Hugging Face's logo

HiTZ
/
mbert-argmining-abstrct-en-es

Token Classification
Transformers
Safetensors
Spanish
English
bert
Inference Endpoints
Model card Files Community
anaryegen commited on
Commit
042a36c
•
1 Parent(s): 0876883

update

Browse files
Files changed (6) hide show
  1. README.md +0 -1
  2. all_results.json +5 -5
  3. model.safetensors +1 -1
  4. train_results.json +5 -5
  5. trainer_state.json +24 -12
  6. training_args.bin +1 -1
README.md DELETED
@@ -1 +0,0 @@
1
- mbert-argument-mining-es
 
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.2825497290938373,
4
- "train_runtime": 130.292,
5
- "train_samples": 4405,
6
- "train_samples_per_second": 101.426,
7
- "train_steps_per_second": 6.355
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.24564219588448766,
4
+ "train_runtime": 262.0679,
5
+ "train_samples": 8808,
6
+ "train_samples_per_second": 100.829,
7
+ "train_steps_per_second": 6.308
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b98906def43a21275da98472d2ecf560cc290a2e7fcbef119eee61b4420310d
3
  size 709090132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88e185b8f01e5d7aff8d660772f93e7497df7ea384348229e5a140bbc692235
3
  size 709090132
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.2825497290938373,
4
- "train_runtime": 130.292,
5
- "train_samples": 4405,
6
- "train_samples_per_second": 101.426,
7
- "train_steps_per_second": 6.355
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.24564219588448766,
4
+ "train_runtime": 262.0679,
5
+ "train_samples": 8808,
6
+ "train_samples_per_second": 100.829,
7
+ "train_steps_per_second": 6.308
8
  }
trainer_state.json CHANGED
@@ -3,33 +3,45 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 828,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 1.81,
13
- "learning_rate": 1.9806763285024154e-05,
14
- "loss": 0.3629,
15
  "step": 500
16
  },
 
 
 
 
 
 
 
 
 
 
 
 
17
  {
18
  "epoch": 3.0,
19
- "step": 828,
20
- "total_flos": 739078528656780.0,
21
- "train_loss": 0.2825497290938373,
22
- "train_runtime": 130.292,
23
- "train_samples_per_second": 101.426,
24
- "train_steps_per_second": 6.355
25
  }
26
  ],
27
  "logging_steps": 500,
28
- "max_steps": 828,
29
  "num_input_tokens_seen": 0,
30
  "num_train_epochs": 3,
31
  "save_steps": 500,
32
- "total_flos": 739078528656780.0,
33
  "train_batch_size": 16,
34
  "trial_name": null,
35
  "trial_params": null
 
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 1653,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.91,
13
+ "learning_rate": 3.487598306110103e-05,
14
+ "loss": 0.4056,
15
  "step": 500
16
  },
17
+ {
18
+ "epoch": 1.81,
19
+ "learning_rate": 1.975196612220206e-05,
20
+ "loss": 0.2455,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 2.72,
25
+ "learning_rate": 4.627949183303086e-06,
26
+ "loss": 0.1298,
27
+ "step": 1500
28
+ },
29
  {
30
  "epoch": 3.0,
31
+ "step": 1653,
32
+ "total_flos": 1395101222261760.0,
33
+ "train_loss": 0.24564219588448766,
34
+ "train_runtime": 262.0679,
35
+ "train_samples_per_second": 100.829,
36
+ "train_steps_per_second": 6.308
37
  }
38
  ],
39
  "logging_steps": 500,
40
+ "max_steps": 1653,
41
  "num_input_tokens_seen": 0,
42
  "num_train_epochs": 3,
43
  "save_steps": 500,
44
+ "total_flos": 1395101222261760.0,
45
  "train_batch_size": 16,
46
  "trial_name": null,
47
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad3b261ba9512d1ea5f688672dc310df685d90c435dad4b05f113db6468be4c3
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de11250632abb8e8078d16652e77145ac8ead77ea6eca4e95f9eb9fc9d3743bf
3
  size 4664