jimypbr commited on
Commit
fddddad
1 Parent(s): 0ef0efd

End of training

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_HasAns_exact": 78.12078272604589,
4
+ "eval_HasAns_f1": 84.65686766557162,
5
+ "eval_HasAns_total": 5928,
6
+ "eval_NoAns_exact": 82.03532380151388,
7
+ "eval_NoAns_f1": 82.03532380151388,
8
+ "eval_NoAns_total": 5945,
9
+ "eval_best_exact": 80.08085572306915,
10
+ "eval_best_exact_thresh": 0.0,
11
+ "eval_best_f1": 83.34421894394902,
12
+ "eval_best_f1_thresh": 0.0,
13
+ "eval_exact": 80.08085572306915,
14
+ "eval_f1": 83.34421894394914,
15
+ "eval_samples": 12165,
16
+ "eval_total": 11873,
17
+ "train_loss": 0.9981908340553056,
18
+ "train_runtime": 284.2177,
19
+ "train_samples": 131823,
20
+ "train_samples_per_second": 1391.43,
21
+ "train_steps_per_second": 5.425
22
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "PoptorchPipelinedRobertaForQuestionAnswering"
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": "4.18.0.dev0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a418c97dd30993901dae3fdc148c4a763d2b8a768542609664a0b19845839c
3
+ size 51639652
eval_null_odds.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_HasAns_exact": 78.12078272604589,
4
+ "eval_HasAns_f1": 84.65686766557162,
5
+ "eval_HasAns_total": 5928,
6
+ "eval_NoAns_exact": 82.03532380151388,
7
+ "eval_NoAns_f1": 82.03532380151388,
8
+ "eval_NoAns_total": 5945,
9
+ "eval_best_exact": 80.08085572306915,
10
+ "eval_best_exact_thresh": 0.0,
11
+ "eval_best_f1": 83.34421894394902,
12
+ "eval_best_f1_thresh": 0.0,
13
+ "eval_exact": 80.08085572306915,
14
+ "eval_f1": 83.34421894394914,
15
+ "eval_samples": 12165,
16
+ "eval_total": 11873
17
+ }
ipu_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 16,
8
+ "inference_device_iterations": 5,
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
+ 0.25
19
+ ],
20
+ "optimizer_state_offchip": false,
21
+ "optimum_version": "0.1.2",
22
+ "output_mode": "final",
23
+ "profile_dir": "",
24
+ "recompute_checkpoint_every_layer": true,
25
+ "replicated_tensor_sharding": true,
26
+ "replication_factor": 4,
27
+ "seed": 1984,
28
+ "use_popdist": false
29
+ }
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 sha256:5499f29b5af86820cee3fb671d790f79ad0033b74b7f9c6bf2fc59cc06ec99cd
3
+ size 248181489
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.9981908340553056,
4
+ "train_runtime": 284.2177,
5
+ "train_samples": 131823,
6
+ "train_samples_per_second": 1391.43,
7
+ "train_steps_per_second": 5.425
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec0a9d3da96a3ffa1a591a34ffff96c8922c4b9d0f8ef585db652ce8fdc3fd4
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff