Commit
·
47f6cfc
1
Parent(s):
23c1dda
Upload 13 files
Browse files- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
- trainer_state.json +731 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-large",
|
| 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": 1280,
|
| 16 |
+
"n_head": 20,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 36,
|
| 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 |
+
"conversational": {
|
| 31 |
+
"max_length": 1000
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.33.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
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": "4.33.3"
|
| 6 |
+
}
|
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 sha256:6a512064c53a7902c7e5732596ad87db152d47478a421115fb372bcbe8c10b13
|
| 3 |
+
size 6192613541
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c907589f131258a5c958d499703a9c84d8774a64150b9ec7a679d450d0fccde
|
| 3 |
+
size 3096262685
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df86bc1036ccd2ea8489e328a1827c1047e623465c54c482b9e33f3168bf2594
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1644f4272a5614e5abec86ab375f8e3e64085c9aa2cdafd4c3ad61d11ff69bb2
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 1024,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 56415,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 9.911371089249314e-05,
|
| 14 |
+
"loss": 0.156,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 9.822742178498626e-05,
|
| 20 |
+
"loss": 0.1245,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.13,
|
| 25 |
+
"learning_rate": 9.73411326774794e-05,
|
| 26 |
+
"loss": 0.1381,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.18,
|
| 31 |
+
"learning_rate": 9.645484356997254e-05,
|
| 32 |
+
"loss": 0.1251,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.22,
|
| 37 |
+
"learning_rate": 9.556855446246566e-05,
|
| 38 |
+
"loss": 0.123,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.27,
|
| 43 |
+
"learning_rate": 9.468226535495879e-05,
|
| 44 |
+
"loss": 0.1149,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.31,
|
| 49 |
+
"learning_rate": 9.379597624745192e-05,
|
| 50 |
+
"loss": 0.1299,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"learning_rate": 9.290968713994506e-05,
|
| 56 |
+
"loss": 0.1237,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.4,
|
| 61 |
+
"learning_rate": 9.20233980324382e-05,
|
| 62 |
+
"loss": 0.1249,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.44,
|
| 67 |
+
"learning_rate": 9.113710892493131e-05,
|
| 68 |
+
"loss": 0.1191,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.49,
|
| 73 |
+
"learning_rate": 9.025081981742445e-05,
|
| 74 |
+
"loss": 0.1135,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.53,
|
| 79 |
+
"learning_rate": 8.936453070991759e-05,
|
| 80 |
+
"loss": 0.114,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.58,
|
| 85 |
+
"learning_rate": 8.84782416024107e-05,
|
| 86 |
+
"loss": 0.1165,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.62,
|
| 91 |
+
"learning_rate": 8.759195249490384e-05,
|
| 92 |
+
"loss": 0.1191,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.66,
|
| 97 |
+
"learning_rate": 8.670566338739697e-05,
|
| 98 |
+
"loss": 0.1164,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.71,
|
| 103 |
+
"learning_rate": 8.581937427989011e-05,
|
| 104 |
+
"loss": 0.1211,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.75,
|
| 109 |
+
"learning_rate": 8.493308517238323e-05,
|
| 110 |
+
"loss": 0.1091,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.8,
|
| 115 |
+
"learning_rate": 8.404679606487636e-05,
|
| 116 |
+
"loss": 0.1096,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.84,
|
| 121 |
+
"learning_rate": 8.31605069573695e-05,
|
| 122 |
+
"loss": 0.1117,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.89,
|
| 127 |
+
"learning_rate": 8.227421784986264e-05,
|
| 128 |
+
"loss": 0.1125,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.93,
|
| 133 |
+
"learning_rate": 8.138792874235575e-05,
|
| 134 |
+
"loss": 0.1193,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.97,
|
| 139 |
+
"learning_rate": 8.050163963484889e-05,
|
| 140 |
+
"loss": 0.1094,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.0,
|
| 145 |
+
"eval_loss": 0.10602948069572449,
|
| 146 |
+
"eval_runtime": 418.0898,
|
| 147 |
+
"eval_samples_per_second": 6.747,
|
| 148 |
+
"eval_steps_per_second": 3.375,
|
| 149 |
+
"step": 11283
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.02,
|
| 153 |
+
"learning_rate": 7.961535052734203e-05,
|
| 154 |
+
"loss": 0.0908,
|
| 155 |
+
"step": 11500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.06,
|
| 159 |
+
"learning_rate": 7.872906141983516e-05,
|
| 160 |
+
"loss": 0.0683,
|
| 161 |
+
"step": 12000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.11,
|
| 165 |
+
"learning_rate": 7.784277231232828e-05,
|
| 166 |
+
"loss": 0.0725,
|
| 167 |
+
"step": 12500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.15,
|
| 171 |
+
"learning_rate": 7.695648320482141e-05,
|
| 172 |
+
"loss": 0.0723,
|
| 173 |
+
"step": 13000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.2,
|
| 177 |
+
"learning_rate": 7.607019409731455e-05,
|
| 178 |
+
"loss": 0.0707,
|
| 179 |
+
"step": 13500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.24,
|
| 183 |
+
"learning_rate": 7.518390498980768e-05,
|
| 184 |
+
"loss": 0.0731,
|
| 185 |
+
"step": 14000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.29,
|
| 189 |
+
"learning_rate": 7.42976158823008e-05,
|
| 190 |
+
"loss": 0.0687,
|
| 191 |
+
"step": 14500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.33,
|
| 195 |
+
"learning_rate": 7.341132677479394e-05,
|
| 196 |
+
"loss": 0.0686,
|
| 197 |
+
"step": 15000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.37,
|
| 201 |
+
"learning_rate": 7.252503766728708e-05,
|
| 202 |
+
"loss": 0.0717,
|
| 203 |
+
"step": 15500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.42,
|
| 207 |
+
"learning_rate": 7.16387485597802e-05,
|
| 208 |
+
"loss": 0.0703,
|
| 209 |
+
"step": 16000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.46,
|
| 213 |
+
"learning_rate": 7.075245945227334e-05,
|
| 214 |
+
"loss": 0.0702,
|
| 215 |
+
"step": 16500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.51,
|
| 219 |
+
"learning_rate": 6.986617034476646e-05,
|
| 220 |
+
"loss": 0.0687,
|
| 221 |
+
"step": 17000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.55,
|
| 225 |
+
"learning_rate": 6.89798812372596e-05,
|
| 226 |
+
"loss": 0.0695,
|
| 227 |
+
"step": 17500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.6,
|
| 231 |
+
"learning_rate": 6.809359212975273e-05,
|
| 232 |
+
"loss": 0.0667,
|
| 233 |
+
"step": 18000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.64,
|
| 237 |
+
"learning_rate": 6.720730302224585e-05,
|
| 238 |
+
"loss": 0.0706,
|
| 239 |
+
"step": 18500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.68,
|
| 243 |
+
"learning_rate": 6.6321013914739e-05,
|
| 244 |
+
"loss": 0.061,
|
| 245 |
+
"step": 19000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.73,
|
| 249 |
+
"learning_rate": 6.543472480723212e-05,
|
| 250 |
+
"loss": 0.063,
|
| 251 |
+
"step": 19500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.77,
|
| 255 |
+
"learning_rate": 6.454843569972525e-05,
|
| 256 |
+
"loss": 0.0692,
|
| 257 |
+
"step": 20000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.82,
|
| 261 |
+
"learning_rate": 6.366214659221839e-05,
|
| 262 |
+
"loss": 0.0691,
|
| 263 |
+
"step": 20500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.86,
|
| 267 |
+
"learning_rate": 6.277585748471153e-05,
|
| 268 |
+
"loss": 0.0649,
|
| 269 |
+
"step": 21000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.91,
|
| 273 |
+
"learning_rate": 6.188956837720464e-05,
|
| 274 |
+
"loss": 0.0629,
|
| 275 |
+
"step": 21500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.95,
|
| 279 |
+
"learning_rate": 6.100327926969778e-05,
|
| 280 |
+
"loss": 0.0678,
|
| 281 |
+
"step": 22000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.99,
|
| 285 |
+
"learning_rate": 6.011699016219091e-05,
|
| 286 |
+
"loss": 0.0659,
|
| 287 |
+
"step": 22500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.0,
|
| 291 |
+
"eval_loss": 0.09332570433616638,
|
| 292 |
+
"eval_runtime": 419.0801,
|
| 293 |
+
"eval_samples_per_second": 6.731,
|
| 294 |
+
"eval_steps_per_second": 3.367,
|
| 295 |
+
"step": 22566
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.04,
|
| 299 |
+
"learning_rate": 5.9230701054684045e-05,
|
| 300 |
+
"loss": 0.0358,
|
| 301 |
+
"step": 23000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.08,
|
| 305 |
+
"learning_rate": 5.834441194717717e-05,
|
| 306 |
+
"loss": 0.0333,
|
| 307 |
+
"step": 23500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.13,
|
| 311 |
+
"learning_rate": 5.7458122839670305e-05,
|
| 312 |
+
"loss": 0.034,
|
| 313 |
+
"step": 24000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.17,
|
| 317 |
+
"learning_rate": 5.657183373216344e-05,
|
| 318 |
+
"loss": 0.0331,
|
| 319 |
+
"step": 24500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.22,
|
| 323 |
+
"learning_rate": 5.568554462465656e-05,
|
| 324 |
+
"loss": 0.0353,
|
| 325 |
+
"step": 25000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.26,
|
| 329 |
+
"learning_rate": 5.47992555171497e-05,
|
| 330 |
+
"loss": 0.0362,
|
| 331 |
+
"step": 25500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.3,
|
| 335 |
+
"learning_rate": 5.391296640964283e-05,
|
| 336 |
+
"loss": 0.0339,
|
| 337 |
+
"step": 26000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.35,
|
| 341 |
+
"learning_rate": 5.302667730213596e-05,
|
| 342 |
+
"loss": 0.0332,
|
| 343 |
+
"step": 26500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.39,
|
| 347 |
+
"learning_rate": 5.214038819462909e-05,
|
| 348 |
+
"loss": 0.0343,
|
| 349 |
+
"step": 27000
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.44,
|
| 353 |
+
"learning_rate": 5.125409908712222e-05,
|
| 354 |
+
"loss": 0.0337,
|
| 355 |
+
"step": 27500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.48,
|
| 359 |
+
"learning_rate": 5.0367809979615356e-05,
|
| 360 |
+
"loss": 0.0324,
|
| 361 |
+
"step": 28000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.53,
|
| 365 |
+
"learning_rate": 4.948152087210848e-05,
|
| 366 |
+
"loss": 0.0341,
|
| 367 |
+
"step": 28500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.57,
|
| 371 |
+
"learning_rate": 4.8595231764601615e-05,
|
| 372 |
+
"loss": 0.0332,
|
| 373 |
+
"step": 29000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.61,
|
| 377 |
+
"learning_rate": 4.770894265709475e-05,
|
| 378 |
+
"loss": 0.0346,
|
| 379 |
+
"step": 29500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.66,
|
| 383 |
+
"learning_rate": 4.682265354958788e-05,
|
| 384 |
+
"loss": 0.0346,
|
| 385 |
+
"step": 30000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.7,
|
| 389 |
+
"learning_rate": 4.593636444208101e-05,
|
| 390 |
+
"loss": 0.034,
|
| 391 |
+
"step": 30500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.75,
|
| 395 |
+
"learning_rate": 4.505007533457414e-05,
|
| 396 |
+
"loss": 0.0371,
|
| 397 |
+
"step": 31000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.79,
|
| 401 |
+
"learning_rate": 4.4163786227067274e-05,
|
| 402 |
+
"loss": 0.0335,
|
| 403 |
+
"step": 31500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.84,
|
| 407 |
+
"learning_rate": 4.32774971195604e-05,
|
| 408 |
+
"loss": 0.0337,
|
| 409 |
+
"step": 32000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.88,
|
| 413 |
+
"learning_rate": 4.239120801205353e-05,
|
| 414 |
+
"loss": 0.0332,
|
| 415 |
+
"step": 32500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.92,
|
| 419 |
+
"learning_rate": 4.1504918904546666e-05,
|
| 420 |
+
"loss": 0.0325,
|
| 421 |
+
"step": 33000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.97,
|
| 425 |
+
"learning_rate": 4.06186297970398e-05,
|
| 426 |
+
"loss": 0.0335,
|
| 427 |
+
"step": 33500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 3.0,
|
| 431 |
+
"eval_loss": 0.09837915003299713,
|
| 432 |
+
"eval_runtime": 419.1038,
|
| 433 |
+
"eval_samples_per_second": 6.731,
|
| 434 |
+
"eval_steps_per_second": 3.367,
|
| 435 |
+
"step": 33849
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.01,
|
| 439 |
+
"learning_rate": 3.9732340689532926e-05,
|
| 440 |
+
"loss": 0.028,
|
| 441 |
+
"step": 34000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.06,
|
| 445 |
+
"learning_rate": 3.884605158202606e-05,
|
| 446 |
+
"loss": 0.0163,
|
| 447 |
+
"step": 34500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.1,
|
| 451 |
+
"learning_rate": 3.795976247451919e-05,
|
| 452 |
+
"loss": 0.0153,
|
| 453 |
+
"step": 35000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.15,
|
| 457 |
+
"learning_rate": 3.7073473367012325e-05,
|
| 458 |
+
"loss": 0.0165,
|
| 459 |
+
"step": 35500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.19,
|
| 463 |
+
"learning_rate": 3.618718425950545e-05,
|
| 464 |
+
"loss": 0.0167,
|
| 465 |
+
"step": 36000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.23,
|
| 469 |
+
"learning_rate": 3.5300895151998584e-05,
|
| 470 |
+
"loss": 0.0164,
|
| 471 |
+
"step": 36500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.28,
|
| 475 |
+
"learning_rate": 3.441460604449172e-05,
|
| 476 |
+
"loss": 0.0166,
|
| 477 |
+
"step": 37000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.32,
|
| 481 |
+
"learning_rate": 3.3528316936984844e-05,
|
| 482 |
+
"loss": 0.0185,
|
| 483 |
+
"step": 37500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.37,
|
| 487 |
+
"learning_rate": 3.264202782947798e-05,
|
| 488 |
+
"loss": 0.0174,
|
| 489 |
+
"step": 38000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.41,
|
| 493 |
+
"learning_rate": 3.175573872197111e-05,
|
| 494 |
+
"loss": 0.0176,
|
| 495 |
+
"step": 38500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.46,
|
| 499 |
+
"learning_rate": 3.086944961446424e-05,
|
| 500 |
+
"loss": 0.0171,
|
| 501 |
+
"step": 39000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.5,
|
| 505 |
+
"learning_rate": 2.998316050695737e-05,
|
| 506 |
+
"loss": 0.0167,
|
| 507 |
+
"step": 39500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.55,
|
| 511 |
+
"learning_rate": 2.9096871399450502e-05,
|
| 512 |
+
"loss": 0.0177,
|
| 513 |
+
"step": 40000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.59,
|
| 517 |
+
"learning_rate": 2.8210582291943632e-05,
|
| 518 |
+
"loss": 0.0173,
|
| 519 |
+
"step": 40500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.63,
|
| 523 |
+
"learning_rate": 2.7324293184436765e-05,
|
| 524 |
+
"loss": 0.0178,
|
| 525 |
+
"step": 41000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.68,
|
| 529 |
+
"learning_rate": 2.6438004076929895e-05,
|
| 530 |
+
"loss": 0.0168,
|
| 531 |
+
"step": 41500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.72,
|
| 535 |
+
"learning_rate": 2.555171496942303e-05,
|
| 536 |
+
"loss": 0.0172,
|
| 537 |
+
"step": 42000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.77,
|
| 541 |
+
"learning_rate": 2.4665425861916157e-05,
|
| 542 |
+
"loss": 0.0171,
|
| 543 |
+
"step": 42500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.81,
|
| 547 |
+
"learning_rate": 2.377913675440929e-05,
|
| 548 |
+
"loss": 0.0173,
|
| 549 |
+
"step": 43000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.86,
|
| 553 |
+
"learning_rate": 2.289284764690242e-05,
|
| 554 |
+
"loss": 0.0165,
|
| 555 |
+
"step": 43500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.9,
|
| 559 |
+
"learning_rate": 2.2006558539395553e-05,
|
| 560 |
+
"loss": 0.0167,
|
| 561 |
+
"step": 44000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.94,
|
| 565 |
+
"learning_rate": 2.1120269431888683e-05,
|
| 566 |
+
"loss": 0.0169,
|
| 567 |
+
"step": 44500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.99,
|
| 571 |
+
"learning_rate": 2.0233980324381816e-05,
|
| 572 |
+
"loss": 0.0161,
|
| 573 |
+
"step": 45000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.0,
|
| 577 |
+
"eval_loss": 0.10828191787004471,
|
| 578 |
+
"eval_runtime": 419.188,
|
| 579 |
+
"eval_samples_per_second": 6.73,
|
| 580 |
+
"eval_steps_per_second": 3.366,
|
| 581 |
+
"step": 45132
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 4.03,
|
| 585 |
+
"learning_rate": 1.9347691216874946e-05,
|
| 586 |
+
"loss": 0.0116,
|
| 587 |
+
"step": 45500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 4.08,
|
| 591 |
+
"learning_rate": 1.8461402109368076e-05,
|
| 592 |
+
"loss": 0.0098,
|
| 593 |
+
"step": 46000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.12,
|
| 597 |
+
"learning_rate": 1.757511300186121e-05,
|
| 598 |
+
"loss": 0.0094,
|
| 599 |
+
"step": 46500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 4.17,
|
| 603 |
+
"learning_rate": 1.6688823894354338e-05,
|
| 604 |
+
"loss": 0.01,
|
| 605 |
+
"step": 47000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.21,
|
| 609 |
+
"learning_rate": 1.580253478684747e-05,
|
| 610 |
+
"loss": 0.0099,
|
| 611 |
+
"step": 47500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.25,
|
| 615 |
+
"learning_rate": 1.4916245679340601e-05,
|
| 616 |
+
"loss": 0.0099,
|
| 617 |
+
"step": 48000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.3,
|
| 621 |
+
"learning_rate": 1.4029956571833732e-05,
|
| 622 |
+
"loss": 0.0098,
|
| 623 |
+
"step": 48500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 4.34,
|
| 627 |
+
"learning_rate": 1.3143667464326864e-05,
|
| 628 |
+
"loss": 0.0097,
|
| 629 |
+
"step": 49000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.39,
|
| 633 |
+
"learning_rate": 1.2257378356819995e-05,
|
| 634 |
+
"loss": 0.0097,
|
| 635 |
+
"step": 49500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.43,
|
| 639 |
+
"learning_rate": 1.1371089249313127e-05,
|
| 640 |
+
"loss": 0.01,
|
| 641 |
+
"step": 50000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 4.48,
|
| 645 |
+
"learning_rate": 1.0484800141806258e-05,
|
| 646 |
+
"loss": 0.0101,
|
| 647 |
+
"step": 50500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.52,
|
| 651 |
+
"learning_rate": 9.59851103429939e-06,
|
| 652 |
+
"loss": 0.01,
|
| 653 |
+
"step": 51000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.56,
|
| 657 |
+
"learning_rate": 8.71222192679252e-06,
|
| 658 |
+
"loss": 0.0141,
|
| 659 |
+
"step": 51500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.61,
|
| 663 |
+
"learning_rate": 7.825932819285652e-06,
|
| 664 |
+
"loss": 0.0097,
|
| 665 |
+
"step": 52000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 4.65,
|
| 669 |
+
"learning_rate": 6.939643711778783e-06,
|
| 670 |
+
"loss": 0.0097,
|
| 671 |
+
"step": 52500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 4.7,
|
| 675 |
+
"learning_rate": 6.053354604271914e-06,
|
| 676 |
+
"loss": 0.0111,
|
| 677 |
+
"step": 53000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.74,
|
| 681 |
+
"learning_rate": 5.1670654967650455e-06,
|
| 682 |
+
"loss": 0.0097,
|
| 683 |
+
"step": 53500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.79,
|
| 687 |
+
"learning_rate": 4.280776389258176e-06,
|
| 688 |
+
"loss": 0.0102,
|
| 689 |
+
"step": 54000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.83,
|
| 693 |
+
"learning_rate": 3.3944872817513074e-06,
|
| 694 |
+
"loss": 0.0097,
|
| 695 |
+
"step": 54500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 4.87,
|
| 699 |
+
"learning_rate": 2.508198174244439e-06,
|
| 700 |
+
"loss": 0.0097,
|
| 701 |
+
"step": 55000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.92,
|
| 705 |
+
"learning_rate": 1.62190906673757e-06,
|
| 706 |
+
"loss": 0.0098,
|
| 707 |
+
"step": 55500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 4.96,
|
| 711 |
+
"learning_rate": 7.35619959230701e-07,
|
| 712 |
+
"loss": 0.0095,
|
| 713 |
+
"step": 56000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.0,
|
| 717 |
+
"eval_loss": 0.11257254332304001,
|
| 718 |
+
"eval_runtime": 419.1321,
|
| 719 |
+
"eval_samples_per_second": 6.731,
|
| 720 |
+
"eval_steps_per_second": 3.366,
|
| 721 |
+
"step": 56415
|
| 722 |
+
}
|
| 723 |
+
],
|
| 724 |
+
"logging_steps": 500,
|
| 725 |
+
"max_steps": 56415,
|
| 726 |
+
"num_train_epochs": 5,
|
| 727 |
+
"save_steps": 500,
|
| 728 |
+
"total_flos": 4.9105395843072e+17,
|
| 729 |
+
"trial_name": null,
|
| 730 |
+
"trial_params": null
|
| 731 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30215808f9c22ea7377cab1d5d0d5eec3bcc709165517c2cfe59b1102a410087
|
| 3 |
+
size 4091
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|