Upload 13 files
Browse files- added_tokens.json +3 -0
- config.json +45 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- trainer_state.json +1483 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"id2label": {
|
| 10 |
+
"0": "issue",
|
| 11 |
+
"1": "symptom",
|
| 12 |
+
"2": "fix"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"fix": 2,
|
| 18 |
+
"issue": 0,
|
| 19 |
+
"symptom": 1
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-07,
|
| 22 |
+
"legacy": true,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"max_relative_positions": -1,
|
| 25 |
+
"model_type": "deberta-v2",
|
| 26 |
+
"norm_rel_ebd": "layer_norm",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_dropout": 0,
|
| 31 |
+
"pooler_hidden_act": "gelu",
|
| 32 |
+
"pooler_hidden_size": 768,
|
| 33 |
+
"pos_att_type": [
|
| 34 |
+
"p2c",
|
| 35 |
+
"c2p"
|
| 36 |
+
],
|
| 37 |
+
"position_biased_input": false,
|
| 38 |
+
"position_buckets": 256,
|
| 39 |
+
"relative_attention": true,
|
| 40 |
+
"share_att_key": true,
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.52.4",
|
| 43 |
+
"type_vocab_size": 0,
|
| 44 |
+
"vocab_size": 128100
|
| 45 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ea662fd1fcee4780eb1474a79426adbc9a19d493fa3cb45f150633781fbef16
|
| 3 |
+
size 737722356
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def67e5504cb9af0aa70de181ade38f3e0455a22e48e2a98cd24fd84d5d325b8
|
| 3 |
+
size 1475565003
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7b11355dc0869a31f784b85283fd78024a689960d240e4100873bfbb41919ed
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bbeb17cae9279bcd1516d9870f8465924185888f2efcdfe87cef2478365ff6c
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2759d85db0ab211dcd810d2d36191a9ec639a3802f52d4b57d750289e7b2687d
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 +1,1483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2667,
|
| 3 |
+
"best_metric": 0.8418311044589408,
|
| 4 |
+
"best_model_checkpoint": "3class_classification_results/run_20250610_161638/checkpoints/checkpoint-2667",
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8890,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.056274620146314014,
|
| 14 |
+
"grad_norm": 1.2899854183197021,
|
| 15 |
+
"learning_rate": 1.1023622047244096e-06,
|
| 16 |
+
"loss": 1.1147,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.11254924029262803,
|
| 21 |
+
"grad_norm": 2.2132718563079834,
|
| 22 |
+
"learning_rate": 2.227221597300338e-06,
|
| 23 |
+
"loss": 1.0842,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.16882386043894204,
|
| 28 |
+
"grad_norm": 2.2031383514404297,
|
| 29 |
+
"learning_rate": 3.3520809898762658e-06,
|
| 30 |
+
"loss": 0.9439,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.22509848058525606,
|
| 35 |
+
"grad_norm": 2.492532730102539,
|
| 36 |
+
"learning_rate": 4.476940382452194e-06,
|
| 37 |
+
"loss": 0.7497,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.28137310073157007,
|
| 42 |
+
"grad_norm": 5.415732383728027,
|
| 43 |
+
"learning_rate": 5.6017997750281215e-06,
|
| 44 |
+
"loss": 0.5953,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.3376477208778841,
|
| 49 |
+
"grad_norm": 3.040374755859375,
|
| 50 |
+
"learning_rate": 6.726659167604051e-06,
|
| 51 |
+
"loss": 0.47,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3939223410241981,
|
| 56 |
+
"grad_norm": 2.420459747314453,
|
| 57 |
+
"learning_rate": 7.851518560179978e-06,
|
| 58 |
+
"loss": 0.4128,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.4501969611705121,
|
| 63 |
+
"grad_norm": 2.526780128479004,
|
| 64 |
+
"learning_rate": 8.976377952755906e-06,
|
| 65 |
+
"loss": 0.3899,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5064715813168261,
|
| 70 |
+
"grad_norm": 6.837190628051758,
|
| 71 |
+
"learning_rate": 1.0101237345331833e-05,
|
| 72 |
+
"loss": 0.4092,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5627462014631401,
|
| 77 |
+
"grad_norm": 2.692833185195923,
|
| 78 |
+
"learning_rate": 1.1226096737907763e-05,
|
| 79 |
+
"loss": 0.3887,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6190208216094542,
|
| 84 |
+
"grad_norm": 1.8825379610061646,
|
| 85 |
+
"learning_rate": 1.2350956130483691e-05,
|
| 86 |
+
"loss": 0.3891,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6752954417557682,
|
| 91 |
+
"grad_norm": 3.277323007583618,
|
| 92 |
+
"learning_rate": 1.3453318335208101e-05,
|
| 93 |
+
"loss": 0.3878,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.7315700619020822,
|
| 98 |
+
"grad_norm": 2.1386890411376953,
|
| 99 |
+
"learning_rate": 1.4578177727784028e-05,
|
| 100 |
+
"loss": 0.3823,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.7878446820483962,
|
| 105 |
+
"grad_norm": 5.464720249176025,
|
| 106 |
+
"learning_rate": 1.5703037120359956e-05,
|
| 107 |
+
"loss": 0.3854,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.8441193021947102,
|
| 112 |
+
"grad_norm": 2.195767402648926,
|
| 113 |
+
"learning_rate": 1.6827896512935883e-05,
|
| 114 |
+
"loss": 0.383,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9003939223410242,
|
| 119 |
+
"grad_norm": 3.1674859523773193,
|
| 120 |
+
"learning_rate": 1.7952755905511813e-05,
|
| 121 |
+
"loss": 0.3622,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.9566685424873382,
|
| 126 |
+
"grad_norm": 2.137552499771118,
|
| 127 |
+
"learning_rate": 1.9077615298087743e-05,
|
| 128 |
+
"loss": 0.3679,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_accuracy": 0.8270935960591133,
|
| 134 |
+
"eval_f1_fix": 0.9979395604395604,
|
| 135 |
+
"eval_f1_issue": 0.8027574563871693,
|
| 136 |
+
"eval_f1_symptom": 0.77491961414791,
|
| 137 |
+
"eval_f1_weighted": 0.8262810094793769,
|
| 138 |
+
"eval_loss": 0.3870583176612854,
|
| 139 |
+
"eval_precision_fix": 0.9965706447187929,
|
| 140 |
+
"eval_precision_issue": 0.7557615894039735,
|
| 141 |
+
"eval_precision_symptom": 0.8347765846899896,
|
| 142 |
+
"eval_precision_weighted": 0.8313149571029931,
|
| 143 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 144 |
+
"eval_recall_issue": 0.855985598559856,
|
| 145 |
+
"eval_recall_symptom": 0.723072307230723,
|
| 146 |
+
"eval_recall_weighted": 0.8270935960591133,
|
| 147 |
+
"eval_runtime": 50.1716,
|
| 148 |
+
"eval_samples_per_second": 161.845,
|
| 149 |
+
"eval_steps_per_second": 2.531,
|
| 150 |
+
"step": 889
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.012380416432189,
|
| 154 |
+
"grad_norm": 2.139568567276001,
|
| 155 |
+
"learning_rate": 1.9977502812148483e-05,
|
| 156 |
+
"loss": 0.3606,
|
| 157 |
+
"step": 900
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.068655036578503,
|
| 161 |
+
"grad_norm": 1.6121031045913696,
|
| 162 |
+
"learning_rate": 1.9852518435195604e-05,
|
| 163 |
+
"loss": 0.3454,
|
| 164 |
+
"step": 950
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.124929656724817,
|
| 168 |
+
"grad_norm": 2.136821985244751,
|
| 169 |
+
"learning_rate": 1.972753405824272e-05,
|
| 170 |
+
"loss": 0.3622,
|
| 171 |
+
"step": 1000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.181204276871131,
|
| 175 |
+
"grad_norm": 2.97175669670105,
|
| 176 |
+
"learning_rate": 1.960254968128984e-05,
|
| 177 |
+
"loss": 0.3678,
|
| 178 |
+
"step": 1050
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.237478897017445,
|
| 182 |
+
"grad_norm": 2.862729549407959,
|
| 183 |
+
"learning_rate": 1.947756530433696e-05,
|
| 184 |
+
"loss": 0.3742,
|
| 185 |
+
"step": 1100
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.293753517163759,
|
| 189 |
+
"grad_norm": 1.6733105182647705,
|
| 190 |
+
"learning_rate": 1.935258092738408e-05,
|
| 191 |
+
"loss": 0.3575,
|
| 192 |
+
"step": 1150
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.350028137310073,
|
| 196 |
+
"grad_norm": 2.2922866344451904,
|
| 197 |
+
"learning_rate": 1.92275965504312e-05,
|
| 198 |
+
"loss": 0.3593,
|
| 199 |
+
"step": 1200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.406302757456387,
|
| 203 |
+
"grad_norm": 1.7616901397705078,
|
| 204 |
+
"learning_rate": 1.9102612173478316e-05,
|
| 205 |
+
"loss": 0.371,
|
| 206 |
+
"step": 1250
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.4625773776027011,
|
| 210 |
+
"grad_norm": 3.089038610458374,
|
| 211 |
+
"learning_rate": 1.8977627796525436e-05,
|
| 212 |
+
"loss": 0.3577,
|
| 213 |
+
"step": 1300
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.5188519977490151,
|
| 217 |
+
"grad_norm": 2.3721745014190674,
|
| 218 |
+
"learning_rate": 1.8852643419572557e-05,
|
| 219 |
+
"loss": 0.3542,
|
| 220 |
+
"step": 1350
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.5751266178953292,
|
| 224 |
+
"grad_norm": 4.346639156341553,
|
| 225 |
+
"learning_rate": 1.8727659042619674e-05,
|
| 226 |
+
"loss": 0.3562,
|
| 227 |
+
"step": 1400
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.6314012380416432,
|
| 231 |
+
"grad_norm": 1.6947968006134033,
|
| 232 |
+
"learning_rate": 1.8602674665666794e-05,
|
| 233 |
+
"loss": 0.344,
|
| 234 |
+
"step": 1450
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.6876758581879572,
|
| 238 |
+
"grad_norm": 3.7869679927825928,
|
| 239 |
+
"learning_rate": 1.847769028871391e-05,
|
| 240 |
+
"loss": 0.3459,
|
| 241 |
+
"step": 1500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.7439504783342712,
|
| 245 |
+
"grad_norm": 3.708456039428711,
|
| 246 |
+
"learning_rate": 1.835270591176103e-05,
|
| 247 |
+
"loss": 0.3502,
|
| 248 |
+
"step": 1550
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.8002250984805852,
|
| 252 |
+
"grad_norm": 1.927826166152954,
|
| 253 |
+
"learning_rate": 1.8227721534808152e-05,
|
| 254 |
+
"loss": 0.343,
|
| 255 |
+
"step": 1600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.8564997186268992,
|
| 259 |
+
"grad_norm": 3.222015142440796,
|
| 260 |
+
"learning_rate": 1.810273715785527e-05,
|
| 261 |
+
"loss": 0.3358,
|
| 262 |
+
"step": 1650
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.9127743387732132,
|
| 266 |
+
"grad_norm": 2.057603597640991,
|
| 267 |
+
"learning_rate": 1.797775278090239e-05,
|
| 268 |
+
"loss": 0.3532,
|
| 269 |
+
"step": 1700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.9690489589195272,
|
| 273 |
+
"grad_norm": 3.3761789798736572,
|
| 274 |
+
"learning_rate": 1.7852768403949506e-05,
|
| 275 |
+
"loss": 0.3392,
|
| 276 |
+
"step": 1750
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.0,
|
| 280 |
+
"eval_accuracy": 0.8397783251231528,
|
| 281 |
+
"eval_f1_fix": 0.9979395604395604,
|
| 282 |
+
"eval_f1_issue": 0.7946936197094125,
|
| 283 |
+
"eval_f1_symptom": 0.8147512864493996,
|
| 284 |
+
"eval_f1_weighted": 0.839320688806212,
|
| 285 |
+
"eval_loss": 0.3833693265914917,
|
| 286 |
+
"eval_precision_fix": 0.9965706447187929,
|
| 287 |
+
"eval_precision_issue": 0.8389463154384795,
|
| 288 |
+
"eval_precision_symptom": 0.778050778050778,
|
| 289 |
+
"eval_precision_weighted": 0.8421754963079828,
|
| 290 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 291 |
+
"eval_recall_issue": 0.7548754875487549,
|
| 292 |
+
"eval_recall_symptom": 0.8550855085508551,
|
| 293 |
+
"eval_recall_weighted": 0.8397783251231528,
|
| 294 |
+
"eval_runtime": 51.072,
|
| 295 |
+
"eval_samples_per_second": 158.991,
|
| 296 |
+
"eval_steps_per_second": 2.487,
|
| 297 |
+
"step": 1778
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.024760832864378,
|
| 301 |
+
"grad_norm": 1.9975008964538574,
|
| 302 |
+
"learning_rate": 1.7727784026996627e-05,
|
| 303 |
+
"loss": 0.3269,
|
| 304 |
+
"step": 1800
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.081035453010692,
|
| 308 |
+
"grad_norm": 1.5703338384628296,
|
| 309 |
+
"learning_rate": 1.7602799650043747e-05,
|
| 310 |
+
"loss": 0.3253,
|
| 311 |
+
"step": 1850
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.137310073157006,
|
| 315 |
+
"grad_norm": 1.7055504322052002,
|
| 316 |
+
"learning_rate": 1.7477815273090864e-05,
|
| 317 |
+
"loss": 0.3076,
|
| 318 |
+
"step": 1900
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.19358469330332,
|
| 322 |
+
"grad_norm": 2.055391550064087,
|
| 323 |
+
"learning_rate": 1.7352830896137985e-05,
|
| 324 |
+
"loss": 0.3175,
|
| 325 |
+
"step": 1950
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.249859313449634,
|
| 329 |
+
"grad_norm": 2.3307132720947266,
|
| 330 |
+
"learning_rate": 1.72278465191851e-05,
|
| 331 |
+
"loss": 0.3166,
|
| 332 |
+
"step": 2000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.306133933595948,
|
| 336 |
+
"grad_norm": 1.9831819534301758,
|
| 337 |
+
"learning_rate": 1.7102862142232222e-05,
|
| 338 |
+
"loss": 0.3272,
|
| 339 |
+
"step": 2050
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.362408553742262,
|
| 343 |
+
"grad_norm": 2.037224292755127,
|
| 344 |
+
"learning_rate": 1.6977877765279342e-05,
|
| 345 |
+
"loss": 0.3217,
|
| 346 |
+
"step": 2100
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.418683173888576,
|
| 350 |
+
"grad_norm": 2.2483575344085693,
|
| 351 |
+
"learning_rate": 1.6852893388326463e-05,
|
| 352 |
+
"loss": 0.3483,
|
| 353 |
+
"step": 2150
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.47495779403489,
|
| 357 |
+
"grad_norm": 2.124046564102173,
|
| 358 |
+
"learning_rate": 1.672790901137358e-05,
|
| 359 |
+
"loss": 0.3032,
|
| 360 |
+
"step": 2200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.531232414181204,
|
| 364 |
+
"grad_norm": 2.424370288848877,
|
| 365 |
+
"learning_rate": 1.6602924634420697e-05,
|
| 366 |
+
"loss": 0.3173,
|
| 367 |
+
"step": 2250
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.587507034327518,
|
| 371 |
+
"grad_norm": 3.231492757797241,
|
| 372 |
+
"learning_rate": 1.6477940257467817e-05,
|
| 373 |
+
"loss": 0.3346,
|
| 374 |
+
"step": 2300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.643781654473832,
|
| 378 |
+
"grad_norm": 1.850974440574646,
|
| 379 |
+
"learning_rate": 1.6355455568053996e-05,
|
| 380 |
+
"loss": 0.3341,
|
| 381 |
+
"step": 2350
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.700056274620146,
|
| 385 |
+
"grad_norm": 2.1213784217834473,
|
| 386 |
+
"learning_rate": 1.6230471191101113e-05,
|
| 387 |
+
"loss": 0.3137,
|
| 388 |
+
"step": 2400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.75633089476646,
|
| 392 |
+
"grad_norm": 1.9203131198883057,
|
| 393 |
+
"learning_rate": 1.6105486814148233e-05,
|
| 394 |
+
"loss": 0.3434,
|
| 395 |
+
"step": 2450
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.812605514912774,
|
| 399 |
+
"grad_norm": 2.571561336517334,
|
| 400 |
+
"learning_rate": 1.598050243719535e-05,
|
| 401 |
+
"loss": 0.311,
|
| 402 |
+
"step": 2500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.8688801350590882,
|
| 406 |
+
"grad_norm": 1.646263837814331,
|
| 407 |
+
"learning_rate": 1.585551806024247e-05,
|
| 408 |
+
"loss": 0.3265,
|
| 409 |
+
"step": 2550
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.9251547552054022,
|
| 413 |
+
"grad_norm": 3.992446184158325,
|
| 414 |
+
"learning_rate": 1.573053368328959e-05,
|
| 415 |
+
"loss": 0.3231,
|
| 416 |
+
"step": 2600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.9814293753517163,
|
| 420 |
+
"grad_norm": 3.225480794906616,
|
| 421 |
+
"learning_rate": 1.5605549306336708e-05,
|
| 422 |
+
"loss": 0.3164,
|
| 423 |
+
"step": 2650
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.0,
|
| 427 |
+
"eval_accuracy": 0.8419950738916256,
|
| 428 |
+
"eval_f1_fix": 0.998282377189969,
|
| 429 |
+
"eval_f1_issue": 0.8020994133991973,
|
| 430 |
+
"eval_f1_symptom": 0.8133119252663845,
|
| 431 |
+
"eval_f1_weighted": 0.8418311044589408,
|
| 432 |
+
"eval_loss": 0.3592279255390167,
|
| 433 |
+
"eval_precision_fix": 0.997254632807138,
|
| 434 |
+
"eval_precision_issue": 0.8260731319554849,
|
| 435 |
+
"eval_precision_symptom": 0.7919272313814667,
|
| 436 |
+
"eval_precision_weighted": 0.8427097841260638,
|
| 437 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 438 |
+
"eval_recall_issue": 0.7794779477947795,
|
| 439 |
+
"eval_recall_symptom": 0.8358835883588359,
|
| 440 |
+
"eval_recall_weighted": 0.8419950738916256,
|
| 441 |
+
"eval_runtime": 51.3031,
|
| 442 |
+
"eval_samples_per_second": 158.275,
|
| 443 |
+
"eval_steps_per_second": 2.475,
|
| 444 |
+
"step": 2667
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.037141249296567,
|
| 448 |
+
"grad_norm": 2.5545248985290527,
|
| 449 |
+
"learning_rate": 1.548056492938383e-05,
|
| 450 |
+
"loss": 0.3147,
|
| 451 |
+
"step": 2700
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.093415869442881,
|
| 455 |
+
"grad_norm": 1.628539800643921,
|
| 456 |
+
"learning_rate": 1.5355580552430946e-05,
|
| 457 |
+
"loss": 0.2979,
|
| 458 |
+
"step": 2750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.1496904895891955,
|
| 462 |
+
"grad_norm": 1.9369264841079712,
|
| 463 |
+
"learning_rate": 1.5230596175478068e-05,
|
| 464 |
+
"loss": 0.2869,
|
| 465 |
+
"step": 2800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.205965109735509,
|
| 469 |
+
"grad_norm": 2.5903725624084473,
|
| 470 |
+
"learning_rate": 1.5105611798525186e-05,
|
| 471 |
+
"loss": 0.272,
|
| 472 |
+
"step": 2850
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.2622397298818235,
|
| 476 |
+
"grad_norm": 2.560624361038208,
|
| 477 |
+
"learning_rate": 1.4980627421572305e-05,
|
| 478 |
+
"loss": 0.2914,
|
| 479 |
+
"step": 2900
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.3185143500281375,
|
| 483 |
+
"grad_norm": 3.008889675140381,
|
| 484 |
+
"learning_rate": 1.4855643044619424e-05,
|
| 485 |
+
"loss": 0.2858,
|
| 486 |
+
"step": 2950
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.3747889701744516,
|
| 490 |
+
"grad_norm": 2.466245651245117,
|
| 491 |
+
"learning_rate": 1.4730658667666542e-05,
|
| 492 |
+
"loss": 0.3021,
|
| 493 |
+
"step": 3000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.4310635903207656,
|
| 497 |
+
"grad_norm": 2.1926143169403076,
|
| 498 |
+
"learning_rate": 1.4605674290713663e-05,
|
| 499 |
+
"loss": 0.2961,
|
| 500 |
+
"step": 3050
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.4873382104670796,
|
| 504 |
+
"grad_norm": 2.4998419284820557,
|
| 505 |
+
"learning_rate": 1.4480689913760782e-05,
|
| 506 |
+
"loss": 0.2851,
|
| 507 |
+
"step": 3100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.5436128306133936,
|
| 511 |
+
"grad_norm": 2.801224946975708,
|
| 512 |
+
"learning_rate": 1.43557055368079e-05,
|
| 513 |
+
"loss": 0.3003,
|
| 514 |
+
"step": 3150
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.5998874507597076,
|
| 518 |
+
"grad_norm": 1.9596877098083496,
|
| 519 |
+
"learning_rate": 1.4230721159855019e-05,
|
| 520 |
+
"loss": 0.3019,
|
| 521 |
+
"step": 3200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.6561620709060216,
|
| 525 |
+
"grad_norm": 1.780312418937683,
|
| 526 |
+
"learning_rate": 1.4105736782902138e-05,
|
| 527 |
+
"loss": 0.2962,
|
| 528 |
+
"step": 3250
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.7124366910523356,
|
| 532 |
+
"grad_norm": 3.569025754928589,
|
| 533 |
+
"learning_rate": 1.3980752405949258e-05,
|
| 534 |
+
"loss": 0.2923,
|
| 535 |
+
"step": 3300
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 3.7687113111986497,
|
| 539 |
+
"grad_norm": 2.3551599979400635,
|
| 540 |
+
"learning_rate": 1.3855768028996377e-05,
|
| 541 |
+
"loss": 0.3113,
|
| 542 |
+
"step": 3350
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.8249859313449637,
|
| 546 |
+
"grad_norm": 1.77907133102417,
|
| 547 |
+
"learning_rate": 1.3730783652043495e-05,
|
| 548 |
+
"loss": 0.3056,
|
| 549 |
+
"step": 3400
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.8812605514912777,
|
| 553 |
+
"grad_norm": 4.4045610427856445,
|
| 554 |
+
"learning_rate": 1.3605799275090614e-05,
|
| 555 |
+
"loss": 0.2942,
|
| 556 |
+
"step": 3450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 3.9375351716375917,
|
| 560 |
+
"grad_norm": 1.8489115238189697,
|
| 561 |
+
"learning_rate": 1.3480814898137733e-05,
|
| 562 |
+
"loss": 0.3136,
|
| 563 |
+
"step": 3500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.9938097917839057,
|
| 567 |
+
"grad_norm": 1.9342581033706665,
|
| 568 |
+
"learning_rate": 1.3355830521184853e-05,
|
| 569 |
+
"loss": 0.3061,
|
| 570 |
+
"step": 3550
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.0,
|
| 574 |
+
"eval_accuracy": 0.84064039408867,
|
| 575 |
+
"eval_f1_fix": 0.998282377189969,
|
| 576 |
+
"eval_f1_issue": 0.7974306752310826,
|
| 577 |
+
"eval_f1_symptom": 0.8142816009213936,
|
| 578 |
+
"eval_f1_weighted": 0.8403127577401992,
|
| 579 |
+
"eval_loss": 0.3966975510120392,
|
| 580 |
+
"eval_precision_fix": 0.997254632807138,
|
| 581 |
+
"eval_precision_issue": 0.8344262295081967,
|
| 582 |
+
"eval_precision_symptom": 0.782729034043731,
|
| 583 |
+
"eval_precision_weighted": 0.8423628977241568,
|
| 584 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 585 |
+
"eval_recall_issue": 0.7635763576357636,
|
| 586 |
+
"eval_recall_symptom": 0.8484848484848485,
|
| 587 |
+
"eval_recall_weighted": 0.84064039408867,
|
| 588 |
+
"eval_runtime": 50.3322,
|
| 589 |
+
"eval_samples_per_second": 161.328,
|
| 590 |
+
"eval_steps_per_second": 2.523,
|
| 591 |
+
"step": 3556
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.049521665728756,
|
| 595 |
+
"grad_norm": 2.619023084640503,
|
| 596 |
+
"learning_rate": 1.3230846144231972e-05,
|
| 597 |
+
"loss": 0.2784,
|
| 598 |
+
"step": 3600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.10579628587507,
|
| 602 |
+
"grad_norm": 2.1567516326904297,
|
| 603 |
+
"learning_rate": 1.310586176727909e-05,
|
| 604 |
+
"loss": 0.2836,
|
| 605 |
+
"step": 3650
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.162070906021384,
|
| 609 |
+
"grad_norm": 1.734316110610962,
|
| 610 |
+
"learning_rate": 1.298087739032621e-05,
|
| 611 |
+
"loss": 0.2725,
|
| 612 |
+
"step": 3700
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.218345526167698,
|
| 616 |
+
"grad_norm": 2.4064743518829346,
|
| 617 |
+
"learning_rate": 1.2855893013373328e-05,
|
| 618 |
+
"loss": 0.2674,
|
| 619 |
+
"step": 3750
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 4.274620146314012,
|
| 623 |
+
"grad_norm": 4.878196716308594,
|
| 624 |
+
"learning_rate": 1.2730908636420448e-05,
|
| 625 |
+
"loss": 0.2614,
|
| 626 |
+
"step": 3800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.330894766460326,
|
| 630 |
+
"grad_norm": 3.776557683944702,
|
| 631 |
+
"learning_rate": 1.2605924259467567e-05,
|
| 632 |
+
"loss": 0.2759,
|
| 633 |
+
"step": 3850
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.38716938660664,
|
| 637 |
+
"grad_norm": 2.9769930839538574,
|
| 638 |
+
"learning_rate": 1.2480939882514686e-05,
|
| 639 |
+
"loss": 0.27,
|
| 640 |
+
"step": 3900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.443444006752954,
|
| 644 |
+
"grad_norm": 2.369786500930786,
|
| 645 |
+
"learning_rate": 1.2355955505561805e-05,
|
| 646 |
+
"loss": 0.2661,
|
| 647 |
+
"step": 3950
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.499718626899268,
|
| 651 |
+
"grad_norm": 3.501908540725708,
|
| 652 |
+
"learning_rate": 1.2230971128608923e-05,
|
| 653 |
+
"loss": 0.2756,
|
| 654 |
+
"step": 4000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.555993247045582,
|
| 658 |
+
"grad_norm": 3.2472310066223145,
|
| 659 |
+
"learning_rate": 1.2105986751656045e-05,
|
| 660 |
+
"loss": 0.2638,
|
| 661 |
+
"step": 4050
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.612267867191896,
|
| 665 |
+
"grad_norm": 1.875646710395813,
|
| 666 |
+
"learning_rate": 1.1981002374703164e-05,
|
| 667 |
+
"loss": 0.2455,
|
| 668 |
+
"step": 4100
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.66854248733821,
|
| 672 |
+
"grad_norm": 2.917334794998169,
|
| 673 |
+
"learning_rate": 1.1856017997750283e-05,
|
| 674 |
+
"loss": 0.2608,
|
| 675 |
+
"step": 4150
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.724817107484524,
|
| 679 |
+
"grad_norm": 2.597090482711792,
|
| 680 |
+
"learning_rate": 1.1731033620797401e-05,
|
| 681 |
+
"loss": 0.2565,
|
| 682 |
+
"step": 4200
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.781091727630838,
|
| 686 |
+
"grad_norm": 2.790834903717041,
|
| 687 |
+
"learning_rate": 1.160604924384452e-05,
|
| 688 |
+
"loss": 0.2724,
|
| 689 |
+
"step": 4250
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.837366347777152,
|
| 693 |
+
"grad_norm": 2.6425554752349854,
|
| 694 |
+
"learning_rate": 1.148106486689164e-05,
|
| 695 |
+
"loss": 0.2826,
|
| 696 |
+
"step": 4300
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 4.893640967923466,
|
| 700 |
+
"grad_norm": 2.039649486541748,
|
| 701 |
+
"learning_rate": 1.135608048993876e-05,
|
| 702 |
+
"loss": 0.2584,
|
| 703 |
+
"step": 4350
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.94991558806978,
|
| 707 |
+
"grad_norm": 3.3404409885406494,
|
| 708 |
+
"learning_rate": 1.1231096112985878e-05,
|
| 709 |
+
"loss": 0.2704,
|
| 710 |
+
"step": 4400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 5.0,
|
| 714 |
+
"eval_accuracy": 0.8385467980295567,
|
| 715 |
+
"eval_f1_fix": 0.9986254295532646,
|
| 716 |
+
"eval_f1_issue": 0.7967101179391682,
|
| 717 |
+
"eval_f1_symptom": 0.8100493755445832,
|
| 718 |
+
"eval_f1_weighted": 0.8383412273832256,
|
| 719 |
+
"eval_loss": 0.3984265625476837,
|
| 720 |
+
"eval_precision_fix": 0.9979395604395604,
|
| 721 |
+
"eval_precision_issue": 0.825136612021858,
|
| 722 |
+
"eval_precision_symptom": 0.7849704475091472,
|
| 723 |
+
"eval_precision_weighted": 0.839592481563542,
|
| 724 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 725 |
+
"eval_recall_issue": 0.7701770177017702,
|
| 726 |
+
"eval_recall_symptom": 0.8367836783678367,
|
| 727 |
+
"eval_recall_weighted": 0.8385467980295567,
|
| 728 |
+
"eval_runtime": 103.4526,
|
| 729 |
+
"eval_samples_per_second": 78.49,
|
| 730 |
+
"eval_steps_per_second": 1.228,
|
| 731 |
+
"step": 4445
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 5.0056274620146315,
|
| 735 |
+
"grad_norm": 1.412779688835144,
|
| 736 |
+
"learning_rate": 1.1106111736032997e-05,
|
| 737 |
+
"loss": 0.2558,
|
| 738 |
+
"step": 4450
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 5.0619020821609455,
|
| 742 |
+
"grad_norm": 3.5638949871063232,
|
| 743 |
+
"learning_rate": 1.0981127359080115e-05,
|
| 744 |
+
"loss": 0.2201,
|
| 745 |
+
"step": 4500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 5.1181767023072595,
|
| 749 |
+
"grad_norm": 2.8439533710479736,
|
| 750 |
+
"learning_rate": 1.0856142982127236e-05,
|
| 751 |
+
"loss": 0.2406,
|
| 752 |
+
"step": 4550
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 5.1744513224535735,
|
| 756 |
+
"grad_norm": 3.5135629177093506,
|
| 757 |
+
"learning_rate": 1.0731158605174354e-05,
|
| 758 |
+
"loss": 0.2282,
|
| 759 |
+
"step": 4600
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.2307259425998875,
|
| 763 |
+
"grad_norm": 3.6669528484344482,
|
| 764 |
+
"learning_rate": 1.0606174228221473e-05,
|
| 765 |
+
"loss": 0.2266,
|
| 766 |
+
"step": 4650
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 5.287000562746202,
|
| 770 |
+
"grad_norm": 3.3074584007263184,
|
| 771 |
+
"learning_rate": 1.0481189851268592e-05,
|
| 772 |
+
"loss": 0.2635,
|
| 773 |
+
"step": 4700
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 5.343275182892516,
|
| 777 |
+
"grad_norm": 2.5459887981414795,
|
| 778 |
+
"learning_rate": 1.035620547431571e-05,
|
| 779 |
+
"loss": 0.2471,
|
| 780 |
+
"step": 4750
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 5.39954980303883,
|
| 784 |
+
"grad_norm": 3.6159589290618896,
|
| 785 |
+
"learning_rate": 1.0231221097362831e-05,
|
| 786 |
+
"loss": 0.2443,
|
| 787 |
+
"step": 4800
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 5.455824423185144,
|
| 791 |
+
"grad_norm": 4.78350830078125,
|
| 792 |
+
"learning_rate": 1.010623672040995e-05,
|
| 793 |
+
"loss": 0.2465,
|
| 794 |
+
"step": 4850
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 5.512099043331458,
|
| 798 |
+
"grad_norm": 3.147178888320923,
|
| 799 |
+
"learning_rate": 9.981252343457068e-06,
|
| 800 |
+
"loss": 0.2523,
|
| 801 |
+
"step": 4900
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 5.568373663477772,
|
| 805 |
+
"grad_norm": 3.182088613510132,
|
| 806 |
+
"learning_rate": 9.856267966504189e-06,
|
| 807 |
+
"loss": 0.2382,
|
| 808 |
+
"step": 4950
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 5.624648283624086,
|
| 812 |
+
"grad_norm": 4.077524662017822,
|
| 813 |
+
"learning_rate": 9.733783277090364e-06,
|
| 814 |
+
"loss": 0.2342,
|
| 815 |
+
"step": 5000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 5.6809229037704,
|
| 819 |
+
"grad_norm": 4.5491509437561035,
|
| 820 |
+
"learning_rate": 9.608798900137485e-06,
|
| 821 |
+
"loss": 0.2438,
|
| 822 |
+
"step": 5050
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 5.737197523916714,
|
| 826 |
+
"grad_norm": 3.9461286067962646,
|
| 827 |
+
"learning_rate": 9.483814523184603e-06,
|
| 828 |
+
"loss": 0.2294,
|
| 829 |
+
"step": 5100
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 5.793472144063028,
|
| 833 |
+
"grad_norm": 2.644874095916748,
|
| 834 |
+
"learning_rate": 9.358830146231722e-06,
|
| 835 |
+
"loss": 0.2431,
|
| 836 |
+
"step": 5150
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 5.849746764209342,
|
| 840 |
+
"grad_norm": 3.191740036010742,
|
| 841 |
+
"learning_rate": 9.23384576927884e-06,
|
| 842 |
+
"loss": 0.2455,
|
| 843 |
+
"step": 5200
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 5.906021384355656,
|
| 847 |
+
"grad_norm": 2.2712607383728027,
|
| 848 |
+
"learning_rate": 9.10886139232596e-06,
|
| 849 |
+
"loss": 0.2407,
|
| 850 |
+
"step": 5250
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 5.96229600450197,
|
| 854 |
+
"grad_norm": 2.775583505630493,
|
| 855 |
+
"learning_rate": 8.98387701537308e-06,
|
| 856 |
+
"loss": 0.2551,
|
| 857 |
+
"step": 5300
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 6.0,
|
| 861 |
+
"eval_accuracy": 0.8370689655172414,
|
| 862 |
+
"eval_f1_fix": 0.9979395604395604,
|
| 863 |
+
"eval_f1_issue": 0.8008436275986743,
|
| 864 |
+
"eval_f1_symptom": 0.8029895366218236,
|
| 865 |
+
"eval_f1_weighted": 0.8370172484268523,
|
| 866 |
+
"eval_loss": 0.4547211527824402,
|
| 867 |
+
"eval_precision_fix": 0.9965706447187929,
|
| 868 |
+
"eval_precision_issue": 0.8042360060514372,
|
| 869 |
+
"eval_precision_symptom": 0.8001191540065534,
|
| 870 |
+
"eval_precision_weighted": 0.8369863874254196,
|
| 871 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 872 |
+
"eval_recall_issue": 0.7974797479747975,
|
| 873 |
+
"eval_recall_symptom": 0.8058805880588059,
|
| 874 |
+
"eval_recall_weighted": 0.8370689655172414,
|
| 875 |
+
"eval_runtime": 52.2924,
|
| 876 |
+
"eval_samples_per_second": 155.281,
|
| 877 |
+
"eval_steps_per_second": 2.429,
|
| 878 |
+
"step": 5334
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 6.01800787844682,
|
| 882 |
+
"grad_norm": 2.528533697128296,
|
| 883 |
+
"learning_rate": 8.858892638420198e-06,
|
| 884 |
+
"loss": 0.2138,
|
| 885 |
+
"step": 5350
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 6.074282498593134,
|
| 889 |
+
"grad_norm": 5.1876091957092285,
|
| 890 |
+
"learning_rate": 8.733908261467317e-06,
|
| 891 |
+
"loss": 0.2319,
|
| 892 |
+
"step": 5400
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 6.130557118739448,
|
| 896 |
+
"grad_norm": 1.4345381259918213,
|
| 897 |
+
"learning_rate": 8.608923884514436e-06,
|
| 898 |
+
"loss": 0.2118,
|
| 899 |
+
"step": 5450
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 6.186831738885762,
|
| 903 |
+
"grad_norm": 6.736217021942139,
|
| 904 |
+
"learning_rate": 8.483939507561556e-06,
|
| 905 |
+
"loss": 0.2171,
|
| 906 |
+
"step": 5500
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 6.243106359032076,
|
| 910 |
+
"grad_norm": 3.6418821811676025,
|
| 911 |
+
"learning_rate": 8.358955130608675e-06,
|
| 912 |
+
"loss": 0.2339,
|
| 913 |
+
"step": 5550
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 6.299380979178391,
|
| 917 |
+
"grad_norm": 3.062988758087158,
|
| 918 |
+
"learning_rate": 8.233970753655794e-06,
|
| 919 |
+
"loss": 0.2121,
|
| 920 |
+
"step": 5600
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 6.355655599324704,
|
| 924 |
+
"grad_norm": 3.603121519088745,
|
| 925 |
+
"learning_rate": 8.108986376702912e-06,
|
| 926 |
+
"loss": 0.211,
|
| 927 |
+
"step": 5650
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 6.411930219471018,
|
| 931 |
+
"grad_norm": 3.1732518672943115,
|
| 932 |
+
"learning_rate": 7.984001999750031e-06,
|
| 933 |
+
"loss": 0.1988,
|
| 934 |
+
"step": 5700
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 6.468204839617332,
|
| 938 |
+
"grad_norm": 4.5081071853637695,
|
| 939 |
+
"learning_rate": 7.859017622797151e-06,
|
| 940 |
+
"loss": 0.2006,
|
| 941 |
+
"step": 5750
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 6.524479459763647,
|
| 945 |
+
"grad_norm": 3.192850112915039,
|
| 946 |
+
"learning_rate": 7.73403324584427e-06,
|
| 947 |
+
"loss": 0.2225,
|
| 948 |
+
"step": 5800
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 6.58075407990996,
|
| 952 |
+
"grad_norm": 4.354557514190674,
|
| 953 |
+
"learning_rate": 7.609048868891389e-06,
|
| 954 |
+
"loss": 0.2232,
|
| 955 |
+
"step": 5850
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 6.637028700056275,
|
| 959 |
+
"grad_norm": 2.804410934448242,
|
| 960 |
+
"learning_rate": 7.484064491938508e-06,
|
| 961 |
+
"loss": 0.2207,
|
| 962 |
+
"step": 5900
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 6.693303320202588,
|
| 966 |
+
"grad_norm": 4.296571731567383,
|
| 967 |
+
"learning_rate": 7.359080114985627e-06,
|
| 968 |
+
"loss": 0.21,
|
| 969 |
+
"step": 5950
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 6.749577940348903,
|
| 973 |
+
"grad_norm": 2.1833271980285645,
|
| 974 |
+
"learning_rate": 7.234095738032747e-06,
|
| 975 |
+
"loss": 0.2101,
|
| 976 |
+
"step": 6000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 6.805852560495216,
|
| 980 |
+
"grad_norm": 4.7521138191223145,
|
| 981 |
+
"learning_rate": 7.109111361079865e-06,
|
| 982 |
+
"loss": 0.2263,
|
| 983 |
+
"step": 6050
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 6.862127180641531,
|
| 987 |
+
"grad_norm": 4.192446231842041,
|
| 988 |
+
"learning_rate": 6.984126984126984e-06,
|
| 989 |
+
"loss": 0.2127,
|
| 990 |
+
"step": 6100
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 6.918401800787844,
|
| 994 |
+
"grad_norm": 3.3775792121887207,
|
| 995 |
+
"learning_rate": 6.859142607174104e-06,
|
| 996 |
+
"loss": 0.2254,
|
| 997 |
+
"step": 6150
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 6.974676420934159,
|
| 1001 |
+
"grad_norm": 3.5780911445617676,
|
| 1002 |
+
"learning_rate": 6.734158230221223e-06,
|
| 1003 |
+
"loss": 0.1976,
|
| 1004 |
+
"step": 6200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 7.0,
|
| 1008 |
+
"eval_accuracy": 0.8341133004926108,
|
| 1009 |
+
"eval_f1_fix": 0.998282377189969,
|
| 1010 |
+
"eval_f1_issue": 0.7951293759512937,
|
| 1011 |
+
"eval_f1_symptom": 0.8013019677467081,
|
| 1012 |
+
"eval_f1_weighted": 0.8340404242585783,
|
| 1013 |
+
"eval_loss": 0.45761045813560486,
|
| 1014 |
+
"eval_precision_fix": 0.997254632807138,
|
| 1015 |
+
"eval_precision_issue": 0.8069199876428792,
|
| 1016 |
+
"eval_precision_symptom": 0.7904261529480444,
|
| 1017 |
+
"eval_precision_weighted": 0.8342318870309269,
|
| 1018 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 1019 |
+
"eval_recall_issue": 0.7836783678367837,
|
| 1020 |
+
"eval_recall_symptom": 0.8124812481248125,
|
| 1021 |
+
"eval_recall_weighted": 0.8341133004926108,
|
| 1022 |
+
"eval_runtime": 50.9303,
|
| 1023 |
+
"eval_samples_per_second": 159.433,
|
| 1024 |
+
"eval_steps_per_second": 2.494,
|
| 1025 |
+
"step": 6223
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 7.0303882948790095,
|
| 1029 |
+
"grad_norm": 6.685973167419434,
|
| 1030 |
+
"learning_rate": 6.609173853268343e-06,
|
| 1031 |
+
"loss": 0.197,
|
| 1032 |
+
"step": 6250
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 7.0866629150253235,
|
| 1036 |
+
"grad_norm": 3.8742218017578125,
|
| 1037 |
+
"learning_rate": 6.484189476315461e-06,
|
| 1038 |
+
"loss": 0.183,
|
| 1039 |
+
"step": 6300
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 7.1429375351716375,
|
| 1043 |
+
"grad_norm": 5.564633846282959,
|
| 1044 |
+
"learning_rate": 6.35920509936258e-06,
|
| 1045 |
+
"loss": 0.2029,
|
| 1046 |
+
"step": 6350
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 7.1992121553179516,
|
| 1050 |
+
"grad_norm": 4.8350677490234375,
|
| 1051 |
+
"learning_rate": 6.2342207224097e-06,
|
| 1052 |
+
"loss": 0.1889,
|
| 1053 |
+
"step": 6400
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 7.255486775464266,
|
| 1057 |
+
"grad_norm": 2.719174385070801,
|
| 1058 |
+
"learning_rate": 6.109236345456818e-06,
|
| 1059 |
+
"loss": 0.2021,
|
| 1060 |
+
"step": 6450
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 7.31176139561058,
|
| 1064 |
+
"grad_norm": 3.9081249237060547,
|
| 1065 |
+
"learning_rate": 5.984251968503938e-06,
|
| 1066 |
+
"loss": 0.1916,
|
| 1067 |
+
"step": 6500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 7.368036015756894,
|
| 1071 |
+
"grad_norm": 4.187448024749756,
|
| 1072 |
+
"learning_rate": 5.859267591551057e-06,
|
| 1073 |
+
"loss": 0.2077,
|
| 1074 |
+
"step": 6550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 7.424310635903208,
|
| 1078 |
+
"grad_norm": 2.6563658714294434,
|
| 1079 |
+
"learning_rate": 5.734283214598175e-06,
|
| 1080 |
+
"loss": 0.2,
|
| 1081 |
+
"step": 6600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 7.480585256049522,
|
| 1085 |
+
"grad_norm": 5.274929523468018,
|
| 1086 |
+
"learning_rate": 5.609298837645295e-06,
|
| 1087 |
+
"loss": 0.203,
|
| 1088 |
+
"step": 6650
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 7.536859876195836,
|
| 1092 |
+
"grad_norm": 4.843599319458008,
|
| 1093 |
+
"learning_rate": 5.4843144606924135e-06,
|
| 1094 |
+
"loss": 0.1909,
|
| 1095 |
+
"step": 6700
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 7.59313449634215,
|
| 1099 |
+
"grad_norm": 3.966811418533325,
|
| 1100 |
+
"learning_rate": 5.359330083739533e-06,
|
| 1101 |
+
"loss": 0.1953,
|
| 1102 |
+
"step": 6750
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 7.649409116488464,
|
| 1106 |
+
"grad_norm": 3.038121461868286,
|
| 1107 |
+
"learning_rate": 5.234345706786652e-06,
|
| 1108 |
+
"loss": 0.2036,
|
| 1109 |
+
"step": 6800
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 7.705683736634778,
|
| 1113 |
+
"grad_norm": 4.253869533538818,
|
| 1114 |
+
"learning_rate": 5.1093613298337705e-06,
|
| 1115 |
+
"loss": 0.1942,
|
| 1116 |
+
"step": 6850
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 7.761958356781092,
|
| 1120 |
+
"grad_norm": 2.9078307151794434,
|
| 1121 |
+
"learning_rate": 4.984376952880891e-06,
|
| 1122 |
+
"loss": 0.1957,
|
| 1123 |
+
"step": 6900
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 7.818232976927406,
|
| 1127 |
+
"grad_norm": 4.637989044189453,
|
| 1128 |
+
"learning_rate": 4.85939257592801e-06,
|
| 1129 |
+
"loss": 0.1803,
|
| 1130 |
+
"step": 6950
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 7.87450759707372,
|
| 1134 |
+
"grad_norm": 4.39274787902832,
|
| 1135 |
+
"learning_rate": 4.734408198975128e-06,
|
| 1136 |
+
"loss": 0.2025,
|
| 1137 |
+
"step": 7000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 7.930782217220034,
|
| 1141 |
+
"grad_norm": 4.669205665588379,
|
| 1142 |
+
"learning_rate": 4.609423822022248e-06,
|
| 1143 |
+
"loss": 0.195,
|
| 1144 |
+
"step": 7050
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 7.987056837366348,
|
| 1148 |
+
"grad_norm": 5.979293346405029,
|
| 1149 |
+
"learning_rate": 4.4844394450693665e-06,
|
| 1150 |
+
"loss": 0.1966,
|
| 1151 |
+
"step": 7100
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 8.0,
|
| 1155 |
+
"eval_accuracy": 0.8283251231527093,
|
| 1156 |
+
"eval_f1_fix": 0.998282377189969,
|
| 1157 |
+
"eval_f1_issue": 0.7821735731039875,
|
| 1158 |
+
"eval_f1_symptom": 0.799538505912893,
|
| 1159 |
+
"eval_f1_weighted": 0.8279986374134825,
|
| 1160 |
+
"eval_loss": 0.5127028226852417,
|
| 1161 |
+
"eval_precision_fix": 0.997254632807138,
|
| 1162 |
+
"eval_precision_issue": 0.8167864141084259,
|
| 1163 |
+
"eval_precision_symptom": 0.7697861705081922,
|
| 1164 |
+
"eval_precision_weighted": 0.8298096872695525,
|
| 1165 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 1166 |
+
"eval_recall_issue": 0.7503750375037503,
|
| 1167 |
+
"eval_recall_symptom": 0.8316831683168316,
|
| 1168 |
+
"eval_recall_weighted": 0.8283251231527093,
|
| 1169 |
+
"eval_runtime": 51.6048,
|
| 1170 |
+
"eval_samples_per_second": 157.35,
|
| 1171 |
+
"eval_steps_per_second": 2.461,
|
| 1172 |
+
"step": 7112
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 8.042768711311199,
|
| 1176 |
+
"grad_norm": 4.806234836578369,
|
| 1177 |
+
"learning_rate": 4.359455068116486e-06,
|
| 1178 |
+
"loss": 0.1907,
|
| 1179 |
+
"step": 7150
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 8.099043331457512,
|
| 1183 |
+
"grad_norm": 4.466273784637451,
|
| 1184 |
+
"learning_rate": 4.234470691163605e-06,
|
| 1185 |
+
"loss": 0.1822,
|
| 1186 |
+
"step": 7200
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 8.155317951603827,
|
| 1190 |
+
"grad_norm": 6.873985767364502,
|
| 1191 |
+
"learning_rate": 4.1094863142107235e-06,
|
| 1192 |
+
"loss": 0.174,
|
| 1193 |
+
"step": 7250
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 8.21159257175014,
|
| 1197 |
+
"grad_norm": 8.243498802185059,
|
| 1198 |
+
"learning_rate": 3.984501937257843e-06,
|
| 1199 |
+
"loss": 0.1684,
|
| 1200 |
+
"step": 7300
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 8.267867191896455,
|
| 1204 |
+
"grad_norm": 4.151490211486816,
|
| 1205 |
+
"learning_rate": 3.859517560304963e-06,
|
| 1206 |
+
"loss": 0.1736,
|
| 1207 |
+
"step": 7350
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 8.324141812042768,
|
| 1211 |
+
"grad_norm": 5.426071643829346,
|
| 1212 |
+
"learning_rate": 3.7345331833520813e-06,
|
| 1213 |
+
"loss": 0.1849,
|
| 1214 |
+
"step": 7400
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 8.380416432189083,
|
| 1218 |
+
"grad_norm": 3.12210750579834,
|
| 1219 |
+
"learning_rate": 3.6095488063992e-06,
|
| 1220 |
+
"loss": 0.1703,
|
| 1221 |
+
"step": 7450
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 8.436691052335396,
|
| 1225 |
+
"grad_norm": 4.037646770477295,
|
| 1226 |
+
"learning_rate": 3.4845644294463195e-06,
|
| 1227 |
+
"loss": 0.1632,
|
| 1228 |
+
"step": 7500
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 8.492965672481711,
|
| 1232 |
+
"grad_norm": 3.56674861907959,
|
| 1233 |
+
"learning_rate": 3.3595800524934387e-06,
|
| 1234 |
+
"loss": 0.1709,
|
| 1235 |
+
"step": 7550
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 8.549240292628024,
|
| 1239 |
+
"grad_norm": 4.258781433105469,
|
| 1240 |
+
"learning_rate": 3.234595675540558e-06,
|
| 1241 |
+
"loss": 0.1754,
|
| 1242 |
+
"step": 7600
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 8.605514912774339,
|
| 1246 |
+
"grad_norm": 4.218986511230469,
|
| 1247 |
+
"learning_rate": 3.109611298587677e-06,
|
| 1248 |
+
"loss": 0.1683,
|
| 1249 |
+
"step": 7650
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 8.661789532920652,
|
| 1253 |
+
"grad_norm": 4.169147491455078,
|
| 1254 |
+
"learning_rate": 2.984626921634796e-06,
|
| 1255 |
+
"loss": 0.1865,
|
| 1256 |
+
"step": 7700
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 8.718064153066967,
|
| 1260 |
+
"grad_norm": 2.8161799907684326,
|
| 1261 |
+
"learning_rate": 2.8596425446819147e-06,
|
| 1262 |
+
"loss": 0.1877,
|
| 1263 |
+
"step": 7750
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 8.77433877321328,
|
| 1267 |
+
"grad_norm": 3.580389976501465,
|
| 1268 |
+
"learning_rate": 2.734658167729034e-06,
|
| 1269 |
+
"loss": 0.1694,
|
| 1270 |
+
"step": 7800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 8.830613393359595,
|
| 1274 |
+
"grad_norm": 5.852592468261719,
|
| 1275 |
+
"learning_rate": 2.6096737907761534e-06,
|
| 1276 |
+
"loss": 0.1801,
|
| 1277 |
+
"step": 7850
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 8.886888013505908,
|
| 1281 |
+
"grad_norm": 3.4175920486450195,
|
| 1282 |
+
"learning_rate": 2.484689413823272e-06,
|
| 1283 |
+
"loss": 0.1768,
|
| 1284 |
+
"step": 7900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 8.943162633652223,
|
| 1288 |
+
"grad_norm": 6.1865081787109375,
|
| 1289 |
+
"learning_rate": 2.3597050368703912e-06,
|
| 1290 |
+
"loss": 0.1811,
|
| 1291 |
+
"step": 7950
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 8.999437253798536,
|
| 1295 |
+
"grad_norm": 5.233773708343506,
|
| 1296 |
+
"learning_rate": 2.2347206599175104e-06,
|
| 1297 |
+
"loss": 0.1829,
|
| 1298 |
+
"step": 8000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 9.0,
|
| 1302 |
+
"eval_accuracy": 0.8298029556650246,
|
| 1303 |
+
"eval_f1_fix": 0.9986254295532646,
|
| 1304 |
+
"eval_f1_issue": 0.7910425177787865,
|
| 1305 |
+
"eval_f1_symptom": 0.7948221990775183,
|
| 1306 |
+
"eval_f1_weighted": 0.8297645906222303,
|
| 1307 |
+
"eval_loss": 0.5134788751602173,
|
| 1308 |
+
"eval_precision_fix": 0.9979395604395604,
|
| 1309 |
+
"eval_precision_issue": 0.797924297924298,
|
| 1310 |
+
"eval_precision_symptom": 0.788370720188902,
|
| 1311 |
+
"eval_precision_weighted": 0.8298184010160612,
|
| 1312 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 1313 |
+
"eval_recall_issue": 0.7842784278427842,
|
| 1314 |
+
"eval_recall_symptom": 0.8013801380138014,
|
| 1315 |
+
"eval_recall_weighted": 0.8298029556650246,
|
| 1316 |
+
"eval_runtime": 53.8444,
|
| 1317 |
+
"eval_samples_per_second": 150.805,
|
| 1318 |
+
"eval_steps_per_second": 2.359,
|
| 1319 |
+
"step": 8001
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 9.055149127743388,
|
| 1323 |
+
"grad_norm": 3.5759809017181396,
|
| 1324 |
+
"learning_rate": 2.1097362829646295e-06,
|
| 1325 |
+
"loss": 0.1629,
|
| 1326 |
+
"step": 8050
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 9.111423747889702,
|
| 1330 |
+
"grad_norm": 3.6214778423309326,
|
| 1331 |
+
"learning_rate": 1.987251593550806e-06,
|
| 1332 |
+
"loss": 0.1694,
|
| 1333 |
+
"step": 8100
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 9.167698368036016,
|
| 1337 |
+
"grad_norm": 6.99995756149292,
|
| 1338 |
+
"learning_rate": 1.8622672165979255e-06,
|
| 1339 |
+
"loss": 0.1775,
|
| 1340 |
+
"step": 8150
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 9.22397298818233,
|
| 1344 |
+
"grad_norm": 4.065187931060791,
|
| 1345 |
+
"learning_rate": 1.7372828396450444e-06,
|
| 1346 |
+
"loss": 0.182,
|
| 1347 |
+
"step": 8200
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 9.280247608328644,
|
| 1351 |
+
"grad_norm": 2.9803073406219482,
|
| 1352 |
+
"learning_rate": 1.6122984626921637e-06,
|
| 1353 |
+
"loss": 0.168,
|
| 1354 |
+
"step": 8250
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 9.336522228474958,
|
| 1358 |
+
"grad_norm": 5.370956897735596,
|
| 1359 |
+
"learning_rate": 1.4873140857392826e-06,
|
| 1360 |
+
"loss": 0.1493,
|
| 1361 |
+
"step": 8300
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 9.392796848621272,
|
| 1365 |
+
"grad_norm": 5.8644890785217285,
|
| 1366 |
+
"learning_rate": 1.3623297087864017e-06,
|
| 1367 |
+
"loss": 0.1511,
|
| 1368 |
+
"step": 8350
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 9.449071468767587,
|
| 1372 |
+
"grad_norm": 4.59880256652832,
|
| 1373 |
+
"learning_rate": 1.2373453318335209e-06,
|
| 1374 |
+
"loss": 0.1626,
|
| 1375 |
+
"step": 8400
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 9.5053460889139,
|
| 1379 |
+
"grad_norm": 3.982597827911377,
|
| 1380 |
+
"learning_rate": 1.11236095488064e-06,
|
| 1381 |
+
"loss": 0.165,
|
| 1382 |
+
"step": 8450
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 9.561620709060215,
|
| 1386 |
+
"grad_norm": 6.357668876647949,
|
| 1387 |
+
"learning_rate": 9.873765779277591e-07,
|
| 1388 |
+
"loss": 0.1659,
|
| 1389 |
+
"step": 8500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 9.617895329206528,
|
| 1393 |
+
"grad_norm": 8.072972297668457,
|
| 1394 |
+
"learning_rate": 8.623922009748782e-07,
|
| 1395 |
+
"loss": 0.186,
|
| 1396 |
+
"step": 8550
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 9.674169949352843,
|
| 1400 |
+
"grad_norm": 4.884040832519531,
|
| 1401 |
+
"learning_rate": 7.374078240219973e-07,
|
| 1402 |
+
"loss": 0.1702,
|
| 1403 |
+
"step": 8600
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 9.730444569499156,
|
| 1407 |
+
"grad_norm": 7.7868123054504395,
|
| 1408 |
+
"learning_rate": 6.124234470691164e-07,
|
| 1409 |
+
"loss": 0.1603,
|
| 1410 |
+
"step": 8650
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 9.78671918964547,
|
| 1414 |
+
"grad_norm": 5.416253089904785,
|
| 1415 |
+
"learning_rate": 4.874390701162355e-07,
|
| 1416 |
+
"loss": 0.152,
|
| 1417 |
+
"step": 8700
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 9.842993809791784,
|
| 1421 |
+
"grad_norm": 5.989937782287598,
|
| 1422 |
+
"learning_rate": 3.6245469316335464e-07,
|
| 1423 |
+
"loss": 0.1558,
|
| 1424 |
+
"step": 8750
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 9.899268429938099,
|
| 1428 |
+
"grad_norm": 5.493338108062744,
|
| 1429 |
+
"learning_rate": 2.374703162104737e-07,
|
| 1430 |
+
"loss": 0.1645,
|
| 1431 |
+
"step": 8800
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 9.955543050084412,
|
| 1435 |
+
"grad_norm": 6.584114074707031,
|
| 1436 |
+
"learning_rate": 1.124859392575928e-07,
|
| 1437 |
+
"loss": 0.1569,
|
| 1438 |
+
"step": 8850
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 10.0,
|
| 1442 |
+
"eval_accuracy": 0.8299261083743842,
|
| 1443 |
+
"eval_f1_fix": 0.998282377189969,
|
| 1444 |
+
"eval_f1_issue": 0.7886029411764706,
|
| 1445 |
+
"eval_f1_symptom": 0.7975297750330834,
|
| 1446 |
+
"eval_f1_weighted": 0.8298131674335786,
|
| 1447 |
+
"eval_loss": 0.5292249321937561,
|
| 1448 |
+
"eval_precision_fix": 0.997254632807138,
|
| 1449 |
+
"eval_precision_issue": 0.8056338028169014,
|
| 1450 |
+
"eval_precision_symptom": 0.7820069204152249,
|
| 1451 |
+
"eval_precision_weighted": 0.8302481239697359,
|
| 1452 |
+
"eval_recall_fix": 0.9993122420907841,
|
| 1453 |
+
"eval_recall_issue": 0.7722772277227723,
|
| 1454 |
+
"eval_recall_symptom": 0.8136813681368137,
|
| 1455 |
+
"eval_recall_weighted": 0.8299261083743842,
|
| 1456 |
+
"eval_runtime": 51.5276,
|
| 1457 |
+
"eval_samples_per_second": 157.585,
|
| 1458 |
+
"eval_steps_per_second": 2.465,
|
| 1459 |
+
"step": 8890
|
| 1460 |
+
}
|
| 1461 |
+
],
|
| 1462 |
+
"logging_steps": 50,
|
| 1463 |
+
"max_steps": 8890,
|
| 1464 |
+
"num_input_tokens_seen": 0,
|
| 1465 |
+
"num_train_epochs": 10,
|
| 1466 |
+
"save_steps": 500,
|
| 1467 |
+
"stateful_callbacks": {
|
| 1468 |
+
"TrainerControl": {
|
| 1469 |
+
"args": {
|
| 1470 |
+
"should_epoch_stop": false,
|
| 1471 |
+
"should_evaluate": false,
|
| 1472 |
+
"should_log": false,
|
| 1473 |
+
"should_save": true,
|
| 1474 |
+
"should_training_stop": true
|
| 1475 |
+
},
|
| 1476 |
+
"attributes": {}
|
| 1477 |
+
}
|
| 1478 |
+
},
|
| 1479 |
+
"total_flos": 3.73930339431168e+16,
|
| 1480 |
+
"train_batch_size": 32,
|
| 1481 |
+
"trial_name": null,
|
| 1482 |
+
"trial_params": null
|
| 1483 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce56ab1da77e9276db469f6da075eed136c005951bc4ce468d1e08ad19e8c618
|
| 3 |
+
size 5777
|