balaguru.s
commited on
Commit
•
787edde
1
Parent(s):
bb3db25
checking in the initial version files
Browse files- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/config.json +36 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/merges.txt +0 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/optimizer.pt +3 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/pytorch_model.bin +3 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/scheduler.pt +3 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/special_tokens_map.json +1 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/tokenizer_config.json +1 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/trainer_state.json +90 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/training_args.bin +3 -0
- Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/vocab.json +0 -0
- config.json +36 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 50
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"transformers_version": "4.3.2",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50257
|
36 |
+
}
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32b4bd756116544a3796f0262a49e2e52c359fce21f6f78df9729e68b3d47856
|
3 |
+
size 995611287
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7823b696f0e4c4df4fdae6c1a5ef0a9121fcd9dee4d4bc84a6f7186fb0fd0043
|
3 |
+
size 510408315
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:889349d3cbf5b5010c0ba7ca85c6a7d913eaedb8ba23c23ddcddc68d1d0ed5bd
|
3 |
+
size 623
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/trainer_state.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9876124858856201,
|
3 |
+
"best_model_checkpoint": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 5130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.19,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 2.1955,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.39,
|
18 |
+
"learning_rate": 4.4600431965442765e-05,
|
19 |
+
"loss": 1.8704,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.58,
|
24 |
+
"learning_rate": 3.920086393088553e-05,
|
25 |
+
"loss": 1.7624,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.78,
|
30 |
+
"learning_rate": 3.38012958963283e-05,
|
31 |
+
"loss": 1.7039,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.97,
|
36 |
+
"learning_rate": 2.840172786177106e-05,
|
37 |
+
"loss": 1.6626,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.0,
|
42 |
+
"eval_loss": 2.0070595741271973,
|
43 |
+
"eval_runtime": 102.1824,
|
44 |
+
"eval_samples_per_second": 386.446,
|
45 |
+
"step": 2565
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.17,
|
49 |
+
"learning_rate": 2.3002159827213822e-05,
|
50 |
+
"loss": 1.6134,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.36,
|
55 |
+
"learning_rate": 1.7602591792656588e-05,
|
56 |
+
"loss": 1.5933,
|
57 |
+
"step": 3500
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.56,
|
61 |
+
"learning_rate": 1.2203023758099353e-05,
|
62 |
+
"loss": 1.5742,
|
63 |
+
"step": 4000
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.75,
|
67 |
+
"learning_rate": 6.803455723542117e-06,
|
68 |
+
"loss": 1.5735,
|
69 |
+
"step": 4500
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 1.95,
|
73 |
+
"learning_rate": 1.4038876889848812e-06,
|
74 |
+
"loss": 1.5623,
|
75 |
+
"step": 5000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.0,
|
79 |
+
"eval_loss": 1.9876124858856201,
|
80 |
+
"eval_runtime": 102.2828,
|
81 |
+
"eval_samples_per_second": 386.067,
|
82 |
+
"step": 5130
|
83 |
+
}
|
84 |
+
],
|
85 |
+
"max_steps": 5130,
|
86 |
+
"num_train_epochs": 2,
|
87 |
+
"total_flos": 31377467721646080,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2f8fdc136c0bb46924b24f040a6637be9e4fc5e59e4d88776a32348fdfbc02
|
3 |
+
size 2159
|
Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
|
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": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 500
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"transformers_version": "4.3.2",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50257
|
36 |
+
}
|
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 sha256:967afc9178c6e73626cf1546465c3956939ccfe109696be51c5af53b0f82de15
|
3 |
+
size 510408315
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e2f8fdc136c0bb46924b24f040a6637be9e4fc5e59e4d88776a32348fdfbc02
|
3 |
+
size 2159
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|