Training in progress, epoch 5, checkpoint
Browse files- checkpoint-46510/config.json +38 -0
- checkpoint-46510/merges.txt +0 -0
- checkpoint-46510/model.safetensors +3 -0
- checkpoint-46510/optimizer.pt +3 -0
- checkpoint-46510/rng_state.pth +3 -0
- checkpoint-46510/scheduler.pt +3 -0
- checkpoint-46510/special_tokens_map.json +15 -0
- checkpoint-46510/tokenizer.json +0 -0
- checkpoint-46510/tokenizer_config.json +57 -0
- checkpoint-46510/trainer_state.json +128 -0
- checkpoint-46510/training_args.bin +3 -0
- checkpoint-46510/vocab.json +0 -0
checkpoint-46510/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.42.3",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50265
|
38 |
+
}
|
checkpoint-46510/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-46510/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aca94eb741cc45f3f3ede9174fc0265171f523bdb239e4f894367a36453c2db
|
3 |
+
size 498615900
|
checkpoint-46510/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6abb2c0e199976e392a2653713a5ed01626344270f56ab229cc1326ab04b01
|
3 |
+
size 997351674
|
checkpoint-46510/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdfd5dc4f28b63451fe2dfb78bf1cb37cc6afcab1fb3f83df512caaf03f97e5f
|
3 |
+
size 14244
|
checkpoint-46510/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6f0c422a02f583b13d590af36609795de4d7cf948f6903ace120c8efdfd97b4
|
3 |
+
size 1064
|
checkpoint-46510/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 |
+
}
|
checkpoint-46510/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-46510/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
checkpoint-46510/trainer_state.json
ADDED
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.528473834809328,
|
3 |
+
"best_model_checkpoint": "training_dir-augmented\\checkpoint-46510",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 46510,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 0.9803293943405151,
|
14 |
+
"learning_rate": 8.086937622256031e-06,
|
15 |
+
"loss": 0.5312,
|
16 |
+
"step": 9302
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.40428321678321677,
|
21 |
+
"eval_f1": 0.3406020494510067,
|
22 |
+
"eval_loss": 3.0353851318359375,
|
23 |
+
"eval_precision": 0.6901256632128517,
|
24 |
+
"eval_recall": 0.40428321678321677,
|
25 |
+
"eval_runtime": 16.0409,
|
26 |
+
"eval_samples_per_second": 142.636,
|
27 |
+
"eval_steps_per_second": 17.829,
|
28 |
+
"step": 9302
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 196.54563903808594,
|
33 |
+
"learning_rate": 6.065203216692024e-06,
|
34 |
+
"loss": 0.3949,
|
35 |
+
"step": 18604
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.527972027972028,
|
40 |
+
"eval_f1": 0.526961176646401,
|
41 |
+
"eval_loss": 2.4327211380004883,
|
42 |
+
"eval_precision": 0.6358079986576912,
|
43 |
+
"eval_recall": 0.527972027972028,
|
44 |
+
"eval_runtime": 16.8165,
|
45 |
+
"eval_samples_per_second": 136.057,
|
46 |
+
"eval_steps_per_second": 17.007,
|
47 |
+
"step": 18604
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.0,
|
51 |
+
"grad_norm": 0.016049087047576904,
|
52 |
+
"learning_rate": 4.0434688111280154e-06,
|
53 |
+
"loss": 0.3459,
|
54 |
+
"step": 27906
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.4943181818181818,
|
59 |
+
"eval_f1": 0.46533481595237636,
|
60 |
+
"eval_loss": 3.3212876319885254,
|
61 |
+
"eval_precision": 0.6366932825610363,
|
62 |
+
"eval_recall": 0.4943181818181818,
|
63 |
+
"eval_runtime": 16.4685,
|
64 |
+
"eval_samples_per_second": 138.932,
|
65 |
+
"eval_steps_per_second": 17.366,
|
66 |
+
"step": 27906
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 4.0,
|
70 |
+
"grad_norm": 0.18690501153469086,
|
71 |
+
"learning_rate": 2.0217344055640077e-06,
|
72 |
+
"loss": 0.2889,
|
73 |
+
"step": 37208
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.5380244755244755,
|
78 |
+
"eval_f1": 0.5246359275298862,
|
79 |
+
"eval_loss": 2.901275157928467,
|
80 |
+
"eval_precision": 0.606438596036477,
|
81 |
+
"eval_recall": 0.5380244755244755,
|
82 |
+
"eval_runtime": 16.3842,
|
83 |
+
"eval_samples_per_second": 139.647,
|
84 |
+
"eval_steps_per_second": 17.456,
|
85 |
+
"step": 37208
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 5.0,
|
89 |
+
"grad_norm": 0.032341405749320984,
|
90 |
+
"learning_rate": 0.0,
|
91 |
+
"loss": 0.2405,
|
92 |
+
"step": 46510
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.5354020979020979,
|
97 |
+
"eval_f1": 0.528473834809328,
|
98 |
+
"eval_loss": 3.196098566055298,
|
99 |
+
"eval_precision": 0.6116035335408587,
|
100 |
+
"eval_recall": 0.5354020979020979,
|
101 |
+
"eval_runtime": 18.2453,
|
102 |
+
"eval_samples_per_second": 125.402,
|
103 |
+
"eval_steps_per_second": 15.675,
|
104 |
+
"step": 46510
|
105 |
+
}
|
106 |
+
],
|
107 |
+
"logging_steps": 500,
|
108 |
+
"max_steps": 46510,
|
109 |
+
"num_input_tokens_seen": 0,
|
110 |
+
"num_train_epochs": 5,
|
111 |
+
"save_steps": 500,
|
112 |
+
"stateful_callbacks": {
|
113 |
+
"TrainerControl": {
|
114 |
+
"args": {
|
115 |
+
"should_epoch_stop": false,
|
116 |
+
"should_evaluate": false,
|
117 |
+
"should_log": false,
|
118 |
+
"should_save": true,
|
119 |
+
"should_training_stop": true
|
120 |
+
},
|
121 |
+
"attributes": {}
|
122 |
+
}
|
123 |
+
},
|
124 |
+
"total_flos": 9.524204110411717e+16,
|
125 |
+
"train_batch_size": 8,
|
126 |
+
"trial_name": null,
|
127 |
+
"trial_params": null
|
128 |
+
}
|
checkpoint-46510/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dbf1e2674cf52d458f94b2caeee62e7225f15edfb61f198e097040d7d1a7268
|
3 |
+
size 5240
|
checkpoint-46510/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|