NightMachinery commited on
Commit
22ac0cc
1 Parent(s): 8ab46c3

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
last-checkpoint/mlm/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": "nice",
10
+ "inv_adapter_reduction_factor": 2,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "relu",
18
+ "original_ln_after": true,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "config_id": "9ed5b5a29de19b71",
35
+ "hidden_size": 768,
36
+ "model_class": "XLMRobertaForMaskedLM",
37
+ "model_name": "xlm-roberta-base",
38
+ "model_type": "xlm-roberta",
39
+ "name": "mlm",
40
+ "version": "3.2.0a0"
41
+ }
last-checkpoint/mlm/head_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 768,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1
7
+ },
8
+ "model_class": "XLMRobertaForMaskedLM",
9
+ "model_name": "xlm-roberta-base",
10
+ "model_type": "xlm-roberta",
11
+ "name": null,
12
+ "num_labels": 2,
13
+ "version": "3.2.0a0"
14
+ }
last-checkpoint/mlm/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d68f83cd7fca4ace5b67862ca41e198d28ead11100294b8b1e41f64b8e3bd4
3
+ size 4782029
last-checkpoint/mlm/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0492ea9c95a77ad6c26888404030bfb64af235908ec2384b3c8e4702ae4212ea
3
+ size 771377007
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d725cb4b15853c8d8ab48cd9ac10b5e96548111b07054b1ab953c3a70f09c5ec
3
+ size 16297733
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef12f40a043f312c84af952a05fcc8c7e366ecdd0c0d9a6c44fad7c01b79ac67
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c549098864e24e541dbd3170d92c43e192c5c2a4bc019737309012c3628e02bc
3
+ size 627
last-checkpoint/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
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.2368199825286865,
3
+ "best_model_checkpoint": "./test-mlm/checkpoint-500",
4
+ "epoch": 0.3698224852071006,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.37,
12
+ "learning_rate": 9.6301775147929e-05,
13
+ "loss": 2.703,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.37,
18
+ "eval_accuracy": 0.5554450522128295,
19
+ "eval_loss": 2.2368199825286865,
20
+ "eval_runtime": 81.9171,
21
+ "eval_samples_per_second": 10.608,
22
+ "eval_steps_per_second": 2.124,
23
+ "step": 500
24
+ }
25
+ ],
26
+ "max_steps": 13520,
27
+ "num_train_epochs": 10,
28
+ "total_flos": 668841384960000.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df2b6641708b0e7a1eb6d8e9bc7c8eb16223fbde2ebdc920843d9462399a795
3
+ size 3515
runs/Mar03_09-17-36_375a4f73e1b6/1677835107.0174103/events.out.tfevents.1677835107.375a4f73e1b6.1412.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639184a0fe96e46d788fee136aecf52a94a8e64be686009b5cc6d3dbf37225ef
3
+ size 5686
runs/Mar03_09-17-36_375a4f73e1b6/events.out.tfevents.1677835107.375a4f73e1b6.1412.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476f58a9a67f6ecd0fc56f0be129bd93f2a5455151b41a4966c1be6e4d7de010
3
+ size 5016
runs/Mar03_09-29-00_375a4f73e1b6/1677835778.9662023/events.out.tfevents.1677835778.375a4f73e1b6.4551.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409bba58c6adf3132af51b6711e173a245f11086819b5c6aae8a8565031235e6
3
+ size 5686
runs/Mar03_09-29-00_375a4f73e1b6/events.out.tfevents.1677835778.375a4f73e1b6.4551.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6fc89aef6e6b2d7b786cba8d40d41e4329999cef59cfdaba398302c742c8ad
3
+ size 5495
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df2b6641708b0e7a1eb6d8e9bc7c8eb16223fbde2ebdc920843d9462399a795
3
+ size 3515