zhiyil commited on
Commit
85e15f5
1 Parent(s): 94ebe3b

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +58 -0
  3. ipu_config.json +30 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "PoptorchPipelinedRobertaForSequenceClassification"
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
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1,
33
+ "LABEL_10": 10,
34
+ "LABEL_11": 11,
35
+ "LABEL_12": 12,
36
+ "LABEL_2": 2,
37
+ "LABEL_3": 3,
38
+ "LABEL_4": 4,
39
+ "LABEL_5": 5,
40
+ "LABEL_6": 6,
41
+ "LABEL_7": 7,
42
+ "LABEL_8": 8,
43
+ "LABEL_9": 9
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "roberta",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "pad_token_id": 1,
51
+ "position_embedding_type": "absolute",
52
+ "problem_type": "single_label_classification",
53
+ "torch_dtype": "float16",
54
+ "transformers_version": "4.20.1",
55
+ "type_vocab_size": 1,
56
+ "use_cache": true,
57
+ "vocab_size": 50265
58
+ }
ipu_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_loss_scaling": false,
3
+ "device_iterations": 1,
4
+ "embedding_serialization_factor": 0,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "/tmp/exe_cache//intent_classification_ipu",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "gradient_accumulation_steps": 8,
9
+ "inference_device_iterations": 5,
10
+ "inference_replication_factor": 1,
11
+ "ipus_per_replica": 4,
12
+ "layers_per_ipu": [
13
+ 0,
14
+ 4,
15
+ 4,
16
+ 4
17
+ ],
18
+ "matmul_proportion": [
19
+ 0.25
20
+ ],
21
+ "optimizer_state_offchip": true,
22
+ "optimum_version": "1.5.1",
23
+ "output_mode": "final",
24
+ "recompute_checkpoint_every_layer": true,
25
+ "replicated_tensor_sharding": false,
26
+ "replication_factor": 1,
27
+ "seed": 42,
28
+ "sharded_execution_for_inference": false,
29
+ "transformers_version": "4.20.1"
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27341774510e1be27b75e59033eff26066b2cbebd2eb41561d7d9c90a4918725
3
+ size 249380077
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c8850b0e21bd93acf6ed748340c9d5cadfeb208acd3df700824097fbc039e7
3
+ size 2735