Commit
•
5d22d0c
1
Parent(s):
24e43a4
adding model finetuned on QA (TAR)
Browse files- .gitattributes +1 -0
- all_results.json +11 -0
- config.json +33 -0
- eval_nbest_predictions.json +3 -0
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +721 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_exact_match": 48.33491012298959,
|
| 4 |
+
"eval_f1": 66.26645652732091,
|
| 5 |
+
"eval_samples": 10624,
|
| 6 |
+
"train_loss": 1.5832800059288115,
|
| 7 |
+
"train_runtime": 4642.7737,
|
| 8 |
+
"train_samples": 87747,
|
| 9 |
+
"train_samples_per_second": 75.599,
|
| 10 |
+
"train_steps_per_second": 4.726
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CenIA/albert_tiny_spanish",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 312,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"inner_group_num": 1,
|
| 18 |
+
"intermediate_size": 1248,
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "albert",
|
| 22 |
+
"net_structure_type": 0,
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_groups": 1,
|
| 25 |
+
"num_hidden_layers": 4,
|
| 26 |
+
"num_memory_blocks": 0,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.15.0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"vocab_size": 31000
|
| 33 |
+
}
|
eval_nbest_predictions.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44fc814520bf527058d9b3242f2ba9452822b7af130cd1d01a257caa73aa4d86
|
| 3 |
+
size 45642296
|
eval_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_exact_match": 48.33491012298959,
|
| 4 |
+
"eval_f1": 66.26645652732091,
|
| 5 |
+
"eval_samples": 10624
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78e5f4d5d65979fda9fbf3f567f6c704a322b10d53e30b3e8bb698200fc3b72d
|
| 3 |
+
size 21002519
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/albert_tiny_spanish", "tokenizer_class": "AlbertTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 1.5832800059288115,
|
| 4 |
+
"train_runtime": 4642.7737,
|
| 5 |
+
"train_samples": 87747,
|
| 6 |
+
"train_samples_per_second": 75.599,
|
| 7 |
+
"train_steps_per_second": 4.726
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 66.26645652732091,
|
| 3 |
+
"best_model_checkpoint": "/data/jcanete/all_results/tar/albeto_tiny/epochs_4_bs_16_lr_5e-5/checkpoint-10800",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 21940,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"eval_exact_match": 25.279091769157993,
|
| 13 |
+
"eval_f1": 41.71460503665182,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.8867365542388335e-05,
|
| 19 |
+
"loss": 3.1064,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"eval_exact_match": 33.77483443708609,
|
| 25 |
+
"eval_f1": 51.462032531677195,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"eval_exact_match": 37.78618732261116,
|
| 31 |
+
"eval_f1": 55.147295523401176,
|
| 32 |
+
"step": 900
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 4.7727894257064726e-05,
|
| 37 |
+
"loss": 2.4193,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"eval_exact_match": 39.735099337748345,
|
| 43 |
+
"eval_f1": 57.70943484117446,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 4.6588422971741116e-05,
|
| 49 |
+
"loss": 2.2494,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"eval_exact_match": 40.69063386944182,
|
| 55 |
+
"eval_f1": 58.161449729726456,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"eval_exact_match": 41.72185430463576,
|
| 61 |
+
"eval_f1": 59.240651392335586,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36,
|
| 66 |
+
"learning_rate": 4.544895168641751e-05,
|
| 67 |
+
"loss": 2.1889,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.38,
|
| 72 |
+
"eval_exact_match": 41.627246925260174,
|
| 73 |
+
"eval_f1": 60.05133975647362,
|
| 74 |
+
"step": 2100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"eval_exact_match": 43.33964049195837,
|
| 79 |
+
"eval_f1": 61.334205952553624,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.46,
|
| 84 |
+
"learning_rate": 4.431175934366454e-05,
|
| 85 |
+
"loss": 2.0954,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.49,
|
| 90 |
+
"eval_exact_match": 44.1438032166509,
|
| 91 |
+
"eval_f1": 61.6109819191811,
|
| 92 |
+
"step": 2700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.55,
|
| 96 |
+
"learning_rate": 4.317228805834093e-05,
|
| 97 |
+
"loss": 2.0585,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.55,
|
| 102 |
+
"eval_exact_match": 44.55061494796594,
|
| 103 |
+
"eval_f1": 62.74097437748746,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.6,
|
| 108 |
+
"eval_exact_match": 45.14664143803217,
|
| 109 |
+
"eval_f1": 62.716820973684904,
|
| 110 |
+
"step": 3300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.64,
|
| 114 |
+
"learning_rate": 4.203281677301732e-05,
|
| 115 |
+
"loss": 2.0252,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.66,
|
| 120 |
+
"eval_exact_match": 45.22232734153264,
|
| 121 |
+
"eval_f1": 63.111925308146255,
|
| 122 |
+
"step": 3600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.71,
|
| 126 |
+
"eval_exact_match": 45.13718070009461,
|
| 127 |
+
"eval_f1": 63.12474940531198,
|
| 128 |
+
"step": 3900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"learning_rate": 4.0893345487693714e-05,
|
| 133 |
+
"loss": 1.9861,
|
| 134 |
+
"step": 4000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.77,
|
| 138 |
+
"eval_exact_match": 46.21570482497635,
|
| 139 |
+
"eval_f1": 64.00817566022319,
|
| 140 |
+
"step": 4200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.82,
|
| 144 |
+
"learning_rate": 3.975615314494075e-05,
|
| 145 |
+
"loss": 1.9881,
|
| 146 |
+
"step": 4500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"eval_exact_match": 46.72658467360454,
|
| 151 |
+
"eval_f1": 64.45739871415881,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.88,
|
| 156 |
+
"eval_exact_match": 46.31031220435194,
|
| 157 |
+
"eval_f1": 64.03851598846974,
|
| 158 |
+
"step": 4800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.91,
|
| 162 |
+
"learning_rate": 3.861668185961714e-05,
|
| 163 |
+
"loss": 1.9619,
|
| 164 |
+
"step": 5000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"eval_exact_match": 46.57521286660359,
|
| 169 |
+
"eval_f1": 64.71289725300291,
|
| 170 |
+
"step": 5100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.98,
|
| 174 |
+
"eval_exact_match": 46.80227057710501,
|
| 175 |
+
"eval_f1": 64.89896140882486,
|
| 176 |
+
"step": 5400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0,
|
| 180 |
+
"learning_rate": 3.747721057429353e-05,
|
| 181 |
+
"loss": 1.8961,
|
| 182 |
+
"step": 5500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.04,
|
| 186 |
+
"eval_exact_match": 46.868495742667925,
|
| 187 |
+
"eval_f1": 64.9566553926742,
|
| 188 |
+
"step": 5700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.09,
|
| 192 |
+
"learning_rate": 3.633773928896992e-05,
|
| 193 |
+
"loss": 1.6613,
|
| 194 |
+
"step": 6000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.09,
|
| 198 |
+
"eval_exact_match": 47.05771050141911,
|
| 199 |
+
"eval_f1": 65.16060187033897,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.15,
|
| 204 |
+
"eval_exact_match": 47.010406811731315,
|
| 205 |
+
"eval_f1": 64.63527459887219,
|
| 206 |
+
"step": 6300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.19,
|
| 210 |
+
"learning_rate": 3.520054694621696e-05,
|
| 211 |
+
"loss": 1.6724,
|
| 212 |
+
"step": 6500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"eval_exact_match": 46.44276253547777,
|
| 217 |
+
"eval_f1": 64.6485660215026,
|
| 218 |
+
"step": 6600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.26,
|
| 222 |
+
"eval_exact_match": 47.02932828760643,
|
| 223 |
+
"eval_f1": 65.25056698142618,
|
| 224 |
+
"step": 6900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.28,
|
| 228 |
+
"learning_rate": 3.406107566089335e-05,
|
| 229 |
+
"loss": 1.6622,
|
| 230 |
+
"step": 7000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.31,
|
| 234 |
+
"eval_exact_match": 47.38883632923368,
|
| 235 |
+
"eval_f1": 65.14765281416761,
|
| 236 |
+
"step": 7200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.37,
|
| 240 |
+
"learning_rate": 3.292160437556974e-05,
|
| 241 |
+
"loss": 1.6765,
|
| 242 |
+
"step": 7500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.37,
|
| 246 |
+
"eval_exact_match": 47.52128666035951,
|
| 247 |
+
"eval_f1": 65.23959133286817,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.42,
|
| 252 |
+
"eval_exact_match": 47.24692526017029,
|
| 253 |
+
"eval_f1": 64.89498224105805,
|
| 254 |
+
"step": 7800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.46,
|
| 258 |
+
"learning_rate": 3.178213309024613e-05,
|
| 259 |
+
"loss": 1.6831,
|
| 260 |
+
"step": 8000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.48,
|
| 264 |
+
"eval_exact_match": 47.42667928098392,
|
| 265 |
+
"eval_f1": 65.43419870447086,
|
| 266 |
+
"step": 8100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.53,
|
| 270 |
+
"eval_exact_match": 47.237464522232735,
|
| 271 |
+
"eval_f1": 65.29424940770944,
|
| 272 |
+
"step": 8400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.55,
|
| 276 |
+
"learning_rate": 3.0644940747493164e-05,
|
| 277 |
+
"loss": 1.6652,
|
| 278 |
+
"step": 8500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.59,
|
| 282 |
+
"eval_exact_match": 47.74834437086093,
|
| 283 |
+
"eval_f1": 65.62503101399187,
|
| 284 |
+
"step": 8700
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.64,
|
| 288 |
+
"learning_rate": 2.9505469462169554e-05,
|
| 289 |
+
"loss": 1.6622,
|
| 290 |
+
"step": 9000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.64,
|
| 294 |
+
"eval_exact_match": 48.04162724692526,
|
| 295 |
+
"eval_f1": 66.13531062019833,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7,
|
| 300 |
+
"eval_exact_match": 47.6631977294229,
|
| 301 |
+
"eval_f1": 65.69495765526571,
|
| 302 |
+
"step": 9300
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.73,
|
| 306 |
+
"learning_rate": 2.836599817684594e-05,
|
| 307 |
+
"loss": 1.6282,
|
| 308 |
+
"step": 9500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.75,
|
| 312 |
+
"eval_exact_match": 48.15515610217597,
|
| 313 |
+
"eval_f1": 65.85406198831797,
|
| 314 |
+
"step": 9600
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.8,
|
| 318 |
+
"eval_exact_match": 48.34437086092715,
|
| 319 |
+
"eval_f1": 65.82648855586231,
|
| 320 |
+
"step": 9900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.82,
|
| 324 |
+
"learning_rate": 2.7226526891522335e-05,
|
| 325 |
+
"loss": 1.6311,
|
| 326 |
+
"step": 10000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.86,
|
| 330 |
+
"eval_exact_match": 48.17407757805109,
|
| 331 |
+
"eval_f1": 65.95821129767383,
|
| 332 |
+
"step": 10200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.91,
|
| 336 |
+
"learning_rate": 2.6089334548769374e-05,
|
| 337 |
+
"loss": 1.6879,
|
| 338 |
+
"step": 10500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.91,
|
| 342 |
+
"eval_exact_match": 48.070009460737936,
|
| 343 |
+
"eval_f1": 65.61674709032437,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.97,
|
| 348 |
+
"eval_exact_match": 48.33491012298959,
|
| 349 |
+
"eval_f1": 66.26645652732091,
|
| 350 |
+
"step": 10800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.01,
|
| 354 |
+
"learning_rate": 2.4949863263445765e-05,
|
| 355 |
+
"loss": 1.6127,
|
| 356 |
+
"step": 11000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.02,
|
| 360 |
+
"eval_exact_match": 47.776726584673604,
|
| 361 |
+
"eval_f1": 65.67716714026636,
|
| 362 |
+
"step": 11100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.08,
|
| 366 |
+
"eval_exact_match": 46.97256385998108,
|
| 367 |
+
"eval_f1": 65.35488377881,
|
| 368 |
+
"step": 11400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.1,
|
| 372 |
+
"learning_rate": 2.3810391978122152e-05,
|
| 373 |
+
"loss": 1.3442,
|
| 374 |
+
"step": 11500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.13,
|
| 378 |
+
"eval_exact_match": 47.25638599810785,
|
| 379 |
+
"eval_f1": 65.11588968827414,
|
| 380 |
+
"step": 11700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.19,
|
| 384 |
+
"learning_rate": 2.2670920692798542e-05,
|
| 385 |
+
"loss": 1.3419,
|
| 386 |
+
"step": 12000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.19,
|
| 390 |
+
"eval_exact_match": 47.918637653736994,
|
| 391 |
+
"eval_f1": 65.76384490998669,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.24,
|
| 396 |
+
"eval_exact_match": 47.71996215704825,
|
| 397 |
+
"eval_f1": 65.51523648050365,
|
| 398 |
+
"step": 12300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.28,
|
| 402 |
+
"learning_rate": 2.1533728350045578e-05,
|
| 403 |
+
"loss": 1.3392,
|
| 404 |
+
"step": 12500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.3,
|
| 408 |
+
"eval_exact_match": 47.81456953642384,
|
| 409 |
+
"eval_f1": 65.72328974412012,
|
| 410 |
+
"step": 12600
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.35,
|
| 414 |
+
"eval_exact_match": 46.868495742667925,
|
| 415 |
+
"eval_f1": 64.95043374963731,
|
| 416 |
+
"step": 12900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.37,
|
| 420 |
+
"learning_rate": 2.0396536007292617e-05,
|
| 421 |
+
"loss": 1.3365,
|
| 422 |
+
"step": 13000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.41,
|
| 426 |
+
"eval_exact_match": 47.47398297067171,
|
| 427 |
+
"eval_f1": 65.46687084562042,
|
| 428 |
+
"step": 13200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.46,
|
| 432 |
+
"learning_rate": 1.9257064721969007e-05,
|
| 433 |
+
"loss": 1.3863,
|
| 434 |
+
"step": 13500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.46,
|
| 438 |
+
"eval_exact_match": 47.64427625354778,
|
| 439 |
+
"eval_f1": 65.54344572464974,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.52,
|
| 444 |
+
"eval_exact_match": 47.70104068117313,
|
| 445 |
+
"eval_f1": 65.29014560945414,
|
| 446 |
+
"step": 13800
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.55,
|
| 450 |
+
"learning_rate": 1.8117593436645398e-05,
|
| 451 |
+
"loss": 1.364,
|
| 452 |
+
"step": 14000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.57,
|
| 456 |
+
"eval_exact_match": 47.918637653736994,
|
| 457 |
+
"eval_f1": 65.66170183373373,
|
| 458 |
+
"step": 14100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.63,
|
| 462 |
+
"eval_exact_match": 48.33491012298959,
|
| 463 |
+
"eval_f1": 65.94289128043252,
|
| 464 |
+
"step": 14400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.64,
|
| 468 |
+
"learning_rate": 1.697812215132179e-05,
|
| 469 |
+
"loss": 1.3864,
|
| 470 |
+
"step": 14500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.68,
|
| 474 |
+
"eval_exact_match": 48.24976348155156,
|
| 475 |
+
"eval_f1": 65.78253411845539,
|
| 476 |
+
"step": 14700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.73,
|
| 480 |
+
"learning_rate": 1.583865086599818e-05,
|
| 481 |
+
"loss": 1.3636,
|
| 482 |
+
"step": 15000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.73,
|
| 486 |
+
"eval_exact_match": 48.438978240302745,
|
| 487 |
+
"eval_f1": 66.07660779936401,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.79,
|
| 492 |
+
"eval_exact_match": 48.16461684011353,
|
| 493 |
+
"eval_f1": 66.2498588216324,
|
| 494 |
+
"step": 15300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.83,
|
| 498 |
+
"learning_rate": 1.469917958067457e-05,
|
| 499 |
+
"loss": 1.3726,
|
| 500 |
+
"step": 15500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.84,
|
| 504 |
+
"eval_exact_match": 47.95648060548723,
|
| 505 |
+
"eval_f1": 65.7260651497257,
|
| 506 |
+
"step": 15600
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.9,
|
| 510 |
+
"eval_exact_match": 47.88079470198676,
|
| 511 |
+
"eval_f1": 66.01379305937202,
|
| 512 |
+
"step": 15900
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.92,
|
| 516 |
+
"learning_rate": 1.355970829535096e-05,
|
| 517 |
+
"loss": 1.379,
|
| 518 |
+
"step": 16000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.95,
|
| 522 |
+
"eval_exact_match": 48.240302743614,
|
| 523 |
+
"eval_f1": 65.53479147043561,
|
| 524 |
+
"step": 16200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.01,
|
| 528 |
+
"learning_rate": 1.2422515952597995e-05,
|
| 529 |
+
"loss": 1.3401,
|
| 530 |
+
"step": 16500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.01,
|
| 534 |
+
"eval_exact_match": 48.221381267738884,
|
| 535 |
+
"eval_f1": 65.86023587215384,
|
| 536 |
+
"step": 16500
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.06,
|
| 540 |
+
"eval_exact_match": 47.615894039735096,
|
| 541 |
+
"eval_f1": 65.12853949917962,
|
| 542 |
+
"step": 16800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.1,
|
| 546 |
+
"learning_rate": 1.1283044667274386e-05,
|
| 547 |
+
"loss": 1.1281,
|
| 548 |
+
"step": 17000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.12,
|
| 552 |
+
"eval_exact_match": 47.12393566698202,
|
| 553 |
+
"eval_f1": 65.15991467915553,
|
| 554 |
+
"step": 17100
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.17,
|
| 558 |
+
"eval_exact_match": 47.21854304635762,
|
| 559 |
+
"eval_f1": 65.02752189426162,
|
| 560 |
+
"step": 17400
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.19,
|
| 564 |
+
"learning_rate": 1.0143573381950776e-05,
|
| 565 |
+
"loss": 1.1161,
|
| 566 |
+
"step": 17500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.23,
|
| 570 |
+
"eval_exact_match": 47.13339640491959,
|
| 571 |
+
"eval_f1": 65.2429493800908,
|
| 572 |
+
"step": 17700
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.28,
|
| 576 |
+
"learning_rate": 9.004102096627165e-06,
|
| 577 |
+
"loss": 1.1337,
|
| 578 |
+
"step": 18000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.28,
|
| 582 |
+
"eval_exact_match": 47.010406811731315,
|
| 583 |
+
"eval_f1": 65.03577782296541,
|
| 584 |
+
"step": 18000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.34,
|
| 588 |
+
"eval_exact_match": 47.379375591296125,
|
| 589 |
+
"eval_f1": 65.13654689416043,
|
| 590 |
+
"step": 18300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.37,
|
| 594 |
+
"learning_rate": 7.864630811303556e-06,
|
| 595 |
+
"loss": 1.1477,
|
| 596 |
+
"step": 18500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.39,
|
| 600 |
+
"eval_exact_match": 47.35099337748344,
|
| 601 |
+
"eval_f1": 64.86398318568581,
|
| 602 |
+
"step": 18600
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.45,
|
| 606 |
+
"eval_exact_match": 47.30368968779565,
|
| 607 |
+
"eval_f1": 65.05463221900013,
|
| 608 |
+
"step": 18900
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.46,
|
| 612 |
+
"learning_rate": 6.725159525979946e-06,
|
| 613 |
+
"loss": 1.1414,
|
| 614 |
+
"step": 19000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.5,
|
| 618 |
+
"eval_exact_match": 46.97256385998108,
|
| 619 |
+
"eval_f1": 65.11680930447929,
|
| 620 |
+
"step": 19200
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.56,
|
| 624 |
+
"learning_rate": 5.587967183226983e-06,
|
| 625 |
+
"loss": 1.1454,
|
| 626 |
+
"step": 19500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.56,
|
| 630 |
+
"eval_exact_match": 47.13339640491959,
|
| 631 |
+
"eval_f1": 65.165125839751,
|
| 632 |
+
"step": 19500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.61,
|
| 636 |
+
"eval_exact_match": 47.20908230842006,
|
| 637 |
+
"eval_f1": 65.09005212297234,
|
| 638 |
+
"step": 19800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.65,
|
| 642 |
+
"learning_rate": 4.448495897903373e-06,
|
| 643 |
+
"loss": 1.1318,
|
| 644 |
+
"step": 20000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.66,
|
| 648 |
+
"eval_exact_match": 46.95364238410596,
|
| 649 |
+
"eval_f1": 65.02854138983005,
|
| 650 |
+
"step": 20100
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.72,
|
| 654 |
+
"eval_exact_match": 46.773888363292336,
|
| 655 |
+
"eval_f1": 64.98586781544525,
|
| 656 |
+
"step": 20400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 3.74,
|
| 660 |
+
"learning_rate": 3.3090246125797635e-06,
|
| 661 |
+
"loss": 1.124,
|
| 662 |
+
"step": 20500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 3.77,
|
| 666 |
+
"eval_exact_match": 46.76442762535478,
|
| 667 |
+
"eval_f1": 65.02603195736303,
|
| 668 |
+
"step": 20700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.83,
|
| 672 |
+
"learning_rate": 2.169553327256153e-06,
|
| 673 |
+
"loss": 1.1301,
|
| 674 |
+
"step": 21000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.83,
|
| 678 |
+
"eval_exact_match": 46.88741721854305,
|
| 679 |
+
"eval_f1": 65.03187807653661,
|
| 680 |
+
"step": 21000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.88,
|
| 684 |
+
"eval_exact_match": 47.086092715231786,
|
| 685 |
+
"eval_f1": 65.13748531716237,
|
| 686 |
+
"step": 21300
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 3.92,
|
| 690 |
+
"learning_rate": 1.0323609845031905e-06,
|
| 691 |
+
"loss": 1.1298,
|
| 692 |
+
"step": 21500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.94,
|
| 696 |
+
"eval_exact_match": 47.095553453169344,
|
| 697 |
+
"eval_f1": 65.03629129514118,
|
| 698 |
+
"step": 21600
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.99,
|
| 702 |
+
"eval_exact_match": 47.095553453169344,
|
| 703 |
+
"eval_f1": 65.08861259333764,
|
| 704 |
+
"step": 21900
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 4.0,
|
| 708 |
+
"step": 21940,
|
| 709 |
+
"total_flos": 859515753161088.0,
|
| 710 |
+
"train_loss": 1.5832800059288115,
|
| 711 |
+
"train_runtime": 4642.7737,
|
| 712 |
+
"train_samples_per_second": 75.599,
|
| 713 |
+
"train_steps_per_second": 4.726
|
| 714 |
+
}
|
| 715 |
+
],
|
| 716 |
+
"max_steps": 21940,
|
| 717 |
+
"num_train_epochs": 4,
|
| 718 |
+
"total_flos": 859515753161088.0,
|
| 719 |
+
"trial_name": null,
|
| 720 |
+
"trial_params": null
|
| 721 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:982e4931a79301177c8bf323ef95407c0eedc1337333ab618067287f62a88e26
|
| 3 |
+
size 2991
|