Callis6699
commited on
Commit
•
81b71d3
1
Parent(s):
02c3d20
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- runs/Mar10_15-22-18_d09419a20441/events.out.tfevents.1710084185.d09419a20441.24137.1 +2 -2
- runs/Mar10_15-39-45_d09419a20441/events.out.tfevents.1710085185.d09419a20441.36629.1 +3 -0
- tmp-checkpoint-2675/config.json +28 -0
- tmp-checkpoint-2675/merges.txt +0 -0
- tmp-checkpoint-2675/model.safetensors +3 -0
- tmp-checkpoint-2675/optimizer.pt +3 -0
- tmp-checkpoint-2675/rng_state.pth +3 -0
- tmp-checkpoint-2675/scheduler.pt +3 -0
- tmp-checkpoint-2675/special_tokens_map.json +15 -0
- tmp-checkpoint-2675/tokenizer.json +0 -0
- tmp-checkpoint-2675/tokenizer_config.json +57 -0
- tmp-checkpoint-2675/trainer_state.json +101 -0
- tmp-checkpoint-2675/training_args.bin +3 -0
- tmp-checkpoint-2675/vocab.json +0 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498612824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:208f9ebf9703f0e5fcd0ebbfc7e5f5189ca92fdadddda0cbd038fbb44bc6350f
|
3 |
size 498612824
|
runs/Mar10_15-22-18_d09419a20441/events.out.tfevents.1710084185.d09419a20441.24137.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24b0f461deec982ac93cef5b241a922a6f711efbd9d1cb22044f2237823b17a5
|
3 |
+
size 7342
|
runs/Mar10_15-39-45_d09419a20441/events.out.tfevents.1710085185.d09419a20441.36629.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f882824cedb13133248643bb5a03add2916ce9cc47858ad60b7cac545fc6445
|
3 |
+
size 5158
|
tmp-checkpoint-2675/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.38.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
tmp-checkpoint-2675/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tmp-checkpoint-2675/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50816a000e025e5b4222994aafc1a734ae12008f418b256a91519adda6d4ca85
|
3 |
+
size 498612824
|
tmp-checkpoint-2675/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f8defdf84131f885318b922418a9854043845a9f9836ae8804918fefa59760
|
3 |
+
size 997345530
|
tmp-checkpoint-2675/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc4514325d1cd6218f8ffac41df456f6df58def147da72679c5129fa36d1c85e
|
3 |
+
size 14244
|
tmp-checkpoint-2675/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a113978a7c5fe803444afa83adccda9aab3ebb5099a00818e17eb47d7f66ccbd
|
3 |
+
size 1064
|
tmp-checkpoint-2675/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 |
+
}
|
tmp-checkpoint-2675/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tmp-checkpoint-2675/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 |
+
}
|
tmp-checkpoint-2675/trainer_state.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6372231085109245,
|
3 |
+
"best_model_checkpoint": "roberta-base-finetuned-cola/checkpoint-1070",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2675,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"grad_norm": 16.3082275390625,
|
14 |
+
"learning_rate": 1.6261682242990654e-05,
|
15 |
+
"loss": 0.4777,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.43241721391677856,
|
21 |
+
"eval_matthews_correlation": 0.5493333540758192,
|
22 |
+
"eval_runtime": 1.2622,
|
23 |
+
"eval_samples_per_second": 826.355,
|
24 |
+
"eval_steps_per_second": 52.291,
|
25 |
+
"step": 535
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.87,
|
29 |
+
"grad_norm": 23.89521598815918,
|
30 |
+
"learning_rate": 1.2523364485981309e-05,
|
31 |
+
"loss": 0.3138,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_loss": 0.4074053466320038,
|
37 |
+
"eval_matthews_correlation": 0.6372231085109245,
|
38 |
+
"eval_runtime": 1.315,
|
39 |
+
"eval_samples_per_second": 793.178,
|
40 |
+
"eval_steps_per_second": 50.191,
|
41 |
+
"step": 1070
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.8,
|
45 |
+
"grad_norm": 18.608760833740234,
|
46 |
+
"learning_rate": 8.785046728971963e-06,
|
47 |
+
"loss": 0.2262,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_loss": 0.6061288714408875,
|
53 |
+
"eval_matthews_correlation": 0.576660981486724,
|
54 |
+
"eval_runtime": 1.3277,
|
55 |
+
"eval_samples_per_second": 785.578,
|
56 |
+
"eval_steps_per_second": 49.711,
|
57 |
+
"step": 1605
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.74,
|
61 |
+
"grad_norm": 2.4630796909332275,
|
62 |
+
"learning_rate": 5.046728971962617e-06,
|
63 |
+
"loss": 0.1786,
|
64 |
+
"step": 2000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.0,
|
68 |
+
"eval_loss": 0.884406328201294,
|
69 |
+
"eval_matthews_correlation": 0.5855361143791362,
|
70 |
+
"eval_runtime": 1.2996,
|
71 |
+
"eval_samples_per_second": 802.571,
|
72 |
+
"eval_steps_per_second": 50.786,
|
73 |
+
"step": 2140
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.67,
|
77 |
+
"grad_norm": 0.05961179360747337,
|
78 |
+
"learning_rate": 1.308411214953271e-06,
|
79 |
+
"loss": 0.1253,
|
80 |
+
"step": 2500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"eval_loss": 0.9215266704559326,
|
85 |
+
"eval_matthews_correlation": 0.6158197390467447,
|
86 |
+
"eval_runtime": 1.2999,
|
87 |
+
"eval_samples_per_second": 802.375,
|
88 |
+
"eval_steps_per_second": 50.773,
|
89 |
+
"step": 2675
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"logging_steps": 500,
|
93 |
+
"max_steps": 2675,
|
94 |
+
"num_input_tokens_seen": 0,
|
95 |
+
"num_train_epochs": 5,
|
96 |
+
"save_steps": 500,
|
97 |
+
"total_flos": 449687113048260.0,
|
98 |
+
"train_batch_size": 16,
|
99 |
+
"trial_name": null,
|
100 |
+
"trial_params": null
|
101 |
+
}
|
tmp-checkpoint-2675/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f59fe0b682b5ab5291019e04201cbbd5a4fbdcb480c63867e2a08aedf682af2
|
3 |
+
size 4920
|
tmp-checkpoint-2675/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf0aada722587d583beb9ca32d87ee803e61f84e40d1f366d5b9e684ee28ef8
|
3 |
size 4920
|