Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +26 -0
- ipu_config.json +32 -0
- pytorch_model.bin +3 -0
- 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": "4.20.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 28996
|
26 |
+
}
|
ipu_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_loss_scaling": false,
|
3 |
+
"decompose_grad_sum": false,
|
4 |
+
"device_iterations": 1,
|
5 |
+
"embedding_serialization_factor": 0,
|
6 |
+
"enable_half_first_order_momentum": true,
|
7 |
+
"enable_half_partials": true,
|
8 |
+
"executable_cache_dir": "./exe_cache",
|
9 |
+
"execute_encoder_on_cpu_for_generation": false,
|
10 |
+
"gradient_accumulation_steps": 64,
|
11 |
+
"inference_device_iterations": 5,
|
12 |
+
"inference_replication_factor": 4,
|
13 |
+
"ipus_per_replica": 4,
|
14 |
+
"layers_per_ipu": [
|
15 |
+
0,
|
16 |
+
4,
|
17 |
+
4,
|
18 |
+
4
|
19 |
+
],
|
20 |
+
"matmul_proportion": 0.25,
|
21 |
+
"optimizer_state_offchip": false,
|
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": "4.20.0",
|
31 |
+
"use_popdist": false
|
32 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c810daa24852fac933d4302c7ca1dfc20b6efc87bb3b449e52d8f686052089d
|
3 |
+
size 216750379
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a07f4b4775b4ef66943e280c2f9b70cce030cc87c2c63268b6836974b1babb1
|
3 |
+
size 2671
|