Commit
•
fcaaddc
1
Parent(s):
09f867b
adding model finetuned on XNLI
Browse files- all_results.json +14 -0
- config.json +46 -0
- eval_results.json +9 -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 +829 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.8373493975903614,
|
| 4 |
+
"eval_loss": 0.4270777404308319,
|
| 5 |
+
"eval_runtime": 84.2227,
|
| 6 |
+
"eval_samples": 2490,
|
| 7 |
+
"eval_samples_per_second": 29.564,
|
| 8 |
+
"eval_steps_per_second": 3.704,
|
| 9 |
+
"train_loss": 0.4176930578855368,
|
| 10 |
+
"train_runtime": 61258.2129,
|
| 11 |
+
"train_samples": 392702,
|
| 12 |
+
"train_samples_per_second": 12.821,
|
| 13 |
+
"train_steps_per_second": 0.801
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CenIA/albert_xxlarge_spanish",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForSequenceClassification"
|
| 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 |
+
"finetuning_task": "xnli",
|
| 13 |
+
"gap_size": 0,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0,
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "LABEL_0",
|
| 19 |
+
"1": "LABEL_1",
|
| 20 |
+
"2": "LABEL_2"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.01,
|
| 23 |
+
"inner_group_num": 1,
|
| 24 |
+
"intermediate_size": 16384,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"layers_to_keep": [],
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "albert",
|
| 34 |
+
"net_structure_type": 0,
|
| 35 |
+
"num_attention_heads": 64,
|
| 36 |
+
"num_hidden_groups": 1,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"num_memory_blocks": 0,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.12.5",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"vocab_size": 31000
|
| 46 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.8373493975903614,
|
| 4 |
+
"eval_loss": 0.4270777404308319,
|
| 5 |
+
"eval_runtime": 84.2227,
|
| 6 |
+
"eval_samples": 2490,
|
| 7 |
+
"eval_samples_per_second": 29.564,
|
| 8 |
+
"eval_steps_per_second": 3.704
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:904a8f1f77806f954ce5d9af7d0c87e4e983023553deeb2421b51546abfb2efb
|
| 3 |
+
size 890958545
|
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_xxlarge_spanish", "tokenizer_class": "AlbertTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.4176930578855368,
|
| 4 |
+
"train_runtime": 61258.2129,
|
| 5 |
+
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 12.821,
|
| 7 |
+
"train_steps_per_second": 0.801
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,829 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4270777404308319,
|
| 3 |
+
"best_model_checkpoint": "/data/jcanete/all_results/xnli/albeto_xxlarge/epochs_2_bs_16_lr_5e-6/checkpoint-22000",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 49088,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.9493766297262065e-06,
|
| 13 |
+
"loss": 0.8888,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 4.898549543676663e-06,
|
| 19 |
+
"loss": 0.7298,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 4.847620599739244e-06,
|
| 25 |
+
"loss": 0.6804,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 4.796691655801826e-06,
|
| 31 |
+
"loss": 0.6317,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"eval_accuracy": 0.7558232931726908,
|
| 37 |
+
"eval_loss": 0.598174512386322,
|
| 38 |
+
"eval_runtime": 84.2575,
|
| 39 |
+
"eval_samples_per_second": 29.552,
|
| 40 |
+
"eval_steps_per_second": 3.703,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1,
|
| 45 |
+
"learning_rate": 4.745762711864408e-06,
|
| 46 |
+
"loss": 0.6141,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.12,
|
| 51 |
+
"learning_rate": 4.694833767926988e-06,
|
| 52 |
+
"loss": 0.5958,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 4.644006681877445e-06,
|
| 58 |
+
"loss": 0.5947,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16,
|
| 63 |
+
"learning_rate": 4.593179595827901e-06,
|
| 64 |
+
"loss": 0.5644,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16,
|
| 69 |
+
"eval_accuracy": 0.7831325301204819,
|
| 70 |
+
"eval_loss": 0.5494194626808167,
|
| 71 |
+
"eval_runtime": 84.263,
|
| 72 |
+
"eval_samples_per_second": 29.55,
|
| 73 |
+
"eval_steps_per_second": 3.703,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.18,
|
| 78 |
+
"learning_rate": 4.5423525097783575e-06,
|
| 79 |
+
"loss": 0.5719,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2,
|
| 84 |
+
"learning_rate": 4.491423565840939e-06,
|
| 85 |
+
"loss": 0.5633,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22,
|
| 90 |
+
"learning_rate": 4.440494621903521e-06,
|
| 91 |
+
"loss": 0.5673,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.24,
|
| 96 |
+
"learning_rate": 4.389565677966102e-06,
|
| 97 |
+
"loss": 0.5429,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.24,
|
| 102 |
+
"eval_accuracy": 0.7959839357429719,
|
| 103 |
+
"eval_loss": 0.527809202671051,
|
| 104 |
+
"eval_runtime": 84.2589,
|
| 105 |
+
"eval_samples_per_second": 29.552,
|
| 106 |
+
"eval_steps_per_second": 3.703,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26,
|
| 111 |
+
"learning_rate": 4.338636734028683e-06,
|
| 112 |
+
"loss": 0.5402,
|
| 113 |
+
"step": 6500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.29,
|
| 117 |
+
"learning_rate": 4.287707790091265e-06,
|
| 118 |
+
"loss": 0.5457,
|
| 119 |
+
"step": 7000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.31,
|
| 123 |
+
"learning_rate": 4.236778846153847e-06,
|
| 124 |
+
"loss": 0.5426,
|
| 125 |
+
"step": 7500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.33,
|
| 129 |
+
"learning_rate": 4.185849902216428e-06,
|
| 130 |
+
"loss": 0.5279,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.33,
|
| 135 |
+
"eval_accuracy": 0.7991967871485943,
|
| 136 |
+
"eval_loss": 0.5055843591690063,
|
| 137 |
+
"eval_runtime": 84.2703,
|
| 138 |
+
"eval_samples_per_second": 29.548,
|
| 139 |
+
"eval_steps_per_second": 3.702,
|
| 140 |
+
"step": 8000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.35,
|
| 144 |
+
"learning_rate": 4.134920958279009e-06,
|
| 145 |
+
"loss": 0.5204,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.37,
|
| 150 |
+
"learning_rate": 4.0841957301173405e-06,
|
| 151 |
+
"loss": 0.5139,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.39,
|
| 156 |
+
"learning_rate": 4.033266786179922e-06,
|
| 157 |
+
"loss": 0.5189,
|
| 158 |
+
"step": 9500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.41,
|
| 162 |
+
"learning_rate": 3.982337842242504e-06,
|
| 163 |
+
"loss": 0.5149,
|
| 164 |
+
"step": 10000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.41,
|
| 168 |
+
"eval_accuracy": 0.814859437751004,
|
| 169 |
+
"eval_loss": 0.4850701093673706,
|
| 170 |
+
"eval_runtime": 84.292,
|
| 171 |
+
"eval_samples_per_second": 29.54,
|
| 172 |
+
"eval_steps_per_second": 3.701,
|
| 173 |
+
"step": 10000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.43,
|
| 177 |
+
"learning_rate": 3.931408898305085e-06,
|
| 178 |
+
"loss": 0.5143,
|
| 179 |
+
"step": 10500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.45,
|
| 183 |
+
"learning_rate": 3.880479954367666e-06,
|
| 184 |
+
"loss": 0.5011,
|
| 185 |
+
"step": 11000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.47,
|
| 189 |
+
"learning_rate": 3.829551010430248e-06,
|
| 190 |
+
"loss": 0.5051,
|
| 191 |
+
"step": 11500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.49,
|
| 195 |
+
"learning_rate": 3.7786220664928295e-06,
|
| 196 |
+
"loss": 0.4991,
|
| 197 |
+
"step": 12000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.49,
|
| 201 |
+
"eval_accuracy": 0.8116465863453816,
|
| 202 |
+
"eval_loss": 0.4848240613937378,
|
| 203 |
+
"eval_runtime": 84.2552,
|
| 204 |
+
"eval_samples_per_second": 29.553,
|
| 205 |
+
"eval_steps_per_second": 3.703,
|
| 206 |
+
"step": 12000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.51,
|
| 210 |
+
"learning_rate": 3.7276931225554107e-06,
|
| 211 |
+
"loss": 0.4942,
|
| 212 |
+
"step": 12500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.53,
|
| 216 |
+
"learning_rate": 3.676866036505867e-06,
|
| 217 |
+
"loss": 0.515,
|
| 218 |
+
"step": 13000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.55,
|
| 222 |
+
"learning_rate": 3.625937092568449e-06,
|
| 223 |
+
"loss": 0.5015,
|
| 224 |
+
"step": 13500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.57,
|
| 228 |
+
"learning_rate": 3.5750081486310302e-06,
|
| 229 |
+
"loss": 0.4943,
|
| 230 |
+
"step": 14000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.57,
|
| 234 |
+
"eval_accuracy": 0.8232931726907631,
|
| 235 |
+
"eval_loss": 0.4758189022541046,
|
| 236 |
+
"eval_runtime": 84.249,
|
| 237 |
+
"eval_samples_per_second": 29.555,
|
| 238 |
+
"eval_steps_per_second": 3.703,
|
| 239 |
+
"step": 14000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.59,
|
| 243 |
+
"learning_rate": 3.5240792046936118e-06,
|
| 244 |
+
"loss": 0.4901,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.61,
|
| 249 |
+
"learning_rate": 3.4731502607561934e-06,
|
| 250 |
+
"loss": 0.5031,
|
| 251 |
+
"step": 15000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.63,
|
| 255 |
+
"learning_rate": 3.4222213168187745e-06,
|
| 256 |
+
"loss": 0.4825,
|
| 257 |
+
"step": 15500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.65,
|
| 261 |
+
"learning_rate": 3.371292372881356e-06,
|
| 262 |
+
"loss": 0.4925,
|
| 263 |
+
"step": 16000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.65,
|
| 267 |
+
"eval_accuracy": 0.8240963855421687,
|
| 268 |
+
"eval_loss": 0.45331594347953796,
|
| 269 |
+
"eval_runtime": 84.2469,
|
| 270 |
+
"eval_samples_per_second": 29.556,
|
| 271 |
+
"eval_steps_per_second": 3.703,
|
| 272 |
+
"step": 16000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.67,
|
| 276 |
+
"learning_rate": 3.320363428943938e-06,
|
| 277 |
+
"loss": 0.4896,
|
| 278 |
+
"step": 16500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.69,
|
| 282 |
+
"learning_rate": 3.2695363428943936e-06,
|
| 283 |
+
"loss": 0.4854,
|
| 284 |
+
"step": 17000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.71,
|
| 288 |
+
"learning_rate": 3.2189129726205997e-06,
|
| 289 |
+
"loss": 0.4973,
|
| 290 |
+
"step": 17500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.73,
|
| 294 |
+
"learning_rate": 3.1679840286831813e-06,
|
| 295 |
+
"loss": 0.4695,
|
| 296 |
+
"step": 18000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.73,
|
| 300 |
+
"eval_accuracy": 0.821285140562249,
|
| 301 |
+
"eval_loss": 0.4604874551296234,
|
| 302 |
+
"eval_runtime": 84.2777,
|
| 303 |
+
"eval_samples_per_second": 29.545,
|
| 304 |
+
"eval_steps_per_second": 3.702,
|
| 305 |
+
"step": 18000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.75,
|
| 309 |
+
"learning_rate": 3.1170550847457633e-06,
|
| 310 |
+
"loss": 0.4713,
|
| 311 |
+
"step": 18500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.77,
|
| 315 |
+
"learning_rate": 3.0661261408083444e-06,
|
| 316 |
+
"loss": 0.4788,
|
| 317 |
+
"step": 19000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.79,
|
| 321 |
+
"learning_rate": 3.015197196870926e-06,
|
| 322 |
+
"loss": 0.4718,
|
| 323 |
+
"step": 19500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.81,
|
| 327 |
+
"learning_rate": 2.9642682529335076e-06,
|
| 328 |
+
"loss": 0.469,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.81,
|
| 333 |
+
"eval_accuracy": 0.8244979919678714,
|
| 334 |
+
"eval_loss": 0.44962260127067566,
|
| 335 |
+
"eval_runtime": 84.2647,
|
| 336 |
+
"eval_samples_per_second": 29.55,
|
| 337 |
+
"eval_steps_per_second": 3.703,
|
| 338 |
+
"step": 20000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.84,
|
| 342 |
+
"learning_rate": 2.9133393089960887e-06,
|
| 343 |
+
"loss": 0.4782,
|
| 344 |
+
"step": 20500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.86,
|
| 348 |
+
"learning_rate": 2.8624103650586703e-06,
|
| 349 |
+
"loss": 0.4783,
|
| 350 |
+
"step": 21000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.88,
|
| 354 |
+
"learning_rate": 2.8114814211212523e-06,
|
| 355 |
+
"loss": 0.4619,
|
| 356 |
+
"step": 21500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.9,
|
| 360 |
+
"learning_rate": 2.7605524771838334e-06,
|
| 361 |
+
"loss": 0.4671,
|
| 362 |
+
"step": 22000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.9,
|
| 366 |
+
"eval_accuracy": 0.8373493975903614,
|
| 367 |
+
"eval_loss": 0.4270777404308319,
|
| 368 |
+
"eval_runtime": 84.2512,
|
| 369 |
+
"eval_samples_per_second": 29.554,
|
| 370 |
+
"eval_steps_per_second": 3.703,
|
| 371 |
+
"step": 22000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.92,
|
| 375 |
+
"learning_rate": 2.709623533246415e-06,
|
| 376 |
+
"loss": 0.4665,
|
| 377 |
+
"step": 22500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.94,
|
| 381 |
+
"learning_rate": 2.658694589308996e-06,
|
| 382 |
+
"loss": 0.4703,
|
| 383 |
+
"step": 23000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.96,
|
| 387 |
+
"learning_rate": 2.6077656453715777e-06,
|
| 388 |
+
"loss": 0.4559,
|
| 389 |
+
"step": 23500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.98,
|
| 393 |
+
"learning_rate": 2.5568367014341593e-06,
|
| 394 |
+
"loss": 0.4709,
|
| 395 |
+
"step": 24000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.98,
|
| 399 |
+
"eval_accuracy": 0.8337349397590361,
|
| 400 |
+
"eval_loss": 0.436306357383728,
|
| 401 |
+
"eval_runtime": 84.2829,
|
| 402 |
+
"eval_samples_per_second": 29.543,
|
| 403 |
+
"eval_steps_per_second": 3.702,
|
| 404 |
+
"step": 24000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.0,
|
| 408 |
+
"learning_rate": 2.5059077574967404e-06,
|
| 409 |
+
"loss": 0.4581,
|
| 410 |
+
"step": 24500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.02,
|
| 414 |
+
"learning_rate": 2.454978813559322e-06,
|
| 415 |
+
"loss": 0.3387,
|
| 416 |
+
"step": 25000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.04,
|
| 420 |
+
"learning_rate": 2.4040498696219036e-06,
|
| 421 |
+
"loss": 0.3281,
|
| 422 |
+
"step": 25500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.06,
|
| 426 |
+
"learning_rate": 2.353120925684485e-06,
|
| 427 |
+
"loss": 0.3167,
|
| 428 |
+
"step": 26000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.06,
|
| 432 |
+
"eval_accuracy": 0.8289156626506025,
|
| 433 |
+
"eval_loss": 0.47485458850860596,
|
| 434 |
+
"eval_runtime": 84.2522,
|
| 435 |
+
"eval_samples_per_second": 29.554,
|
| 436 |
+
"eval_steps_per_second": 3.703,
|
| 437 |
+
"step": 26000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.08,
|
| 441 |
+
"learning_rate": 2.3021919817470667e-06,
|
| 442 |
+
"loss": 0.3267,
|
| 443 |
+
"step": 26500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.1,
|
| 447 |
+
"learning_rate": 2.2512630378096483e-06,
|
| 448 |
+
"loss": 0.3058,
|
| 449 |
+
"step": 27000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.12,
|
| 453 |
+
"learning_rate": 2.2003340938722295e-06,
|
| 454 |
+
"loss": 0.3249,
|
| 455 |
+
"step": 27500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.14,
|
| 459 |
+
"learning_rate": 2.149405149934811e-06,
|
| 460 |
+
"loss": 0.3214,
|
| 461 |
+
"step": 28000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.14,
|
| 465 |
+
"eval_accuracy": 0.8325301204819278,
|
| 466 |
+
"eval_loss": 0.47795429825782776,
|
| 467 |
+
"eval_runtime": 84.2738,
|
| 468 |
+
"eval_samples_per_second": 29.547,
|
| 469 |
+
"eval_steps_per_second": 3.702,
|
| 470 |
+
"step": 28000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.16,
|
| 474 |
+
"learning_rate": 2.0985780638852674e-06,
|
| 475 |
+
"loss": 0.3289,
|
| 476 |
+
"step": 28500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.18,
|
| 480 |
+
"learning_rate": 2.047649119947849e-06,
|
| 481 |
+
"loss": 0.3176,
|
| 482 |
+
"step": 29000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.2,
|
| 486 |
+
"learning_rate": 1.9967201760104306e-06,
|
| 487 |
+
"loss": 0.3292,
|
| 488 |
+
"step": 29500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.22,
|
| 492 |
+
"learning_rate": 1.9457912320730117e-06,
|
| 493 |
+
"loss": 0.326,
|
| 494 |
+
"step": 30000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.22,
|
| 498 |
+
"eval_accuracy": 0.8309236947791164,
|
| 499 |
+
"eval_loss": 0.46767711639404297,
|
| 500 |
+
"eval_runtime": 84.2707,
|
| 501 |
+
"eval_samples_per_second": 29.548,
|
| 502 |
+
"eval_steps_per_second": 3.702,
|
| 503 |
+
"step": 30000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.24,
|
| 507 |
+
"learning_rate": 1.8948622881355933e-06,
|
| 508 |
+
"loss": 0.3164,
|
| 509 |
+
"step": 30500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.26,
|
| 513 |
+
"learning_rate": 1.8439333441981749e-06,
|
| 514 |
+
"loss": 0.3151,
|
| 515 |
+
"step": 31000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.28,
|
| 519 |
+
"learning_rate": 1.7930044002607562e-06,
|
| 520 |
+
"loss": 0.3196,
|
| 521 |
+
"step": 31500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.3,
|
| 525 |
+
"learning_rate": 1.7420754563233378e-06,
|
| 526 |
+
"loss": 0.3192,
|
| 527 |
+
"step": 32000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.3,
|
| 531 |
+
"eval_accuracy": 0.8353413654618473,
|
| 532 |
+
"eval_loss": 0.4579215347766876,
|
| 533 |
+
"eval_runtime": 84.2732,
|
| 534 |
+
"eval_samples_per_second": 29.547,
|
| 535 |
+
"eval_steps_per_second": 3.702,
|
| 536 |
+
"step": 32000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.32,
|
| 540 |
+
"learning_rate": 1.6911465123859194e-06,
|
| 541 |
+
"loss": 0.3148,
|
| 542 |
+
"step": 32500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.34,
|
| 546 |
+
"learning_rate": 1.6402175684485007e-06,
|
| 547 |
+
"loss": 0.3126,
|
| 548 |
+
"step": 33000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.36,
|
| 552 |
+
"learning_rate": 1.5892886245110823e-06,
|
| 553 |
+
"loss": 0.3106,
|
| 554 |
+
"step": 33500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.39,
|
| 558 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 559 |
+
"loss": 0.3239,
|
| 560 |
+
"step": 34000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.39,
|
| 564 |
+
"eval_accuracy": 0.8333333333333334,
|
| 565 |
+
"eval_loss": 0.4818671643733978,
|
| 566 |
+
"eval_runtime": 84.2403,
|
| 567 |
+
"eval_samples_per_second": 29.558,
|
| 568 |
+
"eval_steps_per_second": 3.704,
|
| 569 |
+
"step": 34000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.41,
|
| 573 |
+
"learning_rate": 1.48753259452412e-06,
|
| 574 |
+
"loss": 0.3131,
|
| 575 |
+
"step": 34500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.43,
|
| 579 |
+
"learning_rate": 1.4366036505867014e-06,
|
| 580 |
+
"loss": 0.3057,
|
| 581 |
+
"step": 35000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.45,
|
| 585 |
+
"learning_rate": 1.3856747066492832e-06,
|
| 586 |
+
"loss": 0.3032,
|
| 587 |
+
"step": 35500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.47,
|
| 591 |
+
"learning_rate": 1.3347457627118646e-06,
|
| 592 |
+
"loss": 0.3026,
|
| 593 |
+
"step": 36000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.47,
|
| 597 |
+
"eval_accuracy": 0.8389558232931726,
|
| 598 |
+
"eval_loss": 0.47428080439567566,
|
| 599 |
+
"eval_runtime": 84.2812,
|
| 600 |
+
"eval_samples_per_second": 29.544,
|
| 601 |
+
"eval_steps_per_second": 3.702,
|
| 602 |
+
"step": 36000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.49,
|
| 606 |
+
"learning_rate": 1.2839186766623208e-06,
|
| 607 |
+
"loss": 0.3007,
|
| 608 |
+
"step": 36500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.51,
|
| 612 |
+
"learning_rate": 1.2329897327249023e-06,
|
| 613 |
+
"loss": 0.3148,
|
| 614 |
+
"step": 37000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.53,
|
| 618 |
+
"learning_rate": 1.1820607887874837e-06,
|
| 619 |
+
"loss": 0.299,
|
| 620 |
+
"step": 37500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.55,
|
| 624 |
+
"learning_rate": 1.1311318448500653e-06,
|
| 625 |
+
"loss": 0.3176,
|
| 626 |
+
"step": 38000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.55,
|
| 630 |
+
"eval_accuracy": 0.8437751004016064,
|
| 631 |
+
"eval_loss": 0.46083542704582214,
|
| 632 |
+
"eval_runtime": 84.2921,
|
| 633 |
+
"eval_samples_per_second": 29.54,
|
| 634 |
+
"eval_steps_per_second": 3.701,
|
| 635 |
+
"step": 38000
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.57,
|
| 639 |
+
"learning_rate": 1.0803047588005217e-06,
|
| 640 |
+
"loss": 0.3099,
|
| 641 |
+
"step": 38500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.59,
|
| 645 |
+
"learning_rate": 1.029375814863103e-06,
|
| 646 |
+
"loss": 0.2976,
|
| 647 |
+
"step": 39000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.61,
|
| 651 |
+
"learning_rate": 9.785487288135595e-07,
|
| 652 |
+
"loss": 0.2978,
|
| 653 |
+
"step": 39500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.63,
|
| 657 |
+
"learning_rate": 9.276197848761409e-07,
|
| 658 |
+
"loss": 0.309,
|
| 659 |
+
"step": 40000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.63,
|
| 663 |
+
"eval_accuracy": 0.8409638554216867,
|
| 664 |
+
"eval_loss": 0.46184200048446655,
|
| 665 |
+
"eval_runtime": 84.2612,
|
| 666 |
+
"eval_samples_per_second": 29.551,
|
| 667 |
+
"eval_steps_per_second": 3.703,
|
| 668 |
+
"step": 40000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.65,
|
| 672 |
+
"learning_rate": 8.766908409387223e-07,
|
| 673 |
+
"loss": 0.2989,
|
| 674 |
+
"step": 40500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.67,
|
| 678 |
+
"learning_rate": 8.257618970013039e-07,
|
| 679 |
+
"loss": 0.309,
|
| 680 |
+
"step": 41000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.69,
|
| 684 |
+
"learning_rate": 7.749348109517601e-07,
|
| 685 |
+
"loss": 0.3016,
|
| 686 |
+
"step": 41500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.71,
|
| 690 |
+
"learning_rate": 7.240058670143417e-07,
|
| 691 |
+
"loss": 0.2999,
|
| 692 |
+
"step": 42000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.71,
|
| 696 |
+
"eval_accuracy": 0.838152610441767,
|
| 697 |
+
"eval_loss": 0.4617726802825928,
|
| 698 |
+
"eval_runtime": 84.2688,
|
| 699 |
+
"eval_samples_per_second": 29.548,
|
| 700 |
+
"eval_steps_per_second": 3.702,
|
| 701 |
+
"step": 42000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.73,
|
| 705 |
+
"learning_rate": 6.730769230769231e-07,
|
| 706 |
+
"loss": 0.3081,
|
| 707 |
+
"step": 42500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.75,
|
| 711 |
+
"learning_rate": 6.221479791395047e-07,
|
| 712 |
+
"loss": 0.3019,
|
| 713 |
+
"step": 43000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.77,
|
| 717 |
+
"learning_rate": 5.712190352020861e-07,
|
| 718 |
+
"loss": 0.3049,
|
| 719 |
+
"step": 43500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.79,
|
| 723 |
+
"learning_rate": 5.202900912646676e-07,
|
| 724 |
+
"loss": 0.2941,
|
| 725 |
+
"step": 44000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.79,
|
| 729 |
+
"eval_accuracy": 0.8449799196787149,
|
| 730 |
+
"eval_loss": 0.4609120190143585,
|
| 731 |
+
"eval_runtime": 84.2453,
|
| 732 |
+
"eval_samples_per_second": 29.557,
|
| 733 |
+
"eval_steps_per_second": 3.703,
|
| 734 |
+
"step": 44000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.81,
|
| 738 |
+
"learning_rate": 4.6936114732724906e-07,
|
| 739 |
+
"loss": 0.3002,
|
| 740 |
+
"step": 44500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.83,
|
| 744 |
+
"learning_rate": 4.184322033898305e-07,
|
| 745 |
+
"loss": 0.3008,
|
| 746 |
+
"step": 45000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.85,
|
| 750 |
+
"learning_rate": 3.676051173402868e-07,
|
| 751 |
+
"loss": 0.296,
|
| 752 |
+
"step": 45500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.87,
|
| 756 |
+
"learning_rate": 3.166761734028683e-07,
|
| 757 |
+
"loss": 0.2946,
|
| 758 |
+
"step": 46000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.87,
|
| 762 |
+
"eval_accuracy": 0.8461847389558232,
|
| 763 |
+
"eval_loss": 0.460882306098938,
|
| 764 |
+
"eval_runtime": 84.2508,
|
| 765 |
+
"eval_samples_per_second": 29.555,
|
| 766 |
+
"eval_steps_per_second": 3.703,
|
| 767 |
+
"step": 46000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.89,
|
| 771 |
+
"learning_rate": 2.657472294654498e-07,
|
| 772 |
+
"loss": 0.2888,
|
| 773 |
+
"step": 46500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.91,
|
| 777 |
+
"learning_rate": 2.1492014341590616e-07,
|
| 778 |
+
"loss": 0.2907,
|
| 779 |
+
"step": 47000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.94,
|
| 783 |
+
"learning_rate": 1.6399119947848762e-07,
|
| 784 |
+
"loss": 0.3067,
|
| 785 |
+
"step": 47500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.96,
|
| 789 |
+
"learning_rate": 1.130622555410691e-07,
|
| 790 |
+
"loss": 0.2757,
|
| 791 |
+
"step": 48000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.96,
|
| 795 |
+
"eval_accuracy": 0.8437751004016064,
|
| 796 |
+
"eval_loss": 0.4675902724266052,
|
| 797 |
+
"eval_runtime": 84.2793,
|
| 798 |
+
"eval_samples_per_second": 29.545,
|
| 799 |
+
"eval_steps_per_second": 3.702,
|
| 800 |
+
"step": 48000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.98,
|
| 804 |
+
"learning_rate": 6.21333116036506e-08,
|
| 805 |
+
"loss": 0.3026,
|
| 806 |
+
"step": 48500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.0,
|
| 810 |
+
"learning_rate": 1.1204367666232074e-08,
|
| 811 |
+
"loss": 0.309,
|
| 812 |
+
"step": 49000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.0,
|
| 816 |
+
"step": 49088,
|
| 817 |
+
"total_flos": 7.899132922600589e+16,
|
| 818 |
+
"train_loss": 0.4176930578855368,
|
| 819 |
+
"train_runtime": 61258.2129,
|
| 820 |
+
"train_samples_per_second": 12.821,
|
| 821 |
+
"train_steps_per_second": 0.801
|
| 822 |
+
}
|
| 823 |
+
],
|
| 824 |
+
"max_steps": 49088,
|
| 825 |
+
"num_train_epochs": 2,
|
| 826 |
+
"total_flos": 7.899132922600589e+16,
|
| 827 |
+
"trial_name": null,
|
| 828 |
+
"trial_params": null
|
| 829 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a79acf2485e45bd1219ddff62f832ad060bbcb4e5a42ee77fdad624799b64b39
|
| 3 |
+
size 2863
|