gantenbe commited on
Commit
be7917e
1 Parent(s): 9c55768

german finetuning

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "init_mem_cpu_alloc_delta": 346890,
4
+ "init_mem_cpu_peaked_delta": 18306,
5
+ "init_mem_gpu_alloc_delta": 497524736,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 587733,
8
+ "train_mem_cpu_peaked_delta": 221105,
9
+ "train_mem_gpu_alloc_delta": 1509221376,
10
+ "train_mem_gpu_peaked_delta": 3575343104,
11
+ "train_runtime": 41.401,
12
+ "train_samples": 818,
13
+ "train_samples_per_second": 2.488
14
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/cloud-user/gpt2_colab/models/roberta_e1_CHpart_adapt_",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.4.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02ffd4e04248e24a1498b724938940fe18c842e8866cd0ca0bbfa9cdc3aff50
3
+ size 496314063
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/cloud-user/gpt2_colab/models/roberta_e1_CHpart_adapt_"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "init_mem_cpu_alloc_delta": 346890,
4
+ "init_mem_cpu_peaked_delta": 18306,
5
+ "init_mem_gpu_alloc_delta": 497524736,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 587733,
8
+ "train_mem_cpu_peaked_delta": 221105,
9
+ "train_mem_gpu_alloc_delta": 1509221376,
10
+ "train_mem_gpu_peaked_delta": 3575343104,
11
+ "train_runtime": 41.401,
12
+ "train_samples": 818,
13
+ "train_samples_per_second": 2.488
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 103,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "step": 103,
13
+ "total_flos": 233805958972416.0,
14
+ "train_runtime": 41.401,
15
+ "train_samples_per_second": 2.488
16
+ }
17
+ ],
18
+ "max_steps": 103,
19
+ "num_train_epochs": 1,
20
+ "total_flos": 233805958972416.0,
21
+ "trial_name": null,
22
+ "trial_params": null
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594c840f0c5a7a6ffb6e859fb111ee38506bba85a977cec952e7414688f1bd2b
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff