luukschmitz
commited on
Commit
•
c8a81cc
1
Parent(s):
b7edba9
Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-204/config.json +42 -0
- checkpoint-204/model.safetensors +3 -0
- checkpoint-204/optimizer.pt +3 -0
- checkpoint-204/rng_state.pth +3 -0
- checkpoint-204/scheduler.pt +3 -0
- checkpoint-204/trainer_state.json +810 -0
- checkpoint-204/training_args.bin +3 -0
- config.json +42 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jul13_18-20-58_r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh/events.out.tfevents.1720894859.r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh.164.0 +2 -2
- runs/Jul13_18-20-58_r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh/events.out.tfevents.1720894933.r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh.164.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +61 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.9263564944267273
|
17 |
+
|
18 |
+
f1_macro: 0.6193851541399454
|
19 |
+
|
20 |
+
f1_micro: 0.700836820083682
|
21 |
+
|
22 |
+
f1_weighted: 0.6928921325883705
|
23 |
+
|
24 |
+
precision_macro: 0.6728486680867634
|
25 |
+
|
26 |
+
precision_micro: 0.700836820083682
|
27 |
+
|
28 |
+
precision_weighted: 0.7079874543114232
|
29 |
+
|
30 |
+
recall_macro: 0.6147070748686357
|
31 |
+
|
32 |
+
recall_micro: 0.700836820083682
|
33 |
+
|
34 |
+
recall_weighted: 0.700836820083682
|
35 |
+
|
36 |
+
accuracy: 0.700836820083682
|
checkpoint-204/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
3 |
+
"_num_labels": 4,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1",
|
18 |
+
"2": "2",
|
19 |
+
"3": "3"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"0": 0,
|
25 |
+
"1": 1,
|
26 |
+
"2": 2,
|
27 |
+
"3": 3
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-05,
|
30 |
+
"max_position_embeddings": 514,
|
31 |
+
"model_type": "roberta",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 6,
|
34 |
+
"pad_token_id": 1,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.42.2",
|
39 |
+
"type_vocab_size": 1,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50265
|
42 |
+
}
|
checkpoint-204/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f85feff09068599bc4cd8390b12c71d99e89f439bfb666841473a9a7f23bd61e
|
3 |
+
size 328498432
|
checkpoint-204/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b9532c7820e91a16d50c8d0a332d2cde3e79c3242a10a6e16fd54261349ad6
|
3 |
+
size 657059898
|
checkpoint-204/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a5442cb8d0ad1183849111de42c7f47db1523c5952eb2750b2bdfba8393ca43
|
3 |
+
size 14244
|
checkpoint-204/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30df69ee004ba9369d6e17f16a306eceb28690811f9374db82690dccb12d89e1
|
3 |
+
size 1064
|
checkpoint-204/trainer_state.json
ADDED
@@ -0,0 +1,810 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9263564944267273,
|
3 |
+
"best_model_checkpoint": "Geofin5/checkpoint-204",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 204,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.029411764705882353,
|
13 |
+
"grad_norm": 7.102517604827881,
|
14 |
+
"learning_rate": 1.2195121951219514e-06,
|
15 |
+
"loss": 1.3725,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.058823529411764705,
|
20 |
+
"grad_norm": 5.622996807098389,
|
21 |
+
"learning_rate": 2.4390243902439027e-06,
|
22 |
+
"loss": 1.3922,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.08823529411764706,
|
27 |
+
"grad_norm": 7.666197299957275,
|
28 |
+
"learning_rate": 3.6585365853658537e-06,
|
29 |
+
"loss": 1.3371,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.11764705882352941,
|
34 |
+
"grad_norm": 5.953295707702637,
|
35 |
+
"learning_rate": 4.8780487804878055e-06,
|
36 |
+
"loss": 1.322,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.14705882352941177,
|
41 |
+
"grad_norm": 4.027065277099609,
|
42 |
+
"learning_rate": 6.0975609756097564e-06,
|
43 |
+
"loss": 1.2841,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.17647058823529413,
|
48 |
+
"grad_norm": 6.355094909667969,
|
49 |
+
"learning_rate": 7.317073170731707e-06,
|
50 |
+
"loss": 1.2458,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.20588235294117646,
|
55 |
+
"grad_norm": 4.935754776000977,
|
56 |
+
"learning_rate": 8.53658536585366e-06,
|
57 |
+
"loss": 1.2534,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.23529411764705882,
|
62 |
+
"grad_norm": 3.921065330505371,
|
63 |
+
"learning_rate": 9.756097560975611e-06,
|
64 |
+
"loss": 1.2224,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2647058823529412,
|
69 |
+
"grad_norm": 4.3277482986450195,
|
70 |
+
"learning_rate": 1.0975609756097562e-05,
|
71 |
+
"loss": 1.125,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.29411764705882354,
|
76 |
+
"grad_norm": 4.808041572570801,
|
77 |
+
"learning_rate": 1.2195121951219513e-05,
|
78 |
+
"loss": 1.0728,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3235294117647059,
|
83 |
+
"grad_norm": 2.6956660747528076,
|
84 |
+
"learning_rate": 1.3414634146341466e-05,
|
85 |
+
"loss": 1.2269,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.35294117647058826,
|
90 |
+
"grad_norm": 2.8759944438934326,
|
91 |
+
"learning_rate": 1.4634146341463415e-05,
|
92 |
+
"loss": 1.094,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.38235294117647056,
|
97 |
+
"grad_norm": 5.900161266326904,
|
98 |
+
"learning_rate": 1.5853658536585366e-05,
|
99 |
+
"loss": 1.1418,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4117647058823529,
|
104 |
+
"grad_norm": 8.949163436889648,
|
105 |
+
"learning_rate": 1.707317073170732e-05,
|
106 |
+
"loss": 1.1931,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4411764705882353,
|
111 |
+
"grad_norm": 4.940980911254883,
|
112 |
+
"learning_rate": 1.8292682926829268e-05,
|
113 |
+
"loss": 1.0575,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.47058823529411764,
|
118 |
+
"grad_norm": 4.716662406921387,
|
119 |
+
"learning_rate": 1.9512195121951222e-05,
|
120 |
+
"loss": 1.0049,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5,
|
125 |
+
"grad_norm": 9.422857284545898,
|
126 |
+
"learning_rate": 2.073170731707317e-05,
|
127 |
+
"loss": 1.1533,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5294117647058824,
|
132 |
+
"grad_norm": 7.63829231262207,
|
133 |
+
"learning_rate": 2.1951219512195124e-05,
|
134 |
+
"loss": 1.1386,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5588235294117647,
|
139 |
+
"grad_norm": 4.745357036590576,
|
140 |
+
"learning_rate": 2.3170731707317075e-05,
|
141 |
+
"loss": 0.9919,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5882352941176471,
|
146 |
+
"grad_norm": 4.796962261199951,
|
147 |
+
"learning_rate": 2.4390243902439026e-05,
|
148 |
+
"loss": 0.9971,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6176470588235294,
|
153 |
+
"grad_norm": 4.623069763183594,
|
154 |
+
"learning_rate": 2.5609756097560977e-05,
|
155 |
+
"loss": 1.016,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6470588235294118,
|
160 |
+
"grad_norm": 7.526188373565674,
|
161 |
+
"learning_rate": 2.682926829268293e-05,
|
162 |
+
"loss": 1.1257,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.6764705882352942,
|
167 |
+
"grad_norm": 6.750401973724365,
|
168 |
+
"learning_rate": 2.8048780487804882e-05,
|
169 |
+
"loss": 1.0988,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7058823529411765,
|
174 |
+
"grad_norm": 5.956785678863525,
|
175 |
+
"learning_rate": 2.926829268292683e-05,
|
176 |
+
"loss": 1.0436,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.7352941176470589,
|
181 |
+
"grad_norm": 6.079898834228516,
|
182 |
+
"learning_rate": 3.048780487804878e-05,
|
183 |
+
"loss": 1.0277,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.7647058823529411,
|
188 |
+
"grad_norm": 4.464956760406494,
|
189 |
+
"learning_rate": 3.170731707317073e-05,
|
190 |
+
"loss": 0.8688,
|
191 |
+
"step": 52
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.7941176470588235,
|
195 |
+
"grad_norm": 6.561495304107666,
|
196 |
+
"learning_rate": 3.292682926829269e-05,
|
197 |
+
"loss": 0.8962,
|
198 |
+
"step": 54
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.8235294117647058,
|
202 |
+
"grad_norm": 6.373690128326416,
|
203 |
+
"learning_rate": 3.353658536585366e-05,
|
204 |
+
"loss": 1.0343,
|
205 |
+
"step": 56
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.8529411764705882,
|
209 |
+
"grad_norm": 8.000486373901367,
|
210 |
+
"learning_rate": 3.475609756097561e-05,
|
211 |
+
"loss": 1.0543,
|
212 |
+
"step": 58
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.8823529411764706,
|
216 |
+
"grad_norm": 5.830896854400635,
|
217 |
+
"learning_rate": 3.597560975609756e-05,
|
218 |
+
"loss": 1.0761,
|
219 |
+
"step": 60
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9117647058823529,
|
223 |
+
"grad_norm": 10.151026725769043,
|
224 |
+
"learning_rate": 3.7195121951219514e-05,
|
225 |
+
"loss": 1.0737,
|
226 |
+
"step": 62
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.9411764705882353,
|
230 |
+
"grad_norm": 9.73624038696289,
|
231 |
+
"learning_rate": 3.8414634146341465e-05,
|
232 |
+
"loss": 0.9112,
|
233 |
+
"step": 64
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.9705882352941176,
|
237 |
+
"grad_norm": 9.713314056396484,
|
238 |
+
"learning_rate": 3.9634146341463416e-05,
|
239 |
+
"loss": 0.8498,
|
240 |
+
"step": 66
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.0,
|
244 |
+
"grad_norm": 10.631162643432617,
|
245 |
+
"learning_rate": 4.085365853658537e-05,
|
246 |
+
"loss": 0.9937,
|
247 |
+
"step": 68
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.0,
|
251 |
+
"eval_accuracy": 0.5564853556485355,
|
252 |
+
"eval_f1_macro": 0.39598376878805575,
|
253 |
+
"eval_f1_micro": 0.5564853556485355,
|
254 |
+
"eval_f1_weighted": 0.4741897095372058,
|
255 |
+
"eval_loss": 1.0355333089828491,
|
256 |
+
"eval_precision_macro": 0.5140887485587238,
|
257 |
+
"eval_precision_micro": 0.5564853556485355,
|
258 |
+
"eval_precision_weighted": 0.5576172702264479,
|
259 |
+
"eval_recall_macro": 0.4827948905153814,
|
260 |
+
"eval_recall_micro": 0.5564853556485355,
|
261 |
+
"eval_recall_weighted": 0.5564853556485355,
|
262 |
+
"eval_runtime": 0.6549,
|
263 |
+
"eval_samples_per_second": 729.907,
|
264 |
+
"eval_steps_per_second": 12.216,
|
265 |
+
"step": 68
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.0294117647058822,
|
269 |
+
"grad_norm": 7.002508163452148,
|
270 |
+
"learning_rate": 4.207317073170732e-05,
|
271 |
+
"loss": 0.9379,
|
272 |
+
"step": 70
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.0588235294117647,
|
276 |
+
"grad_norm": 9.145544052124023,
|
277 |
+
"learning_rate": 4.329268292682927e-05,
|
278 |
+
"loss": 0.8374,
|
279 |
+
"step": 72
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.088235294117647,
|
283 |
+
"grad_norm": 10.859468460083008,
|
284 |
+
"learning_rate": 4.451219512195122e-05,
|
285 |
+
"loss": 1.0609,
|
286 |
+
"step": 74
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.1176470588235294,
|
290 |
+
"grad_norm": 5.649864196777344,
|
291 |
+
"learning_rate": 4.573170731707318e-05,
|
292 |
+
"loss": 0.8415,
|
293 |
+
"step": 76
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.1470588235294117,
|
297 |
+
"grad_norm": 7.1180877685546875,
|
298 |
+
"learning_rate": 4.695121951219512e-05,
|
299 |
+
"loss": 0.9504,
|
300 |
+
"step": 78
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.1764705882352942,
|
304 |
+
"grad_norm": 11.018819808959961,
|
305 |
+
"learning_rate": 4.817073170731707e-05,
|
306 |
+
"loss": 0.9917,
|
307 |
+
"step": 80
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.2058823529411764,
|
311 |
+
"grad_norm": 9.096946716308594,
|
312 |
+
"learning_rate": 4.9390243902439024e-05,
|
313 |
+
"loss": 0.7748,
|
314 |
+
"step": 82
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.2352941176470589,
|
318 |
+
"grad_norm": 14.755735397338867,
|
319 |
+
"learning_rate": 4.993188010899183e-05,
|
320 |
+
"loss": 0.8427,
|
321 |
+
"step": 84
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.2647058823529411,
|
325 |
+
"grad_norm": 9.15238094329834,
|
326 |
+
"learning_rate": 4.979564032697548e-05,
|
327 |
+
"loss": 0.8695,
|
328 |
+
"step": 86
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.2941176470588236,
|
332 |
+
"grad_norm": 10.265277862548828,
|
333 |
+
"learning_rate": 4.9659400544959125e-05,
|
334 |
+
"loss": 0.6385,
|
335 |
+
"step": 88
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.3235294117647058,
|
339 |
+
"grad_norm": 9.704151153564453,
|
340 |
+
"learning_rate": 4.952316076294278e-05,
|
341 |
+
"loss": 0.756,
|
342 |
+
"step": 90
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.3529411764705883,
|
346 |
+
"grad_norm": 9.141586303710938,
|
347 |
+
"learning_rate": 4.9386920980926435e-05,
|
348 |
+
"loss": 0.7567,
|
349 |
+
"step": 92
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 1.3823529411764706,
|
353 |
+
"grad_norm": 9.520133018493652,
|
354 |
+
"learning_rate": 4.925068119891008e-05,
|
355 |
+
"loss": 0.9081,
|
356 |
+
"step": 94
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.4117647058823528,
|
360 |
+
"grad_norm": 17.20820426940918,
|
361 |
+
"learning_rate": 4.911444141689374e-05,
|
362 |
+
"loss": 0.9661,
|
363 |
+
"step": 96
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.4411764705882353,
|
367 |
+
"grad_norm": 9.26347827911377,
|
368 |
+
"learning_rate": 4.8978201634877385e-05,
|
369 |
+
"loss": 0.8661,
|
370 |
+
"step": 98
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 1.4705882352941178,
|
374 |
+
"grad_norm": 12.740453720092773,
|
375 |
+
"learning_rate": 4.884196185286104e-05,
|
376 |
+
"loss": 0.8978,
|
377 |
+
"step": 100
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.5,
|
381 |
+
"grad_norm": 8.899398803710938,
|
382 |
+
"learning_rate": 4.870572207084469e-05,
|
383 |
+
"loss": 0.6809,
|
384 |
+
"step": 102
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.5294117647058822,
|
388 |
+
"grad_norm": 13.515447616577148,
|
389 |
+
"learning_rate": 4.8569482288828335e-05,
|
390 |
+
"loss": 0.7378,
|
391 |
+
"step": 104
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 1.5588235294117647,
|
395 |
+
"grad_norm": 6.7167439460754395,
|
396 |
+
"learning_rate": 4.843324250681199e-05,
|
397 |
+
"loss": 0.7376,
|
398 |
+
"step": 106
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.5882352941176472,
|
402 |
+
"grad_norm": 19.798791885375977,
|
403 |
+
"learning_rate": 4.8297002724795645e-05,
|
404 |
+
"loss": 0.7125,
|
405 |
+
"step": 108
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.6176470588235294,
|
409 |
+
"grad_norm": Infinity,
|
410 |
+
"learning_rate": 4.822888283378747e-05,
|
411 |
+
"loss": 0.7425,
|
412 |
+
"step": 110
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 1.6470588235294117,
|
416 |
+
"grad_norm": 8.12073040008545,
|
417 |
+
"learning_rate": 4.809264305177112e-05,
|
418 |
+
"loss": 0.672,
|
419 |
+
"step": 112
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.6764705882352942,
|
423 |
+
"grad_norm": 7.961780071258545,
|
424 |
+
"learning_rate": 4.795640326975477e-05,
|
425 |
+
"loss": 0.7023,
|
426 |
+
"step": 114
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 1.7058823529411766,
|
430 |
+
"grad_norm": 15.105574607849121,
|
431 |
+
"learning_rate": 4.782016348773842e-05,
|
432 |
+
"loss": 0.6107,
|
433 |
+
"step": 116
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 1.7352941176470589,
|
437 |
+
"grad_norm": 15.375845909118652,
|
438 |
+
"learning_rate": 4.768392370572207e-05,
|
439 |
+
"loss": 0.648,
|
440 |
+
"step": 118
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.7647058823529411,
|
444 |
+
"grad_norm": 11.371450424194336,
|
445 |
+
"learning_rate": 4.7547683923705725e-05,
|
446 |
+
"loss": 0.7948,
|
447 |
+
"step": 120
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.7941176470588234,
|
451 |
+
"grad_norm": 13.418404579162598,
|
452 |
+
"learning_rate": 4.741144414168938e-05,
|
453 |
+
"loss": 0.5621,
|
454 |
+
"step": 122
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 1.8235294117647058,
|
458 |
+
"grad_norm": 14.923059463500977,
|
459 |
+
"learning_rate": 4.727520435967303e-05,
|
460 |
+
"loss": 0.7301,
|
461 |
+
"step": 124
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.8529411764705883,
|
465 |
+
"grad_norm": 9.319025993347168,
|
466 |
+
"learning_rate": 4.713896457765668e-05,
|
467 |
+
"loss": 0.8735,
|
468 |
+
"step": 126
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 1.8823529411764706,
|
472 |
+
"grad_norm": 7.903226375579834,
|
473 |
+
"learning_rate": 4.700272479564033e-05,
|
474 |
+
"loss": 0.7913,
|
475 |
+
"step": 128
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 1.9117647058823528,
|
479 |
+
"grad_norm": 13.043506622314453,
|
480 |
+
"learning_rate": 4.686648501362398e-05,
|
481 |
+
"loss": 0.8099,
|
482 |
+
"step": 130
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.9411764705882353,
|
486 |
+
"grad_norm": 12.253973007202148,
|
487 |
+
"learning_rate": 4.673024523160763e-05,
|
488 |
+
"loss": 0.7651,
|
489 |
+
"step": 132
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.9705882352941178,
|
493 |
+
"grad_norm": 9.918290138244629,
|
494 |
+
"learning_rate": 4.659400544959128e-05,
|
495 |
+
"loss": 0.7537,
|
496 |
+
"step": 134
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 2.0,
|
500 |
+
"grad_norm": 17.887121200561523,
|
501 |
+
"learning_rate": 4.6457765667574935e-05,
|
502 |
+
"loss": 0.8837,
|
503 |
+
"step": 136
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 2.0,
|
507 |
+
"eval_accuracy": 0.6401673640167364,
|
508 |
+
"eval_f1_macro": 0.5112056699141869,
|
509 |
+
"eval_f1_micro": 0.6401673640167364,
|
510 |
+
"eval_f1_weighted": 0.623119203970463,
|
511 |
+
"eval_loss": 0.9266994595527649,
|
512 |
+
"eval_precision_macro": 0.6451808449222778,
|
513 |
+
"eval_precision_micro": 0.6401673640167364,
|
514 |
+
"eval_precision_weighted": 0.6880713224888448,
|
515 |
+
"eval_recall_macro": 0.5646276187019543,
|
516 |
+
"eval_recall_micro": 0.6401673640167364,
|
517 |
+
"eval_recall_weighted": 0.6401673640167364,
|
518 |
+
"eval_runtime": 0.6577,
|
519 |
+
"eval_samples_per_second": 726.807,
|
520 |
+
"eval_steps_per_second": 12.164,
|
521 |
+
"step": 136
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 2.0294117647058822,
|
525 |
+
"grad_norm": 12.88015365600586,
|
526 |
+
"learning_rate": 4.632152588555859e-05,
|
527 |
+
"loss": 0.6675,
|
528 |
+
"step": 138
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 2.0588235294117645,
|
532 |
+
"grad_norm": 7.740164756774902,
|
533 |
+
"learning_rate": 4.618528610354224e-05,
|
534 |
+
"loss": 0.726,
|
535 |
+
"step": 140
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 2.088235294117647,
|
539 |
+
"grad_norm": 6.169182777404785,
|
540 |
+
"learning_rate": 4.604904632152589e-05,
|
541 |
+
"loss": 0.5834,
|
542 |
+
"step": 142
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 2.1176470588235294,
|
546 |
+
"grad_norm": 5.821132659912109,
|
547 |
+
"learning_rate": 4.591280653950954e-05,
|
548 |
+
"loss": 0.5636,
|
549 |
+
"step": 144
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 2.1470588235294117,
|
553 |
+
"grad_norm": 7.872137069702148,
|
554 |
+
"learning_rate": 4.577656675749319e-05,
|
555 |
+
"loss": 0.566,
|
556 |
+
"step": 146
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 2.176470588235294,
|
560 |
+
"grad_norm": 7.407035827636719,
|
561 |
+
"learning_rate": 4.564032697547684e-05,
|
562 |
+
"loss": 0.5023,
|
563 |
+
"step": 148
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 2.2058823529411766,
|
567 |
+
"grad_norm": 8.054471015930176,
|
568 |
+
"learning_rate": 4.550408719346049e-05,
|
569 |
+
"loss": 0.4304,
|
570 |
+
"step": 150
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 2.235294117647059,
|
574 |
+
"grad_norm": 20.935813903808594,
|
575 |
+
"learning_rate": 4.5367847411444145e-05,
|
576 |
+
"loss": 0.5301,
|
577 |
+
"step": 152
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 2.264705882352941,
|
581 |
+
"grad_norm": 15.824753761291504,
|
582 |
+
"learning_rate": 4.52316076294278e-05,
|
583 |
+
"loss": 0.5815,
|
584 |
+
"step": 154
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.2941176470588234,
|
588 |
+
"grad_norm": 11.326836585998535,
|
589 |
+
"learning_rate": 4.509536784741145e-05,
|
590 |
+
"loss": 0.7101,
|
591 |
+
"step": 156
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 2.323529411764706,
|
595 |
+
"grad_norm": 27.99034309387207,
|
596 |
+
"learning_rate": 4.4959128065395095e-05,
|
597 |
+
"loss": 0.6138,
|
598 |
+
"step": 158
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 2.3529411764705883,
|
602 |
+
"grad_norm": 7.2306623458862305,
|
603 |
+
"learning_rate": 4.482288828337875e-05,
|
604 |
+
"loss": 0.5515,
|
605 |
+
"step": 160
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 2.3823529411764706,
|
609 |
+
"grad_norm": 15.374252319335938,
|
610 |
+
"learning_rate": 4.46866485013624e-05,
|
611 |
+
"loss": 0.7274,
|
612 |
+
"step": 162
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 2.411764705882353,
|
616 |
+
"grad_norm": 11.15127182006836,
|
617 |
+
"learning_rate": 4.4550408719346046e-05,
|
618 |
+
"loss": 0.685,
|
619 |
+
"step": 164
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 2.4411764705882355,
|
623 |
+
"grad_norm": 18.0255069732666,
|
624 |
+
"learning_rate": 4.44141689373297e-05,
|
625 |
+
"loss": 0.6403,
|
626 |
+
"step": 166
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.4705882352941178,
|
630 |
+
"grad_norm": 15.681634902954102,
|
631 |
+
"learning_rate": 4.4277929155313355e-05,
|
632 |
+
"loss": 0.5377,
|
633 |
+
"step": 168
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 2.5,
|
637 |
+
"grad_norm": 13.26118278503418,
|
638 |
+
"learning_rate": 4.414168937329701e-05,
|
639 |
+
"loss": 0.6531,
|
640 |
+
"step": 170
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 2.5294117647058822,
|
644 |
+
"grad_norm": 5.877330780029297,
|
645 |
+
"learning_rate": 4.400544959128066e-05,
|
646 |
+
"loss": 0.4888,
|
647 |
+
"step": 172
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 2.5588235294117645,
|
651 |
+
"grad_norm": 17.445058822631836,
|
652 |
+
"learning_rate": 4.3869209809264305e-05,
|
653 |
+
"loss": 0.5194,
|
654 |
+
"step": 174
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.588235294117647,
|
658 |
+
"grad_norm": 11.56258487701416,
|
659 |
+
"learning_rate": 4.373297002724796e-05,
|
660 |
+
"loss": 0.3939,
|
661 |
+
"step": 176
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 2.6176470588235294,
|
665 |
+
"grad_norm": 14.838981628417969,
|
666 |
+
"learning_rate": 4.359673024523161e-05,
|
667 |
+
"loss": 0.4646,
|
668 |
+
"step": 178
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.6470588235294117,
|
672 |
+
"grad_norm": 16.686960220336914,
|
673 |
+
"learning_rate": 4.3460490463215255e-05,
|
674 |
+
"loss": 0.4943,
|
675 |
+
"step": 180
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 2.6764705882352944,
|
679 |
+
"grad_norm": 13.008139610290527,
|
680 |
+
"learning_rate": 4.332425068119891e-05,
|
681 |
+
"loss": 0.6352,
|
682 |
+
"step": 182
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 2.7058823529411766,
|
686 |
+
"grad_norm": 18.054786682128906,
|
687 |
+
"learning_rate": 4.3188010899182565e-05,
|
688 |
+
"loss": 0.4034,
|
689 |
+
"step": 184
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 2.735294117647059,
|
693 |
+
"grad_norm": 9.771907806396484,
|
694 |
+
"learning_rate": 4.305177111716621e-05,
|
695 |
+
"loss": 0.3427,
|
696 |
+
"step": 186
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.764705882352941,
|
700 |
+
"grad_norm": 8.055870056152344,
|
701 |
+
"learning_rate": 4.291553133514987e-05,
|
702 |
+
"loss": 0.3218,
|
703 |
+
"step": 188
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 2.7941176470588234,
|
707 |
+
"grad_norm": 14.025898933410645,
|
708 |
+
"learning_rate": 4.2779291553133515e-05,
|
709 |
+
"loss": 0.5226,
|
710 |
+
"step": 190
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.8235294117647056,
|
714 |
+
"grad_norm": 7.227923393249512,
|
715 |
+
"learning_rate": 4.264305177111717e-05,
|
716 |
+
"loss": 0.3266,
|
717 |
+
"step": 192
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 2.8529411764705883,
|
721 |
+
"grad_norm": 15.04366397857666,
|
722 |
+
"learning_rate": 4.250681198910082e-05,
|
723 |
+
"loss": 0.6136,
|
724 |
+
"step": 194
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 2.8823529411764706,
|
728 |
+
"grad_norm": 15.145903587341309,
|
729 |
+
"learning_rate": 4.237057220708447e-05,
|
730 |
+
"loss": 0.4222,
|
731 |
+
"step": 196
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 2.911764705882353,
|
735 |
+
"grad_norm": 14.604679107666016,
|
736 |
+
"learning_rate": 4.223433242506813e-05,
|
737 |
+
"loss": 0.6989,
|
738 |
+
"step": 198
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.9411764705882355,
|
742 |
+
"grad_norm": 10.518308639526367,
|
743 |
+
"learning_rate": 4.2098092643051775e-05,
|
744 |
+
"loss": 0.4435,
|
745 |
+
"step": 200
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 2.9705882352941178,
|
749 |
+
"grad_norm": 16.961441040039062,
|
750 |
+
"learning_rate": 4.196185286103542e-05,
|
751 |
+
"loss": 0.6116,
|
752 |
+
"step": 202
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 3.0,
|
756 |
+
"grad_norm": 14.586898803710938,
|
757 |
+
"learning_rate": 4.182561307901908e-05,
|
758 |
+
"loss": 0.4291,
|
759 |
+
"step": 204
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 3.0,
|
763 |
+
"eval_accuracy": 0.700836820083682,
|
764 |
+
"eval_f1_macro": 0.6193851541399454,
|
765 |
+
"eval_f1_micro": 0.700836820083682,
|
766 |
+
"eval_f1_weighted": 0.6928921325883705,
|
767 |
+
"eval_loss": 0.9263564944267273,
|
768 |
+
"eval_precision_macro": 0.6728486680867634,
|
769 |
+
"eval_precision_micro": 0.700836820083682,
|
770 |
+
"eval_precision_weighted": 0.7079874543114232,
|
771 |
+
"eval_recall_macro": 0.6147070748686357,
|
772 |
+
"eval_recall_micro": 0.700836820083682,
|
773 |
+
"eval_recall_weighted": 0.700836820083682,
|
774 |
+
"eval_runtime": 0.6574,
|
775 |
+
"eval_samples_per_second": 727.055,
|
776 |
+
"eval_steps_per_second": 12.168,
|
777 |
+
"step": 204
|
778 |
+
}
|
779 |
+
],
|
780 |
+
"logging_steps": 2,
|
781 |
+
"max_steps": 816,
|
782 |
+
"num_input_tokens_seen": 0,
|
783 |
+
"num_train_epochs": 12,
|
784 |
+
"save_steps": 500,
|
785 |
+
"stateful_callbacks": {
|
786 |
+
"EarlyStoppingCallback": {
|
787 |
+
"args": {
|
788 |
+
"early_stopping_patience": 5,
|
789 |
+
"early_stopping_threshold": 0.01
|
790 |
+
},
|
791 |
+
"attributes": {
|
792 |
+
"early_stopping_patience_counter": 0
|
793 |
+
}
|
794 |
+
},
|
795 |
+
"TrainerControl": {
|
796 |
+
"args": {
|
797 |
+
"should_epoch_stop": false,
|
798 |
+
"should_evaluate": false,
|
799 |
+
"should_log": false,
|
800 |
+
"should_save": true,
|
801 |
+
"should_training_stop": false
|
802 |
+
},
|
803 |
+
"attributes": {}
|
804 |
+
}
|
805 |
+
},
|
806 |
+
"total_flos": 428613555234816.0,
|
807 |
+
"train_batch_size": 32,
|
808 |
+
"trial_name": null,
|
809 |
+
"trial_params": null
|
810 |
+
}
|
checkpoint-204/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a6125a2ed5251eb518ed4ad20f0b6350c86a01be35fa42f5d100c0eae9d4fc5
|
3 |
+
size 5112
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
3 |
+
"_num_labels": 4,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1",
|
18 |
+
"2": "2",
|
19 |
+
"3": "3"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"0": 0,
|
25 |
+
"1": 1,
|
26 |
+
"2": 2,
|
27 |
+
"3": 3
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-05,
|
30 |
+
"max_position_embeddings": 514,
|
31 |
+
"model_type": "roberta",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 6,
|
34 |
+
"pad_token_id": 1,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.42.2",
|
39 |
+
"type_vocab_size": 1,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50265
|
42 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f85feff09068599bc4cd8390b12c71d99e89f439bfb666841473a9a7f23bd61e
|
3 |
+
size 328498432
|
runs/Jul13_18-20-58_r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh/events.out.tfevents.1720894859.r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh.164.0
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 sha256:9f2c6f651fd5dbe4d2e70ccc46841634a602877967c751c441e8dc639b900c4d
|
3 |
+
size 61313
|
runs/Jul13_18-20-58_r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh/events.out.tfevents.1720894933.r-luukschmitz-geogeogeo-8ylkil48-d8ae1-suegh.164.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:419a03f45b23032b51bda9253880f5071da561cd41ef97e3f0abe82635d11890
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
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 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"stride": 0,
|
56 |
+
"tokenizer_class": "RobertaTokenizer",
|
57 |
+
"trim_offsets": true,
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a6125a2ed5251eb518ed4ad20f0b6350c86a01be35fa42f5d100c0eae9d4fc5
|
3 |
+
size 5112
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "Geofin5/autotrain-data",
|
3 |
+
"model": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 12,
|
6 |
+
"max_seq_length": 256,
|
7 |
+
"batch_size": 32,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "Geofin5",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "luukschmitz",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|