Inital commit.
Browse files- README.md +0 -0
- config.json +32 -0
- data_args.json +16 -0
- eval_metrics.json +4 -0
- evaluate_timing.json +1 -0
- model_args.json +7 -0
- predictions.json +0 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- sparse_args.json +37 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
- trainer_state.json +744 -0
- training_args.bin +3 -0
README.md
ADDED
|
File without changes
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert-base-v2",
|
| 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_new",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"inner_group_num": 1,
|
| 18 |
+
"intermediate_size": 3072,
|
| 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": 12,
|
| 26 |
+
"num_memory_blocks": 0,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"transformers_version": "4.5.0.dev0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"vocab_size": 30000
|
| 32 |
+
}
|
data_args.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_cache_dir": "dataset_cache",
|
| 3 |
+
"dataset_config_name": null,
|
| 4 |
+
"dataset_name": "squad",
|
| 5 |
+
"doc_stride": 128,
|
| 6 |
+
"max_answer_length": 30,
|
| 7 |
+
"max_seq_length": 384,
|
| 8 |
+
"n_best_size": 20,
|
| 9 |
+
"null_score_diff_threshold": 0.0,
|
| 10 |
+
"overwrite_cache": 0,
|
| 11 |
+
"pad_to_max_length": true,
|
| 12 |
+
"preprocessing_num_workers": null,
|
| 13 |
+
"train_file": null,
|
| 14 |
+
"validation_file": null,
|
| 15 |
+
"version_2_with_negative": false
|
| 16 |
+
}
|
eval_metrics.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"exact_match": 83.74645222327341,
|
| 3 |
+
"f1": 90.78776054621733
|
| 4 |
+
}
|
evaluate_timing.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eval_elapsed_time": 54.7689094375819, "cuda_eval_elapsed_time": 50.769064575195316}
|
model_args.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_dir": null,
|
| 3 |
+
"config_name": null,
|
| 4 |
+
"model_name_or_path": "albert-base-v2",
|
| 5 |
+
"tokenizer_name": "albert-base-v2",
|
| 6 |
+
"use_fast_tokenizer": true
|
| 7 |
+
}
|
predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb659ad3854c5d988f0c30549bff33f3ece09c372a37fca2af93f2ab47b5fd81
|
| 3 |
+
size 44393497
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3efb47b48f2529e5a647ddc807b45fa670bdecf81c6556e90e2318707a57c88
|
| 3 |
+
size 623
|
sparse_args.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ampere_pruning_method": "disabled",
|
| 3 |
+
"attention_block_cols": 32,
|
| 4 |
+
"attention_block_rows": 32,
|
| 5 |
+
"attention_lambda": 1.0,
|
| 6 |
+
"attention_output_with_dense": 0,
|
| 7 |
+
"attention_pruning_method": "sigmoied_threshold",
|
| 8 |
+
"bias_mask": true,
|
| 9 |
+
"dense_block_cols": 1,
|
| 10 |
+
"dense_block_rows": 1,
|
| 11 |
+
"dense_lambda": 1.0,
|
| 12 |
+
"dense_pruning_method": "sigmoied_threshold:1d_alt",
|
| 13 |
+
"distil_alpha_ce": 0.1,
|
| 14 |
+
"distil_alpha_teacher": 0.9,
|
| 15 |
+
"distil_teacher_name_or_path": null,
|
| 16 |
+
"distil_temperature": 2.0,
|
| 17 |
+
"eval_with_current_patch_params": 1,
|
| 18 |
+
"final_ampere_temperature": 20.0,
|
| 19 |
+
"final_finetune": false,
|
| 20 |
+
"final_threshold": 1.0,
|
| 21 |
+
"final_warmup": 0.0,
|
| 22 |
+
"gelu_patch": 0,
|
| 23 |
+
"gelu_patch_steps": 50000,
|
| 24 |
+
"initial_ampere_temperature": 0.0,
|
| 25 |
+
"initial_threshold": 1.0,
|
| 26 |
+
"initial_warmup": 1,
|
| 27 |
+
"layer_norm_patch": 0,
|
| 28 |
+
"layer_norm_patch_start_delta": 0.99,
|
| 29 |
+
"layer_norm_patch_steps": 50000,
|
| 30 |
+
"linear_min_parameters": 0,
|
| 31 |
+
"mask_init": "constant",
|
| 32 |
+
"mask_scale": 0.0,
|
| 33 |
+
"mask_scores_learning_rate": 0.01,
|
| 34 |
+
"regularization": "l1",
|
| 35 |
+
"regularization_final_lambda": 0,
|
| 36 |
+
"rewind_model_name_or_path": null
|
| 37 |
+
}
|
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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
| 3 |
+
size 760289
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "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": "albert-base-v2"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9927797833935017,
|
| 5 |
+
"global_step": 11040,
|
| 6 |
+
"is_hyper_param_search": true,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"ampere_temperature": 0.0,
|
| 12 |
+
"ce_loss": 4.599947213172912,
|
| 13 |
+
"distil_loss": 0.0,
|
| 14 |
+
"epoch": 0.05,
|
| 15 |
+
"learning_rate": 0.001,
|
| 16 |
+
"loss": 4.5999,
|
| 17 |
+
"nnz_perc": 1.0,
|
| 18 |
+
"progress": 0.0,
|
| 19 |
+
"regu_lambda": 0.0,
|
| 20 |
+
"regu_loss": 0.0,
|
| 21 |
+
"step": 250,
|
| 22 |
+
"threshold": 1.0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"ampere_temperature": 0.0,
|
| 26 |
+
"ce_loss": 1.8339186582565308,
|
| 27 |
+
"distil_loss": 0.0,
|
| 28 |
+
"epoch": 0.09,
|
| 29 |
+
"learning_rate": 0.002,
|
| 30 |
+
"loss": 1.8339,
|
| 31 |
+
"nnz_perc": 1.0,
|
| 32 |
+
"progress": 0.0,
|
| 33 |
+
"regu_lambda": 0.0,
|
| 34 |
+
"regu_loss": 0.0,
|
| 35 |
+
"step": 500,
|
| 36 |
+
"threshold": 1.0
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"ampere_temperature": 0.0,
|
| 40 |
+
"ce_loss": 1.3567713406085968,
|
| 41 |
+
"distil_loss": 0.0,
|
| 42 |
+
"epoch": 0.14,
|
| 43 |
+
"learning_rate": 0.003,
|
| 44 |
+
"loss": 1.3568,
|
| 45 |
+
"nnz_perc": 1.0,
|
| 46 |
+
"progress": 0.0,
|
| 47 |
+
"regu_lambda": 0.0,
|
| 48 |
+
"regu_loss": 0.0,
|
| 49 |
+
"step": 750,
|
| 50 |
+
"threshold": 1.0
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"ampere_temperature": 0.0,
|
| 54 |
+
"ce_loss": 1.2095605379343033,
|
| 55 |
+
"distil_loss": 0.0,
|
| 56 |
+
"epoch": 0.18,
|
| 57 |
+
"learning_rate": 0.004,
|
| 58 |
+
"loss": 1.2096,
|
| 59 |
+
"nnz_perc": 1.0,
|
| 60 |
+
"progress": 0.0,
|
| 61 |
+
"regu_lambda": 0.0,
|
| 62 |
+
"regu_loss": 0.0,
|
| 63 |
+
"step": 1000,
|
| 64 |
+
"threshold": 1.0
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"ampere_temperature": 0.0,
|
| 68 |
+
"ce_loss": 1.1451576855182648,
|
| 69 |
+
"distil_loss": 0.0,
|
| 70 |
+
"epoch": 0.23,
|
| 71 |
+
"learning_rate": 0.005,
|
| 72 |
+
"loss": 1.1452,
|
| 73 |
+
"nnz_perc": 1.0,
|
| 74 |
+
"progress": 0.0,
|
| 75 |
+
"regu_lambda": 0.0,
|
| 76 |
+
"regu_loss": 0.0,
|
| 77 |
+
"step": 1250,
|
| 78 |
+
"threshold": 1.0
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"ce_loss": 1.1159179366551912,
|
| 82 |
+
"distil_loss": 0.0,
|
| 83 |
+
"epoch": 0.25,
|
| 84 |
+
"eval_ampere_temperature": 0.0,
|
| 85 |
+
"eval_exact_match": 77.360454115421,
|
| 86 |
+
"eval_f1": 86.34721419771964,
|
| 87 |
+
"eval_progress": 0.0,
|
| 88 |
+
"eval_regu_lambda": 0.0,
|
| 89 |
+
"eval_threshold": 1.0,
|
| 90 |
+
"nnz_perc": 1.0,
|
| 91 |
+
"regu_loss": 0.0,
|
| 92 |
+
"step": 1380
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"ampere_temperature": 0.0,
|
| 96 |
+
"ce_loss": 1.0835382461547851,
|
| 97 |
+
"distil_loss": 0.0,
|
| 98 |
+
"epoch": 0.27,
|
| 99 |
+
"learning_rate": 0.006,
|
| 100 |
+
"loss": 1.1004,
|
| 101 |
+
"nnz_perc": 1.0,
|
| 102 |
+
"progress": 0.0,
|
| 103 |
+
"regu_lambda": 0.0,
|
| 104 |
+
"regu_loss": 0.0,
|
| 105 |
+
"step": 1500,
|
| 106 |
+
"threshold": 1.0
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"ampere_temperature": 0.0,
|
| 110 |
+
"ce_loss": 1.1237352261543274,
|
| 111 |
+
"distil_loss": 0.0,
|
| 112 |
+
"epoch": 0.32,
|
| 113 |
+
"learning_rate": 0.006999999999999999,
|
| 114 |
+
"loss": 1.1237,
|
| 115 |
+
"nnz_perc": 1.0,
|
| 116 |
+
"progress": 0.0,
|
| 117 |
+
"regu_lambda": 0.0,
|
| 118 |
+
"regu_loss": 0.0,
|
| 119 |
+
"step": 1750,
|
| 120 |
+
"threshold": 1.0
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"ampere_temperature": 0.0,
|
| 124 |
+
"ce_loss": 1.116382148861885,
|
| 125 |
+
"distil_loss": 0.0,
|
| 126 |
+
"epoch": 0.36,
|
| 127 |
+
"learning_rate": 0.008,
|
| 128 |
+
"loss": 1.1164,
|
| 129 |
+
"nnz_perc": 1.0,
|
| 130 |
+
"progress": 0.0,
|
| 131 |
+
"regu_lambda": 0.0,
|
| 132 |
+
"regu_loss": 0.0,
|
| 133 |
+
"step": 2000,
|
| 134 |
+
"threshold": 1.0
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"ampere_temperature": 0.0,
|
| 138 |
+
"ce_loss": 1.0670130407810212,
|
| 139 |
+
"distil_loss": 0.0,
|
| 140 |
+
"epoch": 0.41,
|
| 141 |
+
"learning_rate": 0.009000000000000001,
|
| 142 |
+
"loss": 1.067,
|
| 143 |
+
"nnz_perc": 1.0,
|
| 144 |
+
"progress": 0.0,
|
| 145 |
+
"regu_lambda": 0.0,
|
| 146 |
+
"regu_loss": 0.0,
|
| 147 |
+
"step": 2250,
|
| 148 |
+
"threshold": 1.0
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"ampere_temperature": 0.0,
|
| 152 |
+
"ce_loss": 1.0639437032938004,
|
| 153 |
+
"distil_loss": 0.0,
|
| 154 |
+
"epoch": 0.45,
|
| 155 |
+
"learning_rate": 0.01,
|
| 156 |
+
"loss": 1.0639,
|
| 157 |
+
"nnz_perc": 1.0,
|
| 158 |
+
"progress": 0.0,
|
| 159 |
+
"regu_lambda": 0.0,
|
| 160 |
+
"regu_loss": 0.0,
|
| 161 |
+
"step": 2500,
|
| 162 |
+
"threshold": 1.0
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"ampere_temperature": 1.6912145472259645,
|
| 166 |
+
"ce_loss": 1.0629408322572709,
|
| 167 |
+
"distil_loss": 0.0,
|
| 168 |
+
"epoch": 0.5,
|
| 169 |
+
"learning_rate": 0.00970862470862471,
|
| 170 |
+
"loss": 1.0629,
|
| 171 |
+
"nnz_perc": 1.0,
|
| 172 |
+
"progress": 0.029020979020979,
|
| 173 |
+
"regu_lambda": 0.0,
|
| 174 |
+
"regu_loss": 0.0,
|
| 175 |
+
"step": 2750,
|
| 176 |
+
"threshold": 1.0
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"ce_loss": 1.0985989689826965,
|
| 180 |
+
"distil_loss": 0.0,
|
| 181 |
+
"epoch": 0.5,
|
| 182 |
+
"eval_ampere_temperature": 1.7570655286803998,
|
| 183 |
+
"eval_exact_match": 75.37369914853359,
|
| 184 |
+
"eval_f1": 85.4846023509551,
|
| 185 |
+
"eval_progress": 0.03018648018648018,
|
| 186 |
+
"eval_regu_lambda": 0.0,
|
| 187 |
+
"eval_threshold": 1.0,
|
| 188 |
+
"nnz_perc": 1.0,
|
| 189 |
+
"regu_loss": 0.0,
|
| 190 |
+
"step": 2760
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"ampere_temperature": 3.2905000860378912,
|
| 194 |
+
"ce_loss": 1.0230497049788634,
|
| 195 |
+
"distil_loss": 0.0,
|
| 196 |
+
"epoch": 0.54,
|
| 197 |
+
"learning_rate": 0.009417249417249416,
|
| 198 |
+
"loss": 1.0261,
|
| 199 |
+
"nnz_perc": 1.0,
|
| 200 |
+
"progress": 0.058158508158508204,
|
| 201 |
+
"regu_lambda": 0.0,
|
| 202 |
+
"regu_loss": 0.0,
|
| 203 |
+
"step": 3000,
|
| 204 |
+
"threshold": 1.0
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"ampere_temperature": 4.793831310474058,
|
| 208 |
+
"ce_loss": 0.9981409941911698,
|
| 209 |
+
"distil_loss": 0.0,
|
| 210 |
+
"epoch": 0.59,
|
| 211 |
+
"learning_rate": 0.009125874125874126,
|
| 212 |
+
"loss": 0.9981,
|
| 213 |
+
"nnz_perc": 1.0,
|
| 214 |
+
"progress": 0.0872960372960373,
|
| 215 |
+
"regu_lambda": 0.0,
|
| 216 |
+
"regu_loss": 0.0,
|
| 217 |
+
"step": 3250,
|
| 218 |
+
"threshold": 1.0
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"ampere_temperature": 6.204176736633212,
|
| 222 |
+
"ce_loss": 1.0074045011997224,
|
| 223 |
+
"distil_loss": 0.0,
|
| 224 |
+
"epoch": 0.63,
|
| 225 |
+
"learning_rate": 0.008834498834498834,
|
| 226 |
+
"loss": 1.0074,
|
| 227 |
+
"nnz_perc": 1.0,
|
| 228 |
+
"progress": 0.1164335664335664,
|
| 229 |
+
"regu_lambda": 0.0,
|
| 230 |
+
"regu_loss": 0.0,
|
| 231 |
+
"step": 3500,
|
| 232 |
+
"threshold": 1.0
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"ampere_temperature": 7.524504880614105,
|
| 236 |
+
"ce_loss": 0.9891920503377915,
|
| 237 |
+
"distil_loss": 0.0,
|
| 238 |
+
"epoch": 0.68,
|
| 239 |
+
"learning_rate": 0.008543123543123544,
|
| 240 |
+
"loss": 0.9892,
|
| 241 |
+
"nnz_perc": 1.0,
|
| 242 |
+
"progress": 0.1455710955710956,
|
| 243 |
+
"regu_lambda": 0.0,
|
| 244 |
+
"regu_loss": 0.0,
|
| 245 |
+
"step": 3750,
|
| 246 |
+
"threshold": 1.0
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"ampere_temperature": 8.757784258515466,
|
| 250 |
+
"ce_loss": 1.0083434996008873,
|
| 251 |
+
"distil_loss": 0.0,
|
| 252 |
+
"epoch": 0.72,
|
| 253 |
+
"learning_rate": 0.008251748251748252,
|
| 254 |
+
"loss": 1.0083,
|
| 255 |
+
"nnz_perc": 1.0,
|
| 256 |
+
"progress": 0.1747086247086247,
|
| 257 |
+
"regu_lambda": 0.0,
|
| 258 |
+
"regu_loss": 0.0,
|
| 259 |
+
"step": 4000,
|
| 260 |
+
"threshold": 1.0
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"ce_loss": 0.9699458577803203,
|
| 264 |
+
"distil_loss": 0.0,
|
| 265 |
+
"epoch": 0.75,
|
| 266 |
+
"eval_ampere_temperature": 9.411504281933276,
|
| 267 |
+
"eval_exact_match": 79.94323557237465,
|
| 268 |
+
"eval_f1": 88.17033886272301,
|
| 269 |
+
"eval_progress": 0.191025641025641,
|
| 270 |
+
"eval_regu_lambda": 0.0,
|
| 271 |
+
"eval_threshold": 1.0,
|
| 272 |
+
"nnz_perc": 1.0,
|
| 273 |
+
"regu_loss": 0.0,
|
| 274 |
+
"step": 4140
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"ampere_temperature": 9.906983386436048,
|
| 278 |
+
"ce_loss": 0.9698418254202062,
|
| 279 |
+
"distil_loss": 0.0,
|
| 280 |
+
"epoch": 0.77,
|
| 281 |
+
"learning_rate": 0.00796037296037296,
|
| 282 |
+
"loss": 0.9699,
|
| 283 |
+
"nnz_perc": 1.0,
|
| 284 |
+
"progress": 0.2038461538461538,
|
| 285 |
+
"regu_lambda": 0.0,
|
| 286 |
+
"regu_loss": 0.0,
|
| 287 |
+
"step": 4250,
|
| 288 |
+
"threshold": 1.0
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"ampere_temperature": 10.97507078047459,
|
| 292 |
+
"ce_loss": 0.9425091907978058,
|
| 293 |
+
"distil_loss": 0.0,
|
| 294 |
+
"epoch": 0.81,
|
| 295 |
+
"learning_rate": 0.007668997668997669,
|
| 296 |
+
"loss": 0.9425,
|
| 297 |
+
"nnz_perc": 1.0,
|
| 298 |
+
"progress": 0.232983682983683,
|
| 299 |
+
"regu_lambda": 0.0,
|
| 300 |
+
"regu_loss": 0.0,
|
| 301 |
+
"step": 4500,
|
| 302 |
+
"threshold": 1.0
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"ampere_temperature": 11.965014956729835,
|
| 306 |
+
"ce_loss": 0.9731772248744964,
|
| 307 |
+
"distil_loss": 0.0,
|
| 308 |
+
"epoch": 0.86,
|
| 309 |
+
"learning_rate": 0.007377622377622378,
|
| 310 |
+
"loss": 0.9732,
|
| 311 |
+
"nnz_perc": 1.0,
|
| 312 |
+
"progress": 0.2621212121212122,
|
| 313 |
+
"regu_lambda": 0.0,
|
| 314 |
+
"regu_loss": 0.0,
|
| 315 |
+
"step": 4750,
|
| 316 |
+
"threshold": 1.0
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"ampere_temperature": 12.879784431300521,
|
| 320 |
+
"ce_loss": 0.9197172073125839,
|
| 321 |
+
"distil_loss": 0.0,
|
| 322 |
+
"epoch": 0.9,
|
| 323 |
+
"learning_rate": 0.007086247086247086,
|
| 324 |
+
"loss": 0.9197,
|
| 325 |
+
"nnz_perc": 1.0,
|
| 326 |
+
"progress": 0.2912587412587413,
|
| 327 |
+
"regu_lambda": 0.0,
|
| 328 |
+
"regu_loss": 0.0,
|
| 329 |
+
"step": 5000,
|
| 330 |
+
"threshold": 1.0
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"ampere_temperature": 13.722347720285395,
|
| 334 |
+
"ce_loss": 0.9390108388662338,
|
| 335 |
+
"distil_loss": 0.0,
|
| 336 |
+
"epoch": 0.95,
|
| 337 |
+
"learning_rate": 0.006794871794871795,
|
| 338 |
+
"loss": 0.939,
|
| 339 |
+
"nnz_perc": 1.0,
|
| 340 |
+
"progress": 0.3203962703962704,
|
| 341 |
+
"regu_lambda": 0.0,
|
| 342 |
+
"regu_loss": 0.0,
|
| 343 |
+
"step": 5250,
|
| 344 |
+
"threshold": 1.0
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"ampere_temperature": 14.495673339783197,
|
| 348 |
+
"ce_loss": 0.9188237161636352,
|
| 349 |
+
"distil_loss": 0.0,
|
| 350 |
+
"epoch": 0.99,
|
| 351 |
+
"learning_rate": 0.006503496503496503,
|
| 352 |
+
"loss": 0.9188,
|
| 353 |
+
"nnz_perc": 1.0,
|
| 354 |
+
"progress": 0.3495337995337995,
|
| 355 |
+
"regu_lambda": 0.0,
|
| 356 |
+
"regu_loss": 0.0,
|
| 357 |
+
"step": 5500,
|
| 358 |
+
"threshold": 1.0
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"ce_loss": 0.9402093678712845,
|
| 362 |
+
"distil_loss": 0.0,
|
| 363 |
+
"epoch": 1.0,
|
| 364 |
+
"eval_ampere_temperature": 14.55463723501537,
|
| 365 |
+
"eval_exact_match": 81.63670766319773,
|
| 366 |
+
"eval_f1": 89.21446798933258,
|
| 367 |
+
"eval_progress": 0.35186480186480185,
|
| 368 |
+
"eval_regu_lambda": 0.0,
|
| 369 |
+
"eval_threshold": 1.0,
|
| 370 |
+
"nnz_perc": 1.0,
|
| 371 |
+
"regu_loss": 0.0,
|
| 372 |
+
"step": 5520
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"ampere_temperature": 15.202729805892675,
|
| 376 |
+
"ce_loss": 0.7292252867118172,
|
| 377 |
+
"distil_loss": 0.0,
|
| 378 |
+
"epoch": 1.04,
|
| 379 |
+
"learning_rate": 0.006212121212121212,
|
| 380 |
+
"loss": 0.7461,
|
| 381 |
+
"nnz_perc": 1.0,
|
| 382 |
+
"progress": 0.3786713286713287,
|
| 383 |
+
"regu_lambda": 0.0,
|
| 384 |
+
"regu_loss": 0.0,
|
| 385 |
+
"step": 5750,
|
| 386 |
+
"threshold": 1.0
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"ampere_temperature": 15.846485634712565,
|
| 390 |
+
"ce_loss": 0.7380791381597519,
|
| 391 |
+
"distil_loss": 0.0,
|
| 392 |
+
"epoch": 1.08,
|
| 393 |
+
"learning_rate": 0.005920745920745921,
|
| 394 |
+
"loss": 0.7381,
|
| 395 |
+
"nnz_perc": 1.0,
|
| 396 |
+
"progress": 0.4078088578088578,
|
| 397 |
+
"regu_lambda": 0.0,
|
| 398 |
+
"regu_loss": 0.0,
|
| 399 |
+
"step": 6000,
|
| 400 |
+
"threshold": 1.0
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"ampere_temperature": 16.429909342341613,
|
| 404 |
+
"ce_loss": 0.7548821606636047,
|
| 405 |
+
"distil_loss": 0.0,
|
| 406 |
+
"epoch": 1.13,
|
| 407 |
+
"learning_rate": 0.005629370629370629,
|
| 408 |
+
"loss": 0.7549,
|
| 409 |
+
"nnz_perc": 1.0,
|
| 410 |
+
"progress": 0.436946386946387,
|
| 411 |
+
"regu_lambda": 0.0,
|
| 412 |
+
"regu_loss": 0.0,
|
| 413 |
+
"step": 6250,
|
| 414 |
+
"threshold": 1.0
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"ampere_temperature": 16.955969444878562,
|
| 418 |
+
"ce_loss": 0.7157313173413277,
|
| 419 |
+
"distil_loss": 0.0,
|
| 420 |
+
"epoch": 1.17,
|
| 421 |
+
"learning_rate": 0.005337995337995338,
|
| 422 |
+
"loss": 0.7157,
|
| 423 |
+
"nnz_perc": 1.0,
|
| 424 |
+
"progress": 0.4660839160839161,
|
| 425 |
+
"regu_lambda": 0.0,
|
| 426 |
+
"regu_loss": 0.0,
|
| 427 |
+
"step": 6500,
|
| 428 |
+
"threshold": 1.0
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"ampere_temperature": 17.427634458422148,
|
| 432 |
+
"ce_loss": 0.7611533465385437,
|
| 433 |
+
"distil_loss": 0.0,
|
| 434 |
+
"epoch": 1.22,
|
| 435 |
+
"learning_rate": 0.005046620046620046,
|
| 436 |
+
"loss": 0.7612,
|
| 437 |
+
"nnz_perc": 1.0,
|
| 438 |
+
"progress": 0.4952214452214452,
|
| 439 |
+
"regu_lambda": 0.0,
|
| 440 |
+
"regu_loss": 0.0,
|
| 441 |
+
"step": 6750,
|
| 442 |
+
"threshold": 1.0
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"ce_loss": 0.7508984424670537,
|
| 446 |
+
"distil_loss": 0.0,
|
| 447 |
+
"epoch": 1.25,
|
| 448 |
+
"eval_ampere_temperature": 17.68575872652857,
|
| 449 |
+
"eval_exact_match": 81.51371807000946,
|
| 450 |
+
"eval_f1": 88.80037767793473,
|
| 451 |
+
"eval_progress": 0.5127039627039627,
|
| 452 |
+
"eval_regu_lambda": 0.0,
|
| 453 |
+
"eval_threshold": 1.0,
|
| 454 |
+
"nnz_perc": 1.0,
|
| 455 |
+
"regu_loss": 0.0,
|
| 456 |
+
"step": 6900
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"ampere_temperature": 17.847872899071124,
|
| 460 |
+
"ce_loss": 0.6947148644924164,
|
| 461 |
+
"distil_loss": 0.0,
|
| 462 |
+
"epoch": 1.26,
|
| 463 |
+
"learning_rate": 0.004755244755244755,
|
| 464 |
+
"loss": 0.7284,
|
| 465 |
+
"nnz_perc": 1.0,
|
| 466 |
+
"progress": 0.5243589743589744,
|
| 467 |
+
"regu_lambda": 0.0,
|
| 468 |
+
"regu_loss": 0.0,
|
| 469 |
+
"step": 7000,
|
| 470 |
+
"threshold": 1.0
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"ampere_temperature": 18.219653282924224,
|
| 474 |
+
"ce_loss": 0.7663285417556762,
|
| 475 |
+
"distil_loss": 0.0,
|
| 476 |
+
"epoch": 1.31,
|
| 477 |
+
"learning_rate": 0.004463869463869464,
|
| 478 |
+
"loss": 0.7663,
|
| 479 |
+
"nnz_perc": 1.0,
|
| 480 |
+
"progress": 0.5534965034965035,
|
| 481 |
+
"regu_lambda": 0.0,
|
| 482 |
+
"regu_loss": 0.0,
|
| 483 |
+
"step": 7250,
|
| 484 |
+
"threshold": 1.0
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"ampere_temperature": 18.545944126080197,
|
| 488 |
+
"ce_loss": 0.691897637873888,
|
| 489 |
+
"distil_loss": 0.0,
|
| 490 |
+
"epoch": 1.35,
|
| 491 |
+
"learning_rate": 0.004172494172494173,
|
| 492 |
+
"loss": 0.6919,
|
| 493 |
+
"nnz_perc": 1.0,
|
| 494 |
+
"progress": 0.5826340326340327,
|
| 495 |
+
"regu_lambda": 0.0,
|
| 496 |
+
"regu_loss": 0.0,
|
| 497 |
+
"step": 7500,
|
| 498 |
+
"threshold": 1.0
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"ampere_temperature": 18.82971394463778,
|
| 502 |
+
"ce_loss": 0.7088325002193451,
|
| 503 |
+
"distil_loss": 0.0,
|
| 504 |
+
"epoch": 1.4,
|
| 505 |
+
"learning_rate": 0.0038811188811188812,
|
| 506 |
+
"loss": 0.7088,
|
| 507 |
+
"nnz_perc": 1.0,
|
| 508 |
+
"progress": 0.6117715617715618,
|
| 509 |
+
"regu_lambda": 0.0,
|
| 510 |
+
"regu_loss": 0.0,
|
| 511 |
+
"step": 7750,
|
| 512 |
+
"threshold": 1.0
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"ampere_temperature": 19.07393125469572,
|
| 516 |
+
"ce_loss": 0.7107383124232293,
|
| 517 |
+
"distil_loss": 0.0,
|
| 518 |
+
"epoch": 1.44,
|
| 519 |
+
"learning_rate": 0.0035897435897435897,
|
| 520 |
+
"loss": 0.7107,
|
| 521 |
+
"nnz_perc": 1.0,
|
| 522 |
+
"progress": 0.6409090909090909,
|
| 523 |
+
"regu_lambda": 0.0,
|
| 524 |
+
"regu_loss": 0.0,
|
| 525 |
+
"step": 8000,
|
| 526 |
+
"threshold": 1.0
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"ampere_temperature": 19.281564572352753,
|
| 530 |
+
"ce_loss": 0.7073436776399612,
|
| 531 |
+
"distil_loss": 0.0,
|
| 532 |
+
"epoch": 1.49,
|
| 533 |
+
"learning_rate": 0.0032983682983682983,
|
| 534 |
+
"loss": 0.7073,
|
| 535 |
+
"nnz_perc": 1.0,
|
| 536 |
+
"progress": 0.6700466200466201,
|
| 537 |
+
"regu_lambda": 0.0,
|
| 538 |
+
"regu_loss": 0.0,
|
| 539 |
+
"step": 8250,
|
| 540 |
+
"threshold": 1.0
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"ce_loss": 0.7176821072896321,
|
| 544 |
+
"distil_loss": 0.0,
|
| 545 |
+
"epoch": 1.49,
|
| 546 |
+
"eval_ampere_temperature": 19.304163095074752,
|
| 547 |
+
"eval_exact_match": 82.71523178807946,
|
| 548 |
+
"eval_f1": 89.82467226075393,
|
| 549 |
+
"eval_progress": 0.6735431235431235,
|
| 550 |
+
"eval_regu_lambda": 0.0,
|
| 551 |
+
"eval_threshold": 1.0,
|
| 552 |
+
"nnz_perc": 1.0,
|
| 553 |
+
"regu_loss": 0.0,
|
| 554 |
+
"step": 8280
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"ampere_temperature": 19.455582413707628,
|
| 558 |
+
"ce_loss": 0.7027889224615964,
|
| 559 |
+
"distil_loss": 0.0,
|
| 560 |
+
"epoch": 1.53,
|
| 561 |
+
"learning_rate": 0.0030069930069930068,
|
| 562 |
+
"loss": 0.7046,
|
| 563 |
+
"nnz_perc": 1.0,
|
| 564 |
+
"progress": 0.6991841491841492,
|
| 565 |
+
"regu_lambda": 0.0,
|
| 566 |
+
"regu_loss": 0.0,
|
| 567 |
+
"step": 8500,
|
| 568 |
+
"threshold": 1.0
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"ampere_temperature": 19.598953294859086,
|
| 572 |
+
"ce_loss": 0.6954642720222474,
|
| 573 |
+
"distil_loss": 0.0,
|
| 574 |
+
"epoch": 1.58,
|
| 575 |
+
"learning_rate": 0.0027156177156177157,
|
| 576 |
+
"loss": 0.6955,
|
| 577 |
+
"nnz_perc": 1.0,
|
| 578 |
+
"progress": 0.7283216783216783,
|
| 579 |
+
"regu_lambda": 0.0,
|
| 580 |
+
"regu_loss": 0.0,
|
| 581 |
+
"step": 8750,
|
| 582 |
+
"threshold": 1.0
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"ampere_temperature": 19.71464573190587,
|
| 586 |
+
"ce_loss": 0.7050508892536164,
|
| 587 |
+
"distil_loss": 0.0,
|
| 588 |
+
"epoch": 1.62,
|
| 589 |
+
"learning_rate": 0.0024242424242424242,
|
| 590 |
+
"loss": 0.7051,
|
| 591 |
+
"nnz_perc": 1.0,
|
| 592 |
+
"progress": 0.7574592074592075,
|
| 593 |
+
"regu_lambda": 0.0,
|
| 594 |
+
"regu_loss": 0.0,
|
| 595 |
+
"step": 9000,
|
| 596 |
+
"threshold": 1.0
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"ampere_temperature": 19.805628240946717,
|
| 600 |
+
"ce_loss": 0.6534205512404442,
|
| 601 |
+
"distil_loss": 0.0,
|
| 602 |
+
"epoch": 1.67,
|
| 603 |
+
"learning_rate": 0.0021328671328671328,
|
| 604 |
+
"loss": 0.6534,
|
| 605 |
+
"nnz_perc": 1.0,
|
| 606 |
+
"progress": 0.7865967365967366,
|
| 607 |
+
"regu_lambda": 0.0,
|
| 608 |
+
"regu_loss": 0.0,
|
| 609 |
+
"step": 9250,
|
| 610 |
+
"threshold": 1.0
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"ampere_temperature": 19.874869338080376,
|
| 614 |
+
"ce_loss": 0.6931327093839645,
|
| 615 |
+
"distil_loss": 0.0,
|
| 616 |
+
"epoch": 1.71,
|
| 617 |
+
"learning_rate": 0.0018414918414918417,
|
| 618 |
+
"loss": 0.6931,
|
| 619 |
+
"nnz_perc": 1.0,
|
| 620 |
+
"progress": 0.8157342657342658,
|
| 621 |
+
"regu_lambda": 0.0,
|
| 622 |
+
"regu_loss": 0.0,
|
| 623 |
+
"step": 9500,
|
| 624 |
+
"threshold": 1.0
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"ce_loss": 0.6803905916400254,
|
| 628 |
+
"distil_loss": 0.0,
|
| 629 |
+
"epoch": 1.74,
|
| 630 |
+
"eval_ampere_temperature": 19.90914467925581,
|
| 631 |
+
"eval_exact_match": 83.3112582781457,
|
| 632 |
+
"eval_f1": 90.48253679391624,
|
| 633 |
+
"eval_progress": 0.8343822843822843,
|
| 634 |
+
"eval_regu_lambda": 0.0,
|
| 635 |
+
"eval_threshold": 1.0,
|
| 636 |
+
"nnz_perc": 1.0,
|
| 637 |
+
"regu_loss": 0.0,
|
| 638 |
+
"step": 9660
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"ampere_temperature": 19.925337539405586,
|
| 642 |
+
"ce_loss": 0.6604658047358195,
|
| 643 |
+
"distil_loss": 0.0,
|
| 644 |
+
"epoch": 1.76,
|
| 645 |
+
"learning_rate": 0.0015501165501165502,
|
| 646 |
+
"loss": 0.6732,
|
| 647 |
+
"nnz_perc": 1.0,
|
| 648 |
+
"progress": 0.8448717948717949,
|
| 649 |
+
"regu_lambda": 0.0,
|
| 650 |
+
"regu_loss": 0.0,
|
| 651 |
+
"step": 9750,
|
| 652 |
+
"threshold": 1.0
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"ampere_temperature": 19.960001361021092,
|
| 656 |
+
"ce_loss": 0.6589477426409721,
|
| 657 |
+
"distil_loss": 0.0,
|
| 658 |
+
"epoch": 1.81,
|
| 659 |
+
"learning_rate": 0.001258741258741259,
|
| 660 |
+
"loss": 0.6589,
|
| 661 |
+
"nnz_perc": 1.0,
|
| 662 |
+
"progress": 0.874009324009324,
|
| 663 |
+
"regu_lambda": 0.0,
|
| 664 |
+
"regu_loss": 0.0,
|
| 665 |
+
"step": 10000,
|
| 666 |
+
"threshold": 1.0
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"ampere_temperature": 19.981829319025636,
|
| 670 |
+
"ce_loss": 0.6645486508607864,
|
| 671 |
+
"distil_loss": 0.0,
|
| 672 |
+
"epoch": 1.85,
|
| 673 |
+
"learning_rate": 0.0009673659673659674,
|
| 674 |
+
"loss": 0.6645,
|
| 675 |
+
"nnz_perc": 1.0,
|
| 676 |
+
"progress": 0.9031468531468532,
|
| 677 |
+
"regu_lambda": 0.0,
|
| 678 |
+
"regu_loss": 0.0,
|
| 679 |
+
"step": 10250,
|
| 680 |
+
"threshold": 1.0
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"ampere_temperature": 19.99378992951796,
|
| 684 |
+
"ce_loss": 0.6627120378017426,
|
| 685 |
+
"distil_loss": 0.0,
|
| 686 |
+
"epoch": 1.9,
|
| 687 |
+
"learning_rate": 0.000675990675990676,
|
| 688 |
+
"loss": 0.6627,
|
| 689 |
+
"nnz_perc": 1.0,
|
| 690 |
+
"progress": 0.9322843822843823,
|
| 691 |
+
"regu_lambda": 0.0,
|
| 692 |
+
"regu_loss": 0.0,
|
| 693 |
+
"step": 10500,
|
| 694 |
+
"threshold": 1.0
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"ampere_temperature": 19.998851708596806,
|
| 698 |
+
"ce_loss": 0.6525639802217483,
|
| 699 |
+
"distil_loss": 0.0,
|
| 700 |
+
"epoch": 1.94,
|
| 701 |
+
"learning_rate": 0.00038461538461538467,
|
| 702 |
+
"loss": 0.6526,
|
| 703 |
+
"nnz_perc": 1.0,
|
| 704 |
+
"progress": 0.9614219114219115,
|
| 705 |
+
"regu_lambda": 0.0,
|
| 706 |
+
"regu_loss": 0.0,
|
| 707 |
+
"step": 10750,
|
| 708 |
+
"threshold": 1.0
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"ampere_temperature": 19.999983172360917,
|
| 712 |
+
"ce_loss": 0.630506355702877,
|
| 713 |
+
"distil_loss": 0.0,
|
| 714 |
+
"epoch": 1.99,
|
| 715 |
+
"learning_rate": 9.324009324009324e-05,
|
| 716 |
+
"loss": 0.6305,
|
| 717 |
+
"nnz_perc": 1.0,
|
| 718 |
+
"progress": 0.9905594405594406,
|
| 719 |
+
"regu_lambda": 0.0,
|
| 720 |
+
"regu_loss": 0.0,
|
| 721 |
+
"step": 11000,
|
| 722 |
+
"threshold": 1.0
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"ce_loss": 0.6976410485804081,
|
| 726 |
+
"distil_loss": 0.0,
|
| 727 |
+
"epoch": 1.99,
|
| 728 |
+
"eval_ampere_temperature": 19.99999781767362,
|
| 729 |
+
"eval_exact_match": 83.74645222327341,
|
| 730 |
+
"eval_f1": 90.78776054621733,
|
| 731 |
+
"eval_progress": 0.9952214452214452,
|
| 732 |
+
"eval_regu_lambda": 0.0,
|
| 733 |
+
"eval_threshold": 1.0,
|
| 734 |
+
"nnz_perc": 1.0,
|
| 735 |
+
"regu_loss": 0.0,
|
| 736 |
+
"step": 11040
|
| 737 |
+
}
|
| 738 |
+
],
|
| 739 |
+
"max_steps": 11080,
|
| 740 |
+
"num_train_epochs": 2,
|
| 741 |
+
"total_flos": 0,
|
| 742 |
+
"trial_name": "hp_mnop-albert-base-v2_tn-albert-base-v2_od-__data_2to__devel_data__nn_pruning__output_sequence__squad_test_teacher___es-steps_pdebs128_nte2_ws2500_ls250_ss1380_stl50_est1380_rn-__da--3c944a736efd9cf3",
|
| 743 |
+
"trial_params": {}
|
| 744 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47449325d252d34ff18fda0c7a3bf3dd57546e99a7f8befb130692cf2688c4fb
|
| 3 |
+
size 2479
|