Training completed!
Browse files- .gitignore +1 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May22_22-40-10_DFWLRND0013/1684813215.270266/events.out.tfevents.1684813215.DFWLRND0013.2862.1 +3 -0
- runs/May22_22-40-10_DFWLRND0013/events.out.tfevents.1684813215.DFWLRND0013.2862.0 +3 -0
- runs/May23_05-54-33_DFWLRND0013/1684839276.647166/events.out.tfevents.1684839276.DFWLRND0013.5365.1 +3 -0
- runs/May23_05-54-33_DFWLRND0013/events.out.tfevents.1684839276.DFWLRND0013.5365.0 +3 -0
- runs/May23_17-39-29_DFWLRND0013/1684881573.409884/events.out.tfevents.1684881573.DFWLRND0013.9699.1 +3 -0
- runs/May23_17-39-29_DFWLRND0013/events.out.tfevents.1684881573.DFWLRND0013.9699.0 +3 -0
- runs/May23_23-05-21_DFWLRND0013/1684901124.683074/events.out.tfevents.1684901124.DFWLRND0013.15200.1 +3 -0
- runs/May23_23-05-21_DFWLRND0013/events.out.tfevents.1684901124.DFWLRND0013.15200.0 +3 -0
- runs/May23_23-10-23_DFWLRND0013/1684901428.521045/events.out.tfevents.1684901428.DFWLRND0013.15409.1 +3 -0
- runs/May23_23-10-23_DFWLRND0013/events.out.tfevents.1684901428.DFWLRND0013.15409.0 +3 -0
- runs/May28_13-55-53_DFWLRND0013/1685300156.002938/events.out.tfevents.1685300156.DFWLRND0013.48836.1 +3 -0
- runs/May28_13-55-53_DFWLRND0013/events.out.tfevents.1685300155.DFWLRND0013.48836.0 +3 -0
- runs/May28_14-24-56_DFWLRND0013/1685301898.976235/events.out.tfevents.1685301898.DFWLRND0013.49299.1 +3 -0
- runs/May28_14-24-56_DFWLRND0013/events.out.tfevents.1685301898.DFWLRND0013.49299.0 +3 -0
- runs/May28_14-28-11_DFWLRND0013/1685302094.664999/events.out.tfevents.1685302094.DFWLRND0013.49580.1 +3 -0
- runs/May28_14-28-11_DFWLRND0013/events.out.tfevents.1685302094.DFWLRND0013.49580.0 +3 -0
- runs/May29_15-09-16_DFWLRND0013/1685390959.249681/events.out.tfevents.1685390959.DFWLRND0013.58309.1 +3 -0
- runs/May29_15-09-16_DFWLRND0013/events.out.tfevents.1685390959.DFWLRND0013.58309.0 +3 -0
- runs/May29_15-28-31_DFWLRND0013/1685392114.440107/events.out.tfevents.1685392114.DFWLRND0013.58684.1 +3 -0
- runs/May29_15-28-31_DFWLRND0013/events.out.tfevents.1685392114.DFWLRND0013.58684.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
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": "4.29.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.29.2"
|
| 6 |
+
}
|
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 sha256:44a2fd2e3b830a5323294052eea36e4ea60192fdb1850fb408fa28353df8dacd
|
| 3 |
+
size 510396022
|
runs/May22_22-40-10_DFWLRND0013/1684813215.270266/events.out.tfevents.1684813215.DFWLRND0013.2862.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba6065220cb919966e20c48a425f8993ae7d882178804ad11c65b1838650088a
|
| 3 |
+
size 5897
|
runs/May22_22-40-10_DFWLRND0013/events.out.tfevents.1684813215.DFWLRND0013.2862.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2d2b0c03a11806a0d34a7e1eee7017a4683dafc63c11fd75109c41861ee09a6
|
| 3 |
+
size 4586
|
runs/May23_05-54-33_DFWLRND0013/1684839276.647166/events.out.tfevents.1684839276.DFWLRND0013.5365.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:062f8227aef93c786221c94ceedea93543a509980318485d1dfd1918e48e7871
|
| 3 |
+
size 5897
|
runs/May23_05-54-33_DFWLRND0013/events.out.tfevents.1684839276.DFWLRND0013.5365.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce8293a3287f5e34f0d64a317fe042ce29c1ba351212831e7285f997d60913b
|
| 3 |
+
size 4238
|
runs/May23_17-39-29_DFWLRND0013/1684881573.409884/events.out.tfevents.1684881573.DFWLRND0013.9699.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:182764ce3434b3b2f869dd22be7d89675fce52805924112f699a89ae198cf77f
|
| 3 |
+
size 5897
|
runs/May23_17-39-29_DFWLRND0013/events.out.tfevents.1684881573.DFWLRND0013.9699.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db88baa92b4107b9d9b5892473885422b215d3a94212d120912846947879a49f
|
| 3 |
+
size 4585
|
runs/May23_23-05-21_DFWLRND0013/1684901124.683074/events.out.tfevents.1684901124.DFWLRND0013.15200.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d820c199a1df9301a7f222c6c0e83e20b34e702f1b8f169c90ca667d6667ba9
|
| 3 |
+
size 5897
|
runs/May23_23-05-21_DFWLRND0013/events.out.tfevents.1684901124.DFWLRND0013.15200.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1511655197d59a9f423b27702473256b382470cb176844182d1106cc190cc340
|
| 3 |
+
size 4238
|
runs/May23_23-10-23_DFWLRND0013/1684901428.521045/events.out.tfevents.1684901428.DFWLRND0013.15409.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10cf1ed6c345273c3bc69d4f269d49f3632caee28601ef2fd5f341bb5718b3b9
|
| 3 |
+
size 5897
|
runs/May23_23-10-23_DFWLRND0013/events.out.tfevents.1684901428.DFWLRND0013.15409.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6acc0216ed8b86f528395793762eb9ed878fb2c1b8c3931ecbc72b6dec3862
|
| 3 |
+
size 4585
|
runs/May28_13-55-53_DFWLRND0013/1685300156.002938/events.out.tfevents.1685300156.DFWLRND0013.48836.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d78f2e1147f91b20ecd5e385263e276c649d00cc930dad12649c083b6d0d8c8
|
| 3 |
+
size 5897
|
runs/May28_13-55-53_DFWLRND0013/events.out.tfevents.1685300155.DFWLRND0013.48836.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af246e3c3301516283f76e1dc74eed0f7e9ca28ca024dcaa297665d7e3ea17ed
|
| 3 |
+
size 4583
|
runs/May28_14-24-56_DFWLRND0013/1685301898.976235/events.out.tfevents.1685301898.DFWLRND0013.49299.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:486b1e96296f58ddc6a0f2f92a6ad552040a8ddb8d322ad2026a47d488648531
|
| 3 |
+
size 5897
|
runs/May28_14-24-56_DFWLRND0013/events.out.tfevents.1685301898.DFWLRND0013.49299.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9845969f71a2fe8c298ef9c21b551549623df46edc7f69399964659b9b5204be
|
| 3 |
+
size 4235
|
runs/May28_14-28-11_DFWLRND0013/1685302094.664999/events.out.tfevents.1685302094.DFWLRND0013.49580.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6015e661153a6668c4f90169b36298d9c5995c0e4734cbe80f7f6be04bd1ea1
|
| 3 |
+
size 5897
|
runs/May28_14-28-11_DFWLRND0013/events.out.tfevents.1685302094.DFWLRND0013.49580.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98a0db8b31b3a2da65ec9c275fad38ca14ea89bd6a5a6d744abbeb199c22aa12
|
| 3 |
+
size 4583
|
runs/May29_15-09-16_DFWLRND0013/1685390959.249681/events.out.tfevents.1685390959.DFWLRND0013.58309.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b08d5274c93f73c79df6ce348acc228ed4297cd1fb0d203c33656408778e71a1
|
| 3 |
+
size 5897
|
runs/May29_15-09-16_DFWLRND0013/events.out.tfevents.1685390959.DFWLRND0013.58309.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1456e2df7fbe18974f03a60aa1e550404ab7c1212ca1537ee11153b7f8d07d
|
| 3 |
+
size 4235
|
runs/May29_15-28-31_DFWLRND0013/1685392114.440107/events.out.tfevents.1685392114.DFWLRND0013.58684.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11faccbeb1e4d1913ad812278d4e2829dc1a0ee3fb34c934f6a873a16d1df1b1
|
| 3 |
+
size 5897
|
runs/May29_15-28-31_DFWLRND0013/events.out.tfevents.1685392114.DFWLRND0013.58684.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:add6833162eeb50510ec08153fde6dba3117c4dee037f4fccc44898e65f2c66f
|
| 3 |
+
size 4583
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1024,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25882ff72fecbd2ef89ec1a7c6c1668029368c7245ef7014198054a766ee21b
|
| 3 |
+
size 4340
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|