End of training
Browse files- README.md +3 -3
- config.json +19 -2
- model.safetensors +2 -2
- runs/Jul17_15-42-05_26b177582b09/events.out.tfevents.1721230927.26b177582b09.255.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -42,9 +42,9 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
-
|
47 |
-
| No log | 1.0 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
47 |
+
| No log | 1.0 | 125 | 4.2178 | 0.0595 | 0.0654 | 0.0623 | 0.4945 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "google/mt5-small",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
"d_ff": 1024,
|
@@ -12,16 +12,33 @@
|
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "mt5",
|
20 |
"num_decoder_layers": 8,
|
21 |
"num_heads": 6,
|
22 |
"num_layers": 8,
|
23 |
"pad_token_id": 0,
|
24 |
-
"problem_type": "single_label_classification",
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
"_name_or_path": "google/mt5-small",
|
3 |
"architectures": [
|
4 |
+
"MT5ForTokenClassification"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
"d_ff": 1024,
|
|
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 1,
|
14 |
"feed_forward_proj": "gated-gelu",
|
15 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2",
|
19 |
+
"3": "LABEL_3",
|
20 |
+
"4": "LABEL_4",
|
21 |
+
"5": "LABEL_5",
|
22 |
+
"6": "LABEL_6"
|
23 |
+
},
|
24 |
"initializer_factor": 1.0,
|
25 |
"is_encoder_decoder": true,
|
26 |
"is_gated_act": true,
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2,
|
31 |
+
"LABEL_3": 3,
|
32 |
+
"LABEL_4": 4,
|
33 |
+
"LABEL_5": 5,
|
34 |
+
"LABEL_6": 6
|
35 |
+
},
|
36 |
"layer_norm_epsilon": 1e-06,
|
37 |
"model_type": "mt5",
|
38 |
"num_decoder_layers": 8,
|
39 |
"num_heads": 6,
|
40 |
"num_layers": 8,
|
41 |
"pad_token_id": 0,
|
|
|
42 |
"relative_attention_max_distance": 128,
|
43 |
"relative_attention_num_buckets": 32,
|
44 |
"tie_word_embeddings": false,
|
model.safetensors
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 sha256:9ee4b3beb0258e4bd1c480f201b10586583cf516328cf7ac097e3bc5243cb39c
|
3 |
+
size 587786644
|
runs/Jul17_15-42-05_26b177582b09/events.out.tfevents.1721230927.26b177582b09.255.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7062cdd7b2802e3e89375a4db9f0118e1a898b67eeec0e777d46695eacac1784
|
3 |
+
size 6042
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18860ea2a004dfc9ee8c0db72739b4129a360e6d39f8405d4b54c4625b1bc878
|
3 |
size 5112
|