592405770868824,
|
| 1233 |
+
"loss": 0.4275,
|
| 1234 |
+
"step": 98000
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 5.24,
|
| 1238 |
+
"learning_rate": 0.00019590326208475297,
|
| 1239 |
+
"loss": 0.424,
|
| 1240 |
+
"step": 98500
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 5.27,
|
| 1244 |
+
"learning_rate": 0.00019588246646081773,
|
| 1245 |
+
"loss": 0.4277,
|
| 1246 |
+
"step": 99000
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 5.3,
|
| 1250 |
+
"learning_rate": 0.00019586167083688246,
|
| 1251 |
+
"loss": 0.4265,
|
| 1252 |
+
"step": 99500
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 5.32,
|
| 1256 |
+
"learning_rate": 0.0001958408752129472,
|
| 1257 |
+
"loss": 0.4272,
|
| 1258 |
+
"step": 100000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 5.35,
|
| 1262 |
+
"learning_rate": 0.00019582007958901193,
|
| 1263 |
+
"loss": 0.4221,
|
| 1264 |
+
"step": 100500
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 5.38,
|
| 1268 |
+
"learning_rate": 0.00019579928396507669,
|
| 1269 |
+
"loss": 0.4289,
|
| 1270 |
+
"step": 101000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 5.4,
|
| 1274 |
+
"learning_rate": 0.00019577848834114142,
|
| 1275 |
+
"loss": 0.4427,
|
| 1276 |
+
"step": 101500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 5.43,
|
| 1280 |
+
"learning_rate": 0.00019575769271720615,
|
| 1281 |
+
"loss": 0.4201,
|
| 1282 |
+
"step": 102000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 5.46,
|
| 1286 |
+
"learning_rate": 0.00019573689709327088,
|
| 1287 |
+
"loss": 0.4202,
|
| 1288 |
+
"step": 102500
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 5.48,
|
| 1292 |
+
"learning_rate": 0.00019571610146933561,
|
| 1293 |
+
"loss": 0.4257,
|
| 1294 |
+
"step": 103000
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 5.51,
|
| 1298 |
+
"learning_rate": 0.00019569530584540035,
|
| 1299 |
+
"loss": 0.4409,
|
| 1300 |
+
"step": 103500
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 5.54,
|
| 1304 |
+
"learning_rate": 0.00019567451022146508,
|
| 1305 |
+
"loss": 0.4371,
|
| 1306 |
+
"step": 104000
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 5.56,
|
| 1310 |
+
"learning_rate": 0.0001956537145975298,
|
| 1311 |
+
"loss": 0.426,
|
| 1312 |
+
"step": 104500
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 5.59,
|
| 1316 |
+
"learning_rate": 0.00019563291897359454,
|
| 1317 |
+
"loss": 0.4298,
|
| 1318 |
+
"step": 105000
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 5.62,
|
| 1322 |
+
"learning_rate": 0.0001956121233496593,
|
| 1323 |
+
"loss": 0.4349,
|
| 1324 |
+
"step": 105500
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 5.64,
|
| 1328 |
+
"learning_rate": 0.00019559132772572403,
|
| 1329 |
+
"loss": 0.4282,
|
| 1330 |
+
"step": 106000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 5.67,
|
| 1334 |
+
"learning_rate": 0.00019557053210178876,
|
| 1335 |
+
"loss": 0.4281,
|
| 1336 |
+
"step": 106500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 5.7,
|
| 1340 |
+
"learning_rate": 0.0001955497364778535,
|
| 1341 |
+
"loss": 0.4389,
|
| 1342 |
+
"step": 107000
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 5.72,
|
| 1346 |
+
"learning_rate": 0.00019552894085391823,
|
| 1347 |
+
"loss": 0.4358,
|
| 1348 |
+
"step": 107500
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 5.75,
|
| 1352 |
+
"learning_rate": 0.000195508145229983,
|
| 1353 |
+
"loss": 0.4324,
|
| 1354 |
+
"step": 108000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 5.78,
|
| 1358 |
+
"learning_rate": 0.00019548734960604772,
|
| 1359 |
+
"loss": 0.4292,
|
| 1360 |
+
"step": 108500
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 5.8,
|
| 1364 |
+
"learning_rate": 0.00019546655398211245,
|
| 1365 |
+
"loss": 0.442,
|
| 1366 |
+
"step": 109000
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 5.83,
|
| 1370 |
+
"learning_rate": 0.00019544575835817718,
|
| 1371 |
+
"loss": 0.4322,
|
| 1372 |
+
"step": 109500
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 5.86,
|
| 1376 |
+
"learning_rate": 0.00019542496273424191,
|
| 1377 |
+
"loss": 0.4261,
|
| 1378 |
+
"step": 110000
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 5.88,
|
| 1382 |
+
"learning_rate": 0.00019540416711030665,
|
| 1383 |
+
"loss": 0.4313,
|
| 1384 |
+
"step": 110500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 5.91,
|
| 1388 |
+
"learning_rate": 0.00019538337148637138,
|
| 1389 |
+
"loss": 0.4275,
|
| 1390 |
+
"step": 111000
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 5.94,
|
| 1394 |
+
"learning_rate": 0.0001953625758624361,
|
| 1395 |
+
"loss": 0.4447,
|
| 1396 |
+
"step": 111500
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 5.96,
|
| 1400 |
+
"learning_rate": 0.00019534178023850087,
|
| 1401 |
+
"loss": 0.4365,
|
| 1402 |
+
"step": 112000
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 5.99,
|
| 1406 |
+
"learning_rate": 0.0001953209846145656,
|
| 1407 |
+
"loss": 0.4339,
|
| 1408 |
+
"step": 112500
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 6.0,
|
| 1412 |
+
"eval_bleu": 0.3111,
|
| 1413 |
+
"eval_gen_len": 18.0894,
|
| 1414 |
+
"eval_loss": 0.4859704375267029,
|
| 1415 |
+
"eval_runtime": 732.0314,
|
| 1416 |
+
"eval_samples_per_second": 12.831,
|
| 1417 |
+
"eval_steps_per_second": 3.209,
|
| 1418 |
+
"step": 112704
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 6.02,
|
| 1422 |
+
"learning_rate": 0.00019530018899063033,
|
| 1423 |
+
"loss": 0.4059,
|
| 1424 |
+
"step": 113000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 6.04,
|
| 1428 |
+
"learning_rate": 0.00019527939336669506,
|
| 1429 |
+
"loss": 0.3739,
|
| 1430 |
+
"step": 113500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 6.07,
|
| 1434 |
+
"learning_rate": 0.0001952585977427598,
|
| 1435 |
+
"loss": 0.365,
|
| 1436 |
+
"step": 114000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 6.1,
|
| 1440 |
+
"learning_rate": 0.00019523780211882456,
|
| 1441 |
+
"loss": 0.3764,
|
| 1442 |
+
"step": 114500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 6.12,
|
| 1446 |
+
"learning_rate": 0.0001952170064948893,
|
| 1447 |
+
"loss": 0.3829,
|
| 1448 |
+
"step": 115000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 6.15,
|
| 1452 |
+
"learning_rate": 0.00019519621087095402,
|
| 1453 |
+
"loss": 0.3851,
|
| 1454 |
+
"step": 115500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 6.18,
|
| 1458 |
+
"learning_rate": 0.00019517541524701875,
|
| 1459 |
+
"loss": 0.382,
|
| 1460 |
+
"step": 116000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 6.2,
|
| 1464 |
+
"learning_rate": 0.00019515461962308348,
|
| 1465 |
+
"loss": 0.383,
|
| 1466 |
+
"step": 116500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 6.23,
|
| 1470 |
+
"learning_rate": 0.00019513382399914821,
|
| 1471 |
+
"loss": 0.3926,
|
| 1472 |
+
"step": 117000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 6.26,
|
| 1476 |
+
"learning_rate": 0.00019511302837521295,
|
| 1477 |
+
"loss": 0.3897,
|
| 1478 |
+
"step": 117500
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 6.28,
|
| 1482 |
+
"learning_rate": 0.00019509223275127768,
|
| 1483 |
+
"loss": 0.3809,
|
| 1484 |
+
"step": 118000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 6.31,
|
| 1488 |
+
"learning_rate": 0.00019507143712734244,
|
| 1489 |
+
"loss": 0.3964,
|
| 1490 |
+
"step": 118500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 6.34,
|
| 1494 |
+
"learning_rate": 0.00019505064150340717,
|
| 1495 |
+
"loss": 0.3768,
|
| 1496 |
+
"step": 119000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 6.36,
|
| 1500 |
+
"learning_rate": 0.0001950298458794719,
|
| 1501 |
+
"loss": 0.3799,
|
| 1502 |
+
"step": 119500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 6.39,
|
| 1506 |
+
"learning_rate": 0.00019500905025553663,
|
| 1507 |
+
"loss": 0.3896,
|
| 1508 |
+
"step": 120000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 6.42,
|
| 1512 |
+
"learning_rate": 0.00019498825463160136,
|
| 1513 |
+
"loss": 0.3885,
|
| 1514 |
+
"step": 120500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 6.44,
|
| 1518 |
+
"learning_rate": 0.0001949674590076661,
|
| 1519 |
+
"loss": 0.3873,
|
| 1520 |
+
"step": 121000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 6.47,
|
| 1524 |
+
"learning_rate": 0.00019494666338373086,
|
| 1525 |
+
"loss": 0.386,
|
| 1526 |
+
"step": 121500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 6.49,
|
| 1530 |
+
"learning_rate": 0.0001949258677597956,
|
| 1531 |
+
"loss": 0.3842,
|
| 1532 |
+
"step": 122000
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 6.52,
|
| 1536 |
+
"learning_rate": 0.00019490507213586032,
|
| 1537 |
+
"loss": 0.396,
|
| 1538 |
+
"step": 122500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 6.55,
|
| 1542 |
+
"learning_rate": 0.00019488427651192505,
|
| 1543 |
+
"loss": 0.3954,
|
| 1544 |
+
"step": 123000
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 6.57,
|
| 1548 |
+
"learning_rate": 0.00019486348088798978,
|
| 1549 |
+
"loss": 0.391,
|
| 1550 |
+
"step": 123500
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 6.6,
|
| 1554 |
+
"learning_rate": 0.00019484268526405451,
|
| 1555 |
+
"loss": 0.3892,
|
| 1556 |
+
"step": 124000
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 6.63,
|
| 1560 |
+
"learning_rate": 0.00019482188964011927,
|
| 1561 |
+
"loss": 0.3992,
|
| 1562 |
+
"step": 124500
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 6.65,
|
| 1566 |
+
"learning_rate": 0.000194801094016184,
|
| 1567 |
+
"loss": 0.4063,
|
| 1568 |
+
"step": 125000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 6.68,
|
| 1572 |
+
"learning_rate": 0.00019478029839224874,
|
| 1573 |
+
"loss": 0.4054,
|
| 1574 |
+
"step": 125500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 6.71,
|
| 1578 |
+
"learning_rate": 0.00019475950276831347,
|
| 1579 |
+
"loss": 0.3992,
|
| 1580 |
+
"step": 126000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 6.73,
|
| 1584 |
+
"learning_rate": 0.0001947387071443782,
|
| 1585 |
+
"loss": 0.397,
|
| 1586 |
+
"step": 126500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 6.76,
|
| 1590 |
+
"learning_rate": 0.00019471791152044293,
|
| 1591 |
+
"loss": 0.3971,
|
| 1592 |
+
"step": 127000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 6.79,
|
| 1596 |
+
"learning_rate": 0.00019469711589650766,
|
| 1597 |
+
"loss": 0.401,
|
| 1598 |
+
"step": 127500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 6.81,
|
| 1602 |
+
"learning_rate": 0.0001946763202725724,
|
| 1603 |
+
"loss": 0.402,
|
| 1604 |
+
"step": 128000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 6.84,
|
| 1608 |
+
"learning_rate": 0.00019465552464863716,
|
| 1609 |
+
"loss": 0.4024,
|
| 1610 |
+
"step": 128500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 6.87,
|
| 1614 |
+
"learning_rate": 0.0001946347290247019,
|
| 1615 |
+
"loss": 0.3934,
|
| 1616 |
+
"step": 129000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 6.89,
|
| 1620 |
+
"learning_rate": 0.00019461393340076662,
|
| 1621 |
+
"loss": 0.3928,
|
| 1622 |
+
"step": 129500
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 6.92,
|
| 1626 |
+
"learning_rate": 0.00019459313777683135,
|
| 1627 |
+
"loss": 0.4037,
|
| 1628 |
+
"step": 130000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 6.95,
|
| 1632 |
+
"learning_rate": 0.00019457234215289608,
|
| 1633 |
+
"loss": 0.3969,
|
| 1634 |
+
"step": 130500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 6.97,
|
| 1638 |
+
"learning_rate": 0.00019455154652896084,
|
| 1639 |
+
"loss": 0.4045,
|
| 1640 |
+
"step": 131000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 7.0,
|
| 1644 |
+
"eval_bleu": 0.3151,
|
| 1645 |
+
"eval_gen_len": 18.1157,
|
| 1646 |
+
"eval_loss": 0.4873952865600586,
|
| 1647 |
+
"eval_runtime": 742.15,
|
| 1648 |
+
"eval_samples_per_second": 12.656,
|
| 1649 |
+
"eval_steps_per_second": 3.165,
|
| 1650 |
+
"step": 131488
|
| 1651 |
+
}
|
| 1652 |
+
],
|
| 1653 |
+
"max_steps": 4808704,
|
| 1654 |
+
"num_train_epochs": 256,
|
| 1655 |
+
"total_flos": 6.426846373591757e+16,
|
| 1656 |
+
"trial_name": null,
|
| 1657 |
+
"trial_params": null
|
| 1658 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f56982e27b4a05475eb966f9da9ff4d838cb1174efb8c72df3fa9b2f97477e94
|
| 3 |
+
size 3119
|