Upload 12 files
Browse files- all_results.json +22 -0
- config.json +60 -0
- eval_results.json +10 -0
- generated_predictions.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
- train_results.json +8 -0
- trainer_state.json +723 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 1.8179,
|
| 4 |
+
"eval_gen_len": 22.5684,
|
| 5 |
+
"eval_loss": 3.1342360973358154,
|
| 6 |
+
"eval_runtime": 209.2446,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 27.007,
|
| 9 |
+
"eval_steps_per_second": 1.352,
|
| 10 |
+
"predict_bleu": 1.8793,
|
| 11 |
+
"predict_gen_len": 22.9004,
|
| 12 |
+
"predict_loss": 3.1284537315368652,
|
| 13 |
+
"predict_runtime": 214.036,
|
| 14 |
+
"predict_samples": 5482,
|
| 15 |
+
"predict_samples_per_second": 25.613,
|
| 16 |
+
"predict_steps_per_second": 1.285,
|
| 17 |
+
"train_loss": 3.1156047950088093,
|
| 18 |
+
"train_runtime": 18325.9577,
|
| 19 |
+
"train_samples": 27018,
|
| 20 |
+
"train_samples_per_second": 73.715,
|
| 21 |
+
"train_steps_per_second": 0.919
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": false,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 6,
|
| 21 |
+
"num_heads": 8,
|
| 22 |
+
"num_layers": 6,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.24.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32103
|
| 60 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 1.8179,
|
| 4 |
+
"eval_gen_len": 22.5684,
|
| 5 |
+
"eval_loss": 3.1342360973358154,
|
| 6 |
+
"eval_runtime": 209.2446,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 27.007,
|
| 9 |
+
"eval_steps_per_second": 1.352
|
| 10 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 1.8793,
|
| 3 |
+
"predict_gen_len": 22.9004,
|
| 4 |
+
"predict_loss": 3.1284537315368652,
|
| 5 |
+
"predict_runtime": 214.036,
|
| 6 |
+
"predict_samples": 5482,
|
| 7 |
+
"predict_samples_per_second": 25.613,
|
| 8 |
+
"predict_steps_per_second": 1.285
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:214d4ac9a6653ee3b74c509195e4afb7c3b9d10c68d096f6ed10ff72d213ac5a
|
| 3 |
+
size 242020441
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"name_or_path": "t5-small",
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"special_tokens_map_file": null,
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 3.1156047950088093,
|
| 4 |
+
"train_runtime": 18325.9577,
|
| 5 |
+
"train_samples": 27018,
|
| 6 |
+
"train_samples_per_second": 73.715,
|
| 7 |
+
"train_steps_per_second": 0.919
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.99777942264989,
|
| 5 |
+
"global_step": 16850,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_bleu": 0.8119,
|
| 13 |
+
"eval_gen_len": 15.295,
|
| 14 |
+
"eval_loss": 3.3328945636749268,
|
| 15 |
+
"eval_runtime": 64.1416,
|
| 16 |
+
"eval_samples_per_second": 88.102,
|
| 17 |
+
"eval_steps_per_second": 4.412,
|
| 18 |
+
"step": 337
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.48,
|
| 22 |
+
"learning_rate": 4.851632047477745e-05,
|
| 23 |
+
"loss": 3.528,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_bleu": 0.9197,
|
| 29 |
+
"eval_gen_len": 15.3056,
|
| 30 |
+
"eval_loss": 3.283737897872925,
|
| 31 |
+
"eval_runtime": 63.9504,
|
| 32 |
+
"eval_samples_per_second": 88.365,
|
| 33 |
+
"eval_steps_per_second": 4.425,
|
| 34 |
+
"step": 674
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.97,
|
| 38 |
+
"learning_rate": 4.70326409495549e-05,
|
| 39 |
+
"loss": 3.3932,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_bleu": 0.9536,
|
| 45 |
+
"eval_gen_len": 15.6238,
|
| 46 |
+
"eval_loss": 3.2553622722625732,
|
| 47 |
+
"eval_runtime": 62.6609,
|
| 48 |
+
"eval_samples_per_second": 90.184,
|
| 49 |
+
"eval_steps_per_second": 4.516,
|
| 50 |
+
"step": 1011
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_bleu": 1.0082,
|
| 55 |
+
"eval_gen_len": 15.5254,
|
| 56 |
+
"eval_loss": 3.236884117126465,
|
| 57 |
+
"eval_runtime": 62.9428,
|
| 58 |
+
"eval_samples_per_second": 89.78,
|
| 59 |
+
"eval_steps_per_second": 4.496,
|
| 60 |
+
"step": 1348
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.45,
|
| 64 |
+
"learning_rate": 4.554896142433235e-05,
|
| 65 |
+
"loss": 3.3394,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.0,
|
| 70 |
+
"eval_bleu": 1.088,
|
| 71 |
+
"eval_gen_len": 15.7466,
|
| 72 |
+
"eval_loss": 3.222892999649048,
|
| 73 |
+
"eval_runtime": 64.2741,
|
| 74 |
+
"eval_samples_per_second": 87.92,
|
| 75 |
+
"eval_steps_per_second": 4.403,
|
| 76 |
+
"step": 1685
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.93,
|
| 80 |
+
"learning_rate": 4.4065281899109794e-05,
|
| 81 |
+
"loss": 3.2982,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 6.0,
|
| 86 |
+
"eval_bleu": 1.1295,
|
| 87 |
+
"eval_gen_len": 15.7866,
|
| 88 |
+
"eval_loss": 3.210378885269165,
|
| 89 |
+
"eval_runtime": 64.1493,
|
| 90 |
+
"eval_samples_per_second": 88.091,
|
| 91 |
+
"eval_steps_per_second": 4.412,
|
| 92 |
+
"step": 2022
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_bleu": 1.1648,
|
| 97 |
+
"eval_gen_len": 15.6852,
|
| 98 |
+
"eval_loss": 3.200908899307251,
|
| 99 |
+
"eval_runtime": 63.0315,
|
| 100 |
+
"eval_samples_per_second": 89.654,
|
| 101 |
+
"eval_steps_per_second": 4.49,
|
| 102 |
+
"step": 2359
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.42,
|
| 106 |
+
"learning_rate": 4.258160237388724e-05,
|
| 107 |
+
"loss": 3.2658,
|
| 108 |
+
"step": 2500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_bleu": 1.1548,
|
| 113 |
+
"eval_gen_len": 15.9358,
|
| 114 |
+
"eval_loss": 3.191558361053467,
|
| 115 |
+
"eval_runtime": 64.0034,
|
| 116 |
+
"eval_samples_per_second": 88.292,
|
| 117 |
+
"eval_steps_per_second": 4.422,
|
| 118 |
+
"step": 2696
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 8.9,
|
| 122 |
+
"learning_rate": 4.109792284866469e-05,
|
| 123 |
+
"loss": 3.2397,
|
| 124 |
+
"step": 3000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 9.0,
|
| 128 |
+
"eval_bleu": 1.0651,
|
| 129 |
+
"eval_gen_len": 16.0241,
|
| 130 |
+
"eval_loss": 3.1847681999206543,
|
| 131 |
+
"eval_runtime": 64.3166,
|
| 132 |
+
"eval_samples_per_second": 87.862,
|
| 133 |
+
"eval_steps_per_second": 4.4,
|
| 134 |
+
"step": 3033
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"eval_bleu": 1.1443,
|
| 139 |
+
"eval_gen_len": 16.0409,
|
| 140 |
+
"eval_loss": 3.1797027587890625,
|
| 141 |
+
"eval_runtime": 62.6803,
|
| 142 |
+
"eval_samples_per_second": 90.156,
|
| 143 |
+
"eval_steps_per_second": 4.515,
|
| 144 |
+
"step": 3370
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.38,
|
| 148 |
+
"learning_rate": 3.961424332344214e-05,
|
| 149 |
+
"loss": 3.2203,
|
| 150 |
+
"step": 3500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.0,
|
| 154 |
+
"eval_bleu": 1.1562,
|
| 155 |
+
"eval_gen_len": 15.9648,
|
| 156 |
+
"eval_loss": 3.1735124588012695,
|
| 157 |
+
"eval_runtime": 64.1808,
|
| 158 |
+
"eval_samples_per_second": 88.048,
|
| 159 |
+
"eval_steps_per_second": 4.409,
|
| 160 |
+
"step": 3707
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 11.87,
|
| 164 |
+
"learning_rate": 3.8130563798219586e-05,
|
| 165 |
+
"loss": 3.1935,
|
| 166 |
+
"step": 4000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 12.0,
|
| 170 |
+
"eval_bleu": 1.145,
|
| 171 |
+
"eval_gen_len": 15.7811,
|
| 172 |
+
"eval_loss": 3.1689915657043457,
|
| 173 |
+
"eval_runtime": 62.6765,
|
| 174 |
+
"eval_samples_per_second": 90.161,
|
| 175 |
+
"eval_steps_per_second": 4.515,
|
| 176 |
+
"step": 4044
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_bleu": 1.1534,
|
| 181 |
+
"eval_gen_len": 15.9582,
|
| 182 |
+
"eval_loss": 3.1667888164520264,
|
| 183 |
+
"eval_runtime": 64.2839,
|
| 184 |
+
"eval_samples_per_second": 87.907,
|
| 185 |
+
"eval_steps_per_second": 4.402,
|
| 186 |
+
"step": 4381
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 13.35,
|
| 190 |
+
"learning_rate": 3.664688427299703e-05,
|
| 191 |
+
"loss": 3.1791,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 14.0,
|
| 196 |
+
"eval_bleu": 1.1476,
|
| 197 |
+
"eval_gen_len": 15.9605,
|
| 198 |
+
"eval_loss": 3.1629080772399902,
|
| 199 |
+
"eval_runtime": 63.0085,
|
| 200 |
+
"eval_samples_per_second": 89.686,
|
| 201 |
+
"eval_steps_per_second": 4.491,
|
| 202 |
+
"step": 4718
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 14.83,
|
| 206 |
+
"learning_rate": 3.516320474777448e-05,
|
| 207 |
+
"loss": 3.1562,
|
| 208 |
+
"step": 5000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 15.0,
|
| 212 |
+
"eval_bleu": 1.1504,
|
| 213 |
+
"eval_gen_len": 15.9747,
|
| 214 |
+
"eval_loss": 3.1592817306518555,
|
| 215 |
+
"eval_runtime": 63.8036,
|
| 216 |
+
"eval_samples_per_second": 88.569,
|
| 217 |
+
"eval_steps_per_second": 4.435,
|
| 218 |
+
"step": 5055
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"eval_bleu": 1.2003,
|
| 223 |
+
"eval_gen_len": 15.6548,
|
| 224 |
+
"eval_loss": 3.1569018363952637,
|
| 225 |
+
"eval_runtime": 63.7567,
|
| 226 |
+
"eval_samples_per_second": 88.634,
|
| 227 |
+
"eval_steps_per_second": 4.439,
|
| 228 |
+
"step": 5392
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.32,
|
| 232 |
+
"learning_rate": 3.3679525222551934e-05,
|
| 233 |
+
"loss": 3.1461,
|
| 234 |
+
"step": 5500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 17.0,
|
| 238 |
+
"eval_bleu": 1.187,
|
| 239 |
+
"eval_gen_len": 16.2831,
|
| 240 |
+
"eval_loss": 3.1528096199035645,
|
| 241 |
+
"eval_runtime": 62.8317,
|
| 242 |
+
"eval_samples_per_second": 89.939,
|
| 243 |
+
"eval_steps_per_second": 4.504,
|
| 244 |
+
"step": 5729
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 17.8,
|
| 248 |
+
"learning_rate": 3.219584569732938e-05,
|
| 249 |
+
"loss": 3.1301,
|
| 250 |
+
"step": 6000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 18.0,
|
| 254 |
+
"eval_bleu": 1.1908,
|
| 255 |
+
"eval_gen_len": 16.2078,
|
| 256 |
+
"eval_loss": 3.15116024017334,
|
| 257 |
+
"eval_runtime": 62.7949,
|
| 258 |
+
"eval_samples_per_second": 89.991,
|
| 259 |
+
"eval_steps_per_second": 4.507,
|
| 260 |
+
"step": 6066
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_bleu": 1.2164,
|
| 265 |
+
"eval_gen_len": 16.1816,
|
| 266 |
+
"eval_loss": 3.149709463119507,
|
| 267 |
+
"eval_runtime": 63.3277,
|
| 268 |
+
"eval_samples_per_second": 89.234,
|
| 269 |
+
"eval_steps_per_second": 4.469,
|
| 270 |
+
"step": 6403
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 19.29,
|
| 274 |
+
"learning_rate": 3.071216617210683e-05,
|
| 275 |
+
"loss": 3.1199,
|
| 276 |
+
"step": 6500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 20.0,
|
| 280 |
+
"eval_bleu": 1.2493,
|
| 281 |
+
"eval_gen_len": 16.0138,
|
| 282 |
+
"eval_loss": 3.147409200668335,
|
| 283 |
+
"eval_runtime": 62.5603,
|
| 284 |
+
"eval_samples_per_second": 90.329,
|
| 285 |
+
"eval_steps_per_second": 4.524,
|
| 286 |
+
"step": 6740
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.77,
|
| 290 |
+
"learning_rate": 2.9228486646884274e-05,
|
| 291 |
+
"loss": 3.1012,
|
| 292 |
+
"step": 7000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 21.0,
|
| 296 |
+
"eval_bleu": 1.2189,
|
| 297 |
+
"eval_gen_len": 15.9667,
|
| 298 |
+
"eval_loss": 3.1471338272094727,
|
| 299 |
+
"eval_runtime": 62.6224,
|
| 300 |
+
"eval_samples_per_second": 90.239,
|
| 301 |
+
"eval_steps_per_second": 4.519,
|
| 302 |
+
"step": 7077
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 22.0,
|
| 306 |
+
"eval_bleu": 1.2535,
|
| 307 |
+
"eval_gen_len": 16.0239,
|
| 308 |
+
"eval_loss": 3.145897150039673,
|
| 309 |
+
"eval_runtime": 62.7278,
|
| 310 |
+
"eval_samples_per_second": 90.088,
|
| 311 |
+
"eval_steps_per_second": 4.512,
|
| 312 |
+
"step": 7414
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 22.25,
|
| 316 |
+
"learning_rate": 2.774480712166172e-05,
|
| 317 |
+
"loss": 3.0953,
|
| 318 |
+
"step": 7500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 23.0,
|
| 322 |
+
"eval_bleu": 1.2554,
|
| 323 |
+
"eval_gen_len": 15.7225,
|
| 324 |
+
"eval_loss": 3.143968343734741,
|
| 325 |
+
"eval_runtime": 63.12,
|
| 326 |
+
"eval_samples_per_second": 89.528,
|
| 327 |
+
"eval_steps_per_second": 4.484,
|
| 328 |
+
"step": 7751
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 23.74,
|
| 332 |
+
"learning_rate": 2.6261127596439174e-05,
|
| 333 |
+
"loss": 3.0761,
|
| 334 |
+
"step": 8000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 24.0,
|
| 338 |
+
"eval_bleu": 1.2086,
|
| 339 |
+
"eval_gen_len": 16.0069,
|
| 340 |
+
"eval_loss": 3.141495943069458,
|
| 341 |
+
"eval_runtime": 62.7045,
|
| 342 |
+
"eval_samples_per_second": 90.121,
|
| 343 |
+
"eval_steps_per_second": 4.513,
|
| 344 |
+
"step": 8088
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"eval_bleu": 1.305,
|
| 349 |
+
"eval_gen_len": 15.9912,
|
| 350 |
+
"eval_loss": 3.1416375637054443,
|
| 351 |
+
"eval_runtime": 62.5621,
|
| 352 |
+
"eval_samples_per_second": 90.326,
|
| 353 |
+
"eval_steps_per_second": 4.524,
|
| 354 |
+
"step": 8425
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 25.22,
|
| 358 |
+
"learning_rate": 2.4777448071216618e-05,
|
| 359 |
+
"loss": 3.0822,
|
| 360 |
+
"step": 8500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 26.0,
|
| 364 |
+
"eval_bleu": 1.248,
|
| 365 |
+
"eval_gen_len": 15.8406,
|
| 366 |
+
"eval_loss": 3.1405673027038574,
|
| 367 |
+
"eval_runtime": 62.6069,
|
| 368 |
+
"eval_samples_per_second": 90.262,
|
| 369 |
+
"eval_steps_per_second": 4.52,
|
| 370 |
+
"step": 8762
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 26.7,
|
| 374 |
+
"learning_rate": 2.3293768545994066e-05,
|
| 375 |
+
"loss": 3.0614,
|
| 376 |
+
"step": 9000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 27.0,
|
| 380 |
+
"eval_bleu": 1.2888,
|
| 381 |
+
"eval_gen_len": 16.3189,
|
| 382 |
+
"eval_loss": 3.140249252319336,
|
| 383 |
+
"eval_runtime": 62.6544,
|
| 384 |
+
"eval_samples_per_second": 90.193,
|
| 385 |
+
"eval_steps_per_second": 4.517,
|
| 386 |
+
"step": 9099
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 28.0,
|
| 390 |
+
"eval_bleu": 1.3016,
|
| 391 |
+
"eval_gen_len": 16.0096,
|
| 392 |
+
"eval_loss": 3.1379010677337646,
|
| 393 |
+
"eval_runtime": 62.5617,
|
| 394 |
+
"eval_samples_per_second": 90.327,
|
| 395 |
+
"eval_steps_per_second": 4.524,
|
| 396 |
+
"step": 9436
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 28.19,
|
| 400 |
+
"learning_rate": 2.1810089020771514e-05,
|
| 401 |
+
"loss": 3.0594,
|
| 402 |
+
"step": 9500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 29.0,
|
| 406 |
+
"eval_bleu": 1.2268,
|
| 407 |
+
"eval_gen_len": 16.3702,
|
| 408 |
+
"eval_loss": 3.139193058013916,
|
| 409 |
+
"eval_runtime": 62.7397,
|
| 410 |
+
"eval_samples_per_second": 90.071,
|
| 411 |
+
"eval_steps_per_second": 4.511,
|
| 412 |
+
"step": 9773
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 29.67,
|
| 416 |
+
"learning_rate": 2.0326409495548962e-05,
|
| 417 |
+
"loss": 3.0453,
|
| 418 |
+
"step": 10000
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 30.0,
|
| 422 |
+
"eval_bleu": 1.278,
|
| 423 |
+
"eval_gen_len": 15.9722,
|
| 424 |
+
"eval_loss": 3.1378531455993652,
|
| 425 |
+
"eval_runtime": 62.634,
|
| 426 |
+
"eval_samples_per_second": 90.223,
|
| 427 |
+
"eval_steps_per_second": 4.518,
|
| 428 |
+
"step": 10110
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"eval_bleu": 1.2832,
|
| 433 |
+
"eval_gen_len": 15.9759,
|
| 434 |
+
"eval_loss": 3.136270046234131,
|
| 435 |
+
"eval_runtime": 62.6958,
|
| 436 |
+
"eval_samples_per_second": 90.134,
|
| 437 |
+
"eval_steps_per_second": 4.514,
|
| 438 |
+
"step": 10447
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 31.16,
|
| 442 |
+
"learning_rate": 1.884272997032641e-05,
|
| 443 |
+
"loss": 3.0425,
|
| 444 |
+
"step": 10500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 32.0,
|
| 448 |
+
"eval_bleu": 1.3089,
|
| 449 |
+
"eval_gen_len": 16.1499,
|
| 450 |
+
"eval_loss": 3.136704206466675,
|
| 451 |
+
"eval_runtime": 62.6194,
|
| 452 |
+
"eval_samples_per_second": 90.244,
|
| 453 |
+
"eval_steps_per_second": 4.519,
|
| 454 |
+
"step": 10784
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 32.64,
|
| 458 |
+
"learning_rate": 1.7359050445103858e-05,
|
| 459 |
+
"loss": 3.0339,
|
| 460 |
+
"step": 11000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 33.0,
|
| 464 |
+
"eval_bleu": 1.2718,
|
| 465 |
+
"eval_gen_len": 16.1051,
|
| 466 |
+
"eval_loss": 3.1367685794830322,
|
| 467 |
+
"eval_runtime": 62.5638,
|
| 468 |
+
"eval_samples_per_second": 90.324,
|
| 469 |
+
"eval_steps_per_second": 4.523,
|
| 470 |
+
"step": 11121
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 34.0,
|
| 474 |
+
"eval_bleu": 1.2683,
|
| 475 |
+
"eval_gen_len": 16.0159,
|
| 476 |
+
"eval_loss": 3.1349706649780273,
|
| 477 |
+
"eval_runtime": 62.675,
|
| 478 |
+
"eval_samples_per_second": 90.164,
|
| 479 |
+
"eval_steps_per_second": 4.515,
|
| 480 |
+
"step": 11458
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 34.12,
|
| 484 |
+
"learning_rate": 1.5875370919881306e-05,
|
| 485 |
+
"loss": 3.0301,
|
| 486 |
+
"step": 11500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 35.0,
|
| 490 |
+
"eval_bleu": 1.286,
|
| 491 |
+
"eval_gen_len": 16.1807,
|
| 492 |
+
"eval_loss": 3.135624408721924,
|
| 493 |
+
"eval_runtime": 62.61,
|
| 494 |
+
"eval_samples_per_second": 90.257,
|
| 495 |
+
"eval_steps_per_second": 4.52,
|
| 496 |
+
"step": 11795
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 35.61,
|
| 500 |
+
"learning_rate": 1.4391691394658754e-05,
|
| 501 |
+
"loss": 3.0197,
|
| 502 |
+
"step": 12000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 36.0,
|
| 506 |
+
"eval_bleu": 1.267,
|
| 507 |
+
"eval_gen_len": 16.0966,
|
| 508 |
+
"eval_loss": 3.1348326206207275,
|
| 509 |
+
"eval_runtime": 62.637,
|
| 510 |
+
"eval_samples_per_second": 90.218,
|
| 511 |
+
"eval_steps_per_second": 4.518,
|
| 512 |
+
"step": 12132
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"eval_bleu": 1.3013,
|
| 517 |
+
"eval_gen_len": 15.9283,
|
| 518 |
+
"eval_loss": 3.1351914405822754,
|
| 519 |
+
"eval_runtime": 62.7389,
|
| 520 |
+
"eval_samples_per_second": 90.072,
|
| 521 |
+
"eval_steps_per_second": 4.511,
|
| 522 |
+
"step": 12469
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 37.09,
|
| 526 |
+
"learning_rate": 1.29080118694362e-05,
|
| 527 |
+
"loss": 3.0204,
|
| 528 |
+
"step": 12500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 38.0,
|
| 532 |
+
"eval_bleu": 1.282,
|
| 533 |
+
"eval_gen_len": 16.0099,
|
| 534 |
+
"eval_loss": 3.1345412731170654,
|
| 535 |
+
"eval_runtime": 62.6541,
|
| 536 |
+
"eval_samples_per_second": 90.194,
|
| 537 |
+
"eval_steps_per_second": 4.517,
|
| 538 |
+
"step": 12806
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 38.57,
|
| 542 |
+
"learning_rate": 1.142433234421365e-05,
|
| 543 |
+
"loss": 3.0169,
|
| 544 |
+
"step": 13000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 39.0,
|
| 548 |
+
"eval_bleu": 1.3076,
|
| 549 |
+
"eval_gen_len": 16.1136,
|
| 550 |
+
"eval_loss": 3.1348047256469727,
|
| 551 |
+
"eval_runtime": 62.7366,
|
| 552 |
+
"eval_samples_per_second": 90.075,
|
| 553 |
+
"eval_steps_per_second": 4.511,
|
| 554 |
+
"step": 13143
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 40.0,
|
| 558 |
+
"eval_bleu": 1.2947,
|
| 559 |
+
"eval_gen_len": 16.0117,
|
| 560 |
+
"eval_loss": 3.135272979736328,
|
| 561 |
+
"eval_runtime": 62.894,
|
| 562 |
+
"eval_samples_per_second": 89.85,
|
| 563 |
+
"eval_steps_per_second": 4.5,
|
| 564 |
+
"step": 13480
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 40.06,
|
| 568 |
+
"learning_rate": 9.940652818991098e-06,
|
| 569 |
+
"loss": 3.0093,
|
| 570 |
+
"step": 13500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 41.0,
|
| 574 |
+
"eval_bleu": 1.3047,
|
| 575 |
+
"eval_gen_len": 16.0662,
|
| 576 |
+
"eval_loss": 3.134445905685425,
|
| 577 |
+
"eval_runtime": 62.7291,
|
| 578 |
+
"eval_samples_per_second": 90.086,
|
| 579 |
+
"eval_steps_per_second": 4.511,
|
| 580 |
+
"step": 13817
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 41.54,
|
| 584 |
+
"learning_rate": 8.456973293768548e-06,
|
| 585 |
+
"loss": 3.0009,
|
| 586 |
+
"step": 14000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 42.0,
|
| 590 |
+
"eval_bleu": 1.3017,
|
| 591 |
+
"eval_gen_len": 16.1531,
|
| 592 |
+
"eval_loss": 3.134453535079956,
|
| 593 |
+
"eval_runtime": 62.7311,
|
| 594 |
+
"eval_samples_per_second": 90.083,
|
| 595 |
+
"eval_steps_per_second": 4.511,
|
| 596 |
+
"step": 14154
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 43.0,
|
| 600 |
+
"eval_bleu": 1.2762,
|
| 601 |
+
"eval_gen_len": 16.0741,
|
| 602 |
+
"eval_loss": 3.1347758769989014,
|
| 603 |
+
"eval_runtime": 62.6827,
|
| 604 |
+
"eval_samples_per_second": 90.152,
|
| 605 |
+
"eval_steps_per_second": 4.515,
|
| 606 |
+
"step": 14491
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 43.03,
|
| 610 |
+
"learning_rate": 6.973293768545995e-06,
|
| 611 |
+
"loss": 3.0066,
|
| 612 |
+
"step": 14500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 44.0,
|
| 616 |
+
"eval_bleu": 1.2743,
|
| 617 |
+
"eval_gen_len": 16.069,
|
| 618 |
+
"eval_loss": 3.1343321800231934,
|
| 619 |
+
"eval_runtime": 62.7369,
|
| 620 |
+
"eval_samples_per_second": 90.075,
|
| 621 |
+
"eval_steps_per_second": 4.511,
|
| 622 |
+
"step": 14828
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 44.51,
|
| 626 |
+
"learning_rate": 5.489614243323442e-06,
|
| 627 |
+
"loss": 3.0014,
|
| 628 |
+
"step": 15000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 45.0,
|
| 632 |
+
"eval_bleu": 1.264,
|
| 633 |
+
"eval_gen_len": 16.0232,
|
| 634 |
+
"eval_loss": 3.1345059871673584,
|
| 635 |
+
"eval_runtime": 62.8103,
|
| 636 |
+
"eval_samples_per_second": 89.969,
|
| 637 |
+
"eval_steps_per_second": 4.506,
|
| 638 |
+
"step": 15165
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 45.99,
|
| 642 |
+
"learning_rate": 4.005934718100891e-06,
|
| 643 |
+
"loss": 2.9948,
|
| 644 |
+
"step": 15500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 46.0,
|
| 648 |
+
"eval_bleu": 1.2856,
|
| 649 |
+
"eval_gen_len": 16.1014,
|
| 650 |
+
"eval_loss": 3.134138345718384,
|
| 651 |
+
"eval_runtime": 62.6814,
|
| 652 |
+
"eval_samples_per_second": 90.154,
|
| 653 |
+
"eval_steps_per_second": 4.515,
|
| 654 |
+
"step": 15502
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 47.0,
|
| 658 |
+
"eval_bleu": 1.2889,
|
| 659 |
+
"eval_gen_len": 16.0956,
|
| 660 |
+
"eval_loss": 3.1343159675598145,
|
| 661 |
+
"eval_runtime": 62.7663,
|
| 662 |
+
"eval_samples_per_second": 90.032,
|
| 663 |
+
"eval_steps_per_second": 4.509,
|
| 664 |
+
"step": 15839
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 47.48,
|
| 668 |
+
"learning_rate": 2.5222551928783385e-06,
|
| 669 |
+
"loss": 3.0016,
|
| 670 |
+
"step": 16000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 48.0,
|
| 674 |
+
"eval_bleu": 1.2823,
|
| 675 |
+
"eval_gen_len": 16.0342,
|
| 676 |
+
"eval_loss": 3.13439679145813,
|
| 677 |
+
"eval_runtime": 62.7228,
|
| 678 |
+
"eval_samples_per_second": 90.095,
|
| 679 |
+
"eval_steps_per_second": 4.512,
|
| 680 |
+
"step": 16176
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 48.96,
|
| 684 |
+
"learning_rate": 1.0385756676557863e-06,
|
| 685 |
+
"loss": 2.992,
|
| 686 |
+
"step": 16500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 49.0,
|
| 690 |
+
"eval_bleu": 1.2903,
|
| 691 |
+
"eval_gen_len": 16.0894,
|
| 692 |
+
"eval_loss": 3.134230136871338,
|
| 693 |
+
"eval_runtime": 62.7414,
|
| 694 |
+
"eval_samples_per_second": 90.068,
|
| 695 |
+
"eval_steps_per_second": 4.511,
|
| 696 |
+
"step": 16513
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 50.0,
|
| 700 |
+
"eval_bleu": 1.279,
|
| 701 |
+
"eval_gen_len": 16.0568,
|
| 702 |
+
"eval_loss": 3.1342360973358154,
|
| 703 |
+
"eval_runtime": 62.8254,
|
| 704 |
+
"eval_samples_per_second": 89.948,
|
| 705 |
+
"eval_steps_per_second": 4.505,
|
| 706 |
+
"step": 16850
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 50.0,
|
| 710 |
+
"step": 16850,
|
| 711 |
+
"total_flos": 8.49568285776937e+16,
|
| 712 |
+
"train_loss": 3.1156047950088093,
|
| 713 |
+
"train_runtime": 18325.9577,
|
| 714 |
+
"train_samples_per_second": 73.715,
|
| 715 |
+
"train_steps_per_second": 0.919
|
| 716 |
+
}
|
| 717 |
+
],
|
| 718 |
+
"max_steps": 16850,
|
| 719 |
+
"num_train_epochs": 50,
|
| 720 |
+
"total_flos": 8.49568285776937e+16,
|
| 721 |
+
"trial_name": null,
|
| 722 |
+
"trial_params": null
|
| 723 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa7e96fdee839ff8357ed0a1d12fae48f17f039b4353a3a7ecde2a74789d4256
|
| 3 |
+
size 3515
|