internetoftim commited on
Commit
6df10e3
1 Parent(s): bfda5e2

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. .gitignore +1 -0
  2. config.json +28 -0
  3. ipu_config.json +32 -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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.21.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
ipu_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "/tmp/exe_cache/",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "gradient_accumulation_steps": 16,
9
+ "inference_device_iterations": 5,
10
+ "inference_replication_factor": 4,
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": "1.3.0",
23
+ "output_mode": "final",
24
+ "profile_dir": "",
25
+ "recompute_checkpoint_every_layer": true,
26
+ "replicated_tensor_sharding": true,
27
+ "replication_factor": 4,
28
+ "seed": 42,
29
+ "sharded_execution_for_inference": false,
30
+ "transformers_version": "4.21.0",
31
+ "use_popdist": false
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a154483e959c045b8f2248df62643101cfee332f008b687e8fee5c327c1f2b
3
+ size 249363181
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb3539f7ab1baf61fb231cfaf86091641b94b899cfa696c3c78eed40b886a77
3
+ size 2671