ZaaCo commited on
Commit
22c080e
·
verified ·
1 Parent(s): 120a213

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f8a76cbb60b5451580ffdde7d9a4462ff9b3bf8c4a7c8aac66e1154437aaa8
3
  size 470641664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3fc766ab0093cf34f31cdc674b7f31d8e666c9892cc02763446c4f4b0dfed5
3
  size 470641664
run-7/checkpoint-422/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "tokenizer_class": "XLMRobertaTokenizer",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 250037
27
+ }
run-7/checkpoint-422/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384518faf29f2ffe6efdc41419dfdf97b113150f026ea9437da57a6432f3af0a
3
+ size 470641664
run-7/checkpoint-422/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d1793ccf32ebdf0459ee293815e211cba235329e32c5869fd86d6778c1743e
3
+ size 941404410
run-7/checkpoint-422/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77709b1896d23d26e08bd16aab08ecbe725beb573571c18284b077f90d605b1
3
+ size 14244
run-7/checkpoint-422/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4760cd37cffe0806df52ee69f4b3f5ceee92cae8b3f6189fd108ec74f4a725
3
+ size 1064
run-7/checkpoint-422/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
run-7/checkpoint-422/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
+ }
run-7/checkpoint-422/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
3
+ size 17098273
run-7/checkpoint-422/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
run-7/checkpoint-422/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8176605504587156,
3
+ "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-7/checkpoint-422",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 422,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.8119266055045872,
14
+ "eval_loss": 0.44363221526145935,
15
+ "eval_runtime": 0.9149,
16
+ "eval_samples_per_second": 953.157,
17
+ "eval_steps_per_second": 60.119,
18
+ "step": 211
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.8176605504587156,
23
+ "eval_loss": 0.41796988248825073,
24
+ "eval_runtime": 1.0061,
25
+ "eval_samples_per_second": 866.703,
26
+ "eval_steps_per_second": 54.666,
27
+ "step": 422
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 422,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.7420099230252167e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 12
43
+ }
44
+ }
run-7/checkpoint-422/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c94191c0ad987493b022bf2df16f9d29bf8c5807f2f4ddb0c28f593979ff2cf
3
+ size 4984
runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640474.0db4763e2117.1712.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3878cd5dc5d5e9c05adac758f2da622567958c09f5e0b8030028f88075aa1088
3
+ size 4993
runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640514.0db4763e2117.1712.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187e739fc4ec06ea642ff38b8036fa69d1a2a77f7e618638ddb95c39655df138
3
+ size 5204
runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640879.0db4763e2117.1712.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecebd526810631e1c913902a6ebef9faf73d204f01f333ff67a095b609a56a4
3
+ size 6905
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c94191c0ad987493b022bf2df16f9d29bf8c5807f2f4ddb0c28f593979ff2cf
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e429b7a648ede63895839361e40497178ac098dbcde1deb4b4550ebe214f14
3
  size 4984