Upload DeBERTa v3 hydrangea leaf spot classifier
Browse files- README.md +13 -0
- added_tokens.json +3 -0
- config.json +53 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer_config.json +59 -0
- trainer_state.json +1912 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- text-classification
|
| 5 |
+
- plant-disease
|
| 6 |
+
- hydrangea
|
| 7 |
+
- deberta
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# DeBERTa v3 — Hydrangea Leaf Spot Disease Classifier
|
| 11 |
+
|
| 12 |
+
Fine-tuned DeBERTa v3 on ~70,000 Q&A pairs for 6 leaf spot disease types.
|
| 13 |
+
- Validation Accuracy: 98.4% | Macro-F1: 0.98
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Bacterial Leaf Scorch",
|
| 14 |
+
"1": "Cercospora Leaf Spot",
|
| 15 |
+
"2": "Dogwood Anthracnose",
|
| 16 |
+
"3": "Phyllosticta Leaf Spot",
|
| 17 |
+
"4": "Septoria Leaf Spot",
|
| 18 |
+
"5": "Spot Anthracnose"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"Bacterial Leaf Scorch": 0,
|
| 24 |
+
"Cercospora Leaf Spot": 1,
|
| 25 |
+
"Dogwood Anthracnose": 2,
|
| 26 |
+
"Phyllosticta Leaf Spot": 3,
|
| 27 |
+
"Septoria Leaf Spot": 4,
|
| 28 |
+
"Spot Anthracnose": 5
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-07,
|
| 31 |
+
"legacy": true,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"max_relative_positions": -1,
|
| 34 |
+
"model_type": "deberta-v2",
|
| 35 |
+
"norm_rel_ebd": "layer_norm",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"pooler_dropout": 0,
|
| 40 |
+
"pooler_hidden_act": "gelu",
|
| 41 |
+
"pooler_hidden_size": 768,
|
| 42 |
+
"pos_att_type": [
|
| 43 |
+
"p2c",
|
| 44 |
+
"c2p"
|
| 45 |
+
],
|
| 46 |
+
"position_biased_input": false,
|
| 47 |
+
"position_buckets": 256,
|
| 48 |
+
"relative_attention": true,
|
| 49 |
+
"share_att_key": true,
|
| 50 |
+
"transformers_version": "4.57.1",
|
| 51 |
+
"type_vocab_size": 0,
|
| 52 |
+
"vocab_size": 128100
|
| 53 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2175b9f513e630550a75d1f9edf4947b37b881e0afa7ec61091bec499ebc2e12
|
| 3 |
+
size 378273792
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:904782405d841a5902c1970e95584252bed0aa84dcacb3197094efaa48ba0e30
|
| 3 |
+
size 475529216
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0248212e91629f1ce0aeb54fe08d3772ddd6cad5dc2dbb2668edbf66a62dedc9
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7db84837c9cfa08f5631d31fde262c48665daff40e89b896255a8d6a626221f
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "[SEP]",
|
| 49 |
+
"extra_special_tokens": {},
|
| 50 |
+
"mask_token": "[MASK]",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"split_by_punct": false,
|
| 56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 57 |
+
"unk_token": "[UNK]",
|
| 58 |
+
"vocab_type": "spm"
|
| 59 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1912 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 13206,
|
| 3 |
+
"best_metric": 0.9868791709426586,
|
| 4 |
+
"best_model_checkpoint": "/home/myid/bp67339/plant_disease/models/deberta_v3_base_textclf_phase3/checkpoint-13206",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 13206,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011358473421172195,
|
| 14 |
+
"grad_norm": 2.552668809890747,
|
| 15 |
+
"learning_rate": 1.9925791306981678e-05,
|
| 16 |
+
"loss": 0.1196,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02271694684234439,
|
| 21 |
+
"grad_norm": 0.47541937232017517,
|
| 22 |
+
"learning_rate": 1.985006815084053e-05,
|
| 23 |
+
"loss": 0.0812,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.034075420263516586,
|
| 28 |
+
"grad_norm": 7.045262813568115,
|
| 29 |
+
"learning_rate": 1.977434499469938e-05,
|
| 30 |
+
"loss": 0.0859,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04543389368468878,
|
| 35 |
+
"grad_norm": 0.03415582329034805,
|
| 36 |
+
"learning_rate": 1.9698621838558232e-05,
|
| 37 |
+
"loss": 0.0847,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05679236710586097,
|
| 42 |
+
"grad_norm": 0.05752035602927208,
|
| 43 |
+
"learning_rate": 1.9622898682417084e-05,
|
| 44 |
+
"loss": 0.0988,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06815084052703317,
|
| 49 |
+
"grad_norm": 3.0614030361175537,
|
| 50 |
+
"learning_rate": 1.9547175526275936e-05,
|
| 51 |
+
"loss": 0.1058,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07950931394820536,
|
| 56 |
+
"grad_norm": 1.2528300285339355,
|
| 57 |
+
"learning_rate": 1.947145237013479e-05,
|
| 58 |
+
"loss": 0.0842,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09086778736937756,
|
| 63 |
+
"grad_norm": 8.556694984436035,
|
| 64 |
+
"learning_rate": 1.9395729213993642e-05,
|
| 65 |
+
"loss": 0.0777,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10222626079054975,
|
| 70 |
+
"grad_norm": 20.690099716186523,
|
| 71 |
+
"learning_rate": 1.9320006057852494e-05,
|
| 72 |
+
"loss": 0.0764,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11358473421172194,
|
| 77 |
+
"grad_norm": 4.0012030601501465,
|
| 78 |
+
"learning_rate": 1.9244282901711345e-05,
|
| 79 |
+
"loss": 0.0814,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.12494320763289414,
|
| 84 |
+
"grad_norm": 0.06608668714761734,
|
| 85 |
+
"learning_rate": 1.9168559745570197e-05,
|
| 86 |
+
"loss": 0.0637,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13630168105406634,
|
| 91 |
+
"grad_norm": 5.306321620941162,
|
| 92 |
+
"learning_rate": 1.909283658942905e-05,
|
| 93 |
+
"loss": 0.0479,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.14766015447523853,
|
| 98 |
+
"grad_norm": 5.900157451629639,
|
| 99 |
+
"learning_rate": 1.90171134332879e-05,
|
| 100 |
+
"loss": 0.0892,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.15901862789641072,
|
| 105 |
+
"grad_norm": 2.73388934135437,
|
| 106 |
+
"learning_rate": 1.8941390277146755e-05,
|
| 107 |
+
"loss": 0.0721,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1703771013175829,
|
| 112 |
+
"grad_norm": 6.770120143890381,
|
| 113 |
+
"learning_rate": 1.8865667121005603e-05,
|
| 114 |
+
"loss": 0.082,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.18173557473875512,
|
| 119 |
+
"grad_norm": 0.010230629704892635,
|
| 120 |
+
"learning_rate": 1.8789943964864458e-05,
|
| 121 |
+
"loss": 0.0604,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1930940481599273,
|
| 126 |
+
"grad_norm": 11.530449867248535,
|
| 127 |
+
"learning_rate": 1.871422080872331e-05,
|
| 128 |
+
"loss": 0.0578,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2044525215810995,
|
| 133 |
+
"grad_norm": 0.014014088548719883,
|
| 134 |
+
"learning_rate": 1.863849765258216e-05,
|
| 135 |
+
"loss": 0.0574,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2158109950022717,
|
| 140 |
+
"grad_norm": 0.016662120819091797,
|
| 141 |
+
"learning_rate": 1.8562774496441013e-05,
|
| 142 |
+
"loss": 0.0654,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.22716946842344388,
|
| 147 |
+
"grad_norm": 1.2837393283843994,
|
| 148 |
+
"learning_rate": 1.8487051340299865e-05,
|
| 149 |
+
"loss": 0.0638,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2385279418446161,
|
| 154 |
+
"grad_norm": 0.45574066042900085,
|
| 155 |
+
"learning_rate": 1.8411328184158716e-05,
|
| 156 |
+
"loss": 0.0448,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.24988641526578828,
|
| 161 |
+
"grad_norm": 2.423413038253784,
|
| 162 |
+
"learning_rate": 1.8335605028017568e-05,
|
| 163 |
+
"loss": 0.0535,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2612448886869605,
|
| 168 |
+
"grad_norm": 4.537928104400635,
|
| 169 |
+
"learning_rate": 1.8259881871876423e-05,
|
| 170 |
+
"loss": 0.0833,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2726033621081327,
|
| 175 |
+
"grad_norm": 6.994387626647949,
|
| 176 |
+
"learning_rate": 1.8184158715735274e-05,
|
| 177 |
+
"loss": 0.06,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2839618355293049,
|
| 182 |
+
"grad_norm": 0.01928258314728737,
|
| 183 |
+
"learning_rate": 1.8108435559594126e-05,
|
| 184 |
+
"loss": 0.0498,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.29532030895047706,
|
| 189 |
+
"grad_norm": 0.4064951241016388,
|
| 190 |
+
"learning_rate": 1.8032712403452977e-05,
|
| 191 |
+
"loss": 0.0491,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.30667878237164925,
|
| 196 |
+
"grad_norm": 2.6388704776763916,
|
| 197 |
+
"learning_rate": 1.795698924731183e-05,
|
| 198 |
+
"loss": 0.0327,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.31803725579282144,
|
| 203 |
+
"grad_norm": 2.0852885246276855,
|
| 204 |
+
"learning_rate": 1.788126609117068e-05,
|
| 205 |
+
"loss": 0.0978,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3293957292139936,
|
| 210 |
+
"grad_norm": 2.8278560638427734,
|
| 211 |
+
"learning_rate": 1.7805542935029532e-05,
|
| 212 |
+
"loss": 0.0521,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3407542026351658,
|
| 217 |
+
"grad_norm": 4.4425177574157715,
|
| 218 |
+
"learning_rate": 1.7729819778888387e-05,
|
| 219 |
+
"loss": 0.0532,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.352112676056338,
|
| 224 |
+
"grad_norm": 0.0768510028719902,
|
| 225 |
+
"learning_rate": 1.7654096622747235e-05,
|
| 226 |
+
"loss": 0.0486,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.36347114947751025,
|
| 231 |
+
"grad_norm": 0.4614756405353546,
|
| 232 |
+
"learning_rate": 1.757837346660609e-05,
|
| 233 |
+
"loss": 0.0419,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.37482962289868244,
|
| 238 |
+
"grad_norm": 0.5945758819580078,
|
| 239 |
+
"learning_rate": 1.7502650310464942e-05,
|
| 240 |
+
"loss": 0.055,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3861880963198546,
|
| 245 |
+
"grad_norm": 0.5370413661003113,
|
| 246 |
+
"learning_rate": 1.7426927154323794e-05,
|
| 247 |
+
"loss": 0.0434,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3975465697410268,
|
| 252 |
+
"grad_norm": 13.6658296585083,
|
| 253 |
+
"learning_rate": 1.7351203998182645e-05,
|
| 254 |
+
"loss": 0.0329,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.408905043162199,
|
| 259 |
+
"grad_norm": 0.9185870885848999,
|
| 260 |
+
"learning_rate": 1.72754808420415e-05,
|
| 261 |
+
"loss": 0.0584,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4202635165833712,
|
| 266 |
+
"grad_norm": 0.3048367500305176,
|
| 267 |
+
"learning_rate": 1.719975768590035e-05,
|
| 268 |
+
"loss": 0.0561,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.4316219900045434,
|
| 273 |
+
"grad_norm": 3.6233348846435547,
|
| 274 |
+
"learning_rate": 1.71240345297592e-05,
|
| 275 |
+
"loss": 0.0568,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.44298046342571556,
|
| 280 |
+
"grad_norm": 7.301445007324219,
|
| 281 |
+
"learning_rate": 1.7048311373618055e-05,
|
| 282 |
+
"loss": 0.0545,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.45433893684688775,
|
| 287 |
+
"grad_norm": 12.261190414428711,
|
| 288 |
+
"learning_rate": 1.6972588217476907e-05,
|
| 289 |
+
"loss": 0.0347,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.46569741026806,
|
| 294 |
+
"grad_norm": 0.004870145116001368,
|
| 295 |
+
"learning_rate": 1.6896865061335758e-05,
|
| 296 |
+
"loss": 0.0297,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4770558836892322,
|
| 301 |
+
"grad_norm": 0.08898526430130005,
|
| 302 |
+
"learning_rate": 1.682114190519461e-05,
|
| 303 |
+
"loss": 0.0368,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4884143571104044,
|
| 308 |
+
"grad_norm": 0.007771740201860666,
|
| 309 |
+
"learning_rate": 1.674541874905346e-05,
|
| 310 |
+
"loss": 0.037,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.49977283053157656,
|
| 315 |
+
"grad_norm": 0.06338020414113998,
|
| 316 |
+
"learning_rate": 1.6669695592912313e-05,
|
| 317 |
+
"loss": 0.0351,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5111313039527488,
|
| 322 |
+
"grad_norm": 0.2080918550491333,
|
| 323 |
+
"learning_rate": 1.6593972436771168e-05,
|
| 324 |
+
"loss": 0.0424,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.522489777373921,
|
| 329 |
+
"grad_norm": 0.005484211724251509,
|
| 330 |
+
"learning_rate": 1.651824928063002e-05,
|
| 331 |
+
"loss": 0.0498,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5338482507950931,
|
| 336 |
+
"grad_norm": 1.5300865173339844,
|
| 337 |
+
"learning_rate": 1.6442526124488868e-05,
|
| 338 |
+
"loss": 0.0309,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5452067242162654,
|
| 343 |
+
"grad_norm": 1.4512425661087036,
|
| 344 |
+
"learning_rate": 1.6366802968347723e-05,
|
| 345 |
+
"loss": 0.0397,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5565651976374375,
|
| 350 |
+
"grad_norm": 0.07551686465740204,
|
| 351 |
+
"learning_rate": 1.6291079812206574e-05,
|
| 352 |
+
"loss": 0.0368,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5679236710586097,
|
| 357 |
+
"grad_norm": 5.5924272537231445,
|
| 358 |
+
"learning_rate": 1.6215356656065426e-05,
|
| 359 |
+
"loss": 0.0169,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5792821444797819,
|
| 364 |
+
"grad_norm": 0.03456870838999748,
|
| 365 |
+
"learning_rate": 1.6139633499924277e-05,
|
| 366 |
+
"loss": 0.0397,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5906406179009541,
|
| 371 |
+
"grad_norm": 1.605539321899414,
|
| 372 |
+
"learning_rate": 1.6063910343783132e-05,
|
| 373 |
+
"loss": 0.0353,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6019990913221263,
|
| 378 |
+
"grad_norm": 2.287083864212036,
|
| 379 |
+
"learning_rate": 1.598818718764198e-05,
|
| 380 |
+
"loss": 0.0233,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6133575647432985,
|
| 385 |
+
"grad_norm": 0.02498025633394718,
|
| 386 |
+
"learning_rate": 1.5912464031500836e-05,
|
| 387 |
+
"loss": 0.0389,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6247160381644707,
|
| 392 |
+
"grad_norm": 0.009853340685367584,
|
| 393 |
+
"learning_rate": 1.5836740875359687e-05,
|
| 394 |
+
"loss": 0.0343,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6360745115856429,
|
| 399 |
+
"grad_norm": 0.006630271207541227,
|
| 400 |
+
"learning_rate": 1.576101771921854e-05,
|
| 401 |
+
"loss": 0.0211,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6474329850068151,
|
| 406 |
+
"grad_norm": 9.345346450805664,
|
| 407 |
+
"learning_rate": 1.568529456307739e-05,
|
| 408 |
+
"loss": 0.0374,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6587914584279873,
|
| 413 |
+
"grad_norm": 6.142024040222168,
|
| 414 |
+
"learning_rate": 1.5609571406936242e-05,
|
| 415 |
+
"loss": 0.0551,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6701499318491595,
|
| 420 |
+
"grad_norm": 0.0021689136046916246,
|
| 421 |
+
"learning_rate": 1.5533848250795093e-05,
|
| 422 |
+
"loss": 0.0223,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6815084052703316,
|
| 427 |
+
"grad_norm": 0.12782888114452362,
|
| 428 |
+
"learning_rate": 1.5458125094653945e-05,
|
| 429 |
+
"loss": 0.0397,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6928668786915039,
|
| 434 |
+
"grad_norm": 0.021150466054677963,
|
| 435 |
+
"learning_rate": 1.53824019385128e-05,
|
| 436 |
+
"loss": 0.0465,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.704225352112676,
|
| 441 |
+
"grad_norm": 0.03622226044535637,
|
| 442 |
+
"learning_rate": 1.530667878237165e-05,
|
| 443 |
+
"loss": 0.0245,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7155838255338483,
|
| 448 |
+
"grad_norm": 0.01021323911845684,
|
| 449 |
+
"learning_rate": 1.5230955626230503e-05,
|
| 450 |
+
"loss": 0.04,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7269422989550205,
|
| 455 |
+
"grad_norm": 0.3106459677219391,
|
| 456 |
+
"learning_rate": 1.5155232470089353e-05,
|
| 457 |
+
"loss": 0.0257,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7383007723761926,
|
| 462 |
+
"grad_norm": 0.00275537115521729,
|
| 463 |
+
"learning_rate": 1.5079509313948206e-05,
|
| 464 |
+
"loss": 0.0263,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7496592457973649,
|
| 469 |
+
"grad_norm": 2.062044143676758,
|
| 470 |
+
"learning_rate": 1.5003786157807058e-05,
|
| 471 |
+
"loss": 0.0309,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.761017719218537,
|
| 476 |
+
"grad_norm": 9.71252155303955,
|
| 477 |
+
"learning_rate": 1.4928063001665911e-05,
|
| 478 |
+
"loss": 0.0398,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7723761926397092,
|
| 483 |
+
"grad_norm": 0.1981002688407898,
|
| 484 |
+
"learning_rate": 1.4852339845524763e-05,
|
| 485 |
+
"loss": 0.0361,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7837346660608814,
|
| 490 |
+
"grad_norm": 5.37298059463501,
|
| 491 |
+
"learning_rate": 1.4776616689383614e-05,
|
| 492 |
+
"loss": 0.028,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7950931394820536,
|
| 497 |
+
"grad_norm": 0.01882290095090866,
|
| 498 |
+
"learning_rate": 1.4700893533242466e-05,
|
| 499 |
+
"loss": 0.0326,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8064516129032258,
|
| 504 |
+
"grad_norm": 0.035887233912944794,
|
| 505 |
+
"learning_rate": 1.462517037710132e-05,
|
| 506 |
+
"loss": 0.0416,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.817810086324398,
|
| 511 |
+
"grad_norm": 13.781176567077637,
|
| 512 |
+
"learning_rate": 1.4549447220960171e-05,
|
| 513 |
+
"loss": 0.023,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8291685597455702,
|
| 518 |
+
"grad_norm": 0.06990953534841537,
|
| 519 |
+
"learning_rate": 1.4473724064819024e-05,
|
| 520 |
+
"loss": 0.0213,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8405270331667424,
|
| 525 |
+
"grad_norm": 0.6063719987869263,
|
| 526 |
+
"learning_rate": 1.4398000908677874e-05,
|
| 527 |
+
"loss": 0.0228,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8518855065879146,
|
| 532 |
+
"grad_norm": 4.930353164672852,
|
| 533 |
+
"learning_rate": 1.4322277752536726e-05,
|
| 534 |
+
"loss": 0.0335,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8632439800090868,
|
| 539 |
+
"grad_norm": 0.004565690644085407,
|
| 540 |
+
"learning_rate": 1.4246554596395579e-05,
|
| 541 |
+
"loss": 0.0214,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.874602453430259,
|
| 546 |
+
"grad_norm": 0.17241248488426208,
|
| 547 |
+
"learning_rate": 1.417083144025443e-05,
|
| 548 |
+
"loss": 0.0401,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8859609268514311,
|
| 553 |
+
"grad_norm": 5.231073379516602,
|
| 554 |
+
"learning_rate": 1.4095108284113284e-05,
|
| 555 |
+
"loss": 0.0168,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8973194002726034,
|
| 560 |
+
"grad_norm": 0.25602054595947266,
|
| 561 |
+
"learning_rate": 1.4019385127972135e-05,
|
| 562 |
+
"loss": 0.0399,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9086778736937755,
|
| 567 |
+
"grad_norm": 0.04758666455745697,
|
| 568 |
+
"learning_rate": 1.3943661971830987e-05,
|
| 569 |
+
"loss": 0.0232,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9200363471149478,
|
| 574 |
+
"grad_norm": 0.007415900472551584,
|
| 575 |
+
"learning_rate": 1.3867938815689839e-05,
|
| 576 |
+
"loss": 0.0254,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.93139482053612,
|
| 581 |
+
"grad_norm": 0.05941289663314819,
|
| 582 |
+
"learning_rate": 1.3792215659548692e-05,
|
| 583 |
+
"loss": 0.0182,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9427532939572921,
|
| 588 |
+
"grad_norm": 0.2857076823711395,
|
| 589 |
+
"learning_rate": 1.3716492503407543e-05,
|
| 590 |
+
"loss": 0.015,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9541117673784644,
|
| 595 |
+
"grad_norm": 6.7106852531433105,
|
| 596 |
+
"learning_rate": 1.3640769347266397e-05,
|
| 597 |
+
"loss": 0.0218,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9654702407996365,
|
| 602 |
+
"grad_norm": 2.165870189666748,
|
| 603 |
+
"learning_rate": 1.3565046191125247e-05,
|
| 604 |
+
"loss": 0.0477,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9768287142208087,
|
| 609 |
+
"grad_norm": 1.2232965230941772,
|
| 610 |
+
"learning_rate": 1.3489323034984098e-05,
|
| 611 |
+
"loss": 0.0227,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9881871876419809,
|
| 616 |
+
"grad_norm": 6.756147384643555,
|
| 617 |
+
"learning_rate": 1.3413599878842951e-05,
|
| 618 |
+
"loss": 0.0273,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9995456610631531,
|
| 623 |
+
"grad_norm": 0.07053057104349136,
|
| 624 |
+
"learning_rate": 1.3337876722701803e-05,
|
| 625 |
+
"loss": 0.0217,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0,
|
| 630 |
+
"eval_accuracy": 0.9839739413680781,
|
| 631 |
+
"eval_f1_macro": 0.982934850082554,
|
| 632 |
+
"eval_loss": 0.08169186860322952,
|
| 633 |
+
"eval_runtime": 25.3611,
|
| 634 |
+
"eval_samples_per_second": 302.629,
|
| 635 |
+
"eval_steps_per_second": 4.732,
|
| 636 |
+
"step": 4402
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.0109041344843253,
|
| 640 |
+
"grad_norm": 0.005929551087319851,
|
| 641 |
+
"learning_rate": 1.3262153566560656e-05,
|
| 642 |
+
"loss": 0.0101,
|
| 643 |
+
"step": 4450
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.0222626079054975,
|
| 647 |
+
"grad_norm": 0.011584239080548286,
|
| 648 |
+
"learning_rate": 1.3186430410419508e-05,
|
| 649 |
+
"loss": 0.012,
|
| 650 |
+
"step": 4500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.0336210813266697,
|
| 654 |
+
"grad_norm": 0.06345133483409882,
|
| 655 |
+
"learning_rate": 1.3110707254278358e-05,
|
| 656 |
+
"loss": 0.0295,
|
| 657 |
+
"step": 4550
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.044979554747842,
|
| 661 |
+
"grad_norm": 0.003701810259371996,
|
| 662 |
+
"learning_rate": 1.3034984098137211e-05,
|
| 663 |
+
"loss": 0.0096,
|
| 664 |
+
"step": 4600
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.056338028169014,
|
| 668 |
+
"grad_norm": 0.0013922312064096332,
|
| 669 |
+
"learning_rate": 1.2959260941996063e-05,
|
| 670 |
+
"loss": 0.0267,
|
| 671 |
+
"step": 4650
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.0676965015901863,
|
| 675 |
+
"grad_norm": 0.0026676456909626722,
|
| 676 |
+
"learning_rate": 1.2883537785854916e-05,
|
| 677 |
+
"loss": 0.0145,
|
| 678 |
+
"step": 4700
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.0790549750113585,
|
| 682 |
+
"grad_norm": 0.0031162630766630173,
|
| 683 |
+
"learning_rate": 1.2807814629713768e-05,
|
| 684 |
+
"loss": 0.0124,
|
| 685 |
+
"step": 4750
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.0904134484325307,
|
| 689 |
+
"grad_norm": 3.748222589492798,
|
| 690 |
+
"learning_rate": 1.273209147357262e-05,
|
| 691 |
+
"loss": 0.0074,
|
| 692 |
+
"step": 4800
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.1017719218537028,
|
| 696 |
+
"grad_norm": 0.0014477827353402972,
|
| 697 |
+
"learning_rate": 1.265636831743147e-05,
|
| 698 |
+
"loss": 0.0179,
|
| 699 |
+
"step": 4850
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.113130395274875,
|
| 703 |
+
"grad_norm": 4.411365985870361,
|
| 704 |
+
"learning_rate": 1.2580645161290324e-05,
|
| 705 |
+
"loss": 0.0181,
|
| 706 |
+
"step": 4900
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.1244888686960473,
|
| 710 |
+
"grad_norm": 0.05877981334924698,
|
| 711 |
+
"learning_rate": 1.2504922005149176e-05,
|
| 712 |
+
"loss": 0.013,
|
| 713 |
+
"step": 4950
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.1358473421172195,
|
| 717 |
+
"grad_norm": 0.999143123626709,
|
| 718 |
+
"learning_rate": 1.2429198849008029e-05,
|
| 719 |
+
"loss": 0.0114,
|
| 720 |
+
"step": 5000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.1472058155383915,
|
| 724 |
+
"grad_norm": 0.0030792481265962124,
|
| 725 |
+
"learning_rate": 1.2353475692866879e-05,
|
| 726 |
+
"loss": 0.0114,
|
| 727 |
+
"step": 5050
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.1585642889595638,
|
| 731 |
+
"grad_norm": 0.0014463861007243395,
|
| 732 |
+
"learning_rate": 1.227775253672573e-05,
|
| 733 |
+
"loss": 0.0188,
|
| 734 |
+
"step": 5100
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.169922762380736,
|
| 738 |
+
"grad_norm": 0.0017361458158120513,
|
| 739 |
+
"learning_rate": 1.2202029380584584e-05,
|
| 740 |
+
"loss": 0.0234,
|
| 741 |
+
"step": 5150
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.1812812358019082,
|
| 745 |
+
"grad_norm": 13.90465259552002,
|
| 746 |
+
"learning_rate": 1.2126306224443435e-05,
|
| 747 |
+
"loss": 0.0078,
|
| 748 |
+
"step": 5200
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.1926397092230805,
|
| 752 |
+
"grad_norm": 5.497283935546875,
|
| 753 |
+
"learning_rate": 1.2050583068302289e-05,
|
| 754 |
+
"loss": 0.0124,
|
| 755 |
+
"step": 5250
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.2039981826442525,
|
| 759 |
+
"grad_norm": 3.7859766483306885,
|
| 760 |
+
"learning_rate": 1.197485991216114e-05,
|
| 761 |
+
"loss": 0.0319,
|
| 762 |
+
"step": 5300
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.2153566560654248,
|
| 766 |
+
"grad_norm": 0.0024443278089165688,
|
| 767 |
+
"learning_rate": 1.1899136756019992e-05,
|
| 768 |
+
"loss": 0.0177,
|
| 769 |
+
"step": 5350
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.226715129486597,
|
| 773 |
+
"grad_norm": 0.20258040726184845,
|
| 774 |
+
"learning_rate": 1.1823413599878843e-05,
|
| 775 |
+
"loss": 0.009,
|
| 776 |
+
"step": 5400
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.2380736029077692,
|
| 780 |
+
"grad_norm": 0.0014519239775836468,
|
| 781 |
+
"learning_rate": 1.1747690443737697e-05,
|
| 782 |
+
"loss": 0.0069,
|
| 783 |
+
"step": 5450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.2494320763289415,
|
| 787 |
+
"grad_norm": 0.02450985088944435,
|
| 788 |
+
"learning_rate": 1.1671967287596548e-05,
|
| 789 |
+
"loss": 0.017,
|
| 790 |
+
"step": 5500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.2607905497501135,
|
| 794 |
+
"grad_norm": 0.004507457371801138,
|
| 795 |
+
"learning_rate": 1.1596244131455401e-05,
|
| 796 |
+
"loss": 0.01,
|
| 797 |
+
"step": 5550
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.2721490231712858,
|
| 801 |
+
"grad_norm": 9.089266777038574,
|
| 802 |
+
"learning_rate": 1.1520520975314251e-05,
|
| 803 |
+
"loss": 0.0382,
|
| 804 |
+
"step": 5600
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.283507496592458,
|
| 808 |
+
"grad_norm": 5.648477077484131,
|
| 809 |
+
"learning_rate": 1.1444797819173103e-05,
|
| 810 |
+
"loss": 0.0165,
|
| 811 |
+
"step": 5650
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.2948659700136302,
|
| 815 |
+
"grad_norm": 1.2645410299301147,
|
| 816 |
+
"learning_rate": 1.1369074663031956e-05,
|
| 817 |
+
"loss": 0.0163,
|
| 818 |
+
"step": 5700
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.3062244434348025,
|
| 822 |
+
"grad_norm": 0.0017288923263549805,
|
| 823 |
+
"learning_rate": 1.1293351506890808e-05,
|
| 824 |
+
"loss": 0.0202,
|
| 825 |
+
"step": 5750
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.3175829168559745,
|
| 829 |
+
"grad_norm": 0.00359937222674489,
|
| 830 |
+
"learning_rate": 1.1217628350749661e-05,
|
| 831 |
+
"loss": 0.0135,
|
| 832 |
+
"step": 5800
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.3289413902771468,
|
| 836 |
+
"grad_norm": 4.165374279022217,
|
| 837 |
+
"learning_rate": 1.1141905194608513e-05,
|
| 838 |
+
"loss": 0.0132,
|
| 839 |
+
"step": 5850
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.340299863698319,
|
| 843 |
+
"grad_norm": 0.0018008551560342312,
|
| 844 |
+
"learning_rate": 1.1066182038467364e-05,
|
| 845 |
+
"loss": 0.0112,
|
| 846 |
+
"step": 5900
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.351658337119491,
|
| 850 |
+
"grad_norm": 0.5573896765708923,
|
| 851 |
+
"learning_rate": 1.0990458882326216e-05,
|
| 852 |
+
"loss": 0.0221,
|
| 853 |
+
"step": 5950
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.3630168105406633,
|
| 857 |
+
"grad_norm": 1.456154704093933,
|
| 858 |
+
"learning_rate": 1.091473572618507e-05,
|
| 859 |
+
"loss": 0.011,
|
| 860 |
+
"step": 6000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.3743752839618355,
|
| 864 |
+
"grad_norm": 3.8196120262145996,
|
| 865 |
+
"learning_rate": 1.083901257004392e-05,
|
| 866 |
+
"loss": 0.0158,
|
| 867 |
+
"step": 6050
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.3857337573830077,
|
| 871 |
+
"grad_norm": 0.0017874937038868666,
|
| 872 |
+
"learning_rate": 1.0763289413902774e-05,
|
| 873 |
+
"loss": 0.0107,
|
| 874 |
+
"step": 6100
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.39709223080418,
|
| 878 |
+
"grad_norm": 0.0008583781309425831,
|
| 879 |
+
"learning_rate": 1.0687566257761624e-05,
|
| 880 |
+
"loss": 0.0031,
|
| 881 |
+
"step": 6150
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.408450704225352,
|
| 885 |
+
"grad_norm": 0.44672343134880066,
|
| 886 |
+
"learning_rate": 1.0611843101620476e-05,
|
| 887 |
+
"loss": 0.0223,
|
| 888 |
+
"step": 6200
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.4198091776465243,
|
| 892 |
+
"grad_norm": 0.009662467055022717,
|
| 893 |
+
"learning_rate": 1.0536119945479329e-05,
|
| 894 |
+
"loss": 0.0157,
|
| 895 |
+
"step": 6250
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.4311676510676965,
|
| 899 |
+
"grad_norm": 0.0007439041510224342,
|
| 900 |
+
"learning_rate": 1.046039678933818e-05,
|
| 901 |
+
"loss": 0.0165,
|
| 902 |
+
"step": 6300
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.4425261244888687,
|
| 906 |
+
"grad_norm": 0.001364586642012,
|
| 907 |
+
"learning_rate": 1.0384673633197034e-05,
|
| 908 |
+
"loss": 0.0054,
|
| 909 |
+
"step": 6350
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.453884597910041,
|
| 913 |
+
"grad_norm": 0.001398891326971352,
|
| 914 |
+
"learning_rate": 1.0308950477055884e-05,
|
| 915 |
+
"loss": 0.0087,
|
| 916 |
+
"step": 6400
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.465243071331213,
|
| 920 |
+
"grad_norm": 0.002500066999346018,
|
| 921 |
+
"learning_rate": 1.0233227320914735e-05,
|
| 922 |
+
"loss": 0.0117,
|
| 923 |
+
"step": 6450
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.4766015447523853,
|
| 927 |
+
"grad_norm": 0.0015706096310168505,
|
| 928 |
+
"learning_rate": 1.0157504164773588e-05,
|
| 929 |
+
"loss": 0.0173,
|
| 930 |
+
"step": 6500
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.4879600181735575,
|
| 934 |
+
"grad_norm": 0.0015295586781576276,
|
| 935 |
+
"learning_rate": 1.008178100863244e-05,
|
| 936 |
+
"loss": 0.0284,
|
| 937 |
+
"step": 6550
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.4993184915947297,
|
| 941 |
+
"grad_norm": 2.286747932434082,
|
| 942 |
+
"learning_rate": 1.0006057852491293e-05,
|
| 943 |
+
"loss": 0.011,
|
| 944 |
+
"step": 6600
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.510676965015902,
|
| 948 |
+
"grad_norm": 0.002311094431206584,
|
| 949 |
+
"learning_rate": 9.930334696350145e-06,
|
| 950 |
+
"loss": 0.0166,
|
| 951 |
+
"step": 6650
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.522035438437074,
|
| 955 |
+
"grad_norm": 0.0014053047634661198,
|
| 956 |
+
"learning_rate": 9.854611540208996e-06,
|
| 957 |
+
"loss": 0.0174,
|
| 958 |
+
"step": 6700
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.5333939118582463,
|
| 962 |
+
"grad_norm": 0.012581984512507915,
|
| 963 |
+
"learning_rate": 9.778888384067848e-06,
|
| 964 |
+
"loss": 0.0099,
|
| 965 |
+
"step": 6750
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.5447523852794185,
|
| 969 |
+
"grad_norm": 0.023738177493214607,
|
| 970 |
+
"learning_rate": 9.703165227926701e-06,
|
| 971 |
+
"loss": 0.0098,
|
| 972 |
+
"step": 6800
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.5561108587005905,
|
| 976 |
+
"grad_norm": 0.014806082472205162,
|
| 977 |
+
"learning_rate": 9.627442071785553e-06,
|
| 978 |
+
"loss": 0.017,
|
| 979 |
+
"step": 6850
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.567469332121763,
|
| 983 |
+
"grad_norm": 0.11848437041044235,
|
| 984 |
+
"learning_rate": 9.551718915644405e-06,
|
| 985 |
+
"loss": 0.0051,
|
| 986 |
+
"step": 6900
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.578827805542935,
|
| 990 |
+
"grad_norm": 2.107661485671997,
|
| 991 |
+
"learning_rate": 9.475995759503258e-06,
|
| 992 |
+
"loss": 0.0066,
|
| 993 |
+
"step": 6950
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.5901862789641072,
|
| 997 |
+
"grad_norm": 0.08532427251338959,
|
| 998 |
+
"learning_rate": 9.40027260336211e-06,
|
| 999 |
+
"loss": 0.0162,
|
| 1000 |
+
"step": 7000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.6015447523852795,
|
| 1004 |
+
"grad_norm": 0.0039615873247385025,
|
| 1005 |
+
"learning_rate": 9.324549447220961e-06,
|
| 1006 |
+
"loss": 0.0043,
|
| 1007 |
+
"step": 7050
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.6129032258064515,
|
| 1011 |
+
"grad_norm": 0.0013789839576929808,
|
| 1012 |
+
"learning_rate": 9.248826291079813e-06,
|
| 1013 |
+
"loss": 0.0127,
|
| 1014 |
+
"step": 7100
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.6242616992276238,
|
| 1018 |
+
"grad_norm": 9.550993919372559,
|
| 1019 |
+
"learning_rate": 9.173103134938664e-06,
|
| 1020 |
+
"loss": 0.0106,
|
| 1021 |
+
"step": 7150
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.635620172648796,
|
| 1025 |
+
"grad_norm": 0.0011268022935837507,
|
| 1026 |
+
"learning_rate": 9.097379978797517e-06,
|
| 1027 |
+
"loss": 0.009,
|
| 1028 |
+
"step": 7200
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.6469786460699682,
|
| 1032 |
+
"grad_norm": 0.0006976621225476265,
|
| 1033 |
+
"learning_rate": 9.021656822656369e-06,
|
| 1034 |
+
"loss": 0.015,
|
| 1035 |
+
"step": 7250
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.6583371194911405,
|
| 1039 |
+
"grad_norm": 0.0014887871220707893,
|
| 1040 |
+
"learning_rate": 8.94593366651522e-06,
|
| 1041 |
+
"loss": 0.015,
|
| 1042 |
+
"step": 7300
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.6696955929123125,
|
| 1046 |
+
"grad_norm": 0.0009298041695728898,
|
| 1047 |
+
"learning_rate": 8.870210510374074e-06,
|
| 1048 |
+
"loss": 0.0155,
|
| 1049 |
+
"step": 7350
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.6810540663334848,
|
| 1053 |
+
"grad_norm": 0.287706583738327,
|
| 1054 |
+
"learning_rate": 8.794487354232925e-06,
|
| 1055 |
+
"loss": 0.0116,
|
| 1056 |
+
"step": 7400
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.692412539754657,
|
| 1060 |
+
"grad_norm": 0.051804594695568085,
|
| 1061 |
+
"learning_rate": 8.718764198091777e-06,
|
| 1062 |
+
"loss": 0.0086,
|
| 1063 |
+
"step": 7450
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 1.703771013175829,
|
| 1067 |
+
"grad_norm": 1.3675575256347656,
|
| 1068 |
+
"learning_rate": 8.643041041950629e-06,
|
| 1069 |
+
"loss": 0.023,
|
| 1070 |
+
"step": 7500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.7151294865970015,
|
| 1074 |
+
"grad_norm": 0.0012162342900410295,
|
| 1075 |
+
"learning_rate": 8.56731788580948e-06,
|
| 1076 |
+
"loss": 0.0081,
|
| 1077 |
+
"step": 7550
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.7264879600181735,
|
| 1081 |
+
"grad_norm": 0.0013599529629573226,
|
| 1082 |
+
"learning_rate": 8.491594729668334e-06,
|
| 1083 |
+
"loss": 0.0075,
|
| 1084 |
+
"step": 7600
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.7378464334393458,
|
| 1088 |
+
"grad_norm": 0.0011247453512623906,
|
| 1089 |
+
"learning_rate": 8.415871573527185e-06,
|
| 1090 |
+
"loss": 0.0079,
|
| 1091 |
+
"step": 7650
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.749204906860518,
|
| 1095 |
+
"grad_norm": 0.003529078559949994,
|
| 1096 |
+
"learning_rate": 8.340148417386037e-06,
|
| 1097 |
+
"loss": 0.0053,
|
| 1098 |
+
"step": 7700
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.76056338028169,
|
| 1102 |
+
"grad_norm": 13.674657821655273,
|
| 1103 |
+
"learning_rate": 8.26442526124489e-06,
|
| 1104 |
+
"loss": 0.0058,
|
| 1105 |
+
"step": 7750
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.7719218537028625,
|
| 1109 |
+
"grad_norm": 0.0018937140703201294,
|
| 1110 |
+
"learning_rate": 8.188702105103742e-06,
|
| 1111 |
+
"loss": 0.0073,
|
| 1112 |
+
"step": 7800
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.7832803271240345,
|
| 1116 |
+
"grad_norm": 0.0012737379875034094,
|
| 1117 |
+
"learning_rate": 8.112978948962593e-06,
|
| 1118 |
+
"loss": 0.0067,
|
| 1119 |
+
"step": 7850
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.7946388005452067,
|
| 1123 |
+
"grad_norm": 0.0010197096271440387,
|
| 1124 |
+
"learning_rate": 8.037255792821446e-06,
|
| 1125 |
+
"loss": 0.0057,
|
| 1126 |
+
"step": 7900
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.805997273966379,
|
| 1130 |
+
"grad_norm": 0.009366828948259354,
|
| 1131 |
+
"learning_rate": 7.961532636680296e-06,
|
| 1132 |
+
"loss": 0.026,
|
| 1133 |
+
"step": 7950
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.817355747387551,
|
| 1137 |
+
"grad_norm": 0.012473216280341148,
|
| 1138 |
+
"learning_rate": 7.88580948053915e-06,
|
| 1139 |
+
"loss": 0.024,
|
| 1140 |
+
"step": 8000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.8287142208087233,
|
| 1144 |
+
"grad_norm": 0.26876014471054077,
|
| 1145 |
+
"learning_rate": 7.810086324398001e-06,
|
| 1146 |
+
"loss": 0.0079,
|
| 1147 |
+
"step": 8050
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.8400726942298955,
|
| 1151 |
+
"grad_norm": 0.0026707984507083893,
|
| 1152 |
+
"learning_rate": 7.734363168256853e-06,
|
| 1153 |
+
"loss": 0.0149,
|
| 1154 |
+
"step": 8100
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.8514311676510677,
|
| 1158 |
+
"grad_norm": 0.036166541278362274,
|
| 1159 |
+
"learning_rate": 7.658640012115706e-06,
|
| 1160 |
+
"loss": 0.0062,
|
| 1161 |
+
"step": 8150
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.86278964107224,
|
| 1165 |
+
"grad_norm": 0.013438834808766842,
|
| 1166 |
+
"learning_rate": 7.582916855974558e-06,
|
| 1167 |
+
"loss": 0.0047,
|
| 1168 |
+
"step": 8200
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.874148114493412,
|
| 1172 |
+
"grad_norm": 0.0015038993442431092,
|
| 1173 |
+
"learning_rate": 7.507193699833409e-06,
|
| 1174 |
+
"loss": 0.0155,
|
| 1175 |
+
"step": 8250
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.8855065879145843,
|
| 1179 |
+
"grad_norm": 0.0006626308313570917,
|
| 1180 |
+
"learning_rate": 7.431470543692262e-06,
|
| 1181 |
+
"loss": 0.0014,
|
| 1182 |
+
"step": 8300
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.8968650613357565,
|
| 1186 |
+
"grad_norm": 0.0032690023072063923,
|
| 1187 |
+
"learning_rate": 7.355747387551114e-06,
|
| 1188 |
+
"loss": 0.0103,
|
| 1189 |
+
"step": 8350
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.9082235347569285,
|
| 1193 |
+
"grad_norm": 0.0008181309676729143,
|
| 1194 |
+
"learning_rate": 7.280024231409966e-06,
|
| 1195 |
+
"loss": 0.0184,
|
| 1196 |
+
"step": 8400
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.919582008178101,
|
| 1200 |
+
"grad_norm": 0.0026349183171987534,
|
| 1201 |
+
"learning_rate": 7.204301075268818e-06,
|
| 1202 |
+
"loss": 0.0074,
|
| 1203 |
+
"step": 8450
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.930940481599273,
|
| 1207 |
+
"grad_norm": 0.0025627773720771074,
|
| 1208 |
+
"learning_rate": 7.12857791912767e-06,
|
| 1209 |
+
"loss": 0.0061,
|
| 1210 |
+
"step": 8500
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.9422989550204453,
|
| 1214 |
+
"grad_norm": 0.000963448139373213,
|
| 1215 |
+
"learning_rate": 7.052854762986522e-06,
|
| 1216 |
+
"loss": 0.0049,
|
| 1217 |
+
"step": 8550
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.9536574284416175,
|
| 1221 |
+
"grad_norm": 0.0005609341314993799,
|
| 1222 |
+
"learning_rate": 6.977131606845375e-06,
|
| 1223 |
+
"loss": 0.0007,
|
| 1224 |
+
"step": 8600
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.9650159018627895,
|
| 1228 |
+
"grad_norm": 0.0011694286949932575,
|
| 1229 |
+
"learning_rate": 6.901408450704225e-06,
|
| 1230 |
+
"loss": 0.0017,
|
| 1231 |
+
"step": 8650
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.976374375283962,
|
| 1235 |
+
"grad_norm": 0.0010692242067307234,
|
| 1236 |
+
"learning_rate": 6.825685294563078e-06,
|
| 1237 |
+
"loss": 0.0115,
|
| 1238 |
+
"step": 8700
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.987732848705134,
|
| 1242 |
+
"grad_norm": 0.05440627783536911,
|
| 1243 |
+
"learning_rate": 6.74996213842193e-06,
|
| 1244 |
+
"loss": 0.0068,
|
| 1245 |
+
"step": 8750
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.9990913221263062,
|
| 1249 |
+
"grad_norm": 0.004324722569435835,
|
| 1250 |
+
"learning_rate": 6.674238982280782e-06,
|
| 1251 |
+
"loss": 0.0147,
|
| 1252 |
+
"step": 8800
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.0,
|
| 1256 |
+
"eval_accuracy": 0.9846254071661238,
|
| 1257 |
+
"eval_f1_macro": 0.9835472402504412,
|
| 1258 |
+
"eval_loss": 0.1140478253364563,
|
| 1259 |
+
"eval_runtime": 24.9,
|
| 1260 |
+
"eval_samples_per_second": 308.233,
|
| 1261 |
+
"eval_steps_per_second": 4.819,
|
| 1262 |
+
"step": 8804
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.0104497955474785,
|
| 1266 |
+
"grad_norm": 0.000489537778776139,
|
| 1267 |
+
"learning_rate": 6.598515826139634e-06,
|
| 1268 |
+
"loss": 0.0007,
|
| 1269 |
+
"step": 8850
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.0218082689686505,
|
| 1273 |
+
"grad_norm": 0.0013550950679928064,
|
| 1274 |
+
"learning_rate": 6.522792669998486e-06,
|
| 1275 |
+
"loss": 0.0027,
|
| 1276 |
+
"step": 8900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.033166742389823,
|
| 1280 |
+
"grad_norm": 0.0009673606837168336,
|
| 1281 |
+
"learning_rate": 6.447069513857338e-06,
|
| 1282 |
+
"loss": 0.0091,
|
| 1283 |
+
"step": 8950
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.044525215810995,
|
| 1287 |
+
"grad_norm": 0.0004022994253318757,
|
| 1288 |
+
"learning_rate": 6.371346357716191e-06,
|
| 1289 |
+
"loss": 0.0003,
|
| 1290 |
+
"step": 9000
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.055883689232167,
|
| 1294 |
+
"grad_norm": 0.0007892374997027218,
|
| 1295 |
+
"learning_rate": 6.2956232015750415e-06,
|
| 1296 |
+
"loss": 0.0024,
|
| 1297 |
+
"step": 9050
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.0672421626533395,
|
| 1301 |
+
"grad_norm": 0.012260637246072292,
|
| 1302 |
+
"learning_rate": 6.219900045433894e-06,
|
| 1303 |
+
"loss": 0.0016,
|
| 1304 |
+
"step": 9100
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.0786006360745115,
|
| 1308 |
+
"grad_norm": 0.002542909001931548,
|
| 1309 |
+
"learning_rate": 6.144176889292746e-06,
|
| 1310 |
+
"loss": 0.0001,
|
| 1311 |
+
"step": 9150
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.089959109495684,
|
| 1315 |
+
"grad_norm": 0.002916930941864848,
|
| 1316 |
+
"learning_rate": 6.068453733151598e-06,
|
| 1317 |
+
"loss": 0.0073,
|
| 1318 |
+
"step": 9200
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.101317582916856,
|
| 1322 |
+
"grad_norm": 0.0003816105308942497,
|
| 1323 |
+
"learning_rate": 5.99273057701045e-06,
|
| 1324 |
+
"loss": 0.0089,
|
| 1325 |
+
"step": 9250
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.112676056338028,
|
| 1329 |
+
"grad_norm": 0.0005522597930394113,
|
| 1330 |
+
"learning_rate": 5.917007420869302e-06,
|
| 1331 |
+
"loss": 0.0049,
|
| 1332 |
+
"step": 9300
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.1240345297592005,
|
| 1336 |
+
"grad_norm": 0.0011015296913683414,
|
| 1337 |
+
"learning_rate": 5.841284264728154e-06,
|
| 1338 |
+
"loss": 0.0066,
|
| 1339 |
+
"step": 9350
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.1353930031803725,
|
| 1343 |
+
"grad_norm": 0.00041281242738477886,
|
| 1344 |
+
"learning_rate": 5.765561108587007e-06,
|
| 1345 |
+
"loss": 0.0019,
|
| 1346 |
+
"step": 9400
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.146751476601545,
|
| 1350 |
+
"grad_norm": 0.0007952914456836879,
|
| 1351 |
+
"learning_rate": 5.689837952445858e-06,
|
| 1352 |
+
"loss": 0.0036,
|
| 1353 |
+
"step": 9450
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.158109950022717,
|
| 1357 |
+
"grad_norm": 0.0004673805378843099,
|
| 1358 |
+
"learning_rate": 5.614114796304711e-06,
|
| 1359 |
+
"loss": 0.0042,
|
| 1360 |
+
"step": 9500
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.169468423443889,
|
| 1364 |
+
"grad_norm": 0.00038412591675296426,
|
| 1365 |
+
"learning_rate": 5.538391640163563e-06,
|
| 1366 |
+
"loss": 0.0001,
|
| 1367 |
+
"step": 9550
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.1808268968650615,
|
| 1371 |
+
"grad_norm": 0.00038422050420194864,
|
| 1372 |
+
"learning_rate": 5.462668484022414e-06,
|
| 1373 |
+
"loss": 0.0093,
|
| 1374 |
+
"step": 9600
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.1921853702862335,
|
| 1378 |
+
"grad_norm": 0.0006754286587238312,
|
| 1379 |
+
"learning_rate": 5.3869453278812665e-06,
|
| 1380 |
+
"loss": 0.0028,
|
| 1381 |
+
"step": 9650
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.2035438437074055,
|
| 1385 |
+
"grad_norm": 0.0004887759569101036,
|
| 1386 |
+
"learning_rate": 5.311222171740119e-06,
|
| 1387 |
+
"loss": 0.0051,
|
| 1388 |
+
"step": 9700
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.214902317128578,
|
| 1392 |
+
"grad_norm": 0.05471280589699745,
|
| 1393 |
+
"learning_rate": 5.2354990155989705e-06,
|
| 1394 |
+
"loss": 0.0059,
|
| 1395 |
+
"step": 9750
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.22626079054975,
|
| 1399 |
+
"grad_norm": 0.0008195925038307905,
|
| 1400 |
+
"learning_rate": 5.159775859457823e-06,
|
| 1401 |
+
"loss": 0.0036,
|
| 1402 |
+
"step": 9800
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.2376192639709225,
|
| 1406 |
+
"grad_norm": 0.000433308829087764,
|
| 1407 |
+
"learning_rate": 5.0840527033166745e-06,
|
| 1408 |
+
"loss": 0.0022,
|
| 1409 |
+
"step": 9850
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.2489777373920945,
|
| 1413 |
+
"grad_norm": 0.012868039309978485,
|
| 1414 |
+
"learning_rate": 5.008329547175527e-06,
|
| 1415 |
+
"loss": 0.0051,
|
| 1416 |
+
"step": 9900
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.2603362108132665,
|
| 1420 |
+
"grad_norm": 0.5331919193267822,
|
| 1421 |
+
"learning_rate": 4.9326063910343785e-06,
|
| 1422 |
+
"loss": 0.0115,
|
| 1423 |
+
"step": 9950
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.271694684234439,
|
| 1427 |
+
"grad_norm": 0.0005174391553737223,
|
| 1428 |
+
"learning_rate": 4.856883234893231e-06,
|
| 1429 |
+
"loss": 0.0007,
|
| 1430 |
+
"step": 10000
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.283053157655611,
|
| 1434 |
+
"grad_norm": 0.00032180239213630557,
|
| 1435 |
+
"learning_rate": 4.7811600787520825e-06,
|
| 1436 |
+
"loss": 0.0095,
|
| 1437 |
+
"step": 10050
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.294411631076783,
|
| 1441 |
+
"grad_norm": 0.07410291582345963,
|
| 1442 |
+
"learning_rate": 4.705436922610935e-06,
|
| 1443 |
+
"loss": 0.008,
|
| 1444 |
+
"step": 10100
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.3057701044979555,
|
| 1448 |
+
"grad_norm": 0.024364503100514412,
|
| 1449 |
+
"learning_rate": 4.6297137664697866e-06,
|
| 1450 |
+
"loss": 0.0026,
|
| 1451 |
+
"step": 10150
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.3171285779191275,
|
| 1455 |
+
"grad_norm": 0.00038883680826984346,
|
| 1456 |
+
"learning_rate": 4.553990610328639e-06,
|
| 1457 |
+
"loss": 0.0026,
|
| 1458 |
+
"step": 10200
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.3284870513403,
|
| 1462 |
+
"grad_norm": 0.0038193499203771353,
|
| 1463 |
+
"learning_rate": 4.478267454187491e-06,
|
| 1464 |
+
"loss": 0.0001,
|
| 1465 |
+
"step": 10250
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.339845524761472,
|
| 1469 |
+
"grad_norm": 0.0023336990270763636,
|
| 1470 |
+
"learning_rate": 4.402544298046343e-06,
|
| 1471 |
+
"loss": 0.0084,
|
| 1472 |
+
"step": 10300
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.351203998182644,
|
| 1476 |
+
"grad_norm": 0.04238196834921837,
|
| 1477 |
+
"learning_rate": 4.326821141905195e-06,
|
| 1478 |
+
"loss": 0.0033,
|
| 1479 |
+
"step": 10350
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.3625624716038165,
|
| 1483 |
+
"grad_norm": 0.000569637690205127,
|
| 1484 |
+
"learning_rate": 4.251097985764047e-06,
|
| 1485 |
+
"loss": 0.0012,
|
| 1486 |
+
"step": 10400
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.3739209450249885,
|
| 1490 |
+
"grad_norm": 0.00034202905953861773,
|
| 1491 |
+
"learning_rate": 4.1753748296228995e-06,
|
| 1492 |
+
"loss": 0.0036,
|
| 1493 |
+
"step": 10450
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.385279418446161,
|
| 1497 |
+
"grad_norm": 0.00034673314075917006,
|
| 1498 |
+
"learning_rate": 4.099651673481751e-06,
|
| 1499 |
+
"loss": 0.0013,
|
| 1500 |
+
"step": 10500
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.396637891867333,
|
| 1504 |
+
"grad_norm": 0.0012820770498365164,
|
| 1505 |
+
"learning_rate": 4.023928517340603e-06,
|
| 1506 |
+
"loss": 0.0006,
|
| 1507 |
+
"step": 10550
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.407996365288505,
|
| 1511 |
+
"grad_norm": 0.0017663290491327643,
|
| 1512 |
+
"learning_rate": 3.948205361199455e-06,
|
| 1513 |
+
"loss": 0.0002,
|
| 1514 |
+
"step": 10600
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.4193548387096775,
|
| 1518 |
+
"grad_norm": 13.78622817993164,
|
| 1519 |
+
"learning_rate": 3.8724822050583075e-06,
|
| 1520 |
+
"loss": 0.0029,
|
| 1521 |
+
"step": 10650
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.4307133121308495,
|
| 1525 |
+
"grad_norm": 0.00041380742914043367,
|
| 1526 |
+
"learning_rate": 3.796759048917159e-06,
|
| 1527 |
+
"loss": 0.0051,
|
| 1528 |
+
"step": 10700
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.442071785552022,
|
| 1532 |
+
"grad_norm": 0.0015727384015917778,
|
| 1533 |
+
"learning_rate": 3.721035892776011e-06,
|
| 1534 |
+
"loss": 0.0002,
|
| 1535 |
+
"step": 10750
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.453430258973194,
|
| 1539 |
+
"grad_norm": 0.00039928112528286874,
|
| 1540 |
+
"learning_rate": 3.6453127366348636e-06,
|
| 1541 |
+
"loss": 0.0041,
|
| 1542 |
+
"step": 10800
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.464788732394366,
|
| 1546 |
+
"grad_norm": 0.0007231036433950067,
|
| 1547 |
+
"learning_rate": 3.569589580493715e-06,
|
| 1548 |
+
"loss": 0.0013,
|
| 1549 |
+
"step": 10850
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.4761472058155385,
|
| 1553 |
+
"grad_norm": 0.0004043302033096552,
|
| 1554 |
+
"learning_rate": 3.493866424352567e-06,
|
| 1555 |
+
"loss": 0.0038,
|
| 1556 |
+
"step": 10900
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.4875056792367105,
|
| 1560 |
+
"grad_norm": 0.00035005921381525695,
|
| 1561 |
+
"learning_rate": 3.418143268211419e-06,
|
| 1562 |
+
"loss": 0.0042,
|
| 1563 |
+
"step": 10950
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.498864152657883,
|
| 1567 |
+
"grad_norm": 13.098333358764648,
|
| 1568 |
+
"learning_rate": 3.3424201120702716e-06,
|
| 1569 |
+
"loss": 0.0039,
|
| 1570 |
+
"step": 11000
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.510222626079055,
|
| 1574 |
+
"grad_norm": 0.0030333756003528833,
|
| 1575 |
+
"learning_rate": 3.2666969559291232e-06,
|
| 1576 |
+
"loss": 0.0002,
|
| 1577 |
+
"step": 11050
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.521581099500227,
|
| 1581 |
+
"grad_norm": 0.0002801103692036122,
|
| 1582 |
+
"learning_rate": 3.1909737997879752e-06,
|
| 1583 |
+
"loss": 0.0003,
|
| 1584 |
+
"step": 11100
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.5329395729213995,
|
| 1588 |
+
"grad_norm": 0.5628141164779663,
|
| 1589 |
+
"learning_rate": 3.1152506436468277e-06,
|
| 1590 |
+
"loss": 0.0064,
|
| 1591 |
+
"step": 11150
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.5442980463425715,
|
| 1595 |
+
"grad_norm": 0.002491287887096405,
|
| 1596 |
+
"learning_rate": 3.0395274875056797e-06,
|
| 1597 |
+
"loss": 0.0037,
|
| 1598 |
+
"step": 11200
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.555656519763744,
|
| 1602 |
+
"grad_norm": 0.002808187622576952,
|
| 1603 |
+
"learning_rate": 2.9638043313645317e-06,
|
| 1604 |
+
"loss": 0.0028,
|
| 1605 |
+
"step": 11250
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.567014993184916,
|
| 1609 |
+
"grad_norm": 0.043582722544670105,
|
| 1610 |
+
"learning_rate": 2.8880811752233833e-06,
|
| 1611 |
+
"loss": 0.002,
|
| 1612 |
+
"step": 11300
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.578373466606088,
|
| 1616 |
+
"grad_norm": 0.00028100161580368876,
|
| 1617 |
+
"learning_rate": 2.8123580190822357e-06,
|
| 1618 |
+
"loss": 0.0072,
|
| 1619 |
+
"step": 11350
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.5897319400272605,
|
| 1623 |
+
"grad_norm": 0.0003854044189210981,
|
| 1624 |
+
"learning_rate": 2.7366348629410877e-06,
|
| 1625 |
+
"loss": 0.0085,
|
| 1626 |
+
"step": 11400
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.6010904134484325,
|
| 1630 |
+
"grad_norm": 41.185237884521484,
|
| 1631 |
+
"learning_rate": 2.6609117067999397e-06,
|
| 1632 |
+
"loss": 0.0031,
|
| 1633 |
+
"step": 11450
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.612448886869605,
|
| 1637 |
+
"grad_norm": 0.0006349310860969126,
|
| 1638 |
+
"learning_rate": 2.5851885506587913e-06,
|
| 1639 |
+
"loss": 0.0001,
|
| 1640 |
+
"step": 11500
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.623807360290777,
|
| 1644 |
+
"grad_norm": 0.0002767475671134889,
|
| 1645 |
+
"learning_rate": 2.5094653945176438e-06,
|
| 1646 |
+
"loss": 0.0065,
|
| 1647 |
+
"step": 11550
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.635165833711949,
|
| 1651 |
+
"grad_norm": 0.002331246854737401,
|
| 1652 |
+
"learning_rate": 2.4337422383764958e-06,
|
| 1653 |
+
"loss": 0.006,
|
| 1654 |
+
"step": 11600
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.646524307133121,
|
| 1658 |
+
"grad_norm": 0.0015208119293674827,
|
| 1659 |
+
"learning_rate": 2.3580190822353478e-06,
|
| 1660 |
+
"loss": 0.0037,
|
| 1661 |
+
"step": 11650
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.6578827805542935,
|
| 1665 |
+
"grad_norm": 0.026821589097380638,
|
| 1666 |
+
"learning_rate": 2.2822959260942e-06,
|
| 1667 |
+
"loss": 0.0093,
|
| 1668 |
+
"step": 11700
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.669241253975466,
|
| 1672 |
+
"grad_norm": 5.861845016479492,
|
| 1673 |
+
"learning_rate": 2.206572769953052e-06,
|
| 1674 |
+
"loss": 0.0003,
|
| 1675 |
+
"step": 11750
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.680599727396638,
|
| 1679 |
+
"grad_norm": 0.00030583186889998615,
|
| 1680 |
+
"learning_rate": 2.130849613811904e-06,
|
| 1681 |
+
"loss": 0.0015,
|
| 1682 |
+
"step": 11800
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.69195820081781,
|
| 1686 |
+
"grad_norm": 0.004688043612986803,
|
| 1687 |
+
"learning_rate": 2.055126457670756e-06,
|
| 1688 |
+
"loss": 0.0069,
|
| 1689 |
+
"step": 11850
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.703316674238982,
|
| 1693 |
+
"grad_norm": 0.0014823823003098369,
|
| 1694 |
+
"learning_rate": 1.979403301529608e-06,
|
| 1695 |
+
"loss": 0.0011,
|
| 1696 |
+
"step": 11900
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.7146751476601545,
|
| 1700 |
+
"grad_norm": 0.0003014960384462029,
|
| 1701 |
+
"learning_rate": 1.9036801453884599e-06,
|
| 1702 |
+
"loss": 0.0001,
|
| 1703 |
+
"step": 11950
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.7260336210813265,
|
| 1707 |
+
"grad_norm": 0.0012561273761093616,
|
| 1708 |
+
"learning_rate": 1.827956989247312e-06,
|
| 1709 |
+
"loss": 0.0029,
|
| 1710 |
+
"step": 12000
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.737392094502499,
|
| 1714 |
+
"grad_norm": 0.08546403795480728,
|
| 1715 |
+
"learning_rate": 1.7522338331061639e-06,
|
| 1716 |
+
"loss": 0.0027,
|
| 1717 |
+
"step": 12050
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.748750567923671,
|
| 1721 |
+
"grad_norm": 0.0004358178994152695,
|
| 1722 |
+
"learning_rate": 1.676510676965016e-06,
|
| 1723 |
+
"loss": 0.0002,
|
| 1724 |
+
"step": 12100
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.760109041344843,
|
| 1728 |
+
"grad_norm": 0.0006170666310936213,
|
| 1729 |
+
"learning_rate": 1.600787520823868e-06,
|
| 1730 |
+
"loss": 0.0035,
|
| 1731 |
+
"step": 12150
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.7714675147660155,
|
| 1735 |
+
"grad_norm": 0.00022272793285083026,
|
| 1736 |
+
"learning_rate": 1.5250643646827201e-06,
|
| 1737 |
+
"loss": 0.0005,
|
| 1738 |
+
"step": 12200
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.7828259881871875,
|
| 1742 |
+
"grad_norm": 0.0002821196976583451,
|
| 1743 |
+
"learning_rate": 1.449341208541572e-06,
|
| 1744 |
+
"loss": 0.0003,
|
| 1745 |
+
"step": 12250
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.79418446160836,
|
| 1749 |
+
"grad_norm": 0.0002386348060099408,
|
| 1750 |
+
"learning_rate": 1.3736180524004241e-06,
|
| 1751 |
+
"loss": 0.0009,
|
| 1752 |
+
"step": 12300
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.805542935029532,
|
| 1756 |
+
"grad_norm": 0.05056820809841156,
|
| 1757 |
+
"learning_rate": 1.2978948962592762e-06,
|
| 1758 |
+
"loss": 0.0016,
|
| 1759 |
+
"step": 12350
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.816901408450704,
|
| 1763 |
+
"grad_norm": 0.0051028188318014145,
|
| 1764 |
+
"learning_rate": 1.2221717401181282e-06,
|
| 1765 |
+
"loss": 0.0005,
|
| 1766 |
+
"step": 12400
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.8282598818718765,
|
| 1770 |
+
"grad_norm": 0.00031195359770208597,
|
| 1771 |
+
"learning_rate": 1.1464485839769802e-06,
|
| 1772 |
+
"loss": 0.0047,
|
| 1773 |
+
"step": 12450
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.8396183552930485,
|
| 1777 |
+
"grad_norm": 0.0005304196383804083,
|
| 1778 |
+
"learning_rate": 1.0707254278358322e-06,
|
| 1779 |
+
"loss": 0.0005,
|
| 1780 |
+
"step": 12500
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.850976828714221,
|
| 1784 |
+
"grad_norm": 0.004895700607448816,
|
| 1785 |
+
"learning_rate": 9.950022716946842e-07,
|
| 1786 |
+
"loss": 0.0023,
|
| 1787 |
+
"step": 12550
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.862335302135393,
|
| 1791 |
+
"grad_norm": 0.00021093177201692015,
|
| 1792 |
+
"learning_rate": 9.192791155535363e-07,
|
| 1793 |
+
"loss": 0.0002,
|
| 1794 |
+
"step": 12600
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.873693775556565,
|
| 1798 |
+
"grad_norm": 0.00027342038811184466,
|
| 1799 |
+
"learning_rate": 8.435559594123883e-07,
|
| 1800 |
+
"loss": 0.0002,
|
| 1801 |
+
"step": 12650
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.8850522489777375,
|
| 1805 |
+
"grad_norm": 0.0002328462287550792,
|
| 1806 |
+
"learning_rate": 7.678328032712403e-07,
|
| 1807 |
+
"loss": 0.0001,
|
| 1808 |
+
"step": 12700
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.8964107223989095,
|
| 1812 |
+
"grad_norm": 0.00026081790565513074,
|
| 1813 |
+
"learning_rate": 6.921096471300924e-07,
|
| 1814 |
+
"loss": 0.0008,
|
| 1815 |
+
"step": 12750
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.907769195820082,
|
| 1819 |
+
"grad_norm": 0.07156021147966385,
|
| 1820 |
+
"learning_rate": 6.163864909889445e-07,
|
| 1821 |
+
"loss": 0.0015,
|
| 1822 |
+
"step": 12800
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.919127669241254,
|
| 1826 |
+
"grad_norm": 0.002825228963047266,
|
| 1827 |
+
"learning_rate": 5.406633348477965e-07,
|
| 1828 |
+
"loss": 0.0001,
|
| 1829 |
+
"step": 12850
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.930486142662426,
|
| 1833 |
+
"grad_norm": 0.0006366794114001095,
|
| 1834 |
+
"learning_rate": 4.6494017870664856e-07,
|
| 1835 |
+
"loss": 0.0049,
|
| 1836 |
+
"step": 12900
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.9418446160835985,
|
| 1840 |
+
"grad_norm": 3.086198329925537,
|
| 1841 |
+
"learning_rate": 3.8921702256550057e-07,
|
| 1842 |
+
"loss": 0.0009,
|
| 1843 |
+
"step": 12950
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.9532030895047705,
|
| 1847 |
+
"grad_norm": 0.000288445531623438,
|
| 1848 |
+
"learning_rate": 3.134938664243526e-07,
|
| 1849 |
+
"loss": 0.0003,
|
| 1850 |
+
"step": 13000
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.964561562925943,
|
| 1854 |
+
"grad_norm": 0.00021304447727743536,
|
| 1855 |
+
"learning_rate": 2.3777071028320462e-07,
|
| 1856 |
+
"loss": 0.0006,
|
| 1857 |
+
"step": 13050
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.975920036347115,
|
| 1861 |
+
"grad_norm": 0.0010498821502551436,
|
| 1862 |
+
"learning_rate": 1.6204755414205666e-07,
|
| 1863 |
+
"loss": 0.0001,
|
| 1864 |
+
"step": 13100
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.987278509768287,
|
| 1868 |
+
"grad_norm": 0.00040187168633565307,
|
| 1869 |
+
"learning_rate": 8.632439800090868e-08,
|
| 1870 |
+
"loss": 0.0005,
|
| 1871 |
+
"step": 13150
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.9986369831894595,
|
| 1875 |
+
"grad_norm": 0.0003258317010477185,
|
| 1876 |
+
"learning_rate": 1.0601241859760717e-08,
|
| 1877 |
+
"loss": 0.0092,
|
| 1878 |
+
"step": 13200
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 3.0,
|
| 1882 |
+
"eval_accuracy": 0.9877524429967427,
|
| 1883 |
+
"eval_f1_macro": 0.9868791709426586,
|
| 1884 |
+
"eval_loss": 0.09756067395210266,
|
| 1885 |
+
"eval_runtime": 25.8171,
|
| 1886 |
+
"eval_samples_per_second": 297.284,
|
| 1887 |
+
"eval_steps_per_second": 4.648,
|
| 1888 |
+
"step": 13206
|
| 1889 |
+
}
|
| 1890 |
+
],
|
| 1891 |
+
"logging_steps": 50,
|
| 1892 |
+
"max_steps": 13206,
|
| 1893 |
+
"num_input_tokens_seen": 0,
|
| 1894 |
+
"num_train_epochs": 3,
|
| 1895 |
+
"save_steps": 500,
|
| 1896 |
+
"stateful_callbacks": {
|
| 1897 |
+
"TrainerControl": {
|
| 1898 |
+
"args": {
|
| 1899 |
+
"should_epoch_stop": false,
|
| 1900 |
+
"should_evaluate": false,
|
| 1901 |
+
"should_log": false,
|
| 1902 |
+
"should_save": true,
|
| 1903 |
+
"should_training_stop": true
|
| 1904 |
+
},
|
| 1905 |
+
"attributes": {}
|
| 1906 |
+
}
|
| 1907 |
+
},
|
| 1908 |
+
"total_flos": 2.341359158497128e+16,
|
| 1909 |
+
"train_batch_size": 32,
|
| 1910 |
+
"trial_name": null,
|
| 1911 |
+
"trial_params": null
|
| 1912 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12363598219c475a992e33836dc3f07942edf849a78bdabd0ecd6ebfea291e52
|
| 3 |
+
size 5496
|