Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +33 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +39 -0
- trainer_state.json +533 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 1,
|
| 3 |
+
"<pad>": 0,
|
| 4 |
+
"<unk>": 2
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "mt5",
|
| 20 |
+
"num_decoder_layers": 24,
|
| 21 |
+
"num_heads": 16,
|
| 22 |
+
"num_layers": 24,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "T5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.0.dev0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 250112
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.0.dev0"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf3d945ebdc7a5d9628ed81fe39b9dba4ed7201526b49d9694df9a94b3e3991
|
| 3 |
+
size 4918519193
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5656860d73c30062f90dfdd33f0cc91fbdb1021e9dec8e5cd33d442f26b0ec7
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1a262475d284dada1730d968a8b84dc21b95a8da172bca47f74e743ae773d62
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"tokenizer_file": null,
|
| 38 |
+
"unk_token": "<unk>"
|
| 39 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 41510,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 4.97992451618084e-05,
|
| 14 |
+
"loss": 3.7236,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 4.95984903236168e-05,
|
| 20 |
+
"loss": 0.1859,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 4.93977354854252e-05,
|
| 26 |
+
"loss": 0.1562,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 4.91969806472336e-05,
|
| 32 |
+
"loss": 0.1367,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.12,
|
| 37 |
+
"learning_rate": 4.8996225809042e-05,
|
| 38 |
+
"loss": 0.1307,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.14,
|
| 43 |
+
"learning_rate": 4.8795470970850396e-05,
|
| 44 |
+
"loss": 0.1175,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.17,
|
| 49 |
+
"learning_rate": 4.8594716132658805e-05,
|
| 50 |
+
"loss": 0.1149,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.19,
|
| 55 |
+
"learning_rate": 4.83939612944672e-05,
|
| 56 |
+
"loss": 0.1111,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.22,
|
| 61 |
+
"learning_rate": 4.8193206456275596e-05,
|
| 62 |
+
"loss": 0.1103,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.24,
|
| 67 |
+
"learning_rate": 4.7992451618084e-05,
|
| 68 |
+
"loss": 0.1088,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.26,
|
| 73 |
+
"learning_rate": 4.77916967798924e-05,
|
| 74 |
+
"loss": 0.0994,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.29,
|
| 79 |
+
"learning_rate": 4.7590941941700796e-05,
|
| 80 |
+
"loss": 0.1015,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.31,
|
| 85 |
+
"learning_rate": 4.73901871035092e-05,
|
| 86 |
+
"loss": 0.1046,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.34,
|
| 91 |
+
"learning_rate": 4.7189432265317594e-05,
|
| 92 |
+
"loss": 0.1029,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.36,
|
| 97 |
+
"learning_rate": 4.6988677427125996e-05,
|
| 98 |
+
"loss": 0.094,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.39,
|
| 103 |
+
"learning_rate": 4.67879225889344e-05,
|
| 104 |
+
"loss": 0.0874,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.41,
|
| 109 |
+
"learning_rate": 4.6587167750742794e-05,
|
| 110 |
+
"loss": 0.0915,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.43,
|
| 115 |
+
"learning_rate": 4.6386412912551196e-05,
|
| 116 |
+
"loss": 0.0968,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.46,
|
| 121 |
+
"learning_rate": 4.618565807435959e-05,
|
| 122 |
+
"loss": 0.0928,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.48,
|
| 127 |
+
"learning_rate": 4.5984903236167994e-05,
|
| 128 |
+
"loss": 0.0997,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.51,
|
| 133 |
+
"learning_rate": 4.5784148397976396e-05,
|
| 134 |
+
"loss": 0.0905,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.53,
|
| 139 |
+
"learning_rate": 4.558339355978479e-05,
|
| 140 |
+
"loss": 0.0896,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.55,
|
| 145 |
+
"learning_rate": 4.538263872159319e-05,
|
| 146 |
+
"loss": 0.0846,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.58,
|
| 151 |
+
"learning_rate": 4.5181883883401596e-05,
|
| 152 |
+
"loss": 0.093,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.6,
|
| 157 |
+
"learning_rate": 4.498112904520999e-05,
|
| 158 |
+
"loss": 0.084,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.63,
|
| 163 |
+
"learning_rate": 4.4780374207018394e-05,
|
| 164 |
+
"loss": 0.0876,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.65,
|
| 169 |
+
"learning_rate": 4.457961936882679e-05,
|
| 170 |
+
"loss": 0.0903,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.67,
|
| 175 |
+
"learning_rate": 4.437886453063519e-05,
|
| 176 |
+
"loss": 0.0816,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7,
|
| 181 |
+
"learning_rate": 4.4178109692443594e-05,
|
| 182 |
+
"loss": 0.0842,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.72,
|
| 187 |
+
"learning_rate": 4.397735485425199e-05,
|
| 188 |
+
"loss": 0.0835,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.75,
|
| 193 |
+
"learning_rate": 4.3776600016060385e-05,
|
| 194 |
+
"loss": 0.0861,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.77,
|
| 199 |
+
"learning_rate": 4.357584517786879e-05,
|
| 200 |
+
"loss": 0.0827,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.79,
|
| 205 |
+
"learning_rate": 4.337509033967719e-05,
|
| 206 |
+
"loss": 0.0768,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.82,
|
| 211 |
+
"learning_rate": 4.3174335501485585e-05,
|
| 212 |
+
"loss": 0.082,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.84,
|
| 217 |
+
"learning_rate": 4.297358066329399e-05,
|
| 218 |
+
"loss": 0.0809,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.87,
|
| 223 |
+
"learning_rate": 4.277282582510238e-05,
|
| 224 |
+
"loss": 0.0867,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.89,
|
| 229 |
+
"learning_rate": 4.257207098691079e-05,
|
| 230 |
+
"loss": 0.0762,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.92,
|
| 235 |
+
"learning_rate": 4.237131614871919e-05,
|
| 236 |
+
"loss": 0.0801,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.94,
|
| 241 |
+
"learning_rate": 4.217056131052758e-05,
|
| 242 |
+
"loss": 0.0848,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.96,
|
| 247 |
+
"learning_rate": 4.1969806472335986e-05,
|
| 248 |
+
"loss": 0.0746,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.99,
|
| 253 |
+
"learning_rate": 4.176905163414439e-05,
|
| 254 |
+
"loss": 0.0762,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0,
|
| 259 |
+
"eval_loss": 0.10296186804771423,
|
| 260 |
+
"eval_runtime": 396.5979,
|
| 261 |
+
"eval_samples_per_second": 28.162,
|
| 262 |
+
"eval_steps_per_second": 7.042,
|
| 263 |
+
"step": 20755
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.01,
|
| 267 |
+
"learning_rate": 4.1568296795952783e-05,
|
| 268 |
+
"loss": 0.0693,
|
| 269 |
+
"step": 21000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.04,
|
| 273 |
+
"learning_rate": 4.1367541957761186e-05,
|
| 274 |
+
"loss": 0.0613,
|
| 275 |
+
"step": 21500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.06,
|
| 279 |
+
"learning_rate": 4.116678711956958e-05,
|
| 280 |
+
"loss": 0.0613,
|
| 281 |
+
"step": 22000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.08,
|
| 285 |
+
"learning_rate": 4.0966032281377984e-05,
|
| 286 |
+
"loss": 0.0646,
|
| 287 |
+
"step": 22500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.11,
|
| 291 |
+
"learning_rate": 4.0765277443186386e-05,
|
| 292 |
+
"loss": 0.066,
|
| 293 |
+
"step": 23000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.13,
|
| 297 |
+
"learning_rate": 4.056452260499478e-05,
|
| 298 |
+
"loss": 0.061,
|
| 299 |
+
"step": 23500
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.16,
|
| 303 |
+
"learning_rate": 4.0363767766803184e-05,
|
| 304 |
+
"loss": 0.0697,
|
| 305 |
+
"step": 24000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.18,
|
| 309 |
+
"learning_rate": 4.016301292861158e-05,
|
| 310 |
+
"loss": 0.0657,
|
| 311 |
+
"step": 24500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2,
|
| 315 |
+
"learning_rate": 3.996225809041998e-05,
|
| 316 |
+
"loss": 0.0577,
|
| 317 |
+
"step": 25000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.23,
|
| 321 |
+
"learning_rate": 3.9761503252228384e-05,
|
| 322 |
+
"loss": 0.0598,
|
| 323 |
+
"step": 25500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.25,
|
| 327 |
+
"learning_rate": 3.956074841403678e-05,
|
| 328 |
+
"loss": 0.066,
|
| 329 |
+
"step": 26000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.28,
|
| 333 |
+
"learning_rate": 3.9359993575845175e-05,
|
| 334 |
+
"loss": 0.0656,
|
| 335 |
+
"step": 26500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.3,
|
| 339 |
+
"learning_rate": 3.9159238737653584e-05,
|
| 340 |
+
"loss": 0.0597,
|
| 341 |
+
"step": 27000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.32,
|
| 345 |
+
"learning_rate": 3.895848389946198e-05,
|
| 346 |
+
"loss": 0.0667,
|
| 347 |
+
"step": 27500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.35,
|
| 351 |
+
"learning_rate": 3.8757729061270375e-05,
|
| 352 |
+
"loss": 0.058,
|
| 353 |
+
"step": 28000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.37,
|
| 357 |
+
"learning_rate": 3.855697422307878e-05,
|
| 358 |
+
"loss": 0.0587,
|
| 359 |
+
"step": 28500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.4,
|
| 363 |
+
"learning_rate": 3.835621938488718e-05,
|
| 364 |
+
"loss": 0.0577,
|
| 365 |
+
"step": 29000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.42,
|
| 369 |
+
"learning_rate": 3.815546454669558e-05,
|
| 370 |
+
"loss": 0.0609,
|
| 371 |
+
"step": 29500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.45,
|
| 375 |
+
"learning_rate": 3.795470970850398e-05,
|
| 376 |
+
"loss": 0.0586,
|
| 377 |
+
"step": 30000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.47,
|
| 381 |
+
"learning_rate": 3.775395487031237e-05,
|
| 382 |
+
"loss": 0.0561,
|
| 383 |
+
"step": 30500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.49,
|
| 387 |
+
"learning_rate": 3.7553200032120775e-05,
|
| 388 |
+
"loss": 0.0605,
|
| 389 |
+
"step": 31000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.52,
|
| 393 |
+
"learning_rate": 3.735244519392918e-05,
|
| 394 |
+
"loss": 0.063,
|
| 395 |
+
"step": 31500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.54,
|
| 399 |
+
"learning_rate": 3.715169035573757e-05,
|
| 400 |
+
"loss": 0.0622,
|
| 401 |
+
"step": 32000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.57,
|
| 405 |
+
"learning_rate": 3.6950935517545975e-05,
|
| 406 |
+
"loss": 0.0542,
|
| 407 |
+
"step": 32500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.59,
|
| 411 |
+
"learning_rate": 3.675018067935437e-05,
|
| 412 |
+
"loss": 0.0625,
|
| 413 |
+
"step": 33000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.61,
|
| 417 |
+
"learning_rate": 3.654942584116277e-05,
|
| 418 |
+
"loss": 0.0608,
|
| 419 |
+
"step": 33500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.64,
|
| 423 |
+
"learning_rate": 3.6348671002971175e-05,
|
| 424 |
+
"loss": 0.0588,
|
| 425 |
+
"step": 34000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.66,
|
| 429 |
+
"learning_rate": 3.614791616477957e-05,
|
| 430 |
+
"loss": 0.0632,
|
| 431 |
+
"step": 34500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.69,
|
| 435 |
+
"learning_rate": 3.594716132658797e-05,
|
| 436 |
+
"loss": 0.0554,
|
| 437 |
+
"step": 35000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.71,
|
| 441 |
+
"learning_rate": 3.5746406488396375e-05,
|
| 442 |
+
"loss": 0.0629,
|
| 443 |
+
"step": 35500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.73,
|
| 447 |
+
"learning_rate": 3.554565165020477e-05,
|
| 448 |
+
"loss": 0.0577,
|
| 449 |
+
"step": 36000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.76,
|
| 453 |
+
"learning_rate": 3.534489681201317e-05,
|
| 454 |
+
"loss": 0.0563,
|
| 455 |
+
"step": 36500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.78,
|
| 459 |
+
"learning_rate": 3.514414197382157e-05,
|
| 460 |
+
"loss": 0.0522,
|
| 461 |
+
"step": 37000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.81,
|
| 465 |
+
"learning_rate": 3.494338713562997e-05,
|
| 466 |
+
"loss": 0.0638,
|
| 467 |
+
"step": 37500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.83,
|
| 471 |
+
"learning_rate": 3.474263229743837e-05,
|
| 472 |
+
"loss": 0.056,
|
| 473 |
+
"step": 38000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.85,
|
| 477 |
+
"learning_rate": 3.454187745924677e-05,
|
| 478 |
+
"loss": 0.0578,
|
| 479 |
+
"step": 38500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.88,
|
| 483 |
+
"learning_rate": 3.434112262105517e-05,
|
| 484 |
+
"loss": 0.0692,
|
| 485 |
+
"step": 39000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.9,
|
| 489 |
+
"learning_rate": 3.4140367782863567e-05,
|
| 490 |
+
"loss": 0.0551,
|
| 491 |
+
"step": 39500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.93,
|
| 495 |
+
"learning_rate": 3.393961294467197e-05,
|
| 496 |
+
"loss": 0.0567,
|
| 497 |
+
"step": 40000
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.95,
|
| 501 |
+
"learning_rate": 3.373885810648037e-05,
|
| 502 |
+
"loss": 0.0538,
|
| 503 |
+
"step": 40500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.98,
|
| 507 |
+
"learning_rate": 3.353810326828877e-05,
|
| 508 |
+
"loss": 0.0558,
|
| 509 |
+
"step": 41000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.0,
|
| 513 |
+
"learning_rate": 3.333734843009716e-05,
|
| 514 |
+
"loss": 0.0566,
|
| 515 |
+
"step": 41500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.0,
|
| 519 |
+
"eval_loss": 0.09943284094333649,
|
| 520 |
+
"eval_runtime": 396.5068,
|
| 521 |
+
"eval_samples_per_second": 28.168,
|
| 522 |
+
"eval_steps_per_second": 7.044,
|
| 523 |
+
"step": 41510
|
| 524 |
+
}
|
| 525 |
+
],
|
| 526 |
+
"logging_steps": 500,
|
| 527 |
+
"max_steps": 124530,
|
| 528 |
+
"num_train_epochs": 6,
|
| 529 |
+
"save_steps": 500,
|
| 530 |
+
"total_flos": 4.965283871588352e+17,
|
| 531 |
+
"trial_name": null,
|
| 532 |
+
"trial_params": null
|
| 533 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a1407e37de39eb7b2bbc4acf4f46334dbb56402ea316989990c30009c25a749
|
| 3 |
+
size 4155
|