Initial commit
Browse files- all_results.json +8 -0
- config.json +29 -0
- flax_model.msgpack +3 -0
- pytorch_model.bin +3 -0
- runs/Apr26_12-24-19_pg-gpu17/1650968746.6344287/events.out.tfevents.1650968746.pg-gpu17.21019.1 +3 -0
- runs/Apr26_12-24-19_pg-gpu17/events.out.tfevents.1650968746.pg-gpu17.21019.0 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +1320 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.0,
|
| 3 |
+
"train_loss": 2.493601185993256,
|
| 4 |
+
"train_runtime": 53594.8094,
|
| 5 |
+
"train_samples": 102693,
|
| 6 |
+
"train_samples_per_second": 13.413,
|
| 7 |
+
"train_steps_per_second": 1.677
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": ".",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "relu",
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"is_encoder_decoder": true,
|
| 15 |
+
"layer_norm_epsilon": 1e-06,
|
| 16 |
+
"model_type": "t5",
|
| 17 |
+
"n_positions": 512,
|
| 18 |
+
"num_decoder_layers": 6,
|
| 19 |
+
"num_heads": 8,
|
| 20 |
+
"num_layers": 32,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.15.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32100
|
| 29 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7be0a98101ff985985ff669a29c3e8b1e3ad8c4a6247242141fdbf77c4c382c2
|
| 3 |
+
size 569246164
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaa0ea21cf52c19d65b15b8d56e15056a6991dce40ec0186e6d2f2430ea448b5
|
| 3 |
+
size 569387035
|
runs/Apr26_12-24-19_pg-gpu17/1650968746.6344287/events.out.tfevents.1650968746.pg-gpu17.21019.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5eba0347ed933674202aff8a9bf6341015fd32eee92495aa4bc50fbf75a72f8
|
| 3 |
+
size 5127
|
runs/Apr26_12-24-19_pg-gpu17/events.out.tfevents.1650968746.pg-gpu17.21019.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17c905a9e84aad9dd0dec22e1aa29ba80f54d64b9cd21e22f51d45f337f0e26c
|
| 3 |
+
size 41594
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dffd01fc009b7e92d98eddff8853983e271b41302ed0d363000e8581df12000
|
| 3 |
+
size 817200
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3141082199baf81889949195a4f60fdcc9079cba7e3982f37224d374aadf25c3
|
| 3 |
+
size 569947488
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "special_tokens_map_file": null, "name_or_path": "stefan-it/it5-efficient-small-el32", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.0,
|
| 3 |
+
"train_loss": 2.493601185993256,
|
| 4 |
+
"train_runtime": 53594.8094,
|
| 5 |
+
"train_samples": 102693,
|
| 6 |
+
"train_samples_per_second": 13.413,
|
| 7 |
+
"train_steps_per_second": 1.677
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1320 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"global_step": 89859,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 0.0002983307181250626,
|
| 13 |
+
"loss": 3.5314,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 0.00029666143625012515,
|
| 19 |
+
"loss": 3.2698,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 0.00029499215437518776,
|
| 25 |
+
"loss": 3.1741,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 0.0002933228725002504,
|
| 31 |
+
"loss": 3.1591,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.19,
|
| 36 |
+
"learning_rate": 0.000291653590625313,
|
| 37 |
+
"loss": 3.0795,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.23,
|
| 42 |
+
"learning_rate": 0.00028998430875037555,
|
| 43 |
+
"loss": 3.0526,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 0.00028831502687543816,
|
| 49 |
+
"loss": 3.0228,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.31,
|
| 54 |
+
"learning_rate": 0.0002866457450005008,
|
| 55 |
+
"loss": 2.9966,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.35,
|
| 60 |
+
"learning_rate": 0.0002849764631255634,
|
| 61 |
+
"loss": 2.9799,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.39,
|
| 66 |
+
"learning_rate": 0.00028330718125062595,
|
| 67 |
+
"loss": 2.9632,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.39,
|
| 72 |
+
"eval_gen_len": 18.7655,
|
| 73 |
+
"eval_loss": 2.559084892272949,
|
| 74 |
+
"eval_rouge1": 25.8521,
|
| 75 |
+
"eval_rouge2": 11.6024,
|
| 76 |
+
"eval_rougeL": 21.0887,
|
| 77 |
+
"eval_rougeLsum": 22.857,
|
| 78 |
+
"eval_runtime": 625.5093,
|
| 79 |
+
"eval_samples_per_second": 20.521,
|
| 80 |
+
"eval_steps_per_second": 2.566,
|
| 81 |
+
"step": 5000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.43,
|
| 85 |
+
"learning_rate": 0.00028163789937568856,
|
| 86 |
+
"loss": 2.9402,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.47,
|
| 91 |
+
"learning_rate": 0.0002799686175007512,
|
| 92 |
+
"loss": 2.9157,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.51,
|
| 97 |
+
"learning_rate": 0.00027829933562581373,
|
| 98 |
+
"loss": 2.9143,
|
| 99 |
+
"step": 6500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.55,
|
| 103 |
+
"learning_rate": 0.00027663005375087635,
|
| 104 |
+
"loss": 2.8869,
|
| 105 |
+
"step": 7000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.58,
|
| 109 |
+
"learning_rate": 0.0002749607718759389,
|
| 110 |
+
"loss": 2.9195,
|
| 111 |
+
"step": 7500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.62,
|
| 115 |
+
"learning_rate": 0.0002732914900010015,
|
| 116 |
+
"loss": 2.8558,
|
| 117 |
+
"step": 8000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.66,
|
| 121 |
+
"learning_rate": 0.00027162220812606414,
|
| 122 |
+
"loss": 2.8594,
|
| 123 |
+
"step": 8500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.7,
|
| 127 |
+
"learning_rate": 0.00026995292625112675,
|
| 128 |
+
"loss": 2.8485,
|
| 129 |
+
"step": 9000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.74,
|
| 133 |
+
"learning_rate": 0.0002682836443761893,
|
| 134 |
+
"loss": 2.8491,
|
| 135 |
+
"step": 9500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.78,
|
| 139 |
+
"learning_rate": 0.0002666143625012519,
|
| 140 |
+
"loss": 2.8327,
|
| 141 |
+
"step": 10000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.78,
|
| 145 |
+
"eval_gen_len": 18.8331,
|
| 146 |
+
"eval_loss": 2.4890213012695312,
|
| 147 |
+
"eval_rouge1": 26.508,
|
| 148 |
+
"eval_rouge2": 12.2564,
|
| 149 |
+
"eval_rougeL": 21.7467,
|
| 150 |
+
"eval_rougeLsum": 23.5474,
|
| 151 |
+
"eval_runtime": 624.7506,
|
| 152 |
+
"eval_samples_per_second": 20.546,
|
| 153 |
+
"eval_steps_per_second": 2.569,
|
| 154 |
+
"step": 10000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.82,
|
| 158 |
+
"learning_rate": 0.00026494508062631454,
|
| 159 |
+
"loss": 2.8157,
|
| 160 |
+
"step": 10500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.86,
|
| 164 |
+
"learning_rate": 0.00026327579875137715,
|
| 165 |
+
"loss": 2.8001,
|
| 166 |
+
"step": 11000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.9,
|
| 170 |
+
"learning_rate": 0.0002616065168764397,
|
| 171 |
+
"loss": 2.84,
|
| 172 |
+
"step": 11500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.93,
|
| 176 |
+
"learning_rate": 0.0002599372350015023,
|
| 177 |
+
"loss": 2.8051,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.97,
|
| 182 |
+
"learning_rate": 0.00025826795312656494,
|
| 183 |
+
"loss": 2.8138,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.01,
|
| 188 |
+
"learning_rate": 0.00025659867125162755,
|
| 189 |
+
"loss": 2.7677,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.05,
|
| 194 |
+
"learning_rate": 0.0002549293893766901,
|
| 195 |
+
"loss": 2.6905,
|
| 196 |
+
"step": 13500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.09,
|
| 200 |
+
"learning_rate": 0.0002532601075017527,
|
| 201 |
+
"loss": 2.709,
|
| 202 |
+
"step": 14000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.13,
|
| 206 |
+
"learning_rate": 0.00025159082562681534,
|
| 207 |
+
"loss": 2.7136,
|
| 208 |
+
"step": 14500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.17,
|
| 212 |
+
"learning_rate": 0.00024992154375187795,
|
| 213 |
+
"loss": 2.6873,
|
| 214 |
+
"step": 15000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.17,
|
| 218 |
+
"eval_gen_len": 18.8424,
|
| 219 |
+
"eval_loss": 2.4520416259765625,
|
| 220 |
+
"eval_rouge1": 26.8614,
|
| 221 |
+
"eval_rouge2": 12.7032,
|
| 222 |
+
"eval_rougeL": 22.0965,
|
| 223 |
+
"eval_rougeLsum": 23.832,
|
| 224 |
+
"eval_runtime": 623.6597,
|
| 225 |
+
"eval_samples_per_second": 20.582,
|
| 226 |
+
"eval_steps_per_second": 2.574,
|
| 227 |
+
"step": 15000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.21,
|
| 231 |
+
"learning_rate": 0.0002482522618769405,
|
| 232 |
+
"loss": 2.6962,
|
| 233 |
+
"step": 15500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.25,
|
| 237 |
+
"learning_rate": 0.0002465829800020031,
|
| 238 |
+
"loss": 2.6779,
|
| 239 |
+
"step": 16000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.29,
|
| 243 |
+
"learning_rate": 0.00024491369812706574,
|
| 244 |
+
"loss": 2.6964,
|
| 245 |
+
"step": 16500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.32,
|
| 249 |
+
"learning_rate": 0.00024324441625212832,
|
| 250 |
+
"loss": 2.7048,
|
| 251 |
+
"step": 17000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.36,
|
| 255 |
+
"learning_rate": 0.00024157513437719094,
|
| 256 |
+
"loss": 2.6687,
|
| 257 |
+
"step": 17500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.4,
|
| 261 |
+
"learning_rate": 0.00023990585250225352,
|
| 262 |
+
"loss": 2.6869,
|
| 263 |
+
"step": 18000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.44,
|
| 267 |
+
"learning_rate": 0.00023823657062731608,
|
| 268 |
+
"loss": 2.678,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.48,
|
| 273 |
+
"learning_rate": 0.0002365672887523787,
|
| 274 |
+
"loss": 2.6544,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.52,
|
| 279 |
+
"learning_rate": 0.00023489800687744128,
|
| 280 |
+
"loss": 2.6591,
|
| 281 |
+
"step": 19500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.56,
|
| 285 |
+
"learning_rate": 0.0002332287250025039,
|
| 286 |
+
"loss": 2.6572,
|
| 287 |
+
"step": 20000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.56,
|
| 291 |
+
"eval_gen_len": 18.727,
|
| 292 |
+
"eval_loss": 2.4031243324279785,
|
| 293 |
+
"eval_rouge1": 27.0114,
|
| 294 |
+
"eval_rouge2": 12.8148,
|
| 295 |
+
"eval_rougeL": 22.2407,
|
| 296 |
+
"eval_rougeLsum": 24.0602,
|
| 297 |
+
"eval_runtime": 626.2755,
|
| 298 |
+
"eval_samples_per_second": 20.496,
|
| 299 |
+
"eval_steps_per_second": 2.563,
|
| 300 |
+
"step": 20000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.6,
|
| 304 |
+
"learning_rate": 0.00023155944312756648,
|
| 305 |
+
"loss": 2.628,
|
| 306 |
+
"step": 20500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.64,
|
| 310 |
+
"learning_rate": 0.0002298901612526291,
|
| 311 |
+
"loss": 2.6544,
|
| 312 |
+
"step": 21000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.67,
|
| 316 |
+
"learning_rate": 0.00022822087937769168,
|
| 317 |
+
"loss": 2.6792,
|
| 318 |
+
"step": 21500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.71,
|
| 322 |
+
"learning_rate": 0.0002265515975027543,
|
| 323 |
+
"loss": 2.6493,
|
| 324 |
+
"step": 22000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.75,
|
| 328 |
+
"learning_rate": 0.00022488231562781688,
|
| 329 |
+
"loss": 2.6385,
|
| 330 |
+
"step": 22500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.79,
|
| 334 |
+
"learning_rate": 0.0002232130337528795,
|
| 335 |
+
"loss": 2.6368,
|
| 336 |
+
"step": 23000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.83,
|
| 340 |
+
"learning_rate": 0.00022154375187794208,
|
| 341 |
+
"loss": 2.6319,
|
| 342 |
+
"step": 23500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.87,
|
| 346 |
+
"learning_rate": 0.0002198744700030047,
|
| 347 |
+
"loss": 2.6764,
|
| 348 |
+
"step": 24000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.91,
|
| 352 |
+
"learning_rate": 0.00021820518812806729,
|
| 353 |
+
"loss": 2.6729,
|
| 354 |
+
"step": 24500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.95,
|
| 358 |
+
"learning_rate": 0.0002165359062531299,
|
| 359 |
+
"loss": 2.6461,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.95,
|
| 364 |
+
"eval_gen_len": 18.7416,
|
| 365 |
+
"eval_loss": 2.391615629196167,
|
| 366 |
+
"eval_rouge1": 27.2287,
|
| 367 |
+
"eval_rouge2": 12.9935,
|
| 368 |
+
"eval_rougeL": 22.4718,
|
| 369 |
+
"eval_rougeLsum": 24.2517,
|
| 370 |
+
"eval_runtime": 622.8089,
|
| 371 |
+
"eval_samples_per_second": 20.61,
|
| 372 |
+
"eval_steps_per_second": 2.577,
|
| 373 |
+
"step": 25000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.99,
|
| 377 |
+
"learning_rate": 0.00021486662437819249,
|
| 378 |
+
"loss": 2.6244,
|
| 379 |
+
"step": 25500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.03,
|
| 383 |
+
"learning_rate": 0.0002131973425032551,
|
| 384 |
+
"loss": 2.5805,
|
| 385 |
+
"step": 26000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.06,
|
| 389 |
+
"learning_rate": 0.00021152806062831769,
|
| 390 |
+
"loss": 2.5407,
|
| 391 |
+
"step": 26500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.1,
|
| 395 |
+
"learning_rate": 0.00020985877875338027,
|
| 396 |
+
"loss": 2.5537,
|
| 397 |
+
"step": 27000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.14,
|
| 401 |
+
"learning_rate": 0.00020818949687844289,
|
| 402 |
+
"loss": 2.5253,
|
| 403 |
+
"step": 27500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.18,
|
| 407 |
+
"learning_rate": 0.00020652021500350547,
|
| 408 |
+
"loss": 2.5401,
|
| 409 |
+
"step": 28000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.22,
|
| 413 |
+
"learning_rate": 0.00020485093312856809,
|
| 414 |
+
"loss": 2.5245,
|
| 415 |
+
"step": 28500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.26,
|
| 419 |
+
"learning_rate": 0.00020318165125363067,
|
| 420 |
+
"loss": 2.547,
|
| 421 |
+
"step": 29000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.3,
|
| 425 |
+
"learning_rate": 0.00020151236937869329,
|
| 426 |
+
"loss": 2.5377,
|
| 427 |
+
"step": 29500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.34,
|
| 431 |
+
"learning_rate": 0.00019984308750375587,
|
| 432 |
+
"loss": 2.5374,
|
| 433 |
+
"step": 30000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.34,
|
| 437 |
+
"eval_gen_len": 18.8003,
|
| 438 |
+
"eval_loss": 2.3686139583587646,
|
| 439 |
+
"eval_rouge1": 27.5061,
|
| 440 |
+
"eval_rouge2": 13.241,
|
| 441 |
+
"eval_rougeL": 22.6877,
|
| 442 |
+
"eval_rougeLsum": 24.4465,
|
| 443 |
+
"eval_runtime": 629.1948,
|
| 444 |
+
"eval_samples_per_second": 20.401,
|
| 445 |
+
"eval_steps_per_second": 2.551,
|
| 446 |
+
"step": 30000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.38,
|
| 450 |
+
"learning_rate": 0.00019817380562881846,
|
| 451 |
+
"loss": 2.5457,
|
| 452 |
+
"step": 30500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.41,
|
| 456 |
+
"learning_rate": 0.00019650452375388105,
|
| 457 |
+
"loss": 2.5105,
|
| 458 |
+
"step": 31000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.45,
|
| 462 |
+
"learning_rate": 0.00019483524187894366,
|
| 463 |
+
"loss": 2.5367,
|
| 464 |
+
"step": 31500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.49,
|
| 468 |
+
"learning_rate": 0.00019316596000400625,
|
| 469 |
+
"loss": 2.5471,
|
| 470 |
+
"step": 32000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.53,
|
| 474 |
+
"learning_rate": 0.00019149667812906886,
|
| 475 |
+
"loss": 2.5488,
|
| 476 |
+
"step": 32500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.57,
|
| 480 |
+
"learning_rate": 0.00018982739625413145,
|
| 481 |
+
"loss": 2.5402,
|
| 482 |
+
"step": 33000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.61,
|
| 486 |
+
"learning_rate": 0.00018815811437919406,
|
| 487 |
+
"loss": 2.5437,
|
| 488 |
+
"step": 33500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.65,
|
| 492 |
+
"learning_rate": 0.00018648883250425665,
|
| 493 |
+
"loss": 2.5244,
|
| 494 |
+
"step": 34000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.69,
|
| 498 |
+
"learning_rate": 0.00018481955062931923,
|
| 499 |
+
"loss": 2.5389,
|
| 500 |
+
"step": 34500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.73,
|
| 504 |
+
"learning_rate": 0.00018315026875438185,
|
| 505 |
+
"loss": 2.5081,
|
| 506 |
+
"step": 35000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.73,
|
| 510 |
+
"eval_gen_len": 18.7821,
|
| 511 |
+
"eval_loss": 2.3596315383911133,
|
| 512 |
+
"eval_rouge1": 27.4715,
|
| 513 |
+
"eval_rouge2": 13.2862,
|
| 514 |
+
"eval_rougeL": 22.7022,
|
| 515 |
+
"eval_rougeLsum": 24.4252,
|
| 516 |
+
"eval_runtime": 624.9994,
|
| 517 |
+
"eval_samples_per_second": 20.538,
|
| 518 |
+
"eval_steps_per_second": 2.568,
|
| 519 |
+
"step": 35000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.77,
|
| 523 |
+
"learning_rate": 0.00018148098687944443,
|
| 524 |
+
"loss": 2.5425,
|
| 525 |
+
"step": 35500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.8,
|
| 529 |
+
"learning_rate": 0.00017981170500450705,
|
| 530 |
+
"loss": 2.5245,
|
| 531 |
+
"step": 36000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.84,
|
| 535 |
+
"learning_rate": 0.00017814242312956963,
|
| 536 |
+
"loss": 2.506,
|
| 537 |
+
"step": 36500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.88,
|
| 541 |
+
"learning_rate": 0.00017647314125463225,
|
| 542 |
+
"loss": 2.542,
|
| 543 |
+
"step": 37000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.92,
|
| 547 |
+
"learning_rate": 0.00017480385937969483,
|
| 548 |
+
"loss": 2.5252,
|
| 549 |
+
"step": 37500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.96,
|
| 553 |
+
"learning_rate": 0.00017313457750475745,
|
| 554 |
+
"loss": 2.5175,
|
| 555 |
+
"step": 38000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.0,
|
| 559 |
+
"learning_rate": 0.00017146529562982003,
|
| 560 |
+
"loss": 2.5091,
|
| 561 |
+
"step": 38500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.04,
|
| 565 |
+
"learning_rate": 0.00016979601375488265,
|
| 566 |
+
"loss": 2.4468,
|
| 567 |
+
"step": 39000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.08,
|
| 571 |
+
"learning_rate": 0.00016812673187994523,
|
| 572 |
+
"loss": 2.447,
|
| 573 |
+
"step": 39500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.12,
|
| 577 |
+
"learning_rate": 0.00016645745000500785,
|
| 578 |
+
"loss": 2.4152,
|
| 579 |
+
"step": 40000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.12,
|
| 583 |
+
"eval_gen_len": 18.8203,
|
| 584 |
+
"eval_loss": 2.326728105545044,
|
| 585 |
+
"eval_rouge1": 27.9595,
|
| 586 |
+
"eval_rouge2": 13.5813,
|
| 587 |
+
"eval_rougeL": 23.0493,
|
| 588 |
+
"eval_rougeLsum": 24.9203,
|
| 589 |
+
"eval_runtime": 625.9414,
|
| 590 |
+
"eval_samples_per_second": 20.507,
|
| 591 |
+
"eval_steps_per_second": 2.564,
|
| 592 |
+
"step": 40000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 3.15,
|
| 596 |
+
"learning_rate": 0.00016478816813007043,
|
| 597 |
+
"loss": 2.4379,
|
| 598 |
+
"step": 40500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 3.19,
|
| 602 |
+
"learning_rate": 0.00016311888625513305,
|
| 603 |
+
"loss": 2.4489,
|
| 604 |
+
"step": 41000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.23,
|
| 608 |
+
"learning_rate": 0.00016144960438019564,
|
| 609 |
+
"loss": 2.4212,
|
| 610 |
+
"step": 41500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.27,
|
| 614 |
+
"learning_rate": 0.00015978032250525825,
|
| 615 |
+
"loss": 2.4203,
|
| 616 |
+
"step": 42000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.31,
|
| 620 |
+
"learning_rate": 0.0001581110406303208,
|
| 621 |
+
"loss": 2.433,
|
| 622 |
+
"step": 42500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.35,
|
| 626 |
+
"learning_rate": 0.0001564417587553834,
|
| 627 |
+
"loss": 2.432,
|
| 628 |
+
"step": 43000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 3.39,
|
| 632 |
+
"learning_rate": 0.000154772476880446,
|
| 633 |
+
"loss": 2.4299,
|
| 634 |
+
"step": 43500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.43,
|
| 638 |
+
"learning_rate": 0.0001531031950055086,
|
| 639 |
+
"loss": 2.4201,
|
| 640 |
+
"step": 44000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.47,
|
| 644 |
+
"learning_rate": 0.0001514339131305712,
|
| 645 |
+
"loss": 2.4314,
|
| 646 |
+
"step": 44500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.51,
|
| 650 |
+
"learning_rate": 0.00014976463125563382,
|
| 651 |
+
"loss": 2.4387,
|
| 652 |
+
"step": 45000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.51,
|
| 656 |
+
"eval_gen_len": 18.8376,
|
| 657 |
+
"eval_loss": 2.317692518234253,
|
| 658 |
+
"eval_rouge1": 28.1616,
|
| 659 |
+
"eval_rouge2": 13.668,
|
| 660 |
+
"eval_rougeL": 23.1738,
|
| 661 |
+
"eval_rougeLsum": 25.0342,
|
| 662 |
+
"eval_runtime": 622.4609,
|
| 663 |
+
"eval_samples_per_second": 20.621,
|
| 664 |
+
"eval_steps_per_second": 2.578,
|
| 665 |
+
"step": 45000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.54,
|
| 669 |
+
"learning_rate": 0.0001480953493806964,
|
| 670 |
+
"loss": 2.4389,
|
| 671 |
+
"step": 45500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.58,
|
| 675 |
+
"learning_rate": 0.000146426067505759,
|
| 676 |
+
"loss": 2.4363,
|
| 677 |
+
"step": 46000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.62,
|
| 681 |
+
"learning_rate": 0.0001447567856308216,
|
| 682 |
+
"loss": 2.4395,
|
| 683 |
+
"step": 46500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.66,
|
| 687 |
+
"learning_rate": 0.0001430875037558842,
|
| 688 |
+
"loss": 2.4418,
|
| 689 |
+
"step": 47000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.7,
|
| 693 |
+
"learning_rate": 0.0001414182218809468,
|
| 694 |
+
"loss": 2.4201,
|
| 695 |
+
"step": 47500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.74,
|
| 699 |
+
"learning_rate": 0.0001397489400060094,
|
| 700 |
+
"loss": 2.4169,
|
| 701 |
+
"step": 48000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.78,
|
| 705 |
+
"learning_rate": 0.000138079658131072,
|
| 706 |
+
"loss": 2.4009,
|
| 707 |
+
"step": 48500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 3.82,
|
| 711 |
+
"learning_rate": 0.0001364103762561346,
|
| 712 |
+
"loss": 2.4279,
|
| 713 |
+
"step": 49000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.86,
|
| 717 |
+
"learning_rate": 0.0001347410943811972,
|
| 718 |
+
"loss": 2.4307,
|
| 719 |
+
"step": 49500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.89,
|
| 723 |
+
"learning_rate": 0.0001330718125062598,
|
| 724 |
+
"loss": 2.4387,
|
| 725 |
+
"step": 50000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 3.89,
|
| 729 |
+
"eval_gen_len": 18.7872,
|
| 730 |
+
"eval_loss": 2.3016672134399414,
|
| 731 |
+
"eval_rouge1": 28.1111,
|
| 732 |
+
"eval_rouge2": 13.569,
|
| 733 |
+
"eval_rougeL": 23.1312,
|
| 734 |
+
"eval_rougeLsum": 24.9912,
|
| 735 |
+
"eval_runtime": 628.1204,
|
| 736 |
+
"eval_samples_per_second": 20.436,
|
| 737 |
+
"eval_steps_per_second": 2.555,
|
| 738 |
+
"step": 50000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.93,
|
| 742 |
+
"learning_rate": 0.0001314025306313224,
|
| 743 |
+
"loss": 2.4143,
|
| 744 |
+
"step": 50500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.97,
|
| 748 |
+
"learning_rate": 0.000129733248756385,
|
| 749 |
+
"loss": 2.4197,
|
| 750 |
+
"step": 51000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 4.01,
|
| 754 |
+
"learning_rate": 0.00012806396688144758,
|
| 755 |
+
"loss": 2.4084,
|
| 756 |
+
"step": 51500
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 4.05,
|
| 760 |
+
"learning_rate": 0.00012639468500651017,
|
| 761 |
+
"loss": 2.3544,
|
| 762 |
+
"step": 52000
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 4.09,
|
| 766 |
+
"learning_rate": 0.00012472540313157278,
|
| 767 |
+
"loss": 2.332,
|
| 768 |
+
"step": 52500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.13,
|
| 772 |
+
"learning_rate": 0.00012305612125663537,
|
| 773 |
+
"loss": 2.3597,
|
| 774 |
+
"step": 53000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.17,
|
| 778 |
+
"learning_rate": 0.00012138683938169798,
|
| 779 |
+
"loss": 2.3492,
|
| 780 |
+
"step": 53500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.21,
|
| 784 |
+
"learning_rate": 0.00011971755750676058,
|
| 785 |
+
"loss": 2.3679,
|
| 786 |
+
"step": 54000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.25,
|
| 790 |
+
"learning_rate": 0.00011804827563182318,
|
| 791 |
+
"loss": 2.3633,
|
| 792 |
+
"step": 54500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 4.28,
|
| 796 |
+
"learning_rate": 0.00011637899375688578,
|
| 797 |
+
"loss": 2.3467,
|
| 798 |
+
"step": 55000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 4.28,
|
| 802 |
+
"eval_gen_len": 18.8334,
|
| 803 |
+
"eval_loss": 2.3123602867126465,
|
| 804 |
+
"eval_rouge1": 28.0679,
|
| 805 |
+
"eval_rouge2": 13.7123,
|
| 806 |
+
"eval_rougeL": 23.1516,
|
| 807 |
+
"eval_rougeLsum": 25.0002,
|
| 808 |
+
"eval_runtime": 622.7792,
|
| 809 |
+
"eval_samples_per_second": 20.611,
|
| 810 |
+
"eval_steps_per_second": 2.577,
|
| 811 |
+
"step": 55000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.32,
|
| 815 |
+
"learning_rate": 0.00011470971188194838,
|
| 816 |
+
"loss": 2.3579,
|
| 817 |
+
"step": 55500
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 4.36,
|
| 821 |
+
"learning_rate": 0.00011304043000701098,
|
| 822 |
+
"loss": 2.3501,
|
| 823 |
+
"step": 56000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 4.4,
|
| 827 |
+
"learning_rate": 0.00011137114813207358,
|
| 828 |
+
"loss": 2.3592,
|
| 829 |
+
"step": 56500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.44,
|
| 833 |
+
"learning_rate": 0.00010970186625713618,
|
| 834 |
+
"loss": 2.344,
|
| 835 |
+
"step": 57000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.48,
|
| 839 |
+
"learning_rate": 0.00010803258438219876,
|
| 840 |
+
"loss": 2.3578,
|
| 841 |
+
"step": 57500
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.52,
|
| 845 |
+
"learning_rate": 0.00010636330250726136,
|
| 846 |
+
"loss": 2.3407,
|
| 847 |
+
"step": 58000
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 4.56,
|
| 851 |
+
"learning_rate": 0.00010469402063232396,
|
| 852 |
+
"loss": 2.3452,
|
| 853 |
+
"step": 58500
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 4.6,
|
| 857 |
+
"learning_rate": 0.00010302473875738656,
|
| 858 |
+
"loss": 2.3465,
|
| 859 |
+
"step": 59000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 4.64,
|
| 863 |
+
"learning_rate": 0.00010135545688244916,
|
| 864 |
+
"loss": 2.3687,
|
| 865 |
+
"step": 59500
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 4.67,
|
| 869 |
+
"learning_rate": 9.968617500751176e-05,
|
| 870 |
+
"loss": 2.3367,
|
| 871 |
+
"step": 60000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.67,
|
| 875 |
+
"eval_gen_len": 18.835,
|
| 876 |
+
"eval_loss": 2.2966153621673584,
|
| 877 |
+
"eval_rouge1": 28.293,
|
| 878 |
+
"eval_rouge2": 13.9084,
|
| 879 |
+
"eval_rougeL": 23.3359,
|
| 880 |
+
"eval_rougeLsum": 25.1789,
|
| 881 |
+
"eval_runtime": 625.9275,
|
| 882 |
+
"eval_samples_per_second": 20.507,
|
| 883 |
+
"eval_steps_per_second": 2.564,
|
| 884 |
+
"step": 60000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.71,
|
| 888 |
+
"learning_rate": 9.801689313257436e-05,
|
| 889 |
+
"loss": 2.3306,
|
| 890 |
+
"step": 60500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.75,
|
| 894 |
+
"learning_rate": 9.634761125763696e-05,
|
| 895 |
+
"loss": 2.3497,
|
| 896 |
+
"step": 61000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.79,
|
| 900 |
+
"learning_rate": 9.467832938269956e-05,
|
| 901 |
+
"loss": 2.3313,
|
| 902 |
+
"step": 61500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.83,
|
| 906 |
+
"learning_rate": 9.300904750776216e-05,
|
| 907 |
+
"loss": 2.3427,
|
| 908 |
+
"step": 62000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.87,
|
| 912 |
+
"learning_rate": 9.133976563282476e-05,
|
| 913 |
+
"loss": 2.3259,
|
| 914 |
+
"step": 62500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.91,
|
| 918 |
+
"learning_rate": 8.967048375788736e-05,
|
| 919 |
+
"loss": 2.3544,
|
| 920 |
+
"step": 63000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.95,
|
| 924 |
+
"learning_rate": 8.800120188294995e-05,
|
| 925 |
+
"loss": 2.3307,
|
| 926 |
+
"step": 63500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 4.99,
|
| 930 |
+
"learning_rate": 8.633192000801255e-05,
|
| 931 |
+
"loss": 2.3477,
|
| 932 |
+
"step": 64000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 5.02,
|
| 936 |
+
"learning_rate": 8.466263813307513e-05,
|
| 937 |
+
"loss": 2.3064,
|
| 938 |
+
"step": 64500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 5.06,
|
| 942 |
+
"learning_rate": 8.299335625813773e-05,
|
| 943 |
+
"loss": 2.2882,
|
| 944 |
+
"step": 65000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 5.06,
|
| 948 |
+
"eval_gen_len": 18.7974,
|
| 949 |
+
"eval_loss": 2.2921857833862305,
|
| 950 |
+
"eval_rouge1": 28.3828,
|
| 951 |
+
"eval_rouge2": 14.0129,
|
| 952 |
+
"eval_rougeL": 23.443,
|
| 953 |
+
"eval_rougeLsum": 25.3001,
|
| 954 |
+
"eval_runtime": 621.9943,
|
| 955 |
+
"eval_samples_per_second": 20.637,
|
| 956 |
+
"eval_steps_per_second": 2.58,
|
| 957 |
+
"step": 65000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 5.1,
|
| 961 |
+
"learning_rate": 8.132407438320033e-05,
|
| 962 |
+
"loss": 2.2733,
|
| 963 |
+
"step": 65500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 5.14,
|
| 967 |
+
"learning_rate": 7.965479250826293e-05,
|
| 968 |
+
"loss": 2.2869,
|
| 969 |
+
"step": 66000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 5.18,
|
| 973 |
+
"learning_rate": 7.798551063332553e-05,
|
| 974 |
+
"loss": 2.2904,
|
| 975 |
+
"step": 66500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 5.22,
|
| 979 |
+
"learning_rate": 7.631622875838813e-05,
|
| 980 |
+
"loss": 2.2516,
|
| 981 |
+
"step": 67000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 5.26,
|
| 985 |
+
"learning_rate": 7.464694688345073e-05,
|
| 986 |
+
"loss": 2.2835,
|
| 987 |
+
"step": 67500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 5.3,
|
| 991 |
+
"learning_rate": 7.297766500851333e-05,
|
| 992 |
+
"loss": 2.2802,
|
| 993 |
+
"step": 68000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.34,
|
| 997 |
+
"learning_rate": 7.130838313357593e-05,
|
| 998 |
+
"loss": 2.2779,
|
| 999 |
+
"step": 68500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.38,
|
| 1003 |
+
"learning_rate": 6.963910125863853e-05,
|
| 1004 |
+
"loss": 2.274,
|
| 1005 |
+
"step": 69000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 5.41,
|
| 1009 |
+
"learning_rate": 6.796981938370112e-05,
|
| 1010 |
+
"loss": 2.2908,
|
| 1011 |
+
"step": 69500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 5.45,
|
| 1015 |
+
"learning_rate": 6.630053750876372e-05,
|
| 1016 |
+
"loss": 2.2782,
|
| 1017 |
+
"step": 70000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.45,
|
| 1021 |
+
"eval_gen_len": 18.8495,
|
| 1022 |
+
"eval_loss": 2.2865357398986816,
|
| 1023 |
+
"eval_rouge1": 28.3987,
|
| 1024 |
+
"eval_rouge2": 13.9705,
|
| 1025 |
+
"eval_rougeL": 23.4227,
|
| 1026 |
+
"eval_rougeLsum": 25.3263,
|
| 1027 |
+
"eval_runtime": 625.1399,
|
| 1028 |
+
"eval_samples_per_second": 20.533,
|
| 1029 |
+
"eval_steps_per_second": 2.567,
|
| 1030 |
+
"step": 70000
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 5.49,
|
| 1034 |
+
"learning_rate": 6.463125563382632e-05,
|
| 1035 |
+
"loss": 2.2882,
|
| 1036 |
+
"step": 70500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 5.53,
|
| 1040 |
+
"learning_rate": 6.296197375888892e-05,
|
| 1041 |
+
"loss": 2.2802,
|
| 1042 |
+
"step": 71000
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 5.57,
|
| 1046 |
+
"learning_rate": 6.129269188395152e-05,
|
| 1047 |
+
"loss": 2.2774,
|
| 1048 |
+
"step": 71500
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 5.61,
|
| 1052 |
+
"learning_rate": 5.9623410009014114e-05,
|
| 1053 |
+
"loss": 2.31,
|
| 1054 |
+
"step": 72000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 5.65,
|
| 1058 |
+
"learning_rate": 5.7954128134076714e-05,
|
| 1059 |
+
"loss": 2.2829,
|
| 1060 |
+
"step": 72500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 5.69,
|
| 1064 |
+
"learning_rate": 5.6284846259139314e-05,
|
| 1065 |
+
"loss": 2.2971,
|
| 1066 |
+
"step": 73000
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 5.73,
|
| 1070 |
+
"learning_rate": 5.4615564384201915e-05,
|
| 1071 |
+
"loss": 2.2824,
|
| 1072 |
+
"step": 73500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 5.76,
|
| 1076 |
+
"learning_rate": 5.294628250926451e-05,
|
| 1077 |
+
"loss": 2.2754,
|
| 1078 |
+
"step": 74000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 5.8,
|
| 1082 |
+
"learning_rate": 5.127700063432711e-05,
|
| 1083 |
+
"loss": 2.2893,
|
| 1084 |
+
"step": 74500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 5.84,
|
| 1088 |
+
"learning_rate": 4.960771875938971e-05,
|
| 1089 |
+
"loss": 2.2788,
|
| 1090 |
+
"step": 75000
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 5.84,
|
| 1094 |
+
"eval_gen_len": 18.7967,
|
| 1095 |
+
"eval_loss": 2.278130531311035,
|
| 1096 |
+
"eval_rouge1": 28.4256,
|
| 1097 |
+
"eval_rouge2": 14.0668,
|
| 1098 |
+
"eval_rougeL": 23.4947,
|
| 1099 |
+
"eval_rougeLsum": 25.3403,
|
| 1100 |
+
"eval_runtime": 622.5919,
|
| 1101 |
+
"eval_samples_per_second": 20.617,
|
| 1102 |
+
"eval_steps_per_second": 2.578,
|
| 1103 |
+
"step": 75000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 5.88,
|
| 1107 |
+
"learning_rate": 4.793843688445231e-05,
|
| 1108 |
+
"loss": 2.2898,
|
| 1109 |
+
"step": 75500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.92,
|
| 1113 |
+
"learning_rate": 4.62691550095149e-05,
|
| 1114 |
+
"loss": 2.281,
|
| 1115 |
+
"step": 76000
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 5.96,
|
| 1119 |
+
"learning_rate": 4.45998731345775e-05,
|
| 1120 |
+
"loss": 2.28,
|
| 1121 |
+
"step": 76500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 6.0,
|
| 1125 |
+
"learning_rate": 4.2930591259640095e-05,
|
| 1126 |
+
"loss": 2.269,
|
| 1127 |
+
"step": 77000
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 6.04,
|
| 1131 |
+
"learning_rate": 4.1261309384702695e-05,
|
| 1132 |
+
"loss": 2.2428,
|
| 1133 |
+
"step": 77500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 6.08,
|
| 1137 |
+
"learning_rate": 3.9592027509765295e-05,
|
| 1138 |
+
"loss": 2.2627,
|
| 1139 |
+
"step": 78000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 6.12,
|
| 1143 |
+
"learning_rate": 3.7922745634827896e-05,
|
| 1144 |
+
"loss": 2.2219,
|
| 1145 |
+
"step": 78500
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 6.15,
|
| 1149 |
+
"learning_rate": 3.625346375989049e-05,
|
| 1150 |
+
"loss": 2.218,
|
| 1151 |
+
"step": 79000
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 6.19,
|
| 1155 |
+
"learning_rate": 3.458418188495309e-05,
|
| 1156 |
+
"loss": 2.2205,
|
| 1157 |
+
"step": 79500
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 6.23,
|
| 1161 |
+
"learning_rate": 3.291490001001569e-05,
|
| 1162 |
+
"loss": 2.239,
|
| 1163 |
+
"step": 80000
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 6.23,
|
| 1167 |
+
"eval_gen_len": 18.8384,
|
| 1168 |
+
"eval_loss": 2.2816860675811768,
|
| 1169 |
+
"eval_rouge1": 28.4681,
|
| 1170 |
+
"eval_rouge2": 14.0835,
|
| 1171 |
+
"eval_rougeL": 23.5141,
|
| 1172 |
+
"eval_rougeLsum": 25.4023,
|
| 1173 |
+
"eval_runtime": 624.366,
|
| 1174 |
+
"eval_samples_per_second": 20.558,
|
| 1175 |
+
"eval_steps_per_second": 2.571,
|
| 1176 |
+
"step": 80000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 6.27,
|
| 1180 |
+
"learning_rate": 3.124561813507828e-05,
|
| 1181 |
+
"loss": 2.2095,
|
| 1182 |
+
"step": 80500
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 6.31,
|
| 1186 |
+
"learning_rate": 2.9576336260140883e-05,
|
| 1187 |
+
"loss": 2.2441,
|
| 1188 |
+
"step": 81000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 6.35,
|
| 1192 |
+
"learning_rate": 2.7907054385203483e-05,
|
| 1193 |
+
"loss": 2.2292,
|
| 1194 |
+
"step": 81500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 6.39,
|
| 1198 |
+
"learning_rate": 2.623777251026608e-05,
|
| 1199 |
+
"loss": 2.2482,
|
| 1200 |
+
"step": 82000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.43,
|
| 1204 |
+
"learning_rate": 2.456849063532868e-05,
|
| 1205 |
+
"loss": 2.2243,
|
| 1206 |
+
"step": 82500
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 6.47,
|
| 1210 |
+
"learning_rate": 2.289920876039128e-05,
|
| 1211 |
+
"loss": 2.2177,
|
| 1212 |
+
"step": 83000
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.5,
|
| 1216 |
+
"learning_rate": 2.1229926885453873e-05,
|
| 1217 |
+
"loss": 2.2317,
|
| 1218 |
+
"step": 83500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 6.54,
|
| 1222 |
+
"learning_rate": 1.9560645010516473e-05,
|
| 1223 |
+
"loss": 2.2311,
|
| 1224 |
+
"step": 84000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 6.58,
|
| 1228 |
+
"learning_rate": 1.7891363135579073e-05,
|
| 1229 |
+
"loss": 2.2446,
|
| 1230 |
+
"step": 84500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 6.62,
|
| 1234 |
+
"learning_rate": 1.622208126064167e-05,
|
| 1235 |
+
"loss": 2.2324,
|
| 1236 |
+
"step": 85000
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 6.62,
|
| 1240 |
+
"eval_gen_len": 18.8369,
|
| 1241 |
+
"eval_loss": 2.27907395362854,
|
| 1242 |
+
"eval_rouge1": 28.5356,
|
| 1243 |
+
"eval_rouge2": 14.1871,
|
| 1244 |
+
"eval_rougeL": 23.5477,
|
| 1245 |
+
"eval_rougeLsum": 25.4279,
|
| 1246 |
+
"eval_runtime": 621.3714,
|
| 1247 |
+
"eval_samples_per_second": 20.658,
|
| 1248 |
+
"eval_steps_per_second": 2.583,
|
| 1249 |
+
"step": 85000
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 6.66,
|
| 1253 |
+
"learning_rate": 1.4552799385704269e-05,
|
| 1254 |
+
"loss": 2.241,
|
| 1255 |
+
"step": 85500
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 6.7,
|
| 1259 |
+
"learning_rate": 1.2883517510766869e-05,
|
| 1260 |
+
"loss": 2.2262,
|
| 1261 |
+
"step": 86000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 6.74,
|
| 1265 |
+
"learning_rate": 1.1214235635829465e-05,
|
| 1266 |
+
"loss": 2.2456,
|
| 1267 |
+
"step": 86500
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 6.78,
|
| 1271 |
+
"learning_rate": 9.544953760892062e-06,
|
| 1272 |
+
"loss": 2.2237,
|
| 1273 |
+
"step": 87000
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 6.82,
|
| 1277 |
+
"learning_rate": 7.875671885954662e-06,
|
| 1278 |
+
"loss": 2.2294,
|
| 1279 |
+
"step": 87500
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 6.86,
|
| 1283 |
+
"learning_rate": 6.20639001101726e-06,
|
| 1284 |
+
"loss": 2.2184,
|
| 1285 |
+
"step": 88000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 6.89,
|
| 1289 |
+
"learning_rate": 4.537108136079858e-06,
|
| 1290 |
+
"loss": 2.2167,
|
| 1291 |
+
"step": 88500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 6.93,
|
| 1295 |
+
"learning_rate": 2.867826261142456e-06,
|
| 1296 |
+
"loss": 2.2478,
|
| 1297 |
+
"step": 89000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 6.97,
|
| 1301 |
+
"learning_rate": 1.1985443862050543e-06,
|
| 1302 |
+
"loss": 2.2596,
|
| 1303 |
+
"step": 89500
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 7.0,
|
| 1307 |
+
"step": 89859,
|
| 1308 |
+
"total_flos": 2.6510315204815258e+17,
|
| 1309 |
+
"train_loss": 2.493601185993256,
|
| 1310 |
+
"train_runtime": 53594.8094,
|
| 1311 |
+
"train_samples_per_second": 13.413,
|
| 1312 |
+
"train_steps_per_second": 1.677
|
| 1313 |
+
}
|
| 1314 |
+
],
|
| 1315 |
+
"max_steps": 89859,
|
| 1316 |
+
"num_train_epochs": 7,
|
| 1317 |
+
"total_flos": 2.6510315204815258e+17,
|
| 1318 |
+
"trial_name": null,
|
| 1319 |
+
"trial_params": null
|
| 1320 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2c27343e796a5535886a9562fd8c08ea59e7a94148f452d945a6e0ed6c70685
|
| 3 |
+
size 3183
|