Upload 12 files
Browse files- checkpoint-2200/config.json +36 -0
- checkpoint-2200/dict.txt +0 -0
- checkpoint-2200/generation_config.json +12 -0
- checkpoint-2200/model.safetensors +3 -0
- checkpoint-2200/optimizer.pt +3 -0
- checkpoint-2200/rng_state.pth +3 -0
- checkpoint-2200/scheduler.pt +3 -0
- checkpoint-2200/sentencepiece.bpe.model +3 -0
- checkpoint-2200/special_tokens_map.json +15 -0
- checkpoint-2200/tokenizer_config.json +56 -0
- checkpoint-2200/trainer_state.json +606 -0
- checkpoint-2200/training_args.bin +3 -0
checkpoint-2200/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MBartForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.0,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_attention_heads": 12,
|
| 12 |
+
"decoder_ffn_dim": 3072,
|
| 13 |
+
"decoder_layerdrop": 0.0,
|
| 14 |
+
"decoder_layers": 6,
|
| 15 |
+
"decoder_start_token_id": 2,
|
| 16 |
+
"dropout": 0.1,
|
| 17 |
+
"encoder_attention_heads": 12,
|
| 18 |
+
"encoder_ffn_dim": 3072,
|
| 19 |
+
"encoder_layerdrop": 0.0,
|
| 20 |
+
"encoder_layers": 6,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"forced_eos_token_id": 2,
|
| 23 |
+
"gradient_checkpointing": false,
|
| 24 |
+
"init_std": 0.02,
|
| 25 |
+
"is_encoder_decoder": true,
|
| 26 |
+
"max_position_embeddings": 1024,
|
| 27 |
+
"model_type": "mbart",
|
| 28 |
+
"num_hidden_layers": 6,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"scale_embedding": false,
|
| 31 |
+
"tokenizer_class": "BartphoTokenizer",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.50.3",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 40030
|
| 36 |
+
}
|
checkpoint-2200/dict.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2200/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"max_new_tokens": 512,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 3,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.50.3"
|
| 12 |
+
}
|
checkpoint-2200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:407cb4d24c3388a40006e8c4e906c936145d3e185908a5b0f2a3c659e4bac234
|
| 3 |
+
size 526442440
|
checkpoint-2200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe3502d57c5dd8588695fa7bbb86e3254d40466df00c7ec184d7d2116052634
|
| 3 |
+
size 1052723962
|
checkpoint-2200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d72cbeaa104c4552fabc8029fd59bb31035a2985e357f4d21c5a0e19104fa3f
|
| 3 |
+
size 14244
|
checkpoint-2200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e46574a903e92238f9db1d119c9ed61c27f8bc44447e1e3154f9accc839c0d96
|
| 3 |
+
size 1064
|
checkpoint-2200/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-2200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-2200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"40029": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"tokenizer_class": "BartphoTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
checkpoint-2200/trainer_state.json
ADDED
|
@@ -0,0 +1,606 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 600,
|
| 3 |
+
"best_metric": 72.28,
|
| 4 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Summarization/checkpoints/cur_cp/checkpoint-600",
|
| 5 |
+
"epoch": 8.835341365461847,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 2200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.20080321285140562,
|
| 14 |
+
"grad_norm": 10.723053932189941,
|
| 15 |
+
"learning_rate": 4.995027130745321e-05,
|
| 16 |
+
"loss": 0.8179,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.40160642570281124,
|
| 21 |
+
"grad_norm": 13.537382125854492,
|
| 22 |
+
"learning_rate": 4.980128306524183e-05,
|
| 23 |
+
"loss": 0.7085,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.40160642570281124,
|
| 28 |
+
"eval_f1": 70.31,
|
| 29 |
+
"eval_gen_len": 42.92338709677419,
|
| 30 |
+
"eval_loss": 0.6963455080986023,
|
| 31 |
+
"eval_p": 74.73,
|
| 32 |
+
"eval_r": 70.54,
|
| 33 |
+
"eval_runtime": 46.3873,
|
| 34 |
+
"eval_samples_per_second": 10.693,
|
| 35 |
+
"eval_steps_per_second": 0.668,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.6024096385542169,
|
| 40 |
+
"grad_norm": 3.749103307723999,
|
| 41 |
+
"learning_rate": 4.9553627992605066e-05,
|
| 42 |
+
"loss": 0.6667,
|
| 43 |
+
"step": 150
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.8032128514056225,
|
| 47 |
+
"grad_norm": 7.421478748321533,
|
| 48 |
+
"learning_rate": 4.9208291334580104e-05,
|
| 49 |
+
"loss": 0.5991,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.8032128514056225,
|
| 54 |
+
"eval_f1": 68.09,
|
| 55 |
+
"eval_gen_len": 40.17741935483871,
|
| 56 |
+
"eval_loss": 0.7214160561561584,
|
| 57 |
+
"eval_p": 75.9,
|
| 58 |
+
"eval_r": 66.2,
|
| 59 |
+
"eval_runtime": 45.6263,
|
| 60 |
+
"eval_samples_per_second": 10.871,
|
| 61 |
+
"eval_steps_per_second": 0.679,
|
| 62 |
+
"step": 200
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0040160642570282,
|
| 66 |
+
"grad_norm": 9.242626190185547,
|
| 67 |
+
"learning_rate": 4.87666469424063e-05,
|
| 68 |
+
"loss": 0.752,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.2048192771084336,
|
| 73 |
+
"grad_norm": 4.659054756164551,
|
| 74 |
+
"learning_rate": 4.8230451807939135e-05,
|
| 75 |
+
"loss": 0.4472,
|
| 76 |
+
"step": 300
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.2048192771084336,
|
| 80 |
+
"eval_f1": 67.64,
|
| 81 |
+
"eval_gen_len": 39.01411290322581,
|
| 82 |
+
"eval_loss": 0.7062053084373474,
|
| 83 |
+
"eval_p": 75.6,
|
| 84 |
+
"eval_r": 65.19,
|
| 85 |
+
"eval_runtime": 42.4185,
|
| 86 |
+
"eval_samples_per_second": 11.693,
|
| 87 |
+
"eval_steps_per_second": 0.731,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.4056224899598393,
|
| 92 |
+
"grad_norm": 11.880289077758789,
|
| 93 |
+
"learning_rate": 4.760183907381757e-05,
|
| 94 |
+
"loss": 0.5069,
|
| 95 |
+
"step": 350
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.606425702811245,
|
| 99 |
+
"grad_norm": 9.056407928466797,
|
| 100 |
+
"learning_rate": 4.6883309547192476e-05,
|
| 101 |
+
"loss": 0.519,
|
| 102 |
+
"step": 400
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.606425702811245,
|
| 106 |
+
"eval_f1": 71.67,
|
| 107 |
+
"eval_gen_len": 46.93346774193548,
|
| 108 |
+
"eval_loss": 0.7584968209266663,
|
| 109 |
+
"eval_p": 73.71,
|
| 110 |
+
"eval_r": 74.1,
|
| 111 |
+
"eval_runtime": 55.9551,
|
| 112 |
+
"eval_samples_per_second": 8.864,
|
| 113 |
+
"eval_steps_per_second": 0.554,
|
| 114 |
+
"step": 400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.8072289156626506,
|
| 118 |
+
"grad_norm": 7.793162822723389,
|
| 119 |
+
"learning_rate": 4.607772175077711e-05,
|
| 120 |
+
"loss": 0.4939,
|
| 121 |
+
"step": 450
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.0080321285140563,
|
| 125 |
+
"grad_norm": 7.212235927581787,
|
| 126 |
+
"learning_rate": 4.518828055079925e-05,
|
| 127 |
+
"loss": 0.4646,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.0080321285140563,
|
| 132 |
+
"eval_f1": 69.01,
|
| 133 |
+
"eval_gen_len": 42.16129032258065,
|
| 134 |
+
"eval_loss": 0.7297435998916626,
|
| 135 |
+
"eval_p": 73.93,
|
| 136 |
+
"eval_r": 68.57,
|
| 137 |
+
"eval_runtime": 48.8895,
|
| 138 |
+
"eval_samples_per_second": 10.145,
|
| 139 |
+
"eval_steps_per_second": 0.634,
|
| 140 |
+
"step": 500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.208835341365462,
|
| 144 |
+
"grad_norm": 5.176413536071777,
|
| 145 |
+
"learning_rate": 4.421852440709666e-05,
|
| 146 |
+
"loss": 0.2646,
|
| 147 |
+
"step": 550
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.4096385542168672,
|
| 151 |
+
"grad_norm": 19.735258102416992,
|
| 152 |
+
"learning_rate": 4.3172311296078595e-05,
|
| 153 |
+
"loss": 0.3214,
|
| 154 |
+
"step": 600
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.4096385542168672,
|
| 158 |
+
"eval_f1": 72.28,
|
| 159 |
+
"eval_gen_len": 46.564516129032256,
|
| 160 |
+
"eval_loss": 0.788872241973877,
|
| 161 |
+
"eval_p": 74.17,
|
| 162 |
+
"eval_r": 74.3,
|
| 163 |
+
"eval_runtime": 54.3998,
|
| 164 |
+
"eval_samples_per_second": 9.118,
|
| 165 |
+
"eval_steps_per_second": 0.57,
|
| 166 |
+
"step": 600
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.610441767068273,
|
| 170 |
+
"grad_norm": 9.665975570678711,
|
| 171 |
+
"learning_rate": 4.205380336255594e-05,
|
| 172 |
+
"loss": 0.4161,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.8112449799196786,
|
| 177 |
+
"grad_norm": 8.65356731414795,
|
| 178 |
+
"learning_rate": 4.08674503614997e-05,
|
| 179 |
+
"loss": 0.2973,
|
| 180 |
+
"step": 700
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.8112449799196786,
|
| 184 |
+
"eval_f1": 68.05,
|
| 185 |
+
"eval_gen_len": 41.256048387096776,
|
| 186 |
+
"eval_loss": 0.770168662071228,
|
| 187 |
+
"eval_p": 74.23,
|
| 188 |
+
"eval_r": 66.93,
|
| 189 |
+
"eval_runtime": 44.2971,
|
| 190 |
+
"eval_samples_per_second": 11.197,
|
| 191 |
+
"eval_steps_per_second": 0.7,
|
| 192 |
+
"step": 700
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.0120481927710845,
|
| 196 |
+
"grad_norm": 4.7805867195129395,
|
| 197 |
+
"learning_rate": 3.961797195560118e-05,
|
| 198 |
+
"loss": 0.3477,
|
| 199 |
+
"step": 750
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.21285140562249,
|
| 203 |
+
"grad_norm": 3.864029884338379,
|
| 204 |
+
"learning_rate": 3.8310338939059644e-05,
|
| 205 |
+
"loss": 0.2447,
|
| 206 |
+
"step": 800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.21285140562249,
|
| 210 |
+
"eval_f1": 69.3,
|
| 211 |
+
"eval_gen_len": 42.681451612903224,
|
| 212 |
+
"eval_loss": 0.8243445158004761,
|
| 213 |
+
"eval_p": 74.09,
|
| 214 |
+
"eval_r": 68.98,
|
| 215 |
+
"eval_runtime": 47.774,
|
| 216 |
+
"eval_samples_per_second": 10.382,
|
| 217 |
+
"eval_steps_per_second": 0.649,
|
| 218 |
+
"step": 800
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.4136546184738954,
|
| 222 |
+
"grad_norm": 1.5391823053359985,
|
| 223 |
+
"learning_rate": 3.694975346229458e-05,
|
| 224 |
+
"loss": 0.2272,
|
| 225 |
+
"step": 850
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.6144578313253013,
|
| 229 |
+
"grad_norm": 12.502788543701172,
|
| 230 |
+
"learning_rate": 3.55416283362546e-05,
|
| 231 |
+
"loss": 0.2136,
|
| 232 |
+
"step": 900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.6144578313253013,
|
| 236 |
+
"eval_f1": 72.18,
|
| 237 |
+
"eval_gen_len": 45.850806451612904,
|
| 238 |
+
"eval_loss": 0.8359085917472839,
|
| 239 |
+
"eval_p": 74.24,
|
| 240 |
+
"eval_r": 73.77,
|
| 241 |
+
"eval_runtime": 51.4887,
|
| 242 |
+
"eval_samples_per_second": 9.633,
|
| 243 |
+
"eval_steps_per_second": 0.602,
|
| 244 |
+
"step": 900
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 3.8152610441767068,
|
| 248 |
+
"grad_norm": 6.718369960784912,
|
| 249 |
+
"learning_rate": 3.409156549865654e-05,
|
| 250 |
+
"loss": 0.1959,
|
| 251 |
+
"step": 950
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 4.016064257028113,
|
| 255 |
+
"grad_norm": 32.431217193603516,
|
| 256 |
+
"learning_rate": 3.260533372782234e-05,
|
| 257 |
+
"loss": 0.2571,
|
| 258 |
+
"step": 1000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 4.016064257028113,
|
| 262 |
+
"eval_f1": 69.38,
|
| 263 |
+
"eval_gen_len": 42.243951612903224,
|
| 264 |
+
"eval_loss": 0.8177807927131653,
|
| 265 |
+
"eval_p": 73.87,
|
| 266 |
+
"eval_r": 69.22,
|
| 267 |
+
"eval_runtime": 48.2955,
|
| 268 |
+
"eval_samples_per_second": 10.27,
|
| 269 |
+
"eval_steps_per_second": 0.642,
|
| 270 |
+
"step": 1000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.216867469879518,
|
| 274 |
+
"grad_norm": 5.5347065925598145,
|
| 275 |
+
"learning_rate": 3.10888456927748e-05,
|
| 276 |
+
"loss": 0.1427,
|
| 277 |
+
"step": 1050
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.417670682730924,
|
| 281 |
+
"grad_norm": 4.728146076202393,
|
| 282 |
+
"learning_rate": 2.9548134430893604e-05,
|
| 283 |
+
"loss": 0.1356,
|
| 284 |
+
"step": 1100
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.417670682730924,
|
| 288 |
+
"eval_f1": 70.43,
|
| 289 |
+
"eval_gen_len": 44.792338709677416,
|
| 290 |
+
"eval_loss": 0.8745766878128052,
|
| 291 |
+
"eval_p": 73.6,
|
| 292 |
+
"eval_r": 71.48,
|
| 293 |
+
"eval_runtime": 49.7707,
|
| 294 |
+
"eval_samples_per_second": 9.966,
|
| 295 |
+
"eval_steps_per_second": 0.623,
|
| 296 |
+
"step": 1100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.618473895582329,
|
| 300 |
+
"grad_norm": 4.265488147735596,
|
| 301 |
+
"learning_rate": 2.7989329346710375e-05,
|
| 302 |
+
"loss": 0.1644,
|
| 303 |
+
"step": 1150
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.8192771084337345,
|
| 307 |
+
"grad_norm": 5.412672996520996,
|
| 308 |
+
"learning_rate": 2.6418631827326857e-05,
|
| 309 |
+
"loss": 0.1564,
|
| 310 |
+
"step": 1200
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.8192771084337345,
|
| 314 |
+
"eval_f1": 70.56,
|
| 315 |
+
"eval_gen_len": 45.20967741935484,
|
| 316 |
+
"eval_loss": 0.8563244342803955,
|
| 317 |
+
"eval_p": 73.64,
|
| 318 |
+
"eval_r": 71.76,
|
| 319 |
+
"eval_runtime": 50.2355,
|
| 320 |
+
"eval_samples_per_second": 9.873,
|
| 321 |
+
"eval_steps_per_second": 0.617,
|
| 322 |
+
"step": 1200
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 5.020080321285141,
|
| 326 |
+
"grad_norm": 5.465022087097168,
|
| 327 |
+
"learning_rate": 2.484229057146507e-05,
|
| 328 |
+
"loss": 0.1396,
|
| 329 |
+
"step": 1250
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 5.220883534136546,
|
| 333 |
+
"grad_norm": 4.947805881500244,
|
| 334 |
+
"learning_rate": 2.3266576730297956e-05,
|
| 335 |
+
"loss": 0.0937,
|
| 336 |
+
"step": 1300
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.220883534136546,
|
| 340 |
+
"eval_f1": 70.17,
|
| 341 |
+
"eval_gen_len": 42.51411290322581,
|
| 342 |
+
"eval_loss": 0.8945086002349854,
|
| 343 |
+
"eval_p": 74.73,
|
| 344 |
+
"eval_r": 69.95,
|
| 345 |
+
"eval_runtime": 47.3409,
|
| 346 |
+
"eval_samples_per_second": 10.477,
|
| 347 |
+
"eval_steps_per_second": 0.655,
|
| 348 |
+
"step": 1300
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.421686746987952,
|
| 352 |
+
"grad_norm": 2.938572883605957,
|
| 353 |
+
"learning_rate": 2.1697758958957448e-05,
|
| 354 |
+
"loss": 0.0842,
|
| 355 |
+
"step": 1350
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 5.622489959839357,
|
| 359 |
+
"grad_norm": 7.102436542510986,
|
| 360 |
+
"learning_rate": 2.014207847797256e-05,
|
| 361 |
+
"loss": 0.1031,
|
| 362 |
+
"step": 1400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.622489959839357,
|
| 366 |
+
"eval_f1": 71.86,
|
| 367 |
+
"eval_gen_len": 47.534274193548384,
|
| 368 |
+
"eval_loss": 0.8877253532409668,
|
| 369 |
+
"eval_p": 73.18,
|
| 370 |
+
"eval_r": 74.71,
|
| 371 |
+
"eval_runtime": 53.5518,
|
| 372 |
+
"eval_samples_per_second": 9.262,
|
| 373 |
+
"eval_steps_per_second": 0.579,
|
| 374 |
+
"step": 1400
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.823293172690763,
|
| 378 |
+
"grad_norm": 2.2575900554656982,
|
| 379 |
+
"learning_rate": 1.8605724243850502e-05,
|
| 380 |
+
"loss": 0.1126,
|
| 381 |
+
"step": 1450
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 6.024096385542169,
|
| 385 |
+
"grad_norm": 3.7854058742523193,
|
| 386 |
+
"learning_rate": 1.70948083275794e-05,
|
| 387 |
+
"loss": 0.095,
|
| 388 |
+
"step": 1500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 6.024096385542169,
|
| 392 |
+
"eval_f1": 70.87,
|
| 393 |
+
"eval_gen_len": 45.21774193548387,
|
| 394 |
+
"eval_loss": 0.9038512706756592,
|
| 395 |
+
"eval_p": 73.83,
|
| 396 |
+
"eval_r": 72.16,
|
| 397 |
+
"eval_runtime": 52.1132,
|
| 398 |
+
"eval_samples_per_second": 9.518,
|
| 399 |
+
"eval_steps_per_second": 0.595,
|
| 400 |
+
"step": 1500
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 6.224899598393574,
|
| 404 |
+
"grad_norm": 3.2422773838043213,
|
| 405 |
+
"learning_rate": 1.561534159900441e-05,
|
| 406 |
+
"loss": 0.0689,
|
| 407 |
+
"step": 1550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.42570281124498,
|
| 411 |
+
"grad_norm": 6.3022990226745605,
|
| 412 |
+
"learning_rate": 1.4173209813811788e-05,
|
| 413 |
+
"loss": 0.0764,
|
| 414 |
+
"step": 1600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 6.42570281124498,
|
| 418 |
+
"eval_f1": 71.12,
|
| 419 |
+
"eval_gen_len": 46.310483870967744,
|
| 420 |
+
"eval_loss": 0.9024052619934082,
|
| 421 |
+
"eval_p": 73.55,
|
| 422 |
+
"eval_r": 73.2,
|
| 423 |
+
"eval_runtime": 51.8511,
|
| 424 |
+
"eval_samples_per_second": 9.566,
|
| 425 |
+
"eval_steps_per_second": 0.598,
|
| 426 |
+
"step": 1600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 6.626506024096385,
|
| 430 |
+
"grad_norm": 3.3996074199676514,
|
| 431 |
+
"learning_rate": 1.277415019825417e-05,
|
| 432 |
+
"loss": 0.0639,
|
| 433 |
+
"step": 1650
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 6.827309236947791,
|
| 437 |
+
"grad_norm": 1.7633498907089233,
|
| 438 |
+
"learning_rate": 1.1423728624769695e-05,
|
| 439 |
+
"loss": 0.0499,
|
| 440 |
+
"step": 1700
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.827309236947791,
|
| 444 |
+
"eval_f1": 71.1,
|
| 445 |
+
"eval_gen_len": 45.52620967741935,
|
| 446 |
+
"eval_loss": 0.9023270010948181,
|
| 447 |
+
"eval_p": 73.73,
|
| 448 |
+
"eval_r": 72.63,
|
| 449 |
+
"eval_runtime": 48.5153,
|
| 450 |
+
"eval_samples_per_second": 10.224,
|
| 451 |
+
"eval_steps_per_second": 0.639,
|
| 452 |
+
"step": 1700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 7.028112449799197,
|
| 456 |
+
"grad_norm": 0.14504443109035492,
|
| 457 |
+
"learning_rate": 1.0127317469297277e-05,
|
| 458 |
+
"loss": 0.0707,
|
| 459 |
+
"step": 1750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 7.228915662650603,
|
| 463 |
+
"grad_norm": 0.9350752830505371,
|
| 464 |
+
"learning_rate": 8.890074238378074e-06,
|
| 465 |
+
"loss": 0.0422,
|
| 466 |
+
"step": 1800
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 7.228915662650603,
|
| 470 |
+
"eval_f1": 71.74,
|
| 471 |
+
"eval_gen_len": 46.16935483870968,
|
| 472 |
+
"eval_loss": 0.9106847643852234,
|
| 473 |
+
"eval_p": 73.84,
|
| 474 |
+
"eval_r": 73.54,
|
| 475 |
+
"eval_runtime": 53.7841,
|
| 476 |
+
"eval_samples_per_second": 9.222,
|
| 477 |
+
"eval_steps_per_second": 0.576,
|
| 478 |
+
"step": 1800
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.429718875502008,
|
| 482 |
+
"grad_norm": 2.7118020057678223,
|
| 483 |
+
"learning_rate": 7.71692105107098e-06,
|
| 484 |
+
"loss": 0.0442,
|
| 485 |
+
"step": 1850
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.6305220883534135,
|
| 489 |
+
"grad_norm": 3.540323495864868,
|
| 490 |
+
"learning_rate": 6.612525057308949e-06,
|
| 491 |
+
"loss": 0.0469,
|
| 492 |
+
"step": 1900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.6305220883534135,
|
| 496 |
+
"eval_f1": 71.51,
|
| 497 |
+
"eval_gen_len": 45.40120967741935,
|
| 498 |
+
"eval_loss": 0.9106153845787048,
|
| 499 |
+
"eval_p": 74.15,
|
| 500 |
+
"eval_r": 73.09,
|
| 501 |
+
"eval_runtime": 51.3332,
|
| 502 |
+
"eval_samples_per_second": 9.662,
|
| 503 |
+
"eval_steps_per_second": 0.604,
|
| 504 |
+
"step": 1900
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 7.831325301204819,
|
| 508 |
+
"grad_norm": 1.7734179496765137,
|
| 509 |
+
"learning_rate": 5.581279870597867e-06,
|
| 510 |
+
"loss": 0.0368,
|
| 511 |
+
"step": 1950
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 8.032128514056225,
|
| 515 |
+
"grad_norm": 2.24417781829834,
|
| 516 |
+
"learning_rate": 4.627288088924156e-06,
|
| 517 |
+
"loss": 0.0379,
|
| 518 |
+
"step": 2000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.032128514056225,
|
| 522 |
+
"eval_f1": 70.84,
|
| 523 |
+
"eval_gen_len": 45.127016129032256,
|
| 524 |
+
"eval_loss": 0.9157423973083496,
|
| 525 |
+
"eval_p": 73.79,
|
| 526 |
+
"eval_r": 72.15,
|
| 527 |
+
"eval_runtime": 51.0735,
|
| 528 |
+
"eval_samples_per_second": 9.711,
|
| 529 |
+
"eval_steps_per_second": 0.607,
|
| 530 |
+
"step": 2000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 8.23293172690763,
|
| 534 |
+
"grad_norm": 1.954770565032959,
|
| 535 |
+
"learning_rate": 3.754344973408064e-06,
|
| 536 |
+
"loss": 0.0335,
|
| 537 |
+
"step": 2050
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 8.433734939759036,
|
| 541 |
+
"grad_norm": 1.5767686367034912,
|
| 542 |
+
"learning_rate": 2.9659233496337786e-06,
|
| 543 |
+
"loss": 0.0301,
|
| 544 |
+
"step": 2100
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 8.433734939759036,
|
| 548 |
+
"eval_f1": 71.39,
|
| 549 |
+
"eval_gen_len": 46.381048387096776,
|
| 550 |
+
"eval_loss": 0.9240424633026123,
|
| 551 |
+
"eval_p": 73.77,
|
| 552 |
+
"eval_r": 73.37,
|
| 553 |
+
"eval_runtime": 53.2399,
|
| 554 |
+
"eval_samples_per_second": 9.316,
|
| 555 |
+
"eval_steps_per_second": 0.582,
|
| 556 |
+
"step": 2100
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 8.634538152610443,
|
| 560 |
+
"grad_norm": 0.2601850628852844,
|
| 561 |
+
"learning_rate": 2.265159791723373e-06,
|
| 562 |
+
"loss": 0.0358,
|
| 563 |
+
"step": 2150
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 8.835341365461847,
|
| 567 |
+
"grad_norm": 5.757479667663574,
|
| 568 |
+
"learning_rate": 1.6548421441183875e-06,
|
| 569 |
+
"loss": 0.0254,
|
| 570 |
+
"step": 2200
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 8.835341365461847,
|
| 574 |
+
"eval_f1": 71.82,
|
| 575 |
+
"eval_gen_len": 46.47782258064516,
|
| 576 |
+
"eval_loss": 0.9292237162590027,
|
| 577 |
+
"eval_p": 73.8,
|
| 578 |
+
"eval_r": 74.04,
|
| 579 |
+
"eval_runtime": 54.2877,
|
| 580 |
+
"eval_samples_per_second": 9.137,
|
| 581 |
+
"eval_steps_per_second": 0.571,
|
| 582 |
+
"step": 2200
|
| 583 |
+
}
|
| 584 |
+
],
|
| 585 |
+
"logging_steps": 50,
|
| 586 |
+
"max_steps": 2490,
|
| 587 |
+
"num_input_tokens_seen": 0,
|
| 588 |
+
"num_train_epochs": 10,
|
| 589 |
+
"save_steps": 100,
|
| 590 |
+
"stateful_callbacks": {
|
| 591 |
+
"TrainerControl": {
|
| 592 |
+
"args": {
|
| 593 |
+
"should_epoch_stop": false,
|
| 594 |
+
"should_evaluate": false,
|
| 595 |
+
"should_log": false,
|
| 596 |
+
"should_save": true,
|
| 597 |
+
"should_training_stop": false
|
| 598 |
+
},
|
| 599 |
+
"attributes": {}
|
| 600 |
+
}
|
| 601 |
+
},
|
| 602 |
+
"total_flos": 490953080733696.0,
|
| 603 |
+
"train_batch_size": 4,
|
| 604 |
+
"trial_name": null,
|
| 605 |
+
"trial_params": null
|
| 606 |
+
}
|
checkpoint-2200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6394e6b1fa4ef7d935e2f7613f4253c064d2fa097794737e407c70b78eea9756
|
| 3 |
+
size 5560
|