Payoto commited on
Commit
05672ab
1 Parent(s): b180869

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "PoptorchPipelinedRobertaForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
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
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.24.0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
ipu_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decompose_grad_sum": false,
3
+ "device_iterations": 1,
4
+ "embedding_serialization_factor": 0,
5
+ "enable_half_first_order_momentum": true,
6
+ "enable_half_partials": true,
7
+ "executable_cache_dir": "/tmp/exe_cache",
8
+ "execute_encoder_on_cpu_for_generation": false,
9
+ "gradient_accumulation_steps": 16,
10
+ "inference_device_iterations": 5,
11
+ "inference_replication_factor": 1,
12
+ "ipus_per_replica": 4,
13
+ "layers_per_ipu": [
14
+ 0,
15
+ 4,
16
+ 4,
17
+ 4
18
+ ],
19
+ "matmul_proportion": [
20
+ 0.25
21
+ ],
22
+ "optimizer_state_offchip": true,
23
+ "optimum_version": "1.4.1",
24
+ "output_mode": "final",
25
+ "profile_dir": "",
26
+ "recompute_checkpoint_every_layer": true,
27
+ "replicated_tensor_sharding": false,
28
+ "replication_factor": 1,
29
+ "seed": 42,
30
+ "sharded_execution_for_inference": false,
31
+ "transformers_version": "4.24.0",
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 sha256:57d56b5c78641aeb5f0384df9c2fc1c74a8cf39d252ce179268371f6d8608f9b
3
+ size 249361645
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289af17c2cc930989397aff4a5aa4b60661acf488970848eb18b1b14ae06a2d1
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff