gantenbe commited on
Commit
1c41a0c
1 Parent(s): dea3240

finish finetuining

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "init_mem_cpu_alloc_delta": 347038,
4
+ "init_mem_cpu_peaked_delta": 18306,
5
+ "init_mem_gpu_alloc_delta": 1109893120,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 459108,
8
+ "train_mem_cpu_peaked_delta": 213284,
9
+ "train_mem_gpu_alloc_delta": 3344827392,
10
+ "train_mem_gpu_peaked_delta": 3576786944,
11
+ "train_runtime": 41.8596,
12
+ "train_samples": 821,
13
+ "train_samples_per_second": 2.461
14
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/cloud-user/gpt2_colab/models/xlm_e1_CHpart_adapt_",
3
+ "architectures": [
4
+ "XLMRobertaForQuestionAnswering"
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": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "transformers_version": "4.4.0.dev0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc353177f69fb72a19871eb4bfaba27bd09b318e5882f353cdbac1aa68f4b61
3
+ size 1109906123
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "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/xlm_e1_CHpart_adapt_"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "init_mem_cpu_alloc_delta": 347038,
4
+ "init_mem_cpu_peaked_delta": 18306,
5
+ "init_mem_gpu_alloc_delta": 1109893120,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 459108,
8
+ "train_mem_cpu_peaked_delta": 213284,
9
+ "train_mem_gpu_alloc_delta": 3344827392,
10
+ "train_mem_gpu_peaked_delta": 3576786944,
11
+ "train_runtime": 41.8596,
12
+ "train_samples": 821,
13
+ "train_samples_per_second": 2.461
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": 524828670736896.0,
14
+ "train_runtime": 41.8596,
15
+ "train_samples_per_second": 2.461
16
+ }
17
+ ],
18
+ "max_steps": 103,
19
+ "num_train_epochs": 1,
20
+ "total_flos": 524828670736896.0,
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 sha256:6ff7eb45a320a1a7e212da5694b94384ac6f72d56c9274c93eef208dd6094489
3
+ size 2351