First commit: basic config files and ONNX models
Browse files- config.json +88 -0
- merges.txt +0 -0
- onnx/config.json +87 -0
- onnx/merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/ort_config.json +38 -0
- onnx/ort_config_quantized.json +35 -0
- onnx/special_tokens_map.json +15 -0
- onnx/tokenizer.json +0 -0
- onnx/tokenizer_config.json +22 -0
- onnx/vocab.json +0 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +241 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "admiration",
|
| 15 |
+
"1": "amusement",
|
| 16 |
+
"2": "anger",
|
| 17 |
+
"3": "annoyance",
|
| 18 |
+
"4": "approval",
|
| 19 |
+
"5": "caring",
|
| 20 |
+
"6": "confusion",
|
| 21 |
+
"7": "curiosity",
|
| 22 |
+
"8": "desire",
|
| 23 |
+
"9": "disappointment",
|
| 24 |
+
"10": "disapproval",
|
| 25 |
+
"11": "disgust",
|
| 26 |
+
"12": "embarrassment",
|
| 27 |
+
"13": "excitement",
|
| 28 |
+
"14": "fear",
|
| 29 |
+
"15": "gratitude",
|
| 30 |
+
"16": "grief",
|
| 31 |
+
"17": "joy",
|
| 32 |
+
"18": "love",
|
| 33 |
+
"19": "nervousness",
|
| 34 |
+
"20": "optimism",
|
| 35 |
+
"21": "pride",
|
| 36 |
+
"22": "realization",
|
| 37 |
+
"23": "relief",
|
| 38 |
+
"24": "remorse",
|
| 39 |
+
"25": "sadness",
|
| 40 |
+
"26": "surprise",
|
| 41 |
+
"27": "neutral"
|
| 42 |
+
},
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 3072,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"admiration": 0,
|
| 47 |
+
"amusement": 1,
|
| 48 |
+
"anger": 2,
|
| 49 |
+
"annoyance": 3,
|
| 50 |
+
"approval": 4,
|
| 51 |
+
"caring": 5,
|
| 52 |
+
"confusion": 6,
|
| 53 |
+
"curiosity": 7,
|
| 54 |
+
"desire": 8,
|
| 55 |
+
"disappointment": 9,
|
| 56 |
+
"disapproval": 10,
|
| 57 |
+
"disgust": 11,
|
| 58 |
+
"embarrassment": 12,
|
| 59 |
+
"excitement": 13,
|
| 60 |
+
"fear": 14,
|
| 61 |
+
"gratitude": 15,
|
| 62 |
+
"grief": 16,
|
| 63 |
+
"joy": 17,
|
| 64 |
+
"love": 18,
|
| 65 |
+
"nervousness": 19,
|
| 66 |
+
"neutral": 27,
|
| 67 |
+
"optimism": 20,
|
| 68 |
+
"pride": 21,
|
| 69 |
+
"realization": 22,
|
| 70 |
+
"relief": 23,
|
| 71 |
+
"remorse": 24,
|
| 72 |
+
"sadness": 25,
|
| 73 |
+
"surprise": 26
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"max_position_embeddings": 514,
|
| 77 |
+
"model_type": "roberta",
|
| 78 |
+
"num_attention_heads": 12,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"pad_token_id": 1,
|
| 81 |
+
"position_embedding_type": "absolute",
|
| 82 |
+
"problem_type": "multi_label_classification",
|
| 83 |
+
"torch_dtype": "float32",
|
| 84 |
+
"transformers_version": "4.21.3",
|
| 85 |
+
"type_vocab_size": 1,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/config.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "onnx",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "admiration",
|
| 15 |
+
"1": "amusement",
|
| 16 |
+
"2": "anger",
|
| 17 |
+
"3": "annoyance",
|
| 18 |
+
"4": "approval",
|
| 19 |
+
"5": "caring",
|
| 20 |
+
"6": "confusion",
|
| 21 |
+
"7": "curiosity",
|
| 22 |
+
"8": "desire",
|
| 23 |
+
"9": "disappointment",
|
| 24 |
+
"10": "disapproval",
|
| 25 |
+
"11": "disgust",
|
| 26 |
+
"12": "embarrassment",
|
| 27 |
+
"13": "excitement",
|
| 28 |
+
"14": "fear",
|
| 29 |
+
"15": "gratitude",
|
| 30 |
+
"16": "grief",
|
| 31 |
+
"17": "joy",
|
| 32 |
+
"18": "love",
|
| 33 |
+
"19": "nervousness",
|
| 34 |
+
"20": "optimism",
|
| 35 |
+
"21": "pride",
|
| 36 |
+
"22": "realization",
|
| 37 |
+
"23": "relief",
|
| 38 |
+
"24": "remorse",
|
| 39 |
+
"25": "sadness",
|
| 40 |
+
"26": "surprise",
|
| 41 |
+
"27": "neutral"
|
| 42 |
+
},
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 3072,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"admiration": 0,
|
| 47 |
+
"amusement": 1,
|
| 48 |
+
"anger": 2,
|
| 49 |
+
"annoyance": 3,
|
| 50 |
+
"approval": 4,
|
| 51 |
+
"caring": 5,
|
| 52 |
+
"confusion": 6,
|
| 53 |
+
"curiosity": 7,
|
| 54 |
+
"desire": 8,
|
| 55 |
+
"disappointment": 9,
|
| 56 |
+
"disapproval": 10,
|
| 57 |
+
"disgust": 11,
|
| 58 |
+
"embarrassment": 12,
|
| 59 |
+
"excitement": 13,
|
| 60 |
+
"fear": 14,
|
| 61 |
+
"gratitude": 15,
|
| 62 |
+
"grief": 16,
|
| 63 |
+
"joy": 17,
|
| 64 |
+
"love": 18,
|
| 65 |
+
"nervousness": 19,
|
| 66 |
+
"neutral": 27,
|
| 67 |
+
"optimism": 20,
|
| 68 |
+
"pride": 21,
|
| 69 |
+
"realization": 22,
|
| 70 |
+
"relief": 23,
|
| 71 |
+
"remorse": 24,
|
| 72 |
+
"sadness": 25,
|
| 73 |
+
"surprise": 26
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"max_position_embeddings": 514,
|
| 77 |
+
"model_type": "roberta",
|
| 78 |
+
"num_attention_heads": 12,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"pad_token_id": 1,
|
| 81 |
+
"position_embedding_type": "absolute",
|
| 82 |
+
"problem_type": "multi_label_classification",
|
| 83 |
+
"transformers_version": "4.33.2",
|
| 84 |
+
"type_vocab_size": 1,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"vocab_size": 50265
|
| 87 |
+
}
|
onnx/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bf605adfa0e59ae36723f1136d37865acb0ec4ded7831f7f7f5231eb032d60a
|
| 3 |
+
size 498841248
|
onnx/model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c1981c5b479674747911c8e2228f0c4ec90bf47bf66e830f7d4fc62be082958
|
| 3 |
+
size 125397543
|
onnx/ort_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {
|
| 5 |
+
"disable_attention": null,
|
| 6 |
+
"disable_attention_fusion": false,
|
| 7 |
+
"disable_bias_gelu": null,
|
| 8 |
+
"disable_bias_gelu_fusion": false,
|
| 9 |
+
"disable_bias_skip_layer_norm": null,
|
| 10 |
+
"disable_bias_skip_layer_norm_fusion": false,
|
| 11 |
+
"disable_embed_layer_norm": true,
|
| 12 |
+
"disable_embed_layer_norm_fusion": true,
|
| 13 |
+
"disable_gelu": null,
|
| 14 |
+
"disable_gelu_fusion": false,
|
| 15 |
+
"disable_group_norm_fusion": true,
|
| 16 |
+
"disable_layer_norm": null,
|
| 17 |
+
"disable_layer_norm_fusion": false,
|
| 18 |
+
"disable_packed_kv": true,
|
| 19 |
+
"disable_shape_inference": true,
|
| 20 |
+
"disable_skip_layer_norm": null,
|
| 21 |
+
"disable_skip_layer_norm_fusion": false,
|
| 22 |
+
"enable_gelu_approximation": false,
|
| 23 |
+
"enable_gemm_fast_gelu_fusion": false,
|
| 24 |
+
"enable_transformers_specific_optimizations": false,
|
| 25 |
+
"fp16": false,
|
| 26 |
+
"no_attention_mask": false,
|
| 27 |
+
"optimization_level": 1,
|
| 28 |
+
"optimize_for_gpu": false,
|
| 29 |
+
"optimize_with_onnxruntime_only": null,
|
| 30 |
+
"use_mask_index": false,
|
| 31 |
+
"use_multi_head_attention": false,
|
| 32 |
+
"use_raw_attention_mask": false
|
| 33 |
+
},
|
| 34 |
+
"optimum_version": "1.13.2",
|
| 35 |
+
"quantization": {},
|
| 36 |
+
"transformers_version": "4.33.2",
|
| 37 |
+
"use_external_data_format": false
|
| 38 |
+
}
|
onnx/ort_config_quantized.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {},
|
| 5 |
+
"optimum_version": "1.13.2",
|
| 6 |
+
"quantization": {
|
| 7 |
+
"activations_dtype": "QUInt8",
|
| 8 |
+
"activations_symmetric": false,
|
| 9 |
+
"format": "QOperator",
|
| 10 |
+
"is_static": false,
|
| 11 |
+
"mode": "IntegerOps",
|
| 12 |
+
"nodes_to_exclude": [],
|
| 13 |
+
"nodes_to_quantize": [],
|
| 14 |
+
"operators_to_quantize": [
|
| 15 |
+
"Conv",
|
| 16 |
+
"MatMul",
|
| 17 |
+
"Attention",
|
| 18 |
+
"LSTM",
|
| 19 |
+
"Gather",
|
| 20 |
+
"Transpose",
|
| 21 |
+
"EmbedLayerNormalization"
|
| 22 |
+
],
|
| 23 |
+
"per_channel": false,
|
| 24 |
+
"qdq_add_pair_to_weight": false,
|
| 25 |
+
"qdq_dedicated_pair": false,
|
| 26 |
+
"qdq_op_type_per_channel_support_to_axis": {
|
| 27 |
+
"MatMul": 1
|
| 28 |
+
},
|
| 29 |
+
"reduce_range": false,
|
| 30 |
+
"weights_dtype": "QUInt8",
|
| 31 |
+
"weights_symmetric": true
|
| 32 |
+
},
|
| 33 |
+
"transformers_version": "4.33.2",
|
| 34 |
+
"use_external_data_format": false
|
| 35 |
+
}
|
onnx/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
onnx/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"max_length": 128,
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"pad_to_multiple_of": null,
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"pad_token_type_id": 0,
|
| 14 |
+
"padding_side": "right",
|
| 15 |
+
"sep_token": "</s>",
|
| 16 |
+
"stride": 0,
|
| 17 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 18 |
+
"trim_offsets": true,
|
| 19 |
+
"truncation_side": "right",
|
| 20 |
+
"truncation_strategy": "longest_first",
|
| 21 |
+
"unk_token": "<unk>"
|
| 22 |
+
}
|
onnx/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
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 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "roberta-base",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5862595419847328,
|
| 3 |
+
"best_model_checkpoint": "roberta-base-go_emotions/checkpoint-16281",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 16281,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.9815736134144095e-05,
|
| 13 |
+
"loss": 0.1826,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 1.963147226828819e-05,
|
| 19 |
+
"loss": 0.1317,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.28,
|
| 24 |
+
"learning_rate": 1.9447208402432286e-05,
|
| 25 |
+
"loss": 0.1146,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.37,
|
| 30 |
+
"learning_rate": 1.9262944536576377e-05,
|
| 31 |
+
"loss": 0.1078,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.46,
|
| 36 |
+
"learning_rate": 1.9078680670720474e-05,
|
| 37 |
+
"loss": 0.1006,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.55,
|
| 42 |
+
"learning_rate": 1.8894416804864568e-05,
|
| 43 |
+
"loss": 0.0976,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.64,
|
| 48 |
+
"learning_rate": 1.871015293900866e-05,
|
| 49 |
+
"loss": 0.096,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.74,
|
| 54 |
+
"learning_rate": 1.8525889073152755e-05,
|
| 55 |
+
"loss": 0.0925,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.83,
|
| 60 |
+
"learning_rate": 1.8341625207296852e-05,
|
| 61 |
+
"loss": 0.0921,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.92,
|
| 66 |
+
"learning_rate": 1.8157361341440943e-05,
|
| 67 |
+
"loss": 0.0911,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_accuracy": 0.40213785477331365,
|
| 73 |
+
"eval_f1": 0.5346146303196705,
|
| 74 |
+
"eval_loss": 0.08816272765398026,
|
| 75 |
+
"eval_roc_auc": 0.7098850238721621,
|
| 76 |
+
"eval_runtime": 11.8306,
|
| 77 |
+
"eval_samples_per_second": 458.641,
|
| 78 |
+
"eval_steps_per_second": 57.394,
|
| 79 |
+
"step": 5427
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.01,
|
| 83 |
+
"learning_rate": 1.797309747558504e-05,
|
| 84 |
+
"loss": 0.0897,
|
| 85 |
+
"step": 5500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.11,
|
| 89 |
+
"learning_rate": 1.7788833609729134e-05,
|
| 90 |
+
"loss": 0.0856,
|
| 91 |
+
"step": 6000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 1.7604569743873227e-05,
|
| 96 |
+
"loss": 0.0816,
|
| 97 |
+
"step": 6500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.29,
|
| 101 |
+
"learning_rate": 1.742030587801732e-05,
|
| 102 |
+
"loss": 0.0853,
|
| 103 |
+
"step": 7000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.38,
|
| 107 |
+
"learning_rate": 1.7236042012161415e-05,
|
| 108 |
+
"loss": 0.0846,
|
| 109 |
+
"step": 7500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.47,
|
| 113 |
+
"learning_rate": 1.7051778146305512e-05,
|
| 114 |
+
"loss": 0.0843,
|
| 115 |
+
"step": 8000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.57,
|
| 119 |
+
"learning_rate": 1.6867514280449606e-05,
|
| 120 |
+
"loss": 0.0807,
|
| 121 |
+
"step": 8500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.66,
|
| 125 |
+
"learning_rate": 1.66832504145937e-05,
|
| 126 |
+
"loss": 0.0796,
|
| 127 |
+
"step": 9000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.75,
|
| 131 |
+
"learning_rate": 1.6498986548737793e-05,
|
| 132 |
+
"loss": 0.081,
|
| 133 |
+
"step": 9500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.84,
|
| 137 |
+
"learning_rate": 1.6314722682881887e-05,
|
| 138 |
+
"loss": 0.0798,
|
| 139 |
+
"step": 10000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.93,
|
| 143 |
+
"learning_rate": 1.613045881702598e-05,
|
| 144 |
+
"loss": 0.0821,
|
| 145 |
+
"step": 10500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0,
|
| 149 |
+
"eval_accuracy": 0.44010320678216,
|
| 150 |
+
"eval_f1": 0.5612426312342098,
|
| 151 |
+
"eval_loss": 0.08432479202747345,
|
| 152 |
+
"eval_roc_auc": 0.7305379849481191,
|
| 153 |
+
"eval_runtime": 11.8056,
|
| 154 |
+
"eval_samples_per_second": 459.613,
|
| 155 |
+
"eval_steps_per_second": 57.515,
|
| 156 |
+
"step": 10854
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.03,
|
| 160 |
+
"learning_rate": 1.5946194951170078e-05,
|
| 161 |
+
"loss": 0.0776,
|
| 162 |
+
"step": 11000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.12,
|
| 166 |
+
"learning_rate": 1.5761931085314172e-05,
|
| 167 |
+
"loss": 0.0726,
|
| 168 |
+
"step": 11500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.21,
|
| 172 |
+
"learning_rate": 1.5577667219458266e-05,
|
| 173 |
+
"loss": 0.0718,
|
| 174 |
+
"step": 12000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.3,
|
| 178 |
+
"learning_rate": 1.539340335360236e-05,
|
| 179 |
+
"loss": 0.0735,
|
| 180 |
+
"step": 12500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.4,
|
| 184 |
+
"learning_rate": 1.5209139487746453e-05,
|
| 185 |
+
"loss": 0.0735,
|
| 186 |
+
"step": 13000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.49,
|
| 190 |
+
"learning_rate": 1.5024875621890549e-05,
|
| 191 |
+
"loss": 0.0721,
|
| 192 |
+
"step": 13500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.58,
|
| 196 |
+
"learning_rate": 1.4840611756034643e-05,
|
| 197 |
+
"loss": 0.0722,
|
| 198 |
+
"step": 14000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.67,
|
| 202 |
+
"learning_rate": 1.4656347890178736e-05,
|
| 203 |
+
"loss": 0.0751,
|
| 204 |
+
"step": 14500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.76,
|
| 208 |
+
"learning_rate": 1.4472084024322832e-05,
|
| 209 |
+
"loss": 0.0727,
|
| 210 |
+
"step": 15000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.86,
|
| 214 |
+
"learning_rate": 1.4287820158466926e-05,
|
| 215 |
+
"loss": 0.0735,
|
| 216 |
+
"step": 15500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.95,
|
| 220 |
+
"learning_rate": 1.4103556292611021e-05,
|
| 221 |
+
"loss": 0.0714,
|
| 222 |
+
"step": 16000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.0,
|
| 226 |
+
"eval_accuracy": 0.47475119793586434,
|
| 227 |
+
"eval_f1": 0.5862595419847328,
|
| 228 |
+
"eval_loss": 0.0838962271809578,
|
| 229 |
+
"eval_roc_auc": 0.7506773514396311,
|
| 230 |
+
"eval_runtime": 11.8261,
|
| 231 |
+
"eval_samples_per_second": 458.814,
|
| 232 |
+
"eval_steps_per_second": 57.415,
|
| 233 |
+
"step": 16281
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"max_steps": 54270,
|
| 237 |
+
"num_train_epochs": 10,
|
| 238 |
+
"total_flos": 8568237917583360.0,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": null
|
| 241 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|