jmamou commited on
Commit
caa5d21
1 Parent(s): 17eb282

initial commit

Browse files
all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 4.299047470092773,
4
+ "eval_mem_cpu_alloc_delta": -192512,
5
+ "eval_mem_cpu_peaked_delta": 0,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 1846225408,
8
+ "eval_runtime": 5.1104,
9
+ "eval_samples": 95,
10
+ "eval_samples_per_second": 18.59,
11
+ "init_mem_cpu_alloc_delta": -145973248,
12
+ "init_mem_cpu_peaked_delta": 1313857536,
13
+ "init_mem_gpu_alloc_delta": 1444470784,
14
+ "init_mem_gpu_peaked_delta": 0,
15
+ "perplexity": 73.629625865726,
16
+ "train_mem_cpu_alloc_delta": 90374144,
17
+ "train_mem_cpu_peaked_delta": 10436608,
18
+ "train_mem_gpu_alloc_delta": 4257890816,
19
+ "train_mem_gpu_peaked_delta": 2657059328,
20
+ "train_runtime": 3295.7162,
21
+ "train_samples": 4268,
22
+ "train_samples_per_second": 1.943
23
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "n_special": 0,
22
+ "predict_special_tokens": true,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.6.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 4.299047470092773,
4
+ "eval_mem_cpu_alloc_delta": -192512,
5
+ "eval_mem_cpu_peaked_delta": 0,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 1846225408,
8
+ "eval_runtime": 5.1104,
9
+ "eval_samples": 95,
10
+ "eval_samples_per_second": 18.59,
11
+ "perplexity": 73.629625865726
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 sha256:062b32c2d0f94ed04d3fd1eae2cb1d6d4609bab8ba8e9fdaf5ac5c566accd4a4
3
+ size 1444531445
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-medium"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": -145973248,
4
+ "init_mem_cpu_peaked_delta": 1313857536,
5
+ "init_mem_gpu_alloc_delta": 1444470784,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 90374144,
8
+ "train_mem_cpu_peaked_delta": 10436608,
9
+ "train_mem_gpu_alloc_delta": 4257890816,
10
+ "train_mem_gpu_peaked_delta": 2657059328,
11
+ "train_runtime": 3295.7162,
12
+ "train_samples": 4268,
13
+ "train_samples_per_second": 1.943
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 6402,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.23,
12
+ "learning_rate": 4.609497032177445e-05,
13
+ "loss": 3.0016,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.47,
18
+ "learning_rate": 4.218994064354889e-05,
19
+ "loss": 2.6439,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.7,
24
+ "learning_rate": 3.828491096532334e-05,
25
+ "loss": 2.4277,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.94,
30
+ "learning_rate": 3.437988128709778e-05,
31
+ "loss": 2.27,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.17,
36
+ "learning_rate": 3.047485160887223e-05,
37
+ "loss": 1.9681,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.41,
42
+ "learning_rate": 2.6569821930646678e-05,
43
+ "loss": 1.8284,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.64,
48
+ "learning_rate": 2.266479225242112e-05,
49
+ "loss": 1.7601,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.87,
54
+ "learning_rate": 1.8759762574195563e-05,
55
+ "loss": 1.7051,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.11,
60
+ "learning_rate": 1.4854732895970011e-05,
61
+ "loss": 1.595,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 2.34,
66
+ "learning_rate": 1.0949703217744455e-05,
67
+ "loss": 1.495,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.58,
72
+ "learning_rate": 7.0446735395189e-06,
73
+ "loss": 1.4778,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.81,
78
+ "learning_rate": 3.1396438612933463e-06,
79
+ "loss": 1.4717,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 3.0,
84
+ "step": 6402,
85
+ "total_flos": 438186742382592.0,
86
+ "train_runtime": 3295.7162,
87
+ "train_samples_per_second": 1.943
88
+ }
89
+ ],
90
+ "max_steps": 6402,
91
+ "num_train_epochs": 3,
92
+ "total_flos": 438186742382592.0,
93
+ "trial_name": null,
94
+ "trial_params": null
95
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46814eb34a4a3a0ca39173093be0eebf244a2a3f6d8ce8fda98545b65bec4068
3
+ size 2170
vocab.json ADDED
The diff for this file is too large to render. See raw diff