upload model
Browse files- config.json +63 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- trainer_state.json +1202 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125M",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MultiHeadGPTNeo"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local"
|
| 21 |
+
],
|
| 22 |
+
"attention_types": [
|
| 23 |
+
[
|
| 24 |
+
[
|
| 25 |
+
"global",
|
| 26 |
+
"local"
|
| 27 |
+
],
|
| 28 |
+
6
|
| 29 |
+
]
|
| 30 |
+
],
|
| 31 |
+
"bos_token_id": 50256,
|
| 32 |
+
"embed_dropout": 0,
|
| 33 |
+
"eos_token_id": 50256,
|
| 34 |
+
"gradient_checkpointing": false,
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": null,
|
| 38 |
+
"layer_norm_epsilon": 1e-05,
|
| 39 |
+
"lm_head_layer_indices": [
|
| 40 |
+
12,
|
| 41 |
+
10,
|
| 42 |
+
8,
|
| 43 |
+
6,
|
| 44 |
+
4,
|
| 45 |
+
2
|
| 46 |
+
],
|
| 47 |
+
"max_position_embeddings": 2048,
|
| 48 |
+
"model_type": "gpt_neo",
|
| 49 |
+
"num_heads": 12,
|
| 50 |
+
"num_layers": 12,
|
| 51 |
+
"output_hidden_states": true,
|
| 52 |
+
"resid_dropout": 0,
|
| 53 |
+
"summary_activation": null,
|
| 54 |
+
"summary_first_dropout": 0.1,
|
| 55 |
+
"summary_proj_to_labels": true,
|
| 56 |
+
"summary_type": "cls_index",
|
| 57 |
+
"summary_use_proj": true,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.22.2",
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 50257,
|
| 62 |
+
"window_size": 256
|
| 63 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6276aa270836f174c195149e207a2c4a72142929544c9f02b3dbb97bd6e8bed2
|
| 3 |
+
size 1477524101
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25b763e10d381510ccd6ab2b264c7f30065233642a1e65176496b616ab2d08b3
|
| 3 |
+
size 17563
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"model_max_length": 512,
|
| 22 |
+
"name_or_path": "EleutherAI/gpt-neo-125M",
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"special_tokens_map_file": null,
|
| 32 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 33 |
+
"unk_token": {
|
| 34 |
+
"__type": "AddedToken",
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": true,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
}
|
| 41 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 59688,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.00019832462136442838,
|
| 13 |
+
"loss": 38.657,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.00019664924272885673,
|
| 19 |
+
"loss": 31.308,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"eval_loss": 31.739517211914062,
|
| 25 |
+
"eval_runtime": 0.2575,
|
| 26 |
+
"eval_samples_per_second": 194.153,
|
| 27 |
+
"eval_steps_per_second": 7.766,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.08,
|
| 32 |
+
"learning_rate": 0.00019497386409328508,
|
| 33 |
+
"loss": 29.927,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.1,
|
| 38 |
+
"learning_rate": 0.00019329848545771345,
|
| 39 |
+
"loss": 29.1683,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.1,
|
| 44 |
+
"eval_loss": 30.288894653320312,
|
| 45 |
+
"eval_runtime": 0.2122,
|
| 46 |
+
"eval_samples_per_second": 235.624,
|
| 47 |
+
"eval_steps_per_second": 9.425,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.13,
|
| 52 |
+
"learning_rate": 0.00019162310682214182,
|
| 53 |
+
"loss": 28.6403,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.15,
|
| 58 |
+
"learning_rate": 0.0001899477281865702,
|
| 59 |
+
"loss": 28.258,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.15,
|
| 64 |
+
"eval_loss": 29.558307647705078,
|
| 65 |
+
"eval_runtime": 0.2125,
|
| 66 |
+
"eval_samples_per_second": 235.261,
|
| 67 |
+
"eval_steps_per_second": 9.41,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.18,
|
| 72 |
+
"learning_rate": 0.00018827234955099854,
|
| 73 |
+
"loss": 27.9285,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.2,
|
| 78 |
+
"learning_rate": 0.0001865969709154269,
|
| 79 |
+
"loss": 27.6974,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2,
|
| 84 |
+
"eval_loss": 29.129697799682617,
|
| 85 |
+
"eval_runtime": 0.213,
|
| 86 |
+
"eval_samples_per_second": 234.762,
|
| 87 |
+
"eval_steps_per_second": 9.39,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.23,
|
| 92 |
+
"learning_rate": 0.00018492159227985526,
|
| 93 |
+
"loss": 27.492,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.25,
|
| 98 |
+
"learning_rate": 0.00018324621364428363,
|
| 99 |
+
"loss": 27.3712,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.25,
|
| 104 |
+
"eval_loss": 28.81637954711914,
|
| 105 |
+
"eval_runtime": 0.2107,
|
| 106 |
+
"eval_samples_per_second": 237.354,
|
| 107 |
+
"eval_steps_per_second": 9.494,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.28,
|
| 112 |
+
"learning_rate": 0.00018157083500871198,
|
| 113 |
+
"loss": 27.204,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3,
|
| 118 |
+
"learning_rate": 0.00017989545637314033,
|
| 119 |
+
"loss": 27.0678,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.3,
|
| 124 |
+
"eval_loss": 28.593141555786133,
|
| 125 |
+
"eval_runtime": 0.2097,
|
| 126 |
+
"eval_samples_per_second": 238.454,
|
| 127 |
+
"eval_steps_per_second": 9.538,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.33,
|
| 132 |
+
"learning_rate": 0.0001782200777375687,
|
| 133 |
+
"loss": 26.9572,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.35,
|
| 138 |
+
"learning_rate": 0.00017654469910199707,
|
| 139 |
+
"loss": 26.8814,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.35,
|
| 144 |
+
"eval_loss": 28.419679641723633,
|
| 145 |
+
"eval_runtime": 0.2117,
|
| 146 |
+
"eval_samples_per_second": 236.237,
|
| 147 |
+
"eval_steps_per_second": 9.449,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.38,
|
| 152 |
+
"learning_rate": 0.00017486932046642542,
|
| 153 |
+
"loss": 26.784,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.4,
|
| 158 |
+
"learning_rate": 0.0001731939418308538,
|
| 159 |
+
"loss": 26.6886,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.4,
|
| 164 |
+
"eval_loss": 28.238792419433594,
|
| 165 |
+
"eval_runtime": 0.2269,
|
| 166 |
+
"eval_samples_per_second": 220.371,
|
| 167 |
+
"eval_steps_per_second": 8.815,
|
| 168 |
+
"step": 8000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.43,
|
| 172 |
+
"learning_rate": 0.00017151856319528214,
|
| 173 |
+
"loss": 26.6235,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.45,
|
| 178 |
+
"learning_rate": 0.0001698431845597105,
|
| 179 |
+
"loss": 26.545,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.45,
|
| 184 |
+
"eval_loss": 28.171510696411133,
|
| 185 |
+
"eval_runtime": 0.2133,
|
| 186 |
+
"eval_samples_per_second": 234.396,
|
| 187 |
+
"eval_steps_per_second": 9.376,
|
| 188 |
+
"step": 9000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.48,
|
| 192 |
+
"learning_rate": 0.00016816780592413886,
|
| 193 |
+
"loss": 26.4933,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.5,
|
| 198 |
+
"learning_rate": 0.00016649242728856723,
|
| 199 |
+
"loss": 26.4678,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5,
|
| 204 |
+
"eval_loss": 28.05875015258789,
|
| 205 |
+
"eval_runtime": 0.2106,
|
| 206 |
+
"eval_samples_per_second": 237.401,
|
| 207 |
+
"eval_steps_per_second": 9.496,
|
| 208 |
+
"step": 10000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.53,
|
| 212 |
+
"learning_rate": 0.00016481704865299558,
|
| 213 |
+
"loss": 26.3908,
|
| 214 |
+
"step": 10500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.55,
|
| 218 |
+
"learning_rate": 0.00016314167001742395,
|
| 219 |
+
"loss": 26.3369,
|
| 220 |
+
"step": 11000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.55,
|
| 224 |
+
"eval_loss": 27.978954315185547,
|
| 225 |
+
"eval_runtime": 0.2203,
|
| 226 |
+
"eval_samples_per_second": 226.942,
|
| 227 |
+
"eval_steps_per_second": 9.078,
|
| 228 |
+
"step": 11000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.58,
|
| 232 |
+
"learning_rate": 0.0001614662913818523,
|
| 233 |
+
"loss": 26.3059,
|
| 234 |
+
"step": 11500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6,
|
| 238 |
+
"learning_rate": 0.00015979091274628067,
|
| 239 |
+
"loss": 26.2555,
|
| 240 |
+
"step": 12000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6,
|
| 244 |
+
"eval_loss": 27.862077713012695,
|
| 245 |
+
"eval_runtime": 0.2131,
|
| 246 |
+
"eval_samples_per_second": 234.646,
|
| 247 |
+
"eval_steps_per_second": 9.386,
|
| 248 |
+
"step": 12000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.63,
|
| 252 |
+
"learning_rate": 0.00015811553411070902,
|
| 253 |
+
"loss": 26.197,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.65,
|
| 258 |
+
"learning_rate": 0.0001564401554751374,
|
| 259 |
+
"loss": 26.1535,
|
| 260 |
+
"step": 13000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.65,
|
| 264 |
+
"eval_loss": 27.81878662109375,
|
| 265 |
+
"eval_runtime": 0.2128,
|
| 266 |
+
"eval_samples_per_second": 234.945,
|
| 267 |
+
"eval_steps_per_second": 9.398,
|
| 268 |
+
"step": 13000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.68,
|
| 272 |
+
"learning_rate": 0.00015476477683956574,
|
| 273 |
+
"loss": 26.1223,
|
| 274 |
+
"step": 13500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.7,
|
| 278 |
+
"learning_rate": 0.0001530893982039941,
|
| 279 |
+
"loss": 26.0879,
|
| 280 |
+
"step": 14000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7,
|
| 284 |
+
"eval_loss": 27.750713348388672,
|
| 285 |
+
"eval_runtime": 0.2338,
|
| 286 |
+
"eval_samples_per_second": 213.838,
|
| 287 |
+
"eval_steps_per_second": 8.554,
|
| 288 |
+
"step": 14000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.73,
|
| 292 |
+
"learning_rate": 0.00015141401956842248,
|
| 293 |
+
"loss": 26.0771,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.75,
|
| 298 |
+
"learning_rate": 0.00014973864093285083,
|
| 299 |
+
"loss": 26.0283,
|
| 300 |
+
"step": 15000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.75,
|
| 304 |
+
"eval_loss": 27.70425796508789,
|
| 305 |
+
"eval_runtime": 0.2114,
|
| 306 |
+
"eval_samples_per_second": 236.495,
|
| 307 |
+
"eval_steps_per_second": 9.46,
|
| 308 |
+
"step": 15000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.78,
|
| 312 |
+
"learning_rate": 0.00014806326229727917,
|
| 313 |
+
"loss": 26.0089,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.8,
|
| 318 |
+
"learning_rate": 0.00014638788366170755,
|
| 319 |
+
"loss": 25.9742,
|
| 320 |
+
"step": 16000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.8,
|
| 324 |
+
"eval_loss": 27.637338638305664,
|
| 325 |
+
"eval_runtime": 0.2146,
|
| 326 |
+
"eval_samples_per_second": 233.03,
|
| 327 |
+
"eval_steps_per_second": 9.321,
|
| 328 |
+
"step": 16000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.83,
|
| 332 |
+
"learning_rate": 0.00014471250502613592,
|
| 333 |
+
"loss": 25.9742,
|
| 334 |
+
"step": 16500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.85,
|
| 338 |
+
"learning_rate": 0.00014303712639056427,
|
| 339 |
+
"loss": 25.9445,
|
| 340 |
+
"step": 17000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.85,
|
| 344 |
+
"eval_loss": 27.6143798828125,
|
| 345 |
+
"eval_runtime": 0.2101,
|
| 346 |
+
"eval_samples_per_second": 237.929,
|
| 347 |
+
"eval_steps_per_second": 9.517,
|
| 348 |
+
"step": 17000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.88,
|
| 352 |
+
"learning_rate": 0.00014136174775499264,
|
| 353 |
+
"loss": 25.9146,
|
| 354 |
+
"step": 17500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.9,
|
| 358 |
+
"learning_rate": 0.000139686369119421,
|
| 359 |
+
"loss": 25.8983,
|
| 360 |
+
"step": 18000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.9,
|
| 364 |
+
"eval_loss": 27.574024200439453,
|
| 365 |
+
"eval_runtime": 0.2119,
|
| 366 |
+
"eval_samples_per_second": 236.006,
|
| 367 |
+
"eval_steps_per_second": 9.44,
|
| 368 |
+
"step": 18000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.93,
|
| 372 |
+
"learning_rate": 0.00013801099048384936,
|
| 373 |
+
"loss": 25.8699,
|
| 374 |
+
"step": 18500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.95,
|
| 378 |
+
"learning_rate": 0.00013633561184827773,
|
| 379 |
+
"loss": 25.8736,
|
| 380 |
+
"step": 19000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.95,
|
| 384 |
+
"eval_loss": 27.524921417236328,
|
| 385 |
+
"eval_runtime": 0.2136,
|
| 386 |
+
"eval_samples_per_second": 234.075,
|
| 387 |
+
"eval_steps_per_second": 9.363,
|
| 388 |
+
"step": 19000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.98,
|
| 392 |
+
"learning_rate": 0.00013466023321270608,
|
| 393 |
+
"loss": 25.8176,
|
| 394 |
+
"step": 19500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.01,
|
| 398 |
+
"learning_rate": 0.00013298485457713443,
|
| 399 |
+
"loss": 25.8017,
|
| 400 |
+
"step": 20000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.01,
|
| 404 |
+
"eval_loss": 27.505229949951172,
|
| 405 |
+
"eval_runtime": 0.2283,
|
| 406 |
+
"eval_samples_per_second": 218.987,
|
| 407 |
+
"eval_steps_per_second": 8.759,
|
| 408 |
+
"step": 20000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.03,
|
| 412 |
+
"learning_rate": 0.0001313094759415628,
|
| 413 |
+
"loss": 25.7503,
|
| 414 |
+
"step": 20500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.06,
|
| 418 |
+
"learning_rate": 0.00012963409730599117,
|
| 419 |
+
"loss": 25.7469,
|
| 420 |
+
"step": 21000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.06,
|
| 424 |
+
"eval_loss": 27.50472640991211,
|
| 425 |
+
"eval_runtime": 0.2116,
|
| 426 |
+
"eval_samples_per_second": 236.284,
|
| 427 |
+
"eval_steps_per_second": 9.451,
|
| 428 |
+
"step": 21000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.08,
|
| 432 |
+
"learning_rate": 0.00012795871867041952,
|
| 433 |
+
"loss": 25.7176,
|
| 434 |
+
"step": 21500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.11,
|
| 438 |
+
"learning_rate": 0.00012628334003484786,
|
| 439 |
+
"loss": 25.6876,
|
| 440 |
+
"step": 22000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.11,
|
| 444 |
+
"eval_loss": 27.477006912231445,
|
| 445 |
+
"eval_runtime": 0.215,
|
| 446 |
+
"eval_samples_per_second": 232.548,
|
| 447 |
+
"eval_steps_per_second": 9.302,
|
| 448 |
+
"step": 22000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.13,
|
| 452 |
+
"learning_rate": 0.00012460796139927624,
|
| 453 |
+
"loss": 25.7203,
|
| 454 |
+
"step": 22500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.16,
|
| 458 |
+
"learning_rate": 0.0001229325827637046,
|
| 459 |
+
"loss": 25.6757,
|
| 460 |
+
"step": 23000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.16,
|
| 464 |
+
"eval_loss": 27.425168991088867,
|
| 465 |
+
"eval_runtime": 0.2125,
|
| 466 |
+
"eval_samples_per_second": 235.312,
|
| 467 |
+
"eval_steps_per_second": 9.412,
|
| 468 |
+
"step": 23000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.18,
|
| 472 |
+
"learning_rate": 0.00012125720412813297,
|
| 473 |
+
"loss": 25.6867,
|
| 474 |
+
"step": 23500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.21,
|
| 478 |
+
"learning_rate": 0.00011958182549256132,
|
| 479 |
+
"loss": 25.6558,
|
| 480 |
+
"step": 24000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.21,
|
| 484 |
+
"eval_loss": 27.394458770751953,
|
| 485 |
+
"eval_runtime": 0.2106,
|
| 486 |
+
"eval_samples_per_second": 237.425,
|
| 487 |
+
"eval_steps_per_second": 9.497,
|
| 488 |
+
"step": 24000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.23,
|
| 492 |
+
"learning_rate": 0.00011790644685698968,
|
| 493 |
+
"loss": 25.6432,
|
| 494 |
+
"step": 24500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.26,
|
| 498 |
+
"learning_rate": 0.00011623106822141805,
|
| 499 |
+
"loss": 25.6223,
|
| 500 |
+
"step": 25000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.26,
|
| 504 |
+
"eval_loss": 27.391796112060547,
|
| 505 |
+
"eval_runtime": 0.2101,
|
| 506 |
+
"eval_samples_per_second": 237.937,
|
| 507 |
+
"eval_steps_per_second": 9.517,
|
| 508 |
+
"step": 25000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.28,
|
| 512 |
+
"learning_rate": 0.00011455568958584641,
|
| 513 |
+
"loss": 25.6129,
|
| 514 |
+
"step": 25500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.31,
|
| 518 |
+
"learning_rate": 0.00011288031095027476,
|
| 519 |
+
"loss": 25.6234,
|
| 520 |
+
"step": 26000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.31,
|
| 524 |
+
"eval_loss": 27.368698120117188,
|
| 525 |
+
"eval_runtime": 0.2109,
|
| 526 |
+
"eval_samples_per_second": 237.043,
|
| 527 |
+
"eval_steps_per_second": 9.482,
|
| 528 |
+
"step": 26000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.33,
|
| 532 |
+
"learning_rate": 0.00011120493231470313,
|
| 533 |
+
"loss": 25.5979,
|
| 534 |
+
"step": 26500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.36,
|
| 538 |
+
"learning_rate": 0.00010952955367913149,
|
| 539 |
+
"loss": 25.623,
|
| 540 |
+
"step": 27000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.36,
|
| 544 |
+
"eval_loss": 27.350811004638672,
|
| 545 |
+
"eval_runtime": 0.2251,
|
| 546 |
+
"eval_samples_per_second": 222.106,
|
| 547 |
+
"eval_steps_per_second": 8.884,
|
| 548 |
+
"step": 27000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.38,
|
| 552 |
+
"learning_rate": 0.00010785417504355986,
|
| 553 |
+
"loss": 25.5917,
|
| 554 |
+
"step": 27500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.41,
|
| 558 |
+
"learning_rate": 0.00010617879640798821,
|
| 559 |
+
"loss": 25.5728,
|
| 560 |
+
"step": 28000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.41,
|
| 564 |
+
"eval_loss": 27.310701370239258,
|
| 565 |
+
"eval_runtime": 0.2112,
|
| 566 |
+
"eval_samples_per_second": 236.707,
|
| 567 |
+
"eval_steps_per_second": 9.468,
|
| 568 |
+
"step": 28000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.43,
|
| 572 |
+
"learning_rate": 0.00010450341777241657,
|
| 573 |
+
"loss": 25.5796,
|
| 574 |
+
"step": 28500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.46,
|
| 578 |
+
"learning_rate": 0.00010282803913684493,
|
| 579 |
+
"loss": 25.5648,
|
| 580 |
+
"step": 29000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.46,
|
| 584 |
+
"eval_loss": 27.295310974121094,
|
| 585 |
+
"eval_runtime": 0.217,
|
| 586 |
+
"eval_samples_per_second": 230.466,
|
| 587 |
+
"eval_steps_per_second": 9.219,
|
| 588 |
+
"step": 29000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.48,
|
| 592 |
+
"learning_rate": 0.0001011526605012733,
|
| 593 |
+
"loss": 25.5587,
|
| 594 |
+
"step": 29500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.51,
|
| 598 |
+
"learning_rate": 9.947728186570166e-05,
|
| 599 |
+
"loss": 25.5318,
|
| 600 |
+
"step": 30000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.51,
|
| 604 |
+
"eval_loss": 27.264293670654297,
|
| 605 |
+
"eval_runtime": 0.2116,
|
| 606 |
+
"eval_samples_per_second": 236.263,
|
| 607 |
+
"eval_steps_per_second": 9.451,
|
| 608 |
+
"step": 30000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.53,
|
| 612 |
+
"learning_rate": 9.780190323013e-05,
|
| 613 |
+
"loss": 25.5344,
|
| 614 |
+
"step": 30500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.56,
|
| 618 |
+
"learning_rate": 9.612652459455838e-05,
|
| 619 |
+
"loss": 25.5212,
|
| 620 |
+
"step": 31000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.56,
|
| 624 |
+
"eval_loss": 27.232440948486328,
|
| 625 |
+
"eval_runtime": 0.2137,
|
| 626 |
+
"eval_samples_per_second": 233.953,
|
| 627 |
+
"eval_steps_per_second": 9.358,
|
| 628 |
+
"step": 31000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.58,
|
| 632 |
+
"learning_rate": 9.445114595898673e-05,
|
| 633 |
+
"loss": 25.5354,
|
| 634 |
+
"step": 31500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.61,
|
| 638 |
+
"learning_rate": 9.27757673234151e-05,
|
| 639 |
+
"loss": 25.5099,
|
| 640 |
+
"step": 32000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.61,
|
| 644 |
+
"eval_loss": 27.240272521972656,
|
| 645 |
+
"eval_runtime": 0.2111,
|
| 646 |
+
"eval_samples_per_second": 236.859,
|
| 647 |
+
"eval_steps_per_second": 9.474,
|
| 648 |
+
"step": 32000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.63,
|
| 652 |
+
"learning_rate": 9.110038868784345e-05,
|
| 653 |
+
"loss": 25.5093,
|
| 654 |
+
"step": 32500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.66,
|
| 658 |
+
"learning_rate": 8.942501005227182e-05,
|
| 659 |
+
"loss": 25.497,
|
| 660 |
+
"step": 33000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.66,
|
| 664 |
+
"eval_loss": 27.228918075561523,
|
| 665 |
+
"eval_runtime": 0.2125,
|
| 666 |
+
"eval_samples_per_second": 235.337,
|
| 667 |
+
"eval_steps_per_second": 9.413,
|
| 668 |
+
"step": 33000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.68,
|
| 672 |
+
"learning_rate": 8.774963141670018e-05,
|
| 673 |
+
"loss": 25.5092,
|
| 674 |
+
"step": 33500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.71,
|
| 678 |
+
"learning_rate": 8.607425278112854e-05,
|
| 679 |
+
"loss": 25.4787,
|
| 680 |
+
"step": 34000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.71,
|
| 684 |
+
"eval_loss": 27.228187561035156,
|
| 685 |
+
"eval_runtime": 0.2095,
|
| 686 |
+
"eval_samples_per_second": 238.654,
|
| 687 |
+
"eval_steps_per_second": 9.546,
|
| 688 |
+
"step": 34000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.73,
|
| 692 |
+
"learning_rate": 8.439887414555691e-05,
|
| 693 |
+
"loss": 25.4684,
|
| 694 |
+
"step": 34500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.76,
|
| 698 |
+
"learning_rate": 8.272349550998526e-05,
|
| 699 |
+
"loss": 25.483,
|
| 700 |
+
"step": 35000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.76,
|
| 704 |
+
"eval_loss": 27.22612762451172,
|
| 705 |
+
"eval_runtime": 0.2116,
|
| 706 |
+
"eval_samples_per_second": 236.31,
|
| 707 |
+
"eval_steps_per_second": 9.452,
|
| 708 |
+
"step": 35000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 1.78,
|
| 712 |
+
"learning_rate": 8.104811687441363e-05,
|
| 713 |
+
"loss": 25.4463,
|
| 714 |
+
"step": 35500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.81,
|
| 718 |
+
"learning_rate": 7.937273823884198e-05,
|
| 719 |
+
"loss": 25.4702,
|
| 720 |
+
"step": 36000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.81,
|
| 724 |
+
"eval_loss": 27.186805725097656,
|
| 725 |
+
"eval_runtime": 0.2143,
|
| 726 |
+
"eval_samples_per_second": 233.331,
|
| 727 |
+
"eval_steps_per_second": 9.333,
|
| 728 |
+
"step": 36000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.83,
|
| 732 |
+
"learning_rate": 7.769735960327035e-05,
|
| 733 |
+
"loss": 25.4289,
|
| 734 |
+
"step": 36500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.86,
|
| 738 |
+
"learning_rate": 7.60219809676987e-05,
|
| 739 |
+
"loss": 25.4306,
|
| 740 |
+
"step": 37000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.86,
|
| 744 |
+
"eval_loss": 27.194353103637695,
|
| 745 |
+
"eval_runtime": 0.2096,
|
| 746 |
+
"eval_samples_per_second": 238.518,
|
| 747 |
+
"eval_steps_per_second": 9.541,
|
| 748 |
+
"step": 37000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.88,
|
| 752 |
+
"learning_rate": 7.434660233212707e-05,
|
| 753 |
+
"loss": 25.4421,
|
| 754 |
+
"step": 37500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.91,
|
| 758 |
+
"learning_rate": 7.267122369655543e-05,
|
| 759 |
+
"loss": 25.4518,
|
| 760 |
+
"step": 38000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.91,
|
| 764 |
+
"eval_loss": 27.154298782348633,
|
| 765 |
+
"eval_runtime": 0.22,
|
| 766 |
+
"eval_samples_per_second": 227.255,
|
| 767 |
+
"eval_steps_per_second": 9.09,
|
| 768 |
+
"step": 38000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.94,
|
| 772 |
+
"learning_rate": 7.099584506098379e-05,
|
| 773 |
+
"loss": 25.4411,
|
| 774 |
+
"step": 38500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.96,
|
| 778 |
+
"learning_rate": 6.932046642541215e-05,
|
| 779 |
+
"loss": 25.4264,
|
| 780 |
+
"step": 39000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.96,
|
| 784 |
+
"eval_loss": 27.156774520874023,
|
| 785 |
+
"eval_runtime": 0.2232,
|
| 786 |
+
"eval_samples_per_second": 224.006,
|
| 787 |
+
"eval_steps_per_second": 8.96,
|
| 788 |
+
"step": 39000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.99,
|
| 792 |
+
"learning_rate": 6.764508778984051e-05,
|
| 793 |
+
"loss": 25.4384,
|
| 794 |
+
"step": 39500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.01,
|
| 798 |
+
"learning_rate": 6.596970915426887e-05,
|
| 799 |
+
"loss": 25.4168,
|
| 800 |
+
"step": 40000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.01,
|
| 804 |
+
"eval_loss": 27.140100479125977,
|
| 805 |
+
"eval_runtime": 0.2133,
|
| 806 |
+
"eval_samples_per_second": 234.392,
|
| 807 |
+
"eval_steps_per_second": 9.376,
|
| 808 |
+
"step": 40000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.04,
|
| 812 |
+
"learning_rate": 6.429433051869723e-05,
|
| 813 |
+
"loss": 25.4029,
|
| 814 |
+
"step": 40500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.06,
|
| 818 |
+
"learning_rate": 6.261895188312559e-05,
|
| 819 |
+
"loss": 25.386,
|
| 820 |
+
"step": 41000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.06,
|
| 824 |
+
"eval_loss": 27.135889053344727,
|
| 825 |
+
"eval_runtime": 0.2136,
|
| 826 |
+
"eval_samples_per_second": 234.042,
|
| 827 |
+
"eval_steps_per_second": 9.362,
|
| 828 |
+
"step": 41000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.09,
|
| 832 |
+
"learning_rate": 6.0943573247553954e-05,
|
| 833 |
+
"loss": 25.3667,
|
| 834 |
+
"step": 41500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.11,
|
| 838 |
+
"learning_rate": 5.926819461198231e-05,
|
| 839 |
+
"loss": 25.3798,
|
| 840 |
+
"step": 42000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.11,
|
| 844 |
+
"eval_loss": 27.12567138671875,
|
| 845 |
+
"eval_runtime": 0.2109,
|
| 846 |
+
"eval_samples_per_second": 237.075,
|
| 847 |
+
"eval_steps_per_second": 9.483,
|
| 848 |
+
"step": 42000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.14,
|
| 852 |
+
"learning_rate": 5.7592815976410674e-05,
|
| 853 |
+
"loss": 25.3643,
|
| 854 |
+
"step": 42500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.16,
|
| 858 |
+
"learning_rate": 5.5917437340839026e-05,
|
| 859 |
+
"loss": 25.3643,
|
| 860 |
+
"step": 43000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.16,
|
| 864 |
+
"eval_loss": 27.113182067871094,
|
| 865 |
+
"eval_runtime": 0.2121,
|
| 866 |
+
"eval_samples_per_second": 235.709,
|
| 867 |
+
"eval_steps_per_second": 9.428,
|
| 868 |
+
"step": 43000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.19,
|
| 872 |
+
"learning_rate": 5.424205870526739e-05,
|
| 873 |
+
"loss": 25.3653,
|
| 874 |
+
"step": 43500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.21,
|
| 878 |
+
"learning_rate": 5.256668006969575e-05,
|
| 879 |
+
"loss": 25.3378,
|
| 880 |
+
"step": 44000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.21,
|
| 884 |
+
"eval_loss": 27.1131649017334,
|
| 885 |
+
"eval_runtime": 0.2131,
|
| 886 |
+
"eval_samples_per_second": 234.625,
|
| 887 |
+
"eval_steps_per_second": 9.385,
|
| 888 |
+
"step": 44000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.24,
|
| 892 |
+
"learning_rate": 5.089130143412412e-05,
|
| 893 |
+
"loss": 25.3598,
|
| 894 |
+
"step": 44500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.26,
|
| 898 |
+
"learning_rate": 4.921592279855248e-05,
|
| 899 |
+
"loss": 25.3431,
|
| 900 |
+
"step": 45000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.26,
|
| 904 |
+
"eval_loss": 27.10150909423828,
|
| 905 |
+
"eval_runtime": 0.3343,
|
| 906 |
+
"eval_samples_per_second": 149.553,
|
| 907 |
+
"eval_steps_per_second": 5.982,
|
| 908 |
+
"step": 45000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.29,
|
| 912 |
+
"learning_rate": 4.754054416298084e-05,
|
| 913 |
+
"loss": 25.3568,
|
| 914 |
+
"step": 45500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.31,
|
| 918 |
+
"learning_rate": 4.58651655274092e-05,
|
| 919 |
+
"loss": 25.3384,
|
| 920 |
+
"step": 46000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.31,
|
| 924 |
+
"eval_loss": 27.091062545776367,
|
| 925 |
+
"eval_runtime": 0.2132,
|
| 926 |
+
"eval_samples_per_second": 234.536,
|
| 927 |
+
"eval_steps_per_second": 9.381,
|
| 928 |
+
"step": 46000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.34,
|
| 932 |
+
"learning_rate": 4.418978689183756e-05,
|
| 933 |
+
"loss": 25.3337,
|
| 934 |
+
"step": 46500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.36,
|
| 938 |
+
"learning_rate": 4.251440825626592e-05,
|
| 939 |
+
"loss": 25.3516,
|
| 940 |
+
"step": 47000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.36,
|
| 944 |
+
"eval_loss": 27.0788631439209,
|
| 945 |
+
"eval_runtime": 0.2156,
|
| 946 |
+
"eval_samples_per_second": 231.865,
|
| 947 |
+
"eval_steps_per_second": 9.275,
|
| 948 |
+
"step": 47000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.39,
|
| 952 |
+
"learning_rate": 4.083902962069428e-05,
|
| 953 |
+
"loss": 25.3368,
|
| 954 |
+
"step": 47500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.41,
|
| 958 |
+
"learning_rate": 3.9163650985122644e-05,
|
| 959 |
+
"loss": 25.3104,
|
| 960 |
+
"step": 48000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.41,
|
| 964 |
+
"eval_loss": 27.085359573364258,
|
| 965 |
+
"eval_runtime": 0.2126,
|
| 966 |
+
"eval_samples_per_second": 235.191,
|
| 967 |
+
"eval_steps_per_second": 9.408,
|
| 968 |
+
"step": 48000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.44,
|
| 972 |
+
"learning_rate": 3.7488272349551004e-05,
|
| 973 |
+
"loss": 25.3357,
|
| 974 |
+
"step": 48500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.46,
|
| 978 |
+
"learning_rate": 3.581289371397936e-05,
|
| 979 |
+
"loss": 25.3254,
|
| 980 |
+
"step": 49000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.46,
|
| 984 |
+
"eval_loss": 27.069896697998047,
|
| 985 |
+
"eval_runtime": 0.2134,
|
| 986 |
+
"eval_samples_per_second": 234.3,
|
| 987 |
+
"eval_steps_per_second": 9.372,
|
| 988 |
+
"step": 49000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.49,
|
| 992 |
+
"learning_rate": 3.413751507840772e-05,
|
| 993 |
+
"loss": 25.3286,
|
| 994 |
+
"step": 49500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.51,
|
| 998 |
+
"learning_rate": 3.246213644283608e-05,
|
| 999 |
+
"loss": 25.3307,
|
| 1000 |
+
"step": 50000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.51,
|
| 1004 |
+
"eval_loss": 27.073589324951172,
|
| 1005 |
+
"eval_runtime": 0.2151,
|
| 1006 |
+
"eval_samples_per_second": 232.429,
|
| 1007 |
+
"eval_steps_per_second": 9.297,
|
| 1008 |
+
"step": 50000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 2.54,
|
| 1012 |
+
"learning_rate": 3.078675780726444e-05,
|
| 1013 |
+
"loss": 25.3197,
|
| 1014 |
+
"step": 50500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 2.56,
|
| 1018 |
+
"learning_rate": 2.9111379171692806e-05,
|
| 1019 |
+
"loss": 25.3153,
|
| 1020 |
+
"step": 51000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.56,
|
| 1024 |
+
"eval_loss": 27.077919006347656,
|
| 1025 |
+
"eval_runtime": 0.267,
|
| 1026 |
+
"eval_samples_per_second": 187.287,
|
| 1027 |
+
"eval_steps_per_second": 7.491,
|
| 1028 |
+
"step": 51000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.59,
|
| 1032 |
+
"learning_rate": 2.7436000536121165e-05,
|
| 1033 |
+
"loss": 25.3012,
|
| 1034 |
+
"step": 51500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.61,
|
| 1038 |
+
"learning_rate": 2.5760621900549525e-05,
|
| 1039 |
+
"loss": 25.3149,
|
| 1040 |
+
"step": 52000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.61,
|
| 1044 |
+
"eval_loss": 27.066099166870117,
|
| 1045 |
+
"eval_runtime": 0.2122,
|
| 1046 |
+
"eval_samples_per_second": 235.617,
|
| 1047 |
+
"eval_steps_per_second": 9.425,
|
| 1048 |
+
"step": 52000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.64,
|
| 1052 |
+
"learning_rate": 2.4085243264977885e-05,
|
| 1053 |
+
"loss": 25.2943,
|
| 1054 |
+
"step": 52500
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.66,
|
| 1058 |
+
"learning_rate": 2.2409864629406248e-05,
|
| 1059 |
+
"loss": 25.3251,
|
| 1060 |
+
"step": 53000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.66,
|
| 1064 |
+
"eval_loss": 27.05815887451172,
|
| 1065 |
+
"eval_runtime": 0.2117,
|
| 1066 |
+
"eval_samples_per_second": 236.215,
|
| 1067 |
+
"eval_steps_per_second": 9.449,
|
| 1068 |
+
"step": 53000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 2.69,
|
| 1072 |
+
"learning_rate": 2.0734485993834608e-05,
|
| 1073 |
+
"loss": 25.2907,
|
| 1074 |
+
"step": 53500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.71,
|
| 1078 |
+
"learning_rate": 1.9059107358262967e-05,
|
| 1079 |
+
"loss": 25.3185,
|
| 1080 |
+
"step": 54000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.71,
|
| 1084 |
+
"eval_loss": 27.06610107421875,
|
| 1085 |
+
"eval_runtime": 0.2143,
|
| 1086 |
+
"eval_samples_per_second": 233.359,
|
| 1087 |
+
"eval_steps_per_second": 9.334,
|
| 1088 |
+
"step": 54000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.74,
|
| 1092 |
+
"learning_rate": 1.7383728722691327e-05,
|
| 1093 |
+
"loss": 25.3016,
|
| 1094 |
+
"step": 54500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.76,
|
| 1098 |
+
"learning_rate": 1.570835008711969e-05,
|
| 1099 |
+
"loss": 25.3045,
|
| 1100 |
+
"step": 55000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 2.76,
|
| 1104 |
+
"eval_loss": 27.05499267578125,
|
| 1105 |
+
"eval_runtime": 0.2149,
|
| 1106 |
+
"eval_samples_per_second": 232.706,
|
| 1107 |
+
"eval_steps_per_second": 9.308,
|
| 1108 |
+
"step": 55000
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.79,
|
| 1112 |
+
"learning_rate": 1.403297145154805e-05,
|
| 1113 |
+
"loss": 25.2932,
|
| 1114 |
+
"step": 55500
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 2.81,
|
| 1118 |
+
"learning_rate": 1.2357592815976411e-05,
|
| 1119 |
+
"loss": 25.2952,
|
| 1120 |
+
"step": 56000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 2.81,
|
| 1124 |
+
"eval_loss": 27.059736251831055,
|
| 1125 |
+
"eval_runtime": 0.2105,
|
| 1126 |
+
"eval_samples_per_second": 237.516,
|
| 1127 |
+
"eval_steps_per_second": 9.501,
|
| 1128 |
+
"step": 56000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.84,
|
| 1132 |
+
"learning_rate": 1.0682214180404771e-05,
|
| 1133 |
+
"loss": 25.2941,
|
| 1134 |
+
"step": 56500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.86,
|
| 1138 |
+
"learning_rate": 9.006835544833132e-06,
|
| 1139 |
+
"loss": 25.2863,
|
| 1140 |
+
"step": 57000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.86,
|
| 1144 |
+
"eval_loss": 27.0577392578125,
|
| 1145 |
+
"eval_runtime": 0.231,
|
| 1146 |
+
"eval_samples_per_second": 216.423,
|
| 1147 |
+
"eval_steps_per_second": 8.657,
|
| 1148 |
+
"step": 57000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.89,
|
| 1152 |
+
"learning_rate": 7.331456909261493e-06,
|
| 1153 |
+
"loss": 25.2943,
|
| 1154 |
+
"step": 57500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.92,
|
| 1158 |
+
"learning_rate": 5.656078273689854e-06,
|
| 1159 |
+
"loss": 25.2966,
|
| 1160 |
+
"step": 58000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.92,
|
| 1164 |
+
"eval_loss": 27.05270004272461,
|
| 1165 |
+
"eval_runtime": 0.2335,
|
| 1166 |
+
"eval_samples_per_second": 214.093,
|
| 1167 |
+
"eval_steps_per_second": 8.564,
|
| 1168 |
+
"step": 58000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.94,
|
| 1172 |
+
"learning_rate": 3.980699638118215e-06,
|
| 1173 |
+
"loss": 25.2804,
|
| 1174 |
+
"step": 58500
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.97,
|
| 1178 |
+
"learning_rate": 2.3053210025465755e-06,
|
| 1179 |
+
"loss": 25.2995,
|
| 1180 |
+
"step": 59000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.97,
|
| 1184 |
+
"eval_loss": 27.049020767211914,
|
| 1185 |
+
"eval_runtime": 0.2618,
|
| 1186 |
+
"eval_samples_per_second": 190.997,
|
| 1187 |
+
"eval_steps_per_second": 7.64,
|
| 1188 |
+
"step": 59000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.99,
|
| 1192 |
+
"learning_rate": 6.299423669749365e-07,
|
| 1193 |
+
"loss": 25.2862,
|
| 1194 |
+
"step": 59500
|
| 1195 |
+
}
|
| 1196 |
+
],
|
| 1197 |
+
"max_steps": 59688,
|
| 1198 |
+
"num_train_epochs": 3,
|
| 1199 |
+
"total_flos": 3.715405206616277e+18,
|
| 1200 |
+
"trial_name": null,
|
| 1201 |
+
"trial_params": null
|
| 1202 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|