First version
Browse files- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +22 -0
- trainer_state.json +845 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-medium",
|
| 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": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 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": "4.35.0",
|
| 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": "4.35.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3012101f78db5a3557b265a473b4644e75a878b27ac2b8073f9d51b0dc1a87d9
|
| 3 |
+
size 1419322880
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe4cb98d835c08f2cccb919cab8c5401608d5eca5cd140199472060cf0aa0cce
|
| 3 |
+
size 2838828805
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e360b93ae11b253074ff7e3d33ef4ea1f4d000fc7221b1809ea2474200931f7d
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72f85fedcc452f7a9236995678b92684ff2ca412bc69de0c659dda8c9f322759
|
| 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_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"model_max_length": 1024,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,845 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.029510498046875,
|
| 3 |
+
"best_model_checkpoint": "trained_models/microsoftDialoGPTmedium_crd3/checkpoint-9912",
|
| 4 |
+
"epoch": 2.957040572792363,
|
| 5 |
+
"eval_steps": 168,
|
| 6 |
+
"global_step": 9912,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 4.949880668257757e-05,
|
| 14 |
+
"loss": 3.805,
|
| 15 |
+
"step": 168
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"eval_loss": 3.3926753997802734,
|
| 20 |
+
"eval_runtime": 142.7844,
|
| 21 |
+
"eval_samples_per_second": 29.653,
|
| 22 |
+
"eval_steps_per_second": 3.712,
|
| 23 |
+
"step": 168
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1,
|
| 27 |
+
"learning_rate": 4.899761336515513e-05,
|
| 28 |
+
"loss": 3.3486,
|
| 29 |
+
"step": 336
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1,
|
| 33 |
+
"eval_loss": 3.2977957725524902,
|
| 34 |
+
"eval_runtime": 142.7066,
|
| 35 |
+
"eval_samples_per_second": 29.669,
|
| 36 |
+
"eval_steps_per_second": 3.714,
|
| 37 |
+
"step": 336
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15,
|
| 41 |
+
"learning_rate": 4.84964200477327e-05,
|
| 42 |
+
"loss": 3.2539,
|
| 43 |
+
"step": 504
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.15,
|
| 47 |
+
"eval_loss": 3.2512104511260986,
|
| 48 |
+
"eval_runtime": 142.7113,
|
| 49 |
+
"eval_samples_per_second": 29.668,
|
| 50 |
+
"eval_steps_per_second": 3.714,
|
| 51 |
+
"step": 504
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2,
|
| 55 |
+
"learning_rate": 4.7995226730310264e-05,
|
| 56 |
+
"loss": 3.2009,
|
| 57 |
+
"step": 672
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"eval_loss": 3.221975564956665,
|
| 62 |
+
"eval_runtime": 142.7296,
|
| 63 |
+
"eval_samples_per_second": 29.664,
|
| 64 |
+
"eval_steps_per_second": 3.713,
|
| 65 |
+
"step": 672
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.25,
|
| 69 |
+
"learning_rate": 4.749403341288783e-05,
|
| 70 |
+
"loss": 3.1685,
|
| 71 |
+
"step": 840
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.25,
|
| 75 |
+
"eval_loss": 3.197237014770508,
|
| 76 |
+
"eval_runtime": 142.735,
|
| 77 |
+
"eval_samples_per_second": 29.663,
|
| 78 |
+
"eval_steps_per_second": 3.713,
|
| 79 |
+
"step": 840
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3,
|
| 83 |
+
"learning_rate": 4.6992840095465395e-05,
|
| 84 |
+
"loss": 3.1332,
|
| 85 |
+
"step": 1008
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.3,
|
| 89 |
+
"eval_loss": 3.1779494285583496,
|
| 90 |
+
"eval_runtime": 142.7443,
|
| 91 |
+
"eval_samples_per_second": 29.661,
|
| 92 |
+
"eval_steps_per_second": 3.713,
|
| 93 |
+
"step": 1008
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.35,
|
| 97 |
+
"learning_rate": 4.649164677804296e-05,
|
| 98 |
+
"loss": 3.1231,
|
| 99 |
+
"step": 1176
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.35,
|
| 103 |
+
"eval_loss": 3.163996696472168,
|
| 104 |
+
"eval_runtime": 142.7827,
|
| 105 |
+
"eval_samples_per_second": 29.653,
|
| 106 |
+
"eval_steps_per_second": 3.712,
|
| 107 |
+
"step": 1176
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4,
|
| 111 |
+
"learning_rate": 4.5990453460620526e-05,
|
| 112 |
+
"loss": 3.1005,
|
| 113 |
+
"step": 1344
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.4,
|
| 117 |
+
"eval_loss": 3.1513357162475586,
|
| 118 |
+
"eval_runtime": 142.6836,
|
| 119 |
+
"eval_samples_per_second": 29.674,
|
| 120 |
+
"eval_steps_per_second": 3.715,
|
| 121 |
+
"step": 1344
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.45,
|
| 125 |
+
"learning_rate": 4.548926014319809e-05,
|
| 126 |
+
"loss": 3.0952,
|
| 127 |
+
"step": 1512
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.45,
|
| 131 |
+
"eval_loss": 3.1407930850982666,
|
| 132 |
+
"eval_runtime": 142.6804,
|
| 133 |
+
"eval_samples_per_second": 29.675,
|
| 134 |
+
"eval_steps_per_second": 3.715,
|
| 135 |
+
"step": 1512
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5,
|
| 139 |
+
"learning_rate": 4.498806682577566e-05,
|
| 140 |
+
"loss": 3.0903,
|
| 141 |
+
"step": 1680
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.5,
|
| 145 |
+
"eval_loss": 3.1297414302825928,
|
| 146 |
+
"eval_runtime": 142.7084,
|
| 147 |
+
"eval_samples_per_second": 29.669,
|
| 148 |
+
"eval_steps_per_second": 3.714,
|
| 149 |
+
"step": 1680
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.55,
|
| 153 |
+
"learning_rate": 4.448687350835322e-05,
|
| 154 |
+
"loss": 3.0737,
|
| 155 |
+
"step": 1848
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.55,
|
| 159 |
+
"eval_loss": 3.120724678039551,
|
| 160 |
+
"eval_runtime": 142.7344,
|
| 161 |
+
"eval_samples_per_second": 29.663,
|
| 162 |
+
"eval_steps_per_second": 3.713,
|
| 163 |
+
"step": 1848
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6,
|
| 167 |
+
"learning_rate": 4.398568019093079e-05,
|
| 168 |
+
"loss": 3.0681,
|
| 169 |
+
"step": 2016
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.6,
|
| 173 |
+
"eval_loss": 3.1170568466186523,
|
| 174 |
+
"eval_runtime": 142.7306,
|
| 175 |
+
"eval_samples_per_second": 29.664,
|
| 176 |
+
"eval_steps_per_second": 3.713,
|
| 177 |
+
"step": 2016
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.65,
|
| 181 |
+
"learning_rate": 4.348448687350836e-05,
|
| 182 |
+
"loss": 3.034,
|
| 183 |
+
"step": 2184
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.65,
|
| 187 |
+
"eval_loss": 3.1076815128326416,
|
| 188 |
+
"eval_runtime": 142.7258,
|
| 189 |
+
"eval_samples_per_second": 29.665,
|
| 190 |
+
"eval_steps_per_second": 3.713,
|
| 191 |
+
"step": 2184
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7,
|
| 195 |
+
"learning_rate": 4.298329355608592e-05,
|
| 196 |
+
"loss": 3.0319,
|
| 197 |
+
"step": 2352
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.7,
|
| 201 |
+
"eval_loss": 3.1014297008514404,
|
| 202 |
+
"eval_runtime": 142.7172,
|
| 203 |
+
"eval_samples_per_second": 29.667,
|
| 204 |
+
"eval_steps_per_second": 3.714,
|
| 205 |
+
"step": 2352
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.75,
|
| 209 |
+
"learning_rate": 4.2482100238663484e-05,
|
| 210 |
+
"loss": 3.0075,
|
| 211 |
+
"step": 2520
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.75,
|
| 215 |
+
"eval_loss": 3.0964250564575195,
|
| 216 |
+
"eval_runtime": 142.7047,
|
| 217 |
+
"eval_samples_per_second": 29.67,
|
| 218 |
+
"eval_steps_per_second": 3.714,
|
| 219 |
+
"step": 2520
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8,
|
| 223 |
+
"learning_rate": 4.1980906921241056e-05,
|
| 224 |
+
"loss": 3.0282,
|
| 225 |
+
"step": 2688
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.8,
|
| 229 |
+
"eval_loss": 3.0913186073303223,
|
| 230 |
+
"eval_runtime": 142.7245,
|
| 231 |
+
"eval_samples_per_second": 29.666,
|
| 232 |
+
"eval_steps_per_second": 3.713,
|
| 233 |
+
"step": 2688
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.85,
|
| 237 |
+
"learning_rate": 4.1479713603818615e-05,
|
| 238 |
+
"loss": 3.0055,
|
| 239 |
+
"step": 2856
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.85,
|
| 243 |
+
"eval_loss": 3.0834176540374756,
|
| 244 |
+
"eval_runtime": 142.7795,
|
| 245 |
+
"eval_samples_per_second": 29.654,
|
| 246 |
+
"eval_steps_per_second": 3.712,
|
| 247 |
+
"step": 2856
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9,
|
| 251 |
+
"learning_rate": 4.097852028639618e-05,
|
| 252 |
+
"loss": 3.0101,
|
| 253 |
+
"step": 3024
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.9,
|
| 257 |
+
"eval_loss": 3.0793018341064453,
|
| 258 |
+
"eval_runtime": 142.7762,
|
| 259 |
+
"eval_samples_per_second": 29.655,
|
| 260 |
+
"eval_steps_per_second": 3.712,
|
| 261 |
+
"step": 3024
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.95,
|
| 265 |
+
"learning_rate": 4.047732696897375e-05,
|
| 266 |
+
"loss": 3.0017,
|
| 267 |
+
"step": 3192
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.95,
|
| 271 |
+
"eval_loss": 3.075371742248535,
|
| 272 |
+
"eval_runtime": 142.7297,
|
| 273 |
+
"eval_samples_per_second": 29.664,
|
| 274 |
+
"eval_steps_per_second": 3.713,
|
| 275 |
+
"step": 3192
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.0,
|
| 279 |
+
"learning_rate": 3.997613365155131e-05,
|
| 280 |
+
"loss": 2.977,
|
| 281 |
+
"step": 3360
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0,
|
| 285 |
+
"eval_loss": 3.0743861198425293,
|
| 286 |
+
"eval_runtime": 142.7454,
|
| 287 |
+
"eval_samples_per_second": 29.661,
|
| 288 |
+
"eval_steps_per_second": 3.713,
|
| 289 |
+
"step": 3360
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.05,
|
| 293 |
+
"learning_rate": 3.9474940334128877e-05,
|
| 294 |
+
"loss": 2.8771,
|
| 295 |
+
"step": 3528
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.05,
|
| 299 |
+
"eval_loss": 3.0757055282592773,
|
| 300 |
+
"eval_runtime": 142.7589,
|
| 301 |
+
"eval_samples_per_second": 29.658,
|
| 302 |
+
"eval_steps_per_second": 3.713,
|
| 303 |
+
"step": 3528
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.1,
|
| 307 |
+
"learning_rate": 3.897374701670645e-05,
|
| 308 |
+
"loss": 2.8633,
|
| 309 |
+
"step": 3696
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.1,
|
| 313 |
+
"eval_loss": 3.0775437355041504,
|
| 314 |
+
"eval_runtime": 142.7329,
|
| 315 |
+
"eval_samples_per_second": 29.664,
|
| 316 |
+
"eval_steps_per_second": 3.713,
|
| 317 |
+
"step": 3696
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.15,
|
| 321 |
+
"learning_rate": 3.8472553699284014e-05,
|
| 322 |
+
"loss": 2.8591,
|
| 323 |
+
"step": 3864
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.15,
|
| 327 |
+
"eval_loss": 3.0708892345428467,
|
| 328 |
+
"eval_runtime": 142.7479,
|
| 329 |
+
"eval_samples_per_second": 29.661,
|
| 330 |
+
"eval_steps_per_second": 3.713,
|
| 331 |
+
"step": 3864
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.2,
|
| 335 |
+
"learning_rate": 3.797136038186157e-05,
|
| 336 |
+
"loss": 2.8625,
|
| 337 |
+
"step": 4032
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.2,
|
| 341 |
+
"eval_loss": 3.0683975219726562,
|
| 342 |
+
"eval_runtime": 142.757,
|
| 343 |
+
"eval_samples_per_second": 29.659,
|
| 344 |
+
"eval_steps_per_second": 3.713,
|
| 345 |
+
"step": 4032
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.25,
|
| 349 |
+
"learning_rate": 3.7470167064439145e-05,
|
| 350 |
+
"loss": 2.8605,
|
| 351 |
+
"step": 4200
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.25,
|
| 355 |
+
"eval_loss": 3.066983222961426,
|
| 356 |
+
"eval_runtime": 142.718,
|
| 357 |
+
"eval_samples_per_second": 29.667,
|
| 358 |
+
"eval_steps_per_second": 3.714,
|
| 359 |
+
"step": 4200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.3,
|
| 363 |
+
"learning_rate": 3.696897374701671e-05,
|
| 364 |
+
"loss": 2.8466,
|
| 365 |
+
"step": 4368
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.3,
|
| 369 |
+
"eval_loss": 3.0646440982818604,
|
| 370 |
+
"eval_runtime": 142.755,
|
| 371 |
+
"eval_samples_per_second": 29.659,
|
| 372 |
+
"eval_steps_per_second": 3.713,
|
| 373 |
+
"step": 4368
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.35,
|
| 377 |
+
"learning_rate": 3.6467780429594276e-05,
|
| 378 |
+
"loss": 2.8398,
|
| 379 |
+
"step": 4536
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.35,
|
| 383 |
+
"eval_loss": 3.0618984699249268,
|
| 384 |
+
"eval_runtime": 142.7437,
|
| 385 |
+
"eval_samples_per_second": 29.662,
|
| 386 |
+
"eval_steps_per_second": 3.713,
|
| 387 |
+
"step": 4536
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.4,
|
| 391 |
+
"learning_rate": 3.596658711217184e-05,
|
| 392 |
+
"loss": 2.8502,
|
| 393 |
+
"step": 4704
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.4,
|
| 397 |
+
"eval_loss": 3.059511661529541,
|
| 398 |
+
"eval_runtime": 142.746,
|
| 399 |
+
"eval_samples_per_second": 29.661,
|
| 400 |
+
"eval_steps_per_second": 3.713,
|
| 401 |
+
"step": 4704
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.45,
|
| 405 |
+
"learning_rate": 3.546539379474941e-05,
|
| 406 |
+
"loss": 2.8523,
|
| 407 |
+
"step": 4872
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.45,
|
| 411 |
+
"eval_loss": 3.0564985275268555,
|
| 412 |
+
"eval_runtime": 142.7041,
|
| 413 |
+
"eval_samples_per_second": 29.67,
|
| 414 |
+
"eval_steps_per_second": 3.714,
|
| 415 |
+
"step": 4872
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.5,
|
| 419 |
+
"learning_rate": 3.496420047732697e-05,
|
| 420 |
+
"loss": 2.8545,
|
| 421 |
+
"step": 5040
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.5,
|
| 425 |
+
"eval_loss": 3.0538723468780518,
|
| 426 |
+
"eval_runtime": 142.7089,
|
| 427 |
+
"eval_samples_per_second": 29.669,
|
| 428 |
+
"eval_steps_per_second": 3.714,
|
| 429 |
+
"step": 5040
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.55,
|
| 433 |
+
"learning_rate": 3.446300715990454e-05,
|
| 434 |
+
"loss": 2.8431,
|
| 435 |
+
"step": 5208
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.55,
|
| 439 |
+
"eval_loss": 3.053504705429077,
|
| 440 |
+
"eval_runtime": 142.7279,
|
| 441 |
+
"eval_samples_per_second": 29.665,
|
| 442 |
+
"eval_steps_per_second": 3.713,
|
| 443 |
+
"step": 5208
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.6,
|
| 447 |
+
"learning_rate": 3.39618138424821e-05,
|
| 448 |
+
"loss": 2.865,
|
| 449 |
+
"step": 5376
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.6,
|
| 453 |
+
"eval_loss": 3.0489370822906494,
|
| 454 |
+
"eval_runtime": 142.7484,
|
| 455 |
+
"eval_samples_per_second": 29.661,
|
| 456 |
+
"eval_steps_per_second": 3.713,
|
| 457 |
+
"step": 5376
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.65,
|
| 461 |
+
"learning_rate": 3.346062052505967e-05,
|
| 462 |
+
"loss": 2.8412,
|
| 463 |
+
"step": 5544
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.65,
|
| 467 |
+
"eval_loss": 3.048715114593506,
|
| 468 |
+
"eval_runtime": 142.7028,
|
| 469 |
+
"eval_samples_per_second": 29.67,
|
| 470 |
+
"eval_steps_per_second": 3.714,
|
| 471 |
+
"step": 5544
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.7,
|
| 475 |
+
"learning_rate": 3.2959427207637234e-05,
|
| 476 |
+
"loss": 2.8382,
|
| 477 |
+
"step": 5712
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.7,
|
| 481 |
+
"eval_loss": 3.0453927516937256,
|
| 482 |
+
"eval_runtime": 142.6981,
|
| 483 |
+
"eval_samples_per_second": 29.671,
|
| 484 |
+
"eval_steps_per_second": 3.714,
|
| 485 |
+
"step": 5712
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.75,
|
| 489 |
+
"learning_rate": 3.24582338902148e-05,
|
| 490 |
+
"loss": 2.8356,
|
| 491 |
+
"step": 5880
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.75,
|
| 495 |
+
"eval_loss": 3.0460968017578125,
|
| 496 |
+
"eval_runtime": 142.6846,
|
| 497 |
+
"eval_samples_per_second": 29.674,
|
| 498 |
+
"eval_steps_per_second": 3.714,
|
| 499 |
+
"step": 5880
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.8,
|
| 503 |
+
"learning_rate": 3.1957040572792365e-05,
|
| 504 |
+
"loss": 2.8265,
|
| 505 |
+
"step": 6048
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.8,
|
| 509 |
+
"eval_loss": 3.042219400405884,
|
| 510 |
+
"eval_runtime": 142.7165,
|
| 511 |
+
"eval_samples_per_second": 29.667,
|
| 512 |
+
"eval_steps_per_second": 3.714,
|
| 513 |
+
"step": 6048
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.85,
|
| 517 |
+
"learning_rate": 3.145584725536993e-05,
|
| 518 |
+
"loss": 2.8301,
|
| 519 |
+
"step": 6216
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.85,
|
| 523 |
+
"eval_loss": 3.0397562980651855,
|
| 524 |
+
"eval_runtime": 142.7319,
|
| 525 |
+
"eval_samples_per_second": 29.664,
|
| 526 |
+
"eval_steps_per_second": 3.713,
|
| 527 |
+
"step": 6216
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.9,
|
| 531 |
+
"learning_rate": 3.0954653937947496e-05,
|
| 532 |
+
"loss": 2.8286,
|
| 533 |
+
"step": 6384
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.9,
|
| 537 |
+
"eval_loss": 3.038638114929199,
|
| 538 |
+
"eval_runtime": 142.7562,
|
| 539 |
+
"eval_samples_per_second": 29.659,
|
| 540 |
+
"eval_steps_per_second": 3.713,
|
| 541 |
+
"step": 6384
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.95,
|
| 545 |
+
"learning_rate": 3.045346062052506e-05,
|
| 546 |
+
"loss": 2.8416,
|
| 547 |
+
"step": 6552
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.95,
|
| 551 |
+
"eval_loss": 3.035384178161621,
|
| 552 |
+
"eval_runtime": 142.669,
|
| 553 |
+
"eval_samples_per_second": 29.677,
|
| 554 |
+
"eval_steps_per_second": 3.715,
|
| 555 |
+
"step": 6552
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.0,
|
| 559 |
+
"learning_rate": 2.9952267303102627e-05,
|
| 560 |
+
"loss": 2.8179,
|
| 561 |
+
"step": 6720
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.0,
|
| 565 |
+
"eval_loss": 3.040719509124756,
|
| 566 |
+
"eval_runtime": 142.723,
|
| 567 |
+
"eval_samples_per_second": 29.666,
|
| 568 |
+
"eval_steps_per_second": 3.713,
|
| 569 |
+
"step": 6720
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.05,
|
| 573 |
+
"learning_rate": 2.9451073985680195e-05,
|
| 574 |
+
"loss": 2.6965,
|
| 575 |
+
"step": 6888
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.05,
|
| 579 |
+
"eval_loss": 3.0478203296661377,
|
| 580 |
+
"eval_runtime": 142.7498,
|
| 581 |
+
"eval_samples_per_second": 29.66,
|
| 582 |
+
"eval_steps_per_second": 3.713,
|
| 583 |
+
"step": 6888
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.11,
|
| 587 |
+
"learning_rate": 2.8949880668257757e-05,
|
| 588 |
+
"loss": 2.7437,
|
| 589 |
+
"step": 7056
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.11,
|
| 593 |
+
"eval_loss": 3.048868179321289,
|
| 594 |
+
"eval_runtime": 142.7646,
|
| 595 |
+
"eval_samples_per_second": 29.657,
|
| 596 |
+
"eval_steps_per_second": 3.712,
|
| 597 |
+
"step": 7056
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.16,
|
| 601 |
+
"learning_rate": 2.8448687350835323e-05,
|
| 602 |
+
"loss": 2.7252,
|
| 603 |
+
"step": 7224
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.16,
|
| 607 |
+
"eval_loss": 3.045444965362549,
|
| 608 |
+
"eval_runtime": 142.7306,
|
| 609 |
+
"eval_samples_per_second": 29.664,
|
| 610 |
+
"eval_steps_per_second": 3.713,
|
| 611 |
+
"step": 7224
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.21,
|
| 615 |
+
"learning_rate": 2.794749403341289e-05,
|
| 616 |
+
"loss": 2.718,
|
| 617 |
+
"step": 7392
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.21,
|
| 621 |
+
"eval_loss": 3.04612398147583,
|
| 622 |
+
"eval_runtime": 142.7393,
|
| 623 |
+
"eval_samples_per_second": 29.662,
|
| 624 |
+
"eval_steps_per_second": 3.713,
|
| 625 |
+
"step": 7392
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.26,
|
| 629 |
+
"learning_rate": 2.7446300715990454e-05,
|
| 630 |
+
"loss": 2.7246,
|
| 631 |
+
"step": 7560
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.26,
|
| 635 |
+
"eval_loss": 3.0447964668273926,
|
| 636 |
+
"eval_runtime": 142.6751,
|
| 637 |
+
"eval_samples_per_second": 29.676,
|
| 638 |
+
"eval_steps_per_second": 3.715,
|
| 639 |
+
"step": 7560
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.31,
|
| 643 |
+
"learning_rate": 2.694510739856802e-05,
|
| 644 |
+
"loss": 2.7365,
|
| 645 |
+
"step": 7728
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.31,
|
| 649 |
+
"eval_loss": 3.0433876514434814,
|
| 650 |
+
"eval_runtime": 142.7111,
|
| 651 |
+
"eval_samples_per_second": 29.668,
|
| 652 |
+
"eval_steps_per_second": 3.714,
|
| 653 |
+
"step": 7728
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.36,
|
| 657 |
+
"learning_rate": 2.6443914081145588e-05,
|
| 658 |
+
"loss": 2.7242,
|
| 659 |
+
"step": 7896
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.36,
|
| 663 |
+
"eval_loss": 3.044072151184082,
|
| 664 |
+
"eval_runtime": 142.6648,
|
| 665 |
+
"eval_samples_per_second": 29.678,
|
| 666 |
+
"eval_steps_per_second": 3.715,
|
| 667 |
+
"step": 7896
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.41,
|
| 671 |
+
"learning_rate": 2.594272076372315e-05,
|
| 672 |
+
"loss": 2.7343,
|
| 673 |
+
"step": 8064
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 2.41,
|
| 677 |
+
"eval_loss": 3.0415401458740234,
|
| 678 |
+
"eval_runtime": 142.737,
|
| 679 |
+
"eval_samples_per_second": 29.663,
|
| 680 |
+
"eval_steps_per_second": 3.713,
|
| 681 |
+
"step": 8064
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.46,
|
| 685 |
+
"learning_rate": 2.5441527446300715e-05,
|
| 686 |
+
"loss": 2.7312,
|
| 687 |
+
"step": 8232
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 2.46,
|
| 691 |
+
"eval_loss": 3.0406272411346436,
|
| 692 |
+
"eval_runtime": 142.7448,
|
| 693 |
+
"eval_samples_per_second": 29.661,
|
| 694 |
+
"eval_steps_per_second": 3.713,
|
| 695 |
+
"step": 8232
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.51,
|
| 699 |
+
"learning_rate": 2.494033412887828e-05,
|
| 700 |
+
"loss": 2.7359,
|
| 701 |
+
"step": 8400
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.51,
|
| 705 |
+
"eval_loss": 3.0369086265563965,
|
| 706 |
+
"eval_runtime": 142.71,
|
| 707 |
+
"eval_samples_per_second": 29.669,
|
| 708 |
+
"eval_steps_per_second": 3.714,
|
| 709 |
+
"step": 8400
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.56,
|
| 713 |
+
"learning_rate": 2.443914081145585e-05,
|
| 714 |
+
"loss": 2.714,
|
| 715 |
+
"step": 8568
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 2.56,
|
| 719 |
+
"eval_loss": 3.039921522140503,
|
| 720 |
+
"eval_runtime": 142.7829,
|
| 721 |
+
"eval_samples_per_second": 29.653,
|
| 722 |
+
"eval_steps_per_second": 3.712,
|
| 723 |
+
"step": 8568
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.61,
|
| 727 |
+
"learning_rate": 2.3937947494033415e-05,
|
| 728 |
+
"loss": 2.7311,
|
| 729 |
+
"step": 8736
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.61,
|
| 733 |
+
"eval_loss": 3.0377085208892822,
|
| 734 |
+
"eval_runtime": 142.7212,
|
| 735 |
+
"eval_samples_per_second": 29.666,
|
| 736 |
+
"eval_steps_per_second": 3.714,
|
| 737 |
+
"step": 8736
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.66,
|
| 741 |
+
"learning_rate": 2.3436754176610977e-05,
|
| 742 |
+
"loss": 2.7191,
|
| 743 |
+
"step": 8904
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.66,
|
| 747 |
+
"eval_loss": 3.036844253540039,
|
| 748 |
+
"eval_runtime": 142.7078,
|
| 749 |
+
"eval_samples_per_second": 29.669,
|
| 750 |
+
"eval_steps_per_second": 3.714,
|
| 751 |
+
"step": 8904
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.71,
|
| 755 |
+
"learning_rate": 2.2935560859188546e-05,
|
| 756 |
+
"loss": 2.7246,
|
| 757 |
+
"step": 9072
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.71,
|
| 761 |
+
"eval_loss": 3.0361039638519287,
|
| 762 |
+
"eval_runtime": 142.7607,
|
| 763 |
+
"eval_samples_per_second": 29.658,
|
| 764 |
+
"eval_steps_per_second": 3.713,
|
| 765 |
+
"step": 9072
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.76,
|
| 769 |
+
"learning_rate": 2.243436754176611e-05,
|
| 770 |
+
"loss": 2.721,
|
| 771 |
+
"step": 9240
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.76,
|
| 775 |
+
"eval_loss": 3.0351145267486572,
|
| 776 |
+
"eval_runtime": 142.7366,
|
| 777 |
+
"eval_samples_per_second": 29.663,
|
| 778 |
+
"eval_steps_per_second": 3.713,
|
| 779 |
+
"step": 9240
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.81,
|
| 783 |
+
"learning_rate": 2.1933174224343677e-05,
|
| 784 |
+
"loss": 2.71,
|
| 785 |
+
"step": 9408
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.81,
|
| 789 |
+
"eval_loss": 3.032681941986084,
|
| 790 |
+
"eval_runtime": 142.729,
|
| 791 |
+
"eval_samples_per_second": 29.665,
|
| 792 |
+
"eval_steps_per_second": 3.713,
|
| 793 |
+
"step": 9408
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.86,
|
| 797 |
+
"learning_rate": 2.1431980906921242e-05,
|
| 798 |
+
"loss": 2.7252,
|
| 799 |
+
"step": 9576
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 2.86,
|
| 803 |
+
"eval_loss": 3.033348798751831,
|
| 804 |
+
"eval_runtime": 142.7408,
|
| 805 |
+
"eval_samples_per_second": 29.662,
|
| 806 |
+
"eval_steps_per_second": 3.713,
|
| 807 |
+
"step": 9576
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.91,
|
| 811 |
+
"learning_rate": 2.0930787589498808e-05,
|
| 812 |
+
"loss": 2.7181,
|
| 813 |
+
"step": 9744
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.91,
|
| 817 |
+
"eval_loss": 3.0330820083618164,
|
| 818 |
+
"eval_runtime": 142.7512,
|
| 819 |
+
"eval_samples_per_second": 29.66,
|
| 820 |
+
"eval_steps_per_second": 3.713,
|
| 821 |
+
"step": 9744
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.96,
|
| 825 |
+
"learning_rate": 2.0429594272076373e-05,
|
| 826 |
+
"loss": 2.7141,
|
| 827 |
+
"step": 9912
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.96,
|
| 831 |
+
"eval_loss": 3.029510498046875,
|
| 832 |
+
"eval_runtime": 142.7075,
|
| 833 |
+
"eval_samples_per_second": 29.669,
|
| 834 |
+
"eval_steps_per_second": 3.714,
|
| 835 |
+
"step": 9912
|
| 836 |
+
}
|
| 837 |
+
],
|
| 838 |
+
"logging_steps": 168,
|
| 839 |
+
"max_steps": 16760,
|
| 840 |
+
"num_train_epochs": 5,
|
| 841 |
+
"save_steps": 168,
|
| 842 |
+
"total_flos": 3.221291229039821e+16,
|
| 843 |
+
"trial_name": null,
|
| 844 |
+
"trial_params": null
|
| 845 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b327653b71ceb0028050ddec2b8292fdab8123096015419eaf16718eb43c9807
|
| 3 |
+
size 4091
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|