zack-paperspace commited on
Commit
58e75f5
1 Parent(s): 3180bcd

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +26 -0
  3. ipu_config.json +28 -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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
3
+ "architectures": [
4
+ "PoptorchPipelinedBertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.20.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 28996
26
+ }
ipu_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/language_modelling_from_scratch",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "gradient_accumulation_steps": 64,
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": 0.25,
19
+ "optimizer_state_offchip": false,
20
+ "optimum_version": "1.5.2",
21
+ "output_mode": "final",
22
+ "recompute_checkpoint_every_layer": true,
23
+ "replicated_tensor_sharding": false,
24
+ "replication_factor": 1,
25
+ "seed": 42,
26
+ "sharded_execution_for_inference": false,
27
+ "transformers_version": "4.20.1"
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5156a1c9857df71ffd7d8250de16adf66ea2a73f5db844e2824b6ab486e8888b
3
+ size 216750379
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1487b56232b4f746dd2a39b79be53561a3a2b46e97e1eb31448825aff1a8d667
3
+ size 2735