Shresthadev403
commited on
End of training
Browse files- README.md +6 -8
- config.json +43 -1
- model.safetensors +2 -2
- runs/Jan17_06-31-51_9e8811c6b851/events.out.tfevents.1705473115.9e8811c6b851.3247.3 +3 -0
- trainer_state.json +6 -15
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
-
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -45,13 +50,6 @@ The following hyperparameters were used during training:
|
|
45 |
- num_epochs: 1
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
-
### Training results
|
49 |
-
|
50 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
| 1.0194 | 1.0 | 1 | 4.0211 |
|
53 |
-
|
54 |
-
|
55 |
### Framework versions
|
56 |
|
57 |
- Transformers 4.35.2
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 4.2672
|
19 |
+
- eval_runtime: 0.0497
|
20 |
+
- eval_samples_per_second: 40.249
|
21 |
+
- eval_steps_per_second: 20.124
|
22 |
+
- epoch: 1.0
|
23 |
+
- step: 1
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
- num_epochs: 1
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.35.2
|
config.json
CHANGED
@@ -63,7 +63,28 @@
|
|
63 |
"50": "LABEL_50",
|
64 |
"51": "LABEL_51",
|
65 |
"52": "LABEL_52",
|
66 |
-
"53": "LABEL_53"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
},
|
68 |
"initializer_range": 0.02,
|
69 |
"intermediate_size": 3072,
|
@@ -118,8 +139,29 @@
|
|
118 |
"LABEL_51": 51,
|
119 |
"LABEL_52": 52,
|
120 |
"LABEL_53": 53,
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
"LABEL_6": 6,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
"LABEL_7": 7,
|
|
|
|
|
|
|
|
|
|
|
123 |
"LABEL_8": 8,
|
124 |
"LABEL_9": 9
|
125 |
},
|
|
|
63 |
"50": "LABEL_50",
|
64 |
"51": "LABEL_51",
|
65 |
"52": "LABEL_52",
|
66 |
+
"53": "LABEL_53",
|
67 |
+
"54": "LABEL_54",
|
68 |
+
"55": "LABEL_55",
|
69 |
+
"56": "LABEL_56",
|
70 |
+
"57": "LABEL_57",
|
71 |
+
"58": "LABEL_58",
|
72 |
+
"59": "LABEL_59",
|
73 |
+
"60": "LABEL_60",
|
74 |
+
"61": "LABEL_61",
|
75 |
+
"62": "LABEL_62",
|
76 |
+
"63": "LABEL_63",
|
77 |
+
"64": "LABEL_64",
|
78 |
+
"65": "LABEL_65",
|
79 |
+
"66": "LABEL_66",
|
80 |
+
"67": "LABEL_67",
|
81 |
+
"68": "LABEL_68",
|
82 |
+
"69": "LABEL_69",
|
83 |
+
"70": "LABEL_70",
|
84 |
+
"71": "LABEL_71",
|
85 |
+
"72": "LABEL_72",
|
86 |
+
"73": "LABEL_73",
|
87 |
+
"74": "LABEL_74"
|
88 |
},
|
89 |
"initializer_range": 0.02,
|
90 |
"intermediate_size": 3072,
|
|
|
139 |
"LABEL_51": 51,
|
140 |
"LABEL_52": 52,
|
141 |
"LABEL_53": 53,
|
142 |
+
"LABEL_54": 54,
|
143 |
+
"LABEL_55": 55,
|
144 |
+
"LABEL_56": 56,
|
145 |
+
"LABEL_57": 57,
|
146 |
+
"LABEL_58": 58,
|
147 |
+
"LABEL_59": 59,
|
148 |
"LABEL_6": 6,
|
149 |
+
"LABEL_60": 60,
|
150 |
+
"LABEL_61": 61,
|
151 |
+
"LABEL_62": 62,
|
152 |
+
"LABEL_63": 63,
|
153 |
+
"LABEL_64": 64,
|
154 |
+
"LABEL_65": 65,
|
155 |
+
"LABEL_66": 66,
|
156 |
+
"LABEL_67": 67,
|
157 |
+
"LABEL_68": 68,
|
158 |
+
"LABEL_69": 69,
|
159 |
"LABEL_7": 7,
|
160 |
+
"LABEL_70": 70,
|
161 |
+
"LABEL_71": 71,
|
162 |
+
"LABEL_72": 72,
|
163 |
+
"LABEL_73": 73,
|
164 |
+
"LABEL_74": 74,
|
165 |
"LABEL_8": 8,
|
166 |
"LABEL_9": 9
|
167 |
},
|
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 sha256:9ace794b99ecc7aeae0836b2d1189098821ec78d248963a2fafa027b7254b199
|
3 |
+
size 435820636
|
runs/Jan17_06-31-51_9e8811c6b851/events.out.tfevents.1705473115.9e8811c6b851.3247.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9404232f6b5e8d1b69daa077fd88f79808fe3a4515e6297065858b95ca0d6764
|
3 |
+
size 7822
|
trainer_state.json
CHANGED
@@ -11,32 +11,23 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"learning_rate": 0.0,
|
14 |
-
"loss": 1.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
-
"eval_loss": 4.
|
20 |
-
"eval_runtime": 0.
|
21 |
-
"eval_samples_per_second":
|
22 |
-
"eval_steps_per_second":
|
23 |
"step": 1
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 1.0,
|
27 |
-
"step": 1,
|
28 |
-
"total_flos": 584109418464.0,
|
29 |
-
"train_loss": 1.0194010734558105,
|
30 |
-
"train_runtime": 15.5881,
|
31 |
-
"train_samples_per_second": 0.513,
|
32 |
-
"train_steps_per_second": 0.064
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 1,
|
36 |
"max_steps": 1,
|
37 |
"num_train_epochs": 1,
|
38 |
"save_steps": 20,
|
39 |
-
"total_flos":
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
42 |
}
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"learning_rate": 0.0,
|
14 |
+
"loss": 1.088,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
+
"eval_loss": 4.267153739929199,
|
20 |
+
"eval_runtime": 0.0497,
|
21 |
+
"eval_samples_per_second": 40.249,
|
22 |
+
"eval_steps_per_second": 20.124,
|
23 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 1,
|
27 |
"max_steps": 1,
|
28 |
"num_train_epochs": 1,
|
29 |
"save_steps": 20,
|
30 |
+
"total_flos": 576049352400.0,
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|
33 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1e77e55bc06661cee28bc607d2afecf52b569099f54a752ee68630e59c58460
|
3 |
size 4600
|