add ckpt 70000
Browse files- config.json +30 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +856 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 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 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_weights": true,
|
| 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 |
+
"transformers_version": "4.6.0.dev0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50000
|
| 30 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a56a260c6fa9dffc26c9bd026a43faaae675a007ebac04764658691eddd2adb
|
| 3 |
+
size 1301229097
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e24060d4eb8f1005ad8aa32b1ad522eec177c0d95b95c699360e0e7bf6c6d4
|
| 3 |
+
size 663209284
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:271d7f83ead0e7137e945730b50c6ad08d336a3ce4232e8a6ed2ceed516090e7
|
| 3 |
+
size 13624
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ca13a07f52f9043f35c183885e7e86b589ea8d3a97e2b7563a1aab2a0f361b
|
| 3 |
+
size 13624
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefef0c8eeb20450e9584aba1ee67642960a09462972b2fd611d0206de16af4e
|
| 3 |
+
size 13624
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd00fbdd63d92641c9136fa23406497f2f9aee703ad6151a41f5aa56dc3a148d
|
| 3 |
+
size 13624
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7b64af29c8571e3d4dd1c5549fab25ffcb6ebd25a30cc4e8374c15d97b0aaed
|
| 3 |
+
size 13624
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c737835f8fa4c63d4e75c02376232c97e8cee963424b3688f531ce5ea920407f
|
| 3 |
+
size 13624
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaee72d389d1ded833e0ea3e0613dac7bbae54441d7e22de5e82fc88bd051cc8
|
| 3 |
+
size 13624
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:904772b39e771c862ddaa7c6b9bbb0f45b5d8b307c86f73244572e4b20dad8cd
|
| 3 |
+
size 13624
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:583decf59d289217230db84c73db4aded1a132f5fd2baae59396758067887398
|
| 3 |
+
size 623
|
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.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": {"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, "special_tokens_map_file": null, "name_or_path": "./", "errors": "replace"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,856 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7556620099821925,
|
| 5 |
+
"global_step": 70000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 4.96864889267889e-05,
|
| 13 |
+
"loss": 9.0385,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 4.937297785357779e-05,
|
| 19 |
+
"loss": 8.2693,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 4.9059466780366684e-05,
|
| 25 |
+
"loss": 7.9544,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 4.874595570715558e-05,
|
| 31 |
+
"loss": 7.7454,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"learning_rate": 4.843244463394448e-05,
|
| 37 |
+
"loss": 7.5746,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"learning_rate": 4.8118933560733366e-05,
|
| 43 |
+
"loss": 7.4312,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"learning_rate": 4.780542248752226e-05,
|
| 49 |
+
"loss": 7.3059,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.1,
|
| 54 |
+
"learning_rate": 4.749191141431116e-05,
|
| 55 |
+
"loss": 7.1942,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.11,
|
| 60 |
+
"learning_rate": 4.717840034110005e-05,
|
| 61 |
+
"loss": 7.0934,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.13,
|
| 66 |
+
"learning_rate": 4.6864889267888944e-05,
|
| 67 |
+
"loss": 7.0091,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.14,
|
| 72 |
+
"learning_rate": 4.6551378194677834e-05,
|
| 73 |
+
"loss": 6.9312,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"learning_rate": 4.623786712146673e-05,
|
| 79 |
+
"loss": 6.8625,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.16,
|
| 84 |
+
"learning_rate": 4.5924356048255626e-05,
|
| 85 |
+
"loss": 6.806,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.18,
|
| 90 |
+
"learning_rate": 4.561084497504452e-05,
|
| 91 |
+
"loss": 6.7588,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.19,
|
| 96 |
+
"learning_rate": 4.529733390183342e-05,
|
| 97 |
+
"loss": 6.7066,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.2,
|
| 102 |
+
"learning_rate": 4.498382282862231e-05,
|
| 103 |
+
"loss": 6.6641,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.21,
|
| 108 |
+
"learning_rate": 4.4670311755411204e-05,
|
| 109 |
+
"loss": 6.6211,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.23,
|
| 114 |
+
"learning_rate": 4.4356800682200094e-05,
|
| 115 |
+
"loss": 6.5876,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.24,
|
| 120 |
+
"learning_rate": 4.404328960898899e-05,
|
| 121 |
+
"loss": 6.5559,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25,
|
| 126 |
+
"learning_rate": 4.3729778535777886e-05,
|
| 127 |
+
"loss": 6.524,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26,
|
| 132 |
+
"learning_rate": 4.3416267462566776e-05,
|
| 133 |
+
"loss": 6.4988,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.28,
|
| 138 |
+
"learning_rate": 4.310275638935567e-05,
|
| 139 |
+
"loss": 6.4699,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.29,
|
| 144 |
+
"learning_rate": 4.278924531614457e-05,
|
| 145 |
+
"loss": 6.4434,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.3,
|
| 150 |
+
"learning_rate": 4.2475734242933464e-05,
|
| 151 |
+
"loss": 6.4212,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.31,
|
| 156 |
+
"learning_rate": 4.216222316972236e-05,
|
| 157 |
+
"loss": 6.3987,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.33,
|
| 162 |
+
"learning_rate": 4.184871209651125e-05,
|
| 163 |
+
"loss": 6.3757,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.34,
|
| 168 |
+
"learning_rate": 4.1535201023300146e-05,
|
| 169 |
+
"loss": 6.3612,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.35,
|
| 174 |
+
"learning_rate": 4.1221689950089036e-05,
|
| 175 |
+
"loss": 6.3416,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.36,
|
| 180 |
+
"learning_rate": 4.090817887687793e-05,
|
| 181 |
+
"loss": 6.3212,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.38,
|
| 186 |
+
"learning_rate": 4.059466780366683e-05,
|
| 187 |
+
"loss": 6.3015,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.39,
|
| 192 |
+
"learning_rate": 4.0281156730455724e-05,
|
| 193 |
+
"loss": 6.2876,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.4,
|
| 198 |
+
"learning_rate": 3.996764565724462e-05,
|
| 199 |
+
"loss": 6.2793,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.41,
|
| 204 |
+
"learning_rate": 3.965413458403351e-05,
|
| 205 |
+
"loss": 6.2627,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.43,
|
| 210 |
+
"learning_rate": 3.9340623510822406e-05,
|
| 211 |
+
"loss": 6.2455,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.44,
|
| 216 |
+
"learning_rate": 3.9027112437611296e-05,
|
| 217 |
+
"loss": 6.2309,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.45,
|
| 222 |
+
"learning_rate": 3.871360136440019e-05,
|
| 223 |
+
"loss": 6.2154,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.46,
|
| 228 |
+
"learning_rate": 3.840009029118909e-05,
|
| 229 |
+
"loss": 6.2052,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.48,
|
| 234 |
+
"learning_rate": 3.808657921797798e-05,
|
| 235 |
+
"loss": 6.1916,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.49,
|
| 240 |
+
"learning_rate": 3.7773068144766874e-05,
|
| 241 |
+
"loss": 6.1812,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.5,
|
| 246 |
+
"learning_rate": 3.745955707155577e-05,
|
| 247 |
+
"loss": 6.1724,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.51,
|
| 252 |
+
"learning_rate": 3.7146045998344666e-05,
|
| 253 |
+
"loss": 6.1634,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.53,
|
| 258 |
+
"learning_rate": 3.6832534925133556e-05,
|
| 259 |
+
"loss": 6.1548,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.54,
|
| 264 |
+
"learning_rate": 3.651902385192245e-05,
|
| 265 |
+
"loss": 6.1417,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.55,
|
| 270 |
+
"learning_rate": 3.620551277871135e-05,
|
| 271 |
+
"loss": 6.134,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.56,
|
| 276 |
+
"learning_rate": 3.589200170550024e-05,
|
| 277 |
+
"loss": 6.1222,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.58,
|
| 282 |
+
"learning_rate": 3.5578490632289134e-05,
|
| 283 |
+
"loss": 6.1157,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.59,
|
| 288 |
+
"learning_rate": 3.526497955907802e-05,
|
| 289 |
+
"loss": 6.1062,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6,
|
| 294 |
+
"learning_rate": 3.4951468485866926e-05,
|
| 295 |
+
"loss": 6.0985,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.61,
|
| 300 |
+
"learning_rate": 3.463795741265582e-05,
|
| 301 |
+
"loss": 6.0918,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.63,
|
| 306 |
+
"learning_rate": 3.432444633944471e-05,
|
| 307 |
+
"loss": 6.0845,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.64,
|
| 312 |
+
"learning_rate": 3.401093526623361e-05,
|
| 313 |
+
"loss": 6.0771,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.65,
|
| 318 |
+
"learning_rate": 3.36974241930225e-05,
|
| 319 |
+
"loss": 6.0696,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.66,
|
| 324 |
+
"learning_rate": 3.3383913119811394e-05,
|
| 325 |
+
"loss": 6.0638,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.68,
|
| 330 |
+
"learning_rate": 3.307040204660028e-05,
|
| 331 |
+
"loss": 6.0535,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.69,
|
| 336 |
+
"learning_rate": 3.275689097338918e-05,
|
| 337 |
+
"loss": 6.0473,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7,
|
| 342 |
+
"learning_rate": 3.2443379900178076e-05,
|
| 343 |
+
"loss": 6.042,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.71,
|
| 348 |
+
"learning_rate": 3.212986882696697e-05,
|
| 349 |
+
"loss": 6.0379,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.73,
|
| 354 |
+
"learning_rate": 3.181635775375587e-05,
|
| 355 |
+
"loss": 6.0337,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.74,
|
| 360 |
+
"learning_rate": 3.150284668054476e-05,
|
| 361 |
+
"loss": 6.0254,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.75,
|
| 366 |
+
"learning_rate": 3.1189335607333654e-05,
|
| 367 |
+
"loss": 6.0222,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.76,
|
| 372 |
+
"learning_rate": 3.087582453412255e-05,
|
| 373 |
+
"loss": 6.0072,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.78,
|
| 378 |
+
"learning_rate": 3.056231346091144e-05,
|
| 379 |
+
"loss": 6.005,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.79,
|
| 384 |
+
"learning_rate": 3.0248802387700336e-05,
|
| 385 |
+
"loss": 6.0058,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.8,
|
| 390 |
+
"learning_rate": 2.993529131448923e-05,
|
| 391 |
+
"loss": 5.9953,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.82,
|
| 396 |
+
"learning_rate": 2.9621780241278125e-05,
|
| 397 |
+
"loss": 5.993,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.83,
|
| 402 |
+
"learning_rate": 2.9308269168067014e-05,
|
| 403 |
+
"loss": 5.9817,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.84,
|
| 408 |
+
"learning_rate": 2.899475809485591e-05,
|
| 409 |
+
"loss": 5.978,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.85,
|
| 414 |
+
"learning_rate": 2.8681247021644807e-05,
|
| 415 |
+
"loss": 5.9807,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.87,
|
| 420 |
+
"learning_rate": 2.83677359484337e-05,
|
| 421 |
+
"loss": 5.9742,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.88,
|
| 426 |
+
"learning_rate": 2.8054224875222596e-05,
|
| 427 |
+
"loss": 5.9678,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.89,
|
| 432 |
+
"learning_rate": 2.7740713802011485e-05,
|
| 433 |
+
"loss": 5.9637,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.9,
|
| 438 |
+
"learning_rate": 2.7427202728800385e-05,
|
| 439 |
+
"loss": 5.962,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.92,
|
| 444 |
+
"learning_rate": 2.711369165558928e-05,
|
| 445 |
+
"loss": 5.9555,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.93,
|
| 450 |
+
"learning_rate": 2.680018058237817e-05,
|
| 451 |
+
"loss": 5.952,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.94,
|
| 456 |
+
"learning_rate": 2.6486669509167067e-05,
|
| 457 |
+
"loss": 5.9503,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.95,
|
| 462 |
+
"learning_rate": 2.617315843595596e-05,
|
| 463 |
+
"loss": 5.9442,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.97,
|
| 468 |
+
"learning_rate": 2.5859647362744856e-05,
|
| 469 |
+
"loss": 5.9362,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.98,
|
| 474 |
+
"learning_rate": 2.5546136289533745e-05,
|
| 475 |
+
"loss": 5.9394,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.99,
|
| 480 |
+
"learning_rate": 2.523262521632264e-05,
|
| 481 |
+
"loss": 5.9358,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.0,
|
| 486 |
+
"learning_rate": 2.4919114143111534e-05,
|
| 487 |
+
"loss": 5.931,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.02,
|
| 492 |
+
"learning_rate": 2.460560306990043e-05,
|
| 493 |
+
"loss": 5.9197,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.03,
|
| 498 |
+
"learning_rate": 2.4292091996689323e-05,
|
| 499 |
+
"loss": 5.914,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.04,
|
| 504 |
+
"learning_rate": 2.397858092347822e-05,
|
| 505 |
+
"loss": 5.9091,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.05,
|
| 510 |
+
"learning_rate": 2.3665069850267112e-05,
|
| 511 |
+
"loss": 5.911,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.07,
|
| 516 |
+
"learning_rate": 2.335155877705601e-05,
|
| 517 |
+
"loss": 5.9081,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.08,
|
| 522 |
+
"learning_rate": 2.30380477038449e-05,
|
| 523 |
+
"loss": 5.9025,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.09,
|
| 528 |
+
"learning_rate": 2.2724536630633794e-05,
|
| 529 |
+
"loss": 5.9001,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.1,
|
| 534 |
+
"learning_rate": 2.2411025557422687e-05,
|
| 535 |
+
"loss": 5.9017,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.12,
|
| 540 |
+
"learning_rate": 2.2097514484211583e-05,
|
| 541 |
+
"loss": 5.8982,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.13,
|
| 546 |
+
"learning_rate": 2.178400341100048e-05,
|
| 547 |
+
"loss": 5.8917,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.14,
|
| 552 |
+
"learning_rate": 2.1470492337789372e-05,
|
| 553 |
+
"loss": 5.8934,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.15,
|
| 558 |
+
"learning_rate": 2.1156981264578265e-05,
|
| 559 |
+
"loss": 5.8908,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.17,
|
| 564 |
+
"learning_rate": 2.0843470191367158e-05,
|
| 565 |
+
"loss": 5.891,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.18,
|
| 570 |
+
"learning_rate": 2.0529959118156054e-05,
|
| 571 |
+
"loss": 5.8866,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.19,
|
| 576 |
+
"learning_rate": 2.021644804494495e-05,
|
| 577 |
+
"loss": 5.8782,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.2,
|
| 582 |
+
"learning_rate": 1.9902936971733843e-05,
|
| 583 |
+
"loss": 5.8775,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.22,
|
| 588 |
+
"learning_rate": 1.9589425898522736e-05,
|
| 589 |
+
"loss": 5.8807,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.23,
|
| 594 |
+
"learning_rate": 1.9275914825311632e-05,
|
| 595 |
+
"loss": 5.8766,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.24,
|
| 600 |
+
"learning_rate": 1.8962403752100525e-05,
|
| 601 |
+
"loss": 5.87,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.25,
|
| 606 |
+
"learning_rate": 1.8648892678889418e-05,
|
| 607 |
+
"loss": 5.8691,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.27,
|
| 612 |
+
"learning_rate": 1.8335381605678314e-05,
|
| 613 |
+
"loss": 5.8686,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.28,
|
| 618 |
+
"learning_rate": 1.8021870532467207e-05,
|
| 619 |
+
"loss": 5.8658,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.29,
|
| 624 |
+
"learning_rate": 1.7708359459256103e-05,
|
| 625 |
+
"loss": 5.8609,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.3,
|
| 630 |
+
"learning_rate": 1.7394848386044996e-05,
|
| 631 |
+
"loss": 5.866,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.32,
|
| 636 |
+
"learning_rate": 1.708133731283389e-05,
|
| 637 |
+
"loss": 5.8587,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.33,
|
| 642 |
+
"learning_rate": 1.676782623962278e-05,
|
| 643 |
+
"loss": 5.8565,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.34,
|
| 648 |
+
"learning_rate": 1.645431516641168e-05,
|
| 649 |
+
"loss": 5.8542,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.35,
|
| 654 |
+
"learning_rate": 1.6140804093200574e-05,
|
| 655 |
+
"loss": 5.8546,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.37,
|
| 660 |
+
"learning_rate": 1.5827293019989467e-05,
|
| 661 |
+
"loss": 5.8478,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.38,
|
| 666 |
+
"learning_rate": 1.551378194677836e-05,
|
| 667 |
+
"loss": 5.8457,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.39,
|
| 672 |
+
"learning_rate": 1.5200270873567254e-05,
|
| 673 |
+
"loss": 5.8515,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4,
|
| 678 |
+
"learning_rate": 1.4886759800356149e-05,
|
| 679 |
+
"loss": 5.8507,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.42,
|
| 684 |
+
"learning_rate": 1.4573248727145045e-05,
|
| 685 |
+
"loss": 5.8477,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.43,
|
| 690 |
+
"learning_rate": 1.4259737653933938e-05,
|
| 691 |
+
"loss": 5.8422,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.44,
|
| 696 |
+
"learning_rate": 1.3946226580722832e-05,
|
| 697 |
+
"loss": 5.8443,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.45,
|
| 702 |
+
"learning_rate": 1.3632715507511725e-05,
|
| 703 |
+
"loss": 5.8392,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.47,
|
| 708 |
+
"learning_rate": 1.331920443430062e-05,
|
| 709 |
+
"loss": 5.8372,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.48,
|
| 714 |
+
"learning_rate": 1.3005693361089513e-05,
|
| 715 |
+
"loss": 5.8368,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.49,
|
| 720 |
+
"learning_rate": 1.269218228787841e-05,
|
| 721 |
+
"loss": 5.8384,
|
| 722 |
+
"step": 59500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.5,
|
| 726 |
+
"learning_rate": 1.2378671214667302e-05,
|
| 727 |
+
"loss": 5.8315,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.52,
|
| 732 |
+
"learning_rate": 1.2065160141456198e-05,
|
| 733 |
+
"loss": 5.8347,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.53,
|
| 738 |
+
"learning_rate": 1.175164906824509e-05,
|
| 739 |
+
"loss": 5.8279,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.54,
|
| 744 |
+
"learning_rate": 1.1438137995033985e-05,
|
| 745 |
+
"loss": 5.8289,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.56,
|
| 750 |
+
"learning_rate": 1.112462692182288e-05,
|
| 751 |
+
"loss": 5.829,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.57,
|
| 756 |
+
"learning_rate": 1.0811115848611773e-05,
|
| 757 |
+
"loss": 5.8283,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.58,
|
| 762 |
+
"learning_rate": 1.0497604775400667e-05,
|
| 763 |
+
"loss": 5.8224,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.59,
|
| 768 |
+
"learning_rate": 1.0184093702189562e-05,
|
| 769 |
+
"loss": 5.8251,
|
| 770 |
+
"step": 63500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.61,
|
| 774 |
+
"learning_rate": 9.870582628978456e-06,
|
| 775 |
+
"loss": 5.823,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.62,
|
| 780 |
+
"learning_rate": 9.557071555767349e-06,
|
| 781 |
+
"loss": 5.8226,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.63,
|
| 786 |
+
"learning_rate": 9.243560482556245e-06,
|
| 787 |
+
"loss": 5.8251,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.64,
|
| 792 |
+
"learning_rate": 8.930049409345138e-06,
|
| 793 |
+
"loss": 5.8237,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.66,
|
| 798 |
+
"learning_rate": 8.616538336134033e-06,
|
| 799 |
+
"loss": 5.8247,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.67,
|
| 804 |
+
"learning_rate": 8.303027262922927e-06,
|
| 805 |
+
"loss": 5.8149,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.68,
|
| 810 |
+
"learning_rate": 7.989516189711822e-06,
|
| 811 |
+
"loss": 5.8161,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.69,
|
| 816 |
+
"learning_rate": 7.676005116500714e-06,
|
| 817 |
+
"loss": 5.8129,
|
| 818 |
+
"step": 67500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.71,
|
| 822 |
+
"learning_rate": 7.36249404328961e-06,
|
| 823 |
+
"loss": 5.8167,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.72,
|
| 828 |
+
"learning_rate": 7.0489829700785035e-06,
|
| 829 |
+
"loss": 5.8165,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.73,
|
| 834 |
+
"learning_rate": 6.735471896867397e-06,
|
| 835 |
+
"loss": 5.8153,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.74,
|
| 840 |
+
"learning_rate": 6.4219608236562925e-06,
|
| 841 |
+
"loss": 5.8099,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.76,
|
| 846 |
+
"learning_rate": 6.108449750445186e-06,
|
| 847 |
+
"loss": 5.8079,
|
| 848 |
+
"step": 70000
|
| 849 |
+
}
|
| 850 |
+
],
|
| 851 |
+
"max_steps": 79742,
|
| 852 |
+
"num_train_epochs": 2,
|
| 853 |
+
"total_flos": 7.994200817664e+16,
|
| 854 |
+
"trial_name": null,
|
| 855 |
+
"trial_params": null
|
| 856 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:342242d19d3cc5b6a0c23bec766bc5ea68b9454a39b49978ca8d831a02d4023b
|
| 3 |
+
size 2415
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|