Upload 7 files
Browse files- config (1).json +54 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1108 -0
- training_args.bin +3 -0
config (1).json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8",
|
| 20 |
+
"9": "LABEL_9",
|
| 21 |
+
"10": "LABEL_10",
|
| 22 |
+
"11": "LABEL_11",
|
| 23 |
+
"12": "LABEL_12"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"LABEL_0": 0,
|
| 29 |
+
"LABEL_1": 1,
|
| 30 |
+
"LABEL_10": 10,
|
| 31 |
+
"LABEL_11": 11,
|
| 32 |
+
"LABEL_12": 12,
|
| 33 |
+
"LABEL_2": 2,
|
| 34 |
+
"LABEL_3": 3,
|
| 35 |
+
"LABEL_4": 4,
|
| 36 |
+
"LABEL_5": 5,
|
| 37 |
+
"LABEL_6": 6,
|
| 38 |
+
"LABEL_7": 7,
|
| 39 |
+
"LABEL_8": 8,
|
| 40 |
+
"LABEL_9": 9
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"max_position_embeddings": 1024,
|
| 44 |
+
"model_type": "bert",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 13,
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.33.1",
|
| 51 |
+
"type_vocab_size": 2,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 14
|
| 54 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5039e05a64bb7a680a976dea235ae2656d20c5b2382d62f346bd38ed4a1264e0
|
| 3 |
+
size 691810053
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e521a0a66b3e5635c19f605cf8ae6ff62f562aef85269cb35e65e2ebeaeed2d
|
| 3 |
+
size 345889521
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b205c41d09b324f5102396ec6f30b35cb00cd6243175b1d004b14d1730be266
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83e9efe3690ff9a3fa0833a1fd6e3d3a2ee753521e1cd9c6c3596bdf6991ad17
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.23728813559322,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 69000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"learning_rate": 2.978813559322034e-05,
|
| 14 |
+
"loss": 0.2425,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.42,
|
| 19 |
+
"learning_rate": 2.9576271186440677e-05,
|
| 20 |
+
"loss": 0.2113,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.64,
|
| 25 |
+
"learning_rate": 2.9364406779661017e-05,
|
| 26 |
+
"loss": 0.2168,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.85,
|
| 31 |
+
"learning_rate": 2.9152542372881356e-05,
|
| 32 |
+
"loss": 0.2157,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.0,
|
| 37 |
+
"eval_accuracy": 0.7225042301184433,
|
| 38 |
+
"eval_loss": 0.14853818714618683,
|
| 39 |
+
"eval_runtime": 22.6834,
|
| 40 |
+
"eval_samples_per_second": 26.054,
|
| 41 |
+
"eval_steps_per_second": 1.102,
|
| 42 |
+
"step": 2360
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.06,
|
| 46 |
+
"learning_rate": 2.8940677966101696e-05,
|
| 47 |
+
"loss": 0.2233,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.27,
|
| 52 |
+
"learning_rate": 2.8728813559322036e-05,
|
| 53 |
+
"loss": 0.2157,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.48,
|
| 58 |
+
"learning_rate": 2.8516949152542372e-05,
|
| 59 |
+
"loss": 0.2232,
|
| 60 |
+
"step": 3500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.69,
|
| 64 |
+
"learning_rate": 2.8305084745762712e-05,
|
| 65 |
+
"loss": 0.2166,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.91,
|
| 70 |
+
"learning_rate": 2.809322033898305e-05,
|
| 71 |
+
"loss": 0.216,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.0,
|
| 76 |
+
"eval_accuracy": 0.7225042301184433,
|
| 77 |
+
"eval_loss": 0.13325555622577667,
|
| 78 |
+
"eval_runtime": 22.9508,
|
| 79 |
+
"eval_samples_per_second": 25.751,
|
| 80 |
+
"eval_steps_per_second": 1.089,
|
| 81 |
+
"step": 4720
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.12,
|
| 85 |
+
"learning_rate": 2.788135593220339e-05,
|
| 86 |
+
"loss": 0.2205,
|
| 87 |
+
"step": 5000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.33,
|
| 91 |
+
"learning_rate": 2.766949152542373e-05,
|
| 92 |
+
"loss": 0.2207,
|
| 93 |
+
"step": 5500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.54,
|
| 97 |
+
"learning_rate": 2.7457627118644068e-05,
|
| 98 |
+
"loss": 0.221,
|
| 99 |
+
"step": 6000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.75,
|
| 103 |
+
"learning_rate": 2.7245762711864407e-05,
|
| 104 |
+
"loss": 0.217,
|
| 105 |
+
"step": 6500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.97,
|
| 109 |
+
"learning_rate": 2.7033898305084747e-05,
|
| 110 |
+
"loss": 0.2173,
|
| 111 |
+
"step": 7000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.0,
|
| 115 |
+
"eval_accuracy": 0.7225042301184433,
|
| 116 |
+
"eval_loss": 0.14965683221817017,
|
| 117 |
+
"eval_runtime": 22.3153,
|
| 118 |
+
"eval_samples_per_second": 26.484,
|
| 119 |
+
"eval_steps_per_second": 1.12,
|
| 120 |
+
"step": 7080
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.18,
|
| 124 |
+
"learning_rate": 2.6822033898305083e-05,
|
| 125 |
+
"loss": 0.2149,
|
| 126 |
+
"step": 7500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.39,
|
| 130 |
+
"learning_rate": 2.6610169491525427e-05,
|
| 131 |
+
"loss": 0.2158,
|
| 132 |
+
"step": 8000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.6,
|
| 136 |
+
"learning_rate": 2.6398305084745763e-05,
|
| 137 |
+
"loss": 0.2149,
|
| 138 |
+
"step": 8500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.81,
|
| 142 |
+
"learning_rate": 2.6186440677966103e-05,
|
| 143 |
+
"loss": 0.2208,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.0,
|
| 148 |
+
"eval_accuracy": 0.7225042301184433,
|
| 149 |
+
"eval_loss": 0.14246971905231476,
|
| 150 |
+
"eval_runtime": 22.0006,
|
| 151 |
+
"eval_samples_per_second": 26.863,
|
| 152 |
+
"eval_steps_per_second": 1.136,
|
| 153 |
+
"step": 9440
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.03,
|
| 157 |
+
"learning_rate": 2.5974576271186442e-05,
|
| 158 |
+
"loss": 0.2182,
|
| 159 |
+
"step": 9500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.24,
|
| 163 |
+
"learning_rate": 2.576271186440678e-05,
|
| 164 |
+
"loss": 0.2152,
|
| 165 |
+
"step": 10000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.45,
|
| 169 |
+
"learning_rate": 2.555084745762712e-05,
|
| 170 |
+
"loss": 0.2199,
|
| 171 |
+
"step": 10500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.66,
|
| 175 |
+
"learning_rate": 2.5338983050847458e-05,
|
| 176 |
+
"loss": 0.2145,
|
| 177 |
+
"step": 11000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.87,
|
| 181 |
+
"learning_rate": 2.5127118644067798e-05,
|
| 182 |
+
"loss": 0.2165,
|
| 183 |
+
"step": 11500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.0,
|
| 187 |
+
"eval_accuracy": 0.7225042301184433,
|
| 188 |
+
"eval_loss": 0.1418760120868683,
|
| 189 |
+
"eval_runtime": 22.3285,
|
| 190 |
+
"eval_samples_per_second": 26.468,
|
| 191 |
+
"eval_steps_per_second": 1.12,
|
| 192 |
+
"step": 11800
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 5.08,
|
| 196 |
+
"learning_rate": 2.4915254237288138e-05,
|
| 197 |
+
"loss": 0.2225,
|
| 198 |
+
"step": 12000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 5.3,
|
| 202 |
+
"learning_rate": 2.4703389830508474e-05,
|
| 203 |
+
"loss": 0.2141,
|
| 204 |
+
"step": 12500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.51,
|
| 208 |
+
"learning_rate": 2.4491525423728814e-05,
|
| 209 |
+
"loss": 0.2199,
|
| 210 |
+
"step": 13000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 5.72,
|
| 214 |
+
"learning_rate": 2.427966101694915e-05,
|
| 215 |
+
"loss": 0.2169,
|
| 216 |
+
"step": 13500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.93,
|
| 220 |
+
"learning_rate": 2.4067796610169493e-05,
|
| 221 |
+
"loss": 0.2152,
|
| 222 |
+
"step": 14000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 6.0,
|
| 226 |
+
"eval_accuracy": 0.7225042301184433,
|
| 227 |
+
"eval_loss": 0.14399726688861847,
|
| 228 |
+
"eval_runtime": 22.3281,
|
| 229 |
+
"eval_samples_per_second": 26.469,
|
| 230 |
+
"eval_steps_per_second": 1.12,
|
| 231 |
+
"step": 14160
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.14,
|
| 235 |
+
"learning_rate": 2.3855932203389833e-05,
|
| 236 |
+
"loss": 0.2198,
|
| 237 |
+
"step": 14500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.36,
|
| 241 |
+
"learning_rate": 2.364406779661017e-05,
|
| 242 |
+
"loss": 0.2207,
|
| 243 |
+
"step": 15000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.57,
|
| 247 |
+
"learning_rate": 2.343220338983051e-05,
|
| 248 |
+
"loss": 0.2171,
|
| 249 |
+
"step": 15500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.78,
|
| 253 |
+
"learning_rate": 2.3220338983050846e-05,
|
| 254 |
+
"loss": 0.2123,
|
| 255 |
+
"step": 16000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 6.99,
|
| 259 |
+
"learning_rate": 2.3008474576271185e-05,
|
| 260 |
+
"loss": 0.2166,
|
| 261 |
+
"step": 16500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 7.0,
|
| 265 |
+
"eval_accuracy": 0.7225042301184433,
|
| 266 |
+
"eval_loss": 0.14218531548976898,
|
| 267 |
+
"eval_runtime": 22.4949,
|
| 268 |
+
"eval_samples_per_second": 26.273,
|
| 269 |
+
"eval_steps_per_second": 1.111,
|
| 270 |
+
"step": 16520
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 7.2,
|
| 274 |
+
"learning_rate": 2.279661016949153e-05,
|
| 275 |
+
"loss": 0.2142,
|
| 276 |
+
"step": 17000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 7.42,
|
| 280 |
+
"learning_rate": 2.2584745762711865e-05,
|
| 281 |
+
"loss": 0.2167,
|
| 282 |
+
"step": 17500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 7.63,
|
| 286 |
+
"learning_rate": 2.2372881355932205e-05,
|
| 287 |
+
"loss": 0.2224,
|
| 288 |
+
"step": 18000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 7.84,
|
| 292 |
+
"learning_rate": 2.2161016949152544e-05,
|
| 293 |
+
"loss": 0.2129,
|
| 294 |
+
"step": 18500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 8.0,
|
| 298 |
+
"eval_accuracy": 0.7225042301184433,
|
| 299 |
+
"eval_loss": 0.13575270771980286,
|
| 300 |
+
"eval_runtime": 22.1798,
|
| 301 |
+
"eval_samples_per_second": 26.646,
|
| 302 |
+
"eval_steps_per_second": 1.127,
|
| 303 |
+
"step": 18880
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 8.05,
|
| 307 |
+
"learning_rate": 2.194915254237288e-05,
|
| 308 |
+
"loss": 0.2231,
|
| 309 |
+
"step": 19000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 8.26,
|
| 313 |
+
"learning_rate": 2.173728813559322e-05,
|
| 314 |
+
"loss": 0.2178,
|
| 315 |
+
"step": 19500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 8.47,
|
| 319 |
+
"learning_rate": 2.152542372881356e-05,
|
| 320 |
+
"loss": 0.2218,
|
| 321 |
+
"step": 20000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 8.69,
|
| 325 |
+
"learning_rate": 2.13135593220339e-05,
|
| 326 |
+
"loss": 0.2124,
|
| 327 |
+
"step": 20500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 8.9,
|
| 331 |
+
"learning_rate": 2.110169491525424e-05,
|
| 332 |
+
"loss": 0.2158,
|
| 333 |
+
"step": 21000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 9.0,
|
| 337 |
+
"eval_accuracy": 0.7225042301184433,
|
| 338 |
+
"eval_loss": 0.14425306022167206,
|
| 339 |
+
"eval_runtime": 22.3031,
|
| 340 |
+
"eval_samples_per_second": 26.499,
|
| 341 |
+
"eval_steps_per_second": 1.121,
|
| 342 |
+
"step": 21240
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.11,
|
| 346 |
+
"learning_rate": 2.0889830508474576e-05,
|
| 347 |
+
"loss": 0.2114,
|
| 348 |
+
"step": 21500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 9.32,
|
| 352 |
+
"learning_rate": 2.0677966101694916e-05,
|
| 353 |
+
"loss": 0.218,
|
| 354 |
+
"step": 22000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.53,
|
| 358 |
+
"learning_rate": 2.0466101694915252e-05,
|
| 359 |
+
"loss": 0.2198,
|
| 360 |
+
"step": 22500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 9.75,
|
| 364 |
+
"learning_rate": 2.0254237288135595e-05,
|
| 365 |
+
"loss": 0.2207,
|
| 366 |
+
"step": 23000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 9.96,
|
| 370 |
+
"learning_rate": 2.0042372881355935e-05,
|
| 371 |
+
"loss": 0.2112,
|
| 372 |
+
"step": 23500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 10.0,
|
| 376 |
+
"eval_accuracy": 0.7225042301184433,
|
| 377 |
+
"eval_loss": 0.14262421429157257,
|
| 378 |
+
"eval_runtime": 22.232,
|
| 379 |
+
"eval_samples_per_second": 26.583,
|
| 380 |
+
"eval_steps_per_second": 1.125,
|
| 381 |
+
"step": 23600
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 10.17,
|
| 385 |
+
"learning_rate": 1.983050847457627e-05,
|
| 386 |
+
"loss": 0.2188,
|
| 387 |
+
"step": 24000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 10.38,
|
| 391 |
+
"learning_rate": 1.961864406779661e-05,
|
| 392 |
+
"loss": 0.2103,
|
| 393 |
+
"step": 24500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 10.59,
|
| 397 |
+
"learning_rate": 1.9406779661016948e-05,
|
| 398 |
+
"loss": 0.2221,
|
| 399 |
+
"step": 25000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 10.81,
|
| 403 |
+
"learning_rate": 1.9194915254237287e-05,
|
| 404 |
+
"loss": 0.2128,
|
| 405 |
+
"step": 25500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 11.0,
|
| 409 |
+
"eval_accuracy": 0.7225042301184433,
|
| 410 |
+
"eval_loss": 0.13920965790748596,
|
| 411 |
+
"eval_runtime": 21.869,
|
| 412 |
+
"eval_samples_per_second": 27.025,
|
| 413 |
+
"eval_steps_per_second": 1.143,
|
| 414 |
+
"step": 25960
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 11.02,
|
| 418 |
+
"learning_rate": 1.898305084745763e-05,
|
| 419 |
+
"loss": 0.2196,
|
| 420 |
+
"step": 26000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 11.23,
|
| 424 |
+
"learning_rate": 1.8771186440677967e-05,
|
| 425 |
+
"loss": 0.2134,
|
| 426 |
+
"step": 26500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 11.44,
|
| 430 |
+
"learning_rate": 1.8559322033898307e-05,
|
| 431 |
+
"loss": 0.2157,
|
| 432 |
+
"step": 27000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 11.65,
|
| 436 |
+
"learning_rate": 1.8347457627118643e-05,
|
| 437 |
+
"loss": 0.2112,
|
| 438 |
+
"step": 27500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 11.86,
|
| 442 |
+
"learning_rate": 1.8135593220338983e-05,
|
| 443 |
+
"loss": 0.2242,
|
| 444 |
+
"step": 28000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 12.0,
|
| 448 |
+
"eval_accuracy": 0.7225042301184433,
|
| 449 |
+
"eval_loss": 0.13710011541843414,
|
| 450 |
+
"eval_runtime": 22.1879,
|
| 451 |
+
"eval_samples_per_second": 26.636,
|
| 452 |
+
"eval_steps_per_second": 1.127,
|
| 453 |
+
"step": 28320
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 12.08,
|
| 457 |
+
"learning_rate": 1.7923728813559322e-05,
|
| 458 |
+
"loss": 0.2147,
|
| 459 |
+
"step": 28500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 12.29,
|
| 463 |
+
"learning_rate": 1.7711864406779662e-05,
|
| 464 |
+
"loss": 0.2104,
|
| 465 |
+
"step": 29000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 12.5,
|
| 469 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 470 |
+
"loss": 0.2192,
|
| 471 |
+
"step": 29500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 12.71,
|
| 475 |
+
"learning_rate": 1.728813559322034e-05,
|
| 476 |
+
"loss": 0.2196,
|
| 477 |
+
"step": 30000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 12.92,
|
| 481 |
+
"learning_rate": 1.7076271186440678e-05,
|
| 482 |
+
"loss": 0.219,
|
| 483 |
+
"step": 30500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 13.0,
|
| 487 |
+
"eval_accuracy": 0.7225042301184433,
|
| 488 |
+
"eval_loss": 0.13678474724292755,
|
| 489 |
+
"eval_runtime": 22.3039,
|
| 490 |
+
"eval_samples_per_second": 26.498,
|
| 491 |
+
"eval_steps_per_second": 1.121,
|
| 492 |
+
"step": 30680
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 13.14,
|
| 496 |
+
"learning_rate": 1.6864406779661018e-05,
|
| 497 |
+
"loss": 0.2198,
|
| 498 |
+
"step": 31000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 13.35,
|
| 502 |
+
"learning_rate": 1.6652542372881354e-05,
|
| 503 |
+
"loss": 0.2193,
|
| 504 |
+
"step": 31500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 13.56,
|
| 508 |
+
"learning_rate": 1.6440677966101694e-05,
|
| 509 |
+
"loss": 0.2149,
|
| 510 |
+
"step": 32000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 13.77,
|
| 514 |
+
"learning_rate": 1.6228813559322037e-05,
|
| 515 |
+
"loss": 0.2136,
|
| 516 |
+
"step": 32500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 13.98,
|
| 520 |
+
"learning_rate": 1.6016949152542373e-05,
|
| 521 |
+
"loss": 0.215,
|
| 522 |
+
"step": 33000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 14.0,
|
| 526 |
+
"eval_accuracy": 0.7225042301184433,
|
| 527 |
+
"eval_loss": 0.1423649787902832,
|
| 528 |
+
"eval_runtime": 22.5006,
|
| 529 |
+
"eval_samples_per_second": 26.266,
|
| 530 |
+
"eval_steps_per_second": 1.111,
|
| 531 |
+
"step": 33040
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 14.19,
|
| 535 |
+
"learning_rate": 1.5805084745762713e-05,
|
| 536 |
+
"loss": 0.2148,
|
| 537 |
+
"step": 33500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 14.41,
|
| 541 |
+
"learning_rate": 1.559322033898305e-05,
|
| 542 |
+
"loss": 0.2197,
|
| 543 |
+
"step": 34000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 14.62,
|
| 547 |
+
"learning_rate": 1.538135593220339e-05,
|
| 548 |
+
"loss": 0.2165,
|
| 549 |
+
"step": 34500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 14.83,
|
| 553 |
+
"learning_rate": 1.5169491525423727e-05,
|
| 554 |
+
"loss": 0.2183,
|
| 555 |
+
"step": 35000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 15.0,
|
| 559 |
+
"eval_accuracy": 0.7225042301184433,
|
| 560 |
+
"eval_loss": 0.14253665506839752,
|
| 561 |
+
"eval_runtime": 22.0912,
|
| 562 |
+
"eval_samples_per_second": 26.753,
|
| 563 |
+
"eval_steps_per_second": 1.132,
|
| 564 |
+
"step": 35400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 15.04,
|
| 568 |
+
"learning_rate": 1.4957627118644067e-05,
|
| 569 |
+
"loss": 0.21,
|
| 570 |
+
"step": 35500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 15.25,
|
| 574 |
+
"learning_rate": 1.4745762711864408e-05,
|
| 575 |
+
"loss": 0.2191,
|
| 576 |
+
"step": 36000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 15.47,
|
| 580 |
+
"learning_rate": 1.4533898305084746e-05,
|
| 581 |
+
"loss": 0.2156,
|
| 582 |
+
"step": 36500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 15.68,
|
| 586 |
+
"learning_rate": 1.4322033898305085e-05,
|
| 587 |
+
"loss": 0.2171,
|
| 588 |
+
"step": 37000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 15.89,
|
| 592 |
+
"learning_rate": 1.4110169491525424e-05,
|
| 593 |
+
"loss": 0.2196,
|
| 594 |
+
"step": 37500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 16.0,
|
| 598 |
+
"eval_accuracy": 0.7225042301184433,
|
| 599 |
+
"eval_loss": 0.14593291282653809,
|
| 600 |
+
"eval_runtime": 22.3278,
|
| 601 |
+
"eval_samples_per_second": 26.469,
|
| 602 |
+
"eval_steps_per_second": 1.12,
|
| 603 |
+
"step": 37760
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 16.1,
|
| 607 |
+
"learning_rate": 1.3898305084745764e-05,
|
| 608 |
+
"loss": 0.2096,
|
| 609 |
+
"step": 38000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 16.31,
|
| 613 |
+
"learning_rate": 1.3686440677966102e-05,
|
| 614 |
+
"loss": 0.2163,
|
| 615 |
+
"step": 38500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 16.53,
|
| 619 |
+
"learning_rate": 1.3474576271186442e-05,
|
| 620 |
+
"loss": 0.2202,
|
| 621 |
+
"step": 39000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 16.74,
|
| 625 |
+
"learning_rate": 1.326271186440678e-05,
|
| 626 |
+
"loss": 0.2143,
|
| 627 |
+
"step": 39500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 16.95,
|
| 631 |
+
"learning_rate": 1.3050847457627118e-05,
|
| 632 |
+
"loss": 0.2166,
|
| 633 |
+
"step": 40000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 17.0,
|
| 637 |
+
"eval_accuracy": 0.7225042301184433,
|
| 638 |
+
"eval_loss": 0.14286492764949799,
|
| 639 |
+
"eval_runtime": 22.0561,
|
| 640 |
+
"eval_samples_per_second": 26.795,
|
| 641 |
+
"eval_steps_per_second": 1.133,
|
| 642 |
+
"step": 40120
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 17.16,
|
| 646 |
+
"learning_rate": 1.283898305084746e-05,
|
| 647 |
+
"loss": 0.2153,
|
| 648 |
+
"step": 40500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 17.37,
|
| 652 |
+
"learning_rate": 1.2627118644067797e-05,
|
| 653 |
+
"loss": 0.218,
|
| 654 |
+
"step": 41000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 17.58,
|
| 658 |
+
"learning_rate": 1.2415254237288135e-05,
|
| 659 |
+
"loss": 0.2148,
|
| 660 |
+
"step": 41500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 17.8,
|
| 664 |
+
"learning_rate": 1.2203389830508475e-05,
|
| 665 |
+
"loss": 0.2127,
|
| 666 |
+
"step": 42000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 18.0,
|
| 670 |
+
"eval_accuracy": 0.7225042301184433,
|
| 671 |
+
"eval_loss": 0.14040569961071014,
|
| 672 |
+
"eval_runtime": 21.8515,
|
| 673 |
+
"eval_samples_per_second": 27.046,
|
| 674 |
+
"eval_steps_per_second": 1.144,
|
| 675 |
+
"step": 42480
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 18.01,
|
| 679 |
+
"learning_rate": 1.1991525423728813e-05,
|
| 680 |
+
"loss": 0.2214,
|
| 681 |
+
"step": 42500
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 18.22,
|
| 685 |
+
"learning_rate": 1.1779661016949153e-05,
|
| 686 |
+
"loss": 0.2125,
|
| 687 |
+
"step": 43000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 18.43,
|
| 691 |
+
"learning_rate": 1.1567796610169493e-05,
|
| 692 |
+
"loss": 0.2161,
|
| 693 |
+
"step": 43500
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 18.64,
|
| 697 |
+
"learning_rate": 1.135593220338983e-05,
|
| 698 |
+
"loss": 0.2197,
|
| 699 |
+
"step": 44000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 18.86,
|
| 703 |
+
"learning_rate": 1.1144067796610169e-05,
|
| 704 |
+
"loss": 0.2174,
|
| 705 |
+
"step": 44500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 19.0,
|
| 709 |
+
"eval_accuracy": 0.7225042301184433,
|
| 710 |
+
"eval_loss": 0.13983392715454102,
|
| 711 |
+
"eval_runtime": 22.1759,
|
| 712 |
+
"eval_samples_per_second": 26.651,
|
| 713 |
+
"eval_steps_per_second": 1.127,
|
| 714 |
+
"step": 44840
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 19.07,
|
| 718 |
+
"learning_rate": 1.0932203389830509e-05,
|
| 719 |
+
"loss": 0.2163,
|
| 720 |
+
"step": 45000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 19.28,
|
| 724 |
+
"learning_rate": 1.0720338983050848e-05,
|
| 725 |
+
"loss": 0.2206,
|
| 726 |
+
"step": 45500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 19.49,
|
| 730 |
+
"learning_rate": 1.0508474576271186e-05,
|
| 731 |
+
"loss": 0.2159,
|
| 732 |
+
"step": 46000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 19.7,
|
| 736 |
+
"learning_rate": 1.0296610169491524e-05,
|
| 737 |
+
"loss": 0.2129,
|
| 738 |
+
"step": 46500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 19.92,
|
| 742 |
+
"learning_rate": 1.0084745762711864e-05,
|
| 743 |
+
"loss": 0.2174,
|
| 744 |
+
"step": 47000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 20.0,
|
| 748 |
+
"eval_accuracy": 0.7225042301184433,
|
| 749 |
+
"eval_loss": 0.14546626806259155,
|
| 750 |
+
"eval_runtime": 22.2976,
|
| 751 |
+
"eval_samples_per_second": 26.505,
|
| 752 |
+
"eval_steps_per_second": 1.121,
|
| 753 |
+
"step": 47200
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 20.13,
|
| 757 |
+
"learning_rate": 9.872881355932204e-06,
|
| 758 |
+
"loss": 0.2146,
|
| 759 |
+
"step": 47500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 20.34,
|
| 763 |
+
"learning_rate": 9.661016949152542e-06,
|
| 764 |
+
"loss": 0.2163,
|
| 765 |
+
"step": 48000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 20.55,
|
| 769 |
+
"learning_rate": 9.449152542372882e-06,
|
| 770 |
+
"loss": 0.2113,
|
| 771 |
+
"step": 48500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 20.76,
|
| 775 |
+
"learning_rate": 9.23728813559322e-06,
|
| 776 |
+
"loss": 0.2208,
|
| 777 |
+
"step": 49000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 20.97,
|
| 781 |
+
"learning_rate": 9.02542372881356e-06,
|
| 782 |
+
"loss": 0.2114,
|
| 783 |
+
"step": 49500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 21.0,
|
| 787 |
+
"eval_accuracy": 0.7225042301184433,
|
| 788 |
+
"eval_loss": 0.14164069294929504,
|
| 789 |
+
"eval_runtime": 22.6001,
|
| 790 |
+
"eval_samples_per_second": 26.15,
|
| 791 |
+
"eval_steps_per_second": 1.106,
|
| 792 |
+
"step": 49560
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 21.19,
|
| 796 |
+
"learning_rate": 8.8135593220339e-06,
|
| 797 |
+
"loss": 0.2155,
|
| 798 |
+
"step": 50000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 21.4,
|
| 802 |
+
"learning_rate": 8.601694915254237e-06,
|
| 803 |
+
"loss": 0.2197,
|
| 804 |
+
"step": 50500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 21.61,
|
| 808 |
+
"learning_rate": 8.389830508474575e-06,
|
| 809 |
+
"loss": 0.2151,
|
| 810 |
+
"step": 51000
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 21.82,
|
| 814 |
+
"learning_rate": 8.177966101694915e-06,
|
| 815 |
+
"loss": 0.2123,
|
| 816 |
+
"step": 51500
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 22.0,
|
| 820 |
+
"eval_accuracy": 0.7225042301184433,
|
| 821 |
+
"eval_loss": 0.13964423537254333,
|
| 822 |
+
"eval_runtime": 22.1829,
|
| 823 |
+
"eval_samples_per_second": 26.642,
|
| 824 |
+
"eval_steps_per_second": 1.127,
|
| 825 |
+
"step": 51920
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 22.03,
|
| 829 |
+
"learning_rate": 7.966101694915255e-06,
|
| 830 |
+
"loss": 0.2176,
|
| 831 |
+
"step": 52000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 22.25,
|
| 835 |
+
"learning_rate": 7.754237288135593e-06,
|
| 836 |
+
"loss": 0.2136,
|
| 837 |
+
"step": 52500
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 22.46,
|
| 841 |
+
"learning_rate": 7.542372881355933e-06,
|
| 842 |
+
"loss": 0.2261,
|
| 843 |
+
"step": 53000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 22.67,
|
| 847 |
+
"learning_rate": 7.330508474576272e-06,
|
| 848 |
+
"loss": 0.2111,
|
| 849 |
+
"step": 53500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 22.88,
|
| 853 |
+
"learning_rate": 7.1186440677966106e-06,
|
| 854 |
+
"loss": 0.2129,
|
| 855 |
+
"step": 54000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 23.0,
|
| 859 |
+
"eval_accuracy": 0.7225042301184433,
|
| 860 |
+
"eval_loss": 0.14013490080833435,
|
| 861 |
+
"eval_runtime": 22.24,
|
| 862 |
+
"eval_samples_per_second": 26.574,
|
| 863 |
+
"eval_steps_per_second": 1.124,
|
| 864 |
+
"step": 54280
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 23.09,
|
| 868 |
+
"learning_rate": 6.906779661016949e-06,
|
| 869 |
+
"loss": 0.2161,
|
| 870 |
+
"step": 54500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 23.31,
|
| 874 |
+
"learning_rate": 6.694915254237288e-06,
|
| 875 |
+
"loss": 0.2181,
|
| 876 |
+
"step": 55000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 23.52,
|
| 880 |
+
"learning_rate": 6.483050847457627e-06,
|
| 881 |
+
"loss": 0.2151,
|
| 882 |
+
"step": 55500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 23.73,
|
| 886 |
+
"learning_rate": 6.271186440677966e-06,
|
| 887 |
+
"loss": 0.215,
|
| 888 |
+
"step": 56000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 23.94,
|
| 892 |
+
"learning_rate": 6.059322033898305e-06,
|
| 893 |
+
"loss": 0.2156,
|
| 894 |
+
"step": 56500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 24.0,
|
| 898 |
+
"eval_accuracy": 0.7225042301184433,
|
| 899 |
+
"eval_loss": 0.14107845723628998,
|
| 900 |
+
"eval_runtime": 22.1976,
|
| 901 |
+
"eval_samples_per_second": 26.625,
|
| 902 |
+
"eval_steps_per_second": 1.126,
|
| 903 |
+
"step": 56640
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 24.15,
|
| 907 |
+
"learning_rate": 5.847457627118645e-06,
|
| 908 |
+
"loss": 0.2168,
|
| 909 |
+
"step": 57000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 24.36,
|
| 913 |
+
"learning_rate": 5.635593220338983e-06,
|
| 914 |
+
"loss": 0.2138,
|
| 915 |
+
"step": 57500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 24.58,
|
| 919 |
+
"learning_rate": 5.423728813559322e-06,
|
| 920 |
+
"loss": 0.2113,
|
| 921 |
+
"step": 58000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 24.79,
|
| 925 |
+
"learning_rate": 5.2118644067796615e-06,
|
| 926 |
+
"loss": 0.2153,
|
| 927 |
+
"step": 58500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 25.0,
|
| 931 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 932 |
+
"loss": 0.2193,
|
| 933 |
+
"step": 59000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 25.0,
|
| 937 |
+
"eval_accuracy": 0.7225042301184433,
|
| 938 |
+
"eval_loss": 0.13969872891902924,
|
| 939 |
+
"eval_runtime": 22.1245,
|
| 940 |
+
"eval_samples_per_second": 26.712,
|
| 941 |
+
"eval_steps_per_second": 1.13,
|
| 942 |
+
"step": 59000
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 25.21,
|
| 946 |
+
"learning_rate": 4.788135593220339e-06,
|
| 947 |
+
"loss": 0.2183,
|
| 948 |
+
"step": 59500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 25.42,
|
| 952 |
+
"learning_rate": 4.576271186440678e-06,
|
| 953 |
+
"loss": 0.2184,
|
| 954 |
+
"step": 60000
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 25.64,
|
| 958 |
+
"learning_rate": 4.364406779661017e-06,
|
| 959 |
+
"loss": 0.2161,
|
| 960 |
+
"step": 60500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 25.85,
|
| 964 |
+
"learning_rate": 4.152542372881356e-06,
|
| 965 |
+
"loss": 0.2072,
|
| 966 |
+
"step": 61000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 26.0,
|
| 970 |
+
"eval_accuracy": 0.7225042301184433,
|
| 971 |
+
"eval_loss": 0.14177070558071136,
|
| 972 |
+
"eval_runtime": 22.3038,
|
| 973 |
+
"eval_samples_per_second": 26.498,
|
| 974 |
+
"eval_steps_per_second": 1.121,
|
| 975 |
+
"step": 61360
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 26.06,
|
| 979 |
+
"learning_rate": 3.940677966101696e-06,
|
| 980 |
+
"loss": 0.2173,
|
| 981 |
+
"step": 61500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 26.27,
|
| 985 |
+
"learning_rate": 3.7288135593220342e-06,
|
| 986 |
+
"loss": 0.2123,
|
| 987 |
+
"step": 62000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 26.48,
|
| 991 |
+
"learning_rate": 3.516949152542373e-06,
|
| 992 |
+
"loss": 0.2133,
|
| 993 |
+
"step": 62500
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 26.69,
|
| 997 |
+
"learning_rate": 3.305084745762712e-06,
|
| 998 |
+
"loss": 0.2166,
|
| 999 |
+
"step": 63000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 26.91,
|
| 1003 |
+
"learning_rate": 3.093220338983051e-06,
|
| 1004 |
+
"loss": 0.2188,
|
| 1005 |
+
"step": 63500
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 27.0,
|
| 1009 |
+
"eval_accuracy": 0.7225042301184433,
|
| 1010 |
+
"eval_loss": 0.13952849805355072,
|
| 1011 |
+
"eval_runtime": 22.4612,
|
| 1012 |
+
"eval_samples_per_second": 26.312,
|
| 1013 |
+
"eval_steps_per_second": 1.113,
|
| 1014 |
+
"step": 63720
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 27.12,
|
| 1018 |
+
"learning_rate": 2.88135593220339e-06,
|
| 1019 |
+
"loss": 0.2155,
|
| 1020 |
+
"step": 64000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 27.33,
|
| 1024 |
+
"learning_rate": 2.6694915254237287e-06,
|
| 1025 |
+
"loss": 0.2186,
|
| 1026 |
+
"step": 64500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 27.54,
|
| 1030 |
+
"learning_rate": 2.4576271186440676e-06,
|
| 1031 |
+
"loss": 0.2195,
|
| 1032 |
+
"step": 65000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 27.75,
|
| 1036 |
+
"learning_rate": 2.245762711864407e-06,
|
| 1037 |
+
"loss": 0.222,
|
| 1038 |
+
"step": 65500
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 27.97,
|
| 1042 |
+
"learning_rate": 2.033898305084746e-06,
|
| 1043 |
+
"loss": 0.2082,
|
| 1044 |
+
"step": 66000
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 28.0,
|
| 1048 |
+
"eval_accuracy": 0.7225042301184433,
|
| 1049 |
+
"eval_loss": 0.14052434265613556,
|
| 1050 |
+
"eval_runtime": 22.7926,
|
| 1051 |
+
"eval_samples_per_second": 25.929,
|
| 1052 |
+
"eval_steps_per_second": 1.097,
|
| 1053 |
+
"step": 66080
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 28.18,
|
| 1057 |
+
"learning_rate": 1.8220338983050848e-06,
|
| 1058 |
+
"loss": 0.211,
|
| 1059 |
+
"step": 66500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 28.39,
|
| 1063 |
+
"learning_rate": 1.6101694915254237e-06,
|
| 1064 |
+
"loss": 0.2196,
|
| 1065 |
+
"step": 67000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 28.6,
|
| 1069 |
+
"learning_rate": 1.3983050847457628e-06,
|
| 1070 |
+
"loss": 0.2172,
|
| 1071 |
+
"step": 67500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 28.81,
|
| 1075 |
+
"learning_rate": 1.186440677966102e-06,
|
| 1076 |
+
"loss": 0.214,
|
| 1077 |
+
"step": 68000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 29.0,
|
| 1081 |
+
"eval_accuracy": 0.7225042301184433,
|
| 1082 |
+
"eval_loss": 0.14071397483348846,
|
| 1083 |
+
"eval_runtime": 22.1609,
|
| 1084 |
+
"eval_samples_per_second": 26.669,
|
| 1085 |
+
"eval_steps_per_second": 1.128,
|
| 1086 |
+
"step": 68440
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 29.03,
|
| 1090 |
+
"learning_rate": 9.745762711864406e-07,
|
| 1091 |
+
"loss": 0.2116,
|
| 1092 |
+
"step": 68500
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 29.24,
|
| 1096 |
+
"learning_rate": 7.627118644067797e-07,
|
| 1097 |
+
"loss": 0.216,
|
| 1098 |
+
"step": 69000
|
| 1099 |
+
}
|
| 1100 |
+
],
|
| 1101 |
+
"logging_steps": 500,
|
| 1102 |
+
"max_steps": 70800,
|
| 1103 |
+
"num_train_epochs": 30,
|
| 1104 |
+
"save_steps": 1500,
|
| 1105 |
+
"total_flos": 1.8723845102688e+16,
|
| 1106 |
+
"trial_name": null,
|
| 1107 |
+
"trial_params": null
|
| 1108 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13c8b3b2578eb0827ef7fc46072784378950a5687a74162940d7dc8e6c15718f
|
| 3 |
+
size 4027
|