Upload folder using huggingface_hub
Browse files- checkpoint-11000/added_tokens.json +3 -0
- checkpoint-11000/config.json +59 -0
- checkpoint-11000/model.safetensors +3 -0
- checkpoint-11000/optimizer.pt +3 -0
- checkpoint-11000/rng_state.pth +3 -0
- checkpoint-11000/scheduler.pt +3 -0
- checkpoint-11000/special_tokens_map.json +15 -0
- checkpoint-11000/spm.model +3 -0
- checkpoint-11000/tokenizer.json +0 -0
- checkpoint-11000/tokenizer_config.json +59 -0
- checkpoint-11000/trainer_state.json +1610 -0
- checkpoint-11000/training_args.bin +3 -0
- checkpoint-11250/added_tokens.json +3 -0
- checkpoint-11250/config.json +59 -0
- checkpoint-11250/model.safetensors +3 -0
- checkpoint-11250/optimizer.pt +3 -0
- checkpoint-11250/rng_state.pth +3 -0
- checkpoint-11250/scheduler.pt +3 -0
- checkpoint-11250/special_tokens_map.json +15 -0
- checkpoint-11250/spm.model +3 -0
- checkpoint-11250/tokenizer.json +0 -0
- checkpoint-11250/tokenizer_config.json +59 -0
- checkpoint-11250/trainer_state.json +1645 -0
- checkpoint-11250/training_args.bin +3 -0
- config.json +18 -18
- training_args.bin +1 -1
checkpoint-11000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-11000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForTokenClassification"
|
| 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": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6,
|
| 33 |
+
"LABEL_7": 7,
|
| 34 |
+
"LABEL_8": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"max_relative_positions": -1,
|
| 40 |
+
"model_type": "deberta-v2",
|
| 41 |
+
"norm_rel_ebd": "layer_norm",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pooler_dropout": 0,
|
| 46 |
+
"pooler_hidden_act": "gelu",
|
| 47 |
+
"pooler_hidden_size": 768,
|
| 48 |
+
"pos_att_type": [
|
| 49 |
+
"p2c",
|
| 50 |
+
"c2p"
|
| 51 |
+
],
|
| 52 |
+
"position_biased_input": false,
|
| 53 |
+
"position_buckets": 256,
|
| 54 |
+
"relative_attention": true,
|
| 55 |
+
"share_att_key": true,
|
| 56 |
+
"transformers_version": "4.56.1",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
checkpoint-11000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7be134a213b3f5ba1c8cbd8675288bf98b8eca7b890f57bb1ced689d13b1580d
|
| 3 |
+
size 735378268
|
checkpoint-11000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb94ae915eb967a324195739cd401341c643a77a1ebd9c3e8e177a721faca63d
|
| 3 |
+
size 1470878283
|
checkpoint-11000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27c48ae1baa095d00c34734e0c44a3088c7026668efcbb7c0c18c9c8a0b52854
|
| 3 |
+
size 14645
|
checkpoint-11000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4465649d300de9496daf05727c4662b51bf21545195893b7cb1a08daed34ad9
|
| 3 |
+
size 1465
|
checkpoint-11000/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 |
+
}
|
checkpoint-11000/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-11000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11000/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 |
+
}
|
checkpoint-11000/trainer_state.json
ADDED
|
@@ -0,0 +1,1610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.888888888888889,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 11000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022222222222222223,
|
| 14 |
+
"grad_norm": 0.4169579744338989,
|
| 15 |
+
"learning_rate": 4.9782222222222224e-05,
|
| 16 |
+
"loss": 0.2263,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.044444444444444446,
|
| 21 |
+
"grad_norm": 0.33507040143013,
|
| 22 |
+
"learning_rate": 4.956e-05,
|
| 23 |
+
"loss": 0.0174,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06666666666666667,
|
| 28 |
+
"grad_norm": 0.11501526087522507,
|
| 29 |
+
"learning_rate": 4.933777777777778e-05,
|
| 30 |
+
"loss": 0.0101,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08888888888888889,
|
| 35 |
+
"grad_norm": 0.09099342674016953,
|
| 36 |
+
"learning_rate": 4.911555555555556e-05,
|
| 37 |
+
"loss": 0.0061,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1111111111111111,
|
| 42 |
+
"grad_norm": 0.08669792860746384,
|
| 43 |
+
"learning_rate": 4.8893333333333335e-05,
|
| 44 |
+
"loss": 0.0036,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13333333333333333,
|
| 49 |
+
"grad_norm": 0.07038326561450958,
|
| 50 |
+
"learning_rate": 4.867111111111111e-05,
|
| 51 |
+
"loss": 0.0037,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15555555555555556,
|
| 56 |
+
"grad_norm": 0.08929373323917389,
|
| 57 |
+
"learning_rate": 4.8448888888888894e-05,
|
| 58 |
+
"loss": 0.0025,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17777777777777778,
|
| 63 |
+
"grad_norm": 0.010555864311754704,
|
| 64 |
+
"learning_rate": 4.822666666666667e-05,
|
| 65 |
+
"loss": 0.0011,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2,
|
| 70 |
+
"grad_norm": 0.12513870000839233,
|
| 71 |
+
"learning_rate": 4.8004444444444446e-05,
|
| 72 |
+
"loss": 0.0014,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2222222222222222,
|
| 77 |
+
"grad_norm": 0.008826244622468948,
|
| 78 |
+
"learning_rate": 4.778222222222222e-05,
|
| 79 |
+
"loss": 0.0009,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.24444444444444444,
|
| 84 |
+
"grad_norm": 0.3243519067764282,
|
| 85 |
+
"learning_rate": 4.7560000000000005e-05,
|
| 86 |
+
"loss": 0.0003,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.26666666666666666,
|
| 91 |
+
"grad_norm": 0.013048608787357807,
|
| 92 |
+
"learning_rate": 4.733777777777778e-05,
|
| 93 |
+
"loss": 0.003,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.28888888888888886,
|
| 98 |
+
"grad_norm": 0.004392141476273537,
|
| 99 |
+
"learning_rate": 4.711555555555556e-05,
|
| 100 |
+
"loss": 0.0017,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3111111111111111,
|
| 105 |
+
"grad_norm": 0.009453477337956429,
|
| 106 |
+
"learning_rate": 4.6893333333333334e-05,
|
| 107 |
+
"loss": 0.0007,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3333333333333333,
|
| 112 |
+
"grad_norm": 0.29423239827156067,
|
| 113 |
+
"learning_rate": 4.667111111111112e-05,
|
| 114 |
+
"loss": 0.0004,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.35555555555555557,
|
| 119 |
+
"grad_norm": 0.007287424057722092,
|
| 120 |
+
"learning_rate": 4.644888888888889e-05,
|
| 121 |
+
"loss": 0.0004,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37777777777777777,
|
| 126 |
+
"grad_norm": 0.006468615494668484,
|
| 127 |
+
"learning_rate": 4.622666666666667e-05,
|
| 128 |
+
"loss": 0.001,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4,
|
| 133 |
+
"grad_norm": 0.0032176165841519833,
|
| 134 |
+
"learning_rate": 4.6004444444444445e-05,
|
| 135 |
+
"loss": 0.0013,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4222222222222222,
|
| 140 |
+
"grad_norm": 0.0045009879395365715,
|
| 141 |
+
"learning_rate": 4.578222222222223e-05,
|
| 142 |
+
"loss": 0.0009,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4444444444444444,
|
| 147 |
+
"grad_norm": 0.04195983707904816,
|
| 148 |
+
"learning_rate": 4.5560000000000004e-05,
|
| 149 |
+
"loss": 0.0002,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4666666666666667,
|
| 154 |
+
"grad_norm": 0.0009760915418155491,
|
| 155 |
+
"learning_rate": 4.533777777777778e-05,
|
| 156 |
+
"loss": 0.0001,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4888888888888889,
|
| 161 |
+
"grad_norm": 0.0008424059487879276,
|
| 162 |
+
"learning_rate": 4.5115555555555557e-05,
|
| 163 |
+
"loss": 0.0001,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5111111111111111,
|
| 168 |
+
"grad_norm": 0.001366421696729958,
|
| 169 |
+
"learning_rate": 4.489333333333334e-05,
|
| 170 |
+
"loss": 0.0001,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5333333333333333,
|
| 175 |
+
"grad_norm": 0.0733928307890892,
|
| 176 |
+
"learning_rate": 4.4671111111111116e-05,
|
| 177 |
+
"loss": 0.0001,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5555555555555556,
|
| 182 |
+
"grad_norm": 0.005551271606236696,
|
| 183 |
+
"learning_rate": 4.444888888888889e-05,
|
| 184 |
+
"loss": 0.0008,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5777777777777777,
|
| 189 |
+
"grad_norm": 0.0026340284384787083,
|
| 190 |
+
"learning_rate": 4.422666666666667e-05,
|
| 191 |
+
"loss": 0.0002,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6,
|
| 196 |
+
"grad_norm": 0.002755340188741684,
|
| 197 |
+
"learning_rate": 4.400444444444445e-05,
|
| 198 |
+
"loss": 0.0001,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6222222222222222,
|
| 203 |
+
"grad_norm": 0.0008212323882617056,
|
| 204 |
+
"learning_rate": 4.378222222222223e-05,
|
| 205 |
+
"loss": 0.0,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6444444444444445,
|
| 210 |
+
"grad_norm": 0.0005921730189584196,
|
| 211 |
+
"learning_rate": 4.356e-05,
|
| 212 |
+
"loss": 0.0,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6666666666666666,
|
| 217 |
+
"grad_norm": 0.0008460666285827756,
|
| 218 |
+
"learning_rate": 4.333777777777778e-05,
|
| 219 |
+
"loss": 0.0001,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6888888888888889,
|
| 224 |
+
"grad_norm": 0.0006111777038313448,
|
| 225 |
+
"learning_rate": 4.311555555555556e-05,
|
| 226 |
+
"loss": 0.0,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7111111111111111,
|
| 231 |
+
"grad_norm": 0.00046472539543174207,
|
| 232 |
+
"learning_rate": 4.289333333333334e-05,
|
| 233 |
+
"loss": 0.0,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7333333333333333,
|
| 238 |
+
"grad_norm": 0.0007363149197772145,
|
| 239 |
+
"learning_rate": 4.2671111111111114e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7555555555555555,
|
| 245 |
+
"grad_norm": 0.0006023353198543191,
|
| 246 |
+
"learning_rate": 4.244888888888889e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7777777777777778,
|
| 252 |
+
"grad_norm": 0.0004273591039236635,
|
| 253 |
+
"learning_rate": 4.222666666666667e-05,
|
| 254 |
+
"loss": 0.0,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8,
|
| 259 |
+
"grad_norm": 0.0006913533434271812,
|
| 260 |
+
"learning_rate": 4.200444444444445e-05,
|
| 261 |
+
"loss": 0.0,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8222222222222222,
|
| 266 |
+
"grad_norm": 0.0014112872304394841,
|
| 267 |
+
"learning_rate": 4.1782222222222226e-05,
|
| 268 |
+
"loss": 0.0002,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8444444444444444,
|
| 273 |
+
"grad_norm": 0.0024269793648272753,
|
| 274 |
+
"learning_rate": 4.156e-05,
|
| 275 |
+
"loss": 0.0005,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8666666666666667,
|
| 280 |
+
"grad_norm": 0.46272382140159607,
|
| 281 |
+
"learning_rate": 4.133777777777778e-05,
|
| 282 |
+
"loss": 0.0013,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8888888888888888,
|
| 287 |
+
"grad_norm": 0.006871496792882681,
|
| 288 |
+
"learning_rate": 4.1115555555555554e-05,
|
| 289 |
+
"loss": 0.001,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9111111111111111,
|
| 294 |
+
"grad_norm": 0.0022507584653794765,
|
| 295 |
+
"learning_rate": 4.089333333333333e-05,
|
| 296 |
+
"loss": 0.001,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9333333333333333,
|
| 301 |
+
"grad_norm": 0.0077248550951480865,
|
| 302 |
+
"learning_rate": 4.067111111111111e-05,
|
| 303 |
+
"loss": 0.0005,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9555555555555556,
|
| 308 |
+
"grad_norm": 0.0006559474277310073,
|
| 309 |
+
"learning_rate": 4.044888888888889e-05,
|
| 310 |
+
"loss": 0.0003,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.9777777777777777,
|
| 315 |
+
"grad_norm": 0.000827161071356386,
|
| 316 |
+
"learning_rate": 4.0226666666666666e-05,
|
| 317 |
+
"loss": 0.0012,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0,
|
| 322 |
+
"grad_norm": 0.22399061918258667,
|
| 323 |
+
"learning_rate": 4.000444444444444e-05,
|
| 324 |
+
"loss": 0.0005,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0,
|
| 329 |
+
"eval_loss": 0.0001230358611792326,
|
| 330 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 331 |
+
"eval_runtime": 39.9747,
|
| 332 |
+
"eval_samples_per_second": 50.032,
|
| 333 |
+
"eval_steps_per_second": 6.254,
|
| 334 |
+
"step": 2250
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.0222222222222221,
|
| 338 |
+
"grad_norm": 0.0034671323373913765,
|
| 339 |
+
"learning_rate": 3.9782222222222225e-05,
|
| 340 |
+
"loss": 0.0005,
|
| 341 |
+
"step": 2300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.0444444444444445,
|
| 345 |
+
"grad_norm": 0.005704512819647789,
|
| 346 |
+
"learning_rate": 3.956e-05,
|
| 347 |
+
"loss": 0.0024,
|
| 348 |
+
"step": 2350
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.0666666666666667,
|
| 352 |
+
"grad_norm": 0.0016336466651409864,
|
| 353 |
+
"learning_rate": 3.933777777777778e-05,
|
| 354 |
+
"loss": 0.0004,
|
| 355 |
+
"step": 2400
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.0888888888888888,
|
| 359 |
+
"grad_norm": 0.0009551944676786661,
|
| 360 |
+
"learning_rate": 3.911555555555555e-05,
|
| 361 |
+
"loss": 0.0002,
|
| 362 |
+
"step": 2450
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.1111111111111112,
|
| 366 |
+
"grad_norm": 0.0004279686836525798,
|
| 367 |
+
"learning_rate": 3.8893333333333336e-05,
|
| 368 |
+
"loss": 0.0001,
|
| 369 |
+
"step": 2500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.1333333333333333,
|
| 373 |
+
"grad_norm": 0.00043013374670408666,
|
| 374 |
+
"learning_rate": 3.867111111111111e-05,
|
| 375 |
+
"loss": 0.0001,
|
| 376 |
+
"step": 2550
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.1555555555555554,
|
| 380 |
+
"grad_norm": 0.00034906569635495543,
|
| 381 |
+
"learning_rate": 3.844888888888889e-05,
|
| 382 |
+
"loss": 0.0,
|
| 383 |
+
"step": 2600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.1777777777777778,
|
| 387 |
+
"grad_norm": 0.0014709575334563851,
|
| 388 |
+
"learning_rate": 3.8226666666666664e-05,
|
| 389 |
+
"loss": 0.0002,
|
| 390 |
+
"step": 2650
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.2,
|
| 394 |
+
"grad_norm": 0.0006022250163368881,
|
| 395 |
+
"learning_rate": 3.800444444444445e-05,
|
| 396 |
+
"loss": 0.0,
|
| 397 |
+
"step": 2700
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.2222222222222223,
|
| 401 |
+
"grad_norm": 0.000542789523024112,
|
| 402 |
+
"learning_rate": 3.778222222222222e-05,
|
| 403 |
+
"loss": 0.0001,
|
| 404 |
+
"step": 2750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.2444444444444445,
|
| 408 |
+
"grad_norm": 0.00048277038149535656,
|
| 409 |
+
"learning_rate": 3.756e-05,
|
| 410 |
+
"loss": 0.0002,
|
| 411 |
+
"step": 2800
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.2666666666666666,
|
| 415 |
+
"grad_norm": 0.0003071363898925483,
|
| 416 |
+
"learning_rate": 3.7337777777777776e-05,
|
| 417 |
+
"loss": 0.0,
|
| 418 |
+
"step": 2850
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.2888888888888888,
|
| 422 |
+
"grad_norm": 0.0003033171233255416,
|
| 423 |
+
"learning_rate": 3.711555555555556e-05,
|
| 424 |
+
"loss": 0.0,
|
| 425 |
+
"step": 2900
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.3111111111111111,
|
| 429 |
+
"grad_norm": 0.001257324474863708,
|
| 430 |
+
"learning_rate": 3.6893333333333335e-05,
|
| 431 |
+
"loss": 0.0011,
|
| 432 |
+
"step": 2950
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.3333333333333333,
|
| 436 |
+
"grad_norm": 0.0003226712578907609,
|
| 437 |
+
"learning_rate": 3.667111111111111e-05,
|
| 438 |
+
"loss": 0.0002,
|
| 439 |
+
"step": 3000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.3555555555555556,
|
| 443 |
+
"grad_norm": 0.00033422038541175425,
|
| 444 |
+
"learning_rate": 3.644888888888889e-05,
|
| 445 |
+
"loss": 0.0001,
|
| 446 |
+
"step": 3050
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.3777777777777778,
|
| 450 |
+
"grad_norm": 0.0004989306908100843,
|
| 451 |
+
"learning_rate": 3.622666666666667e-05,
|
| 452 |
+
"loss": 0.0,
|
| 453 |
+
"step": 3100
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.4,
|
| 457 |
+
"grad_norm": 0.0002919055405072868,
|
| 458 |
+
"learning_rate": 3.6004444444444446e-05,
|
| 459 |
+
"loss": 0.0,
|
| 460 |
+
"step": 3150
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.4222222222222223,
|
| 464 |
+
"grad_norm": 0.00027494438108988106,
|
| 465 |
+
"learning_rate": 3.578222222222222e-05,
|
| 466 |
+
"loss": 0.0,
|
| 467 |
+
"step": 3200
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.4444444444444444,
|
| 471 |
+
"grad_norm": 0.000610452436376363,
|
| 472 |
+
"learning_rate": 3.5560000000000005e-05,
|
| 473 |
+
"loss": 0.0,
|
| 474 |
+
"step": 3250
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4666666666666668,
|
| 478 |
+
"grad_norm": 0.000538027728907764,
|
| 479 |
+
"learning_rate": 3.533777777777778e-05,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 3300
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.488888888888889,
|
| 485 |
+
"grad_norm": 0.00020039589435327798,
|
| 486 |
+
"learning_rate": 3.511555555555556e-05,
|
| 487 |
+
"loss": 0.0,
|
| 488 |
+
"step": 3350
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.511111111111111,
|
| 492 |
+
"grad_norm": 0.00018263465608470142,
|
| 493 |
+
"learning_rate": 3.4893333333333334e-05,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"step": 3400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.5333333333333332,
|
| 499 |
+
"grad_norm": 0.00019636489741969854,
|
| 500 |
+
"learning_rate": 3.4671111111111116e-05,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 3450
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.5555555555555556,
|
| 506 |
+
"grad_norm": 0.00028676423244178295,
|
| 507 |
+
"learning_rate": 3.444888888888889e-05,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 3500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.5777777777777777,
|
| 513 |
+
"grad_norm": 0.00019564179820008576,
|
| 514 |
+
"learning_rate": 3.422666666666667e-05,
|
| 515 |
+
"loss": 0.0,
|
| 516 |
+
"step": 3550
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.6,
|
| 520 |
+
"grad_norm": 0.00020010425942018628,
|
| 521 |
+
"learning_rate": 3.4004444444444445e-05,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"step": 3600
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.6222222222222222,
|
| 527 |
+
"grad_norm": 0.00015156572044361383,
|
| 528 |
+
"learning_rate": 3.378222222222223e-05,
|
| 529 |
+
"loss": 0.0,
|
| 530 |
+
"step": 3650
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.6444444444444444,
|
| 534 |
+
"grad_norm": 0.0001559116062708199,
|
| 535 |
+
"learning_rate": 3.3560000000000004e-05,
|
| 536 |
+
"loss": 0.0,
|
| 537 |
+
"step": 3700
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.6666666666666665,
|
| 541 |
+
"grad_norm": 0.00017668222426436841,
|
| 542 |
+
"learning_rate": 3.333777777777778e-05,
|
| 543 |
+
"loss": 0.0,
|
| 544 |
+
"step": 3750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.6888888888888889,
|
| 548 |
+
"grad_norm": 0.00015294237527996302,
|
| 549 |
+
"learning_rate": 3.3115555555555556e-05,
|
| 550 |
+
"loss": 0.0,
|
| 551 |
+
"step": 3800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.7111111111111112,
|
| 555 |
+
"grad_norm": 0.00020564977603498846,
|
| 556 |
+
"learning_rate": 3.289333333333334e-05,
|
| 557 |
+
"loss": 0.0,
|
| 558 |
+
"step": 3850
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.7333333333333334,
|
| 562 |
+
"grad_norm": 0.00015193119179457426,
|
| 563 |
+
"learning_rate": 3.2671111111111115e-05,
|
| 564 |
+
"loss": 0.0,
|
| 565 |
+
"step": 3900
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.7555555555555555,
|
| 569 |
+
"grad_norm": 0.00013517968181986362,
|
| 570 |
+
"learning_rate": 3.244888888888889e-05,
|
| 571 |
+
"loss": 0.0,
|
| 572 |
+
"step": 3950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.7777777777777777,
|
| 576 |
+
"grad_norm": 0.00027755036717280746,
|
| 577 |
+
"learning_rate": 3.222666666666667e-05,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"step": 4000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.8,
|
| 583 |
+
"grad_norm": 0.0001287544146180153,
|
| 584 |
+
"learning_rate": 3.200444444444445e-05,
|
| 585 |
+
"loss": 0.0,
|
| 586 |
+
"step": 4050
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.8222222222222222,
|
| 590 |
+
"grad_norm": 0.0001332290848949924,
|
| 591 |
+
"learning_rate": 3.178222222222223e-05,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 4100
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.8444444444444446,
|
| 597 |
+
"grad_norm": 0.00012569426326081157,
|
| 598 |
+
"learning_rate": 3.156e-05,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 4150
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.8666666666666667,
|
| 604 |
+
"grad_norm": 0.00011655821435851976,
|
| 605 |
+
"learning_rate": 3.133777777777778e-05,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"step": 4200
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.8888888888888888,
|
| 611 |
+
"grad_norm": 0.0001188791575259529,
|
| 612 |
+
"learning_rate": 3.111555555555556e-05,
|
| 613 |
+
"loss": 0.0,
|
| 614 |
+
"step": 4250
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.911111111111111,
|
| 618 |
+
"grad_norm": 0.00010238583490718156,
|
| 619 |
+
"learning_rate": 3.089333333333334e-05,
|
| 620 |
+
"loss": 0.0,
|
| 621 |
+
"step": 4300
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.9333333333333333,
|
| 625 |
+
"grad_norm": 0.0001092032398446463,
|
| 626 |
+
"learning_rate": 3.0671111111111114e-05,
|
| 627 |
+
"loss": 0.0,
|
| 628 |
+
"step": 4350
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.9555555555555557,
|
| 632 |
+
"grad_norm": 0.00014390636351890862,
|
| 633 |
+
"learning_rate": 3.0448888888888887e-05,
|
| 634 |
+
"loss": 0.0,
|
| 635 |
+
"step": 4400
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.9777777777777779,
|
| 639 |
+
"grad_norm": 0.00010023260256275535,
|
| 640 |
+
"learning_rate": 3.022666666666667e-05,
|
| 641 |
+
"loss": 0.0,
|
| 642 |
+
"step": 4450
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.0,
|
| 646 |
+
"grad_norm": 0.00010638952517183498,
|
| 647 |
+
"learning_rate": 3.0004444444444446e-05,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"step": 4500
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.0,
|
| 653 |
+
"eval_loss": 1.410930394740717e-06,
|
| 654 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 655 |
+
"eval_runtime": 39.342,
|
| 656 |
+
"eval_samples_per_second": 50.836,
|
| 657 |
+
"eval_steps_per_second": 6.355,
|
| 658 |
+
"step": 4500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.022222222222222,
|
| 662 |
+
"grad_norm": 0.00010032003774540499,
|
| 663 |
+
"learning_rate": 2.9782222222222222e-05,
|
| 664 |
+
"loss": 0.0,
|
| 665 |
+
"step": 4550
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.0444444444444443,
|
| 669 |
+
"grad_norm": 0.00048742775106802583,
|
| 670 |
+
"learning_rate": 2.9559999999999998e-05,
|
| 671 |
+
"loss": 0.0,
|
| 672 |
+
"step": 4600
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.066666666666667,
|
| 676 |
+
"grad_norm": 9.531196701573208e-05,
|
| 677 |
+
"learning_rate": 2.933777777777778e-05,
|
| 678 |
+
"loss": 0.0,
|
| 679 |
+
"step": 4650
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.088888888888889,
|
| 683 |
+
"grad_norm": 9.425494499737397e-05,
|
| 684 |
+
"learning_rate": 2.9115555555555557e-05,
|
| 685 |
+
"loss": 0.0,
|
| 686 |
+
"step": 4700
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.111111111111111,
|
| 690 |
+
"grad_norm": 0.00011574638483580202,
|
| 691 |
+
"learning_rate": 2.8893333333333333e-05,
|
| 692 |
+
"loss": 0.0,
|
| 693 |
+
"step": 4750
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.1333333333333333,
|
| 697 |
+
"grad_norm": 9.062536264536902e-05,
|
| 698 |
+
"learning_rate": 2.8671111111111116e-05,
|
| 699 |
+
"loss": 0.0,
|
| 700 |
+
"step": 4800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.1555555555555554,
|
| 704 |
+
"grad_norm": 9.913908434100449e-05,
|
| 705 |
+
"learning_rate": 2.8448888888888892e-05,
|
| 706 |
+
"loss": 0.0,
|
| 707 |
+
"step": 4850
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.1777777777777776,
|
| 711 |
+
"grad_norm": 0.00010020509216701612,
|
| 712 |
+
"learning_rate": 2.822666666666667e-05,
|
| 713 |
+
"loss": 0.0,
|
| 714 |
+
"step": 4900
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.2,
|
| 718 |
+
"grad_norm": 0.00012128752132412046,
|
| 719 |
+
"learning_rate": 2.8004444444444445e-05,
|
| 720 |
+
"loss": 0.0,
|
| 721 |
+
"step": 4950
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.2222222222222223,
|
| 725 |
+
"grad_norm": 0.02587141841650009,
|
| 726 |
+
"learning_rate": 2.7782222222222228e-05,
|
| 727 |
+
"loss": 0.0,
|
| 728 |
+
"step": 5000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.2444444444444445,
|
| 732 |
+
"grad_norm": 8.068871829891577e-05,
|
| 733 |
+
"learning_rate": 2.7560000000000004e-05,
|
| 734 |
+
"loss": 0.0,
|
| 735 |
+
"step": 5050
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.2666666666666666,
|
| 739 |
+
"grad_norm": 8.70975709403865e-05,
|
| 740 |
+
"learning_rate": 2.733777777777778e-05,
|
| 741 |
+
"loss": 0.0,
|
| 742 |
+
"step": 5100
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.2888888888888888,
|
| 746 |
+
"grad_norm": 8.906049333745614e-05,
|
| 747 |
+
"learning_rate": 2.7115555555555556e-05,
|
| 748 |
+
"loss": 0.0,
|
| 749 |
+
"step": 5150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.311111111111111,
|
| 753 |
+
"grad_norm": 7.555448246421292e-05,
|
| 754 |
+
"learning_rate": 2.6893333333333336e-05,
|
| 755 |
+
"loss": 0.0,
|
| 756 |
+
"step": 5200
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.3333333333333335,
|
| 760 |
+
"grad_norm": 0.00033314700704067945,
|
| 761 |
+
"learning_rate": 2.6671111111111112e-05,
|
| 762 |
+
"loss": 0.0,
|
| 763 |
+
"step": 5250
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.3555555555555556,
|
| 767 |
+
"grad_norm": 8.106895256787539e-05,
|
| 768 |
+
"learning_rate": 2.644888888888889e-05,
|
| 769 |
+
"loss": 0.0,
|
| 770 |
+
"step": 5300
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.3777777777777778,
|
| 774 |
+
"grad_norm": 0.0002253134734928608,
|
| 775 |
+
"learning_rate": 2.6226666666666667e-05,
|
| 776 |
+
"loss": 0.0002,
|
| 777 |
+
"step": 5350
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.4,
|
| 781 |
+
"grad_norm": 0.04773925617337227,
|
| 782 |
+
"learning_rate": 2.6004444444444447e-05,
|
| 783 |
+
"loss": 0.0016,
|
| 784 |
+
"step": 5400
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.422222222222222,
|
| 788 |
+
"grad_norm": 0.013284893706440926,
|
| 789 |
+
"learning_rate": 2.5782222222222223e-05,
|
| 790 |
+
"loss": 0.0013,
|
| 791 |
+
"step": 5450
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.4444444444444446,
|
| 795 |
+
"grad_norm": 0.0019914733711630106,
|
| 796 |
+
"learning_rate": 2.556e-05,
|
| 797 |
+
"loss": 0.001,
|
| 798 |
+
"step": 5500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.466666666666667,
|
| 802 |
+
"grad_norm": 0.00029465914121828973,
|
| 803 |
+
"learning_rate": 2.5337777777777775e-05,
|
| 804 |
+
"loss": 0.0001,
|
| 805 |
+
"step": 5550
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.488888888888889,
|
| 809 |
+
"grad_norm": 0.0010584425181150436,
|
| 810 |
+
"learning_rate": 2.5115555555555558e-05,
|
| 811 |
+
"loss": 0.0,
|
| 812 |
+
"step": 5600
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.511111111111111,
|
| 816 |
+
"grad_norm": 0.00024866798776201904,
|
| 817 |
+
"learning_rate": 2.4893333333333334e-05,
|
| 818 |
+
"loss": 0.0,
|
| 819 |
+
"step": 5650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.533333333333333,
|
| 823 |
+
"grad_norm": 0.00015023746527731419,
|
| 824 |
+
"learning_rate": 2.467111111111111e-05,
|
| 825 |
+
"loss": 0.0,
|
| 826 |
+
"step": 5700
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.5555555555555554,
|
| 830 |
+
"grad_norm": 0.00020707614021375775,
|
| 831 |
+
"learning_rate": 2.444888888888889e-05,
|
| 832 |
+
"loss": 0.0,
|
| 833 |
+
"step": 5750
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.5777777777777775,
|
| 837 |
+
"grad_norm": 0.00013307879271451384,
|
| 838 |
+
"learning_rate": 2.4226666666666666e-05,
|
| 839 |
+
"loss": 0.0,
|
| 840 |
+
"step": 5800
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.6,
|
| 844 |
+
"grad_norm": 0.00012964503548573703,
|
| 845 |
+
"learning_rate": 2.4004444444444446e-05,
|
| 846 |
+
"loss": 0.0,
|
| 847 |
+
"step": 5850
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.6222222222222222,
|
| 851 |
+
"grad_norm": 0.00012642733054235578,
|
| 852 |
+
"learning_rate": 2.3782222222222222e-05,
|
| 853 |
+
"loss": 0.0,
|
| 854 |
+
"step": 5900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.6444444444444444,
|
| 858 |
+
"grad_norm": 0.00172146107070148,
|
| 859 |
+
"learning_rate": 2.356e-05,
|
| 860 |
+
"loss": 0.0005,
|
| 861 |
+
"step": 5950
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.6666666666666665,
|
| 865 |
+
"grad_norm": 0.00067210040288046,
|
| 866 |
+
"learning_rate": 2.3337777777777778e-05,
|
| 867 |
+
"loss": 0.0003,
|
| 868 |
+
"step": 6000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.688888888888889,
|
| 872 |
+
"grad_norm": 0.0019879883620887995,
|
| 873 |
+
"learning_rate": 2.3115555555555557e-05,
|
| 874 |
+
"loss": 0.0001,
|
| 875 |
+
"step": 6050
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.7111111111111112,
|
| 879 |
+
"grad_norm": 0.00017190357903018594,
|
| 880 |
+
"learning_rate": 2.2893333333333333e-05,
|
| 881 |
+
"loss": 0.0,
|
| 882 |
+
"step": 6100
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.7333333333333334,
|
| 886 |
+
"grad_norm": 0.00015691675071138889,
|
| 887 |
+
"learning_rate": 2.2671111111111113e-05,
|
| 888 |
+
"loss": 0.0,
|
| 889 |
+
"step": 6150
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.7555555555555555,
|
| 893 |
+
"grad_norm": 0.0001467355468776077,
|
| 894 |
+
"learning_rate": 2.244888888888889e-05,
|
| 895 |
+
"loss": 0.0,
|
| 896 |
+
"step": 6200
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.7777777777777777,
|
| 900 |
+
"grad_norm": 0.00015619705663993955,
|
| 901 |
+
"learning_rate": 2.222666666666667e-05,
|
| 902 |
+
"loss": 0.0,
|
| 903 |
+
"step": 6250
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.8,
|
| 907 |
+
"grad_norm": 0.0002816039486788213,
|
| 908 |
+
"learning_rate": 2.2004444444444445e-05,
|
| 909 |
+
"loss": 0.0,
|
| 910 |
+
"step": 6300
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.822222222222222,
|
| 914 |
+
"grad_norm": 0.0002559045678935945,
|
| 915 |
+
"learning_rate": 2.1782222222222224e-05,
|
| 916 |
+
"loss": 0.0,
|
| 917 |
+
"step": 6350
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.8444444444444446,
|
| 921 |
+
"grad_norm": 0.00017076350923161954,
|
| 922 |
+
"learning_rate": 2.1560000000000004e-05,
|
| 923 |
+
"loss": 0.0,
|
| 924 |
+
"step": 6400
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.8666666666666667,
|
| 928 |
+
"grad_norm": 9.32483744691126e-05,
|
| 929 |
+
"learning_rate": 2.133777777777778e-05,
|
| 930 |
+
"loss": 0.0,
|
| 931 |
+
"step": 6450
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.888888888888889,
|
| 935 |
+
"grad_norm": 9.684438555268571e-05,
|
| 936 |
+
"learning_rate": 2.111555555555556e-05,
|
| 937 |
+
"loss": 0.0,
|
| 938 |
+
"step": 6500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.911111111111111,
|
| 942 |
+
"grad_norm": 0.00010544607357587665,
|
| 943 |
+
"learning_rate": 2.0893333333333335e-05,
|
| 944 |
+
"loss": 0.0,
|
| 945 |
+
"step": 6550
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.9333333333333336,
|
| 949 |
+
"grad_norm": 9.587592649040744e-05,
|
| 950 |
+
"learning_rate": 2.0671111111111115e-05,
|
| 951 |
+
"loss": 0.0,
|
| 952 |
+
"step": 6600
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.9555555555555557,
|
| 956 |
+
"grad_norm": 0.00025339287822134793,
|
| 957 |
+
"learning_rate": 2.044888888888889e-05,
|
| 958 |
+
"loss": 0.0,
|
| 959 |
+
"step": 6650
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.977777777777778,
|
| 963 |
+
"grad_norm": 8.56281112646684e-05,
|
| 964 |
+
"learning_rate": 2.0226666666666667e-05,
|
| 965 |
+
"loss": 0.0,
|
| 966 |
+
"step": 6700
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.0,
|
| 970 |
+
"grad_norm": 8.848596917232499e-05,
|
| 971 |
+
"learning_rate": 2.0004444444444447e-05,
|
| 972 |
+
"loss": 0.0,
|
| 973 |
+
"step": 6750
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.0,
|
| 977 |
+
"eval_loss": 9.946712680175551e-07,
|
| 978 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 979 |
+
"eval_runtime": 39.3914,
|
| 980 |
+
"eval_samples_per_second": 50.773,
|
| 981 |
+
"eval_steps_per_second": 6.347,
|
| 982 |
+
"step": 6750
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.022222222222222,
|
| 986 |
+
"grad_norm": 7.696033571846783e-05,
|
| 987 |
+
"learning_rate": 1.9782222222222223e-05,
|
| 988 |
+
"loss": 0.0,
|
| 989 |
+
"step": 6800
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.0444444444444443,
|
| 993 |
+
"grad_norm": 6.949145608814433e-05,
|
| 994 |
+
"learning_rate": 1.956e-05,
|
| 995 |
+
"loss": 0.0,
|
| 996 |
+
"step": 6850
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.066666666666667,
|
| 1000 |
+
"grad_norm": 8.268443343695253e-05,
|
| 1001 |
+
"learning_rate": 1.933777777777778e-05,
|
| 1002 |
+
"loss": 0.0,
|
| 1003 |
+
"step": 6900
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.088888888888889,
|
| 1007 |
+
"grad_norm": 7.342168828472495e-05,
|
| 1008 |
+
"learning_rate": 1.9115555555555555e-05,
|
| 1009 |
+
"loss": 0.0,
|
| 1010 |
+
"step": 6950
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.111111111111111,
|
| 1014 |
+
"grad_norm": 6.869197386549786e-05,
|
| 1015 |
+
"learning_rate": 1.8893333333333334e-05,
|
| 1016 |
+
"loss": 0.0,
|
| 1017 |
+
"step": 7000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.1333333333333333,
|
| 1021 |
+
"grad_norm": 6.17999758105725e-05,
|
| 1022 |
+
"learning_rate": 1.867111111111111e-05,
|
| 1023 |
+
"loss": 0.0,
|
| 1024 |
+
"step": 7050
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.1555555555555554,
|
| 1028 |
+
"grad_norm": 9.41220423555933e-05,
|
| 1029 |
+
"learning_rate": 1.844888888888889e-05,
|
| 1030 |
+
"loss": 0.0014,
|
| 1031 |
+
"step": 7100
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.1777777777777776,
|
| 1035 |
+
"grad_norm": 0.00021578388987109065,
|
| 1036 |
+
"learning_rate": 1.8226666666666666e-05,
|
| 1037 |
+
"loss": 0.0001,
|
| 1038 |
+
"step": 7150
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.2,
|
| 1042 |
+
"grad_norm": 0.0057373447343707085,
|
| 1043 |
+
"learning_rate": 1.8004444444444446e-05,
|
| 1044 |
+
"loss": 0.0002,
|
| 1045 |
+
"step": 7200
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.2222222222222223,
|
| 1049 |
+
"grad_norm": 0.00015577590966131538,
|
| 1050 |
+
"learning_rate": 1.7782222222222222e-05,
|
| 1051 |
+
"loss": 0.0003,
|
| 1052 |
+
"step": 7250
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.2444444444444445,
|
| 1056 |
+
"grad_norm": 0.0001663435687078163,
|
| 1057 |
+
"learning_rate": 1.756e-05,
|
| 1058 |
+
"loss": 0.0,
|
| 1059 |
+
"step": 7300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.2666666666666666,
|
| 1063 |
+
"grad_norm": 0.00011119741975562647,
|
| 1064 |
+
"learning_rate": 1.7337777777777777e-05,
|
| 1065 |
+
"loss": 0.0,
|
| 1066 |
+
"step": 7350
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.2888888888888888,
|
| 1070 |
+
"grad_norm": 0.0001374996645608917,
|
| 1071 |
+
"learning_rate": 1.7115555555555557e-05,
|
| 1072 |
+
"loss": 0.0,
|
| 1073 |
+
"step": 7400
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.311111111111111,
|
| 1077 |
+
"grad_norm": 0.00021004487643949687,
|
| 1078 |
+
"learning_rate": 1.6893333333333333e-05,
|
| 1079 |
+
"loss": 0.0,
|
| 1080 |
+
"step": 7450
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.3333333333333335,
|
| 1084 |
+
"grad_norm": 0.0001712692028377205,
|
| 1085 |
+
"learning_rate": 1.6671111111111113e-05,
|
| 1086 |
+
"loss": 0.0,
|
| 1087 |
+
"step": 7500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.3555555555555556,
|
| 1091 |
+
"grad_norm": 9.832726209424436e-05,
|
| 1092 |
+
"learning_rate": 1.644888888888889e-05,
|
| 1093 |
+
"loss": 0.0,
|
| 1094 |
+
"step": 7550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.3777777777777778,
|
| 1098 |
+
"grad_norm": 9.489347576163709e-05,
|
| 1099 |
+
"learning_rate": 1.6226666666666668e-05,
|
| 1100 |
+
"loss": 0.0,
|
| 1101 |
+
"step": 7600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.4,
|
| 1105 |
+
"grad_norm": 9.42831247812137e-05,
|
| 1106 |
+
"learning_rate": 1.6004444444444444e-05,
|
| 1107 |
+
"loss": 0.0,
|
| 1108 |
+
"step": 7650
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.422222222222222,
|
| 1112 |
+
"grad_norm": 0.0001237511314684525,
|
| 1113 |
+
"learning_rate": 1.5782222222222224e-05,
|
| 1114 |
+
"loss": 0.0,
|
| 1115 |
+
"step": 7700
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.4444444444444446,
|
| 1119 |
+
"grad_norm": 6.492211105069146e-05,
|
| 1120 |
+
"learning_rate": 1.556e-05,
|
| 1121 |
+
"loss": 0.0,
|
| 1122 |
+
"step": 7750
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.466666666666667,
|
| 1126 |
+
"grad_norm": 6.56497068121098e-05,
|
| 1127 |
+
"learning_rate": 1.533777777777778e-05,
|
| 1128 |
+
"loss": 0.0,
|
| 1129 |
+
"step": 7800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.488888888888889,
|
| 1133 |
+
"grad_norm": 6.696177297271788e-05,
|
| 1134 |
+
"learning_rate": 1.5115555555555556e-05,
|
| 1135 |
+
"loss": 0.0,
|
| 1136 |
+
"step": 7850
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.511111111111111,
|
| 1140 |
+
"grad_norm": 5.779510684078559e-05,
|
| 1141 |
+
"learning_rate": 1.4893333333333334e-05,
|
| 1142 |
+
"loss": 0.0,
|
| 1143 |
+
"step": 7900
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.533333333333333,
|
| 1147 |
+
"grad_norm": 6.52693779557012e-05,
|
| 1148 |
+
"learning_rate": 1.467111111111111e-05,
|
| 1149 |
+
"loss": 0.0,
|
| 1150 |
+
"step": 7950
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.5555555555555554,
|
| 1154 |
+
"grad_norm": 9.678869537310675e-05,
|
| 1155 |
+
"learning_rate": 1.444888888888889e-05,
|
| 1156 |
+
"loss": 0.0,
|
| 1157 |
+
"step": 8000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.5777777777777775,
|
| 1161 |
+
"grad_norm": 5.08545599586796e-05,
|
| 1162 |
+
"learning_rate": 1.4226666666666669e-05,
|
| 1163 |
+
"loss": 0.0,
|
| 1164 |
+
"step": 8050
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.6,
|
| 1168 |
+
"grad_norm": 0.0001278165145777166,
|
| 1169 |
+
"learning_rate": 1.4004444444444445e-05,
|
| 1170 |
+
"loss": 0.0,
|
| 1171 |
+
"step": 8100
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.6222222222222222,
|
| 1175 |
+
"grad_norm": 5.6915894674602896e-05,
|
| 1176 |
+
"learning_rate": 1.3782222222222224e-05,
|
| 1177 |
+
"loss": 0.0,
|
| 1178 |
+
"step": 8150
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.6444444444444444,
|
| 1182 |
+
"grad_norm": 5.536643220693804e-05,
|
| 1183 |
+
"learning_rate": 1.356e-05,
|
| 1184 |
+
"loss": 0.0,
|
| 1185 |
+
"step": 8200
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.6666666666666665,
|
| 1189 |
+
"grad_norm": 6.497505819424987e-05,
|
| 1190 |
+
"learning_rate": 1.333777777777778e-05,
|
| 1191 |
+
"loss": 0.0,
|
| 1192 |
+
"step": 8250
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.688888888888889,
|
| 1196 |
+
"grad_norm": 4.67045720142778e-05,
|
| 1197 |
+
"learning_rate": 1.3115555555555556e-05,
|
| 1198 |
+
"loss": 0.0,
|
| 1199 |
+
"step": 8300
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.7111111111111112,
|
| 1203 |
+
"grad_norm": 5.038898962084204e-05,
|
| 1204 |
+
"learning_rate": 1.2893333333333336e-05,
|
| 1205 |
+
"loss": 0.0,
|
| 1206 |
+
"step": 8350
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.7333333333333334,
|
| 1210 |
+
"grad_norm": 4.441513374331407e-05,
|
| 1211 |
+
"learning_rate": 1.2671111111111112e-05,
|
| 1212 |
+
"loss": 0.0,
|
| 1213 |
+
"step": 8400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.7555555555555555,
|
| 1217 |
+
"grad_norm": 5.228264126344584e-05,
|
| 1218 |
+
"learning_rate": 1.244888888888889e-05,
|
| 1219 |
+
"loss": 0.0,
|
| 1220 |
+
"step": 8450
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.7777777777777777,
|
| 1224 |
+
"grad_norm": 4.654955773730762e-05,
|
| 1225 |
+
"learning_rate": 1.2226666666666668e-05,
|
| 1226 |
+
"loss": 0.0,
|
| 1227 |
+
"step": 8500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.8,
|
| 1231 |
+
"grad_norm": 5.188977957004681e-05,
|
| 1232 |
+
"learning_rate": 1.2004444444444444e-05,
|
| 1233 |
+
"loss": 0.0,
|
| 1234 |
+
"step": 8550
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.822222222222222,
|
| 1238 |
+
"grad_norm": 0.002792242681607604,
|
| 1239 |
+
"learning_rate": 1.1782222222222222e-05,
|
| 1240 |
+
"loss": 0.0,
|
| 1241 |
+
"step": 8600
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.8444444444444446,
|
| 1245 |
+
"grad_norm": 5.102707291371189e-05,
|
| 1246 |
+
"learning_rate": 1.156e-05,
|
| 1247 |
+
"loss": 0.0,
|
| 1248 |
+
"step": 8650
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.8666666666666667,
|
| 1252 |
+
"grad_norm": 4.642659405362792e-05,
|
| 1253 |
+
"learning_rate": 1.1337777777777777e-05,
|
| 1254 |
+
"loss": 0.0,
|
| 1255 |
+
"step": 8700
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.888888888888889,
|
| 1259 |
+
"grad_norm": 4.101167724002153e-05,
|
| 1260 |
+
"learning_rate": 1.1115555555555555e-05,
|
| 1261 |
+
"loss": 0.0,
|
| 1262 |
+
"step": 8750
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.911111111111111,
|
| 1266 |
+
"grad_norm": 4.7815203288337216e-05,
|
| 1267 |
+
"learning_rate": 1.0893333333333333e-05,
|
| 1268 |
+
"loss": 0.0,
|
| 1269 |
+
"step": 8800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.9333333333333336,
|
| 1273 |
+
"grad_norm": 4.7473920858465135e-05,
|
| 1274 |
+
"learning_rate": 1.0671111111111112e-05,
|
| 1275 |
+
"loss": 0.0,
|
| 1276 |
+
"step": 8850
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.9555555555555557,
|
| 1280 |
+
"grad_norm": 4.0860795706976205e-05,
|
| 1281 |
+
"learning_rate": 1.044888888888889e-05,
|
| 1282 |
+
"loss": 0.0,
|
| 1283 |
+
"step": 8900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.977777777777778,
|
| 1287 |
+
"grad_norm": 3.960240792366676e-05,
|
| 1288 |
+
"learning_rate": 1.0226666666666668e-05,
|
| 1289 |
+
"loss": 0.0,
|
| 1290 |
+
"step": 8950
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.0,
|
| 1294 |
+
"grad_norm": 4.005260416306555e-05,
|
| 1295 |
+
"learning_rate": 1.0004444444444446e-05,
|
| 1296 |
+
"loss": 0.0,
|
| 1297 |
+
"step": 9000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.0,
|
| 1301 |
+
"eval_loss": 3.7440361211338313e-07,
|
| 1302 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 1303 |
+
"eval_runtime": 39.2169,
|
| 1304 |
+
"eval_samples_per_second": 50.998,
|
| 1305 |
+
"eval_steps_per_second": 6.375,
|
| 1306 |
+
"step": 9000
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.022222222222222,
|
| 1310 |
+
"grad_norm": 4.486538819037378e-05,
|
| 1311 |
+
"learning_rate": 9.782222222222224e-06,
|
| 1312 |
+
"loss": 0.0,
|
| 1313 |
+
"step": 9050
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 4.044444444444444,
|
| 1317 |
+
"grad_norm": 4.269111741450615e-05,
|
| 1318 |
+
"learning_rate": 9.560000000000002e-06,
|
| 1319 |
+
"loss": 0.0,
|
| 1320 |
+
"step": 9100
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 4.066666666666666,
|
| 1324 |
+
"grad_norm": 3.833163282251917e-05,
|
| 1325 |
+
"learning_rate": 9.337777777777778e-06,
|
| 1326 |
+
"loss": 0.0,
|
| 1327 |
+
"step": 9150
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 4.088888888888889,
|
| 1331 |
+
"grad_norm": 5.278285243548453e-05,
|
| 1332 |
+
"learning_rate": 9.115555555555556e-06,
|
| 1333 |
+
"loss": 0.0,
|
| 1334 |
+
"step": 9200
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.111111111111111,
|
| 1338 |
+
"grad_norm": 3.422492227400653e-05,
|
| 1339 |
+
"learning_rate": 8.893333333333333e-06,
|
| 1340 |
+
"loss": 0.0,
|
| 1341 |
+
"step": 9250
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 4.133333333333334,
|
| 1345 |
+
"grad_norm": 3.486883360892534e-05,
|
| 1346 |
+
"learning_rate": 8.671111111111111e-06,
|
| 1347 |
+
"loss": 0.0,
|
| 1348 |
+
"step": 9300
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 4.155555555555556,
|
| 1352 |
+
"grad_norm": 3.659820868051611e-05,
|
| 1353 |
+
"learning_rate": 8.448888888888889e-06,
|
| 1354 |
+
"loss": 0.0,
|
| 1355 |
+
"step": 9350
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 4.177777777777778,
|
| 1359 |
+
"grad_norm": 3.242024467908777e-05,
|
| 1360 |
+
"learning_rate": 8.226666666666667e-06,
|
| 1361 |
+
"loss": 0.0,
|
| 1362 |
+
"step": 9400
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.2,
|
| 1366 |
+
"grad_norm": 0.0001435010926797986,
|
| 1367 |
+
"learning_rate": 8.004444444444445e-06,
|
| 1368 |
+
"loss": 0.0,
|
| 1369 |
+
"step": 9450
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 4.222222222222222,
|
| 1373 |
+
"grad_norm": 3.879176438204013e-05,
|
| 1374 |
+
"learning_rate": 7.782222222222223e-06,
|
| 1375 |
+
"loss": 0.0,
|
| 1376 |
+
"step": 9500
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 4.2444444444444445,
|
| 1380 |
+
"grad_norm": 3.1664359994465485e-05,
|
| 1381 |
+
"learning_rate": 7.5600000000000005e-06,
|
| 1382 |
+
"loss": 0.0,
|
| 1383 |
+
"step": 9550
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 4.266666666666667,
|
| 1387 |
+
"grad_norm": 3.302018012618646e-05,
|
| 1388 |
+
"learning_rate": 7.337777777777778e-06,
|
| 1389 |
+
"loss": 0.0,
|
| 1390 |
+
"step": 9600
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 4.288888888888889,
|
| 1394 |
+
"grad_norm": 0.00034453265834599733,
|
| 1395 |
+
"learning_rate": 7.115555555555556e-06,
|
| 1396 |
+
"loss": 0.0,
|
| 1397 |
+
"step": 9650
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 4.311111111111111,
|
| 1401 |
+
"grad_norm": 3.3918331610038877e-05,
|
| 1402 |
+
"learning_rate": 6.893333333333334e-06,
|
| 1403 |
+
"loss": 0.0,
|
| 1404 |
+
"step": 9700
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 4.333333333333333,
|
| 1408 |
+
"grad_norm": 3.994768121629022e-05,
|
| 1409 |
+
"learning_rate": 6.671111111111111e-06,
|
| 1410 |
+
"loss": 0.0,
|
| 1411 |
+
"step": 9750
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.355555555555555,
|
| 1415 |
+
"grad_norm": 7.467544492101297e-05,
|
| 1416 |
+
"learning_rate": 6.448888888888889e-06,
|
| 1417 |
+
"loss": 0.0,
|
| 1418 |
+
"step": 9800
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.377777777777778,
|
| 1422 |
+
"grad_norm": 3.103712879237719e-05,
|
| 1423 |
+
"learning_rate": 6.226666666666667e-06,
|
| 1424 |
+
"loss": 0.0,
|
| 1425 |
+
"step": 9850
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 4.4,
|
| 1429 |
+
"grad_norm": 4.751016604132019e-05,
|
| 1430 |
+
"learning_rate": 6.0044444444444445e-06,
|
| 1431 |
+
"loss": 0.0,
|
| 1432 |
+
"step": 9900
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 4.4222222222222225,
|
| 1436 |
+
"grad_norm": 9.309023153036833e-05,
|
| 1437 |
+
"learning_rate": 5.782222222222222e-06,
|
| 1438 |
+
"loss": 0.0,
|
| 1439 |
+
"step": 9950
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 4.444444444444445,
|
| 1443 |
+
"grad_norm": 3.0390472602448426e-05,
|
| 1444 |
+
"learning_rate": 5.56e-06,
|
| 1445 |
+
"loss": 0.0,
|
| 1446 |
+
"step": 10000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 4.466666666666667,
|
| 1450 |
+
"grad_norm": 3.085477146669291e-05,
|
| 1451 |
+
"learning_rate": 5.337777777777778e-06,
|
| 1452 |
+
"loss": 0.0,
|
| 1453 |
+
"step": 10050
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 4.488888888888889,
|
| 1457 |
+
"grad_norm": 3.4081851481460035e-05,
|
| 1458 |
+
"learning_rate": 5.115555555555556e-06,
|
| 1459 |
+
"loss": 0.0,
|
| 1460 |
+
"step": 10100
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 4.511111111111111,
|
| 1464 |
+
"grad_norm": 3.805098822340369e-05,
|
| 1465 |
+
"learning_rate": 4.893333333333334e-06,
|
| 1466 |
+
"loss": 0.0,
|
| 1467 |
+
"step": 10150
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.533333333333333,
|
| 1471 |
+
"grad_norm": 3.679243309306912e-05,
|
| 1472 |
+
"learning_rate": 4.6711111111111115e-06,
|
| 1473 |
+
"loss": 0.0,
|
| 1474 |
+
"step": 10200
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 4.555555555555555,
|
| 1478 |
+
"grad_norm": 3.425304385018535e-05,
|
| 1479 |
+
"learning_rate": 4.448888888888889e-06,
|
| 1480 |
+
"loss": 0.0,
|
| 1481 |
+
"step": 10250
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 4.5777777777777775,
|
| 1485 |
+
"grad_norm": 2.751518513832707e-05,
|
| 1486 |
+
"learning_rate": 4.226666666666667e-06,
|
| 1487 |
+
"loss": 0.0,
|
| 1488 |
+
"step": 10300
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 4.6,
|
| 1492 |
+
"grad_norm": 2.8532382202683948e-05,
|
| 1493 |
+
"learning_rate": 4.004444444444445e-06,
|
| 1494 |
+
"loss": 0.0,
|
| 1495 |
+
"step": 10350
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.622222222222222,
|
| 1499 |
+
"grad_norm": 2.9013817766099237e-05,
|
| 1500 |
+
"learning_rate": 3.7822222222222224e-06,
|
| 1501 |
+
"loss": 0.0,
|
| 1502 |
+
"step": 10400
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 4.644444444444445,
|
| 1506 |
+
"grad_norm": 3.07061527564656e-05,
|
| 1507 |
+
"learning_rate": 3.5600000000000002e-06,
|
| 1508 |
+
"loss": 0.0,
|
| 1509 |
+
"step": 10450
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.666666666666667,
|
| 1513 |
+
"grad_norm": 2.944734660559334e-05,
|
| 1514 |
+
"learning_rate": 3.337777777777778e-06,
|
| 1515 |
+
"loss": 0.0,
|
| 1516 |
+
"step": 10500
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.688888888888889,
|
| 1520 |
+
"grad_norm": 2.6814725060830824e-05,
|
| 1521 |
+
"learning_rate": 3.1155555555555555e-06,
|
| 1522 |
+
"loss": 0.0,
|
| 1523 |
+
"step": 10550
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 4.711111111111111,
|
| 1527 |
+
"grad_norm": 3.8631915231235325e-05,
|
| 1528 |
+
"learning_rate": 2.8933333333333333e-06,
|
| 1529 |
+
"loss": 0.0,
|
| 1530 |
+
"step": 10600
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.733333333333333,
|
| 1534 |
+
"grad_norm": 4.212988278595731e-05,
|
| 1535 |
+
"learning_rate": 2.6711111111111116e-06,
|
| 1536 |
+
"loss": 0.0,
|
| 1537 |
+
"step": 10650
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 4.7555555555555555,
|
| 1541 |
+
"grad_norm": 2.7735224648495205e-05,
|
| 1542 |
+
"learning_rate": 2.448888888888889e-06,
|
| 1543 |
+
"loss": 0.0,
|
| 1544 |
+
"step": 10700
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 4.777777777777778,
|
| 1548 |
+
"grad_norm": 3.2194642699323595e-05,
|
| 1549 |
+
"learning_rate": 2.226666666666667e-06,
|
| 1550 |
+
"loss": 0.0,
|
| 1551 |
+
"step": 10750
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 4.8,
|
| 1555 |
+
"grad_norm": 2.7552601750358008e-05,
|
| 1556 |
+
"learning_rate": 2.0044444444444446e-06,
|
| 1557 |
+
"loss": 0.0,
|
| 1558 |
+
"step": 10800
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 4.822222222222222,
|
| 1562 |
+
"grad_norm": 3.464681503828615e-05,
|
| 1563 |
+
"learning_rate": 1.7822222222222223e-06,
|
| 1564 |
+
"loss": 0.0,
|
| 1565 |
+
"step": 10850
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 4.844444444444444,
|
| 1569 |
+
"grad_norm": 2.8678237868007272e-05,
|
| 1570 |
+
"learning_rate": 1.56e-06,
|
| 1571 |
+
"loss": 0.0,
|
| 1572 |
+
"step": 10900
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 4.866666666666667,
|
| 1576 |
+
"grad_norm": 2.6989377147401683e-05,
|
| 1577 |
+
"learning_rate": 1.337777777777778e-06,
|
| 1578 |
+
"loss": 0.0,
|
| 1579 |
+
"step": 10950
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 4.888888888888889,
|
| 1583 |
+
"grad_norm": 2.9060267479508184e-05,
|
| 1584 |
+
"learning_rate": 1.1155555555555556e-06,
|
| 1585 |
+
"loss": 0.0,
|
| 1586 |
+
"step": 11000
|
| 1587 |
+
}
|
| 1588 |
+
],
|
| 1589 |
+
"logging_steps": 50,
|
| 1590 |
+
"max_steps": 11250,
|
| 1591 |
+
"num_input_tokens_seen": 0,
|
| 1592 |
+
"num_train_epochs": 5,
|
| 1593 |
+
"save_steps": 500,
|
| 1594 |
+
"stateful_callbacks": {
|
| 1595 |
+
"TrainerControl": {
|
| 1596 |
+
"args": {
|
| 1597 |
+
"should_epoch_stop": false,
|
| 1598 |
+
"should_evaluate": false,
|
| 1599 |
+
"should_log": false,
|
| 1600 |
+
"should_save": true,
|
| 1601 |
+
"should_training_stop": false
|
| 1602 |
+
},
|
| 1603 |
+
"attributes": {}
|
| 1604 |
+
}
|
| 1605 |
+
},
|
| 1606 |
+
"total_flos": 1.0134876111806016e+16,
|
| 1607 |
+
"train_batch_size": 8,
|
| 1608 |
+
"trial_name": null,
|
| 1609 |
+
"trial_params": null
|
| 1610 |
+
}
|
checkpoint-11000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2437d3569274a4022188190da6f34872c3e1e86886e244e0bd97efb2e6b5384c
|
| 3 |
+
size 5713
|
checkpoint-11250/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-11250/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForTokenClassification"
|
| 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": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6,
|
| 33 |
+
"LABEL_7": 7,
|
| 34 |
+
"LABEL_8": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"max_relative_positions": -1,
|
| 40 |
+
"model_type": "deberta-v2",
|
| 41 |
+
"norm_rel_ebd": "layer_norm",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"pooler_dropout": 0,
|
| 46 |
+
"pooler_hidden_act": "gelu",
|
| 47 |
+
"pooler_hidden_size": 768,
|
| 48 |
+
"pos_att_type": [
|
| 49 |
+
"p2c",
|
| 50 |
+
"c2p"
|
| 51 |
+
],
|
| 52 |
+
"position_biased_input": false,
|
| 53 |
+
"position_buckets": 256,
|
| 54 |
+
"relative_attention": true,
|
| 55 |
+
"share_att_key": true,
|
| 56 |
+
"transformers_version": "4.56.1",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
checkpoint-11250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10016fab24ea554c4127ed2f5363f71363d520366f4fd4acf3d6516d522b1f92
|
| 3 |
+
size 735378268
|
checkpoint-11250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea08f3db7e2403bbb8948d7a24efdb4847c0f8034ad875aefcaf9cb0ed459882
|
| 3 |
+
size 1470878283
|
checkpoint-11250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c80d3c0c1f1e6f97164c4dd8e1ddd46ae7e23eed7be8b3cf781bafd6fbc2e4
|
| 3 |
+
size 14645
|
checkpoint-11250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ba182a6b24992ed415540c66b4789d972bacea714ff5a20fad3bc4d2f705ba8
|
| 3 |
+
size 1465
|
checkpoint-11250/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 |
+
}
|
checkpoint-11250/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-11250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11250/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 |
+
}
|
checkpoint-11250/trainer_state.json
ADDED
|
@@ -0,0 +1,1645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 11250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022222222222222223,
|
| 14 |
+
"grad_norm": 0.4169579744338989,
|
| 15 |
+
"learning_rate": 4.9782222222222224e-05,
|
| 16 |
+
"loss": 0.2263,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.044444444444444446,
|
| 21 |
+
"grad_norm": 0.33507040143013,
|
| 22 |
+
"learning_rate": 4.956e-05,
|
| 23 |
+
"loss": 0.0174,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06666666666666667,
|
| 28 |
+
"grad_norm": 0.11501526087522507,
|
| 29 |
+
"learning_rate": 4.933777777777778e-05,
|
| 30 |
+
"loss": 0.0101,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08888888888888889,
|
| 35 |
+
"grad_norm": 0.09099342674016953,
|
| 36 |
+
"learning_rate": 4.911555555555556e-05,
|
| 37 |
+
"loss": 0.0061,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1111111111111111,
|
| 42 |
+
"grad_norm": 0.08669792860746384,
|
| 43 |
+
"learning_rate": 4.8893333333333335e-05,
|
| 44 |
+
"loss": 0.0036,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13333333333333333,
|
| 49 |
+
"grad_norm": 0.07038326561450958,
|
| 50 |
+
"learning_rate": 4.867111111111111e-05,
|
| 51 |
+
"loss": 0.0037,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15555555555555556,
|
| 56 |
+
"grad_norm": 0.08929373323917389,
|
| 57 |
+
"learning_rate": 4.8448888888888894e-05,
|
| 58 |
+
"loss": 0.0025,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17777777777777778,
|
| 63 |
+
"grad_norm": 0.010555864311754704,
|
| 64 |
+
"learning_rate": 4.822666666666667e-05,
|
| 65 |
+
"loss": 0.0011,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2,
|
| 70 |
+
"grad_norm": 0.12513870000839233,
|
| 71 |
+
"learning_rate": 4.8004444444444446e-05,
|
| 72 |
+
"loss": 0.0014,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2222222222222222,
|
| 77 |
+
"grad_norm": 0.008826244622468948,
|
| 78 |
+
"learning_rate": 4.778222222222222e-05,
|
| 79 |
+
"loss": 0.0009,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.24444444444444444,
|
| 84 |
+
"grad_norm": 0.3243519067764282,
|
| 85 |
+
"learning_rate": 4.7560000000000005e-05,
|
| 86 |
+
"loss": 0.0003,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.26666666666666666,
|
| 91 |
+
"grad_norm": 0.013048608787357807,
|
| 92 |
+
"learning_rate": 4.733777777777778e-05,
|
| 93 |
+
"loss": 0.003,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.28888888888888886,
|
| 98 |
+
"grad_norm": 0.004392141476273537,
|
| 99 |
+
"learning_rate": 4.711555555555556e-05,
|
| 100 |
+
"loss": 0.0017,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3111111111111111,
|
| 105 |
+
"grad_norm": 0.009453477337956429,
|
| 106 |
+
"learning_rate": 4.6893333333333334e-05,
|
| 107 |
+
"loss": 0.0007,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3333333333333333,
|
| 112 |
+
"grad_norm": 0.29423239827156067,
|
| 113 |
+
"learning_rate": 4.667111111111112e-05,
|
| 114 |
+
"loss": 0.0004,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.35555555555555557,
|
| 119 |
+
"grad_norm": 0.007287424057722092,
|
| 120 |
+
"learning_rate": 4.644888888888889e-05,
|
| 121 |
+
"loss": 0.0004,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37777777777777777,
|
| 126 |
+
"grad_norm": 0.006468615494668484,
|
| 127 |
+
"learning_rate": 4.622666666666667e-05,
|
| 128 |
+
"loss": 0.001,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4,
|
| 133 |
+
"grad_norm": 0.0032176165841519833,
|
| 134 |
+
"learning_rate": 4.6004444444444445e-05,
|
| 135 |
+
"loss": 0.0013,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4222222222222222,
|
| 140 |
+
"grad_norm": 0.0045009879395365715,
|
| 141 |
+
"learning_rate": 4.578222222222223e-05,
|
| 142 |
+
"loss": 0.0009,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4444444444444444,
|
| 147 |
+
"grad_norm": 0.04195983707904816,
|
| 148 |
+
"learning_rate": 4.5560000000000004e-05,
|
| 149 |
+
"loss": 0.0002,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4666666666666667,
|
| 154 |
+
"grad_norm": 0.0009760915418155491,
|
| 155 |
+
"learning_rate": 4.533777777777778e-05,
|
| 156 |
+
"loss": 0.0001,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4888888888888889,
|
| 161 |
+
"grad_norm": 0.0008424059487879276,
|
| 162 |
+
"learning_rate": 4.5115555555555557e-05,
|
| 163 |
+
"loss": 0.0001,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5111111111111111,
|
| 168 |
+
"grad_norm": 0.001366421696729958,
|
| 169 |
+
"learning_rate": 4.489333333333334e-05,
|
| 170 |
+
"loss": 0.0001,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5333333333333333,
|
| 175 |
+
"grad_norm": 0.0733928307890892,
|
| 176 |
+
"learning_rate": 4.4671111111111116e-05,
|
| 177 |
+
"loss": 0.0001,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5555555555555556,
|
| 182 |
+
"grad_norm": 0.005551271606236696,
|
| 183 |
+
"learning_rate": 4.444888888888889e-05,
|
| 184 |
+
"loss": 0.0008,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5777777777777777,
|
| 189 |
+
"grad_norm": 0.0026340284384787083,
|
| 190 |
+
"learning_rate": 4.422666666666667e-05,
|
| 191 |
+
"loss": 0.0002,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6,
|
| 196 |
+
"grad_norm": 0.002755340188741684,
|
| 197 |
+
"learning_rate": 4.400444444444445e-05,
|
| 198 |
+
"loss": 0.0001,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6222222222222222,
|
| 203 |
+
"grad_norm": 0.0008212323882617056,
|
| 204 |
+
"learning_rate": 4.378222222222223e-05,
|
| 205 |
+
"loss": 0.0,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6444444444444445,
|
| 210 |
+
"grad_norm": 0.0005921730189584196,
|
| 211 |
+
"learning_rate": 4.356e-05,
|
| 212 |
+
"loss": 0.0,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6666666666666666,
|
| 217 |
+
"grad_norm": 0.0008460666285827756,
|
| 218 |
+
"learning_rate": 4.333777777777778e-05,
|
| 219 |
+
"loss": 0.0001,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6888888888888889,
|
| 224 |
+
"grad_norm": 0.0006111777038313448,
|
| 225 |
+
"learning_rate": 4.311555555555556e-05,
|
| 226 |
+
"loss": 0.0,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7111111111111111,
|
| 231 |
+
"grad_norm": 0.00046472539543174207,
|
| 232 |
+
"learning_rate": 4.289333333333334e-05,
|
| 233 |
+
"loss": 0.0,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7333333333333333,
|
| 238 |
+
"grad_norm": 0.0007363149197772145,
|
| 239 |
+
"learning_rate": 4.2671111111111114e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7555555555555555,
|
| 245 |
+
"grad_norm": 0.0006023353198543191,
|
| 246 |
+
"learning_rate": 4.244888888888889e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7777777777777778,
|
| 252 |
+
"grad_norm": 0.0004273591039236635,
|
| 253 |
+
"learning_rate": 4.222666666666667e-05,
|
| 254 |
+
"loss": 0.0,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8,
|
| 259 |
+
"grad_norm": 0.0006913533434271812,
|
| 260 |
+
"learning_rate": 4.200444444444445e-05,
|
| 261 |
+
"loss": 0.0,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8222222222222222,
|
| 266 |
+
"grad_norm": 0.0014112872304394841,
|
| 267 |
+
"learning_rate": 4.1782222222222226e-05,
|
| 268 |
+
"loss": 0.0002,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8444444444444444,
|
| 273 |
+
"grad_norm": 0.0024269793648272753,
|
| 274 |
+
"learning_rate": 4.156e-05,
|
| 275 |
+
"loss": 0.0005,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8666666666666667,
|
| 280 |
+
"grad_norm": 0.46272382140159607,
|
| 281 |
+
"learning_rate": 4.133777777777778e-05,
|
| 282 |
+
"loss": 0.0013,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8888888888888888,
|
| 287 |
+
"grad_norm": 0.006871496792882681,
|
| 288 |
+
"learning_rate": 4.1115555555555554e-05,
|
| 289 |
+
"loss": 0.001,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9111111111111111,
|
| 294 |
+
"grad_norm": 0.0022507584653794765,
|
| 295 |
+
"learning_rate": 4.089333333333333e-05,
|
| 296 |
+
"loss": 0.001,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9333333333333333,
|
| 301 |
+
"grad_norm": 0.0077248550951480865,
|
| 302 |
+
"learning_rate": 4.067111111111111e-05,
|
| 303 |
+
"loss": 0.0005,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9555555555555556,
|
| 308 |
+
"grad_norm": 0.0006559474277310073,
|
| 309 |
+
"learning_rate": 4.044888888888889e-05,
|
| 310 |
+
"loss": 0.0003,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.9777777777777777,
|
| 315 |
+
"grad_norm": 0.000827161071356386,
|
| 316 |
+
"learning_rate": 4.0226666666666666e-05,
|
| 317 |
+
"loss": 0.0012,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0,
|
| 322 |
+
"grad_norm": 0.22399061918258667,
|
| 323 |
+
"learning_rate": 4.000444444444444e-05,
|
| 324 |
+
"loss": 0.0005,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.0,
|
| 329 |
+
"eval_loss": 0.0001230358611792326,
|
| 330 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 331 |
+
"eval_runtime": 39.9747,
|
| 332 |
+
"eval_samples_per_second": 50.032,
|
| 333 |
+
"eval_steps_per_second": 6.254,
|
| 334 |
+
"step": 2250
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.0222222222222221,
|
| 338 |
+
"grad_norm": 0.0034671323373913765,
|
| 339 |
+
"learning_rate": 3.9782222222222225e-05,
|
| 340 |
+
"loss": 0.0005,
|
| 341 |
+
"step": 2300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.0444444444444445,
|
| 345 |
+
"grad_norm": 0.005704512819647789,
|
| 346 |
+
"learning_rate": 3.956e-05,
|
| 347 |
+
"loss": 0.0024,
|
| 348 |
+
"step": 2350
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.0666666666666667,
|
| 352 |
+
"grad_norm": 0.0016336466651409864,
|
| 353 |
+
"learning_rate": 3.933777777777778e-05,
|
| 354 |
+
"loss": 0.0004,
|
| 355 |
+
"step": 2400
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.0888888888888888,
|
| 359 |
+
"grad_norm": 0.0009551944676786661,
|
| 360 |
+
"learning_rate": 3.911555555555555e-05,
|
| 361 |
+
"loss": 0.0002,
|
| 362 |
+
"step": 2450
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.1111111111111112,
|
| 366 |
+
"grad_norm": 0.0004279686836525798,
|
| 367 |
+
"learning_rate": 3.8893333333333336e-05,
|
| 368 |
+
"loss": 0.0001,
|
| 369 |
+
"step": 2500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.1333333333333333,
|
| 373 |
+
"grad_norm": 0.00043013374670408666,
|
| 374 |
+
"learning_rate": 3.867111111111111e-05,
|
| 375 |
+
"loss": 0.0001,
|
| 376 |
+
"step": 2550
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.1555555555555554,
|
| 380 |
+
"grad_norm": 0.00034906569635495543,
|
| 381 |
+
"learning_rate": 3.844888888888889e-05,
|
| 382 |
+
"loss": 0.0,
|
| 383 |
+
"step": 2600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.1777777777777778,
|
| 387 |
+
"grad_norm": 0.0014709575334563851,
|
| 388 |
+
"learning_rate": 3.8226666666666664e-05,
|
| 389 |
+
"loss": 0.0002,
|
| 390 |
+
"step": 2650
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.2,
|
| 394 |
+
"grad_norm": 0.0006022250163368881,
|
| 395 |
+
"learning_rate": 3.800444444444445e-05,
|
| 396 |
+
"loss": 0.0,
|
| 397 |
+
"step": 2700
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.2222222222222223,
|
| 401 |
+
"grad_norm": 0.000542789523024112,
|
| 402 |
+
"learning_rate": 3.778222222222222e-05,
|
| 403 |
+
"loss": 0.0001,
|
| 404 |
+
"step": 2750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.2444444444444445,
|
| 408 |
+
"grad_norm": 0.00048277038149535656,
|
| 409 |
+
"learning_rate": 3.756e-05,
|
| 410 |
+
"loss": 0.0002,
|
| 411 |
+
"step": 2800
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.2666666666666666,
|
| 415 |
+
"grad_norm": 0.0003071363898925483,
|
| 416 |
+
"learning_rate": 3.7337777777777776e-05,
|
| 417 |
+
"loss": 0.0,
|
| 418 |
+
"step": 2850
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.2888888888888888,
|
| 422 |
+
"grad_norm": 0.0003033171233255416,
|
| 423 |
+
"learning_rate": 3.711555555555556e-05,
|
| 424 |
+
"loss": 0.0,
|
| 425 |
+
"step": 2900
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.3111111111111111,
|
| 429 |
+
"grad_norm": 0.001257324474863708,
|
| 430 |
+
"learning_rate": 3.6893333333333335e-05,
|
| 431 |
+
"loss": 0.0011,
|
| 432 |
+
"step": 2950
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.3333333333333333,
|
| 436 |
+
"grad_norm": 0.0003226712578907609,
|
| 437 |
+
"learning_rate": 3.667111111111111e-05,
|
| 438 |
+
"loss": 0.0002,
|
| 439 |
+
"step": 3000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.3555555555555556,
|
| 443 |
+
"grad_norm": 0.00033422038541175425,
|
| 444 |
+
"learning_rate": 3.644888888888889e-05,
|
| 445 |
+
"loss": 0.0001,
|
| 446 |
+
"step": 3050
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.3777777777777778,
|
| 450 |
+
"grad_norm": 0.0004989306908100843,
|
| 451 |
+
"learning_rate": 3.622666666666667e-05,
|
| 452 |
+
"loss": 0.0,
|
| 453 |
+
"step": 3100
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.4,
|
| 457 |
+
"grad_norm": 0.0002919055405072868,
|
| 458 |
+
"learning_rate": 3.6004444444444446e-05,
|
| 459 |
+
"loss": 0.0,
|
| 460 |
+
"step": 3150
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.4222222222222223,
|
| 464 |
+
"grad_norm": 0.00027494438108988106,
|
| 465 |
+
"learning_rate": 3.578222222222222e-05,
|
| 466 |
+
"loss": 0.0,
|
| 467 |
+
"step": 3200
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.4444444444444444,
|
| 471 |
+
"grad_norm": 0.000610452436376363,
|
| 472 |
+
"learning_rate": 3.5560000000000005e-05,
|
| 473 |
+
"loss": 0.0,
|
| 474 |
+
"step": 3250
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.4666666666666668,
|
| 478 |
+
"grad_norm": 0.000538027728907764,
|
| 479 |
+
"learning_rate": 3.533777777777778e-05,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 3300
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.488888888888889,
|
| 485 |
+
"grad_norm": 0.00020039589435327798,
|
| 486 |
+
"learning_rate": 3.511555555555556e-05,
|
| 487 |
+
"loss": 0.0,
|
| 488 |
+
"step": 3350
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.511111111111111,
|
| 492 |
+
"grad_norm": 0.00018263465608470142,
|
| 493 |
+
"learning_rate": 3.4893333333333334e-05,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"step": 3400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.5333333333333332,
|
| 499 |
+
"grad_norm": 0.00019636489741969854,
|
| 500 |
+
"learning_rate": 3.4671111111111116e-05,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 3450
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.5555555555555556,
|
| 506 |
+
"grad_norm": 0.00028676423244178295,
|
| 507 |
+
"learning_rate": 3.444888888888889e-05,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 3500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.5777777777777777,
|
| 513 |
+
"grad_norm": 0.00019564179820008576,
|
| 514 |
+
"learning_rate": 3.422666666666667e-05,
|
| 515 |
+
"loss": 0.0,
|
| 516 |
+
"step": 3550
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.6,
|
| 520 |
+
"grad_norm": 0.00020010425942018628,
|
| 521 |
+
"learning_rate": 3.4004444444444445e-05,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"step": 3600
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.6222222222222222,
|
| 527 |
+
"grad_norm": 0.00015156572044361383,
|
| 528 |
+
"learning_rate": 3.378222222222223e-05,
|
| 529 |
+
"loss": 0.0,
|
| 530 |
+
"step": 3650
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.6444444444444444,
|
| 534 |
+
"grad_norm": 0.0001559116062708199,
|
| 535 |
+
"learning_rate": 3.3560000000000004e-05,
|
| 536 |
+
"loss": 0.0,
|
| 537 |
+
"step": 3700
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.6666666666666665,
|
| 541 |
+
"grad_norm": 0.00017668222426436841,
|
| 542 |
+
"learning_rate": 3.333777777777778e-05,
|
| 543 |
+
"loss": 0.0,
|
| 544 |
+
"step": 3750
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.6888888888888889,
|
| 548 |
+
"grad_norm": 0.00015294237527996302,
|
| 549 |
+
"learning_rate": 3.3115555555555556e-05,
|
| 550 |
+
"loss": 0.0,
|
| 551 |
+
"step": 3800
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.7111111111111112,
|
| 555 |
+
"grad_norm": 0.00020564977603498846,
|
| 556 |
+
"learning_rate": 3.289333333333334e-05,
|
| 557 |
+
"loss": 0.0,
|
| 558 |
+
"step": 3850
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.7333333333333334,
|
| 562 |
+
"grad_norm": 0.00015193119179457426,
|
| 563 |
+
"learning_rate": 3.2671111111111115e-05,
|
| 564 |
+
"loss": 0.0,
|
| 565 |
+
"step": 3900
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.7555555555555555,
|
| 569 |
+
"grad_norm": 0.00013517968181986362,
|
| 570 |
+
"learning_rate": 3.244888888888889e-05,
|
| 571 |
+
"loss": 0.0,
|
| 572 |
+
"step": 3950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.7777777777777777,
|
| 576 |
+
"grad_norm": 0.00027755036717280746,
|
| 577 |
+
"learning_rate": 3.222666666666667e-05,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"step": 4000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.8,
|
| 583 |
+
"grad_norm": 0.0001287544146180153,
|
| 584 |
+
"learning_rate": 3.200444444444445e-05,
|
| 585 |
+
"loss": 0.0,
|
| 586 |
+
"step": 4050
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.8222222222222222,
|
| 590 |
+
"grad_norm": 0.0001332290848949924,
|
| 591 |
+
"learning_rate": 3.178222222222223e-05,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 4100
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.8444444444444446,
|
| 597 |
+
"grad_norm": 0.00012569426326081157,
|
| 598 |
+
"learning_rate": 3.156e-05,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 4150
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.8666666666666667,
|
| 604 |
+
"grad_norm": 0.00011655821435851976,
|
| 605 |
+
"learning_rate": 3.133777777777778e-05,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"step": 4200
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.8888888888888888,
|
| 611 |
+
"grad_norm": 0.0001188791575259529,
|
| 612 |
+
"learning_rate": 3.111555555555556e-05,
|
| 613 |
+
"loss": 0.0,
|
| 614 |
+
"step": 4250
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.911111111111111,
|
| 618 |
+
"grad_norm": 0.00010238583490718156,
|
| 619 |
+
"learning_rate": 3.089333333333334e-05,
|
| 620 |
+
"loss": 0.0,
|
| 621 |
+
"step": 4300
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.9333333333333333,
|
| 625 |
+
"grad_norm": 0.0001092032398446463,
|
| 626 |
+
"learning_rate": 3.0671111111111114e-05,
|
| 627 |
+
"loss": 0.0,
|
| 628 |
+
"step": 4350
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.9555555555555557,
|
| 632 |
+
"grad_norm": 0.00014390636351890862,
|
| 633 |
+
"learning_rate": 3.0448888888888887e-05,
|
| 634 |
+
"loss": 0.0,
|
| 635 |
+
"step": 4400
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.9777777777777779,
|
| 639 |
+
"grad_norm": 0.00010023260256275535,
|
| 640 |
+
"learning_rate": 3.022666666666667e-05,
|
| 641 |
+
"loss": 0.0,
|
| 642 |
+
"step": 4450
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.0,
|
| 646 |
+
"grad_norm": 0.00010638952517183498,
|
| 647 |
+
"learning_rate": 3.0004444444444446e-05,
|
| 648 |
+
"loss": 0.0,
|
| 649 |
+
"step": 4500
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.0,
|
| 653 |
+
"eval_loss": 1.410930394740717e-06,
|
| 654 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 655 |
+
"eval_runtime": 39.342,
|
| 656 |
+
"eval_samples_per_second": 50.836,
|
| 657 |
+
"eval_steps_per_second": 6.355,
|
| 658 |
+
"step": 4500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.022222222222222,
|
| 662 |
+
"grad_norm": 0.00010032003774540499,
|
| 663 |
+
"learning_rate": 2.9782222222222222e-05,
|
| 664 |
+
"loss": 0.0,
|
| 665 |
+
"step": 4550
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.0444444444444443,
|
| 669 |
+
"grad_norm": 0.00048742775106802583,
|
| 670 |
+
"learning_rate": 2.9559999999999998e-05,
|
| 671 |
+
"loss": 0.0,
|
| 672 |
+
"step": 4600
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.066666666666667,
|
| 676 |
+
"grad_norm": 9.531196701573208e-05,
|
| 677 |
+
"learning_rate": 2.933777777777778e-05,
|
| 678 |
+
"loss": 0.0,
|
| 679 |
+
"step": 4650
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 2.088888888888889,
|
| 683 |
+
"grad_norm": 9.425494499737397e-05,
|
| 684 |
+
"learning_rate": 2.9115555555555557e-05,
|
| 685 |
+
"loss": 0.0,
|
| 686 |
+
"step": 4700
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.111111111111111,
|
| 690 |
+
"grad_norm": 0.00011574638483580202,
|
| 691 |
+
"learning_rate": 2.8893333333333333e-05,
|
| 692 |
+
"loss": 0.0,
|
| 693 |
+
"step": 4750
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.1333333333333333,
|
| 697 |
+
"grad_norm": 9.062536264536902e-05,
|
| 698 |
+
"learning_rate": 2.8671111111111116e-05,
|
| 699 |
+
"loss": 0.0,
|
| 700 |
+
"step": 4800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.1555555555555554,
|
| 704 |
+
"grad_norm": 9.913908434100449e-05,
|
| 705 |
+
"learning_rate": 2.8448888888888892e-05,
|
| 706 |
+
"loss": 0.0,
|
| 707 |
+
"step": 4850
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.1777777777777776,
|
| 711 |
+
"grad_norm": 0.00010020509216701612,
|
| 712 |
+
"learning_rate": 2.822666666666667e-05,
|
| 713 |
+
"loss": 0.0,
|
| 714 |
+
"step": 4900
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.2,
|
| 718 |
+
"grad_norm": 0.00012128752132412046,
|
| 719 |
+
"learning_rate": 2.8004444444444445e-05,
|
| 720 |
+
"loss": 0.0,
|
| 721 |
+
"step": 4950
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 2.2222222222222223,
|
| 725 |
+
"grad_norm": 0.02587141841650009,
|
| 726 |
+
"learning_rate": 2.7782222222222228e-05,
|
| 727 |
+
"loss": 0.0,
|
| 728 |
+
"step": 5000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.2444444444444445,
|
| 732 |
+
"grad_norm": 8.068871829891577e-05,
|
| 733 |
+
"learning_rate": 2.7560000000000004e-05,
|
| 734 |
+
"loss": 0.0,
|
| 735 |
+
"step": 5050
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.2666666666666666,
|
| 739 |
+
"grad_norm": 8.70975709403865e-05,
|
| 740 |
+
"learning_rate": 2.733777777777778e-05,
|
| 741 |
+
"loss": 0.0,
|
| 742 |
+
"step": 5100
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.2888888888888888,
|
| 746 |
+
"grad_norm": 8.906049333745614e-05,
|
| 747 |
+
"learning_rate": 2.7115555555555556e-05,
|
| 748 |
+
"loss": 0.0,
|
| 749 |
+
"step": 5150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.311111111111111,
|
| 753 |
+
"grad_norm": 7.555448246421292e-05,
|
| 754 |
+
"learning_rate": 2.6893333333333336e-05,
|
| 755 |
+
"loss": 0.0,
|
| 756 |
+
"step": 5200
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.3333333333333335,
|
| 760 |
+
"grad_norm": 0.00033314700704067945,
|
| 761 |
+
"learning_rate": 2.6671111111111112e-05,
|
| 762 |
+
"loss": 0.0,
|
| 763 |
+
"step": 5250
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 2.3555555555555556,
|
| 767 |
+
"grad_norm": 8.106895256787539e-05,
|
| 768 |
+
"learning_rate": 2.644888888888889e-05,
|
| 769 |
+
"loss": 0.0,
|
| 770 |
+
"step": 5300
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.3777777777777778,
|
| 774 |
+
"grad_norm": 0.0002253134734928608,
|
| 775 |
+
"learning_rate": 2.6226666666666667e-05,
|
| 776 |
+
"loss": 0.0002,
|
| 777 |
+
"step": 5350
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.4,
|
| 781 |
+
"grad_norm": 0.04773925617337227,
|
| 782 |
+
"learning_rate": 2.6004444444444447e-05,
|
| 783 |
+
"loss": 0.0016,
|
| 784 |
+
"step": 5400
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.422222222222222,
|
| 788 |
+
"grad_norm": 0.013284893706440926,
|
| 789 |
+
"learning_rate": 2.5782222222222223e-05,
|
| 790 |
+
"loss": 0.0013,
|
| 791 |
+
"step": 5450
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.4444444444444446,
|
| 795 |
+
"grad_norm": 0.0019914733711630106,
|
| 796 |
+
"learning_rate": 2.556e-05,
|
| 797 |
+
"loss": 0.001,
|
| 798 |
+
"step": 5500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.466666666666667,
|
| 802 |
+
"grad_norm": 0.00029465914121828973,
|
| 803 |
+
"learning_rate": 2.5337777777777775e-05,
|
| 804 |
+
"loss": 0.0001,
|
| 805 |
+
"step": 5550
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.488888888888889,
|
| 809 |
+
"grad_norm": 0.0010584425181150436,
|
| 810 |
+
"learning_rate": 2.5115555555555558e-05,
|
| 811 |
+
"loss": 0.0,
|
| 812 |
+
"step": 5600
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.511111111111111,
|
| 816 |
+
"grad_norm": 0.00024866798776201904,
|
| 817 |
+
"learning_rate": 2.4893333333333334e-05,
|
| 818 |
+
"loss": 0.0,
|
| 819 |
+
"step": 5650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.533333333333333,
|
| 823 |
+
"grad_norm": 0.00015023746527731419,
|
| 824 |
+
"learning_rate": 2.467111111111111e-05,
|
| 825 |
+
"loss": 0.0,
|
| 826 |
+
"step": 5700
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.5555555555555554,
|
| 830 |
+
"grad_norm": 0.00020707614021375775,
|
| 831 |
+
"learning_rate": 2.444888888888889e-05,
|
| 832 |
+
"loss": 0.0,
|
| 833 |
+
"step": 5750
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 2.5777777777777775,
|
| 837 |
+
"grad_norm": 0.00013307879271451384,
|
| 838 |
+
"learning_rate": 2.4226666666666666e-05,
|
| 839 |
+
"loss": 0.0,
|
| 840 |
+
"step": 5800
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.6,
|
| 844 |
+
"grad_norm": 0.00012964503548573703,
|
| 845 |
+
"learning_rate": 2.4004444444444446e-05,
|
| 846 |
+
"loss": 0.0,
|
| 847 |
+
"step": 5850
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 2.6222222222222222,
|
| 851 |
+
"grad_norm": 0.00012642733054235578,
|
| 852 |
+
"learning_rate": 2.3782222222222222e-05,
|
| 853 |
+
"loss": 0.0,
|
| 854 |
+
"step": 5900
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.6444444444444444,
|
| 858 |
+
"grad_norm": 0.00172146107070148,
|
| 859 |
+
"learning_rate": 2.356e-05,
|
| 860 |
+
"loss": 0.0005,
|
| 861 |
+
"step": 5950
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.6666666666666665,
|
| 865 |
+
"grad_norm": 0.00067210040288046,
|
| 866 |
+
"learning_rate": 2.3337777777777778e-05,
|
| 867 |
+
"loss": 0.0003,
|
| 868 |
+
"step": 6000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.688888888888889,
|
| 872 |
+
"grad_norm": 0.0019879883620887995,
|
| 873 |
+
"learning_rate": 2.3115555555555557e-05,
|
| 874 |
+
"loss": 0.0001,
|
| 875 |
+
"step": 6050
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 2.7111111111111112,
|
| 879 |
+
"grad_norm": 0.00017190357903018594,
|
| 880 |
+
"learning_rate": 2.2893333333333333e-05,
|
| 881 |
+
"loss": 0.0,
|
| 882 |
+
"step": 6100
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.7333333333333334,
|
| 886 |
+
"grad_norm": 0.00015691675071138889,
|
| 887 |
+
"learning_rate": 2.2671111111111113e-05,
|
| 888 |
+
"loss": 0.0,
|
| 889 |
+
"step": 6150
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.7555555555555555,
|
| 893 |
+
"grad_norm": 0.0001467355468776077,
|
| 894 |
+
"learning_rate": 2.244888888888889e-05,
|
| 895 |
+
"loss": 0.0,
|
| 896 |
+
"step": 6200
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.7777777777777777,
|
| 900 |
+
"grad_norm": 0.00015619705663993955,
|
| 901 |
+
"learning_rate": 2.222666666666667e-05,
|
| 902 |
+
"loss": 0.0,
|
| 903 |
+
"step": 6250
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.8,
|
| 907 |
+
"grad_norm": 0.0002816039486788213,
|
| 908 |
+
"learning_rate": 2.2004444444444445e-05,
|
| 909 |
+
"loss": 0.0,
|
| 910 |
+
"step": 6300
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.822222222222222,
|
| 914 |
+
"grad_norm": 0.0002559045678935945,
|
| 915 |
+
"learning_rate": 2.1782222222222224e-05,
|
| 916 |
+
"loss": 0.0,
|
| 917 |
+
"step": 6350
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.8444444444444446,
|
| 921 |
+
"grad_norm": 0.00017076350923161954,
|
| 922 |
+
"learning_rate": 2.1560000000000004e-05,
|
| 923 |
+
"loss": 0.0,
|
| 924 |
+
"step": 6400
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.8666666666666667,
|
| 928 |
+
"grad_norm": 9.32483744691126e-05,
|
| 929 |
+
"learning_rate": 2.133777777777778e-05,
|
| 930 |
+
"loss": 0.0,
|
| 931 |
+
"step": 6450
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.888888888888889,
|
| 935 |
+
"grad_norm": 9.684438555268571e-05,
|
| 936 |
+
"learning_rate": 2.111555555555556e-05,
|
| 937 |
+
"loss": 0.0,
|
| 938 |
+
"step": 6500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.911111111111111,
|
| 942 |
+
"grad_norm": 0.00010544607357587665,
|
| 943 |
+
"learning_rate": 2.0893333333333335e-05,
|
| 944 |
+
"loss": 0.0,
|
| 945 |
+
"step": 6550
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.9333333333333336,
|
| 949 |
+
"grad_norm": 9.587592649040744e-05,
|
| 950 |
+
"learning_rate": 2.0671111111111115e-05,
|
| 951 |
+
"loss": 0.0,
|
| 952 |
+
"step": 6600
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.9555555555555557,
|
| 956 |
+
"grad_norm": 0.00025339287822134793,
|
| 957 |
+
"learning_rate": 2.044888888888889e-05,
|
| 958 |
+
"loss": 0.0,
|
| 959 |
+
"step": 6650
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.977777777777778,
|
| 963 |
+
"grad_norm": 8.56281112646684e-05,
|
| 964 |
+
"learning_rate": 2.0226666666666667e-05,
|
| 965 |
+
"loss": 0.0,
|
| 966 |
+
"step": 6700
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.0,
|
| 970 |
+
"grad_norm": 8.848596917232499e-05,
|
| 971 |
+
"learning_rate": 2.0004444444444447e-05,
|
| 972 |
+
"loss": 0.0,
|
| 973 |
+
"step": 6750
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.0,
|
| 977 |
+
"eval_loss": 9.946712680175551e-07,
|
| 978 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 979 |
+
"eval_runtime": 39.3914,
|
| 980 |
+
"eval_samples_per_second": 50.773,
|
| 981 |
+
"eval_steps_per_second": 6.347,
|
| 982 |
+
"step": 6750
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.022222222222222,
|
| 986 |
+
"grad_norm": 7.696033571846783e-05,
|
| 987 |
+
"learning_rate": 1.9782222222222223e-05,
|
| 988 |
+
"loss": 0.0,
|
| 989 |
+
"step": 6800
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.0444444444444443,
|
| 993 |
+
"grad_norm": 6.949145608814433e-05,
|
| 994 |
+
"learning_rate": 1.956e-05,
|
| 995 |
+
"loss": 0.0,
|
| 996 |
+
"step": 6850
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.066666666666667,
|
| 1000 |
+
"grad_norm": 8.268443343695253e-05,
|
| 1001 |
+
"learning_rate": 1.933777777777778e-05,
|
| 1002 |
+
"loss": 0.0,
|
| 1003 |
+
"step": 6900
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.088888888888889,
|
| 1007 |
+
"grad_norm": 7.342168828472495e-05,
|
| 1008 |
+
"learning_rate": 1.9115555555555555e-05,
|
| 1009 |
+
"loss": 0.0,
|
| 1010 |
+
"step": 6950
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.111111111111111,
|
| 1014 |
+
"grad_norm": 6.869197386549786e-05,
|
| 1015 |
+
"learning_rate": 1.8893333333333334e-05,
|
| 1016 |
+
"loss": 0.0,
|
| 1017 |
+
"step": 7000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.1333333333333333,
|
| 1021 |
+
"grad_norm": 6.17999758105725e-05,
|
| 1022 |
+
"learning_rate": 1.867111111111111e-05,
|
| 1023 |
+
"loss": 0.0,
|
| 1024 |
+
"step": 7050
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.1555555555555554,
|
| 1028 |
+
"grad_norm": 9.41220423555933e-05,
|
| 1029 |
+
"learning_rate": 1.844888888888889e-05,
|
| 1030 |
+
"loss": 0.0014,
|
| 1031 |
+
"step": 7100
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.1777777777777776,
|
| 1035 |
+
"grad_norm": 0.00021578388987109065,
|
| 1036 |
+
"learning_rate": 1.8226666666666666e-05,
|
| 1037 |
+
"loss": 0.0001,
|
| 1038 |
+
"step": 7150
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.2,
|
| 1042 |
+
"grad_norm": 0.0057373447343707085,
|
| 1043 |
+
"learning_rate": 1.8004444444444446e-05,
|
| 1044 |
+
"loss": 0.0002,
|
| 1045 |
+
"step": 7200
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.2222222222222223,
|
| 1049 |
+
"grad_norm": 0.00015577590966131538,
|
| 1050 |
+
"learning_rate": 1.7782222222222222e-05,
|
| 1051 |
+
"loss": 0.0003,
|
| 1052 |
+
"step": 7250
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.2444444444444445,
|
| 1056 |
+
"grad_norm": 0.0001663435687078163,
|
| 1057 |
+
"learning_rate": 1.756e-05,
|
| 1058 |
+
"loss": 0.0,
|
| 1059 |
+
"step": 7300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.2666666666666666,
|
| 1063 |
+
"grad_norm": 0.00011119741975562647,
|
| 1064 |
+
"learning_rate": 1.7337777777777777e-05,
|
| 1065 |
+
"loss": 0.0,
|
| 1066 |
+
"step": 7350
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.2888888888888888,
|
| 1070 |
+
"grad_norm": 0.0001374996645608917,
|
| 1071 |
+
"learning_rate": 1.7115555555555557e-05,
|
| 1072 |
+
"loss": 0.0,
|
| 1073 |
+
"step": 7400
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.311111111111111,
|
| 1077 |
+
"grad_norm": 0.00021004487643949687,
|
| 1078 |
+
"learning_rate": 1.6893333333333333e-05,
|
| 1079 |
+
"loss": 0.0,
|
| 1080 |
+
"step": 7450
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.3333333333333335,
|
| 1084 |
+
"grad_norm": 0.0001712692028377205,
|
| 1085 |
+
"learning_rate": 1.6671111111111113e-05,
|
| 1086 |
+
"loss": 0.0,
|
| 1087 |
+
"step": 7500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.3555555555555556,
|
| 1091 |
+
"grad_norm": 9.832726209424436e-05,
|
| 1092 |
+
"learning_rate": 1.644888888888889e-05,
|
| 1093 |
+
"loss": 0.0,
|
| 1094 |
+
"step": 7550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.3777777777777778,
|
| 1098 |
+
"grad_norm": 9.489347576163709e-05,
|
| 1099 |
+
"learning_rate": 1.6226666666666668e-05,
|
| 1100 |
+
"loss": 0.0,
|
| 1101 |
+
"step": 7600
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.4,
|
| 1105 |
+
"grad_norm": 9.42831247812137e-05,
|
| 1106 |
+
"learning_rate": 1.6004444444444444e-05,
|
| 1107 |
+
"loss": 0.0,
|
| 1108 |
+
"step": 7650
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.422222222222222,
|
| 1112 |
+
"grad_norm": 0.0001237511314684525,
|
| 1113 |
+
"learning_rate": 1.5782222222222224e-05,
|
| 1114 |
+
"loss": 0.0,
|
| 1115 |
+
"step": 7700
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.4444444444444446,
|
| 1119 |
+
"grad_norm": 6.492211105069146e-05,
|
| 1120 |
+
"learning_rate": 1.556e-05,
|
| 1121 |
+
"loss": 0.0,
|
| 1122 |
+
"step": 7750
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.466666666666667,
|
| 1126 |
+
"grad_norm": 6.56497068121098e-05,
|
| 1127 |
+
"learning_rate": 1.533777777777778e-05,
|
| 1128 |
+
"loss": 0.0,
|
| 1129 |
+
"step": 7800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.488888888888889,
|
| 1133 |
+
"grad_norm": 6.696177297271788e-05,
|
| 1134 |
+
"learning_rate": 1.5115555555555556e-05,
|
| 1135 |
+
"loss": 0.0,
|
| 1136 |
+
"step": 7850
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.511111111111111,
|
| 1140 |
+
"grad_norm": 5.779510684078559e-05,
|
| 1141 |
+
"learning_rate": 1.4893333333333334e-05,
|
| 1142 |
+
"loss": 0.0,
|
| 1143 |
+
"step": 7900
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.533333333333333,
|
| 1147 |
+
"grad_norm": 6.52693779557012e-05,
|
| 1148 |
+
"learning_rate": 1.467111111111111e-05,
|
| 1149 |
+
"loss": 0.0,
|
| 1150 |
+
"step": 7950
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.5555555555555554,
|
| 1154 |
+
"grad_norm": 9.678869537310675e-05,
|
| 1155 |
+
"learning_rate": 1.444888888888889e-05,
|
| 1156 |
+
"loss": 0.0,
|
| 1157 |
+
"step": 8000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.5777777777777775,
|
| 1161 |
+
"grad_norm": 5.08545599586796e-05,
|
| 1162 |
+
"learning_rate": 1.4226666666666669e-05,
|
| 1163 |
+
"loss": 0.0,
|
| 1164 |
+
"step": 8050
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.6,
|
| 1168 |
+
"grad_norm": 0.0001278165145777166,
|
| 1169 |
+
"learning_rate": 1.4004444444444445e-05,
|
| 1170 |
+
"loss": 0.0,
|
| 1171 |
+
"step": 8100
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 3.6222222222222222,
|
| 1175 |
+
"grad_norm": 5.6915894674602896e-05,
|
| 1176 |
+
"learning_rate": 1.3782222222222224e-05,
|
| 1177 |
+
"loss": 0.0,
|
| 1178 |
+
"step": 8150
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.6444444444444444,
|
| 1182 |
+
"grad_norm": 5.536643220693804e-05,
|
| 1183 |
+
"learning_rate": 1.356e-05,
|
| 1184 |
+
"loss": 0.0,
|
| 1185 |
+
"step": 8200
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 3.6666666666666665,
|
| 1189 |
+
"grad_norm": 6.497505819424987e-05,
|
| 1190 |
+
"learning_rate": 1.333777777777778e-05,
|
| 1191 |
+
"loss": 0.0,
|
| 1192 |
+
"step": 8250
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 3.688888888888889,
|
| 1196 |
+
"grad_norm": 4.67045720142778e-05,
|
| 1197 |
+
"learning_rate": 1.3115555555555556e-05,
|
| 1198 |
+
"loss": 0.0,
|
| 1199 |
+
"step": 8300
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.7111111111111112,
|
| 1203 |
+
"grad_norm": 5.038898962084204e-05,
|
| 1204 |
+
"learning_rate": 1.2893333333333336e-05,
|
| 1205 |
+
"loss": 0.0,
|
| 1206 |
+
"step": 8350
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.7333333333333334,
|
| 1210 |
+
"grad_norm": 4.441513374331407e-05,
|
| 1211 |
+
"learning_rate": 1.2671111111111112e-05,
|
| 1212 |
+
"loss": 0.0,
|
| 1213 |
+
"step": 8400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 3.7555555555555555,
|
| 1217 |
+
"grad_norm": 5.228264126344584e-05,
|
| 1218 |
+
"learning_rate": 1.244888888888889e-05,
|
| 1219 |
+
"loss": 0.0,
|
| 1220 |
+
"step": 8450
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.7777777777777777,
|
| 1224 |
+
"grad_norm": 4.654955773730762e-05,
|
| 1225 |
+
"learning_rate": 1.2226666666666668e-05,
|
| 1226 |
+
"loss": 0.0,
|
| 1227 |
+
"step": 8500
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 3.8,
|
| 1231 |
+
"grad_norm": 5.188977957004681e-05,
|
| 1232 |
+
"learning_rate": 1.2004444444444444e-05,
|
| 1233 |
+
"loss": 0.0,
|
| 1234 |
+
"step": 8550
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 3.822222222222222,
|
| 1238 |
+
"grad_norm": 0.002792242681607604,
|
| 1239 |
+
"learning_rate": 1.1782222222222222e-05,
|
| 1240 |
+
"loss": 0.0,
|
| 1241 |
+
"step": 8600
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.8444444444444446,
|
| 1245 |
+
"grad_norm": 5.102707291371189e-05,
|
| 1246 |
+
"learning_rate": 1.156e-05,
|
| 1247 |
+
"loss": 0.0,
|
| 1248 |
+
"step": 8650
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.8666666666666667,
|
| 1252 |
+
"grad_norm": 4.642659405362792e-05,
|
| 1253 |
+
"learning_rate": 1.1337777777777777e-05,
|
| 1254 |
+
"loss": 0.0,
|
| 1255 |
+
"step": 8700
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 3.888888888888889,
|
| 1259 |
+
"grad_norm": 4.101167724002153e-05,
|
| 1260 |
+
"learning_rate": 1.1115555555555555e-05,
|
| 1261 |
+
"loss": 0.0,
|
| 1262 |
+
"step": 8750
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.911111111111111,
|
| 1266 |
+
"grad_norm": 4.7815203288337216e-05,
|
| 1267 |
+
"learning_rate": 1.0893333333333333e-05,
|
| 1268 |
+
"loss": 0.0,
|
| 1269 |
+
"step": 8800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.9333333333333336,
|
| 1273 |
+
"grad_norm": 4.7473920858465135e-05,
|
| 1274 |
+
"learning_rate": 1.0671111111111112e-05,
|
| 1275 |
+
"loss": 0.0,
|
| 1276 |
+
"step": 8850
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.9555555555555557,
|
| 1280 |
+
"grad_norm": 4.0860795706976205e-05,
|
| 1281 |
+
"learning_rate": 1.044888888888889e-05,
|
| 1282 |
+
"loss": 0.0,
|
| 1283 |
+
"step": 8900
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 3.977777777777778,
|
| 1287 |
+
"grad_norm": 3.960240792366676e-05,
|
| 1288 |
+
"learning_rate": 1.0226666666666668e-05,
|
| 1289 |
+
"loss": 0.0,
|
| 1290 |
+
"step": 8950
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.0,
|
| 1294 |
+
"grad_norm": 4.005260416306555e-05,
|
| 1295 |
+
"learning_rate": 1.0004444444444446e-05,
|
| 1296 |
+
"loss": 0.0,
|
| 1297 |
+
"step": 9000
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.0,
|
| 1301 |
+
"eval_loss": 3.7440361211338313e-07,
|
| 1302 |
+
"eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 8666\n EDUCATION 1.00 1.00 1.00 10841\n LANGUAGE 1.00 1.00 1.00 4050\n SKILL 1.00 1.00 1.00 14410\n\n micro avg 1.00 1.00 1.00 37967\n macro avg 1.00 1.00 1.00 37967\n weighted avg 1.00 1.00 1.00 37967\n",
|
| 1303 |
+
"eval_runtime": 39.2169,
|
| 1304 |
+
"eval_samples_per_second": 50.998,
|
| 1305 |
+
"eval_steps_per_second": 6.375,
|
| 1306 |
+
"step": 9000
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.022222222222222,
|
| 1310 |
+
"grad_norm": 4.486538819037378e-05,
|
| 1311 |
+
"learning_rate": 9.782222222222224e-06,
|
| 1312 |
+
"loss": 0.0,
|
| 1313 |
+
"step": 9050
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 4.044444444444444,
|
| 1317 |
+
"grad_norm": 4.269111741450615e-05,
|
| 1318 |
+
"learning_rate": 9.560000000000002e-06,
|
| 1319 |
+
"loss": 0.0,
|
| 1320 |
+
"step": 9100
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 4.066666666666666,
|
| 1324 |
+
"grad_norm": 3.833163282251917e-05,
|
| 1325 |
+
"learning_rate": 9.337777777777778e-06,
|
| 1326 |
+
"loss": 0.0,
|
| 1327 |
+
"step": 9150
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 4.088888888888889,
|
| 1331 |
+
"grad_norm": 5.278285243548453e-05,
|
| 1332 |
+
"learning_rate": 9.115555555555556e-06,
|
| 1333 |
+
"loss": 0.0,
|
| 1334 |
+
"step": 9200
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.111111111111111,
|
| 1338 |
+
"grad_norm": 3.422492227400653e-05,
|
| 1339 |
+
"learning_rate": 8.893333333333333e-06,
|
| 1340 |
+
"loss": 0.0,
|
| 1341 |
+
"step": 9250
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 4.133333333333334,
|
| 1345 |
+
"grad_norm": 3.486883360892534e-05,
|
| 1346 |
+
"learning_rate": 8.671111111111111e-06,
|
| 1347 |
+
"loss": 0.0,
|
| 1348 |
+
"step": 9300
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 4.155555555555556,
|
| 1352 |
+
"grad_norm": 3.659820868051611e-05,
|
| 1353 |
+
"learning_rate": 8.448888888888889e-06,
|
| 1354 |
+
"loss": 0.0,
|
| 1355 |
+
"step": 9350
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 4.177777777777778,
|
| 1359 |
+
"grad_norm": 3.242024467908777e-05,
|
| 1360 |
+
"learning_rate": 8.226666666666667e-06,
|
| 1361 |
+
"loss": 0.0,
|
| 1362 |
+
"step": 9400
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.2,
|
| 1366 |
+
"grad_norm": 0.0001435010926797986,
|
| 1367 |
+
"learning_rate": 8.004444444444445e-06,
|
| 1368 |
+
"loss": 0.0,
|
| 1369 |
+
"step": 9450
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 4.222222222222222,
|
| 1373 |
+
"grad_norm": 3.879176438204013e-05,
|
| 1374 |
+
"learning_rate": 7.782222222222223e-06,
|
| 1375 |
+
"loss": 0.0,
|
| 1376 |
+
"step": 9500
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 4.2444444444444445,
|
| 1380 |
+
"grad_norm": 3.1664359994465485e-05,
|
| 1381 |
+
"learning_rate": 7.5600000000000005e-06,
|
| 1382 |
+
"loss": 0.0,
|
| 1383 |
+
"step": 9550
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 4.266666666666667,
|
| 1387 |
+
"grad_norm": 3.302018012618646e-05,
|
| 1388 |
+
"learning_rate": 7.337777777777778e-06,
|
| 1389 |
+
"loss": 0.0,
|
| 1390 |
+
"step": 9600
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 4.288888888888889,
|
| 1394 |
+
"grad_norm": 0.00034453265834599733,
|
| 1395 |
+
"learning_rate": 7.115555555555556e-06,
|
| 1396 |
+
"loss": 0.0,
|
| 1397 |
+
"step": 9650
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 4.311111111111111,
|
| 1401 |
+
"grad_norm": 3.3918331610038877e-05,
|
| 1402 |
+
"learning_rate": 6.893333333333334e-06,
|
| 1403 |
+
"loss": 0.0,
|
| 1404 |
+
"step": 9700
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 4.333333333333333,
|
| 1408 |
+
"grad_norm": 3.994768121629022e-05,
|
| 1409 |
+
"learning_rate": 6.671111111111111e-06,
|
| 1410 |
+
"loss": 0.0,
|
| 1411 |
+
"step": 9750
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.355555555555555,
|
| 1415 |
+
"grad_norm": 7.467544492101297e-05,
|
| 1416 |
+
"learning_rate": 6.448888888888889e-06,
|
| 1417 |
+
"loss": 0.0,
|
| 1418 |
+
"step": 9800
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.377777777777778,
|
| 1422 |
+
"grad_norm": 3.103712879237719e-05,
|
| 1423 |
+
"learning_rate": 6.226666666666667e-06,
|
| 1424 |
+
"loss": 0.0,
|
| 1425 |
+
"step": 9850
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 4.4,
|
| 1429 |
+
"grad_norm": 4.751016604132019e-05,
|
| 1430 |
+
"learning_rate": 6.0044444444444445e-06,
|
| 1431 |
+
"loss": 0.0,
|
| 1432 |
+
"step": 9900
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 4.4222222222222225,
|
| 1436 |
+
"grad_norm": 9.309023153036833e-05,
|
| 1437 |
+
"learning_rate": 5.782222222222222e-06,
|
| 1438 |
+
"loss": 0.0,
|
| 1439 |
+
"step": 9950
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 4.444444444444445,
|
| 1443 |
+
"grad_norm": 3.0390472602448426e-05,
|
| 1444 |
+
"learning_rate": 5.56e-06,
|
| 1445 |
+
"loss": 0.0,
|
| 1446 |
+
"step": 10000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 4.466666666666667,
|
| 1450 |
+
"grad_norm": 3.085477146669291e-05,
|
| 1451 |
+
"learning_rate": 5.337777777777778e-06,
|
| 1452 |
+
"loss": 0.0,
|
| 1453 |
+
"step": 10050
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 4.488888888888889,
|
| 1457 |
+
"grad_norm": 3.4081851481460035e-05,
|
| 1458 |
+
"learning_rate": 5.115555555555556e-06,
|
| 1459 |
+
"loss": 0.0,
|
| 1460 |
+
"step": 10100
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 4.511111111111111,
|
| 1464 |
+
"grad_norm": 3.805098822340369e-05,
|
| 1465 |
+
"learning_rate": 4.893333333333334e-06,
|
| 1466 |
+
"loss": 0.0,
|
| 1467 |
+
"step": 10150
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.533333333333333,
|
| 1471 |
+
"grad_norm": 3.679243309306912e-05,
|
| 1472 |
+
"learning_rate": 4.6711111111111115e-06,
|
| 1473 |
+
"loss": 0.0,
|
| 1474 |
+
"step": 10200
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 4.555555555555555,
|
| 1478 |
+
"grad_norm": 3.425304385018535e-05,
|
| 1479 |
+
"learning_rate": 4.448888888888889e-06,
|
| 1480 |
+
"loss": 0.0,
|
| 1481 |
+
"step": 10250
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 4.5777777777777775,
|
| 1485 |
+
"grad_norm": 2.751518513832707e-05,
|
| 1486 |
+
"learning_rate": 4.226666666666667e-06,
|
| 1487 |
+
"loss": 0.0,
|
| 1488 |
+
"step": 10300
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 4.6,
|
| 1492 |
+
"grad_norm": 2.8532382202683948e-05,
|
| 1493 |
+
"learning_rate": 4.004444444444445e-06,
|
| 1494 |
+
"loss": 0.0,
|
| 1495 |
+
"step": 10350
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.622222222222222,
|
| 1499 |
+
"grad_norm": 2.9013817766099237e-05,
|
| 1500 |
+
"learning_rate": 3.7822222222222224e-06,
|
| 1501 |
+
"loss": 0.0,
|
| 1502 |
+
"step": 10400
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 4.644444444444445,
|
| 1506 |
+
"grad_norm": 3.07061527564656e-05,
|
| 1507 |
+
"learning_rate": 3.5600000000000002e-06,
|
| 1508 |
+
"loss": 0.0,
|
| 1509 |
+
"step": 10450
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.666666666666667,
|
| 1513 |
+
"grad_norm": 2.944734660559334e-05,
|
| 1514 |
+
"learning_rate": 3.337777777777778e-06,
|
| 1515 |
+
"loss": 0.0,
|
| 1516 |
+
"step": 10500
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.688888888888889,
|
| 1520 |
+
"grad_norm": 2.6814725060830824e-05,
|
| 1521 |
+
"learning_rate": 3.1155555555555555e-06,
|
| 1522 |
+
"loss": 0.0,
|
| 1523 |
+
"step": 10550
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 4.711111111111111,
|
| 1527 |
+
"grad_norm": 3.8631915231235325e-05,
|
| 1528 |
+
"learning_rate": 2.8933333333333333e-06,
|
| 1529 |
+
"loss": 0.0,
|
| 1530 |
+
"step": 10600
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.733333333333333,
|
| 1534 |
+
"grad_norm": 4.212988278595731e-05,
|
| 1535 |
+
"learning_rate": 2.6711111111111116e-06,
|
| 1536 |
+
"loss": 0.0,
|
| 1537 |
+
"step": 10650
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 4.7555555555555555,
|
| 1541 |
+
"grad_norm": 2.7735224648495205e-05,
|
| 1542 |
+
"learning_rate": 2.448888888888889e-06,
|
| 1543 |
+
"loss": 0.0,
|
| 1544 |
+
"step": 10700
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 4.777777777777778,
|
| 1548 |
+
"grad_norm": 3.2194642699323595e-05,
|
| 1549 |
+
"learning_rate": 2.226666666666667e-06,
|
| 1550 |
+
"loss": 0.0,
|
| 1551 |
+
"step": 10750
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 4.8,
|
| 1555 |
+
"grad_norm": 2.7552601750358008e-05,
|
| 1556 |
+
"learning_rate": 2.0044444444444446e-06,
|
| 1557 |
+
"loss": 0.0,
|
| 1558 |
+
"step": 10800
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 4.822222222222222,
|
| 1562 |
+
"grad_norm": 3.464681503828615e-05,
|
| 1563 |
+
"learning_rate": 1.7822222222222223e-06,
|
| 1564 |
+
"loss": 0.0,
|
| 1565 |
+
"step": 10850
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 4.844444444444444,
|
| 1569 |
+
"grad_norm": 2.8678237868007272e-05,
|
| 1570 |
+
"learning_rate": 1.56e-06,
|
| 1571 |
+
"loss": 0.0,
|
| 1572 |
+
"step": 10900
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 4.866666666666667,
|
| 1576 |
+
"grad_norm": 2.6989377147401683e-05,
|
| 1577 |
+
"learning_rate": 1.337777777777778e-06,
|
| 1578 |
+
"loss": 0.0,
|
| 1579 |
+
"step": 10950
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 4.888888888888889,
|
| 1583 |
+
"grad_norm": 2.9060267479508184e-05,
|
| 1584 |
+
"learning_rate": 1.1155555555555556e-06,
|
| 1585 |
+
"loss": 0.0,
|
| 1586 |
+
"step": 11000
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 4.911111111111111,
|
| 1590 |
+
"grad_norm": 4.428656757227145e-05,
|
| 1591 |
+
"learning_rate": 8.933333333333334e-07,
|
| 1592 |
+
"loss": 0.0,
|
| 1593 |
+
"step": 11050
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 4.933333333333334,
|
| 1597 |
+
"grad_norm": 2.6587131287669763e-05,
|
| 1598 |
+
"learning_rate": 6.711111111111111e-07,
|
| 1599 |
+
"loss": 0.0,
|
| 1600 |
+
"step": 11100
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 4.955555555555556,
|
| 1604 |
+
"grad_norm": 3.082263719988987e-05,
|
| 1605 |
+
"learning_rate": 4.488888888888889e-07,
|
| 1606 |
+
"loss": 0.0,
|
| 1607 |
+
"step": 11150
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 4.977777777777778,
|
| 1611 |
+
"grad_norm": 3.0073399102548137e-05,
|
| 1612 |
+
"learning_rate": 2.2666666666666668e-07,
|
| 1613 |
+
"loss": 0.0,
|
| 1614 |
+
"step": 11200
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 5.0,
|
| 1618 |
+
"grad_norm": 2.95465397357475e-05,
|
| 1619 |
+
"learning_rate": 4.444444444444445e-09,
|
| 1620 |
+
"loss": 0.0,
|
| 1621 |
+
"step": 11250
|
| 1622 |
+
}
|
| 1623 |
+
],
|
| 1624 |
+
"logging_steps": 50,
|
| 1625 |
+
"max_steps": 11250,
|
| 1626 |
+
"num_input_tokens_seen": 0,
|
| 1627 |
+
"num_train_epochs": 5,
|
| 1628 |
+
"save_steps": 500,
|
| 1629 |
+
"stateful_callbacks": {
|
| 1630 |
+
"TrainerControl": {
|
| 1631 |
+
"args": {
|
| 1632 |
+
"should_epoch_stop": false,
|
| 1633 |
+
"should_evaluate": false,
|
| 1634 |
+
"should_log": false,
|
| 1635 |
+
"should_save": true,
|
| 1636 |
+
"should_training_stop": true
|
| 1637 |
+
},
|
| 1638 |
+
"attributes": {}
|
| 1639 |
+
}
|
| 1640 |
+
},
|
| 1641 |
+
"total_flos": 1.0362271779289728e+16,
|
| 1642 |
+
"train_batch_size": 8,
|
| 1643 |
+
"trial_name": null,
|
| 1644 |
+
"trial_params": null
|
| 1645 |
+
}
|
checkpoint-11250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2437d3569274a4022188190da6f34872c3e1e86886e244e0bd97efb2e6b5384c
|
| 3 |
+
size 5713
|
config.json
CHANGED
|
@@ -10,28 +10,28 @@
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
-
"0": "
|
| 14 |
-
"1": "
|
| 15 |
-
"2": "
|
| 16 |
-
"3": "
|
| 17 |
-
"4": "
|
| 18 |
-
"5": "
|
| 19 |
-
"6": "
|
| 20 |
-
"7": "
|
| 21 |
-
"8": "
|
| 22 |
},
|
| 23 |
"initializer_range": 0.02,
|
| 24 |
"intermediate_size": 3072,
|
| 25 |
"label2id": {
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
},
|
| 36 |
"layer_norm_eps": 1e-07,
|
| 37 |
"legacy": true,
|
|
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "B-EDUCATION",
|
| 15 |
+
"2": "I-EDUCATION",
|
| 16 |
+
"3": "B-SKILL",
|
| 17 |
+
"4": "I-SKILL",
|
| 18 |
+
"5": "B-CERTIFICATION",
|
| 19 |
+
"6": "I-CERTIFICATION",
|
| 20 |
+
"7": "B-LANGUAGE",
|
| 21 |
+
"8": "I-LANGUAGE"
|
| 22 |
},
|
| 23 |
"initializer_range": 0.02,
|
| 24 |
"intermediate_size": 3072,
|
| 25 |
"label2id": {
|
| 26 |
+
"B-CERTIFICATION": 5,
|
| 27 |
+
"B-EDUCATION": 1,
|
| 28 |
+
"B-LANGUAGE": 7,
|
| 29 |
+
"B-SKILL": 3,
|
| 30 |
+
"I-CERTIFICATION": 6,
|
| 31 |
+
"I-EDUCATION": 2,
|
| 32 |
+
"I-LANGUAGE": 8,
|
| 33 |
+
"I-SKILL": 4,
|
| 34 |
+
"O": 0
|
| 35 |
},
|
| 36 |
"layer_norm_eps": 1e-07,
|
| 37 |
"legacy": true,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5713
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2437d3569274a4022188190da6f34872c3e1e86886e244e0bd97efb2e6b5384c
|
| 3 |
size 5713
|