Hugging Face's logo

gagan3012
/
project-code-py-micro

Text Generation
Transformers
PyTorch
JAX
gpt2
Inference Endpoints
text-generation-inference
Model card Files Community
1
gagan3012 commited on
Commit
14e2397
•
1 Parent(s): 27d7a9a

Initial commit

Browse files
Files changed (11) hide show
  1. all_results.json +23 -0
  2. config.json +43 -0
  3. eval_results.json +12 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer_config.json +1 -0
  8. train_results.json +14 -0
  9. trainer_state.json +29 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.1778761148452759,
4
+ "eval_mem_cpu_alloc_delta": 89380,
5
+ "eval_mem_cpu_peaked_delta": 18278,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 471300608,
8
+ "eval_runtime": 1.5089,
9
+ "eval_samples": 18,
10
+ "eval_samples_per_second": 11.929,
11
+ "init_mem_cpu_alloc_delta": 10338468,
12
+ "init_mem_cpu_peaked_delta": 18306,
13
+ "init_mem_gpu_alloc_delta": 334744576,
14
+ "init_mem_gpu_peaked_delta": 0,
15
+ "perplexity": 3.247469620697528,
16
+ "train_mem_cpu_alloc_delta": 1179270,
17
+ "train_mem_cpu_peaked_delta": 576384,
18
+ "train_mem_gpu_alloc_delta": 987446784,
19
+ "train_mem_gpu_peaked_delta": 2037095424,
20
+ "train_runtime": 145.1649,
21
+ "train_samples": 160,
22
+ "train_samples_per_second": 5.511
23
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "gradient_checkpointing": false,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 6,
27
+ "n_positions": 1024,
28
+ "resid_pdrop": 0.1,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "task_specific_params": {
35
+ "text-generation": {
36
+ "do_sample": true,
37
+ "max_length": 50
38
+ }
39
+ },
40
+ "transformers_version": "4.4.0.dev0",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.1778761148452759,
4
+ "eval_mem_cpu_alloc_delta": 89380,
5
+ "eval_mem_cpu_peaked_delta": 18278,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 471300608,
8
+ "eval_runtime": 1.5089,
9
+ "eval_samples": 18,
10
+ "eval_samples_per_second": 11.929,
11
+ "perplexity": 3.247469620697528
12
+ }
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 sha256:0d1384e1795de8262d0da2ed0224acec2d57d54b81f1fd98a4d613ab7074c8ed
3
+ size 333975623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "distilgpt2"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "init_mem_cpu_alloc_delta": 10338468,
4
+ "init_mem_cpu_peaked_delta": 18306,
5
+ "init_mem_gpu_alloc_delta": 334744576,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 1179270,
8
+ "train_mem_cpu_peaked_delta": 576384,
9
+ "train_mem_gpu_alloc_delta": 987446784,
10
+ "train_mem_gpu_peaked_delta": 2037095424,
11
+ "train_runtime": 145.1649,
12
+ "train_samples": 160,
13
+ "train_samples_per_second": 5.511
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 800,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.12,
12
+ "learning_rate": 1.8750000000000002e-05,
13
+ "loss": 1.419,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.0,
18
+ "step": 800,
19
+ "total_flos": 402616693555200.0,
20
+ "train_runtime": 145.1649,
21
+ "train_samples_per_second": 5.511
22
+ }
23
+ ],
24
+ "max_steps": 800,
25
+ "num_train_epochs": 5,
26
+ "total_flos": 402616693555200.0,
27
+ "trial_name": null,
28
+ "trial_params": null
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b16acc6f513b0fda5978ab2209d23d0b80dbbd510eb37b40967eeb866764966
3
+ size 2287
vocab.json ADDED
The diff for this file is too large to render. See raw diff