jimypbr commited on
Commit
2a93418
1 Parent(s): 81292cb

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +75 -0
  3. ipu_config.json +33 -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 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "PoptorchPipelinedBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float16",
72
+ "transformers_version": "4.20.1",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
ipu_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_loss_scaling": false,
3
+ "device_iterations": 1,
4
+ "embedding_serialization_factor": 5,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "/tmp/exe_cache//summarization",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "gradient_accumulation_steps": 16,
9
+ "inference_device_iterations": 6,
10
+ "inference_replication_factor": 4,
11
+ "ipus_per_replica": 4,
12
+ "layers_per_ipu": [
13
+ 0,
14
+ 6,
15
+ 3,
16
+ 3
17
+ ],
18
+ "matmul_proportion": [
19
+ 0.25,
20
+ 0.25,
21
+ 0.25,
22
+ 0.25
23
+ ],
24
+ "optimizer_state_offchip": true,
25
+ "optimum_version": "1.6.2.dev0",
26
+ "output_mode": "final",
27
+ "recompute_checkpoint_every_layer": true,
28
+ "replicated_tensor_sharding": true,
29
+ "replication_factor": 4,
30
+ "seed": 42,
31
+ "sharded_execution_for_inference": false,
32
+ "transformers_version": "4.20.1"
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cffdc0879c62753815d9da145619f031e0abcac471ee82c5fe3d559a24d3c63a
3
+ size 279026141
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4925b2494a8874f689f9d9fc9564a17f0fee3a6c513c352c87366e8901f0e4
3
+ size 2875