Nick Ball commited on
Commit
be7c32c
1 Parent(s): e40724f

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "PoptorchPipelinedGPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.20.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
ipu_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_loss_scaling": false,
3
+ "device_iterations": 2,
4
+ "embedding_serialization_factor": 4,
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": true,
20
+ "optimum_version": "1.5.1",
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
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bd6ab684d4a7e912bdfaa6ebead7c5aab4b168087b30d1bb14c90fc1655b68
3
+ size 261514473
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "sgugger/gpt2-like-tokenizer",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bc9f09650137cc443b7cf37c7fcd1c8f7039133b589b7e9c25632c17dd8c1a
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff