Upload 12 files
Browse files- added_tokens.json +5 -0
- all_results.json +15 -0
- config.json +60 -0
- eval_results.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- train_results.json +8 -0
- trainer_state.json +537 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<CTX>": 32101,
|
| 3 |
+
"<PS>": 32100,
|
| 4 |
+
"<SEP>": 32102
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.99,
|
| 3 |
+
"eval_bleu": 1.3579,
|
| 4 |
+
"eval_gen_len": 25.1463,
|
| 5 |
+
"eval_loss": 3.203944444656372,
|
| 6 |
+
"eval_runtime": 459.3966,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 12.301,
|
| 9 |
+
"eval_steps_per_second": 0.309,
|
| 10 |
+
"train_loss": 3.3598651123046874,
|
| 11 |
+
"train_runtime": 21589.3175,
|
| 12 |
+
"train_samples": 27018,
|
| 13 |
+
"train_samples_per_second": 62.573,
|
| 14 |
+
"train_steps_per_second": 0.065
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/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": 1,
|
| 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": 49.99,
|
| 3 |
+
"eval_bleu": 1.3579,
|
| 4 |
+
"eval_gen_len": 25.1463,
|
| 5 |
+
"eval_loss": 3.203944444656372,
|
| 6 |
+
"eval_runtime": 459.3966,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 12.301,
|
| 9 |
+
"eval_steps_per_second": 0.309
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7fc5442a0a390c069a0df3661d0dab77610a9b16002f720ade85e401f4d5a13
|
| 3 |
+
size 242020886
|
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": "</s>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 512,
|
| 108 |
+
"name_or_path": "google-t5/t5-small",
|
| 109 |
+
"pad_token": "<pad>",
|
| 110 |
+
"special_tokens_map_file": null,
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.99,
|
| 3 |
+
"train_loss": 3.3598651123046874,
|
| 4 |
+
"train_runtime": 21589.3175,
|
| 5 |
+
"train_samples": 27018,
|
| 6 |
+
"train_samples_per_second": 62.573,
|
| 7 |
+
"train_steps_per_second": 0.065
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.99467140319716,
|
| 5 |
+
"global_step": 1400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"eval_bleu": 0.6549,
|
| 13 |
+
"eval_gen_len": 14.2911,
|
| 14 |
+
"eval_loss": 3.51861834526062,
|
| 15 |
+
"eval_runtime": 90.1677,
|
| 16 |
+
"eval_samples_per_second": 62.672,
|
| 17 |
+
"eval_steps_per_second": 1.575,
|
| 18 |
+
"step": 28
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.99,
|
| 22 |
+
"eval_bleu": 0.7119,
|
| 23 |
+
"eval_gen_len": 15.2173,
|
| 24 |
+
"eval_loss": 3.422013998031616,
|
| 25 |
+
"eval_runtime": 90.001,
|
| 26 |
+
"eval_samples_per_second": 62.788,
|
| 27 |
+
"eval_steps_per_second": 1.578,
|
| 28 |
+
"step": 56
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.99,
|
| 32 |
+
"eval_bleu": 0.7933,
|
| 33 |
+
"eval_gen_len": 15.77,
|
| 34 |
+
"eval_loss": 3.3816401958465576,
|
| 35 |
+
"eval_runtime": 90.2248,
|
| 36 |
+
"eval_samples_per_second": 62.632,
|
| 37 |
+
"eval_steps_per_second": 1.574,
|
| 38 |
+
"step": 84
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.99,
|
| 42 |
+
"eval_bleu": 0.828,
|
| 43 |
+
"eval_gen_len": 15.9515,
|
| 44 |
+
"eval_loss": 3.357332944869995,
|
| 45 |
+
"eval_runtime": 90.0431,
|
| 46 |
+
"eval_samples_per_second": 62.759,
|
| 47 |
+
"eval_steps_per_second": 1.577,
|
| 48 |
+
"step": 112
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.99,
|
| 52 |
+
"eval_bleu": 0.8564,
|
| 53 |
+
"eval_gen_len": 15.9135,
|
| 54 |
+
"eval_loss": 3.3394410610198975,
|
| 55 |
+
"eval_runtime": 90.2255,
|
| 56 |
+
"eval_samples_per_second": 62.632,
|
| 57 |
+
"eval_steps_per_second": 1.574,
|
| 58 |
+
"step": 140
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 5.99,
|
| 62 |
+
"eval_bleu": 0.9038,
|
| 63 |
+
"eval_gen_len": 15.9788,
|
| 64 |
+
"eval_loss": 3.324686050415039,
|
| 65 |
+
"eval_runtime": 90.177,
|
| 66 |
+
"eval_samples_per_second": 62.666,
|
| 67 |
+
"eval_steps_per_second": 1.575,
|
| 68 |
+
"step": 168
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.99,
|
| 72 |
+
"eval_bleu": 0.9239,
|
| 73 |
+
"eval_gen_len": 16.1274,
|
| 74 |
+
"eval_loss": 3.312596082687378,
|
| 75 |
+
"eval_runtime": 90.2242,
|
| 76 |
+
"eval_samples_per_second": 62.633,
|
| 77 |
+
"eval_steps_per_second": 1.574,
|
| 78 |
+
"step": 196
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 7.99,
|
| 82 |
+
"eval_bleu": 0.9535,
|
| 83 |
+
"eval_gen_len": 16.1568,
|
| 84 |
+
"eval_loss": 3.3029773235321045,
|
| 85 |
+
"eval_runtime": 89.9892,
|
| 86 |
+
"eval_samples_per_second": 62.796,
|
| 87 |
+
"eval_steps_per_second": 1.578,
|
| 88 |
+
"step": 224
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 8.99,
|
| 92 |
+
"eval_bleu": 0.9392,
|
| 93 |
+
"eval_gen_len": 16.2577,
|
| 94 |
+
"eval_loss": 3.2943568229675293,
|
| 95 |
+
"eval_runtime": 90.2103,
|
| 96 |
+
"eval_samples_per_second": 62.643,
|
| 97 |
+
"eval_steps_per_second": 1.574,
|
| 98 |
+
"step": 252
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 9.99,
|
| 102 |
+
"eval_bleu": 1.0057,
|
| 103 |
+
"eval_gen_len": 16.4258,
|
| 104 |
+
"eval_loss": 3.286745548248291,
|
| 105 |
+
"eval_runtime": 90.3866,
|
| 106 |
+
"eval_samples_per_second": 62.52,
|
| 107 |
+
"eval_steps_per_second": 1.571,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 10.99,
|
| 112 |
+
"eval_bleu": 1.0136,
|
| 113 |
+
"eval_gen_len": 16.3022,
|
| 114 |
+
"eval_loss": 3.2792539596557617,
|
| 115 |
+
"eval_runtime": 90.1642,
|
| 116 |
+
"eval_samples_per_second": 62.675,
|
| 117 |
+
"eval_steps_per_second": 1.575,
|
| 118 |
+
"step": 308
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 11.99,
|
| 122 |
+
"eval_bleu": 1.0151,
|
| 123 |
+
"eval_gen_len": 16.3868,
|
| 124 |
+
"eval_loss": 3.273854970932007,
|
| 125 |
+
"eval_runtime": 90.0094,
|
| 126 |
+
"eval_samples_per_second": 62.782,
|
| 127 |
+
"eval_steps_per_second": 1.578,
|
| 128 |
+
"step": 336
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.99,
|
| 132 |
+
"eval_bleu": 1.0137,
|
| 133 |
+
"eval_gen_len": 16.2493,
|
| 134 |
+
"eval_loss": 3.2679247856140137,
|
| 135 |
+
"eval_runtime": 90.2543,
|
| 136 |
+
"eval_samples_per_second": 62.612,
|
| 137 |
+
"eval_steps_per_second": 1.573,
|
| 138 |
+
"step": 364
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 13.99,
|
| 142 |
+
"eval_bleu": 1.0062,
|
| 143 |
+
"eval_gen_len": 16.3263,
|
| 144 |
+
"eval_loss": 3.263322353363037,
|
| 145 |
+
"eval_runtime": 90.0803,
|
| 146 |
+
"eval_samples_per_second": 62.733,
|
| 147 |
+
"eval_steps_per_second": 1.576,
|
| 148 |
+
"step": 392
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 14.99,
|
| 152 |
+
"eval_bleu": 1.0205,
|
| 153 |
+
"eval_gen_len": 16.1936,
|
| 154 |
+
"eval_loss": 3.258091449737549,
|
| 155 |
+
"eval_runtime": 90.2141,
|
| 156 |
+
"eval_samples_per_second": 62.64,
|
| 157 |
+
"eval_steps_per_second": 1.574,
|
| 158 |
+
"step": 420
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 15.99,
|
| 162 |
+
"eval_bleu": 1.0392,
|
| 163 |
+
"eval_gen_len": 16.2488,
|
| 164 |
+
"eval_loss": 3.254173755645752,
|
| 165 |
+
"eval_runtime": 90.1523,
|
| 166 |
+
"eval_samples_per_second": 62.683,
|
| 167 |
+
"eval_steps_per_second": 1.575,
|
| 168 |
+
"step": 448
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 16.99,
|
| 172 |
+
"eval_bleu": 1.0613,
|
| 173 |
+
"eval_gen_len": 16.1219,
|
| 174 |
+
"eval_loss": 3.249685764312744,
|
| 175 |
+
"eval_runtime": 90.3649,
|
| 176 |
+
"eval_samples_per_second": 62.535,
|
| 177 |
+
"eval_steps_per_second": 1.571,
|
| 178 |
+
"step": 476
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 17.85,
|
| 182 |
+
"learning_rate": 3.2142857142857144e-05,
|
| 183 |
+
"loss": 3.4648,
|
| 184 |
+
"step": 500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 17.99,
|
| 188 |
+
"eval_bleu": 1.0755,
|
| 189 |
+
"eval_gen_len": 16.2776,
|
| 190 |
+
"eval_loss": 3.2462830543518066,
|
| 191 |
+
"eval_runtime": 90.126,
|
| 192 |
+
"eval_samples_per_second": 62.701,
|
| 193 |
+
"eval_steps_per_second": 1.576,
|
| 194 |
+
"step": 504
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 18.99,
|
| 198 |
+
"eval_bleu": 1.0772,
|
| 199 |
+
"eval_gen_len": 16.3072,
|
| 200 |
+
"eval_loss": 3.2422850131988525,
|
| 201 |
+
"eval_runtime": 90.07,
|
| 202 |
+
"eval_samples_per_second": 62.74,
|
| 203 |
+
"eval_steps_per_second": 1.577,
|
| 204 |
+
"step": 532
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 19.99,
|
| 208 |
+
"eval_bleu": 1.0893,
|
| 209 |
+
"eval_gen_len": 16.3113,
|
| 210 |
+
"eval_loss": 3.2396700382232666,
|
| 211 |
+
"eval_runtime": 90.1336,
|
| 212 |
+
"eval_samples_per_second": 62.696,
|
| 213 |
+
"eval_steps_per_second": 1.575,
|
| 214 |
+
"step": 560
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 20.99,
|
| 218 |
+
"eval_bleu": 1.0591,
|
| 219 |
+
"eval_gen_len": 16.2219,
|
| 220 |
+
"eval_loss": 3.236823797225952,
|
| 221 |
+
"eval_runtime": 90.1085,
|
| 222 |
+
"eval_samples_per_second": 62.713,
|
| 223 |
+
"eval_steps_per_second": 1.576,
|
| 224 |
+
"step": 588
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 21.99,
|
| 228 |
+
"eval_bleu": 1.0858,
|
| 229 |
+
"eval_gen_len": 16.3468,
|
| 230 |
+
"eval_loss": 3.23404598236084,
|
| 231 |
+
"eval_runtime": 89.9968,
|
| 232 |
+
"eval_samples_per_second": 62.791,
|
| 233 |
+
"eval_steps_per_second": 1.578,
|
| 234 |
+
"step": 616
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 22.99,
|
| 238 |
+
"eval_bleu": 1.1204,
|
| 239 |
+
"eval_gen_len": 16.284,
|
| 240 |
+
"eval_loss": 3.2314248085021973,
|
| 241 |
+
"eval_runtime": 89.8557,
|
| 242 |
+
"eval_samples_per_second": 62.89,
|
| 243 |
+
"eval_steps_per_second": 1.58,
|
| 244 |
+
"step": 644
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 23.99,
|
| 248 |
+
"eval_bleu": 1.1199,
|
| 249 |
+
"eval_gen_len": 16.3371,
|
| 250 |
+
"eval_loss": 3.2291789054870605,
|
| 251 |
+
"eval_runtime": 89.9552,
|
| 252 |
+
"eval_samples_per_second": 62.82,
|
| 253 |
+
"eval_steps_per_second": 1.579,
|
| 254 |
+
"step": 672
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 24.99,
|
| 258 |
+
"eval_bleu": 1.1413,
|
| 259 |
+
"eval_gen_len": 16.3203,
|
| 260 |
+
"eval_loss": 3.226853847503662,
|
| 261 |
+
"eval_runtime": 90.1817,
|
| 262 |
+
"eval_samples_per_second": 62.662,
|
| 263 |
+
"eval_steps_per_second": 1.575,
|
| 264 |
+
"step": 700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 25.99,
|
| 268 |
+
"eval_bleu": 1.1415,
|
| 269 |
+
"eval_gen_len": 16.3137,
|
| 270 |
+
"eval_loss": 3.2246992588043213,
|
| 271 |
+
"eval_runtime": 90.2118,
|
| 272 |
+
"eval_samples_per_second": 62.642,
|
| 273 |
+
"eval_steps_per_second": 1.574,
|
| 274 |
+
"step": 728
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 26.99,
|
| 278 |
+
"eval_bleu": 1.1522,
|
| 279 |
+
"eval_gen_len": 16.2957,
|
| 280 |
+
"eval_loss": 3.2227494716644287,
|
| 281 |
+
"eval_runtime": 90.192,
|
| 282 |
+
"eval_samples_per_second": 62.655,
|
| 283 |
+
"eval_steps_per_second": 1.574,
|
| 284 |
+
"step": 756
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 27.99,
|
| 288 |
+
"eval_bleu": 1.1315,
|
| 289 |
+
"eval_gen_len": 16.2869,
|
| 290 |
+
"eval_loss": 3.2210450172424316,
|
| 291 |
+
"eval_runtime": 90.0566,
|
| 292 |
+
"eval_samples_per_second": 62.749,
|
| 293 |
+
"eval_steps_per_second": 1.577,
|
| 294 |
+
"step": 784
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 28.99,
|
| 298 |
+
"eval_bleu": 1.1366,
|
| 299 |
+
"eval_gen_len": 16.2984,
|
| 300 |
+
"eval_loss": 3.21929669380188,
|
| 301 |
+
"eval_runtime": 90.1542,
|
| 302 |
+
"eval_samples_per_second": 62.681,
|
| 303 |
+
"eval_steps_per_second": 1.575,
|
| 304 |
+
"step": 812
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 29.99,
|
| 308 |
+
"eval_bleu": 1.1557,
|
| 309 |
+
"eval_gen_len": 16.3242,
|
| 310 |
+
"eval_loss": 3.2176640033721924,
|
| 311 |
+
"eval_runtime": 89.9951,
|
| 312 |
+
"eval_samples_per_second": 62.792,
|
| 313 |
+
"eval_steps_per_second": 1.578,
|
| 314 |
+
"step": 840
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 30.99,
|
| 318 |
+
"eval_bleu": 1.1545,
|
| 319 |
+
"eval_gen_len": 16.378,
|
| 320 |
+
"eval_loss": 3.216632604598999,
|
| 321 |
+
"eval_runtime": 90.1702,
|
| 322 |
+
"eval_samples_per_second": 62.67,
|
| 323 |
+
"eval_steps_per_second": 1.575,
|
| 324 |
+
"step": 868
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 31.99,
|
| 328 |
+
"eval_bleu": 1.1612,
|
| 329 |
+
"eval_gen_len": 16.3198,
|
| 330 |
+
"eval_loss": 3.2149343490600586,
|
| 331 |
+
"eval_runtime": 90.3354,
|
| 332 |
+
"eval_samples_per_second": 62.556,
|
| 333 |
+
"eval_steps_per_second": 1.572,
|
| 334 |
+
"step": 896
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 32.99,
|
| 338 |
+
"eval_bleu": 1.1612,
|
| 339 |
+
"eval_gen_len": 16.3831,
|
| 340 |
+
"eval_loss": 3.2138538360595703,
|
| 341 |
+
"eval_runtime": 89.9561,
|
| 342 |
+
"eval_samples_per_second": 62.82,
|
| 343 |
+
"eval_steps_per_second": 1.579,
|
| 344 |
+
"step": 924
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 33.99,
|
| 348 |
+
"eval_bleu": 1.1849,
|
| 349 |
+
"eval_gen_len": 16.3297,
|
| 350 |
+
"eval_loss": 3.2125675678253174,
|
| 351 |
+
"eval_runtime": 90.1068,
|
| 352 |
+
"eval_samples_per_second": 62.714,
|
| 353 |
+
"eval_steps_per_second": 1.576,
|
| 354 |
+
"step": 952
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 34.99,
|
| 358 |
+
"eval_bleu": 1.1838,
|
| 359 |
+
"eval_gen_len": 16.3698,
|
| 360 |
+
"eval_loss": 3.211477279663086,
|
| 361 |
+
"eval_runtime": 90.1237,
|
| 362 |
+
"eval_samples_per_second": 62.703,
|
| 363 |
+
"eval_steps_per_second": 1.576,
|
| 364 |
+
"step": 980
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 35.71,
|
| 368 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 369 |
+
"loss": 3.3175,
|
| 370 |
+
"step": 1000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 35.99,
|
| 374 |
+
"eval_bleu": 1.1849,
|
| 375 |
+
"eval_gen_len": 16.3953,
|
| 376 |
+
"eval_loss": 3.2102482318878174,
|
| 377 |
+
"eval_runtime": 89.7847,
|
| 378 |
+
"eval_samples_per_second": 62.939,
|
| 379 |
+
"eval_steps_per_second": 1.582,
|
| 380 |
+
"step": 1008
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 36.99,
|
| 384 |
+
"eval_bleu": 1.2054,
|
| 385 |
+
"eval_gen_len": 16.4488,
|
| 386 |
+
"eval_loss": 3.2095632553100586,
|
| 387 |
+
"eval_runtime": 90.0872,
|
| 388 |
+
"eval_samples_per_second": 62.728,
|
| 389 |
+
"eval_steps_per_second": 1.576,
|
| 390 |
+
"step": 1036
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 37.99,
|
| 394 |
+
"eval_bleu": 1.1967,
|
| 395 |
+
"eval_gen_len": 16.4178,
|
| 396 |
+
"eval_loss": 3.208686113357544,
|
| 397 |
+
"eval_runtime": 90.1581,
|
| 398 |
+
"eval_samples_per_second": 62.679,
|
| 399 |
+
"eval_steps_per_second": 1.575,
|
| 400 |
+
"step": 1064
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 38.99,
|
| 404 |
+
"eval_bleu": 1.1766,
|
| 405 |
+
"eval_gen_len": 16.3684,
|
| 406 |
+
"eval_loss": 3.207756996154785,
|
| 407 |
+
"eval_runtime": 89.9296,
|
| 408 |
+
"eval_samples_per_second": 62.838,
|
| 409 |
+
"eval_steps_per_second": 1.579,
|
| 410 |
+
"step": 1092
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 39.99,
|
| 414 |
+
"eval_bleu": 1.1795,
|
| 415 |
+
"eval_gen_len": 16.4084,
|
| 416 |
+
"eval_loss": 3.2069926261901855,
|
| 417 |
+
"eval_runtime": 90.2544,
|
| 418 |
+
"eval_samples_per_second": 62.612,
|
| 419 |
+
"eval_steps_per_second": 1.573,
|
| 420 |
+
"step": 1120
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 40.99,
|
| 424 |
+
"eval_bleu": 1.1961,
|
| 425 |
+
"eval_gen_len": 16.4006,
|
| 426 |
+
"eval_loss": 3.206512928009033,
|
| 427 |
+
"eval_runtime": 90.0766,
|
| 428 |
+
"eval_samples_per_second": 62.735,
|
| 429 |
+
"eval_steps_per_second": 1.576,
|
| 430 |
+
"step": 1148
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 41.99,
|
| 434 |
+
"eval_bleu": 1.1815,
|
| 435 |
+
"eval_gen_len": 16.421,
|
| 436 |
+
"eval_loss": 3.205848455429077,
|
| 437 |
+
"eval_runtime": 90.3074,
|
| 438 |
+
"eval_samples_per_second": 62.575,
|
| 439 |
+
"eval_steps_per_second": 1.572,
|
| 440 |
+
"step": 1176
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 42.99,
|
| 444 |
+
"eval_bleu": 1.1988,
|
| 445 |
+
"eval_gen_len": 16.4063,
|
| 446 |
+
"eval_loss": 3.2054076194763184,
|
| 447 |
+
"eval_runtime": 90.2177,
|
| 448 |
+
"eval_samples_per_second": 62.637,
|
| 449 |
+
"eval_steps_per_second": 1.574,
|
| 450 |
+
"step": 1204
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 43.99,
|
| 454 |
+
"eval_bleu": 1.1869,
|
| 455 |
+
"eval_gen_len": 16.3886,
|
| 456 |
+
"eval_loss": 3.2050981521606445,
|
| 457 |
+
"eval_runtime": 90.1457,
|
| 458 |
+
"eval_samples_per_second": 62.687,
|
| 459 |
+
"eval_steps_per_second": 1.575,
|
| 460 |
+
"step": 1232
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 44.99,
|
| 464 |
+
"eval_bleu": 1.1861,
|
| 465 |
+
"eval_gen_len": 16.4121,
|
| 466 |
+
"eval_loss": 3.204746723175049,
|
| 467 |
+
"eval_runtime": 90.0329,
|
| 468 |
+
"eval_samples_per_second": 62.766,
|
| 469 |
+
"eval_steps_per_second": 1.577,
|
| 470 |
+
"step": 1260
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 45.99,
|
| 474 |
+
"eval_bleu": 1.1751,
|
| 475 |
+
"eval_gen_len": 16.3983,
|
| 476 |
+
"eval_loss": 3.204568386077881,
|
| 477 |
+
"eval_runtime": 90.1067,
|
| 478 |
+
"eval_samples_per_second": 62.715,
|
| 479 |
+
"eval_steps_per_second": 1.576,
|
| 480 |
+
"step": 1288
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 46.99,
|
| 484 |
+
"eval_bleu": 1.181,
|
| 485 |
+
"eval_gen_len": 16.4228,
|
| 486 |
+
"eval_loss": 3.2042646408081055,
|
| 487 |
+
"eval_runtime": 90.0428,
|
| 488 |
+
"eval_samples_per_second": 62.759,
|
| 489 |
+
"eval_steps_per_second": 1.577,
|
| 490 |
+
"step": 1316
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 47.99,
|
| 494 |
+
"eval_bleu": 1.1787,
|
| 495 |
+
"eval_gen_len": 16.4403,
|
| 496 |
+
"eval_loss": 3.204113245010376,
|
| 497 |
+
"eval_runtime": 90.1802,
|
| 498 |
+
"eval_samples_per_second": 62.663,
|
| 499 |
+
"eval_steps_per_second": 1.575,
|
| 500 |
+
"step": 1344
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 48.99,
|
| 504 |
+
"eval_bleu": 1.1932,
|
| 505 |
+
"eval_gen_len": 16.4201,
|
| 506 |
+
"eval_loss": 3.203984260559082,
|
| 507 |
+
"eval_runtime": 90.324,
|
| 508 |
+
"eval_samples_per_second": 62.564,
|
| 509 |
+
"eval_steps_per_second": 1.572,
|
| 510 |
+
"step": 1372
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 49.99,
|
| 514 |
+
"eval_bleu": 1.1935,
|
| 515 |
+
"eval_gen_len": 16.4247,
|
| 516 |
+
"eval_loss": 3.203944444656372,
|
| 517 |
+
"eval_runtime": 90.1016,
|
| 518 |
+
"eval_samples_per_second": 62.718,
|
| 519 |
+
"eval_steps_per_second": 1.576,
|
| 520 |
+
"step": 1400
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 49.99,
|
| 524 |
+
"step": 1400,
|
| 525 |
+
"total_flos": 1.2293823395620454e+17,
|
| 526 |
+
"train_loss": 3.3598651123046874,
|
| 527 |
+
"train_runtime": 21589.3175,
|
| 528 |
+
"train_samples_per_second": 62.573,
|
| 529 |
+
"train_steps_per_second": 0.065
|
| 530 |
+
}
|
| 531 |
+
],
|
| 532 |
+
"max_steps": 1400,
|
| 533 |
+
"num_train_epochs": 50,
|
| 534 |
+
"total_flos": 1.2293823395620454e+17,
|
| 535 |
+
"trial_name": null,
|
| 536 |
+
"trial_params": null
|
| 537 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ceccfaa19402d803b45376b86a84465b574c624818ad1c60d125bbb43265c0
|
| 3 |
+
size 3960
|