marcsun13 HF staff commited on
Commit
102e533
1 Parent(s): b623f70

Training in progress, step 5, checkpoint

Browse files
checkpoint-5/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
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": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 28996
26
+ }
checkpoint-5/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.40.2"
5
+ }
checkpoint-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ed8e33be3f30165ded875de0d3d8a94e75e3302ebc28c7960784f6abce0475
3
+ size 433386912
checkpoint-5/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2718ff8526278b7841fa6f6f93b7478030381c430ffb91ae1df75b12527d1395
3
+ size 866895354
checkpoint-5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797ae513ea2c3b4b8a096003d70d7015814d17c41ef73abc3424bd7235872747
3
+ size 14244
checkpoint-5/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c67f4c0c84490d9ab91ce25949988532c8a1049298729caa9fba405b74ea36
3
+ size 1064
checkpoint-5/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8333333333333334,
5
+ "eval_steps": 500,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 30,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 5,
15
+ "save_steps": 5,
16
+ "total_flos": 10795317624.0,
17
+ "train_batch_size": 1,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0bd895b3cb35ae663511b545c6c33197aed3cbbdf468d9f21ce4fc75a8ec8f
3
+ size 5048