Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-10000/config.json +39 -0
- checkpoint-10000/generation_config.json +6 -0
- checkpoint-10000/merges.txt +0 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/pytorch_model.bin +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/special_tokens_map.json +6 -0
- checkpoint-10000/tokenizer.json +0 -0
- checkpoint-10000/tokenizer_config.json +13 -0
- checkpoint-10000/trainer_state.json +0 -0
- checkpoint-10000/training_args.bin +3 -0
- checkpoint-10000/vocab.json +0 -0
- checkpoint-10100/config.json +39 -0
- checkpoint-10100/generation_config.json +6 -0
- checkpoint-10100/merges.txt +0 -0
- checkpoint-10100/optimizer.pt +3 -0
- checkpoint-10100/pytorch_model.bin +3 -0
- checkpoint-10100/rng_state.pth +3 -0
- checkpoint-10100/scheduler.pt +3 -0
- checkpoint-10100/special_tokens_map.json +6 -0
- checkpoint-10100/tokenizer.json +0 -0
- checkpoint-10100/tokenizer_config.json +13 -0
- checkpoint-10100/trainer_state.json +0 -0
- checkpoint-10100/training_args.bin +3 -0
- checkpoint-10100/vocab.json +0 -0
- checkpoint-10200/config.json +39 -0
- checkpoint-10200/generation_config.json +6 -0
- checkpoint-10200/merges.txt +0 -0
- checkpoint-10200/optimizer.pt +3 -0
- checkpoint-10200/pytorch_model.bin +3 -0
- checkpoint-10200/rng_state.pth +3 -0
- checkpoint-10200/scheduler.pt +3 -0
- checkpoint-10200/special_tokens_map.json +6 -0
- checkpoint-10200/tokenizer.json +0 -0
- checkpoint-10200/tokenizer_config.json +13 -0
- checkpoint-10200/trainer_state.json +0 -0
- checkpoint-10200/training_args.bin +3 -0
- checkpoint-10200/vocab.json +0 -0
- checkpoint-10300/config.json +39 -0
- checkpoint-10300/generation_config.json +6 -0
- checkpoint-10300/merges.txt +0 -0
- checkpoint-10300/optimizer.pt +3 -0
- checkpoint-10300/pytorch_model.bin +3 -0
- checkpoint-10300/rng_state.pth +3 -0
- checkpoint-10300/scheduler.pt +3 -0
- checkpoint-10300/special_tokens_map.json +6 -0
- checkpoint-10300/tokenizer.json +0 -0
- checkpoint-10300/tokenizer_config.json +13 -0
- checkpoint-10300/train.dat +206 -0
checkpoint-10000/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./codeparrot-ds/",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 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": "4.33.3",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50000
|
| 39 |
+
}
|
checkpoint-10000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.3"
|
| 6 |
+
}
|
checkpoint-10000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6479d2a768dcc096bcd6a136a9f64315d6b835e4760777b900f45492b21f5122
|
| 3 |
+
size 994063290
|
checkpoint-10000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b84e41fd94f5f566cc125a7931cceec7c774a25f2b6c5ec0c6cc2442e0a52d4
|
| 3 |
+
size 497018202
|
checkpoint-10000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7625f0f1a72e7d469ee566dd3a4ceef850cfb55f0a54fb9fe4af8a847f74d25e
|
| 3 |
+
size 14244
|
checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc6c5cd66f35ac55512c851ca5dff0e5e575e0fd65c85e7aebf0f487e731d7e7
|
| 3 |
+
size 1064
|
checkpoint-10000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-10000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"max_length": 128,
|
| 7 |
+
"model_max_length": 1024,
|
| 8 |
+
"stride": 0,
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"truncation_side": "right",
|
| 11 |
+
"truncation_strategy": "longest_first",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
checkpoint-10000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc996ddf5bf2aa938695ca3827f270f481a84e212a0153a85f2b519a3755070a
|
| 3 |
+
size 4472
|
checkpoint-10000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10100/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./codeparrot-ds/",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 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": "4.33.3",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50000
|
| 39 |
+
}
|
checkpoint-10100/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.3"
|
| 6 |
+
}
|
checkpoint-10100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa62109375456addce2ffbb3d22759bb9b8a37a9e26c0dd2e44146ec9312d3b3
|
| 3 |
+
size 994063290
|
checkpoint-10100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b121c385cc4f4216a0c396a4bef6b6b881b9d48bd980f9bad3084cbe0399577
|
| 3 |
+
size 497018202
|
checkpoint-10100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bffe5b3975040df280cba625c904855047af23bcabe582a256110c0ca4011ccf
|
| 3 |
+
size 14244
|
checkpoint-10100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d64e8dea00abfe7e696dc543a5630d1ddec59e55ea651d0da2cb501e3226365
|
| 3 |
+
size 1064
|
checkpoint-10100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-10100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"max_length": 128,
|
| 7 |
+
"model_max_length": 1024,
|
| 8 |
+
"stride": 0,
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"truncation_side": "right",
|
| 11 |
+
"truncation_strategy": "longest_first",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
checkpoint-10100/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc996ddf5bf2aa938695ca3827f270f481a84e212a0153a85f2b519a3755070a
|
| 3 |
+
size 4472
|
checkpoint-10100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10200/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./codeparrot-ds/",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 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": "4.33.3",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50000
|
| 39 |
+
}
|
checkpoint-10200/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.3"
|
| 6 |
+
}
|
checkpoint-10200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b37a0918902281a572deee590bc7f3b0789bd4834fa1e35d5800065a550fb4a
|
| 3 |
+
size 994063290
|
checkpoint-10200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a454bf8fe688683f31d2bd2db9f5003f9b317c52b377a0cd0ecf1bbeb5abda53
|
| 3 |
+
size 497018202
|
checkpoint-10200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:367e8eefcd860a5710c6593ffe363738ece6da93256c72f1ab7c4fdfc7f3c1fb
|
| 3 |
+
size 14244
|
checkpoint-10200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29651c459843f7ffb2c5b6bccfef8cd6019089d0f5672017a3d5415cbb2fb175
|
| 3 |
+
size 1064
|
checkpoint-10200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-10200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"max_length": 128,
|
| 7 |
+
"model_max_length": 1024,
|
| 8 |
+
"stride": 0,
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"truncation_side": "right",
|
| 11 |
+
"truncation_strategy": "longest_first",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
checkpoint-10200/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc996ddf5bf2aa938695ca3827f270f481a84e212a0153a85f2b519a3755070a
|
| 3 |
+
size 4472
|
checkpoint-10200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10300/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./codeparrot-ds/",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 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": "4.33.3",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50000
|
| 39 |
+
}
|
checkpoint-10300/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.33.3"
|
| 6 |
+
}
|
checkpoint-10300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e6aa93188b69ede317eb5d67f8b578ed660b7a884e5f3f313d78d2f1e7c9db
|
| 3 |
+
size 994063290
|
checkpoint-10300/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efb1513920ebadc0cdda0d242b5878572c0059c8f98cf67fd75ff2bc72253361
|
| 3 |
+
size 497018202
|
checkpoint-10300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d30ce49f407fd9749c928157beb4db7444fdba9205230971d6f28cbfe6efef0d
|
| 3 |
+
size 14244
|
checkpoint-10300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b723d1614f7aeef2c6d6b38cb96b04a1f6f5ab23dd498799924067b79675391f
|
| 3 |
+
size 1064
|
checkpoint-10300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-10300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"max_length": 128,
|
| 7 |
+
"model_max_length": 1024,
|
| 8 |
+
"stride": 0,
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"truncation_side": "right",
|
| 11 |
+
"truncation_strategy": "longest_first",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
+
}
|
checkpoint-10300/train.dat
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"loss": 4.2182,
|
| 2 |
+
"loss": 3.9201,
|
| 3 |
+
"loss": 3.8079,
|
| 4 |
+
"loss": 3.9802,
|
| 5 |
+
"loss": 3.9497,
|
| 6 |
+
"loss": 3.7474,
|
| 7 |
+
"loss": 3.7449,
|
| 8 |
+
"loss": 3.6893,
|
| 9 |
+
"loss": 3.518,
|
| 10 |
+
"loss": 3.5812,
|
| 11 |
+
"loss": 3.4697,
|
| 12 |
+
"loss": 3.4005,
|
| 13 |
+
"loss": 3.202,
|
| 14 |
+
"loss": 3.2481,
|
| 15 |
+
"loss": 3.4377,
|
| 16 |
+
"loss": 3.2781,
|
| 17 |
+
"loss": 3.1309,
|
| 18 |
+
"loss": 3.0013,
|
| 19 |
+
"loss": 2.9647,
|
| 20 |
+
"loss": 3.0833,
|
| 21 |
+
"loss": 2.9659,
|
| 22 |
+
"loss": 2.9136,
|
| 23 |
+
"loss": 2.9501,
|
| 24 |
+
"loss": 3.0921,
|
| 25 |
+
"loss": 2.8951,
|
| 26 |
+
"loss": 2.8615,
|
| 27 |
+
"loss": 2.886,
|
| 28 |
+
"loss": 2.6634,
|
| 29 |
+
"loss": 2.7992,
|
| 30 |
+
"loss": 2.7284,
|
| 31 |
+
"loss": 2.5383,
|
| 32 |
+
"loss": 2.9158,
|
| 33 |
+
"loss": 2.569,
|
| 34 |
+
"loss": 2.639,
|
| 35 |
+
"loss": 2.6051,
|
| 36 |
+
"loss": 2.5859,
|
| 37 |
+
"loss": 2.8165,
|
| 38 |
+
"loss": 2.7914,
|
| 39 |
+
"loss": 2.8124,
|
| 40 |
+
"loss": 2.536,
|
| 41 |
+
"loss": 2.4832,
|
| 42 |
+
"loss": 2.7004,
|
| 43 |
+
"loss": 2.5611,
|
| 44 |
+
"loss": 2.4008,
|
| 45 |
+
"loss": 2.6482,
|
| 46 |
+
"loss": 2.4384,
|
| 47 |
+
"loss": 2.6389,
|
| 48 |
+
"loss": 2.33,
|
| 49 |
+
"loss": 2.3862,
|
| 50 |
+
"loss": 2.4908,
|
| 51 |
+
"loss": 2.4269,
|
| 52 |
+
"loss": 2.4281,
|
| 53 |
+
"loss": 2.3384,
|
| 54 |
+
"loss": 2.6808,
|
| 55 |
+
"loss": 2.4791,
|
| 56 |
+
"loss": 2.4134,
|
| 57 |
+
"loss": 2.2267,
|
| 58 |
+
"loss": 2.4479,
|
| 59 |
+
"loss": 2.4216,
|
| 60 |
+
"loss": 2.4072,
|
| 61 |
+
"loss": 2.3671,
|
| 62 |
+
"loss": 2.2338,
|
| 63 |
+
"loss": 2.3592,
|
| 64 |
+
"loss": 2.5145,
|
| 65 |
+
"loss": 2.6603,
|
| 66 |
+
"loss": 2.3985,
|
| 67 |
+
"loss": 2.1567,
|
| 68 |
+
"loss": 2.4226,
|
| 69 |
+
"loss": 2.2642,
|
| 70 |
+
"loss": 2.2697,
|
| 71 |
+
"loss": 2.3797,
|
| 72 |
+
"loss": 2.2473,
|
| 73 |
+
"loss": 2.3887,
|
| 74 |
+
"loss": 2.2165,
|
| 75 |
+
"loss": 2.2813,
|
| 76 |
+
"loss": 2.2621,
|
| 77 |
+
"loss": 2.2801,
|
| 78 |
+
"loss": 2.2543,
|
| 79 |
+
"loss": 2.3779,
|
| 80 |
+
"loss": 2.3853,
|
| 81 |
+
"loss": 2.2737,
|
| 82 |
+
"loss": 2.3751,
|
| 83 |
+
"loss": 2.0766,
|
| 84 |
+
"loss": 2.2456,
|
| 85 |
+
"loss": 2.1394,
|
| 86 |
+
"loss": 2.0715,
|
| 87 |
+
"loss": 2.2069,
|
| 88 |
+
"loss": 2.1304,
|
| 89 |
+
"loss": 2.1161,
|
| 90 |
+
"loss": 2.1512,
|
| 91 |
+
"loss": 2.0955,
|
| 92 |
+
"loss": 2.2466,
|
| 93 |
+
"loss": 2.0475,
|
| 94 |
+
"loss": 2.1238,
|
| 95 |
+
"loss": 2.2063,
|
| 96 |
+
"loss": 1.9169,
|
| 97 |
+
"loss": 2.2551,
|
| 98 |
+
"loss": 2.2897,
|
| 99 |
+
"loss": 2.0693,
|
| 100 |
+
"loss": 2.2112,
|
| 101 |
+
"loss": 2.1032,
|
| 102 |
+
"loss": 1.8994,
|
| 103 |
+
"loss": 2.0233,
|
| 104 |
+
"loss": 2.1795,
|
| 105 |
+
"loss": 2.04,
|
| 106 |
+
"loss": 2.0926,
|
| 107 |
+
"loss": 1.9639,
|
| 108 |
+
"loss": 2.3427,
|
| 109 |
+
"loss": 1.9793,
|
| 110 |
+
"loss": 1.927,
|
| 111 |
+
"loss": 1.8329,
|
| 112 |
+
"loss": 1.9679,
|
| 113 |
+
"loss": 2.1962,
|
| 114 |
+
"loss": 2.0246,
|
| 115 |
+
"loss": 1.9195,
|
| 116 |
+
"loss": 2.0181,
|
| 117 |
+
"loss": 1.9007,
|
| 118 |
+
"loss": 2.029,
|
| 119 |
+
"loss": 1.9925,
|
| 120 |
+
"loss": 1.936,
|
| 121 |
+
"loss": 2.0462,
|
| 122 |
+
"loss": 1.9308,
|
| 123 |
+
"loss": 1.957,
|
| 124 |
+
"loss": 1.9303,
|
| 125 |
+
"loss": 2.0676,
|
| 126 |
+
"loss": 2.0288,
|
| 127 |
+
"loss": 1.833,
|
| 128 |
+
"loss": 2.0001,
|
| 129 |
+
"loss": 1.9148,
|
| 130 |
+
"loss": 1.9895,
|
| 131 |
+
"loss": 2.1705,
|
| 132 |
+
"loss": 1.8735,
|
| 133 |
+
"loss": 1.9762,
|
| 134 |
+
"loss": 1.8613,
|
| 135 |
+
"loss": 1.801,
|
| 136 |
+
"loss": 1.9148,
|
| 137 |
+
"loss": 2.1368,
|
| 138 |
+
"loss": 1.8184,
|
| 139 |
+
"loss": 1.5963,
|
| 140 |
+
"loss": 1.8879,
|
| 141 |
+
"loss": 1.9633,
|
| 142 |
+
"loss": 1.8162,
|
| 143 |
+
"loss": 1.6854,
|
| 144 |
+
"loss": 2.1203,
|
| 145 |
+
"loss": 1.7929,
|
| 146 |
+
"loss": 1.8433,
|
| 147 |
+
"loss": 2.0861,
|
| 148 |
+
"loss": 2.0828,
|
| 149 |
+
"loss": 1.6605,
|
| 150 |
+
"loss": 1.6951,
|
| 151 |
+
"loss": 1.9173,
|
| 152 |
+
"loss": 1.9349,
|
| 153 |
+
"loss": 1.8001,
|
| 154 |
+
"loss": 1.9535,
|
| 155 |
+
"loss": 1.7291,
|
| 156 |
+
"loss": 1.8336,
|
| 157 |
+
"loss": 2.0697,
|
| 158 |
+
"loss": 1.7562,
|
| 159 |
+
"loss": 1.7786,
|
| 160 |
+
"loss": 1.8246,
|
| 161 |
+
"loss": 1.7964,
|
| 162 |
+
"loss": 1.9483,
|
| 163 |
+
"loss": 1.7607,
|
| 164 |
+
"loss": 1.6808,
|
| 165 |
+
"loss": 1.7688,
|
| 166 |
+
"loss": 2.0228,
|
| 167 |
+
"loss": 1.9403,
|
| 168 |
+
"loss": 1.8574,
|
| 169 |
+
"loss": 1.8918,
|
| 170 |
+
"loss": 1.7663,
|
| 171 |
+
"loss": 1.7333,
|
| 172 |
+
"loss": 1.5394,
|
| 173 |
+
"loss": 1.899,
|
| 174 |
+
"loss": 1.9249,
|
| 175 |
+
"loss": 1.747,
|
| 176 |
+
"loss": 1.8479,
|
| 177 |
+
"loss": 1.8021,
|
| 178 |
+
"loss": 1.7032,
|
| 179 |
+
"loss": 1.8989,
|
| 180 |
+
"loss": 1.8185,
|
| 181 |
+
"loss": 1.6985,
|
| 182 |
+
"loss": 1.7797,
|
| 183 |
+
"loss": 1.6903,
|
| 184 |
+
"loss": 1.8766,
|
| 185 |
+
"loss": 1.7187,
|
| 186 |
+
"loss": 1.7295,
|
| 187 |
+
"loss": 1.6285,
|
| 188 |
+
"loss": 1.6925,
|
| 189 |
+
"loss": 1.719,
|
| 190 |
+
"loss": 1.781,
|
| 191 |
+
"loss": 1.7595,
|
| 192 |
+
"loss": 2.1111,
|
| 193 |
+
"loss": 1.9001,
|
| 194 |
+
"loss": 1.85,
|
| 195 |
+
"loss": 1.9016,
|
| 196 |
+
"loss": 1.9073,
|
| 197 |
+
"loss": 1.7666,
|
| 198 |
+
"loss": 1.8695,
|
| 199 |
+
"loss": 1.6799,
|
| 200 |
+
"loss": 1.9409,
|
| 201 |
+
"loss": 1.7277,
|
| 202 |
+
"loss": 1.7612,
|
| 203 |
+
"loss": 1.938,
|
| 204 |
+
"loss": 1.8985,
|
| 205 |
+
"loss": 1.7949,
|
| 206 |
+
"loss": 1.7116,
|