luckycat37 commited on
Commit
586c89f
1 Parent(s): bec95e4

Upload 14 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.4,
3
+ "learning_rate": 5.9914530099610235e-06,
4
+ "train_loss": 4.845045407784673,
5
+ "train_runtime": 1698.7001,
6
+ "train_samples": 2371626,
7
+ "train_samples_per_second": 558.507,
8
+ "train_steps_per_second": 1.091
9
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../../output_models/clm_gpt2_small_2022_new_wmt_0o6_wiki_0o4",
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": "4.29.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50258
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.29.2"
6
+ }
ipu_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_loss_scaling": false,
3
+ "device_iterations": 2,
4
+ "embedding_serialization_factor": 4,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "./exe_cache",
7
+ "execute_encoder_on_cpu_for_generation": false,
8
+ "explicit_ir_inference": false,
9
+ "gradient_accumulation_steps": 64,
10
+ "inference_device_iterations": 5,
11
+ "inference_embedding_serialization_factor": 1,
12
+ "inference_ipus_per_replica": 4,
13
+ "inference_layers_per_ipu": [
14
+ 0,
15
+ 4,
16
+ 4,
17
+ 4
18
+ ],
19
+ "inference_matmul_proportion": 0.25,
20
+ "inference_parallelize_kwargs": {},
21
+ "inference_projection_serialization_factor": 1,
22
+ "inference_replication_factor": 4,
23
+ "inference_serialized_embedding_splits_per_ipu": null,
24
+ "inference_serialized_projection_splits_per_ipu": null,
25
+ "ipus_per_replica": 4,
26
+ "layers_per_ipu": [
27
+ 0,
28
+ 4,
29
+ 4,
30
+ 4
31
+ ],
32
+ "matmul_proportion": 0.25,
33
+ "optimizer_state_offchip": true,
34
+ "optimum_version": "1.6.1",
35
+ "output_mode": "final",
36
+ "parallelize_kwargs": {},
37
+ "projection_serialization_factor": 1,
38
+ "recompute_checkpoint_every_layer": true,
39
+ "replicated_tensor_sharding": true,
40
+ "replication_factor": 4,
41
+ "seed": 42,
42
+ "serialized_embedding_splits_per_ipu": null,
43
+ "serialized_projection_splits_per_ipu": null,
44
+ "transformers_version": "4.29.2"
45
+ }
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 sha256:79b96a5af9f17f9196630eb12007c749140a32fb01fbcf6965bdfe7c2dbc70b0
3
+ size 261517501
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.4,
3
+ "learning_rate": 5.9914530099610235e-06,
4
+ "train_loss": 4.845045407784673,
5
+ "train_runtime": 1698.7001,
6
+ "train_samples": 2371626,
7
+ "train_samples_per_second": 558.507,
8
+ "train_steps_per_second": 1.091
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ebbe630fc8a36c7f7fe42ef931e7a0970098c8797edc5e1e3bda0374bb950d0
3
+ size 2811
vocab.json ADDED
The diff for this file is too large to render. See raw diff