Initial
Browse files- all_results.json +8 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +451 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 1.6082039656264058,
|
| 4 |
+
"train_runtime": 1452.4648,
|
| 5 |
+
"train_samples": 2846,
|
| 6 |
+
"train_samples_per_second": 39.189,
|
| 7 |
+
"train_steps_per_second": 4.902
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 4096,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "relu",
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"model_type": "t5",
|
| 18 |
+
"n_positions": 512,
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 16,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"task_specific_params": {
|
| 26 |
+
"summarization": {
|
| 27 |
+
"early_stopping": true,
|
| 28 |
+
"length_penalty": 2.0,
|
| 29 |
+
"max_length": 200,
|
| 30 |
+
"min_length": 30,
|
| 31 |
+
"no_repeat_ngram_size": 3,
|
| 32 |
+
"num_beams": 4,
|
| 33 |
+
"prefix": "summarize: "
|
| 34 |
+
},
|
| 35 |
+
"translation_en_to_de": {
|
| 36 |
+
"early_stopping": true,
|
| 37 |
+
"max_length": 300,
|
| 38 |
+
"num_beams": 4,
|
| 39 |
+
"prefix": "translate English to German: "
|
| 40 |
+
},
|
| 41 |
+
"translation_en_to_fr": {
|
| 42 |
+
"early_stopping": true,
|
| 43 |
+
"max_length": 300,
|
| 44 |
+
"num_beams": 4,
|
| 45 |
+
"prefix": "translate English to French: "
|
| 46 |
+
},
|
| 47 |
+
"translation_en_to_ro": {
|
| 48 |
+
"early_stopping": true,
|
| 49 |
+
"max_length": 300,
|
| 50 |
+
"num_beams": 4,
|
| 51 |
+
"prefix": "translate English to Romanian: "
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.11.0.dev0",
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 32100
|
| 58 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40686b7396955e900069fa47f553b838b0f55b5d141bbdfbe324230cf16b80d5
|
| 3 |
+
size 2950790023
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256: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 @@
|
|
|
|
| 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, "special_tokens_map_file": null, "name_or_path": "t5-large", "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 1.6082039656264058,
|
| 4 |
+
"train_runtime": 1452.4648,
|
| 5 |
+
"train_samples": 2846,
|
| 6 |
+
"train_samples_per_second": 39.189,
|
| 7 |
+
"train_steps_per_second": 4.902
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 7120,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.28,
|
| 12 |
+
"learning_rate": 2.5e-06,
|
| 13 |
+
"loss": 5.4155,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.56,
|
| 18 |
+
"learning_rate": 5e-06,
|
| 19 |
+
"loss": 4.1706,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.84,
|
| 24 |
+
"learning_rate": 7.500000000000001e-06,
|
| 25 |
+
"loss": 3.4307,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.12,
|
| 30 |
+
"learning_rate": 1e-05,
|
| 31 |
+
"loss": 2.7978,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.4,
|
| 36 |
+
"learning_rate": 9.851190476190477e-06,
|
| 37 |
+
"loss": 2.5436,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.69,
|
| 42 |
+
"learning_rate": 9.702380952380953e-06,
|
| 43 |
+
"loss": 2.4266,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.97,
|
| 48 |
+
"learning_rate": 9.55357142857143e-06,
|
| 49 |
+
"loss": 2.3508,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.25,
|
| 54 |
+
"learning_rate": 9.404761904761905e-06,
|
| 55 |
+
"loss": 2.2192,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.53,
|
| 60 |
+
"learning_rate": 9.255952380952381e-06,
|
| 61 |
+
"loss": 2.1034,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.81,
|
| 66 |
+
"learning_rate": 9.107142857142858e-06,
|
| 67 |
+
"loss": 2.1141,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.09,
|
| 72 |
+
"learning_rate": 8.958333333333334e-06,
|
| 73 |
+
"loss": 2.0817,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.37,
|
| 78 |
+
"learning_rate": 8.80952380952381e-06,
|
| 79 |
+
"loss": 1.9094,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.65,
|
| 84 |
+
"learning_rate": 8.660714285714286e-06,
|
| 85 |
+
"loss": 1.9655,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.93,
|
| 90 |
+
"learning_rate": 8.511904761904762e-06,
|
| 91 |
+
"loss": 1.8821,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.21,
|
| 96 |
+
"learning_rate": 8.36309523809524e-06,
|
| 97 |
+
"loss": 1.8639,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.49,
|
| 102 |
+
"learning_rate": 8.214285714285714e-06,
|
| 103 |
+
"loss": 1.7393,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.78,
|
| 108 |
+
"learning_rate": 8.065476190476192e-06,
|
| 109 |
+
"loss": 1.7837,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.06,
|
| 114 |
+
"learning_rate": 7.916666666666667e-06,
|
| 115 |
+
"loss": 1.8089,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 5.34,
|
| 120 |
+
"learning_rate": 7.767857142857144e-06,
|
| 121 |
+
"loss": 1.652,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.62,
|
| 126 |
+
"learning_rate": 7.61904761904762e-06,
|
| 127 |
+
"loss": 1.6584,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.9,
|
| 132 |
+
"learning_rate": 7.470238095238096e-06,
|
| 133 |
+
"loss": 1.6747,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.18,
|
| 138 |
+
"learning_rate": 7.321428571428572e-06,
|
| 139 |
+
"loss": 1.7032,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.46,
|
| 144 |
+
"learning_rate": 7.172619047619048e-06,
|
| 145 |
+
"loss": 1.6471,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.74,
|
| 150 |
+
"learning_rate": 7.023809523809524e-06,
|
| 151 |
+
"loss": 1.6124,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 7.02,
|
| 156 |
+
"learning_rate": 6.875e-06,
|
| 157 |
+
"loss": 1.4935,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 7.3,
|
| 162 |
+
"learning_rate": 6.726190476190477e-06,
|
| 163 |
+
"loss": 1.5444,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.58,
|
| 168 |
+
"learning_rate": 6.5773809523809525e-06,
|
| 169 |
+
"loss": 1.5369,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.87,
|
| 174 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 175 |
+
"loss": 1.4954,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.15,
|
| 180 |
+
"learning_rate": 6.279761904761906e-06,
|
| 181 |
+
"loss": 1.4372,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.43,
|
| 186 |
+
"learning_rate": 6.130952380952382e-06,
|
| 187 |
+
"loss": 1.4984,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.71,
|
| 192 |
+
"learning_rate": 5.982142857142858e-06,
|
| 193 |
+
"loss": 1.4569,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 8.99,
|
| 198 |
+
"learning_rate": 5.833333333333334e-06,
|
| 199 |
+
"loss": 1.4227,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 9.27,
|
| 204 |
+
"learning_rate": 5.68452380952381e-06,
|
| 205 |
+
"loss": 1.3471,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.55,
|
| 210 |
+
"learning_rate": 5.535714285714286e-06,
|
| 211 |
+
"loss": 1.3956,
|
| 212 |
+
"step": 3400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 9.83,
|
| 216 |
+
"learning_rate": 5.386904761904762e-06,
|
| 217 |
+
"loss": 1.4264,
|
| 218 |
+
"step": 3500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 10.11,
|
| 222 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 223 |
+
"loss": 1.4372,
|
| 224 |
+
"step": 3600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 10.39,
|
| 228 |
+
"learning_rate": 5.0892857142857146e-06,
|
| 229 |
+
"loss": 1.3805,
|
| 230 |
+
"step": 3700
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 10.67,
|
| 234 |
+
"learning_rate": 4.940476190476191e-06,
|
| 235 |
+
"loss": 1.3379,
|
| 236 |
+
"step": 3800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 10.96,
|
| 240 |
+
"learning_rate": 4.791666666666668e-06,
|
| 241 |
+
"loss": 1.2706,
|
| 242 |
+
"step": 3900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 11.24,
|
| 246 |
+
"learning_rate": 4.642857142857144e-06,
|
| 247 |
+
"loss": 1.2747,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.52,
|
| 252 |
+
"learning_rate": 4.49404761904762e-06,
|
| 253 |
+
"loss": 1.3314,
|
| 254 |
+
"step": 4100
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 11.8,
|
| 258 |
+
"learning_rate": 4.345238095238096e-06,
|
| 259 |
+
"loss": 1.2674,
|
| 260 |
+
"step": 4200
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 12.08,
|
| 264 |
+
"learning_rate": 4.196428571428572e-06,
|
| 265 |
+
"loss": 1.2883,
|
| 266 |
+
"step": 4300
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 12.36,
|
| 270 |
+
"learning_rate": 4.047619047619048e-06,
|
| 271 |
+
"loss": 1.2421,
|
| 272 |
+
"step": 4400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 12.64,
|
| 276 |
+
"learning_rate": 3.898809523809524e-06,
|
| 277 |
+
"loss": 1.2721,
|
| 278 |
+
"step": 4500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 12.92,
|
| 282 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 283 |
+
"loss": 1.2663,
|
| 284 |
+
"step": 4600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 13.2,
|
| 288 |
+
"learning_rate": 3.6011904761904766e-06,
|
| 289 |
+
"loss": 1.2647,
|
| 290 |
+
"step": 4700
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 13.48,
|
| 294 |
+
"learning_rate": 3.4523809523809528e-06,
|
| 295 |
+
"loss": 1.225,
|
| 296 |
+
"step": 4800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 13.76,
|
| 300 |
+
"learning_rate": 3.303571428571429e-06,
|
| 301 |
+
"loss": 1.2095,
|
| 302 |
+
"step": 4900
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.04,
|
| 306 |
+
"learning_rate": 3.154761904761905e-06,
|
| 307 |
+
"loss": 1.2523,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.33,
|
| 312 |
+
"learning_rate": 3.005952380952381e-06,
|
| 313 |
+
"loss": 1.2451,
|
| 314 |
+
"step": 5100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 14.61,
|
| 318 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 319 |
+
"loss": 1.2037,
|
| 320 |
+
"step": 5200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 14.89,
|
| 324 |
+
"learning_rate": 2.7083333333333334e-06,
|
| 325 |
+
"loss": 1.1763,
|
| 326 |
+
"step": 5300
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 15.17,
|
| 330 |
+
"learning_rate": 2.5595238095238095e-06,
|
| 331 |
+
"loss": 1.1879,
|
| 332 |
+
"step": 5400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 15.45,
|
| 336 |
+
"learning_rate": 2.410714285714286e-06,
|
| 337 |
+
"loss": 1.195,
|
| 338 |
+
"step": 5500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 15.73,
|
| 342 |
+
"learning_rate": 2.261904761904762e-06,
|
| 343 |
+
"loss": 1.1531,
|
| 344 |
+
"step": 5600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 16.01,
|
| 348 |
+
"learning_rate": 2.1130952380952383e-06,
|
| 349 |
+
"loss": 1.1864,
|
| 350 |
+
"step": 5700
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 16.29,
|
| 354 |
+
"learning_rate": 1.9642857142857144e-06,
|
| 355 |
+
"loss": 1.188,
|
| 356 |
+
"step": 5800
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 16.57,
|
| 360 |
+
"learning_rate": 1.8154761904761905e-06,
|
| 361 |
+
"loss": 1.1434,
|
| 362 |
+
"step": 5900
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 16.85,
|
| 366 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 367 |
+
"loss": 1.1691,
|
| 368 |
+
"step": 6000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 17.13,
|
| 372 |
+
"learning_rate": 1.5178571428571428e-06,
|
| 373 |
+
"loss": 1.1299,
|
| 374 |
+
"step": 6100
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 17.42,
|
| 378 |
+
"learning_rate": 1.3690476190476193e-06,
|
| 379 |
+
"loss": 1.1265,
|
| 380 |
+
"step": 6200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 17.7,
|
| 384 |
+
"learning_rate": 1.2202380952380952e-06,
|
| 385 |
+
"loss": 1.1849,
|
| 386 |
+
"step": 6300
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 17.98,
|
| 390 |
+
"learning_rate": 1.0714285714285714e-06,
|
| 391 |
+
"loss": 1.1179,
|
| 392 |
+
"step": 6400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 18.26,
|
| 396 |
+
"learning_rate": 9.226190476190477e-07,
|
| 397 |
+
"loss": 1.1428,
|
| 398 |
+
"step": 6500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 18.54,
|
| 402 |
+
"learning_rate": 7.738095238095239e-07,
|
| 403 |
+
"loss": 1.1704,
|
| 404 |
+
"step": 6600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 18.82,
|
| 408 |
+
"learning_rate": 6.25e-07,
|
| 409 |
+
"loss": 1.1172,
|
| 410 |
+
"step": 6700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 19.1,
|
| 414 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 415 |
+
"loss": 1.1291,
|
| 416 |
+
"step": 6800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 19.38,
|
| 420 |
+
"learning_rate": 3.273809523809524e-07,
|
| 421 |
+
"loss": 1.1492,
|
| 422 |
+
"step": 6900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 19.66,
|
| 426 |
+
"learning_rate": 1.7857142857142858e-07,
|
| 427 |
+
"loss": 1.1023,
|
| 428 |
+
"step": 7000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 19.94,
|
| 432 |
+
"learning_rate": 2.9761904761904764e-08,
|
| 433 |
+
"loss": 1.1626,
|
| 434 |
+
"step": 7100
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 20.0,
|
| 438 |
+
"step": 7120,
|
| 439 |
+
"total_flos": 1.3000229462016e+16,
|
| 440 |
+
"train_loss": 1.6082039656264058,
|
| 441 |
+
"train_runtime": 1452.4648,
|
| 442 |
+
"train_samples_per_second": 39.189,
|
| 443 |
+
"train_steps_per_second": 4.902
|
| 444 |
+
}
|
| 445 |
+
],
|
| 446 |
+
"max_steps": 7120,
|
| 447 |
+
"num_train_epochs": 20,
|
| 448 |
+
"total_flos": 1.3000229462016e+16,
|
| 449 |
+
"trial_name": null,
|
| 450 |
+
"trial_params": null
|
| 451 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad65936847fc670c8449b7c2ff71d343d79d1c4c1c93260a6b6c8295ffd32c61
|
| 3 |
+
size 2927
|