add files
Browse files- all_results.json +15 -0
- config.json +62 -0
- hypothesis.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +0 -0
- tokenizer_config.json +1 -0
- train_results.json +6 -0
- trainer_state.json +676 -0
- training_args.bin +3 -0
- val_results.json +12 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.114575496670289,
|
| 3 |
+
"train_n_objs": -1,
|
| 4 |
+
"train_runtime": 28429.155,
|
| 5 |
+
"train_samples_per_second": 0.352,
|
| 6 |
+
"val_gen_len": 48.8,
|
| 7 |
+
"val_loss": 1.3495,
|
| 8 |
+
"val_n_objs": 500,
|
| 9 |
+
"val_rouge1": 35.2922,
|
| 10 |
+
"val_rouge2": 15.3773,
|
| 11 |
+
"val_rougeL": 26.3842,
|
| 12 |
+
"val_rougeLsum": 32.2879,
|
| 13 |
+
"val_runtime": 161.8901,
|
| 14 |
+
"val_samples_per_second": 3.089
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"early_stopping": true,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"length_penalty": 2.0,
|
| 18 |
+
"max_length": 200,
|
| 19 |
+
"min_length": 30,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"n_positions": 512,
|
| 22 |
+
"no_repeat_ngram_size": 3,
|
| 23 |
+
"num_beams": 4,
|
| 24 |
+
"num_decoder_layers": 12,
|
| 25 |
+
"num_heads": 12,
|
| 26 |
+
"num_layers": 12,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"prefix": "summarize: ",
|
| 30 |
+
"relative_attention_num_buckets": 32,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"summarization": {
|
| 33 |
+
"early_stopping": true,
|
| 34 |
+
"length_penalty": 2.0,
|
| 35 |
+
"max_length": 200,
|
| 36 |
+
"min_length": 30,
|
| 37 |
+
"no_repeat_ngram_size": 3,
|
| 38 |
+
"num_beams": 4,
|
| 39 |
+
"prefix": "summarize: "
|
| 40 |
+
},
|
| 41 |
+
"translation_en_to_de": {
|
| 42 |
+
"early_stopping": true,
|
| 43 |
+
"max_length": 300,
|
| 44 |
+
"num_beams": 4,
|
| 45 |
+
"prefix": "translate English to German: "
|
| 46 |
+
},
|
| 47 |
+
"translation_en_to_fr": {
|
| 48 |
+
"early_stopping": true,
|
| 49 |
+
"max_length": 300,
|
| 50 |
+
"num_beams": 4,
|
| 51 |
+
"prefix": "translate English to French: "
|
| 52 |
+
},
|
| 53 |
+
"translation_en_to_ro": {
|
| 54 |
+
"early_stopping": true,
|
| 55 |
+
"max_length": 300,
|
| 56 |
+
"num_beams": 4,
|
| 57 |
+
"prefix": "translate English to Romanian: "
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 32128
|
| 62 |
+
}
|
hypothesis.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57e16e0d570c38cd2c36268eef1dc640d3f2d9efad6dd2232efde598dcb55831
|
| 3 |
+
size 891737400
|
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
|
Binary file (792 kB). View file
|
|
|
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>"], "model_max_length": 512, "name_or_path": "t5-base"}
|
train_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.114575496670289,
|
| 3 |
+
"train_n_objs": -1,
|
| 4 |
+
"train_runtime": 28429.155,
|
| 5 |
+
"train_samples_per_second": 0.352
|
| 6 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.114575496670289,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.00011145476329794645,
|
| 12 |
+
"learning_rate": 9.999000000000001e-05,
|
| 13 |
+
"loss": 8.06905746459961,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.011145476329794644,
|
| 18 |
+
"learning_rate": 9.900000000000001e-05,
|
| 19 |
+
"loss": 1.7745859165384312,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02229095265958929,
|
| 24 |
+
"learning_rate": 9.8e-05,
|
| 25 |
+
"loss": 1.4695932006835937,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03343642898938393,
|
| 30 |
+
"learning_rate": 9.7e-05,
|
| 31 |
+
"loss": 1.471973876953125,
|
| 32 |
+
"step": 300
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04458190531917858,
|
| 36 |
+
"learning_rate": 9.6e-05,
|
| 37 |
+
"loss": 1.4246876525878907,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05572738164897322,
|
| 42 |
+
"learning_rate": 9.5e-05,
|
| 43 |
+
"loss": 1.4235630798339844,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06687285797876787,
|
| 48 |
+
"learning_rate": 9.4e-05,
|
| 49 |
+
"loss": 1.4458001708984376,
|
| 50 |
+
"step": 600
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.07801833430856252,
|
| 54 |
+
"learning_rate": 9.300000000000001e-05,
|
| 55 |
+
"loss": 1.4168995666503905,
|
| 56 |
+
"step": 700
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.08916381063835715,
|
| 60 |
+
"learning_rate": 9.200000000000001e-05,
|
| 61 |
+
"loss": 1.432281494140625,
|
| 62 |
+
"step": 800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.1003092869681518,
|
| 66 |
+
"learning_rate": 9.1e-05,
|
| 67 |
+
"loss": 1.3954049682617187,
|
| 68 |
+
"step": 900
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.11145476329794644,
|
| 72 |
+
"learning_rate": 9e-05,
|
| 73 |
+
"loss": 1.41295654296875,
|
| 74 |
+
"step": 1000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.1226002396277411,
|
| 78 |
+
"learning_rate": 8.900000000000001e-05,
|
| 79 |
+
"loss": 1.4206352233886719,
|
| 80 |
+
"step": 1100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13374571595753573,
|
| 84 |
+
"learning_rate": 8.800000000000001e-05,
|
| 85 |
+
"loss": 1.4066107177734375,
|
| 86 |
+
"step": 1200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.14489119228733038,
|
| 90 |
+
"learning_rate": 8.7e-05,
|
| 91 |
+
"loss": 1.3928131103515624,
|
| 92 |
+
"step": 1300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.15603666861712503,
|
| 96 |
+
"learning_rate": 8.6e-05,
|
| 97 |
+
"loss": 1.4154879760742187,
|
| 98 |
+
"step": 1400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.16718214494691966,
|
| 102 |
+
"learning_rate": 8.5e-05,
|
| 103 |
+
"loss": 1.4014813232421874,
|
| 104 |
+
"step": 1500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1783276212767143,
|
| 108 |
+
"learning_rate": 8.4e-05,
|
| 109 |
+
"loss": 1.3965155029296874,
|
| 110 |
+
"step": 1600
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.18947309760650896,
|
| 114 |
+
"learning_rate": 8.3e-05,
|
| 115 |
+
"loss": 1.3976228332519531,
|
| 116 |
+
"step": 1700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.2006185739363036,
|
| 120 |
+
"learning_rate": 8.2e-05,
|
| 121 |
+
"loss": 1.3655722045898437,
|
| 122 |
+
"step": 1800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21176405026609824,
|
| 126 |
+
"learning_rate": 8.1e-05,
|
| 127 |
+
"loss": 1.3941130065917968,
|
| 128 |
+
"step": 1900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2229095265958929,
|
| 132 |
+
"learning_rate": 8e-05,
|
| 133 |
+
"loss": 1.389833984375,
|
| 134 |
+
"step": 2000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.23405500292568754,
|
| 138 |
+
"learning_rate": 7.900000000000001e-05,
|
| 139 |
+
"loss": 1.3948770141601563,
|
| 140 |
+
"step": 2100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.2452004792554822,
|
| 144 |
+
"learning_rate": 7.800000000000001e-05,
|
| 145 |
+
"loss": 1.3855517578125,
|
| 146 |
+
"step": 2200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.25634595558527684,
|
| 150 |
+
"learning_rate": 7.7e-05,
|
| 151 |
+
"loss": 1.4055433654785157,
|
| 152 |
+
"step": 2300
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.26749143191507146,
|
| 156 |
+
"learning_rate": 7.6e-05,
|
| 157 |
+
"loss": 1.3657418823242187,
|
| 158 |
+
"step": 2400
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.2786369082448661,
|
| 162 |
+
"learning_rate": 7.500000000000001e-05,
|
| 163 |
+
"loss": 1.3927548217773438,
|
| 164 |
+
"step": 2500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2786369082448661,
|
| 168 |
+
"eval_gen_len": 50.3,
|
| 169 |
+
"eval_loss": 1.3837015628814697,
|
| 170 |
+
"eval_rouge1": 35.4891,
|
| 171 |
+
"eval_rouge2": 15.6119,
|
| 172 |
+
"eval_rougeL": 26.4862,
|
| 173 |
+
"eval_rougeLsum": 32.3041,
|
| 174 |
+
"eval_runtime": 163.7005,
|
| 175 |
+
"eval_samples_per_second": 3.054,
|
| 176 |
+
"step": 2500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.28978238457466077,
|
| 180 |
+
"learning_rate": 7.4e-05,
|
| 181 |
+
"loss": 1.3879615783691406,
|
| 182 |
+
"step": 2600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.3009278609044554,
|
| 186 |
+
"learning_rate": 7.3e-05,
|
| 187 |
+
"loss": 1.3767970275878907,
|
| 188 |
+
"step": 2700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.31207333723425007,
|
| 192 |
+
"learning_rate": 7.2e-05,
|
| 193 |
+
"loss": 1.3870814514160157,
|
| 194 |
+
"step": 2800
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.3232188135640447,
|
| 198 |
+
"learning_rate": 7.1e-05,
|
| 199 |
+
"loss": 1.3717910766601562,
|
| 200 |
+
"step": 2900
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.3343642898938393,
|
| 204 |
+
"learning_rate": 7e-05,
|
| 205 |
+
"loss": 1.3754934692382812,
|
| 206 |
+
"step": 3000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.345509766223634,
|
| 210 |
+
"learning_rate": 6.9e-05,
|
| 211 |
+
"loss": 1.3606668090820313,
|
| 212 |
+
"step": 3100
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3566552425534286,
|
| 216 |
+
"learning_rate": 6.800000000000001e-05,
|
| 217 |
+
"loss": 1.359674530029297,
|
| 218 |
+
"step": 3200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.3678007188832233,
|
| 222 |
+
"learning_rate": 6.7e-05,
|
| 223 |
+
"loss": 1.37053955078125,
|
| 224 |
+
"step": 3300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.3789461952130179,
|
| 228 |
+
"learning_rate": 6.6e-05,
|
| 229 |
+
"loss": 1.3728164672851562,
|
| 230 |
+
"step": 3400
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.39009167154281255,
|
| 234 |
+
"learning_rate": 6.500000000000001e-05,
|
| 235 |
+
"loss": 1.3717462158203124,
|
| 236 |
+
"step": 3500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.4012371478726072,
|
| 240 |
+
"learning_rate": 6.400000000000001e-05,
|
| 241 |
+
"loss": 1.3698835754394532,
|
| 242 |
+
"step": 3600
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.41238262420240185,
|
| 246 |
+
"learning_rate": 6.3e-05,
|
| 247 |
+
"loss": 1.3624909973144532,
|
| 248 |
+
"step": 3700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.42352810053219647,
|
| 252 |
+
"learning_rate": 6.2e-05,
|
| 253 |
+
"loss": 1.365331268310547,
|
| 254 |
+
"step": 3800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.43467357686199115,
|
| 258 |
+
"learning_rate": 6.1e-05,
|
| 259 |
+
"loss": 1.3554270935058594,
|
| 260 |
+
"step": 3900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.4458190531917858,
|
| 264 |
+
"learning_rate": 6e-05,
|
| 265 |
+
"loss": 1.3769105529785157,
|
| 266 |
+
"step": 4000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.45696452952158045,
|
| 270 |
+
"learning_rate": 5.9e-05,
|
| 271 |
+
"loss": 1.3486868286132812,
|
| 272 |
+
"step": 4100
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.4681100058513751,
|
| 276 |
+
"learning_rate": 5.8e-05,
|
| 277 |
+
"loss": 1.3736349487304687,
|
| 278 |
+
"step": 4200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.4792554821811697,
|
| 282 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 283 |
+
"loss": 1.3558815002441407,
|
| 284 |
+
"step": 4300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.4904009585109644,
|
| 288 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 289 |
+
"loss": 1.3559271240234374,
|
| 290 |
+
"step": 4400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.501546434840759,
|
| 294 |
+
"learning_rate": 5.500000000000001e-05,
|
| 295 |
+
"loss": 1.349674530029297,
|
| 296 |
+
"step": 4500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5126919111705537,
|
| 300 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 301 |
+
"loss": 1.3654806518554687,
|
| 302 |
+
"step": 4600
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.5238373875003483,
|
| 306 |
+
"learning_rate": 5.300000000000001e-05,
|
| 307 |
+
"loss": 1.359230499267578,
|
| 308 |
+
"step": 4700
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.5349828638301429,
|
| 312 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 313 |
+
"loss": 1.359907684326172,
|
| 314 |
+
"step": 4800
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.5461283401599376,
|
| 318 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 319 |
+
"loss": 1.3600314331054688,
|
| 320 |
+
"step": 4900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.5572738164897322,
|
| 324 |
+
"learning_rate": 5e-05,
|
| 325 |
+
"loss": 1.3618020629882812,
|
| 326 |
+
"step": 5000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.5572738164897322,
|
| 330 |
+
"eval_gen_len": 49.3,
|
| 331 |
+
"eval_loss": 1.3626569509506226,
|
| 332 |
+
"eval_rouge1": 35.3235,
|
| 333 |
+
"eval_rouge2": 15.308,
|
| 334 |
+
"eval_rougeL": 26.6971,
|
| 335 |
+
"eval_rougeLsum": 32.2475,
|
| 336 |
+
"eval_runtime": 163.5583,
|
| 337 |
+
"eval_samples_per_second": 3.057,
|
| 338 |
+
"step": 5000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5684192928195269,
|
| 342 |
+
"learning_rate": 4.9e-05,
|
| 343 |
+
"loss": 1.3476010131835938,
|
| 344 |
+
"step": 5100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.5795647691493215,
|
| 348 |
+
"learning_rate": 4.8e-05,
|
| 349 |
+
"loss": 1.3705815124511718,
|
| 350 |
+
"step": 5200
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.5907102454791162,
|
| 354 |
+
"learning_rate": 4.7e-05,
|
| 355 |
+
"loss": 1.3650910949707031,
|
| 356 |
+
"step": 5300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.6018557218089108,
|
| 360 |
+
"learning_rate": 4.600000000000001e-05,
|
| 361 |
+
"loss": 1.3458297729492188,
|
| 362 |
+
"step": 5400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.6130011981387055,
|
| 366 |
+
"learning_rate": 4.5e-05,
|
| 367 |
+
"loss": 1.3574575805664062,
|
| 368 |
+
"step": 5500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.6241466744685001,
|
| 372 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 373 |
+
"loss": 1.3446278381347656,
|
| 374 |
+
"step": 5600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6352921507982947,
|
| 378 |
+
"learning_rate": 4.3e-05,
|
| 379 |
+
"loss": 1.3720254516601562,
|
| 380 |
+
"step": 5700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6464376271280894,
|
| 384 |
+
"learning_rate": 4.2e-05,
|
| 385 |
+
"loss": 1.3550611877441405,
|
| 386 |
+
"step": 5800
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.6575831034578841,
|
| 390 |
+
"learning_rate": 4.1e-05,
|
| 391 |
+
"loss": 1.3649459838867188,
|
| 392 |
+
"step": 5900
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.6687285797876786,
|
| 396 |
+
"learning_rate": 4e-05,
|
| 397 |
+
"loss": 1.3249327087402343,
|
| 398 |
+
"step": 6000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.6798740561174733,
|
| 402 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 403 |
+
"loss": 1.3522917175292968,
|
| 404 |
+
"step": 6100
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.691019532447268,
|
| 408 |
+
"learning_rate": 3.8e-05,
|
| 409 |
+
"loss": 1.3376327514648438,
|
| 410 |
+
"step": 6200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7021650087770626,
|
| 414 |
+
"learning_rate": 3.7e-05,
|
| 415 |
+
"loss": 1.3476719665527344,
|
| 416 |
+
"step": 6300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7133104851068572,
|
| 420 |
+
"learning_rate": 3.6e-05,
|
| 421 |
+
"loss": 1.3413494873046874,
|
| 422 |
+
"step": 6400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7244559614366519,
|
| 426 |
+
"learning_rate": 3.5e-05,
|
| 427 |
+
"loss": 1.3463385009765625,
|
| 428 |
+
"step": 6500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.7356014377664466,
|
| 432 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 433 |
+
"loss": 1.346422882080078,
|
| 434 |
+
"step": 6600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.7467469140962412,
|
| 438 |
+
"learning_rate": 3.3e-05,
|
| 439 |
+
"loss": 1.3565861511230468,
|
| 440 |
+
"step": 6700
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.7578923904260358,
|
| 444 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 445 |
+
"loss": 1.3385652160644532,
|
| 446 |
+
"step": 6800
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7690378667558305,
|
| 450 |
+
"learning_rate": 3.1e-05,
|
| 451 |
+
"loss": 1.3510641479492187,
|
| 452 |
+
"step": 6900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.7801833430856251,
|
| 456 |
+
"learning_rate": 3e-05,
|
| 457 |
+
"loss": 1.3658317565917968,
|
| 458 |
+
"step": 7000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7913288194154198,
|
| 462 |
+
"learning_rate": 2.9e-05,
|
| 463 |
+
"loss": 1.3442698669433595,
|
| 464 |
+
"step": 7100
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8024742957452144,
|
| 468 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 469 |
+
"loss": 1.3289457702636718,
|
| 470 |
+
"step": 7200
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.813619772075009,
|
| 474 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 475 |
+
"loss": 1.3627702331542968,
|
| 476 |
+
"step": 7300
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.8247652484048037,
|
| 480 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 481 |
+
"loss": 1.3569662475585937,
|
| 482 |
+
"step": 7400
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.8359107247345984,
|
| 486 |
+
"learning_rate": 2.5e-05,
|
| 487 |
+
"loss": 1.3445625305175781,
|
| 488 |
+
"step": 7500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.8359107247345984,
|
| 492 |
+
"eval_gen_len": 49.5,
|
| 493 |
+
"eval_loss": 1.3491926193237305,
|
| 494 |
+
"eval_rouge1": 34.7061,
|
| 495 |
+
"eval_rouge2": 15.2333,
|
| 496 |
+
"eval_rougeL": 26.1848,
|
| 497 |
+
"eval_rougeLsum": 31.7067,
|
| 498 |
+
"eval_runtime": 162.9659,
|
| 499 |
+
"eval_samples_per_second": 3.068,
|
| 500 |
+
"step": 7500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8470562010643929,
|
| 504 |
+
"learning_rate": 2.4e-05,
|
| 505 |
+
"loss": 1.3476835632324218,
|
| 506 |
+
"step": 7600
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8582016773941876,
|
| 510 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 511 |
+
"loss": 1.329300079345703,
|
| 512 |
+
"step": 7700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.8693471537239823,
|
| 516 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 517 |
+
"loss": 1.3521742248535156,
|
| 518 |
+
"step": 7800
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.8804926300537769,
|
| 522 |
+
"learning_rate": 2.1e-05,
|
| 523 |
+
"loss": 1.3405534362792968,
|
| 524 |
+
"step": 7900
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.8916381063835715,
|
| 528 |
+
"learning_rate": 2e-05,
|
| 529 |
+
"loss": 1.3501358032226562,
|
| 530 |
+
"step": 8000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.9027835827133662,
|
| 534 |
+
"learning_rate": 1.9e-05,
|
| 535 |
+
"loss": 1.3406822204589843,
|
| 536 |
+
"step": 8100
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.9139290590431609,
|
| 540 |
+
"learning_rate": 1.8e-05,
|
| 541 |
+
"loss": 1.3406187438964843,
|
| 542 |
+
"step": 8200
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9250745353729555,
|
| 546 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 547 |
+
"loss": 1.3410650634765624,
|
| 548 |
+
"step": 8300
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9362200117027502,
|
| 552 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 553 |
+
"loss": 1.3546810913085938,
|
| 554 |
+
"step": 8400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.9473654880325448,
|
| 558 |
+
"learning_rate": 1.5e-05,
|
| 559 |
+
"loss": 1.330055694580078,
|
| 560 |
+
"step": 8500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.9585109643623394,
|
| 564 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 565 |
+
"loss": 1.325668487548828,
|
| 566 |
+
"step": 8600
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.9696564406921341,
|
| 570 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 571 |
+
"loss": 1.331268310546875,
|
| 572 |
+
"step": 8700
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.9808019170219288,
|
| 576 |
+
"learning_rate": 1.2e-05,
|
| 577 |
+
"loss": 1.346514892578125,
|
| 578 |
+
"step": 8800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.9919473933517233,
|
| 582 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 583 |
+
"loss": 1.3515042114257811,
|
| 584 |
+
"step": 8900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0031207333723424,
|
| 588 |
+
"learning_rate": 1e-05,
|
| 589 |
+
"loss": 1.3323361206054687,
|
| 590 |
+
"step": 9000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.014266209702137,
|
| 594 |
+
"learning_rate": 9e-06,
|
| 595 |
+
"loss": 1.2915484619140625,
|
| 596 |
+
"step": 9100
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.0254116860319318,
|
| 600 |
+
"learning_rate": 8.000000000000001e-06,
|
| 601 |
+
"loss": 1.2769253540039063,
|
| 602 |
+
"step": 9200
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.0365571623617265,
|
| 606 |
+
"learning_rate": 7.000000000000001e-06,
|
| 607 |
+
"loss": 1.2951361083984374,
|
| 608 |
+
"step": 9300
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.0477026386915211,
|
| 612 |
+
"learning_rate": 6e-06,
|
| 613 |
+
"loss": 1.30968505859375,
|
| 614 |
+
"step": 9400
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.0588481150213158,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 1.2824142456054688,
|
| 620 |
+
"step": 9500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.0699935913511103,
|
| 624 |
+
"learning_rate": 4.000000000000001e-06,
|
| 625 |
+
"loss": 1.2977745056152343,
|
| 626 |
+
"step": 9600
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.081139067680905,
|
| 630 |
+
"learning_rate": 3e-06,
|
| 631 |
+
"loss": 1.296290283203125,
|
| 632 |
+
"step": 9700
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.0922845440106996,
|
| 636 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 637 |
+
"loss": 1.301255645751953,
|
| 638 |
+
"step": 9800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.1034300203404943,
|
| 642 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 643 |
+
"loss": 1.28552490234375,
|
| 644 |
+
"step": 9900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.114575496670289,
|
| 648 |
+
"learning_rate": 0.0,
|
| 649 |
+
"loss": 1.2935409545898438,
|
| 650 |
+
"step": 10000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.114575496670289,
|
| 654 |
+
"eval_gen_len": 48.8,
|
| 655 |
+
"eval_loss": 1.3494852781295776,
|
| 656 |
+
"eval_rouge1": 35.2792,
|
| 657 |
+
"eval_rouge2": 15.3645,
|
| 658 |
+
"eval_rougeL": 26.3329,
|
| 659 |
+
"eval_rougeLsum": 32.2724,
|
| 660 |
+
"eval_runtime": 161.2437,
|
| 661 |
+
"eval_samples_per_second": 3.101,
|
| 662 |
+
"step": 10000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.114575496670289,
|
| 666 |
+
"step": 10000,
|
| 667 |
+
"train_runtime": 28429.155,
|
| 668 |
+
"train_samples_per_second": 0.352
|
| 669 |
+
}
|
| 670 |
+
],
|
| 671 |
+
"max_steps": 10000,
|
| 672 |
+
"num_train_epochs": 2,
|
| 673 |
+
"total_flos": 454127617474172928,
|
| 674 |
+
"trial_name": null,
|
| 675 |
+
"trial_params": null
|
| 676 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abd4729da194ceaf2f5024cfe68ad929c628a1b1ac6a9074511b2b0e8883df71
|
| 3 |
+
size 2095
|
val_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.114575496670289,
|
| 3 |
+
"val_gen_len": 48.8,
|
| 4 |
+
"val_loss": 1.3495,
|
| 5 |
+
"val_n_objs": 500,
|
| 6 |
+
"val_rouge1": 35.2922,
|
| 7 |
+
"val_rouge2": 15.3773,
|
| 8 |
+
"val_rougeL": 26.3842,
|
| 9 |
+
"val_rougeLsum": 32.2879,
|
| 10 |
+
"val_runtime": 161.8901,
|
| 11 |
+
"val_samples_per_second": 3.089
|
| 12 |
+
}
|