gagan3012 commited on
Commit
6060648
1 Parent(s): b7c7414

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 3.5185182094573975,
4
+ "eval_runtime": 2.7592,
5
+ "eval_samples": 7,
6
+ "eval_samples_per_second": 2.537,
7
+ "eval_steps_per_second": 0.362,
8
+ "perplexity": 33.734404089240414,
9
+ "train_loss": 3.5635623023623513,
10
+ "train_runtime": 37.6452,
11
+ "train_samples": 14,
12
+ "train_samples_per_second": 1.116,
13
+ "train_steps_per_second": 0.558
14
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
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": "float32",
36
+ "transformers_version": "4.12.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 3.5185182094573975,
4
+ "eval_runtime": 2.7592,
5
+ "eval_samples": 7,
6
+ "eval_samples_per_second": 2.537,
7
+ "eval_steps_per_second": 0.362,
8
+ "perplexity": 33.734404089240414
9
+ }
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:c767e50d8bb5a51bdda78ac7c467471cf2ebb3cdcd3f26dc0990336f7389ffd0
3
+ size 510403817
runs/Oct18_18-36-59_955a9c86ed3b/1634582266.2642858/events.out.tfevents.1634582266.955a9c86ed3b.560.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66452e424ced9078740384f52e0f965606ce417fd42d6f70184e1aef275bbe21
3
+ size 4516
runs/Oct18_18-36-59_955a9c86ed3b/events.out.tfevents.1634582266.955a9c86ed3b.560.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8aca0a2ff86c9da52ec9dc6017016e436709717c364a6f1585f9ec3f310e05
3
+ size 3745
runs/Oct18_18-36-59_955a9c86ed3b/events.out.tfevents.1634582308.955a9c86ed3b.560.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde009acf979c08688724582251fa6a1414fa9e30d87f653c923ac30779e671d
3
+ size 306
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
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, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 3.5635623023623513,
4
+ "train_runtime": 37.6452,
5
+ "train_samples": 14,
6
+ "train_samples_per_second": 1.116,
7
+ "train_steps_per_second": 0.558
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 21,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 3.0,
12
+ "step": 21,
13
+ "total_flos": 21948530688000.0,
14
+ "train_loss": 3.5635623023623513,
15
+ "train_runtime": 37.6452,
16
+ "train_samples_per_second": 1.116,
17
+ "train_steps_per_second": 0.558
18
+ }
19
+ ],
20
+ "max_steps": 21,
21
+ "num_train_epochs": 3,
22
+ "total_flos": 21948530688000.0,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827b0cdaea5d8b833e22f58344f5cd4eeb2ef6eb2e6e2fac33d1097dda7172ab
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff