Upload 13 files
Browse files- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +37 -0
- generation_config.json +9 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +12 -0
- trainer_state.json +691 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/bartpho-word-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MBartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 768,
|
| 12 |
+
"decoder_attention_heads": 12,
|
| 13 |
+
"decoder_ffn_dim": 3072,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 2,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"encoder_attention_heads": 12,
|
| 19 |
+
"encoder_ffn_dim": 3072,
|
| 20 |
+
"encoder_layerdrop": 0.0,
|
| 21 |
+
"encoder_layers": 6,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"forced_eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_position_embeddings": 1024,
|
| 28 |
+
"model_type": "mbart",
|
| 29 |
+
"num_hidden_layers": 6,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"scale_embedding": false,
|
| 32 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.33.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 64001
|
| 37 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.33.0"
|
| 9 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:516f10601a2f31950f6928a7f4e76a95314ad9773235fcda69c1f9566201e0c0
|
| 3 |
+
size 1200001349
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5fa650a22bddf1061f48cc591c2bfedd29e17928fba2013a2048db58f298afd
|
| 3 |
+
size 600236781
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c0d3c1ef9c5cc469a4a8805b102cf9c3bd42ee6521ec10c76d2c23850258420
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098c28be5501b728986193eb159ea21e8cbef80badb237cb5fba51feffaf92ec
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "</s>",
|
| 10 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,691 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.607843137254903,
|
| 5 |
+
"eval_steps": 250,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.41,
|
| 13 |
+
"learning_rate": 1.2254901960784313e-05,
|
| 14 |
+
"loss": 2.8121,
|
| 15 |
+
"step": 250
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.41,
|
| 19 |
+
"eval_loss": 0.8146461248397827,
|
| 20 |
+
"eval_runtime": 28.4909,
|
| 21 |
+
"eval_samples_per_second": 50.086,
|
| 22 |
+
"eval_steps_per_second": 3.159,
|
| 23 |
+
"step": 250
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.82,
|
| 27 |
+
"learning_rate": 2.4509803921568626e-05,
|
| 28 |
+
"loss": 0.7537,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.82,
|
| 33 |
+
"eval_loss": 0.7322247624397278,
|
| 34 |
+
"eval_runtime": 28.2904,
|
| 35 |
+
"eval_samples_per_second": 50.441,
|
| 36 |
+
"eval_steps_per_second": 3.181,
|
| 37 |
+
"step": 500
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.23,
|
| 41 |
+
"learning_rate": 2.9643962848297217e-05,
|
| 42 |
+
"loss": 0.6434,
|
| 43 |
+
"step": 750
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.23,
|
| 47 |
+
"eval_loss": 0.6870973706245422,
|
| 48 |
+
"eval_runtime": 28.2349,
|
| 49 |
+
"eval_samples_per_second": 50.54,
|
| 50 |
+
"eval_steps_per_second": 3.188,
|
| 51 |
+
"step": 750
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.63,
|
| 55 |
+
"learning_rate": 2.8998968008255932e-05,
|
| 56 |
+
"loss": 0.6207,
|
| 57 |
+
"step": 1000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.63,
|
| 61 |
+
"eval_loss": 0.6630086898803711,
|
| 62 |
+
"eval_runtime": 28.2684,
|
| 63 |
+
"eval_samples_per_second": 50.48,
|
| 64 |
+
"eval_steps_per_second": 3.184,
|
| 65 |
+
"step": 1000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.04,
|
| 69 |
+
"learning_rate": 2.8353973168214654e-05,
|
| 70 |
+
"loss": 0.5771,
|
| 71 |
+
"step": 1250
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.04,
|
| 75 |
+
"eval_loss": 0.6516671776771545,
|
| 76 |
+
"eval_runtime": 28.2447,
|
| 77 |
+
"eval_samples_per_second": 50.523,
|
| 78 |
+
"eval_steps_per_second": 3.186,
|
| 79 |
+
"step": 1250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.45,
|
| 83 |
+
"learning_rate": 2.7708978328173376e-05,
|
| 84 |
+
"loss": 0.54,
|
| 85 |
+
"step": 1500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.45,
|
| 89 |
+
"eval_loss": 0.6349040269851685,
|
| 90 |
+
"eval_runtime": 28.3054,
|
| 91 |
+
"eval_samples_per_second": 50.414,
|
| 92 |
+
"eval_steps_per_second": 3.18,
|
| 93 |
+
"step": 1500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.86,
|
| 97 |
+
"learning_rate": 2.7063983488132095e-05,
|
| 98 |
+
"loss": 0.5286,
|
| 99 |
+
"step": 1750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.86,
|
| 103 |
+
"eval_loss": 0.6304510831832886,
|
| 104 |
+
"eval_runtime": 28.2763,
|
| 105 |
+
"eval_samples_per_second": 50.466,
|
| 106 |
+
"eval_steps_per_second": 3.183,
|
| 107 |
+
"step": 1750
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.27,
|
| 111 |
+
"learning_rate": 2.6418988648090816e-05,
|
| 112 |
+
"loss": 0.4998,
|
| 113 |
+
"step": 2000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.27,
|
| 117 |
+
"eval_loss": 0.6260914206504822,
|
| 118 |
+
"eval_runtime": 28.3237,
|
| 119 |
+
"eval_samples_per_second": 50.382,
|
| 120 |
+
"eval_steps_per_second": 3.178,
|
| 121 |
+
"step": 2000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.68,
|
| 125 |
+
"learning_rate": 2.577399380804954e-05,
|
| 126 |
+
"loss": 0.4874,
|
| 127 |
+
"step": 2250
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.68,
|
| 131 |
+
"eval_loss": 0.6250064969062805,
|
| 132 |
+
"eval_runtime": 28.23,
|
| 133 |
+
"eval_samples_per_second": 50.549,
|
| 134 |
+
"eval_steps_per_second": 3.188,
|
| 135 |
+
"step": 2250
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.08,
|
| 139 |
+
"learning_rate": 2.5128998968008257e-05,
|
| 140 |
+
"loss": 0.4704,
|
| 141 |
+
"step": 2500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.08,
|
| 145 |
+
"eval_loss": 0.6252643465995789,
|
| 146 |
+
"eval_runtime": 28.3447,
|
| 147 |
+
"eval_samples_per_second": 50.344,
|
| 148 |
+
"eval_steps_per_second": 3.175,
|
| 149 |
+
"step": 2500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.49,
|
| 153 |
+
"learning_rate": 2.4484004127966975e-05,
|
| 154 |
+
"loss": 0.4431,
|
| 155 |
+
"step": 2750
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 4.49,
|
| 159 |
+
"eval_loss": 0.6222314238548279,
|
| 160 |
+
"eval_runtime": 28.3136,
|
| 161 |
+
"eval_samples_per_second": 50.4,
|
| 162 |
+
"eval_steps_per_second": 3.179,
|
| 163 |
+
"step": 2750
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.9,
|
| 167 |
+
"learning_rate": 2.3839009287925697e-05,
|
| 168 |
+
"loss": 0.4502,
|
| 169 |
+
"step": 3000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.9,
|
| 173 |
+
"eval_loss": 0.6138860583305359,
|
| 174 |
+
"eval_runtime": 28.2755,
|
| 175 |
+
"eval_samples_per_second": 50.468,
|
| 176 |
+
"eval_steps_per_second": 3.183,
|
| 177 |
+
"step": 3000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.31,
|
| 181 |
+
"learning_rate": 2.3194014447884416e-05,
|
| 182 |
+
"loss": 0.4216,
|
| 183 |
+
"step": 3250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.31,
|
| 187 |
+
"eval_loss": 0.6158970594406128,
|
| 188 |
+
"eval_runtime": 28.2142,
|
| 189 |
+
"eval_samples_per_second": 50.577,
|
| 190 |
+
"eval_steps_per_second": 3.19,
|
| 191 |
+
"step": 3250
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.72,
|
| 195 |
+
"learning_rate": 2.2549019607843138e-05,
|
| 196 |
+
"loss": 0.4146,
|
| 197 |
+
"step": 3500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 5.72,
|
| 201 |
+
"eval_loss": 0.6141221523284912,
|
| 202 |
+
"eval_runtime": 28.2223,
|
| 203 |
+
"eval_samples_per_second": 50.563,
|
| 204 |
+
"eval_steps_per_second": 3.189,
|
| 205 |
+
"step": 3500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 6.13,
|
| 209 |
+
"learning_rate": 2.190402476780186e-05,
|
| 210 |
+
"loss": 0.4079,
|
| 211 |
+
"step": 3750
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 6.13,
|
| 215 |
+
"eval_loss": 0.6209476590156555,
|
| 216 |
+
"eval_runtime": 28.2459,
|
| 217 |
+
"eval_samples_per_second": 50.521,
|
| 218 |
+
"eval_steps_per_second": 3.186,
|
| 219 |
+
"step": 3750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.54,
|
| 223 |
+
"learning_rate": 2.1259029927760578e-05,
|
| 224 |
+
"loss": 0.3882,
|
| 225 |
+
"step": 4000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 6.54,
|
| 229 |
+
"eval_loss": 0.6084998250007629,
|
| 230 |
+
"eval_runtime": 28.195,
|
| 231 |
+
"eval_samples_per_second": 50.612,
|
| 232 |
+
"eval_steps_per_second": 3.192,
|
| 233 |
+
"step": 4000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.94,
|
| 237 |
+
"learning_rate": 2.06140350877193e-05,
|
| 238 |
+
"loss": 0.3917,
|
| 239 |
+
"step": 4250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.94,
|
| 243 |
+
"eval_loss": 0.6080483198165894,
|
| 244 |
+
"eval_runtime": 28.2021,
|
| 245 |
+
"eval_samples_per_second": 50.599,
|
| 246 |
+
"eval_steps_per_second": 3.191,
|
| 247 |
+
"step": 4250
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.35,
|
| 251 |
+
"learning_rate": 1.9969040247678018e-05,
|
| 252 |
+
"loss": 0.3654,
|
| 253 |
+
"step": 4500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 7.35,
|
| 257 |
+
"eval_loss": 0.616654634475708,
|
| 258 |
+
"eval_runtime": 28.1521,
|
| 259 |
+
"eval_samples_per_second": 50.689,
|
| 260 |
+
"eval_steps_per_second": 3.197,
|
| 261 |
+
"step": 4500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.76,
|
| 265 |
+
"learning_rate": 1.9324045407636737e-05,
|
| 266 |
+
"loss": 0.3672,
|
| 267 |
+
"step": 4750
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 7.76,
|
| 271 |
+
"eval_loss": 0.6128713488578796,
|
| 272 |
+
"eval_runtime": 28.1986,
|
| 273 |
+
"eval_samples_per_second": 50.605,
|
| 274 |
+
"eval_steps_per_second": 3.192,
|
| 275 |
+
"step": 4750
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 8.17,
|
| 279 |
+
"learning_rate": 1.867905056759546e-05,
|
| 280 |
+
"loss": 0.3562,
|
| 281 |
+
"step": 5000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 8.17,
|
| 285 |
+
"eval_loss": 0.6237680315971375,
|
| 286 |
+
"eval_runtime": 28.209,
|
| 287 |
+
"eval_samples_per_second": 50.587,
|
| 288 |
+
"eval_steps_per_second": 3.19,
|
| 289 |
+
"step": 5000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 8.58,
|
| 293 |
+
"learning_rate": 1.803405572755418e-05,
|
| 294 |
+
"loss": 0.3383,
|
| 295 |
+
"step": 5250
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 8.58,
|
| 299 |
+
"eval_loss": 0.6211274266242981,
|
| 300 |
+
"eval_runtime": 28.1959,
|
| 301 |
+
"eval_samples_per_second": 50.61,
|
| 302 |
+
"eval_steps_per_second": 3.192,
|
| 303 |
+
"step": 5250
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.99,
|
| 307 |
+
"learning_rate": 1.73890608875129e-05,
|
| 308 |
+
"loss": 0.347,
|
| 309 |
+
"step": 5500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.99,
|
| 313 |
+
"eval_loss": 0.6140613555908203,
|
| 314 |
+
"eval_runtime": 28.169,
|
| 315 |
+
"eval_samples_per_second": 50.659,
|
| 316 |
+
"eval_steps_per_second": 3.195,
|
| 317 |
+
"step": 5500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.4,
|
| 321 |
+
"learning_rate": 1.674406604747162e-05,
|
| 322 |
+
"loss": 0.3209,
|
| 323 |
+
"step": 5750
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 9.4,
|
| 327 |
+
"eval_loss": 0.6265636682510376,
|
| 328 |
+
"eval_runtime": 28.1893,
|
| 329 |
+
"eval_samples_per_second": 50.622,
|
| 330 |
+
"eval_steps_per_second": 3.193,
|
| 331 |
+
"step": 5750
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 9.8,
|
| 335 |
+
"learning_rate": 1.6099071207430343e-05,
|
| 336 |
+
"loss": 0.3268,
|
| 337 |
+
"step": 6000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 9.8,
|
| 341 |
+
"eval_loss": 0.6181433796882629,
|
| 342 |
+
"eval_runtime": 28.1932,
|
| 343 |
+
"eval_samples_per_second": 50.615,
|
| 344 |
+
"eval_steps_per_second": 3.192,
|
| 345 |
+
"step": 6000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 10.21,
|
| 349 |
+
"learning_rate": 1.545407636738906e-05,
|
| 350 |
+
"loss": 0.3126,
|
| 351 |
+
"step": 6250
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 10.21,
|
| 355 |
+
"eval_loss": 0.6234831809997559,
|
| 356 |
+
"eval_runtime": 28.1977,
|
| 357 |
+
"eval_samples_per_second": 50.607,
|
| 358 |
+
"eval_steps_per_second": 3.192,
|
| 359 |
+
"step": 6250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 10.62,
|
| 363 |
+
"learning_rate": 1.4809081527347781e-05,
|
| 364 |
+
"loss": 0.3075,
|
| 365 |
+
"step": 6500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 10.62,
|
| 369 |
+
"eval_loss": 0.6242398023605347,
|
| 370 |
+
"eval_runtime": 28.2355,
|
| 371 |
+
"eval_samples_per_second": 50.539,
|
| 372 |
+
"eval_steps_per_second": 3.187,
|
| 373 |
+
"step": 6500
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 11.03,
|
| 377 |
+
"learning_rate": 1.4164086687306502e-05,
|
| 378 |
+
"loss": 0.3113,
|
| 379 |
+
"step": 6750
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 11.03,
|
| 383 |
+
"eval_loss": 0.6290929913520813,
|
| 384 |
+
"eval_runtime": 28.2357,
|
| 385 |
+
"eval_samples_per_second": 50.539,
|
| 386 |
+
"eval_steps_per_second": 3.187,
|
| 387 |
+
"step": 6750
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 11.44,
|
| 391 |
+
"learning_rate": 1.3519091847265222e-05,
|
| 392 |
+
"loss": 0.2921,
|
| 393 |
+
"step": 7000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 11.44,
|
| 397 |
+
"eval_loss": 0.6291936039924622,
|
| 398 |
+
"eval_runtime": 28.3781,
|
| 399 |
+
"eval_samples_per_second": 50.285,
|
| 400 |
+
"eval_steps_per_second": 3.171,
|
| 401 |
+
"step": 7000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 11.85,
|
| 405 |
+
"learning_rate": 1.2874097007223944e-05,
|
| 406 |
+
"loss": 0.2933,
|
| 407 |
+
"step": 7250
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 11.85,
|
| 411 |
+
"eval_loss": 0.6279457807540894,
|
| 412 |
+
"eval_runtime": 28.2812,
|
| 413 |
+
"eval_samples_per_second": 50.457,
|
| 414 |
+
"eval_steps_per_second": 3.182,
|
| 415 |
+
"step": 7250
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 12.25,
|
| 419 |
+
"learning_rate": 1.2229102167182664e-05,
|
| 420 |
+
"loss": 0.2808,
|
| 421 |
+
"step": 7500
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 12.25,
|
| 425 |
+
"eval_loss": 0.6309792995452881,
|
| 426 |
+
"eval_runtime": 28.2292,
|
| 427 |
+
"eval_samples_per_second": 50.55,
|
| 428 |
+
"eval_steps_per_second": 3.188,
|
| 429 |
+
"step": 7500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 12.66,
|
| 433 |
+
"learning_rate": 1.1584107327141382e-05,
|
| 434 |
+
"loss": 0.2809,
|
| 435 |
+
"step": 7750
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 12.66,
|
| 439 |
+
"eval_loss": 0.6356364488601685,
|
| 440 |
+
"eval_runtime": 28.2615,
|
| 441 |
+
"eval_samples_per_second": 50.493,
|
| 442 |
+
"eval_steps_per_second": 3.185,
|
| 443 |
+
"step": 7750
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 13.07,
|
| 447 |
+
"learning_rate": 1.0939112487100104e-05,
|
| 448 |
+
"loss": 0.2778,
|
| 449 |
+
"step": 8000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 13.07,
|
| 453 |
+
"eval_loss": 0.6354484558105469,
|
| 454 |
+
"eval_runtime": 28.3136,
|
| 455 |
+
"eval_samples_per_second": 50.4,
|
| 456 |
+
"eval_steps_per_second": 3.179,
|
| 457 |
+
"step": 8000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 13.48,
|
| 461 |
+
"learning_rate": 1.0294117647058824e-05,
|
| 462 |
+
"loss": 0.2707,
|
| 463 |
+
"step": 8250
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 13.48,
|
| 467 |
+
"eval_loss": 0.6366216540336609,
|
| 468 |
+
"eval_runtime": 28.3106,
|
| 469 |
+
"eval_samples_per_second": 50.405,
|
| 470 |
+
"eval_steps_per_second": 3.179,
|
| 471 |
+
"step": 8250
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 13.89,
|
| 475 |
+
"learning_rate": 9.649122807017543e-06,
|
| 476 |
+
"loss": 0.2644,
|
| 477 |
+
"step": 8500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 13.89,
|
| 481 |
+
"eval_loss": 0.6386236548423767,
|
| 482 |
+
"eval_runtime": 28.3478,
|
| 483 |
+
"eval_samples_per_second": 50.339,
|
| 484 |
+
"eval_steps_per_second": 3.175,
|
| 485 |
+
"step": 8500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 14.3,
|
| 489 |
+
"learning_rate": 9.004127966976265e-06,
|
| 490 |
+
"loss": 0.2574,
|
| 491 |
+
"step": 8750
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 14.3,
|
| 495 |
+
"eval_loss": 0.6385951638221741,
|
| 496 |
+
"eval_runtime": 28.3245,
|
| 497 |
+
"eval_samples_per_second": 50.38,
|
| 498 |
+
"eval_steps_per_second": 3.177,
|
| 499 |
+
"step": 8750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 14.71,
|
| 503 |
+
"learning_rate": 8.359133126934985e-06,
|
| 504 |
+
"loss": 0.2564,
|
| 505 |
+
"step": 9000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 14.71,
|
| 509 |
+
"eval_loss": 0.6378169059753418,
|
| 510 |
+
"eval_runtime": 28.3461,
|
| 511 |
+
"eval_samples_per_second": 50.342,
|
| 512 |
+
"eval_steps_per_second": 3.175,
|
| 513 |
+
"step": 9000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 15.11,
|
| 517 |
+
"learning_rate": 7.714138286893705e-06,
|
| 518 |
+
"loss": 0.2555,
|
| 519 |
+
"step": 9250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 15.11,
|
| 523 |
+
"eval_loss": 0.6417073011398315,
|
| 524 |
+
"eval_runtime": 28.3435,
|
| 525 |
+
"eval_samples_per_second": 50.347,
|
| 526 |
+
"eval_steps_per_second": 3.175,
|
| 527 |
+
"step": 9250
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 15.52,
|
| 531 |
+
"learning_rate": 7.069143446852426e-06,
|
| 532 |
+
"loss": 0.2478,
|
| 533 |
+
"step": 9500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 15.52,
|
| 537 |
+
"eval_loss": 0.6406723260879517,
|
| 538 |
+
"eval_runtime": 28.3209,
|
| 539 |
+
"eval_samples_per_second": 50.387,
|
| 540 |
+
"eval_steps_per_second": 3.178,
|
| 541 |
+
"step": 9500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 15.93,
|
| 545 |
+
"learning_rate": 6.424148606811145e-06,
|
| 546 |
+
"loss": 0.2504,
|
| 547 |
+
"step": 9750
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 15.93,
|
| 551 |
+
"eval_loss": 0.6424481272697449,
|
| 552 |
+
"eval_runtime": 28.3698,
|
| 553 |
+
"eval_samples_per_second": 50.3,
|
| 554 |
+
"eval_steps_per_second": 3.172,
|
| 555 |
+
"step": 9750
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 16.34,
|
| 559 |
+
"learning_rate": 5.779153766769866e-06,
|
| 560 |
+
"loss": 0.2437,
|
| 561 |
+
"step": 10000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 16.34,
|
| 565 |
+
"eval_loss": 0.6423542499542236,
|
| 566 |
+
"eval_runtime": 28.3599,
|
| 567 |
+
"eval_samples_per_second": 50.318,
|
| 568 |
+
"eval_steps_per_second": 3.173,
|
| 569 |
+
"step": 10000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 16.75,
|
| 573 |
+
"learning_rate": 5.134158926728587e-06,
|
| 574 |
+
"loss": 0.2399,
|
| 575 |
+
"step": 10250
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 16.75,
|
| 579 |
+
"eval_loss": 0.645331621170044,
|
| 580 |
+
"eval_runtime": 28.3144,
|
| 581 |
+
"eval_samples_per_second": 50.398,
|
| 582 |
+
"eval_steps_per_second": 3.179,
|
| 583 |
+
"step": 10250
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 17.16,
|
| 587 |
+
"learning_rate": 4.489164086687306e-06,
|
| 588 |
+
"loss": 0.238,
|
| 589 |
+
"step": 10500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 17.16,
|
| 593 |
+
"eval_loss": 0.6478310227394104,
|
| 594 |
+
"eval_runtime": 28.3979,
|
| 595 |
+
"eval_samples_per_second": 50.25,
|
| 596 |
+
"eval_steps_per_second": 3.169,
|
| 597 |
+
"step": 10500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 17.57,
|
| 601 |
+
"learning_rate": 3.844169246646027e-06,
|
| 602 |
+
"loss": 0.2359,
|
| 603 |
+
"step": 10750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 17.57,
|
| 607 |
+
"eval_loss": 0.6469157934188843,
|
| 608 |
+
"eval_runtime": 28.3531,
|
| 609 |
+
"eval_samples_per_second": 50.33,
|
| 610 |
+
"eval_steps_per_second": 3.174,
|
| 611 |
+
"step": 10750
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 17.97,
|
| 615 |
+
"learning_rate": 3.1991744066047476e-06,
|
| 616 |
+
"loss": 0.2325,
|
| 617 |
+
"step": 11000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 17.97,
|
| 621 |
+
"eval_loss": 0.6457414031028748,
|
| 622 |
+
"eval_runtime": 28.3364,
|
| 623 |
+
"eval_samples_per_second": 50.359,
|
| 624 |
+
"eval_steps_per_second": 3.176,
|
| 625 |
+
"step": 11000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 18.38,
|
| 629 |
+
"learning_rate": 2.5541795665634673e-06,
|
| 630 |
+
"loss": 0.2294,
|
| 631 |
+
"step": 11250
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 18.38,
|
| 635 |
+
"eval_loss": 0.6480973958969116,
|
| 636 |
+
"eval_runtime": 28.308,
|
| 637 |
+
"eval_samples_per_second": 50.41,
|
| 638 |
+
"eval_steps_per_second": 3.179,
|
| 639 |
+
"step": 11250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 18.79,
|
| 643 |
+
"learning_rate": 1.909184726522188e-06,
|
| 644 |
+
"loss": 0.2306,
|
| 645 |
+
"step": 11500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 18.79,
|
| 649 |
+
"eval_loss": 0.6470589637756348,
|
| 650 |
+
"eval_runtime": 28.2173,
|
| 651 |
+
"eval_samples_per_second": 50.572,
|
| 652 |
+
"eval_steps_per_second": 3.19,
|
| 653 |
+
"step": 11500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 19.2,
|
| 657 |
+
"learning_rate": 1.264189886480908e-06,
|
| 658 |
+
"loss": 0.2289,
|
| 659 |
+
"step": 11750
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 19.2,
|
| 663 |
+
"eval_loss": 0.6486860513687134,
|
| 664 |
+
"eval_runtime": 28.2611,
|
| 665 |
+
"eval_samples_per_second": 50.493,
|
| 666 |
+
"eval_steps_per_second": 3.185,
|
| 667 |
+
"step": 11750
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 19.61,
|
| 671 |
+
"learning_rate": 6.191950464396285e-07,
|
| 672 |
+
"loss": 0.2269,
|
| 673 |
+
"step": 12000
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 19.61,
|
| 677 |
+
"eval_loss": 0.6482470631599426,
|
| 678 |
+
"eval_runtime": 28.2376,
|
| 679 |
+
"eval_samples_per_second": 50.535,
|
| 680 |
+
"eval_steps_per_second": 3.187,
|
| 681 |
+
"step": 12000
|
| 682 |
+
}
|
| 683 |
+
],
|
| 684 |
+
"logging_steps": 250,
|
| 685 |
+
"max_steps": 12240,
|
| 686 |
+
"num_train_epochs": 20,
|
| 687 |
+
"save_steps": 250,
|
| 688 |
+
"total_flos": 5.845452187030733e+16,
|
| 689 |
+
"trial_name": null,
|
| 690 |
+
"trial_params": null
|
| 691 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9a2e11aefc1696027cb71da827188314ba220a15006c4d9af3e59d56edd83f
|
| 3 |
+
size 4155
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|