Hugging Face's logo

jeremierostan
/
Roboerta

TensorBoard
Safetensors
roberta
Model card Files Metrics Community
jeremierostan commited on
Commit
ff71bef
·
verified ·
1 Parent(s): ecb865a

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. checkpoint-2742/config.json +26 -0
  2. checkpoint-2742/model.safetensors +3 -0
  3. checkpoint-2742/optimizer.pt +3 -0
  4. checkpoint-2742/rng_state.pth +3 -0
  5. checkpoint-2742/scheduler.pt +3 -0
  6. checkpoint-2742/trainer_state.json +68 -0
  7. checkpoint-2742/training_args.bin +3 -0
  8. config.json +26 -0
  9. merges.txt +0 -0
  10. model.safetensors +3 -0
  11. runs/Nov07_15-02-54_a4a941b1ce18/events.out.tfevents.1730991791.a4a941b1ce18.4039.0 +3 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
checkpoint-2742/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-2742/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6be18bd5780ada60017e4ed82dca74e67233300e7da321494338bd5099718c7
3
+ size 334030264
checkpoint-2742/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe2f8251757144e5d16d04e233229731704905a5dba9adbbea1d06b603a2666
3
+ size 668124218
checkpoint-2742/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373be77e2bf8fbc37b64087b43037823b24ffe431842ed2105008620e8d4e081
3
+ size 14244
checkpoint-2742/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f31c51c509dd875bd5d678f84a30a260222add871dd098c16f6ecba09645a10
3
+ size 1064
checkpoint-2742/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2742,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18234865061998543,
13
+ "grad_norm": 2.2784087657928467,
14
+ "learning_rate": 4.088256746900073e-05,
15
+ "loss": 7.3652,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.36469730123997085,
20
+ "grad_norm": 2.589686870574951,
21
+ "learning_rate": 3.1765134938001465e-05,
22
+ "loss": 6.6994,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.5470459518599562,
27
+ "grad_norm": 2.6017775535583496,
28
+ "learning_rate": 2.264770240700219e-05,
29
+ "loss": 6.5242,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.7293946024799417,
34
+ "grad_norm": 2.9507861137390137,
35
+ "learning_rate": 1.353026987600292e-05,
36
+ "loss": 6.4029,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.9117432530999271,
41
+ "grad_norm": 2.6451339721679688,
42
+ "learning_rate": 4.412837345003647e-06,
43
+ "loss": 6.3141,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 2742,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 1,
51
+ "save_steps": 10000,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": true
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 5814854438055936.0,
65
+ "train_batch_size": 64,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-2742/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad89d324232c1591750061521ce837d3ad4d6da0ec0ec331bff453875c0ed07e
3
+ size 5304
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6be18bd5780ada60017e4ed82dca74e67233300e7da321494338bd5099718c7
3
+ size 334030264
runs/Nov07_15-02-54_a4a941b1ce18/events.out.tfevents.1730991791.a4a941b1ce18.4039.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f30370cd8f3979a17c23ebf87131431de73eba941adfcc67ce60f424cfef37
3
+ size 6373
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad89d324232c1591750061521ce837d3ad4d6da0ec0ec331bff453875c0ed07e
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff