Upload folder using huggingface_hub
Browse files- all_results.json +39 -0
- config.json +36 -0
- mnli-m_results.json +8 -0
- mnli-mm_results.json +8 -0
- ood_results.json +11 -0
- pred_mnli-m.npz.npy +3 -0
- pred_mnli-mm.npz.npy +3 -0
- pred_ood.npz.npy +3 -0
- pred_stress-antonym.npz.npy +3 -0
- pred_stress-length_mismatch.npz.npy +3 -0
- pred_stress-negation.npz.npy +3 -0
- pred_stress-numerical_reasoning.npz.npy +3 -0
- pred_stress-spelling_error.npz.npy +3 -0
- pred_stress-word_overlap.npz.npy +3 -0
- pred_transfer.npz.npy +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- stress-antonym_results.json +9 -0
- stress-length_mismatch_results.json +9 -0
- stress-negation_results.json +9 -0
- stress-numerical_reasoning_results.json +9 -0
- stress-spelling_error_results.json +9 -0
- stress-word_overlap_results.json +9 -0
- test_results.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +7 -0
- trainer_state.json +889 -0
- training_args.bin +3 -0
- transfer_results.json +8 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.6230926793772671,
|
| 3 |
+
"ave/ood": 0.5047666666666667,
|
| 4 |
+
"ave/stress": 42.38296607553561,
|
| 5 |
+
"ave/transfer": 0.5824019508230035,
|
| 6 |
+
"epoch": 3.0,
|
| 7 |
+
"eval_accuracy": 0.5824019508230035,
|
| 8 |
+
"eval_combined_score": 0.5824019508230035,
|
| 9 |
+
"eval_constituent_accuracy": 0.5099,
|
| 10 |
+
"eval_lexical_overlap_accuracy": 0.4987,
|
| 11 |
+
"eval_loss": 0.9483514428138733,
|
| 12 |
+
"eval_runtime": 1.9985,
|
| 13 |
+
"eval_samples_per_second": 4924.636,
|
| 14 |
+
"eval_steps_per_second": 19.514,
|
| 15 |
+
"eval_subsequence_accuracy": 0.5057,
|
| 16 |
+
"gap/constituent": 0.11319267937726707,
|
| 17 |
+
"gap/lexical_overlap": 0.12439267937726711,
|
| 18 |
+
"gap/ood": 0.11832601271060039,
|
| 19 |
+
"gap/stress": 19.92630186219109,
|
| 20 |
+
"gap/subsequence": 0.11739267937726705,
|
| 21 |
+
"gap/transfer": 0.04069072855426359,
|
| 22 |
+
"mnli-m": 0.6173204279164544,
|
| 23 |
+
"mnli-mm": 0.6288649308380797,
|
| 24 |
+
"ood": 0.5047666666666667,
|
| 25 |
+
"ood/constituent": 0.5099,
|
| 26 |
+
"ood/lexical_overlap": 0.4987,
|
| 27 |
+
"ood/subsequence": 0.5057,
|
| 28 |
+
"stress-antonym": 6.662395900064061,
|
| 29 |
+
"stress-length_mismatch": 58.83851248089659,
|
| 30 |
+
"stress-negation": 45.5960130187144,
|
| 31 |
+
"stress-numerical_reasoning": 26.987888362295948,
|
| 32 |
+
"stress-spelling_error": 60.00875560906206,
|
| 33 |
+
"stress-word_overlap": 56.204231082180634,
|
| 34 |
+
"train_loss": 0.8166523379133837,
|
| 35 |
+
"train_runtime": 2409.4346,
|
| 36 |
+
"train_samples_per_second": 926.607,
|
| 37 |
+
"train_steps_per_second": 28.957,
|
| 38 |
+
"transfer": 0.5824019508230035
|
| 39 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 512,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 2,
|
| 27 |
+
"num_hidden_layers": 2,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.25.0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
mnli-m_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.6173204279164544,
|
| 3 |
+
"eval_combined_score": 0.6173204279164544,
|
| 4 |
+
"eval_loss": 0.8748815059661865,
|
| 5 |
+
"eval_runtime": 2.27,
|
| 6 |
+
"eval_samples_per_second": 4323.771,
|
| 7 |
+
"eval_steps_per_second": 17.181
|
| 8 |
+
}
|
mnli-mm_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.6288649308380797,
|
| 3 |
+
"eval_combined_score": 0.6288649308380797,
|
| 4 |
+
"eval_loss": 0.8644155263900757,
|
| 5 |
+
"eval_runtime": 1.9573,
|
| 6 |
+
"eval_samples_per_second": 5023.121,
|
| 7 |
+
"eval_steps_per_second": 19.925
|
| 8 |
+
}
|
ood_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.5047666666666667,
|
| 3 |
+
"eval_combined_score": 0.5047666666666667,
|
| 4 |
+
"eval_constituent_accuracy": 0.5099,
|
| 5 |
+
"eval_lexical_overlap_accuracy": 0.4987,
|
| 6 |
+
"eval_loss": 1.9909288883209229,
|
| 7 |
+
"eval_runtime": 4.8057,
|
| 8 |
+
"eval_samples_per_second": 6242.527,
|
| 9 |
+
"eval_steps_per_second": 24.554,
|
| 10 |
+
"eval_subsequence_accuracy": 0.5057
|
| 11 |
+
}
|
pred_mnli-m.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f54cbf7fce982b7e47d8962e5def73e2a8de27b8faf1f467174bb9bc98e8e0d
|
| 3 |
+
size 117908
|
pred_mnli-mm.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4365a3237e13c20a2a3c78edc4775c7fba1a413f53c871a55d43e21d2cc4094
|
| 3 |
+
size 118112
|
pred_ood.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7941789b8e2ce3cdf51957a939c0929c5c4d78a9ce2099ff4ef6df7a25eb5be1
|
| 3 |
+
size 360128
|
pred_stress-antonym.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a13d261146c771e034e9d81d53b646d73449ffe411beb908261adc76bcf84968
|
| 3 |
+
size 18860
|
pred_stress-length_mismatch.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86d91c34847ced7ba639cd62e0cc368e6420397c46e09744a04db9f380f28052
|
| 3 |
+
size 117908
|
pred_stress-negation.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48967d12821726139175b548ea887d860a79503cce2f8d5be603384b67dfe683
|
| 3 |
+
size 118112
|
pred_stress-numerical_reasoning.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5f5d16efef6992427e0a1ab44a7b3a7671bbf74ca46653df26d648b6f0bafba
|
| 3 |
+
size 91280
|
pred_stress-spelling_error.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c7c4a2d518c025a02e13cf457c5d49cd608758184a47f107532cb9c9bd8ac5a
|
| 3 |
+
size 109772
|
pred_stress-word_overlap.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01917c1b1dff2014f1ebedfe2912e3b78e83b663baa8cfffa19b404c2ac6ba9
|
| 3 |
+
size 118112
|
pred_transfer.npz.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82a0b3300ce7c03485dec3548b9b78dc2bf58a68f3ddab44abe1f0f44c924b10
|
| 3 |
+
size 118232
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3c6fa3f2580d6da8e2783791411e50d3b177deb19a8a387a75e9bf56b6b759a
|
| 3 |
+
size 17563119
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
stress-antonym_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 6.662395900064061,
|
| 4 |
+
"eval_combined_score": 6.662395900064061,
|
| 5 |
+
"eval_loss": 2.0979509353637695,
|
| 6 |
+
"eval_runtime": 0.815,
|
| 7 |
+
"eval_samples_per_second": 1915.446,
|
| 8 |
+
"eval_steps_per_second": 8.589
|
| 9 |
+
}
|
stress-length_mismatch_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 58.83851248089659,
|
| 4 |
+
"eval_combined_score": 58.83851248089659,
|
| 5 |
+
"eval_loss": 0.944787859916687,
|
| 6 |
+
"eval_runtime": 5.7128,
|
| 7 |
+
"eval_samples_per_second": 1718.07,
|
| 8 |
+
"eval_steps_per_second": 6.827
|
| 9 |
+
}
|
stress-negation_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 45.5960130187144,
|
| 4 |
+
"eval_combined_score": 45.5960130187144,
|
| 5 |
+
"eval_loss": 1.2349395751953125,
|
| 6 |
+
"eval_runtime": 5.4585,
|
| 7 |
+
"eval_samples_per_second": 1801.228,
|
| 8 |
+
"eval_steps_per_second": 7.145
|
| 9 |
+
}
|
stress-numerical_reasoning_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 26.987888362295948,
|
| 4 |
+
"eval_combined_score": 26.987888362295948,
|
| 5 |
+
"eval_loss": 1.9486095905303955,
|
| 6 |
+
"eval_runtime": 4.5423,
|
| 7 |
+
"eval_samples_per_second": 1672.295,
|
| 8 |
+
"eval_steps_per_second": 6.605
|
| 9 |
+
}
|
stress-spelling_error_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 60.00875560906206,
|
| 4 |
+
"eval_combined_score": 60.00875560906206,
|
| 5 |
+
"eval_loss": 0.9045480489730835,
|
| 6 |
+
"eval_runtime": 5.3577,
|
| 7 |
+
"eval_samples_per_second": 1705.389,
|
| 8 |
+
"eval_steps_per_second": 6.719
|
| 9 |
+
}
|
stress-word_overlap_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 56.204231082180634,
|
| 4 |
+
"eval_combined_score": 56.204231082180634,
|
| 5 |
+
"eval_loss": 0.9651319980621338,
|
| 6 |
+
"eval_runtime": 5.5646,
|
| 7 |
+
"eval_samples_per_second": 1766.896,
|
| 8 |
+
"eval_steps_per_second": 7.009
|
| 9 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ave/id": 0.6230926793772671,
|
| 3 |
+
"ave/ood": 0.5047666666666667,
|
| 4 |
+
"ave/transfer": 0.5824019508230035,
|
| 5 |
+
"gap/constituent": 0.11319267937726707,
|
| 6 |
+
"gap/lexical_overlap": 0.12439267937726711,
|
| 7 |
+
"gap/ood": 0.11832601271060039,
|
| 8 |
+
"gap/subsequence": 0.11739267937726705,
|
| 9 |
+
"gap/transfer": 0.04069072855426359,
|
| 10 |
+
"mnli-m": 0.6173204279164544,
|
| 11 |
+
"mnli-mm": 0.6288649308380797,
|
| 12 |
+
"ood": 0.5047666666666667,
|
| 13 |
+
"ood/constituent": 0.5099,
|
| 14 |
+
"ood/lexical_overlap": 0.4987,
|
| 15 |
+
"ood/subsequence": 0.5057,
|
| 16 |
+
"transfer": 0.5824019508230035
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.8166523379133837,
|
| 4 |
+
"train_runtime": 2409.4346,
|
| 5 |
+
"train_samples_per_second": 926.607,
|
| 6 |
+
"train_steps_per_second": 28.957
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,889 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 61.73204279164543,
|
| 3 |
+
"best_model_checkpoint": "outputs/bert-tiny/gd_seqz/mnli_21/checkpoint-69771",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 69771,
|
| 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": 1.9856673976293877e-05,
|
| 13 |
+
"loss": 1.096,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.9713347952587752e-05,
|
| 19 |
+
"loss": 1.0505,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 1.9570021928881627e-05,
|
| 25 |
+
"loss": 1.0032,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 1.9426695905175502e-05,
|
| 31 |
+
"loss": 0.988,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"learning_rate": 1.928336988146938e-05,
|
| 37 |
+
"loss": 0.9801,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13,
|
| 42 |
+
"learning_rate": 1.9140043857763256e-05,
|
| 43 |
+
"loss": 0.9722,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 1.899671783405713e-05,
|
| 49 |
+
"loss": 0.9591,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.17,
|
| 54 |
+
"learning_rate": 1.8853391810351007e-05,
|
| 55 |
+
"loss": 0.9524,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.19,
|
| 60 |
+
"learning_rate": 1.8710065786644882e-05,
|
| 61 |
+
"loss": 0.9486,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.21,
|
| 66 |
+
"learning_rate": 1.856673976293876e-05,
|
| 67 |
+
"loss": 0.9414,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.24,
|
| 72 |
+
"learning_rate": 1.8423413739232636e-05,
|
| 73 |
+
"loss": 0.9409,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.26,
|
| 78 |
+
"learning_rate": 1.8280087715526507e-05,
|
| 79 |
+
"loss": 0.9317,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.28,
|
| 84 |
+
"learning_rate": 1.8136761691820386e-05,
|
| 85 |
+
"loss": 0.9281,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"learning_rate": 1.799343566811426e-05,
|
| 91 |
+
"loss": 0.9224,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.32,
|
| 96 |
+
"learning_rate": 1.7850109644408136e-05,
|
| 97 |
+
"loss": 0.917,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.34,
|
| 102 |
+
"learning_rate": 1.770678362070201e-05,
|
| 103 |
+
"loss": 0.9202,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.37,
|
| 108 |
+
"learning_rate": 1.7563457596995887e-05,
|
| 109 |
+
"loss": 0.9124,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.39,
|
| 114 |
+
"learning_rate": 1.7420131573289765e-05,
|
| 115 |
+
"loss": 0.9116,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.41,
|
| 120 |
+
"learning_rate": 1.727680554958364e-05,
|
| 121 |
+
"loss": 0.9044,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.43,
|
| 126 |
+
"learning_rate": 1.7133479525877516e-05,
|
| 127 |
+
"loss": 0.9049,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"learning_rate": 1.699015350217139e-05,
|
| 133 |
+
"loss": 0.8855,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.47,
|
| 138 |
+
"learning_rate": 1.6846827478465266e-05,
|
| 139 |
+
"loss": 0.8977,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.49,
|
| 144 |
+
"learning_rate": 1.670350145475914e-05,
|
| 145 |
+
"loss": 0.8943,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.52,
|
| 150 |
+
"learning_rate": 1.656017543105302e-05,
|
| 151 |
+
"loss": 0.8939,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.54,
|
| 156 |
+
"learning_rate": 1.641684940734689e-05,
|
| 157 |
+
"loss": 0.8958,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.56,
|
| 162 |
+
"learning_rate": 1.6273523383640767e-05,
|
| 163 |
+
"loss": 0.8785,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.58,
|
| 168 |
+
"learning_rate": 1.6130197359934645e-05,
|
| 169 |
+
"loss": 0.8787,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6,
|
| 174 |
+
"learning_rate": 1.598687133622852e-05,
|
| 175 |
+
"loss": 0.8742,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.62,
|
| 180 |
+
"learning_rate": 1.5843545312522396e-05,
|
| 181 |
+
"loss": 0.8725,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.64,
|
| 186 |
+
"learning_rate": 1.570021928881627e-05,
|
| 187 |
+
"loss": 0.8735,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.67,
|
| 192 |
+
"learning_rate": 1.5556893265110146e-05,
|
| 193 |
+
"loss": 0.8771,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.69,
|
| 198 |
+
"learning_rate": 1.5413567241404025e-05,
|
| 199 |
+
"loss": 0.8684,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.71,
|
| 204 |
+
"learning_rate": 1.52702412176979e-05,
|
| 205 |
+
"loss": 0.8755,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.73,
|
| 210 |
+
"learning_rate": 1.5126915193991773e-05,
|
| 211 |
+
"loss": 0.871,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.75,
|
| 216 |
+
"learning_rate": 1.498358917028565e-05,
|
| 217 |
+
"loss": 0.8695,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.77,
|
| 222 |
+
"learning_rate": 1.4840263146579526e-05,
|
| 223 |
+
"loss": 0.8586,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.8,
|
| 228 |
+
"learning_rate": 1.46969371228734e-05,
|
| 229 |
+
"loss": 0.8567,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.82,
|
| 234 |
+
"learning_rate": 1.4553611099167278e-05,
|
| 235 |
+
"loss": 0.8578,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.84,
|
| 240 |
+
"learning_rate": 1.4410285075461153e-05,
|
| 241 |
+
"loss": 0.8549,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.86,
|
| 246 |
+
"learning_rate": 1.426695905175503e-05,
|
| 247 |
+
"loss": 0.8492,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.88,
|
| 252 |
+
"learning_rate": 1.4123633028048905e-05,
|
| 253 |
+
"loss": 0.8511,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9,
|
| 258 |
+
"learning_rate": 1.3980307004342778e-05,
|
| 259 |
+
"loss": 0.8457,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.92,
|
| 264 |
+
"learning_rate": 1.3836980980636657e-05,
|
| 265 |
+
"loss": 0.8395,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.95,
|
| 270 |
+
"learning_rate": 1.369365495693053e-05,
|
| 271 |
+
"loss": 0.8439,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.97,
|
| 276 |
+
"learning_rate": 1.3550328933224406e-05,
|
| 277 |
+
"loss": 0.8396,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.99,
|
| 282 |
+
"learning_rate": 1.3407002909518283e-05,
|
| 283 |
+
"loss": 0.8333,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.0,
|
| 288 |
+
"eval_accuracy": 58.430973000509425,
|
| 289 |
+
"eval_combined_score": 58.430973000509425,
|
| 290 |
+
"eval_loss": 0.9210277795791626,
|
| 291 |
+
"eval_runtime": 5.4726,
|
| 292 |
+
"eval_samples_per_second": 1793.494,
|
| 293 |
+
"eval_steps_per_second": 7.126,
|
| 294 |
+
"step": 23257
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.01,
|
| 298 |
+
"learning_rate": 1.3263676885812158e-05,
|
| 299 |
+
"loss": 0.8316,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.03,
|
| 304 |
+
"learning_rate": 1.3120350862106033e-05,
|
| 305 |
+
"loss": 0.8371,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.05,
|
| 310 |
+
"learning_rate": 1.297702483839991e-05,
|
| 311 |
+
"loss": 0.8256,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.07,
|
| 316 |
+
"learning_rate": 1.2833698814693785e-05,
|
| 317 |
+
"loss": 0.8267,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1,
|
| 322 |
+
"learning_rate": 1.2690372790987662e-05,
|
| 323 |
+
"loss": 0.8207,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.12,
|
| 328 |
+
"learning_rate": 1.2547046767281537e-05,
|
| 329 |
+
"loss": 0.8202,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.14,
|
| 334 |
+
"learning_rate": 1.2403720743575412e-05,
|
| 335 |
+
"loss": 0.8253,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.16,
|
| 340 |
+
"learning_rate": 1.2260394719869289e-05,
|
| 341 |
+
"loss": 0.8129,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.18,
|
| 346 |
+
"learning_rate": 1.2117068696163163e-05,
|
| 347 |
+
"loss": 0.8134,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.2,
|
| 352 |
+
"learning_rate": 1.1973742672457038e-05,
|
| 353 |
+
"loss": 0.8079,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.23,
|
| 358 |
+
"learning_rate": 1.1830416648750915e-05,
|
| 359 |
+
"loss": 0.7972,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.25,
|
| 364 |
+
"learning_rate": 1.168709062504479e-05,
|
| 365 |
+
"loss": 0.8175,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.27,
|
| 370 |
+
"learning_rate": 1.1543764601338665e-05,
|
| 371 |
+
"loss": 0.8103,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.29,
|
| 376 |
+
"learning_rate": 1.1400438577632542e-05,
|
| 377 |
+
"loss": 0.8058,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.31,
|
| 382 |
+
"learning_rate": 1.1257112553926417e-05,
|
| 383 |
+
"loss": 0.7969,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.33,
|
| 388 |
+
"learning_rate": 1.1113786530220294e-05,
|
| 389 |
+
"loss": 0.8145,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.35,
|
| 394 |
+
"learning_rate": 1.097046050651417e-05,
|
| 395 |
+
"loss": 0.8072,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.38,
|
| 400 |
+
"learning_rate": 1.0827134482808044e-05,
|
| 401 |
+
"loss": 0.7985,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4,
|
| 406 |
+
"learning_rate": 1.0683808459101921e-05,
|
| 407 |
+
"loss": 0.8077,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.42,
|
| 412 |
+
"learning_rate": 1.0540482435395797e-05,
|
| 413 |
+
"loss": 0.7866,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.44,
|
| 418 |
+
"learning_rate": 1.039715641168967e-05,
|
| 419 |
+
"loss": 0.7917,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.46,
|
| 424 |
+
"learning_rate": 1.0253830387983547e-05,
|
| 425 |
+
"loss": 0.803,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.48,
|
| 430 |
+
"learning_rate": 1.0110504364277422e-05,
|
| 431 |
+
"loss": 0.7915,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.5,
|
| 436 |
+
"learning_rate": 9.967178340571299e-06,
|
| 437 |
+
"loss": 0.796,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.53,
|
| 442 |
+
"learning_rate": 9.823852316865174e-06,
|
| 443 |
+
"loss": 0.7903,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.55,
|
| 448 |
+
"learning_rate": 9.68052629315905e-06,
|
| 449 |
+
"loss": 0.7946,
|
| 450 |
+
"step": 36000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.57,
|
| 454 |
+
"learning_rate": 9.537200269452925e-06,
|
| 455 |
+
"loss": 0.7922,
|
| 456 |
+
"step": 36500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.59,
|
| 460 |
+
"learning_rate": 9.393874245746801e-06,
|
| 461 |
+
"loss": 0.7843,
|
| 462 |
+
"step": 37000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.61,
|
| 466 |
+
"learning_rate": 9.250548222040677e-06,
|
| 467 |
+
"loss": 0.7828,
|
| 468 |
+
"step": 37500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.63,
|
| 472 |
+
"learning_rate": 9.107222198334552e-06,
|
| 473 |
+
"loss": 0.7869,
|
| 474 |
+
"step": 38000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.66,
|
| 478 |
+
"learning_rate": 8.963896174628429e-06,
|
| 479 |
+
"loss": 0.7852,
|
| 480 |
+
"step": 38500
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.68,
|
| 484 |
+
"learning_rate": 8.820570150922304e-06,
|
| 485 |
+
"loss": 0.7818,
|
| 486 |
+
"step": 39000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7,
|
| 490 |
+
"learning_rate": 8.677244127216179e-06,
|
| 491 |
+
"loss": 0.7865,
|
| 492 |
+
"step": 39500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.72,
|
| 496 |
+
"learning_rate": 8.533918103510054e-06,
|
| 497 |
+
"loss": 0.7753,
|
| 498 |
+
"step": 40000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.74,
|
| 502 |
+
"learning_rate": 8.390592079803931e-06,
|
| 503 |
+
"loss": 0.7828,
|
| 504 |
+
"step": 40500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.76,
|
| 508 |
+
"learning_rate": 8.247266056097806e-06,
|
| 509 |
+
"loss": 0.776,
|
| 510 |
+
"step": 41000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.78,
|
| 514 |
+
"learning_rate": 8.103940032391682e-06,
|
| 515 |
+
"loss": 0.7762,
|
| 516 |
+
"step": 41500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.81,
|
| 520 |
+
"learning_rate": 7.960614008685558e-06,
|
| 521 |
+
"loss": 0.7881,
|
| 522 |
+
"step": 42000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.83,
|
| 526 |
+
"learning_rate": 7.817287984979434e-06,
|
| 527 |
+
"loss": 0.7836,
|
| 528 |
+
"step": 42500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.85,
|
| 532 |
+
"learning_rate": 7.673961961273309e-06,
|
| 533 |
+
"loss": 0.7757,
|
| 534 |
+
"step": 43000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.87,
|
| 538 |
+
"learning_rate": 7.530635937567185e-06,
|
| 539 |
+
"loss": 0.7645,
|
| 540 |
+
"step": 43500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.89,
|
| 544 |
+
"learning_rate": 7.38730991386106e-06,
|
| 545 |
+
"loss": 0.7721,
|
| 546 |
+
"step": 44000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.91,
|
| 550 |
+
"learning_rate": 7.243983890154936e-06,
|
| 551 |
+
"loss": 0.7725,
|
| 552 |
+
"step": 44500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.93,
|
| 556 |
+
"learning_rate": 7.100657866448811e-06,
|
| 557 |
+
"loss": 0.7741,
|
| 558 |
+
"step": 45000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.96,
|
| 562 |
+
"learning_rate": 6.957331842742687e-06,
|
| 563 |
+
"loss": 0.7829,
|
| 564 |
+
"step": 45500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.98,
|
| 568 |
+
"learning_rate": 6.814005819036563e-06,
|
| 569 |
+
"loss": 0.7746,
|
| 570 |
+
"step": 46000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0,
|
| 574 |
+
"learning_rate": 6.670679795330439e-06,
|
| 575 |
+
"loss": 0.7685,
|
| 576 |
+
"step": 46500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.0,
|
| 580 |
+
"eval_accuracy": 61.29393785022924,
|
| 581 |
+
"eval_combined_score": 61.29393785022924,
|
| 582 |
+
"eval_loss": 0.8761915564537048,
|
| 583 |
+
"eval_runtime": 5.5218,
|
| 584 |
+
"eval_samples_per_second": 1777.495,
|
| 585 |
+
"eval_steps_per_second": 7.063,
|
| 586 |
+
"step": 46514
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.02,
|
| 590 |
+
"learning_rate": 6.527353771624314e-06,
|
| 591 |
+
"loss": 0.7637,
|
| 592 |
+
"step": 47000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.04,
|
| 596 |
+
"learning_rate": 6.38402774791819e-06,
|
| 597 |
+
"loss": 0.755,
|
| 598 |
+
"step": 47500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.06,
|
| 602 |
+
"learning_rate": 6.240701724212066e-06,
|
| 603 |
+
"loss": 0.7487,
|
| 604 |
+
"step": 48000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.09,
|
| 608 |
+
"learning_rate": 6.097375700505941e-06,
|
| 609 |
+
"loss": 0.7652,
|
| 610 |
+
"step": 48500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.11,
|
| 614 |
+
"learning_rate": 5.954049676799817e-06,
|
| 615 |
+
"loss": 0.7661,
|
| 616 |
+
"step": 49000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.13,
|
| 620 |
+
"learning_rate": 5.810723653093693e-06,
|
| 621 |
+
"loss": 0.748,
|
| 622 |
+
"step": 49500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.15,
|
| 626 |
+
"learning_rate": 5.667397629387569e-06,
|
| 627 |
+
"loss": 0.7651,
|
| 628 |
+
"step": 50000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.17,
|
| 632 |
+
"learning_rate": 5.5240716056814435e-06,
|
| 633 |
+
"loss": 0.7529,
|
| 634 |
+
"step": 50500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.19,
|
| 638 |
+
"learning_rate": 5.3807455819753195e-06,
|
| 639 |
+
"loss": 0.7579,
|
| 640 |
+
"step": 51000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.21,
|
| 644 |
+
"learning_rate": 5.237419558269196e-06,
|
| 645 |
+
"loss": 0.756,
|
| 646 |
+
"step": 51500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.24,
|
| 650 |
+
"learning_rate": 5.094093534563072e-06,
|
| 651 |
+
"loss": 0.7665,
|
| 652 |
+
"step": 52000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.26,
|
| 656 |
+
"learning_rate": 4.950767510856947e-06,
|
| 657 |
+
"loss": 0.7613,
|
| 658 |
+
"step": 52500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.28,
|
| 662 |
+
"learning_rate": 4.807441487150822e-06,
|
| 663 |
+
"loss": 0.7516,
|
| 664 |
+
"step": 53000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.3,
|
| 668 |
+
"learning_rate": 4.664115463444698e-06,
|
| 669 |
+
"loss": 0.7505,
|
| 670 |
+
"step": 53500
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.32,
|
| 674 |
+
"learning_rate": 4.520789439738574e-06,
|
| 675 |
+
"loss": 0.7423,
|
| 676 |
+
"step": 54000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.34,
|
| 680 |
+
"learning_rate": 4.377463416032449e-06,
|
| 681 |
+
"loss": 0.7586,
|
| 682 |
+
"step": 54500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.36,
|
| 686 |
+
"learning_rate": 4.234137392326325e-06,
|
| 687 |
+
"loss": 0.7452,
|
| 688 |
+
"step": 55000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.39,
|
| 692 |
+
"learning_rate": 4.0908113686202005e-06,
|
| 693 |
+
"loss": 0.7536,
|
| 694 |
+
"step": 55500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.41,
|
| 698 |
+
"learning_rate": 3.9474853449140765e-06,
|
| 699 |
+
"loss": 0.7465,
|
| 700 |
+
"step": 56000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.43,
|
| 704 |
+
"learning_rate": 3.8041593212079517e-06,
|
| 705 |
+
"loss": 0.7481,
|
| 706 |
+
"step": 56500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.45,
|
| 710 |
+
"learning_rate": 3.6608332975018278e-06,
|
| 711 |
+
"loss": 0.7473,
|
| 712 |
+
"step": 57000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.47,
|
| 716 |
+
"learning_rate": 3.5175072737957034e-06,
|
| 717 |
+
"loss": 0.7572,
|
| 718 |
+
"step": 57500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.49,
|
| 722 |
+
"learning_rate": 3.3741812500895794e-06,
|
| 723 |
+
"loss": 0.7476,
|
| 724 |
+
"step": 58000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.52,
|
| 728 |
+
"learning_rate": 3.2308552263834546e-06,
|
| 729 |
+
"loss": 0.7564,
|
| 730 |
+
"step": 58500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.54,
|
| 734 |
+
"learning_rate": 3.0875292026773302e-06,
|
| 735 |
+
"loss": 0.7488,
|
| 736 |
+
"step": 59000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.56,
|
| 740 |
+
"learning_rate": 2.9442031789712063e-06,
|
| 741 |
+
"loss": 0.7495,
|
| 742 |
+
"step": 59500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.58,
|
| 746 |
+
"learning_rate": 2.8008771552650815e-06,
|
| 747 |
+
"loss": 0.7481,
|
| 748 |
+
"step": 60000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.6,
|
| 752 |
+
"learning_rate": 2.6575511315589575e-06,
|
| 753 |
+
"loss": 0.7429,
|
| 754 |
+
"step": 60500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.62,
|
| 758 |
+
"learning_rate": 2.5142251078528327e-06,
|
| 759 |
+
"loss": 0.748,
|
| 760 |
+
"step": 61000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.64,
|
| 764 |
+
"learning_rate": 2.3708990841467087e-06,
|
| 765 |
+
"loss": 0.7483,
|
| 766 |
+
"step": 61500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.67,
|
| 770 |
+
"learning_rate": 2.2275730604405844e-06,
|
| 771 |
+
"loss": 0.7496,
|
| 772 |
+
"step": 62000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.69,
|
| 776 |
+
"learning_rate": 2.08424703673446e-06,
|
| 777 |
+
"loss": 0.7451,
|
| 778 |
+
"step": 62500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.71,
|
| 782 |
+
"learning_rate": 1.9409210130283356e-06,
|
| 783 |
+
"loss": 0.7466,
|
| 784 |
+
"step": 63000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.73,
|
| 788 |
+
"learning_rate": 1.7975949893222114e-06,
|
| 789 |
+
"loss": 0.7425,
|
| 790 |
+
"step": 63500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.75,
|
| 794 |
+
"learning_rate": 1.654268965616087e-06,
|
| 795 |
+
"loss": 0.7525,
|
| 796 |
+
"step": 64000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.77,
|
| 800 |
+
"learning_rate": 1.5109429419099629e-06,
|
| 801 |
+
"loss": 0.7459,
|
| 802 |
+
"step": 64500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.79,
|
| 806 |
+
"learning_rate": 1.3676169182038385e-06,
|
| 807 |
+
"loss": 0.7492,
|
| 808 |
+
"step": 65000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.82,
|
| 812 |
+
"learning_rate": 1.224290894497714e-06,
|
| 813 |
+
"loss": 0.7443,
|
| 814 |
+
"step": 65500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.84,
|
| 818 |
+
"learning_rate": 1.0809648707915897e-06,
|
| 819 |
+
"loss": 0.7508,
|
| 820 |
+
"step": 66000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.86,
|
| 824 |
+
"learning_rate": 9.376388470854654e-07,
|
| 825 |
+
"loss": 0.7421,
|
| 826 |
+
"step": 66500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.88,
|
| 830 |
+
"learning_rate": 7.94312823379341e-07,
|
| 831 |
+
"loss": 0.7547,
|
| 832 |
+
"step": 67000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.9,
|
| 836 |
+
"learning_rate": 6.509867996732167e-07,
|
| 837 |
+
"loss": 0.7373,
|
| 838 |
+
"step": 67500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.92,
|
| 842 |
+
"learning_rate": 5.076607759670924e-07,
|
| 843 |
+
"loss": 0.7474,
|
| 844 |
+
"step": 68000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.95,
|
| 848 |
+
"learning_rate": 3.6433475226096806e-07,
|
| 849 |
+
"loss": 0.7405,
|
| 850 |
+
"step": 68500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.97,
|
| 854 |
+
"learning_rate": 2.2100872855484373e-07,
|
| 855 |
+
"loss": 0.7406,
|
| 856 |
+
"step": 69000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.99,
|
| 860 |
+
"learning_rate": 7.76827048487194e-08,
|
| 861 |
+
"loss": 0.7424,
|
| 862 |
+
"step": 69500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.0,
|
| 866 |
+
"eval_accuracy": 61.73204279164543,
|
| 867 |
+
"eval_combined_score": 61.73204279164543,
|
| 868 |
+
"eval_loss": 0.8748815059661865,
|
| 869 |
+
"eval_runtime": 5.4694,
|
| 870 |
+
"eval_samples_per_second": 1794.527,
|
| 871 |
+
"eval_steps_per_second": 7.131,
|
| 872 |
+
"step": 69771
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.0,
|
| 876 |
+
"step": 69771,
|
| 877 |
+
"total_flos": 1418687059046400.0,
|
| 878 |
+
"train_loss": 0.8166523379133837,
|
| 879 |
+
"train_runtime": 2409.4346,
|
| 880 |
+
"train_samples_per_second": 926.607,
|
| 881 |
+
"train_steps_per_second": 28.957
|
| 882 |
+
}
|
| 883 |
+
],
|
| 884 |
+
"max_steps": 69771,
|
| 885 |
+
"num_train_epochs": 3,
|
| 886 |
+
"total_flos": 1418687059046400.0,
|
| 887 |
+
"trial_name": null,
|
| 888 |
+
"trial_params": null
|
| 889 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8fc5edce1ac660cb698c50f06bb29a4acbd2fe88ba4c7b1aea25fdddf7d578a
|
| 3 |
+
size 4091
|
transfer_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.5824019508230035,
|
| 3 |
+
"eval_combined_score": 0.5824019508230035,
|
| 4 |
+
"eval_loss": 0.9483514428138733,
|
| 5 |
+
"eval_runtime": 1.9985,
|
| 6 |
+
"eval_samples_per_second": 4924.636,
|
| 7 |
+
"eval_steps_per_second": 19.514
|
| 8 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|