jimypbr commited on
Commit
1d2203c
1 Parent(s): c85441a

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-base",
3
+ "architectures": [
4
+ "PoptorchPipelinedDebertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_dropout": 0,
20
+ "pooler_hidden_act": "gelu",
21
+ "pooler_hidden_size": 768,
22
+ "pos_att_type": [
23
+ "c2p",
24
+ "p2c"
25
+ ],
26
+ "position_biased_input": false,
27
+ "relative_attention": true,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.18.0.dev0",
30
+ "type_vocab_size": 0,
31
+ "vocab_size": 50265
32
+ }
ipu_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "device_iterations": 1,
3
+ "embedding_serialization_factor": 0,
4
+ "enable_half_first_order_momentum": true,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "./exe_cache",
7
+ "gradient_accumulation_steps": 32,
8
+ "inference_device_iterations": 4,
9
+ "inference_replication_factor": 4,
10
+ "ipus_per_replica": 4,
11
+ "layers_per_ipu": [
12
+ 0,
13
+ 4,
14
+ 4,
15
+ 4
16
+ ],
17
+ "matmul_proportion": [
18
+ 0.1,
19
+ 0.1,
20
+ 0.1,
21
+ 0.1
22
+ ],
23
+ "optimizer_state_offchip": true,
24
+ "optimum_version": "1.0.0",
25
+ "output_mode": "final",
26
+ "profile_dir": "",
27
+ "recompute_checkpoint_every_layer": true,
28
+ "replicated_tensor_sharding": true,
29
+ "replication_factor": 4,
30
+ "seed": 1984,
31
+ "transformers_version": "4.18.0.dev0",
32
+ "use_popdist": false
33
+ }
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 sha256:0e1f09f6119a29f383a3d1ea74bf0c26235173cda966dd57182282e10454a2b6
3
+ size 277274547
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "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"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-base", "tokenizer_class": "DebertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc837e7a00a18e38df1f54977c690bcfafbbd010d97f787ceaf49b8bf70387c1
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff