Upload folder using huggingface_hub
Browse files- config.json +24 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +2988 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"transformers_version": "4.49.0",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82081e245eab9e9dd44570083d901ccf854f896ebd452d0d8e4aa679a8d7e70f
|
| 3 |
+
size 438080896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6e55f56b6b21f902d4d66ad4c5f9b0a2b85765ee8c9ab2afb659fdaf686b61a
|
| 3 |
+
size 876283258
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7abf3d8a48de5f50fd0382e4101046ee954a7dfeada8292f492903c1a224b6c5
|
| 3 |
+
size 15024
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e55560599f734dcfe085f23d69b83fd22c94030a765a8d4a5442fda6f4cf7d7c
|
| 3 |
+
size 15024
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2c509b3db898f046695a7f2579630ea122da02e165185a8a9328be9454b697e
|
| 3 |
+
size 15024
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bb2a4e097d6e2436209122e86676326b157896d5995698beb298caa4d59a5b6
|
| 3 |
+
size 15024
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26e5f537b664c6fe19c69f0b7e769dc3608511afacddc6dad39ade9113b7fb41
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:867efd7bec88cf88c8283343b352c5d1f35a79f5c269aa1b2ee6d5c1fc52abed
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2988 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.126425266265869,
|
| 3 |
+
"best_model_checkpoint": "/work/Ccp-OldNewsBERT_2024/modelling/checkpoint-95500",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 98640,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07603406326034064,
|
| 13 |
+
"grad_norm": 1.1528505086898804,
|
| 14 |
+
"learning_rate": 1.25e-05,
|
| 15 |
+
"loss": 8.5532,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07603406326034064,
|
| 20 |
+
"eval_loss": 7.3156208992004395,
|
| 21 |
+
"eval_runtime": 392.108,
|
| 22 |
+
"eval_samples_per_second": 1073.301,
|
| 23 |
+
"eval_steps_per_second": 4.193,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.15206812652068127,
|
| 28 |
+
"grad_norm": 1.3152525424957275,
|
| 29 |
+
"learning_rate": 2.5e-05,
|
| 30 |
+
"loss": 7.0493,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.15206812652068127,
|
| 35 |
+
"eval_loss": 6.841813087463379,
|
| 36 |
+
"eval_runtime": 392.0485,
|
| 37 |
+
"eval_samples_per_second": 1073.464,
|
| 38 |
+
"eval_steps_per_second": 4.193,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.2281021897810219,
|
| 43 |
+
"grad_norm": 1.7870614528656006,
|
| 44 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 45 |
+
"loss": 6.7805,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.2281021897810219,
|
| 50 |
+
"eval_loss": 6.62256383895874,
|
| 51 |
+
"eval_runtime": 391.9186,
|
| 52 |
+
"eval_samples_per_second": 1073.82,
|
| 53 |
+
"eval_steps_per_second": 4.195,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.30413625304136255,
|
| 58 |
+
"grad_norm": 1.1754438877105713,
|
| 59 |
+
"learning_rate": 5e-05,
|
| 60 |
+
"loss": 6.5763,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.30413625304136255,
|
| 65 |
+
"eval_loss": 6.442608833312988,
|
| 66 |
+
"eval_runtime": 391.8632,
|
| 67 |
+
"eval_samples_per_second": 1073.972,
|
| 68 |
+
"eval_steps_per_second": 4.195,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.38017031630170317,
|
| 73 |
+
"grad_norm": 1.4492470026016235,
|
| 74 |
+
"learning_rate": 4.999669762518974e-05,
|
| 75 |
+
"loss": 6.4084,
|
| 76 |
+
"step": 2500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.38017031630170317,
|
| 80 |
+
"eval_loss": 6.2790422439575195,
|
| 81 |
+
"eval_runtime": 395.0617,
|
| 82 |
+
"eval_samples_per_second": 1065.277,
|
| 83 |
+
"eval_steps_per_second": 4.161,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.4562043795620438,
|
| 88 |
+
"grad_norm": 1.4527273178100586,
|
| 89 |
+
"learning_rate": 4.9986791373213283e-05,
|
| 90 |
+
"loss": 6.2422,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.4562043795620438,
|
| 95 |
+
"eval_loss": 6.124966621398926,
|
| 96 |
+
"eval_runtime": 394.995,
|
| 97 |
+
"eval_samples_per_second": 1065.457,
|
| 98 |
+
"eval_steps_per_second": 4.162,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.5322384428223844,
|
| 103 |
+
"grad_norm": 1.8543823957443237,
|
| 104 |
+
"learning_rate": 4.997028386120321e-05,
|
| 105 |
+
"loss": 6.0635,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.5322384428223844,
|
| 110 |
+
"eval_loss": 5.868374347686768,
|
| 111 |
+
"eval_runtime": 394.8994,
|
| 112 |
+
"eval_samples_per_second": 1065.715,
|
| 113 |
+
"eval_steps_per_second": 4.163,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6082725060827251,
|
| 118 |
+
"grad_norm": 1.973868489265442,
|
| 119 |
+
"learning_rate": 4.994717945027886e-05,
|
| 120 |
+
"loss": 5.7633,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6082725060827251,
|
| 125 |
+
"eval_loss": 5.493896961212158,
|
| 126 |
+
"eval_runtime": 394.9221,
|
| 127 |
+
"eval_samples_per_second": 1065.653,
|
| 128 |
+
"eval_steps_per_second": 4.163,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6843065693430657,
|
| 133 |
+
"grad_norm": 1.8778235912322998,
|
| 134 |
+
"learning_rate": 4.99174842443942e-05,
|
| 135 |
+
"loss": 5.429,
|
| 136 |
+
"step": 4500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6843065693430657,
|
| 140 |
+
"eval_loss": 5.116617679595947,
|
| 141 |
+
"eval_runtime": 394.8716,
|
| 142 |
+
"eval_samples_per_second": 1065.79,
|
| 143 |
+
"eval_steps_per_second": 4.163,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.7603406326034063,
|
| 148 |
+
"grad_norm": 2.0149049758911133,
|
| 149 |
+
"learning_rate": 4.9881206088725227e-05,
|
| 150 |
+
"loss": 5.0808,
|
| 151 |
+
"step": 5000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.7603406326034063,
|
| 155 |
+
"eval_loss": 4.774472713470459,
|
| 156 |
+
"eval_runtime": 395.1882,
|
| 157 |
+
"eval_samples_per_second": 1064.936,
|
| 158 |
+
"eval_steps_per_second": 4.16,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.8363746958637469,
|
| 163 |
+
"grad_norm": 1.7959963083267212,
|
| 164 |
+
"learning_rate": 4.983835456759734e-05,
|
| 165 |
+
"loss": 4.7725,
|
| 166 |
+
"step": 5500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.8363746958637469,
|
| 170 |
+
"eval_loss": 4.4951066970825195,
|
| 171 |
+
"eval_runtime": 395.052,
|
| 172 |
+
"eval_samples_per_second": 1065.303,
|
| 173 |
+
"eval_steps_per_second": 4.161,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.9124087591240876,
|
| 178 |
+
"grad_norm": 1.6965287923812866,
|
| 179 |
+
"learning_rate": 4.978894100195325e-05,
|
| 180 |
+
"loss": 4.5344,
|
| 181 |
+
"step": 6000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.9124087591240876,
|
| 185 |
+
"eval_loss": 4.28698205947876,
|
| 186 |
+
"eval_runtime": 395.1764,
|
| 187 |
+
"eval_samples_per_second": 1064.967,
|
| 188 |
+
"eval_steps_per_second": 4.16,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9884428223844283,
|
| 193 |
+
"grad_norm": 1.6758971214294434,
|
| 194 |
+
"learning_rate": 4.973297844636212e-05,
|
| 195 |
+
"loss": 4.3347,
|
| 196 |
+
"step": 6500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.9884428223844283,
|
| 200 |
+
"eval_loss": 4.129937648773193,
|
| 201 |
+
"eval_runtime": 395.104,
|
| 202 |
+
"eval_samples_per_second": 1065.163,
|
| 203 |
+
"eval_steps_per_second": 4.161,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.0644768856447688,
|
| 208 |
+
"grad_norm": 1.7391337156295776,
|
| 209 |
+
"learning_rate": 4.9670481685570645e-05,
|
| 210 |
+
"loss": 4.1883,
|
| 211 |
+
"step": 7000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.0644768856447688,
|
| 215 |
+
"eval_loss": 4.002706050872803,
|
| 216 |
+
"eval_runtime": 395.1014,
|
| 217 |
+
"eval_samples_per_second": 1065.17,
|
| 218 |
+
"eval_steps_per_second": 4.161,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1405109489051095,
|
| 223 |
+
"grad_norm": 1.592909812927246,
|
| 224 |
+
"learning_rate": 4.960146723059713e-05,
|
| 225 |
+
"loss": 4.0579,
|
| 226 |
+
"step": 7500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.1405109489051095,
|
| 230 |
+
"eval_loss": 3.8906095027923584,
|
| 231 |
+
"eval_runtime": 395.0202,
|
| 232 |
+
"eval_samples_per_second": 1065.389,
|
| 233 |
+
"eval_steps_per_second": 4.162,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.2165450121654502,
|
| 238 |
+
"grad_norm": 1.7625865936279297,
|
| 239 |
+
"learning_rate": 4.952595331436939e-05,
|
| 240 |
+
"loss": 3.9484,
|
| 241 |
+
"step": 8000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.2165450121654502,
|
| 245 |
+
"eval_loss": 3.793649673461914,
|
| 246 |
+
"eval_runtime": 395.0939,
|
| 247 |
+
"eval_samples_per_second": 1065.19,
|
| 248 |
+
"eval_steps_per_second": 4.161,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.2925790754257909,
|
| 253 |
+
"grad_norm": 1.5408483743667603,
|
| 254 |
+
"learning_rate": 4.9443959886907786e-05,
|
| 255 |
+
"loss": 3.8541,
|
| 256 |
+
"step": 8500
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.2925790754257909,
|
| 260 |
+
"eval_loss": 3.707909107208252,
|
| 261 |
+
"eval_runtime": 395.0107,
|
| 262 |
+
"eval_samples_per_second": 1065.414,
|
| 263 |
+
"eval_steps_per_second": 4.162,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.3686131386861313,
|
| 268 |
+
"grad_norm": 1.5377788543701172,
|
| 269 |
+
"learning_rate": 4.935550861005469e-05,
|
| 270 |
+
"loss": 3.7751,
|
| 271 |
+
"step": 9000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.3686131386861313,
|
| 275 |
+
"eval_loss": 3.6381478309631348,
|
| 276 |
+
"eval_runtime": 395.0196,
|
| 277 |
+
"eval_samples_per_second": 1065.39,
|
| 278 |
+
"eval_steps_per_second": 4.162,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.444647201946472,
|
| 283 |
+
"grad_norm": 1.5185712575912476,
|
| 284 |
+
"learning_rate": 4.926062285175158e-05,
|
| 285 |
+
"loss": 3.7,
|
| 286 |
+
"step": 9500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.444647201946472,
|
| 290 |
+
"eval_loss": 3.56645131111145,
|
| 291 |
+
"eval_runtime": 395.0168,
|
| 292 |
+
"eval_samples_per_second": 1065.398,
|
| 293 |
+
"eval_steps_per_second": 4.162,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.5206812652068127,
|
| 298 |
+
"grad_norm": 1.4640849828720093,
|
| 299 |
+
"learning_rate": 4.9159536649297986e-05,
|
| 300 |
+
"loss": 3.6397,
|
| 301 |
+
"step": 10000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.5206812652068127,
|
| 305 |
+
"eval_loss": 3.5038576126098633,
|
| 306 |
+
"eval_runtime": 395.2609,
|
| 307 |
+
"eval_samples_per_second": 1064.74,
|
| 308 |
+
"eval_steps_per_second": 4.159,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.5967153284671531,
|
| 313 |
+
"grad_norm": 1.7205146551132202,
|
| 314 |
+
"learning_rate": 4.9051871562474056e-05,
|
| 315 |
+
"loss": 3.5783,
|
| 316 |
+
"step": 10500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.5967153284671531,
|
| 320 |
+
"eval_loss": 3.4472110271453857,
|
| 321 |
+
"eval_runtime": 395.1986,
|
| 322 |
+
"eval_samples_per_second": 1064.908,
|
| 323 |
+
"eval_steps_per_second": 4.16,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.672749391727494,
|
| 328 |
+
"grad_norm": 1.605870008468628,
|
| 329 |
+
"learning_rate": 4.8937852212067106e-05,
|
| 330 |
+
"loss": 3.5196,
|
| 331 |
+
"step": 11000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.672749391727494,
|
| 335 |
+
"eval_loss": 3.3966190814971924,
|
| 336 |
+
"eval_runtime": 395.1285,
|
| 337 |
+
"eval_samples_per_second": 1065.097,
|
| 338 |
+
"eval_steps_per_second": 4.161,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.7487834549878345,
|
| 343 |
+
"grad_norm": 1.6770403385162354,
|
| 344 |
+
"learning_rate": 4.8817508720847596e-05,
|
| 345 |
+
"loss": 3.4701,
|
| 346 |
+
"step": 11500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.7487834549878345,
|
| 350 |
+
"eval_loss": 3.34128999710083,
|
| 351 |
+
"eval_runtime": 395.1091,
|
| 352 |
+
"eval_samples_per_second": 1065.149,
|
| 353 |
+
"eval_steps_per_second": 4.161,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.8248175182481752,
|
| 358 |
+
"grad_norm": 1.5218740701675415,
|
| 359 |
+
"learning_rate": 4.869087288236064e-05,
|
| 360 |
+
"loss": 3.4226,
|
| 361 |
+
"step": 12000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.8248175182481752,
|
| 365 |
+
"eval_loss": 3.301135540008545,
|
| 366 |
+
"eval_runtime": 395.0668,
|
| 367 |
+
"eval_samples_per_second": 1065.263,
|
| 368 |
+
"eval_steps_per_second": 4.161,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9008515815085159,
|
| 373 |
+
"grad_norm": 1.528290867805481,
|
| 374 |
+
"learning_rate": 4.855797815252648e-05,
|
| 375 |
+
"loss": 3.3704,
|
| 376 |
+
"step": 12500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.9008515815085159,
|
| 380 |
+
"eval_loss": 3.255563735961914,
|
| 381 |
+
"eval_runtime": 395.0617,
|
| 382 |
+
"eval_samples_per_second": 1065.277,
|
| 383 |
+
"eval_steps_per_second": 4.161,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.9768856447688563,
|
| 388 |
+
"grad_norm": 1.4962824583053589,
|
| 389 |
+
"learning_rate": 4.8418859640801796e-05,
|
| 390 |
+
"loss": 3.3326,
|
| 391 |
+
"step": 13000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.9768856447688563,
|
| 395 |
+
"eval_loss": 3.2163586616516113,
|
| 396 |
+
"eval_runtime": 395.1594,
|
| 397 |
+
"eval_samples_per_second": 1065.013,
|
| 398 |
+
"eval_steps_per_second": 4.16,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.052919708029197,
|
| 403 |
+
"grad_norm": 1.5214394330978394,
|
| 404 |
+
"learning_rate": 4.8273554100904066e-05,
|
| 405 |
+
"loss": 3.2872,
|
| 406 |
+
"step": 13500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.052919708029197,
|
| 410 |
+
"eval_loss": 3.178077220916748,
|
| 411 |
+
"eval_runtime": 395.023,
|
| 412 |
+
"eval_samples_per_second": 1065.381,
|
| 413 |
+
"eval_steps_per_second": 4.162,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.1289537712895377,
|
| 418 |
+
"grad_norm": 1.6362810134887695,
|
| 419 |
+
"learning_rate": 4.8122408939478185e-05,
|
| 420 |
+
"loss": 3.2453,
|
| 421 |
+
"step": 14000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.1289537712895377,
|
| 425 |
+
"eval_loss": 3.1436197757720947,
|
| 426 |
+
"eval_runtime": 395.163,
|
| 427 |
+
"eval_samples_per_second": 1065.004,
|
| 428 |
+
"eval_steps_per_second": 4.16,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.204987834549878,
|
| 433 |
+
"grad_norm": 1.6314831972122192,
|
| 434 |
+
"learning_rate": 4.79651794790509e-05,
|
| 435 |
+
"loss": 3.2149,
|
| 436 |
+
"step": 14500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.204987834549878,
|
| 440 |
+
"eval_loss": 3.1076748371124268,
|
| 441 |
+
"eval_runtime": 395.3195,
|
| 442 |
+
"eval_samples_per_second": 1064.582,
|
| 443 |
+
"eval_steps_per_second": 4.159,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.281021897810219,
|
| 448 |
+
"grad_norm": 1.5647250413894653,
|
| 449 |
+
"learning_rate": 4.7801573854264494e-05,
|
| 450 |
+
"loss": 3.1836,
|
| 451 |
+
"step": 15000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.281021897810219,
|
| 455 |
+
"eval_loss": 3.081753969192505,
|
| 456 |
+
"eval_runtime": 395.1551,
|
| 457 |
+
"eval_samples_per_second": 1065.025,
|
| 458 |
+
"eval_steps_per_second": 4.16,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.3570559610705595,
|
| 463 |
+
"grad_norm": 1.559869408607483,
|
| 464 |
+
"learning_rate": 4.763194428202762e-05,
|
| 465 |
+
"loss": 3.1459,
|
| 466 |
+
"step": 15500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.3570559610705595,
|
| 470 |
+
"eval_loss": 3.044140100479126,
|
| 471 |
+
"eval_runtime": 395.2791,
|
| 472 |
+
"eval_samples_per_second": 1064.691,
|
| 473 |
+
"eval_steps_per_second": 4.159,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.4330900243309004,
|
| 478 |
+
"grad_norm": 1.669546365737915,
|
| 479 |
+
"learning_rate": 4.745633557677441e-05,
|
| 480 |
+
"loss": 3.1298,
|
| 481 |
+
"step": 16000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.4330900243309004,
|
| 485 |
+
"eval_loss": 3.015268325805664,
|
| 486 |
+
"eval_runtime": 395.2158,
|
| 487 |
+
"eval_samples_per_second": 1064.861,
|
| 488 |
+
"eval_steps_per_second": 4.16,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.509124087591241,
|
| 493 |
+
"grad_norm": 1.5877552032470703,
|
| 494 |
+
"learning_rate": 4.727479413256602e-05,
|
| 495 |
+
"loss": 3.0882,
|
| 496 |
+
"step": 16500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.509124087591241,
|
| 500 |
+
"eval_loss": 2.9866795539855957,
|
| 501 |
+
"eval_runtime": 395.1307,
|
| 502 |
+
"eval_samples_per_second": 1065.091,
|
| 503 |
+
"eval_steps_per_second": 4.161,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.5851581508515817,
|
| 508 |
+
"grad_norm": 1.6820305585861206,
|
| 509 |
+
"learning_rate": 4.708736791083384e-05,
|
| 510 |
+
"loss": 3.0738,
|
| 511 |
+
"step": 17000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.5851581508515817,
|
| 515 |
+
"eval_loss": 2.957209587097168,
|
| 516 |
+
"eval_runtime": 395.2085,
|
| 517 |
+
"eval_samples_per_second": 1064.881,
|
| 518 |
+
"eval_steps_per_second": 4.16,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.661192214111922,
|
| 523 |
+
"grad_norm": 1.4878249168395996,
|
| 524 |
+
"learning_rate": 4.6894106427708574e-05,
|
| 525 |
+
"loss": 3.0409,
|
| 526 |
+
"step": 17500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.661192214111922,
|
| 530 |
+
"eval_loss": 2.931816339492798,
|
| 531 |
+
"eval_runtime": 395.1436,
|
| 532 |
+
"eval_samples_per_second": 1065.056,
|
| 533 |
+
"eval_steps_per_second": 4.161,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.7372262773722627,
|
| 538 |
+
"grad_norm": 1.5256247520446777,
|
| 539 |
+
"learning_rate": 4.669546457024816e-05,
|
| 540 |
+
"loss": 3.0155,
|
| 541 |
+
"step": 18000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.7372262773722627,
|
| 545 |
+
"eval_loss": 2.9121601581573486,
|
| 546 |
+
"eval_runtime": 395.308,
|
| 547 |
+
"eval_samples_per_second": 1064.613,
|
| 548 |
+
"eval_steps_per_second": 4.159,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.8132603406326036,
|
| 553 |
+
"grad_norm": 1.6648399829864502,
|
| 554 |
+
"learning_rate": 4.649069867545623e-05,
|
| 555 |
+
"loss": 2.9909,
|
| 556 |
+
"step": 18500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.8132603406326036,
|
| 560 |
+
"eval_loss": 2.890857219696045,
|
| 561 |
+
"eval_runtime": 395.436,
|
| 562 |
+
"eval_samples_per_second": 1064.268,
|
| 563 |
+
"eval_steps_per_second": 4.157,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.889294403892944,
|
| 568 |
+
"grad_norm": 1.6078656911849976,
|
| 569 |
+
"learning_rate": 4.628025515330744e-05,
|
| 570 |
+
"loss": 2.9754,
|
| 571 |
+
"step": 19000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.889294403892944,
|
| 575 |
+
"eval_loss": 2.865665912628174,
|
| 576 |
+
"eval_runtime": 395.2576,
|
| 577 |
+
"eval_samples_per_second": 1064.749,
|
| 578 |
+
"eval_steps_per_second": 4.159,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.9653284671532845,
|
| 583 |
+
"grad_norm": 1.595712661743164,
|
| 584 |
+
"learning_rate": 4.60641896008727e-05,
|
| 585 |
+
"loss": 2.9512,
|
| 586 |
+
"step": 19500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.9653284671532845,
|
| 590 |
+
"eval_loss": 2.8427441120147705,
|
| 591 |
+
"eval_runtime": 395.1474,
|
| 592 |
+
"eval_samples_per_second": 1065.046,
|
| 593 |
+
"eval_steps_per_second": 4.16,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.0413625304136254,
|
| 598 |
+
"grad_norm": 1.5582592487335205,
|
| 599 |
+
"learning_rate": 4.584255910050703e-05,
|
| 600 |
+
"loss": 2.9132,
|
| 601 |
+
"step": 20000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.0413625304136254,
|
| 605 |
+
"eval_loss": 2.821183681488037,
|
| 606 |
+
"eval_runtime": 395.3458,
|
| 607 |
+
"eval_samples_per_second": 1064.511,
|
| 608 |
+
"eval_steps_per_second": 4.158,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.117396593673966,
|
| 613 |
+
"grad_norm": 1.6548606157302856,
|
| 614 |
+
"learning_rate": 4.561588193429872e-05,
|
| 615 |
+
"loss": 2.9021,
|
| 616 |
+
"step": 20500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 3.117396593673966,
|
| 620 |
+
"eval_loss": 2.802894115447998,
|
| 621 |
+
"eval_runtime": 395.4185,
|
| 622 |
+
"eval_samples_per_second": 1064.315,
|
| 623 |
+
"eval_steps_per_second": 4.158,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.1934306569343067,
|
| 628 |
+
"grad_norm": 1.6921550035476685,
|
| 629 |
+
"learning_rate": 4.538330948241111e-05,
|
| 630 |
+
"loss": 2.8889,
|
| 631 |
+
"step": 21000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.1934306569343067,
|
| 635 |
+
"eval_loss": 2.7827913761138916,
|
| 636 |
+
"eval_runtime": 395.1602,
|
| 637 |
+
"eval_samples_per_second": 1065.011,
|
| 638 |
+
"eval_steps_per_second": 4.16,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.269464720194647,
|
| 643 |
+
"grad_norm": 1.7307897806167603,
|
| 644 |
+
"learning_rate": 4.514535196430073e-05,
|
| 645 |
+
"loss": 2.8642,
|
| 646 |
+
"step": 21500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.269464720194647,
|
| 650 |
+
"eval_loss": 2.767017126083374,
|
| 651 |
+
"eval_runtime": 395.2268,
|
| 652 |
+
"eval_samples_per_second": 1064.832,
|
| 653 |
+
"eval_steps_per_second": 4.16,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.345498783454988,
|
| 658 |
+
"grad_norm": 1.7314034700393677,
|
| 659 |
+
"learning_rate": 4.490207224596068e-05,
|
| 660 |
+
"loss": 2.8517,
|
| 661 |
+
"step": 22000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.345498783454988,
|
| 665 |
+
"eval_loss": 2.747631311416626,
|
| 666 |
+
"eval_runtime": 395.1865,
|
| 667 |
+
"eval_samples_per_second": 1064.94,
|
| 668 |
+
"eval_steps_per_second": 4.16,
|
| 669 |
+
"step": 22000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.4215328467153285,
|
| 673 |
+
"grad_norm": 1.7844088077545166,
|
| 674 |
+
"learning_rate": 4.465353459945605e-05,
|
| 675 |
+
"loss": 2.8341,
|
| 676 |
+
"step": 22500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 3.4215328467153285,
|
| 680 |
+
"eval_loss": 2.7319579124450684,
|
| 681 |
+
"eval_runtime": 395.3244,
|
| 682 |
+
"eval_samples_per_second": 1064.569,
|
| 683 |
+
"eval_steps_per_second": 4.159,
|
| 684 |
+
"step": 22500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.497566909975669,
|
| 688 |
+
"grad_norm": 1.5570697784423828,
|
| 689 |
+
"learning_rate": 4.43998046859439e-05,
|
| 690 |
+
"loss": 2.8102,
|
| 691 |
+
"step": 23000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.497566909975669,
|
| 695 |
+
"eval_loss": 2.7134299278259277,
|
| 696 |
+
"eval_runtime": 395.3813,
|
| 697 |
+
"eval_samples_per_second": 1064.416,
|
| 698 |
+
"eval_steps_per_second": 4.158,
|
| 699 |
+
"step": 23000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.57360097323601,
|
| 703 |
+
"grad_norm": 1.5903196334838867,
|
| 704 |
+
"learning_rate": 4.414094953832625e-05,
|
| 705 |
+
"loss": 2.7942,
|
| 706 |
+
"step": 23500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.57360097323601,
|
| 710 |
+
"eval_loss": 2.696880340576172,
|
| 711 |
+
"eval_runtime": 395.3996,
|
| 712 |
+
"eval_samples_per_second": 1064.366,
|
| 713 |
+
"eval_steps_per_second": 4.158,
|
| 714 |
+
"step": 23500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.6496350364963503,
|
| 718 |
+
"grad_norm": 1.7155580520629883,
|
| 719 |
+
"learning_rate": 4.387703754354059e-05,
|
| 720 |
+
"loss": 2.7893,
|
| 721 |
+
"step": 24000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.6496350364963503,
|
| 725 |
+
"eval_loss": 2.6850531101226807,
|
| 726 |
+
"eval_runtime": 395.3598,
|
| 727 |
+
"eval_samples_per_second": 1064.473,
|
| 728 |
+
"eval_steps_per_second": 4.158,
|
| 729 |
+
"step": 24000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.725669099756691,
|
| 733 |
+
"grad_norm": 1.5948296785354614,
|
| 734 |
+
"learning_rate": 4.3608681152880126e-05,
|
| 735 |
+
"loss": 2.7681,
|
| 736 |
+
"step": 24500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.725669099756691,
|
| 740 |
+
"eval_loss": 2.66740345954895,
|
| 741 |
+
"eval_runtime": 395.2365,
|
| 742 |
+
"eval_samples_per_second": 1064.805,
|
| 743 |
+
"eval_steps_per_second": 4.16,
|
| 744 |
+
"step": 24500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.8017031630170317,
|
| 748 |
+
"grad_norm": 1.5723962783813477,
|
| 749 |
+
"learning_rate": 4.333487571042728e-05,
|
| 750 |
+
"loss": 2.7577,
|
| 751 |
+
"step": 25000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.8017031630170317,
|
| 755 |
+
"eval_loss": 2.654303789138794,
|
| 756 |
+
"eval_runtime": 395.3645,
|
| 757 |
+
"eval_samples_per_second": 1064.461,
|
| 758 |
+
"eval_steps_per_second": 4.158,
|
| 759 |
+
"step": 25000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.877737226277372,
|
| 763 |
+
"grad_norm": 1.6151896715164185,
|
| 764 |
+
"learning_rate": 4.3056226377438776e-05,
|
| 765 |
+
"loss": 2.7427,
|
| 766 |
+
"step": 25500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.877737226277372,
|
| 770 |
+
"eval_loss": 2.643014669418335,
|
| 771 |
+
"eval_runtime": 395.2931,
|
| 772 |
+
"eval_samples_per_second": 1064.653,
|
| 773 |
+
"eval_steps_per_second": 4.159,
|
| 774 |
+
"step": 25500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.9537712895377126,
|
| 778 |
+
"grad_norm": 1.670333743095398,
|
| 779 |
+
"learning_rate": 4.27728067702777e-05,
|
| 780 |
+
"loss": 2.7302,
|
| 781 |
+
"step": 26000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.9537712895377126,
|
| 785 |
+
"eval_loss": 2.6284077167510986,
|
| 786 |
+
"eval_runtime": 395.1357,
|
| 787 |
+
"eval_samples_per_second": 1065.077,
|
| 788 |
+
"eval_steps_per_second": 4.161,
|
| 789 |
+
"step": 26000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.0298053527980535,
|
| 793 |
+
"grad_norm": 1.551099419593811,
|
| 794 |
+
"learning_rate": 4.248469176556575e-05,
|
| 795 |
+
"loss": 2.7106,
|
| 796 |
+
"step": 26500
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 4.0298053527980535,
|
| 800 |
+
"eval_loss": 2.616875171661377,
|
| 801 |
+
"eval_runtime": 395.4614,
|
| 802 |
+
"eval_samples_per_second": 1064.2,
|
| 803 |
+
"eval_steps_per_second": 4.157,
|
| 804 |
+
"step": 26500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 4.105839416058394,
|
| 808 |
+
"grad_norm": 1.6209259033203125,
|
| 809 |
+
"learning_rate": 4.219313751705213e-05,
|
| 810 |
+
"loss": 2.7007,
|
| 811 |
+
"step": 27000
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 4.105839416058394,
|
| 815 |
+
"eval_loss": 2.6068313121795654,
|
| 816 |
+
"eval_runtime": 395.5688,
|
| 817 |
+
"eval_samples_per_second": 1063.911,
|
| 818 |
+
"eval_steps_per_second": 4.156,
|
| 819 |
+
"step": 27000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.181873479318734,
|
| 823 |
+
"grad_norm": 1.616698980331421,
|
| 824 |
+
"learning_rate": 4.189587930102075e-05,
|
| 825 |
+
"loss": 2.6858,
|
| 826 |
+
"step": 27500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 4.181873479318734,
|
| 830 |
+
"eval_loss": 2.5947837829589844,
|
| 831 |
+
"eval_runtime": 395.5316,
|
| 832 |
+
"eval_samples_per_second": 1064.011,
|
| 833 |
+
"eval_steps_per_second": 4.156,
|
| 834 |
+
"step": 27500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 4.257907542579075,
|
| 838 |
+
"grad_norm": 1.6252193450927734,
|
| 839 |
+
"learning_rate": 4.1594157362893294e-05,
|
| 840 |
+
"loss": 2.6748,
|
| 841 |
+
"step": 28000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 4.257907542579075,
|
| 845 |
+
"eval_loss": 2.5821821689605713,
|
| 846 |
+
"eval_runtime": 395.6317,
|
| 847 |
+
"eval_samples_per_second": 1063.742,
|
| 848 |
+
"eval_steps_per_second": 4.155,
|
| 849 |
+
"step": 28000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.333941605839416,
|
| 853 |
+
"grad_norm": 1.5178853273391724,
|
| 854 |
+
"learning_rate": 4.1288051414584004e-05,
|
| 855 |
+
"loss": 2.672,
|
| 856 |
+
"step": 28500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.333941605839416,
|
| 860 |
+
"eval_loss": 2.566763162612915,
|
| 861 |
+
"eval_runtime": 395.3024,
|
| 862 |
+
"eval_samples_per_second": 1064.628,
|
| 863 |
+
"eval_steps_per_second": 4.159,
|
| 864 |
+
"step": 28500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.409975669099756,
|
| 868 |
+
"grad_norm": 1.6428803205490112,
|
| 869 |
+
"learning_rate": 4.097764232621873e-05,
|
| 870 |
+
"loss": 2.6498,
|
| 871 |
+
"step": 29000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.409975669099756,
|
| 875 |
+
"eval_loss": 2.560192823410034,
|
| 876 |
+
"eval_runtime": 395.2916,
|
| 877 |
+
"eval_samples_per_second": 1064.657,
|
| 878 |
+
"eval_steps_per_second": 4.159,
|
| 879 |
+
"step": 29000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.486009732360097,
|
| 883 |
+
"grad_norm": 1.546608805656433,
|
| 884 |
+
"learning_rate": 4.066301210476981e-05,
|
| 885 |
+
"loss": 2.6422,
|
| 886 |
+
"step": 29500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.486009732360097,
|
| 890 |
+
"eval_loss": 2.5504369735717773,
|
| 891 |
+
"eval_runtime": 395.4025,
|
| 892 |
+
"eval_samples_per_second": 1064.358,
|
| 893 |
+
"eval_steps_per_second": 4.158,
|
| 894 |
+
"step": 29500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 4.562043795620438,
|
| 898 |
+
"grad_norm": 1.6463203430175781,
|
| 899 |
+
"learning_rate": 4.034424387239068e-05,
|
| 900 |
+
"loss": 2.6334,
|
| 901 |
+
"step": 30000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 4.562043795620438,
|
| 905 |
+
"eval_loss": 2.540264844894409,
|
| 906 |
+
"eval_runtime": 395.609,
|
| 907 |
+
"eval_samples_per_second": 1063.803,
|
| 908 |
+
"eval_steps_per_second": 4.156,
|
| 909 |
+
"step": 30000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.638077858880779,
|
| 913 |
+
"grad_norm": 1.69281005859375,
|
| 914 |
+
"learning_rate": 4.002142184445579e-05,
|
| 915 |
+
"loss": 2.6246,
|
| 916 |
+
"step": 30500
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.638077858880779,
|
| 920 |
+
"eval_loss": 2.529710292816162,
|
| 921 |
+
"eval_runtime": 395.534,
|
| 922 |
+
"eval_samples_per_second": 1064.005,
|
| 923 |
+
"eval_steps_per_second": 4.156,
|
| 924 |
+
"step": 30500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 4.714111922141119,
|
| 928 |
+
"grad_norm": 1.4954875707626343,
|
| 929 |
+
"learning_rate": 3.969594626065171e-05,
|
| 930 |
+
"loss": 2.6194,
|
| 931 |
+
"step": 31000
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 4.714111922141119,
|
| 935 |
+
"eval_loss": 2.5173487663269043,
|
| 936 |
+
"eval_runtime": 395.5366,
|
| 937 |
+
"eval_samples_per_second": 1063.998,
|
| 938 |
+
"eval_steps_per_second": 4.156,
|
| 939 |
+
"step": 31000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 4.79014598540146,
|
| 943 |
+
"grad_norm": 1.586890459060669,
|
| 944 |
+
"learning_rate": 3.936528890443755e-05,
|
| 945 |
+
"loss": 2.6044,
|
| 946 |
+
"step": 31500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.79014598540146,
|
| 950 |
+
"eval_loss": 2.509347438812256,
|
| 951 |
+
"eval_runtime": 395.6037,
|
| 952 |
+
"eval_samples_per_second": 1063.817,
|
| 953 |
+
"eval_steps_per_second": 4.156,
|
| 954 |
+
"step": 31500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 4.866180048661801,
|
| 958 |
+
"grad_norm": 1.4862339496612549,
|
| 959 |
+
"learning_rate": 3.903083638276577e-05,
|
| 960 |
+
"loss": 2.585,
|
| 961 |
+
"step": 32000
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 4.866180048661801,
|
| 965 |
+
"eval_loss": 2.498917579650879,
|
| 966 |
+
"eval_runtime": 395.4783,
|
| 967 |
+
"eval_samples_per_second": 1064.154,
|
| 968 |
+
"eval_steps_per_second": 4.157,
|
| 969 |
+
"step": 32000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.942214111922141,
|
| 973 |
+
"grad_norm": 1.6119396686553955,
|
| 974 |
+
"learning_rate": 3.869267705464299e-05,
|
| 975 |
+
"loss": 2.5825,
|
| 976 |
+
"step": 32500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.942214111922141,
|
| 980 |
+
"eval_loss": 2.4927380084991455,
|
| 981 |
+
"eval_runtime": 395.5817,
|
| 982 |
+
"eval_samples_per_second": 1063.876,
|
| 983 |
+
"eval_steps_per_second": 4.156,
|
| 984 |
+
"step": 32500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.018248175182482,
|
| 988 |
+
"grad_norm": 1.5895634889602661,
|
| 989 |
+
"learning_rate": 3.835090025837699e-05,
|
| 990 |
+
"loss": 2.5708,
|
| 991 |
+
"step": 33000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 5.018248175182482,
|
| 995 |
+
"eval_loss": 2.4862186908721924,
|
| 996 |
+
"eval_runtime": 395.6219,
|
| 997 |
+
"eval_samples_per_second": 1063.768,
|
| 998 |
+
"eval_steps_per_second": 4.155,
|
| 999 |
+
"step": 33000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.094282238442823,
|
| 1003 |
+
"grad_norm": 1.6652857065200806,
|
| 1004 |
+
"learning_rate": 3.800559628797438e-05,
|
| 1005 |
+
"loss": 2.5612,
|
| 1006 |
+
"step": 33500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 5.094282238442823,
|
| 1010 |
+
"eval_loss": 2.475658416748047,
|
| 1011 |
+
"eval_runtime": 394.9698,
|
| 1012 |
+
"eval_samples_per_second": 1065.525,
|
| 1013 |
+
"eval_steps_per_second": 4.162,
|
| 1014 |
+
"step": 33500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.170316301703163,
|
| 1018 |
+
"grad_norm": 1.6712974309921265,
|
| 1019 |
+
"learning_rate": 3.765685636928585e-05,
|
| 1020 |
+
"loss": 2.5508,
|
| 1021 |
+
"step": 34000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 5.170316301703163,
|
| 1025 |
+
"eval_loss": 2.4684622287750244,
|
| 1026 |
+
"eval_runtime": 394.7029,
|
| 1027 |
+
"eval_samples_per_second": 1066.245,
|
| 1028 |
+
"eval_steps_per_second": 4.165,
|
| 1029 |
+
"step": 34000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 5.2463503649635035,
|
| 1033 |
+
"grad_norm": 1.7370678186416626,
|
| 1034 |
+
"learning_rate": 3.7305480078818275e-05,
|
| 1035 |
+
"loss": 2.5517,
|
| 1036 |
+
"step": 34500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 5.2463503649635035,
|
| 1040 |
+
"eval_loss": 2.4651219844818115,
|
| 1041 |
+
"eval_runtime": 395.1235,
|
| 1042 |
+
"eval_samples_per_second": 1065.11,
|
| 1043 |
+
"eval_steps_per_second": 4.161,
|
| 1044 |
+
"step": 34500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 5.322384428223844,
|
| 1048 |
+
"grad_norm": 1.6240907907485962,
|
| 1049 |
+
"learning_rate": 3.6950151955931227e-05,
|
| 1050 |
+
"loss": 2.536,
|
| 1051 |
+
"step": 35000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 5.322384428223844,
|
| 1055 |
+
"eval_loss": 2.4535937309265137,
|
| 1056 |
+
"eval_runtime": 394.9571,
|
| 1057 |
+
"eval_samples_per_second": 1065.559,
|
| 1058 |
+
"eval_steps_per_second": 4.162,
|
| 1059 |
+
"step": 35000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 5.398418491484185,
|
| 1063 |
+
"grad_norm": 1.8107973337173462,
|
| 1064 |
+
"learning_rate": 3.659166672258033e-05,
|
| 1065 |
+
"loss": 2.5362,
|
| 1066 |
+
"step": 35500
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 5.398418491484185,
|
| 1070 |
+
"eval_loss": 2.4444773197174072,
|
| 1071 |
+
"eval_runtime": 395.3,
|
| 1072 |
+
"eval_samples_per_second": 1064.635,
|
| 1073 |
+
"eval_steps_per_second": 4.159,
|
| 1074 |
+
"step": 35500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 5.474452554744525,
|
| 1078 |
+
"grad_norm": 1.550801396369934,
|
| 1079 |
+
"learning_rate": 3.623011908697394e-05,
|
| 1080 |
+
"loss": 2.5267,
|
| 1081 |
+
"step": 36000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 5.474452554744525,
|
| 1085 |
+
"eval_loss": 2.4367120265960693,
|
| 1086 |
+
"eval_runtime": 395.2579,
|
| 1087 |
+
"eval_samples_per_second": 1064.748,
|
| 1088 |
+
"eval_steps_per_second": 4.159,
|
| 1089 |
+
"step": 36000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 5.550486618004866,
|
| 1093 |
+
"grad_norm": 1.4852931499481201,
|
| 1094 |
+
"learning_rate": 3.5866336492488555e-05,
|
| 1095 |
+
"loss": 2.5165,
|
| 1096 |
+
"step": 36500
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 5.550486618004866,
|
| 1100 |
+
"eval_loss": 2.431751251220703,
|
| 1101 |
+
"eval_runtime": 395.2301,
|
| 1102 |
+
"eval_samples_per_second": 1064.823,
|
| 1103 |
+
"eval_steps_per_second": 4.16,
|
| 1104 |
+
"step": 36500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 5.626520681265207,
|
| 1108 |
+
"grad_norm": 1.603376865386963,
|
| 1109 |
+
"learning_rate": 3.5498957032536564e-05,
|
| 1110 |
+
"loss": 2.5194,
|
| 1111 |
+
"step": 37000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 5.626520681265207,
|
| 1115 |
+
"eval_loss": 2.4255075454711914,
|
| 1116 |
+
"eval_runtime": 395.4389,
|
| 1117 |
+
"eval_samples_per_second": 1064.26,
|
| 1118 |
+
"eval_steps_per_second": 4.157,
|
| 1119 |
+
"step": 37000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 5.702554744525547,
|
| 1123 |
+
"grad_norm": 1.6579174995422363,
|
| 1124 |
+
"learning_rate": 3.512880385328552e-05,
|
| 1125 |
+
"loss": 2.5063,
|
| 1126 |
+
"step": 37500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 5.702554744525547,
|
| 1130 |
+
"eval_loss": 2.4162917137145996,
|
| 1131 |
+
"eval_runtime": 395.2478,
|
| 1132 |
+
"eval_samples_per_second": 1064.775,
|
| 1133 |
+
"eval_steps_per_second": 4.159,
|
| 1134 |
+
"step": 37500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 5.778588807785888,
|
| 1138 |
+
"grad_norm": 1.6467429399490356,
|
| 1139 |
+
"learning_rate": 3.475597474549821e-05,
|
| 1140 |
+
"loss": 2.4969,
|
| 1141 |
+
"step": 38000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 5.778588807785888,
|
| 1145 |
+
"eval_loss": 2.4108052253723145,
|
| 1146 |
+
"eval_runtime": 395.1001,
|
| 1147 |
+
"eval_samples_per_second": 1065.173,
|
| 1148 |
+
"eval_steps_per_second": 4.161,
|
| 1149 |
+
"step": 38000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 5.854622871046229,
|
| 1153 |
+
"grad_norm": 1.6167348623275757,
|
| 1154 |
+
"learning_rate": 3.438056820689096e-05,
|
| 1155 |
+
"loss": 2.492,
|
| 1156 |
+
"step": 38500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 5.854622871046229,
|
| 1160 |
+
"eval_loss": 2.402526617050171,
|
| 1161 |
+
"eval_runtime": 395.2077,
|
| 1162 |
+
"eval_samples_per_second": 1064.883,
|
| 1163 |
+
"eval_steps_per_second": 4.16,
|
| 1164 |
+
"step": 38500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 5.930656934306569,
|
| 1168 |
+
"grad_norm": 1.7401496171951294,
|
| 1169 |
+
"learning_rate": 3.400344159273908e-05,
|
| 1170 |
+
"loss": 2.4729,
|
| 1171 |
+
"step": 39000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 5.930656934306569,
|
| 1175 |
+
"eval_loss": 2.3961234092712402,
|
| 1176 |
+
"eval_runtime": 395.2683,
|
| 1177 |
+
"eval_samples_per_second": 1064.72,
|
| 1178 |
+
"eval_steps_per_second": 4.159,
|
| 1179 |
+
"step": 39000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 6.00669099756691,
|
| 1183 |
+
"grad_norm": 1.7321972846984863,
|
| 1184 |
+
"learning_rate": 3.3623183039946427e-05,
|
| 1185 |
+
"loss": 2.4753,
|
| 1186 |
+
"step": 39500
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 6.00669099756691,
|
| 1190 |
+
"eval_loss": 2.390777826309204,
|
| 1191 |
+
"eval_runtime": 395.3927,
|
| 1192 |
+
"eval_samples_per_second": 1064.385,
|
| 1193 |
+
"eval_steps_per_second": 4.158,
|
| 1194 |
+
"step": 39500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 6.082725060827251,
|
| 1198 |
+
"grad_norm": 1.6455748081207275,
|
| 1199 |
+
"learning_rate": 3.3240646328557325e-05,
|
| 1200 |
+
"loss": 2.4653,
|
| 1201 |
+
"step": 40000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 6.082725060827251,
|
| 1205 |
+
"eval_loss": 2.385394334793091,
|
| 1206 |
+
"eval_runtime": 395.2314,
|
| 1207 |
+
"eval_samples_per_second": 1064.819,
|
| 1208 |
+
"eval_steps_per_second": 4.16,
|
| 1209 |
+
"step": 40000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 6.158759124087592,
|
| 1213 |
+
"grad_norm": 1.6246484518051147,
|
| 1214 |
+
"learning_rate": 3.2855932520939756e-05,
|
| 1215 |
+
"loss": 2.4552,
|
| 1216 |
+
"step": 40500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 6.158759124087592,
|
| 1220 |
+
"eval_loss": 2.3780696392059326,
|
| 1221 |
+
"eval_runtime": 395.2284,
|
| 1222 |
+
"eval_samples_per_second": 1064.827,
|
| 1223 |
+
"eval_steps_per_second": 4.16,
|
| 1224 |
+
"step": 40500
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 6.234793187347932,
|
| 1228 |
+
"grad_norm": 1.6907716989517212,
|
| 1229 |
+
"learning_rate": 3.246914325462873e-05,
|
| 1230 |
+
"loss": 2.4577,
|
| 1231 |
+
"step": 41000
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 6.234793187347932,
|
| 1235 |
+
"eval_loss": 2.3710057735443115,
|
| 1236 |
+
"eval_runtime": 395.2817,
|
| 1237 |
+
"eval_samples_per_second": 1064.684,
|
| 1238 |
+
"eval_steps_per_second": 4.159,
|
| 1239 |
+
"step": 41000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 6.3108272506082725,
|
| 1243 |
+
"grad_norm": 1.733163595199585,
|
| 1244 |
+
"learning_rate": 3.208038071547463e-05,
|
| 1245 |
+
"loss": 2.4512,
|
| 1246 |
+
"step": 41500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 6.3108272506082725,
|
| 1250 |
+
"eval_loss": 2.364978313446045,
|
| 1251 |
+
"eval_runtime": 395.0989,
|
| 1252 |
+
"eval_samples_per_second": 1065.176,
|
| 1253 |
+
"eval_steps_per_second": 4.161,
|
| 1254 |
+
"step": 41500
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 6.386861313868613,
|
| 1258 |
+
"grad_norm": 1.604212999343872,
|
| 1259 |
+
"learning_rate": 3.1690530675165916e-05,
|
| 1260 |
+
"loss": 2.4419,
|
| 1261 |
+
"step": 42000
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 6.386861313868613,
|
| 1265 |
+
"eval_loss": 2.3593010902404785,
|
| 1266 |
+
"eval_runtime": 394.8589,
|
| 1267 |
+
"eval_samples_per_second": 1065.824,
|
| 1268 |
+
"eval_steps_per_second": 4.164,
|
| 1269 |
+
"step": 42000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 6.4628953771289535,
|
| 1273 |
+
"grad_norm": 1.799272060394287,
|
| 1274 |
+
"learning_rate": 3.1298133637437146e-05,
|
| 1275 |
+
"loss": 2.443,
|
| 1276 |
+
"step": 42500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 6.4628953771289535,
|
| 1280 |
+
"eval_loss": 2.3553106784820557,
|
| 1281 |
+
"eval_runtime": 395.5826,
|
| 1282 |
+
"eval_samples_per_second": 1063.874,
|
| 1283 |
+
"eval_steps_per_second": 4.156,
|
| 1284 |
+
"step": 42500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 6.538929440389294,
|
| 1288 |
+
"grad_norm": 1.5894908905029297,
|
| 1289 |
+
"learning_rate": 3.0904072695878296e-05,
|
| 1290 |
+
"loss": 2.4291,
|
| 1291 |
+
"step": 43000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 6.538929440389294,
|
| 1295 |
+
"eval_loss": 2.350308656692505,
|
| 1296 |
+
"eval_runtime": 395.6156,
|
| 1297 |
+
"eval_samples_per_second": 1063.785,
|
| 1298 |
+
"eval_steps_per_second": 4.156,
|
| 1299 |
+
"step": 43000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 6.614963503649635,
|
| 1303 |
+
"grad_norm": 1.6308026313781738,
|
| 1304 |
+
"learning_rate": 3.050845195744353e-05,
|
| 1305 |
+
"loss": 2.4212,
|
| 1306 |
+
"step": 43500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 6.614963503649635,
|
| 1310 |
+
"eval_loss": 2.3425817489624023,
|
| 1311 |
+
"eval_runtime": 395.5628,
|
| 1312 |
+
"eval_samples_per_second": 1063.927,
|
| 1313 |
+
"eval_steps_per_second": 4.156,
|
| 1314 |
+
"step": 43500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 6.690997566909976,
|
| 1318 |
+
"grad_norm": 1.5576202869415283,
|
| 1319 |
+
"learning_rate": 3.011137594116975e-05,
|
| 1320 |
+
"loss": 2.4217,
|
| 1321 |
+
"step": 44000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 6.690997566909976,
|
| 1325 |
+
"eval_loss": 2.3366506099700928,
|
| 1326 |
+
"eval_runtime": 395.6852,
|
| 1327 |
+
"eval_samples_per_second": 1063.598,
|
| 1328 |
+
"eval_steps_per_second": 4.155,
|
| 1329 |
+
"step": 44000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 6.767031630170316,
|
| 1333 |
+
"grad_norm": 1.698960542678833,
|
| 1334 |
+
"learning_rate": 2.9713747681111948e-05,
|
| 1335 |
+
"loss": 2.4191,
|
| 1336 |
+
"step": 44500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 6.767031630170316,
|
| 1340 |
+
"eval_loss": 2.3311471939086914,
|
| 1341 |
+
"eval_runtime": 395.6553,
|
| 1342 |
+
"eval_samples_per_second": 1063.678,
|
| 1343 |
+
"eval_steps_per_second": 4.155,
|
| 1344 |
+
"step": 44500
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 6.843065693430657,
|
| 1348 |
+
"grad_norm": 1.700810194015503,
|
| 1349 |
+
"learning_rate": 2.931407856139074e-05,
|
| 1350 |
+
"loss": 2.4101,
|
| 1351 |
+
"step": 45000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 6.843065693430657,
|
| 1355 |
+
"eval_loss": 2.326604127883911,
|
| 1356 |
+
"eval_runtime": 395.4811,
|
| 1357 |
+
"eval_samples_per_second": 1064.147,
|
| 1358 |
+
"eval_steps_per_second": 4.157,
|
| 1359 |
+
"step": 45000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 6.919099756690997,
|
| 1363 |
+
"grad_norm": 1.675718069076538,
|
| 1364 |
+
"learning_rate": 2.8913269705319878e-05,
|
| 1365 |
+
"loss": 2.4092,
|
| 1366 |
+
"step": 45500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 6.919099756690997,
|
| 1370 |
+
"eval_loss": 2.3215043544769287,
|
| 1371 |
+
"eval_runtime": 395.6152,
|
| 1372 |
+
"eval_samples_per_second": 1063.786,
|
| 1373 |
+
"eval_steps_per_second": 4.156,
|
| 1374 |
+
"step": 45500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 6.995133819951338,
|
| 1378 |
+
"grad_norm": 1.7430431842803955,
|
| 1379 |
+
"learning_rate": 2.851142700258497e-05,
|
| 1380 |
+
"loss": 2.4028,
|
| 1381 |
+
"step": 46000
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 6.995133819951338,
|
| 1385 |
+
"eval_loss": 2.3190836906433105,
|
| 1386 |
+
"eval_runtime": 395.7789,
|
| 1387 |
+
"eval_samples_per_second": 1063.346,
|
| 1388 |
+
"eval_steps_per_second": 4.154,
|
| 1389 |
+
"step": 46000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 7.071167883211679,
|
| 1393 |
+
"grad_norm": 1.7376880645751953,
|
| 1394 |
+
"learning_rate": 2.8108656616003542e-05,
|
| 1395 |
+
"loss": 2.393,
|
| 1396 |
+
"step": 46500
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 7.071167883211679,
|
| 1400 |
+
"eval_loss": 2.314730167388916,
|
| 1401 |
+
"eval_runtime": 395.8715,
|
| 1402 |
+
"eval_samples_per_second": 1063.097,
|
| 1403 |
+
"eval_steps_per_second": 4.153,
|
| 1404 |
+
"step": 46500
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 7.14720194647202,
|
| 1408 |
+
"grad_norm": 1.647200584411621,
|
| 1409 |
+
"learning_rate": 2.7705064953477926e-05,
|
| 1410 |
+
"loss": 2.3864,
|
| 1411 |
+
"step": 47000
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 7.14720194647202,
|
| 1415 |
+
"eval_loss": 2.3095407485961914,
|
| 1416 |
+
"eval_runtime": 392.0209,
|
| 1417 |
+
"eval_samples_per_second": 1073.54,
|
| 1418 |
+
"eval_steps_per_second": 4.194,
|
| 1419 |
+
"step": 47000
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 7.22323600973236,
|
| 1423 |
+
"grad_norm": 1.5628902912139893,
|
| 1424 |
+
"learning_rate": 2.7300758639883305e-05,
|
| 1425 |
+
"loss": 2.3853,
|
| 1426 |
+
"step": 47500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 7.22323600973236,
|
| 1430 |
+
"eval_loss": 2.3034095764160156,
|
| 1431 |
+
"eval_runtime": 392.407,
|
| 1432 |
+
"eval_samples_per_second": 1072.483,
|
| 1433 |
+
"eval_steps_per_second": 4.19,
|
| 1434 |
+
"step": 47500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 7.299270072992701,
|
| 1438 |
+
"grad_norm": 1.6254950761795044,
|
| 1439 |
+
"learning_rate": 2.6896654852743762e-05,
|
| 1440 |
+
"loss": 2.3778,
|
| 1441 |
+
"step": 48000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 7.299270072992701,
|
| 1445 |
+
"eval_loss": 2.3009138107299805,
|
| 1446 |
+
"eval_runtime": 392.2743,
|
| 1447 |
+
"eval_samples_per_second": 1072.846,
|
| 1448 |
+
"eval_steps_per_second": 4.191,
|
| 1449 |
+
"step": 48000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 7.375304136253042,
|
| 1453 |
+
"grad_norm": 1.7831765413284302,
|
| 1454 |
+
"learning_rate": 2.6491240733505536e-05,
|
| 1455 |
+
"loss": 2.3902,
|
| 1456 |
+
"step": 48500
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 7.375304136253042,
|
| 1460 |
+
"eval_loss": 2.2940807342529297,
|
| 1461 |
+
"eval_runtime": 392.0933,
|
| 1462 |
+
"eval_samples_per_second": 1073.342,
|
| 1463 |
+
"eval_steps_per_second": 4.193,
|
| 1464 |
+
"step": 48500
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 7.451338199513382,
|
| 1468 |
+
"grad_norm": 1.7135417461395264,
|
| 1469 |
+
"learning_rate": 2.608543264340055e-05,
|
| 1470 |
+
"loss": 2.3734,
|
| 1471 |
+
"step": 49000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 7.451338199513382,
|
| 1475 |
+
"eval_loss": 2.2903780937194824,
|
| 1476 |
+
"eval_runtime": 392.3395,
|
| 1477 |
+
"eval_samples_per_second": 1072.668,
|
| 1478 |
+
"eval_steps_per_second": 4.19,
|
| 1479 |
+
"step": 49000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 7.5273722627737225,
|
| 1483 |
+
"grad_norm": 1.7215466499328613,
|
| 1484 |
+
"learning_rate": 2.5679337792861973e-05,
|
| 1485 |
+
"loss": 2.3644,
|
| 1486 |
+
"step": 49500
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 7.5273722627737225,
|
| 1490 |
+
"eval_loss": 2.2882533073425293,
|
| 1491 |
+
"eval_runtime": 391.7386,
|
| 1492 |
+
"eval_samples_per_second": 1074.313,
|
| 1493 |
+
"eval_steps_per_second": 4.197,
|
| 1494 |
+
"step": 49500
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 7.603406326034063,
|
| 1498 |
+
"grad_norm": 1.5934220552444458,
|
| 1499 |
+
"learning_rate": 2.527306346808222e-05,
|
| 1500 |
+
"loss": 2.3644,
|
| 1501 |
+
"step": 50000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 7.603406326034063,
|
| 1505 |
+
"eval_loss": 2.278449296951294,
|
| 1506 |
+
"eval_runtime": 392.029,
|
| 1507 |
+
"eval_samples_per_second": 1073.517,
|
| 1508 |
+
"eval_steps_per_second": 4.194,
|
| 1509 |
+
"step": 50000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 7.679440389294404,
|
| 1513 |
+
"grad_norm": 1.734836459159851,
|
| 1514 |
+
"learning_rate": 2.4866717002668977e-05,
|
| 1515 |
+
"loss": 2.3643,
|
| 1516 |
+
"step": 50500
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 7.679440389294404,
|
| 1520 |
+
"eval_loss": 2.2776286602020264,
|
| 1521 |
+
"eval_runtime": 391.9926,
|
| 1522 |
+
"eval_samples_per_second": 1073.617,
|
| 1523 |
+
"eval_steps_per_second": 4.194,
|
| 1524 |
+
"step": 50500
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 7.755474452554744,
|
| 1528 |
+
"grad_norm": 1.6759928464889526,
|
| 1529 |
+
"learning_rate": 2.4461218265301844e-05,
|
| 1530 |
+
"loss": 2.3549,
|
| 1531 |
+
"step": 51000
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 7.755474452554744,
|
| 1535 |
+
"eval_loss": 2.275527000427246,
|
| 1536 |
+
"eval_runtime": 392.0053,
|
| 1537 |
+
"eval_samples_per_second": 1073.582,
|
| 1538 |
+
"eval_steps_per_second": 4.194,
|
| 1539 |
+
"step": 51000
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 7.831508515815085,
|
| 1543 |
+
"grad_norm": 1.6229385137557983,
|
| 1544 |
+
"learning_rate": 2.4055049175099393e-05,
|
| 1545 |
+
"loss": 2.3475,
|
| 1546 |
+
"step": 51500
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 7.831508515815085,
|
| 1550 |
+
"eval_loss": 2.269463539123535,
|
| 1551 |
+
"eval_runtime": 392.7325,
|
| 1552 |
+
"eval_samples_per_second": 1071.594,
|
| 1553 |
+
"eval_steps_per_second": 4.186,
|
| 1554 |
+
"step": 51500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 7.907542579075426,
|
| 1558 |
+
"grad_norm": 1.5919690132141113,
|
| 1559 |
+
"learning_rate": 2.3649129731441017e-05,
|
| 1560 |
+
"loss": 2.3556,
|
| 1561 |
+
"step": 52000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 7.907542579075426,
|
| 1565 |
+
"eval_loss": 2.2632956504821777,
|
| 1566 |
+
"eval_runtime": 392.8483,
|
| 1567 |
+
"eval_samples_per_second": 1071.279,
|
| 1568 |
+
"eval_steps_per_second": 4.185,
|
| 1569 |
+
"step": 52000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 7.983576642335766,
|
| 1573 |
+
"grad_norm": 1.6283611059188843,
|
| 1574 |
+
"learning_rate": 2.32435671741784e-05,
|
| 1575 |
+
"loss": 2.3441,
|
| 1576 |
+
"step": 52500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 7.983576642335766,
|
| 1580 |
+
"eval_loss": 2.2631113529205322,
|
| 1581 |
+
"eval_runtime": 393.1076,
|
| 1582 |
+
"eval_samples_per_second": 1070.572,
|
| 1583 |
+
"eval_steps_per_second": 4.182,
|
| 1584 |
+
"step": 52500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 8.059610705596107,
|
| 1588 |
+
"grad_norm": 1.6927645206451416,
|
| 1589 |
+
"learning_rate": 2.2838468648877376e-05,
|
| 1590 |
+
"loss": 2.3396,
|
| 1591 |
+
"step": 53000
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 8.059610705596107,
|
| 1595 |
+
"eval_loss": 2.2605204582214355,
|
| 1596 |
+
"eval_runtime": 393.0545,
|
| 1597 |
+
"eval_samples_per_second": 1070.717,
|
| 1598 |
+
"eval_steps_per_second": 4.183,
|
| 1599 |
+
"step": 53000
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 8.135644768856448,
|
| 1603 |
+
"grad_norm": 1.6524484157562256,
|
| 1604 |
+
"learning_rate": 2.2433941178511185e-05,
|
| 1605 |
+
"loss": 2.3281,
|
| 1606 |
+
"step": 53500
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 8.135644768856448,
|
| 1610 |
+
"eval_loss": 2.255591869354248,
|
| 1611 |
+
"eval_runtime": 393.065,
|
| 1612 |
+
"eval_samples_per_second": 1070.688,
|
| 1613 |
+
"eval_steps_per_second": 4.183,
|
| 1614 |
+
"step": 53500
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 8.211678832116789,
|
| 1618 |
+
"grad_norm": 1.8136180639266968,
|
| 1619 |
+
"learning_rate": 2.2030091635186097e-05,
|
| 1620 |
+
"loss": 2.3251,
|
| 1621 |
+
"step": 54000
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 8.211678832116789,
|
| 1625 |
+
"eval_loss": 2.2528815269470215,
|
| 1626 |
+
"eval_runtime": 393.1403,
|
| 1627 |
+
"eval_samples_per_second": 1070.483,
|
| 1628 |
+
"eval_steps_per_second": 4.182,
|
| 1629 |
+
"step": 54000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 8.28771289537713,
|
| 1633 |
+
"grad_norm": 1.7461555004119873,
|
| 1634 |
+
"learning_rate": 2.1627831987887616e-05,
|
| 1635 |
+
"loss": 2.3252,
|
| 1636 |
+
"step": 54500
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 8.28771289537713,
|
| 1640 |
+
"eval_loss": 2.247727155685425,
|
| 1641 |
+
"eval_runtime": 394.607,
|
| 1642 |
+
"eval_samples_per_second": 1066.504,
|
| 1643 |
+
"eval_steps_per_second": 4.166,
|
| 1644 |
+
"step": 54500
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 8.363746958637469,
|
| 1648 |
+
"grad_norm": 1.6148008108139038,
|
| 1649 |
+
"learning_rate": 2.1225656282037674e-05,
|
| 1650 |
+
"loss": 2.3231,
|
| 1651 |
+
"step": 55000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 8.363746958637469,
|
| 1655 |
+
"eval_loss": 2.245650291442871,
|
| 1656 |
+
"eval_runtime": 393.1496,
|
| 1657 |
+
"eval_samples_per_second": 1070.458,
|
| 1658 |
+
"eval_steps_per_second": 4.182,
|
| 1659 |
+
"step": 55000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 8.43978102189781,
|
| 1663 |
+
"grad_norm": 1.5390928983688354,
|
| 1664 |
+
"learning_rate": 2.082447771999728e-05,
|
| 1665 |
+
"loss": 2.3218,
|
| 1666 |
+
"step": 55500
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 8.43978102189781,
|
| 1670 |
+
"eval_loss": 2.240283489227295,
|
| 1671 |
+
"eval_runtime": 393.128,
|
| 1672 |
+
"eval_samples_per_second": 1070.517,
|
| 1673 |
+
"eval_steps_per_second": 4.182,
|
| 1674 |
+
"step": 55500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 8.51581508515815,
|
| 1678 |
+
"grad_norm": 1.7353328466415405,
|
| 1679 |
+
"learning_rate": 2.0424402289124667e-05,
|
| 1680 |
+
"loss": 2.3113,
|
| 1681 |
+
"step": 56000
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 8.51581508515815,
|
| 1685 |
+
"eval_loss": 2.236283540725708,
|
| 1686 |
+
"eval_runtime": 392.9933,
|
| 1687 |
+
"eval_samples_per_second": 1070.883,
|
| 1688 |
+
"eval_steps_per_second": 4.183,
|
| 1689 |
+
"step": 56000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 8.591849148418492,
|
| 1693 |
+
"grad_norm": 1.6553759574890137,
|
| 1694 |
+
"learning_rate": 2.0025535685341834e-05,
|
| 1695 |
+
"loss": 2.3137,
|
| 1696 |
+
"step": 56500
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 8.591849148418492,
|
| 1700 |
+
"eval_loss": 2.2341954708099365,
|
| 1701 |
+
"eval_runtime": 394.1952,
|
| 1702 |
+
"eval_samples_per_second": 1067.618,
|
| 1703 |
+
"eval_steps_per_second": 4.171,
|
| 1704 |
+
"step": 56500
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 8.667883211678832,
|
| 1708 |
+
"grad_norm": 1.6300148963928223,
|
| 1709 |
+
"learning_rate": 1.9627983285210795e-05,
|
| 1710 |
+
"loss": 2.3153,
|
| 1711 |
+
"step": 57000
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 8.667883211678832,
|
| 1715 |
+
"eval_loss": 2.2316806316375732,
|
| 1716 |
+
"eval_runtime": 394.4429,
|
| 1717 |
+
"eval_samples_per_second": 1066.948,
|
| 1718 |
+
"eval_steps_per_second": 4.168,
|
| 1719 |
+
"step": 57000
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 8.743917274939173,
|
| 1723 |
+
"grad_norm": 1.7760825157165527,
|
| 1724 |
+
"learning_rate": 1.9231850118094083e-05,
|
| 1725 |
+
"loss": 2.3086,
|
| 1726 |
+
"step": 57500
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 8.743917274939173,
|
| 1730 |
+
"eval_loss": 2.2260444164276123,
|
| 1731 |
+
"eval_runtime": 394.1825,
|
| 1732 |
+
"eval_samples_per_second": 1067.653,
|
| 1733 |
+
"eval_steps_per_second": 4.171,
|
| 1734 |
+
"step": 57500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 8.819951338199512,
|
| 1738 |
+
"grad_norm": 1.6700938940048218,
|
| 1739 |
+
"learning_rate": 1.883724083840713e-05,
|
| 1740 |
+
"loss": 2.3051,
|
| 1741 |
+
"step": 58000
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 8.819951338199512,
|
| 1745 |
+
"eval_loss": 2.2262229919433594,
|
| 1746 |
+
"eval_runtime": 394.2521,
|
| 1747 |
+
"eval_samples_per_second": 1067.464,
|
| 1748 |
+
"eval_steps_per_second": 4.17,
|
| 1749 |
+
"step": 58000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 8.895985401459853,
|
| 1753 |
+
"grad_norm": 1.6361171007156372,
|
| 1754 |
+
"learning_rate": 1.8445043966286124e-05,
|
| 1755 |
+
"loss": 2.2996,
|
| 1756 |
+
"step": 58500
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 8.895985401459853,
|
| 1760 |
+
"eval_loss": 2.2197461128234863,
|
| 1761 |
+
"eval_runtime": 394.2947,
|
| 1762 |
+
"eval_samples_per_second": 1067.349,
|
| 1763 |
+
"eval_steps_per_second": 4.169,
|
| 1764 |
+
"step": 58500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 8.972019464720194,
|
| 1768 |
+
"grad_norm": 1.5987651348114014,
|
| 1769 |
+
"learning_rate": 1.805379121954309e-05,
|
| 1770 |
+
"loss": 2.295,
|
| 1771 |
+
"step": 59000
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 8.972019464720194,
|
| 1775 |
+
"eval_loss": 2.218661069869995,
|
| 1776 |
+
"eval_runtime": 394.4471,
|
| 1777 |
+
"eval_samples_per_second": 1066.936,
|
| 1778 |
+
"eval_steps_per_second": 4.168,
|
| 1779 |
+
"step": 59000
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 9.048053527980535,
|
| 1783 |
+
"grad_norm": 1.6805070638656616,
|
| 1784 |
+
"learning_rate": 1.7664373591592323e-05,
|
| 1785 |
+
"loss": 2.2898,
|
| 1786 |
+
"step": 59500
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 9.048053527980535,
|
| 1790 |
+
"eval_loss": 2.2158923149108887,
|
| 1791 |
+
"eval_runtime": 394.3964,
|
| 1792 |
+
"eval_samples_per_second": 1067.074,
|
| 1793 |
+
"eval_steps_per_second": 4.168,
|
| 1794 |
+
"step": 59500
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 9.124087591240876,
|
| 1798 |
+
"grad_norm": 1.559171199798584,
|
| 1799 |
+
"learning_rate": 1.727689396267106e-05,
|
| 1800 |
+
"loss": 2.294,
|
| 1801 |
+
"step": 60000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 9.124087591240876,
|
| 1805 |
+
"eval_loss": 2.213304281234741,
|
| 1806 |
+
"eval_runtime": 394.3761,
|
| 1807 |
+
"eval_samples_per_second": 1067.129,
|
| 1808 |
+
"eval_steps_per_second": 4.169,
|
| 1809 |
+
"step": 60000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 9.200121654501217,
|
| 1813 |
+
"grad_norm": 1.7154414653778076,
|
| 1814 |
+
"learning_rate": 1.689145470101657e-05,
|
| 1815 |
+
"loss": 2.2905,
|
| 1816 |
+
"step": 60500
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 9.200121654501217,
|
| 1820 |
+
"eval_loss": 2.211729049682617,
|
| 1821 |
+
"eval_runtime": 394.4483,
|
| 1822 |
+
"eval_samples_per_second": 1066.933,
|
| 1823 |
+
"eval_steps_per_second": 4.168,
|
| 1824 |
+
"step": 60500
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 9.276155717761558,
|
| 1828 |
+
"grad_norm": 1.7217854261398315,
|
| 1829 |
+
"learning_rate": 1.6508922024636513e-05,
|
| 1830 |
+
"loss": 2.2776,
|
| 1831 |
+
"step": 61000
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 9.276155717761558,
|
| 1835 |
+
"eval_loss": 2.2076163291931152,
|
| 1836 |
+
"eval_runtime": 394.2479,
|
| 1837 |
+
"eval_samples_per_second": 1067.476,
|
| 1838 |
+
"eval_steps_per_second": 4.17,
|
| 1839 |
+
"step": 61000
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 9.352189781021897,
|
| 1843 |
+
"grad_norm": 1.6988067626953125,
|
| 1844 |
+
"learning_rate": 1.6127863831556155e-05,
|
| 1845 |
+
"loss": 2.2888,
|
| 1846 |
+
"step": 61500
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 9.352189781021897,
|
| 1850 |
+
"eval_loss": 2.2073538303375244,
|
| 1851 |
+
"eval_runtime": 394.4185,
|
| 1852 |
+
"eval_samples_per_second": 1067.014,
|
| 1853 |
+
"eval_steps_per_second": 4.168,
|
| 1854 |
+
"step": 61500
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 9.428223844282238,
|
| 1858 |
+
"grad_norm": 1.6594995260238647,
|
| 1859 |
+
"learning_rate": 1.5749149567995482e-05,
|
| 1860 |
+
"loss": 2.2737,
|
| 1861 |
+
"step": 62000
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 9.428223844282238,
|
| 1865 |
+
"eval_loss": 2.2045233249664307,
|
| 1866 |
+
"eval_runtime": 394.3688,
|
| 1867 |
+
"eval_samples_per_second": 1067.148,
|
| 1868 |
+
"eval_steps_per_second": 4.169,
|
| 1869 |
+
"step": 62000
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 9.504257907542579,
|
| 1873 |
+
"grad_norm": 1.782347321510315,
|
| 1874 |
+
"learning_rate": 1.537287928647002e-05,
|
| 1875 |
+
"loss": 2.2715,
|
| 1876 |
+
"step": 62500
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 9.504257907542579,
|
| 1880 |
+
"eval_loss": 2.1984219551086426,
|
| 1881 |
+
"eval_runtime": 394.2219,
|
| 1882 |
+
"eval_samples_per_second": 1067.546,
|
| 1883 |
+
"eval_steps_per_second": 4.17,
|
| 1884 |
+
"step": 62500
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 9.58029197080292,
|
| 1888 |
+
"grad_norm": 1.7212417125701904,
|
| 1889 |
+
"learning_rate": 1.4999897243562522e-05,
|
| 1890 |
+
"loss": 2.2736,
|
| 1891 |
+
"step": 63000
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 9.58029197080292,
|
| 1895 |
+
"eval_loss": 2.200115919113159,
|
| 1896 |
+
"eval_runtime": 394.4095,
|
| 1897 |
+
"eval_samples_per_second": 1067.038,
|
| 1898 |
+
"eval_steps_per_second": 4.168,
|
| 1899 |
+
"step": 63000
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 9.65632603406326,
|
| 1903 |
+
"grad_norm": 1.636083722114563,
|
| 1904 |
+
"learning_rate": 1.4628807092364161e-05,
|
| 1905 |
+
"loss": 2.2714,
|
| 1906 |
+
"step": 63500
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 9.65632603406326,
|
| 1910 |
+
"eval_loss": 2.196516752243042,
|
| 1911 |
+
"eval_runtime": 394.3398,
|
| 1912 |
+
"eval_samples_per_second": 1067.227,
|
| 1913 |
+
"eval_steps_per_second": 4.169,
|
| 1914 |
+
"step": 63500
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 9.732360097323602,
|
| 1918 |
+
"grad_norm": 1.669154405593872,
|
| 1919 |
+
"learning_rate": 1.4260456906462644e-05,
|
| 1920 |
+
"loss": 2.2581,
|
| 1921 |
+
"step": 64000
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 9.732360097323602,
|
| 1925 |
+
"eval_loss": 2.1947672367095947,
|
| 1926 |
+
"eval_runtime": 394.2775,
|
| 1927 |
+
"eval_samples_per_second": 1067.396,
|
| 1928 |
+
"eval_steps_per_second": 4.17,
|
| 1929 |
+
"step": 64000
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 9.808394160583942,
|
| 1933 |
+
"grad_norm": 1.5820955038070679,
|
| 1934 |
+
"learning_rate": 1.3894944000287996e-05,
|
| 1935 |
+
"loss": 2.2673,
|
| 1936 |
+
"step": 64500
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 9.808394160583942,
|
| 1940 |
+
"eval_loss": 2.1930572986602783,
|
| 1941 |
+
"eval_runtime": 394.3185,
|
| 1942 |
+
"eval_samples_per_second": 1067.284,
|
| 1943 |
+
"eval_steps_per_second": 4.169,
|
| 1944 |
+
"step": 64500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 9.884428223844282,
|
| 1948 |
+
"grad_norm": 1.878128170967102,
|
| 1949 |
+
"learning_rate": 1.3532364938689365e-05,
|
| 1950 |
+
"loss": 2.2532,
|
| 1951 |
+
"step": 65000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 9.884428223844282,
|
| 1955 |
+
"eval_loss": 2.186814069747925,
|
| 1956 |
+
"eval_runtime": 394.1633,
|
| 1957 |
+
"eval_samples_per_second": 1067.705,
|
| 1958 |
+
"eval_steps_per_second": 4.171,
|
| 1959 |
+
"step": 65000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 9.960462287104622,
|
| 1963 |
+
"grad_norm": 1.6541669368743896,
|
| 1964 |
+
"learning_rate": 1.3172815511423497e-05,
|
| 1965 |
+
"loss": 2.2599,
|
| 1966 |
+
"step": 65500
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 9.960462287104622,
|
| 1970 |
+
"eval_loss": 2.186183452606201,
|
| 1971 |
+
"eval_runtime": 394.274,
|
| 1972 |
+
"eval_samples_per_second": 1067.405,
|
| 1973 |
+
"eval_steps_per_second": 4.17,
|
| 1974 |
+
"step": 65500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 10.036496350364963,
|
| 1978 |
+
"grad_norm": 1.6656322479248047,
|
| 1979 |
+
"learning_rate": 1.2817100376353228e-05,
|
| 1980 |
+
"loss": 2.2626,
|
| 1981 |
+
"step": 66000
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 10.036496350364963,
|
| 1985 |
+
"eval_loss": 2.1833560466766357,
|
| 1986 |
+
"eval_runtime": 394.4838,
|
| 1987 |
+
"eval_samples_per_second": 1066.837,
|
| 1988 |
+
"eval_steps_per_second": 4.167,
|
| 1989 |
+
"step": 66000
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 10.112530413625304,
|
| 1993 |
+
"grad_norm": 1.64789617061615,
|
| 1994 |
+
"learning_rate": 1.246388782934231e-05,
|
| 1995 |
+
"loss": 2.2476,
|
| 1996 |
+
"step": 66500
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 10.112530413625304,
|
| 2000 |
+
"eval_loss": 2.1836633682250977,
|
| 2001 |
+
"eval_runtime": 394.475,
|
| 2002 |
+
"eval_samples_per_second": 1066.861,
|
| 2003 |
+
"eval_steps_per_second": 4.168,
|
| 2004 |
+
"step": 66500
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 10.188564476885645,
|
| 2008 |
+
"grad_norm": 1.626693844795227,
|
| 2009 |
+
"learning_rate": 1.2113987197615472e-05,
|
| 2010 |
+
"loss": 2.2597,
|
| 2011 |
+
"step": 67000
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 10.188564476885645,
|
| 2015 |
+
"eval_loss": 2.177664041519165,
|
| 2016 |
+
"eval_runtime": 394.4402,
|
| 2017 |
+
"eval_samples_per_second": 1066.955,
|
| 2018 |
+
"eval_steps_per_second": 4.168,
|
| 2019 |
+
"step": 67000
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 10.264598540145986,
|
| 2023 |
+
"grad_norm": 1.660078525543213,
|
| 2024 |
+
"learning_rate": 1.1767490921415291e-05,
|
| 2025 |
+
"loss": 2.2525,
|
| 2026 |
+
"step": 67500
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 10.264598540145986,
|
| 2030 |
+
"eval_loss": 2.177150011062622,
|
| 2031 |
+
"eval_runtime": 394.2691,
|
| 2032 |
+
"eval_samples_per_second": 1067.418,
|
| 2033 |
+
"eval_steps_per_second": 4.17,
|
| 2034 |
+
"step": 67500
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 10.340632603406325,
|
| 2038 |
+
"grad_norm": 1.6624382734298706,
|
| 2039 |
+
"learning_rate": 1.1424490541587752e-05,
|
| 2040 |
+
"loss": 2.2477,
|
| 2041 |
+
"step": 68000
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 10.340632603406325,
|
| 2045 |
+
"eval_loss": 2.175464630126953,
|
| 2046 |
+
"eval_runtime": 394.3358,
|
| 2047 |
+
"eval_samples_per_second": 1067.238,
|
| 2048 |
+
"eval_steps_per_second": 4.169,
|
| 2049 |
+
"step": 68000
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 10.416666666666666,
|
| 2053 |
+
"grad_norm": 1.7029284238815308,
|
| 2054 |
+
"learning_rate": 1.1085076675397963e-05,
|
| 2055 |
+
"loss": 2.2442,
|
| 2056 |
+
"step": 68500
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 10.416666666666666,
|
| 2060 |
+
"eval_loss": 2.172318935394287,
|
| 2061 |
+
"eval_runtime": 394.363,
|
| 2062 |
+
"eval_samples_per_second": 1067.164,
|
| 2063 |
+
"eval_steps_per_second": 4.169,
|
| 2064 |
+
"step": 68500
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 10.492700729927007,
|
| 2068 |
+
"grad_norm": 1.7094260454177856,
|
| 2069 |
+
"learning_rate": 1.0750006740005564e-05,
|
| 2070 |
+
"loss": 2.2461,
|
| 2071 |
+
"step": 69000
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 10.492700729927007,
|
| 2075 |
+
"eval_loss": 2.1725075244903564,
|
| 2076 |
+
"eval_runtime": 394.3359,
|
| 2077 |
+
"eval_samples_per_second": 1067.237,
|
| 2078 |
+
"eval_steps_per_second": 4.169,
|
| 2079 |
+
"step": 69000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 10.568734793187348,
|
| 2083 |
+
"grad_norm": 1.7138928174972534,
|
| 2084 |
+
"learning_rate": 1.04180263214852e-05,
|
| 2085 |
+
"loss": 2.2428,
|
| 2086 |
+
"step": 69500
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 10.568734793187348,
|
| 2090 |
+
"eval_loss": 2.1679632663726807,
|
| 2091 |
+
"eval_runtime": 394.3498,
|
| 2092 |
+
"eval_samples_per_second": 1067.2,
|
| 2093 |
+
"eval_steps_per_second": 4.169,
|
| 2094 |
+
"step": 69500
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 10.644768856447689,
|
| 2098 |
+
"grad_norm": 1.7748503684997559,
|
| 2099 |
+
"learning_rate": 1.0089898314369628e-05,
|
| 2100 |
+
"loss": 2.2409,
|
| 2101 |
+
"step": 70000
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 10.644768856447689,
|
| 2105 |
+
"eval_loss": 2.167714834213257,
|
| 2106 |
+
"eval_runtime": 394.3096,
|
| 2107 |
+
"eval_samples_per_second": 1067.308,
|
| 2108 |
+
"eval_steps_per_second": 4.169,
|
| 2109 |
+
"step": 70000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 10.72080291970803,
|
| 2113 |
+
"grad_norm": 1.8225022554397583,
|
| 2114 |
+
"learning_rate": 9.765709406792067e-06,
|
| 2115 |
+
"loss": 2.2421,
|
| 2116 |
+
"step": 70500
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 10.72080291970803,
|
| 2120 |
+
"eval_loss": 2.1677842140197754,
|
| 2121 |
+
"eval_runtime": 394.4354,
|
| 2122 |
+
"eval_samples_per_second": 1066.968,
|
| 2123 |
+
"eval_steps_per_second": 4.168,
|
| 2124 |
+
"step": 70500
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 10.79683698296837,
|
| 2128 |
+
"grad_norm": 1.682428002357483,
|
| 2129 |
+
"learning_rate": 9.445545246215093e-06,
|
| 2130 |
+
"loss": 2.2405,
|
| 2131 |
+
"step": 71000
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 10.79683698296837,
|
| 2135 |
+
"eval_loss": 2.162020206451416,
|
| 2136 |
+
"eval_runtime": 394.4337,
|
| 2137 |
+
"eval_samples_per_second": 1066.973,
|
| 2138 |
+
"eval_steps_per_second": 4.168,
|
| 2139 |
+
"step": 71000
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 10.87287104622871,
|
| 2143 |
+
"grad_norm": 1.8187251091003418,
|
| 2144 |
+
"learning_rate": 9.130118369667984e-06,
|
| 2145 |
+
"loss": 2.2338,
|
| 2146 |
+
"step": 71500
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 10.87287104622871,
|
| 2150 |
+
"eval_loss": 2.161623001098633,
|
| 2151 |
+
"eval_runtime": 394.3265,
|
| 2152 |
+
"eval_samples_per_second": 1067.263,
|
| 2153 |
+
"eval_steps_per_second": 4.169,
|
| 2154 |
+
"step": 71500
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 10.94890510948905,
|
| 2158 |
+
"grad_norm": 1.586653470993042,
|
| 2159 |
+
"learning_rate": 8.818247901683923e-06,
|
| 2160 |
+
"loss": 2.2291,
|
| 2161 |
+
"step": 72000
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 10.94890510948905,
|
| 2165 |
+
"eval_loss": 2.1573026180267334,
|
| 2166 |
+
"eval_runtime": 394.3904,
|
| 2167 |
+
"eval_samples_per_second": 1067.09,
|
| 2168 |
+
"eval_steps_per_second": 4.168,
|
| 2169 |
+
"step": 72000
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 11.024939172749392,
|
| 2173 |
+
"grad_norm": 1.6375211477279663,
|
| 2174 |
+
"learning_rate": 8.510652490541102e-06,
|
| 2175 |
+
"loss": 2.2337,
|
| 2176 |
+
"step": 72500
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 11.024939172749392,
|
| 2180 |
+
"eval_loss": 2.158447027206421,
|
| 2181 |
+
"eval_runtime": 394.8845,
|
| 2182 |
+
"eval_samples_per_second": 1065.755,
|
| 2183 |
+
"eval_steps_per_second": 4.163,
|
| 2184 |
+
"step": 72500
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 11.100973236009732,
|
| 2188 |
+
"grad_norm": 1.9024183750152588,
|
| 2189 |
+
"learning_rate": 8.207413399866525e-06,
|
| 2190 |
+
"loss": 2.2243,
|
| 2191 |
+
"step": 73000
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 11.100973236009732,
|
| 2195 |
+
"eval_loss": 2.1577627658843994,
|
| 2196 |
+
"eval_runtime": 394.3929,
|
| 2197 |
+
"eval_samples_per_second": 1067.083,
|
| 2198 |
+
"eval_steps_per_second": 4.168,
|
| 2199 |
+
"step": 73000
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 11.177007299270073,
|
| 2203 |
+
"grad_norm": 1.6612706184387207,
|
| 2204 |
+
"learning_rate": 7.908610742390934e-06,
|
| 2205 |
+
"loss": 2.2206,
|
| 2206 |
+
"step": 73500
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 11.177007299270073,
|
| 2210 |
+
"eval_loss": 2.156655788421631,
|
| 2211 |
+
"eval_runtime": 394.4918,
|
| 2212 |
+
"eval_samples_per_second": 1066.816,
|
| 2213 |
+
"eval_steps_per_second": 4.167,
|
| 2214 |
+
"step": 73500
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 11.253041362530414,
|
| 2218 |
+
"grad_norm": 1.6041182279586792,
|
| 2219 |
+
"learning_rate": 7.614323458783904e-06,
|
| 2220 |
+
"loss": 2.2316,
|
| 2221 |
+
"step": 74000
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 11.253041362530414,
|
| 2225 |
+
"eval_loss": 2.154806137084961,
|
| 2226 |
+
"eval_runtime": 394.5111,
|
| 2227 |
+
"eval_samples_per_second": 1066.763,
|
| 2228 |
+
"eval_steps_per_second": 4.167,
|
| 2229 |
+
"step": 74000
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 11.329075425790755,
|
| 2233 |
+
"grad_norm": 1.7304446697235107,
|
| 2234 |
+
"learning_rate": 7.324629296798397e-06,
|
| 2235 |
+
"loss": 2.2252,
|
| 2236 |
+
"step": 74500
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 11.329075425790755,
|
| 2240 |
+
"eval_loss": 2.1519484519958496,
|
| 2241 |
+
"eval_runtime": 394.2907,
|
| 2242 |
+
"eval_samples_per_second": 1067.36,
|
| 2243 |
+
"eval_steps_per_second": 4.17,
|
| 2244 |
+
"step": 74500
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 11.405109489051094,
|
| 2248 |
+
"grad_norm": 1.6792948246002197,
|
| 2249 |
+
"learning_rate": 7.039604790730683e-06,
|
| 2250 |
+
"loss": 2.2257,
|
| 2251 |
+
"step": 75000
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 11.405109489051094,
|
| 2255 |
+
"eval_loss": 2.1538424491882324,
|
| 2256 |
+
"eval_runtime": 394.5221,
|
| 2257 |
+
"eval_samples_per_second": 1066.734,
|
| 2258 |
+
"eval_steps_per_second": 4.167,
|
| 2259 |
+
"step": 75000
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 11.481143552311435,
|
| 2263 |
+
"grad_norm": 1.5765753984451294,
|
| 2264 |
+
"learning_rate": 6.7598810154057336e-06,
|
| 2265 |
+
"loss": 2.2252,
|
| 2266 |
+
"step": 75500
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 11.481143552311435,
|
| 2270 |
+
"eval_loss": 2.1519691944122314,
|
| 2271 |
+
"eval_runtime": 394.4824,
|
| 2272 |
+
"eval_samples_per_second": 1066.841,
|
| 2273 |
+
"eval_steps_per_second": 4.167,
|
| 2274 |
+
"step": 75500
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 11.557177615571776,
|
| 2278 |
+
"grad_norm": 1.644453525543213,
|
| 2279 |
+
"learning_rate": 6.484410758400267e-06,
|
| 2280 |
+
"loss": 2.2228,
|
| 2281 |
+
"step": 76000
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 11.557177615571776,
|
| 2285 |
+
"eval_loss": 2.1509506702423096,
|
| 2286 |
+
"eval_runtime": 394.5661,
|
| 2287 |
+
"eval_samples_per_second": 1066.615,
|
| 2288 |
+
"eval_steps_per_second": 4.167,
|
| 2289 |
+
"step": 76000
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 11.633211678832117,
|
| 2293 |
+
"grad_norm": 1.7033356428146362,
|
| 2294 |
+
"learning_rate": 6.213832134635486e-06,
|
| 2295 |
+
"loss": 2.2217,
|
| 2296 |
+
"step": 76500
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 11.633211678832117,
|
| 2300 |
+
"eval_loss": 2.1477901935577393,
|
| 2301 |
+
"eval_runtime": 394.5248,
|
| 2302 |
+
"eval_samples_per_second": 1066.726,
|
| 2303 |
+
"eval_steps_per_second": 4.167,
|
| 2304 |
+
"step": 76500
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 11.709245742092458,
|
| 2308 |
+
"grad_norm": 1.6563267707824707,
|
| 2309 |
+
"learning_rate": 5.948216628273909e-06,
|
| 2310 |
+
"loss": 2.2135,
|
| 2311 |
+
"step": 77000
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 11.709245742092458,
|
| 2315 |
+
"eval_loss": 2.1486401557922363,
|
| 2316 |
+
"eval_runtime": 394.3353,
|
| 2317 |
+
"eval_samples_per_second": 1067.239,
|
| 2318 |
+
"eval_steps_per_second": 4.169,
|
| 2319 |
+
"step": 77000
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 11.785279805352799,
|
| 2323 |
+
"grad_norm": 1.6282879114151,
|
| 2324 |
+
"learning_rate": 5.687634412272127e-06,
|
| 2325 |
+
"loss": 2.2254,
|
| 2326 |
+
"step": 77500
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 11.785279805352799,
|
| 2330 |
+
"eval_loss": 2.1465682983398438,
|
| 2331 |
+
"eval_runtime": 394.4898,
|
| 2332 |
+
"eval_samples_per_second": 1066.821,
|
| 2333 |
+
"eval_steps_per_second": 4.167,
|
| 2334 |
+
"step": 77500
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 11.861313868613138,
|
| 2338 |
+
"grad_norm": 1.7813278436660767,
|
| 2339 |
+
"learning_rate": 5.432154329841835e-06,
|
| 2340 |
+
"loss": 2.2166,
|
| 2341 |
+
"step": 78000
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 11.861313868613138,
|
| 2345 |
+
"eval_loss": 2.14347505569458,
|
| 2346 |
+
"eval_runtime": 394.4933,
|
| 2347 |
+
"eval_samples_per_second": 1066.812,
|
| 2348 |
+
"eval_steps_per_second": 4.167,
|
| 2349 |
+
"step": 78000
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 11.937347931873479,
|
| 2353 |
+
"grad_norm": 1.723649024963379,
|
| 2354 |
+
"learning_rate": 5.181843876262127e-06,
|
| 2355 |
+
"loss": 2.2181,
|
| 2356 |
+
"step": 78500
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 11.937347931873479,
|
| 2360 |
+
"eval_loss": 2.1440093517303467,
|
| 2361 |
+
"eval_runtime": 394.3682,
|
| 2362 |
+
"eval_samples_per_second": 1067.15,
|
| 2363 |
+
"eval_steps_per_second": 4.169,
|
| 2364 |
+
"step": 78500
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 12.01338199513382,
|
| 2368 |
+
"grad_norm": 1.7719519138336182,
|
| 2369 |
+
"learning_rate": 4.936769181047937e-06,
|
| 2370 |
+
"loss": 2.2092,
|
| 2371 |
+
"step": 79000
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 12.01338199513382,
|
| 2375 |
+
"eval_loss": 2.141754388809204,
|
| 2376 |
+
"eval_runtime": 394.1783,
|
| 2377 |
+
"eval_samples_per_second": 1067.664,
|
| 2378 |
+
"eval_steps_per_second": 4.171,
|
| 2379 |
+
"step": 79000
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 12.08941605839416,
|
| 2383 |
+
"grad_norm": 1.696637749671936,
|
| 2384 |
+
"learning_rate": 4.697469206617919e-06,
|
| 2385 |
+
"loss": 2.2007,
|
| 2386 |
+
"step": 79500
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 12.08941605839416,
|
| 2390 |
+
"eval_loss": 2.1432430744171143,
|
| 2391 |
+
"eval_runtime": 394.2858,
|
| 2392 |
+
"eval_samples_per_second": 1067.373,
|
| 2393 |
+
"eval_steps_per_second": 4.17,
|
| 2394 |
+
"step": 79500
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 12.165450121654501,
|
| 2398 |
+
"grad_norm": 1.6854994297027588,
|
| 2399 |
+
"learning_rate": 4.463511524513736e-06,
|
| 2400 |
+
"loss": 2.2084,
|
| 2401 |
+
"step": 80000
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 12.165450121654501,
|
| 2405 |
+
"eval_loss": 2.141733407974243,
|
| 2406 |
+
"eval_runtime": 394.4029,
|
| 2407 |
+
"eval_samples_per_second": 1067.056,
|
| 2408 |
+
"eval_steps_per_second": 4.168,
|
| 2409 |
+
"step": 80000
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 12.241484184914842,
|
| 2413 |
+
"grad_norm": 1.6496477127075195,
|
| 2414 |
+
"learning_rate": 4.2345051393941574e-06,
|
| 2415 |
+
"loss": 2.2089,
|
| 2416 |
+
"step": 80500
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 12.241484184914842,
|
| 2420 |
+
"eval_loss": 2.139671802520752,
|
| 2421 |
+
"eval_runtime": 394.4989,
|
| 2422 |
+
"eval_samples_per_second": 1066.796,
|
| 2423 |
+
"eval_steps_per_second": 4.167,
|
| 2424 |
+
"step": 80500
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 12.317518248175183,
|
| 2428 |
+
"grad_norm": 1.6591581106185913,
|
| 2429 |
+
"learning_rate": 4.010984790046615e-06,
|
| 2430 |
+
"loss": 2.2058,
|
| 2431 |
+
"step": 81000
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 12.317518248175183,
|
| 2435 |
+
"eval_loss": 2.1399948596954346,
|
| 2436 |
+
"eval_runtime": 394.4647,
|
| 2437 |
+
"eval_samples_per_second": 1066.889,
|
| 2438 |
+
"eval_steps_per_second": 4.168,
|
| 2439 |
+
"step": 81000
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 12.393552311435522,
|
| 2443 |
+
"grad_norm": 1.7192113399505615,
|
| 2444 |
+
"learning_rate": 3.7930095283087966e-06,
|
| 2445 |
+
"loss": 2.2059,
|
| 2446 |
+
"step": 81500
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 12.393552311435522,
|
| 2450 |
+
"eval_loss": 2.1405417919158936,
|
| 2451 |
+
"eval_runtime": 394.3798,
|
| 2452 |
+
"eval_samples_per_second": 1067.118,
|
| 2453 |
+
"eval_steps_per_second": 4.169,
|
| 2454 |
+
"step": 81500
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 12.469586374695863,
|
| 2458 |
+
"grad_norm": 1.6483603715896606,
|
| 2459 |
+
"learning_rate": 3.5806369410618047e-06,
|
| 2460 |
+
"loss": 2.2144,
|
| 2461 |
+
"step": 82000
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 12.469586374695863,
|
| 2465 |
+
"eval_loss": 2.1386895179748535,
|
| 2466 |
+
"eval_runtime": 394.4506,
|
| 2467 |
+
"eval_samples_per_second": 1066.927,
|
| 2468 |
+
"eval_steps_per_second": 4.168,
|
| 2469 |
+
"step": 82000
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 12.545620437956204,
|
| 2473 |
+
"grad_norm": 1.6323285102844238,
|
| 2474 |
+
"learning_rate": 3.3739231350162437e-06,
|
| 2475 |
+
"loss": 2.2076,
|
| 2476 |
+
"step": 82500
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 12.545620437956204,
|
| 2480 |
+
"eval_loss": 2.1366796493530273,
|
| 2481 |
+
"eval_runtime": 394.6499,
|
| 2482 |
+
"eval_samples_per_second": 1066.388,
|
| 2483 |
+
"eval_steps_per_second": 4.166,
|
| 2484 |
+
"step": 82500
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 12.621654501216545,
|
| 2488 |
+
"grad_norm": 1.7512730360031128,
|
| 2489 |
+
"learning_rate": 3.173318985201379e-06,
|
| 2490 |
+
"loss": 2.21,
|
| 2491 |
+
"step": 83000
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 12.621654501216545,
|
| 2495 |
+
"eval_loss": 2.1367809772491455,
|
| 2496 |
+
"eval_runtime": 394.4888,
|
| 2497 |
+
"eval_samples_per_second": 1066.824,
|
| 2498 |
+
"eval_steps_per_second": 4.167,
|
| 2499 |
+
"step": 83000
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 12.697688564476886,
|
| 2503 |
+
"grad_norm": 1.7279080152511597,
|
| 2504 |
+
"learning_rate": 2.9780734823130846e-06,
|
| 2505 |
+
"loss": 2.2014,
|
| 2506 |
+
"step": 83500
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 12.697688564476886,
|
| 2510 |
+
"eval_loss": 2.136183500289917,
|
| 2511 |
+
"eval_runtime": 394.5466,
|
| 2512 |
+
"eval_samples_per_second": 1066.667,
|
| 2513 |
+
"eval_steps_per_second": 4.167,
|
| 2514 |
+
"step": 83500
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 12.773722627737227,
|
| 2518 |
+
"grad_norm": 1.7061643600463867,
|
| 2519 |
+
"learning_rate": 2.7886459518572467e-06,
|
| 2520 |
+
"loss": 2.2073,
|
| 2521 |
+
"step": 84000
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 12.773722627737227,
|
| 2525 |
+
"eval_loss": 2.136634111404419,
|
| 2526 |
+
"eval_runtime": 394.4488,
|
| 2527 |
+
"eval_samples_per_second": 1066.932,
|
| 2528 |
+
"eval_steps_per_second": 4.168,
|
| 2529 |
+
"step": 84000
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 12.849756690997566,
|
| 2533 |
+
"grad_norm": 1.6525273323059082,
|
| 2534 |
+
"learning_rate": 2.6050864386902433e-06,
|
| 2535 |
+
"loss": 2.2062,
|
| 2536 |
+
"step": 84500
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 12.849756690997566,
|
| 2540 |
+
"eval_loss": 2.135418653488159,
|
| 2541 |
+
"eval_runtime": 394.6522,
|
| 2542 |
+
"eval_samples_per_second": 1066.382,
|
| 2543 |
+
"eval_steps_per_second": 4.166,
|
| 2544 |
+
"step": 84500
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 12.925790754257907,
|
| 2548 |
+
"grad_norm": 1.753316879272461,
|
| 2549 |
+
"learning_rate": 2.4274434373970757e-06,
|
| 2550 |
+
"loss": 2.1969,
|
| 2551 |
+
"step": 85000
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 12.925790754257907,
|
| 2555 |
+
"eval_loss": 2.130448579788208,
|
| 2556 |
+
"eval_runtime": 394.5649,
|
| 2557 |
+
"eval_samples_per_second": 1066.618,
|
| 2558 |
+
"eval_steps_per_second": 4.167,
|
| 2559 |
+
"step": 85000
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 13.001824817518248,
|
| 2563 |
+
"grad_norm": 1.5890535116195679,
|
| 2564 |
+
"learning_rate": 2.256101256668691e-06,
|
| 2565 |
+
"loss": 2.2078,
|
| 2566 |
+
"step": 85500
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 13.001824817518248,
|
| 2570 |
+
"eval_loss": 2.1335136890411377,
|
| 2571 |
+
"eval_runtime": 394.3918,
|
| 2572 |
+
"eval_samples_per_second": 1067.086,
|
| 2573 |
+
"eval_steps_per_second": 4.168,
|
| 2574 |
+
"step": 85500
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 13.077858880778589,
|
| 2578 |
+
"grad_norm": 1.7298823595046997,
|
| 2579 |
+
"learning_rate": 2.0904184363357256e-06,
|
| 2580 |
+
"loss": 2.203,
|
| 2581 |
+
"step": 86000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 13.077858880778589,
|
| 2585 |
+
"eval_loss": 2.132927894592285,
|
| 2586 |
+
"eval_runtime": 394.4131,
|
| 2587 |
+
"eval_samples_per_second": 1067.029,
|
| 2588 |
+
"eval_steps_per_second": 4.168,
|
| 2589 |
+
"step": 86000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 13.15389294403893,
|
| 2593 |
+
"grad_norm": 1.7888143062591553,
|
| 2594 |
+
"learning_rate": 1.930788098008321e-06,
|
| 2595 |
+
"loss": 2.1993,
|
| 2596 |
+
"step": 86500
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 13.15389294403893,
|
| 2600 |
+
"eval_loss": 2.1313769817352295,
|
| 2601 |
+
"eval_runtime": 394.3014,
|
| 2602 |
+
"eval_samples_per_second": 1067.331,
|
| 2603 |
+
"eval_steps_per_second": 4.169,
|
| 2604 |
+
"step": 86500
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 13.22992700729927,
|
| 2608 |
+
"grad_norm": 1.7427315711975098,
|
| 2609 |
+
"learning_rate": 1.7772524144231473e-06,
|
| 2610 |
+
"loss": 2.2032,
|
| 2611 |
+
"step": 87000
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 13.22992700729927,
|
| 2615 |
+
"eval_loss": 2.135279893875122,
|
| 2616 |
+
"eval_runtime": 394.1525,
|
| 2617 |
+
"eval_samples_per_second": 1067.734,
|
| 2618 |
+
"eval_steps_per_second": 4.171,
|
| 2619 |
+
"step": 87000
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 13.305961070559611,
|
| 2623 |
+
"grad_norm": 1.700643539428711,
|
| 2624 |
+
"learning_rate": 1.6298519481701192e-06,
|
| 2625 |
+
"loss": 2.2,
|
| 2626 |
+
"step": 87500
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 13.305961070559611,
|
| 2630 |
+
"eval_loss": 2.130155086517334,
|
| 2631 |
+
"eval_runtime": 393.7376,
|
| 2632 |
+
"eval_samples_per_second": 1068.859,
|
| 2633 |
+
"eval_steps_per_second": 4.175,
|
| 2634 |
+
"step": 87500
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 13.38199513381995,
|
| 2638 |
+
"grad_norm": 1.6336027383804321,
|
| 2639 |
+
"learning_rate": 1.4889019067080928e-06,
|
| 2640 |
+
"loss": 2.1964,
|
| 2641 |
+
"step": 88000
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 13.38199513381995,
|
| 2645 |
+
"eval_loss": 2.129770517349243,
|
| 2646 |
+
"eval_runtime": 394.1127,
|
| 2647 |
+
"eval_samples_per_second": 1067.842,
|
| 2648 |
+
"eval_steps_per_second": 4.171,
|
| 2649 |
+
"step": 88000
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 13.458029197080291,
|
| 2653 |
+
"grad_norm": 1.698116421699524,
|
| 2654 |
+
"learning_rate": 1.3538746100630939e-06,
|
| 2655 |
+
"loss": 2.1957,
|
| 2656 |
+
"step": 88500
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 13.458029197080291,
|
| 2660 |
+
"eval_loss": 2.1296403408050537,
|
| 2661 |
+
"eval_runtime": 394.7051,
|
| 2662 |
+
"eval_samples_per_second": 1066.239,
|
| 2663 |
+
"eval_steps_per_second": 4.165,
|
| 2664 |
+
"step": 88500
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 13.534063260340632,
|
| 2668 |
+
"grad_norm": 1.7204720973968506,
|
| 2669 |
+
"learning_rate": 1.2250943829259454e-06,
|
| 2670 |
+
"loss": 2.1985,
|
| 2671 |
+
"step": 89000
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 13.534063260340632,
|
| 2675 |
+
"eval_loss": 2.131389856338501,
|
| 2676 |
+
"eval_runtime": 394.7347,
|
| 2677 |
+
"eval_samples_per_second": 1066.159,
|
| 2678 |
+
"eval_steps_per_second": 4.165,
|
| 2679 |
+
"step": 89000
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 13.610097323600973,
|
| 2683 |
+
"grad_norm": 1.7444037199020386,
|
| 2684 |
+
"learning_rate": 1.102595247742902e-06,
|
| 2685 |
+
"loss": 2.1967,
|
| 2686 |
+
"step": 89500
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 13.610097323600973,
|
| 2690 |
+
"eval_loss": 2.13096284866333,
|
| 2691 |
+
"eval_runtime": 394.695,
|
| 2692 |
+
"eval_samples_per_second": 1066.266,
|
| 2693 |
+
"eval_steps_per_second": 4.165,
|
| 2694 |
+
"step": 89500
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 13.686131386861314,
|
| 2698 |
+
"grad_norm": 1.7652897834777832,
|
| 2699 |
+
"learning_rate": 9.864095675586272e-07,
|
| 2700 |
+
"loss": 2.1979,
|
| 2701 |
+
"step": 90000
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 13.686131386861314,
|
| 2705 |
+
"eval_loss": 2.1287431716918945,
|
| 2706 |
+
"eval_runtime": 394.6791,
|
| 2707 |
+
"eval_samples_per_second": 1066.309,
|
| 2708 |
+
"eval_steps_per_second": 4.165,
|
| 2709 |
+
"step": 90000
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 13.762165450121655,
|
| 2713 |
+
"grad_norm": 1.6986685991287231,
|
| 2714 |
+
"learning_rate": 8.765680374662105e-07,
|
| 2715 |
+
"loss": 2.2055,
|
| 2716 |
+
"step": 90500
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 13.762165450121655,
|
| 2720 |
+
"eval_loss": 2.128450870513916,
|
| 2721 |
+
"eval_runtime": 394.7254,
|
| 2722 |
+
"eval_samples_per_second": 1066.184,
|
| 2723 |
+
"eval_steps_per_second": 4.165,
|
| 2724 |
+
"step": 90500
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 13.838199513381996,
|
| 2728 |
+
"grad_norm": 1.7826683521270752,
|
| 2729 |
+
"learning_rate": 7.730996764978071e-07,
|
| 2730 |
+
"loss": 2.1933,
|
| 2731 |
+
"step": 91000
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 13.838199513381996,
|
| 2735 |
+
"eval_loss": 2.128603935241699,
|
| 2736 |
+
"eval_runtime": 394.6725,
|
| 2737 |
+
"eval_samples_per_second": 1066.327,
|
| 2738 |
+
"eval_steps_per_second": 4.165,
|
| 2739 |
+
"step": 91000
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 13.914233576642335,
|
| 2743 |
+
"grad_norm": 1.7597603797912598,
|
| 2744 |
+
"learning_rate": 6.76031819958145e-07,
|
| 2745 |
+
"loss": 2.1945,
|
| 2746 |
+
"step": 91500
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 13.914233576642335,
|
| 2750 |
+
"eval_loss": 2.1281092166900635,
|
| 2751 |
+
"eval_runtime": 394.6346,
|
| 2752 |
+
"eval_samples_per_second": 1066.43,
|
| 2753 |
+
"eval_steps_per_second": 4.166,
|
| 2754 |
+
"step": 91500
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 13.990267639902676,
|
| 2758 |
+
"grad_norm": 1.5649290084838867,
|
| 2759 |
+
"learning_rate": 5.855649661219098e-07,
|
| 2760 |
+
"loss": 2.2016,
|
| 2761 |
+
"step": 92000
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 13.990267639902676,
|
| 2765 |
+
"eval_loss": 2.129279613494873,
|
| 2766 |
+
"eval_runtime": 394.55,
|
| 2767 |
+
"eval_samples_per_second": 1066.658,
|
| 2768 |
+
"eval_steps_per_second": 4.167,
|
| 2769 |
+
"step": 92000
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 14.066301703163017,
|
| 2773 |
+
"grad_norm": 1.6939290761947632,
|
| 2774 |
+
"learning_rate": 5.013604308242548e-07,
|
| 2775 |
+
"loss": 2.195,
|
| 2776 |
+
"step": 92500
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 14.066301703163017,
|
| 2780 |
+
"eval_loss": 2.1266942024230957,
|
| 2781 |
+
"eval_runtime": 394.5988,
|
| 2782 |
+
"eval_samples_per_second": 1066.526,
|
| 2783 |
+
"eval_steps_per_second": 4.166,
|
| 2784 |
+
"step": 92500
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 14.142335766423358,
|
| 2788 |
+
"grad_norm": 1.6481035947799683,
|
| 2789 |
+
"learning_rate": 4.236281907425227e-07,
|
| 2790 |
+
"loss": 2.1939,
|
| 2791 |
+
"step": 93000
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 14.142335766423358,
|
| 2795 |
+
"eval_loss": 2.1291019916534424,
|
| 2796 |
+
"eval_runtime": 393.3337,
|
| 2797 |
+
"eval_samples_per_second": 1069.957,
|
| 2798 |
+
"eval_steps_per_second": 4.18,
|
| 2799 |
+
"step": 93000
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 14.218369829683699,
|
| 2803 |
+
"grad_norm": 1.7540963888168335,
|
| 2804 |
+
"learning_rate": 3.523887819560451e-07,
|
| 2805 |
+
"loss": 2.1939,
|
| 2806 |
+
"step": 93500
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 14.218369829683699,
|
| 2810 |
+
"eval_loss": 2.130265474319458,
|
| 2811 |
+
"eval_runtime": 393.7198,
|
| 2812 |
+
"eval_samples_per_second": 1068.907,
|
| 2813 |
+
"eval_steps_per_second": 4.176,
|
| 2814 |
+
"step": 93500
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 14.29440389294404,
|
| 2818 |
+
"grad_norm": 1.7240368127822876,
|
| 2819 |
+
"learning_rate": 2.876610252031453e-07,
|
| 2820 |
+
"loss": 2.1907,
|
| 2821 |
+
"step": 94000
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 14.29440389294404,
|
| 2825 |
+
"eval_loss": 2.126887321472168,
|
| 2826 |
+
"eval_runtime": 393.7098,
|
| 2827 |
+
"eval_samples_per_second": 1068.934,
|
| 2828 |
+
"eval_steps_per_second": 4.176,
|
| 2829 |
+
"step": 94000
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 14.37043795620438,
|
| 2833 |
+
"grad_norm": 1.6906523704528809,
|
| 2834 |
+
"learning_rate": 2.2946202090889657e-07,
|
| 2835 |
+
"loss": 2.1999,
|
| 2836 |
+
"step": 94500
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 14.37043795620438,
|
| 2840 |
+
"eval_loss": 2.126722812652588,
|
| 2841 |
+
"eval_runtime": 393.685,
|
| 2842 |
+
"eval_samples_per_second": 1069.002,
|
| 2843 |
+
"eval_steps_per_second": 4.176,
|
| 2844 |
+
"step": 94500
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 14.44647201946472,
|
| 2848 |
+
"grad_norm": 1.7347662448883057,
|
| 2849 |
+
"learning_rate": 1.7790391402128793e-07,
|
| 2850 |
+
"loss": 2.1989,
|
| 2851 |
+
"step": 95000
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 14.44647201946472,
|
| 2855 |
+
"eval_loss": 2.1272239685058594,
|
| 2856 |
+
"eval_runtime": 393.5995,
|
| 2857 |
+
"eval_samples_per_second": 1069.234,
|
| 2858 |
+
"eval_steps_per_second": 4.177,
|
| 2859 |
+
"step": 95000
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 14.52250608272506,
|
| 2863 |
+
"grad_norm": 1.64090096950531,
|
| 2864 |
+
"learning_rate": 1.327936845155059e-07,
|
| 2865 |
+
"loss": 2.1963,
|
| 2866 |
+
"step": 95500
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 14.52250608272506,
|
| 2870 |
+
"eval_loss": 2.126425266265869,
|
| 2871 |
+
"eval_runtime": 394.5292,
|
| 2872 |
+
"eval_samples_per_second": 1066.715,
|
| 2873 |
+
"eval_steps_per_second": 4.167,
|
| 2874 |
+
"step": 95500
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 14.598540145985401,
|
| 2878 |
+
"grad_norm": 1.6597987413406372,
|
| 2879 |
+
"learning_rate": 9.425312186875923e-08,
|
| 2880 |
+
"loss": 2.1987,
|
| 2881 |
+
"step": 96000
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 14.598540145985401,
|
| 2885 |
+
"eval_loss": 2.1285743713378906,
|
| 2886 |
+
"eval_runtime": 394.6211,
|
| 2887 |
+
"eval_samples_per_second": 1066.466,
|
| 2888 |
+
"eval_steps_per_second": 4.166,
|
| 2889 |
+
"step": 96000
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 14.674574209245742,
|
| 2893 |
+
"grad_norm": 1.6827759742736816,
|
| 2894 |
+
"learning_rate": 6.2292408111711e-08,
|
| 2895 |
+
"loss": 2.2012,
|
| 2896 |
+
"step": 96500
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 14.674574209245742,
|
| 2900 |
+
"eval_loss": 2.1267669200897217,
|
| 2901 |
+
"eval_runtime": 394.6661,
|
| 2902 |
+
"eval_samples_per_second": 1066.344,
|
| 2903 |
+
"eval_steps_per_second": 4.166,
|
| 2904 |
+
"step": 96500
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 14.750608272506083,
|
| 2908 |
+
"grad_norm": 1.9470024108886719,
|
| 2909 |
+
"learning_rate": 3.691998694484722e-08,
|
| 2910 |
+
"loss": 2.2013,
|
| 2911 |
+
"step": 97000
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 14.750608272506083,
|
| 2915 |
+
"eval_loss": 2.128140449523926,
|
| 2916 |
+
"eval_runtime": 394.6676,
|
| 2917 |
+
"eval_samples_per_second": 1066.34,
|
| 2918 |
+
"eval_steps_per_second": 4.166,
|
| 2919 |
+
"step": 97000
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 14.826642335766424,
|
| 2923 |
+
"grad_norm": 1.6369675397872925,
|
| 2924 |
+
"learning_rate": 1.817353096532637e-08,
|
| 2925 |
+
"loss": 2.1923,
|
| 2926 |
+
"step": 97500
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 14.826642335766424,
|
| 2930 |
+
"eval_loss": 2.128028392791748,
|
| 2931 |
+
"eval_runtime": 394.6764,
|
| 2932 |
+
"eval_samples_per_second": 1066.317,
|
| 2933 |
+
"eval_steps_per_second": 4.165,
|
| 2934 |
+
"step": 97500
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 14.902676399026763,
|
| 2938 |
+
"grad_norm": 1.7755557298660278,
|
| 2939 |
+
"learning_rate": 5.982858360498167e-09,
|
| 2940 |
+
"loss": 2.1966,
|
| 2941 |
+
"step": 98000
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 14.902676399026763,
|
| 2945 |
+
"eval_loss": 2.1286511421203613,
|
| 2946 |
+
"eval_runtime": 393.4618,
|
| 2947 |
+
"eval_samples_per_second": 1069.608,
|
| 2948 |
+
"eval_steps_per_second": 4.178,
|
| 2949 |
+
"step": 98000
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 14.978710462287104,
|
| 2953 |
+
"grad_norm": 1.7456624507904053,
|
| 2954 |
+
"learning_rate": 3.953547649482303e-10,
|
| 2955 |
+
"loss": 2.1987,
|
| 2956 |
+
"step": 98500
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 14.978710462287104,
|
| 2960 |
+
"eval_loss": 2.127889394760132,
|
| 2961 |
+
"eval_runtime": 393.3437,
|
| 2962 |
+
"eval_samples_per_second": 1069.93,
|
| 2963 |
+
"eval_steps_per_second": 4.18,
|
| 2964 |
+
"step": 98500
|
| 2965 |
+
}
|
| 2966 |
+
],
|
| 2967 |
+
"logging_steps": 500,
|
| 2968 |
+
"max_steps": 98640,
|
| 2969 |
+
"num_input_tokens_seen": 0,
|
| 2970 |
+
"num_train_epochs": 15,
|
| 2971 |
+
"save_steps": 1000,
|
| 2972 |
+
"stateful_callbacks": {
|
| 2973 |
+
"TrainerControl": {
|
| 2974 |
+
"args": {
|
| 2975 |
+
"should_epoch_stop": false,
|
| 2976 |
+
"should_evaluate": false,
|
| 2977 |
+
"should_log": false,
|
| 2978 |
+
"should_save": true,
|
| 2979 |
+
"should_training_stop": true
|
| 2980 |
+
},
|
| 2981 |
+
"attributes": {}
|
| 2982 |
+
}
|
| 2983 |
+
},
|
| 2984 |
+
"total_flos": 6.646405662995644e+18,
|
| 2985 |
+
"train_batch_size": 16,
|
| 2986 |
+
"trial_name": null,
|
| 2987 |
+
"trial_params": null
|
| 2988 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f379f816e10ade259247be2d7675fdda5e344a5ad9d6570ce93ed7fd9b3ea61a
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|