Upload checkpoint and eval results at step 4500
Browse files- checkpoint-4500/config.json +38 -0
- checkpoint-4500/eval_results.json +12 -0
- checkpoint-4500/eval_step_004500.json +16 -0
- checkpoint-4500/model.safetensors +3 -0
- checkpoint-4500/optimizer.pt +3 -0
- checkpoint-4500/rng_state.pth +3 -0
- checkpoint-4500/scaler.pt +3 -0
- checkpoint-4500/scheduler.pt +3 -0
- checkpoint-4500/tokenizer.json +0 -0
- checkpoint-4500/tokenizer_config.json +15 -0
- checkpoint-4500/trainer_state.json +1418 -0
- checkpoint-4500/training_args.bin +3 -0
checkpoint-4500/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "benign",
|
| 17 |
+
"1": "malicious"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"is_decoder": false,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"benign": 0,
|
| 24 |
+
"malicious": 1
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 512,
|
| 28 |
+
"model_type": "bert",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"tie_word_embeddings": true,
|
| 34 |
+
"transformers_version": "5.13.0",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
checkpoint-4500/eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 4500,
|
| 3 |
+
"epoch": 2.8391167192429023,
|
| 4 |
+
"time": "2026-07-08 14:49:44",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.07868093252182007,
|
| 7 |
+
"eval_accuracy": 0.9823343848580441,
|
| 8 |
+
"eval_precision": 0.968156766687079,
|
| 9 |
+
"eval_recall": 0.9974763406940063,
|
| 10 |
+
"eval_f1": 0.9825978868862648
|
| 11 |
+
}
|
| 12 |
+
}
|
checkpoint-4500/eval_step_004500.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 4500,
|
| 3 |
+
"epoch": 2.8391167192429023,
|
| 4 |
+
"time": "2026-07-08 14:49:44",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.07868093252182007,
|
| 7 |
+
"eval_accuracy": 0.9823343848580441,
|
| 8 |
+
"eval_precision": 0.968156766687079,
|
| 9 |
+
"eval_recall": 0.9974763406940063,
|
| 10 |
+
"eval_f1": 0.9825978868862648,
|
| 11 |
+
"eval_runtime": 61.7337,
|
| 12 |
+
"eval_samples_per_second": 51.35,
|
| 13 |
+
"eval_steps_per_second": 3.224,
|
| 14 |
+
"epoch": 2.8391167192429023
|
| 15 |
+
}
|
| 16 |
+
}
|
checkpoint-4500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44dfe1f2fe3f7bfbfb5496f0dec097e3e73a56eeec5f72e03778cd2d46abb1d7
|
| 3 |
+
size 437958624
|
checkpoint-4500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64c34c7a159741764e1a21129d3927fd732827b627be6d17b44e56e365299cb
|
| 3 |
+
size 876041611
|
checkpoint-4500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63c4d5300ed120a6b97b71993bb3f880154dc2546ffb8733ba282b17ea7eb65a
|
| 3 |
+
size 14645
|
checkpoint-4500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
|
| 3 |
+
size 1383
|
checkpoint-4500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f70efa1cef98f374eb78b2a3c470222a838a11e42fe3773ba2ae2e869043e87
|
| 3 |
+
size 1465
|
checkpoint-4500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
checkpoint-4500/trainer_state.json
ADDED
|
@@ -0,0 +1,1418 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4000,
|
| 3 |
+
"best_metric": 0.9852895148669797,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes_v3/checkpoint-4000",
|
| 5 |
+
"epoch": 2.8391167192429023,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0006309148264984228,
|
| 14 |
+
"grad_norm": 3.877613067626953,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.7508903741836548,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015772870662460567,
|
| 21 |
+
"grad_norm": 3.668174982070923,
|
| 22 |
+
"learning_rate": 7.570977917981073e-07,
|
| 23 |
+
"loss": 0.7018957138061523,
|
| 24 |
+
"step": 25
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.031545741324921134,
|
| 28 |
+
"grad_norm": 3.111140489578247,
|
| 29 |
+
"learning_rate": 1.545741324921136e-06,
|
| 30 |
+
"loss": 0.680956039428711,
|
| 31 |
+
"step": 50
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0473186119873817,
|
| 35 |
+
"grad_norm": 7.506597995758057,
|
| 36 |
+
"learning_rate": 2.3343848580441643e-06,
|
| 37 |
+
"loss": 0.6145588302612305,
|
| 38 |
+
"step": 75
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06309148264984227,
|
| 42 |
+
"grad_norm": 5.972303867340088,
|
| 43 |
+
"learning_rate": 3.1230283911671926e-06,
|
| 44 |
+
"loss": 0.479757080078125,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07886435331230283,
|
| 49 |
+
"grad_norm": 5.248694896697998,
|
| 50 |
+
"learning_rate": 3.911671924290221e-06,
|
| 51 |
+
"loss": 0.40485679626464843,
|
| 52 |
+
"step": 125
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0946372239747634,
|
| 56 |
+
"grad_norm": 11.381202697753906,
|
| 57 |
+
"learning_rate": 4.70031545741325e-06,
|
| 58 |
+
"loss": 0.32495407104492186,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11041009463722397,
|
| 63 |
+
"grad_norm": 7.240411758422852,
|
| 64 |
+
"learning_rate": 5.4889589905362786e-06,
|
| 65 |
+
"loss": 0.2756643295288086,
|
| 66 |
+
"step": 175
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12618296529968454,
|
| 70 |
+
"grad_norm": 5.1150407791137695,
|
| 71 |
+
"learning_rate": 6.2776025236593065e-06,
|
| 72 |
+
"loss": 0.20428766250610353,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14195583596214512,
|
| 77 |
+
"grad_norm": 3.947627067565918,
|
| 78 |
+
"learning_rate": 7.066246056782335e-06,
|
| 79 |
+
"loss": 0.1787812042236328,
|
| 80 |
+
"step": 225
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15772870662460567,
|
| 84 |
+
"grad_norm": 4.546700954437256,
|
| 85 |
+
"learning_rate": 7.854889589905364e-06,
|
| 86 |
+
"loss": 0.13389638900756837,
|
| 87 |
+
"step": 250
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.17350157728706625,
|
| 91 |
+
"grad_norm": 6.136378765106201,
|
| 92 |
+
"learning_rate": 8.643533123028391e-06,
|
| 93 |
+
"loss": 0.12480428695678711,
|
| 94 |
+
"step": 275
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1892744479495268,
|
| 98 |
+
"grad_norm": 1.768776535987854,
|
| 99 |
+
"learning_rate": 9.43217665615142e-06,
|
| 100 |
+
"loss": 0.1406647491455078,
|
| 101 |
+
"step": 300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.20504731861198738,
|
| 105 |
+
"grad_norm": 0.5864288806915283,
|
| 106 |
+
"learning_rate": 1.022082018927445e-05,
|
| 107 |
+
"loss": 0.14702407836914064,
|
| 108 |
+
"step": 325
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.22082018927444794,
|
| 112 |
+
"grad_norm": 0.38222745060920715,
|
| 113 |
+
"learning_rate": 1.1009463722397478e-05,
|
| 114 |
+
"loss": 0.07499588966369629,
|
| 115 |
+
"step": 350
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.23659305993690852,
|
| 119 |
+
"grad_norm": 14.092840194702148,
|
| 120 |
+
"learning_rate": 1.1798107255520506e-05,
|
| 121 |
+
"loss": 0.16605567932128906,
|
| 122 |
+
"step": 375
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25236593059936907,
|
| 126 |
+
"grad_norm": 2.3975512981414795,
|
| 127 |
+
"learning_rate": 1.2586750788643533e-05,
|
| 128 |
+
"loss": 0.1523967456817627,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.26813880126182965,
|
| 133 |
+
"grad_norm": 0.3959171175956726,
|
| 134 |
+
"learning_rate": 1.3375394321766562e-05,
|
| 135 |
+
"loss": 0.10442778587341309,
|
| 136 |
+
"step": 425
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.28391167192429023,
|
| 140 |
+
"grad_norm": 3.2623980045318604,
|
| 141 |
+
"learning_rate": 1.4164037854889591e-05,
|
| 142 |
+
"loss": 0.11238637924194336,
|
| 143 |
+
"step": 450
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2996845425867508,
|
| 147 |
+
"grad_norm": 4.806061744689941,
|
| 148 |
+
"learning_rate": 1.495268138801262e-05,
|
| 149 |
+
"loss": 0.1303548812866211,
|
| 150 |
+
"step": 475
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.31545741324921134,
|
| 154 |
+
"grad_norm": 0.18862925469875336,
|
| 155 |
+
"learning_rate": 1.574132492113565e-05,
|
| 156 |
+
"loss": 0.10338631629943848,
|
| 157 |
+
"step": 500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.31545741324921134,
|
| 161 |
+
"eval_accuracy": 0.9697160883280758,
|
| 162 |
+
"eval_f1": 0.9696778269109286,
|
| 163 |
+
"eval_loss": 0.11820203810930252,
|
| 164 |
+
"eval_precision": 0.9709044908285895,
|
| 165 |
+
"eval_recall": 0.9684542586750788,
|
| 166 |
+
"eval_runtime": 61.8577,
|
| 167 |
+
"eval_samples_per_second": 51.247,
|
| 168 |
+
"eval_steps_per_second": 3.217,
|
| 169 |
+
"step": 500
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.3312302839116719,
|
| 173 |
+
"grad_norm": 0.4667949080467224,
|
| 174 |
+
"learning_rate": 1.6529968454258676e-05,
|
| 175 |
+
"loss": 0.1760481834411621,
|
| 176 |
+
"step": 525
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.3470031545741325,
|
| 180 |
+
"grad_norm": 4.3037638664245605,
|
| 181 |
+
"learning_rate": 1.7318611987381703e-05,
|
| 182 |
+
"loss": 0.17875127792358397,
|
| 183 |
+
"step": 550
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.3627760252365931,
|
| 187 |
+
"grad_norm": 2.3800172805786133,
|
| 188 |
+
"learning_rate": 1.8107255520504733e-05,
|
| 189 |
+
"loss": 0.10842983245849609,
|
| 190 |
+
"step": 575
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.3785488958990536,
|
| 194 |
+
"grad_norm": 5.045812129974365,
|
| 195 |
+
"learning_rate": 1.889589905362776e-05,
|
| 196 |
+
"loss": 0.1655238914489746,
|
| 197 |
+
"step": 600
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.3943217665615142,
|
| 201 |
+
"grad_norm": 2.556612968444824,
|
| 202 |
+
"learning_rate": 1.968454258675079e-05,
|
| 203 |
+
"loss": 0.12010204315185546,
|
| 204 |
+
"step": 625
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.41009463722397477,
|
| 208 |
+
"grad_norm": 0.5126667022705078,
|
| 209 |
+
"learning_rate": 1.999965897496297e-05,
|
| 210 |
+
"loss": 0.11391996383666993,
|
| 211 |
+
"step": 650
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.42586750788643535,
|
| 215 |
+
"grad_norm": 0.0798480287194252,
|
| 216 |
+
"learning_rate": 1.9997575017301754e-05,
|
| 217 |
+
"loss": 0.09276899337768554,
|
| 218 |
+
"step": 675
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.4416403785488959,
|
| 222 |
+
"grad_norm": 5.920562267303467,
|
| 223 |
+
"learning_rate": 1.999359695467383e-05,
|
| 224 |
+
"loss": 0.13868122100830077,
|
| 225 |
+
"step": 700
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.45741324921135645,
|
| 229 |
+
"grad_norm": 0.14535099267959595,
|
| 230 |
+
"learning_rate": 1.998772554074878e-05,
|
| 231 |
+
"loss": 0.07680845737457276,
|
| 232 |
+
"step": 725
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.47318611987381703,
|
| 236 |
+
"grad_norm": 0.07280685007572174,
|
| 237 |
+
"learning_rate": 1.9979961887903783e-05,
|
| 238 |
+
"loss": 0.09489853858947754,
|
| 239 |
+
"step": 750
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.4889589905362776,
|
| 243 |
+
"grad_norm": 0.8039259314537048,
|
| 244 |
+
"learning_rate": 1.9970307467012862e-05,
|
| 245 |
+
"loss": 0.137426700592041,
|
| 246 |
+
"step": 775
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.5047318611987381,
|
| 250 |
+
"grad_norm": 0.18804790079593658,
|
| 251 |
+
"learning_rate": 1.9958764107168226e-05,
|
| 252 |
+
"loss": 0.08404406547546386,
|
| 253 |
+
"step": 800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.5205047318611987,
|
| 257 |
+
"grad_norm": 1.2277655601501465,
|
| 258 |
+
"learning_rate": 1.994533399533373e-05,
|
| 259 |
+
"loss": 0.06400898456573487,
|
| 260 |
+
"step": 825
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.5362776025236593,
|
| 264 |
+
"grad_norm": 0.34563761949539185,
|
| 265 |
+
"learning_rate": 1.9930019675930546e-05,
|
| 266 |
+
"loss": 0.10282803535461425,
|
| 267 |
+
"step": 850
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.5520504731861199,
|
| 271 |
+
"grad_norm": 9.899245262145996,
|
| 272 |
+
"learning_rate": 1.99128240503551e-05,
|
| 273 |
+
"loss": 0.17283258438110352,
|
| 274 |
+
"step": 875
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5678233438485805,
|
| 278 |
+
"grad_norm": 2.8441741466522217,
|
| 279 |
+
"learning_rate": 1.9893750376429396e-05,
|
| 280 |
+
"loss": 0.06587859153747559,
|
| 281 |
+
"step": 900
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.583596214511041,
|
| 285 |
+
"grad_norm": 2.315617799758911,
|
| 286 |
+
"learning_rate": 1.9872802267783777e-05,
|
| 287 |
+
"loss": 0.1376850986480713,
|
| 288 |
+
"step": 925
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5993690851735016,
|
| 292 |
+
"grad_norm": 1.8745895624160767,
|
| 293 |
+
"learning_rate": 1.9849983693172324e-05,
|
| 294 |
+
"loss": 0.14075576782226562,
|
| 295 |
+
"step": 950
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.6151419558359621,
|
| 299 |
+
"grad_norm": 1.8815633058547974,
|
| 300 |
+
"learning_rate": 1.9825298975720938e-05,
|
| 301 |
+
"loss": 0.1421357250213623,
|
| 302 |
+
"step": 975
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.6309148264984227,
|
| 306 |
+
"grad_norm": 0.15319357812404633,
|
| 307 |
+
"learning_rate": 1.97987527921083e-05,
|
| 308 |
+
"loss": 0.062098536491394046,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.6309148264984227,
|
| 313 |
+
"eval_accuracy": 0.9801261829652996,
|
| 314 |
+
"eval_f1": 0.9802816901408451,
|
| 315 |
+
"eval_loss": 0.07721533626317978,
|
| 316 |
+
"eval_precision": 0.9726708074534162,
|
| 317 |
+
"eval_recall": 0.98801261829653,
|
| 318 |
+
"eval_runtime": 61.7227,
|
| 319 |
+
"eval_samples_per_second": 51.359,
|
| 320 |
+
"eval_steps_per_second": 3.224,
|
| 321 |
+
"step": 1000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6466876971608833,
|
| 325 |
+
"grad_norm": 7.767244815826416,
|
| 326 |
+
"learning_rate": 1.977035017167984e-05,
|
| 327 |
+
"loss": 0.09910112380981445,
|
| 328 |
+
"step": 1025
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.6624605678233438,
|
| 332 |
+
"grad_norm": 0.3622685968875885,
|
| 333 |
+
"learning_rate": 1.974009649549489e-05,
|
| 334 |
+
"loss": 0.11072664260864258,
|
| 335 |
+
"step": 1050
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.6782334384858044,
|
| 339 |
+
"grad_norm": 0.2787080705165863,
|
| 340 |
+
"learning_rate": 1.9707997495307232e-05,
|
| 341 |
+
"loss": 0.09833921432495117,
|
| 342 |
+
"step": 1075
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.694006309148265,
|
| 346 |
+
"grad_norm": 2.9150843620300293,
|
| 347 |
+
"learning_rate": 1.9674059252479156e-05,
|
| 348 |
+
"loss": 0.14047959327697754,
|
| 349 |
+
"step": 1100
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.7097791798107256,
|
| 353 |
+
"grad_norm": 8.6441650390625,
|
| 354 |
+
"learning_rate": 1.9638288196829303e-05,
|
| 355 |
+
"loss": 0.11829081535339356,
|
| 356 |
+
"step": 1125
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.7255520504731862,
|
| 360 |
+
"grad_norm": 17.530630111694336,
|
| 361 |
+
"learning_rate": 1.9600691105414523e-05,
|
| 362 |
+
"loss": 0.08339802742004394,
|
| 363 |
+
"step": 1150
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.7413249211356467,
|
| 367 |
+
"grad_norm": 0.10623405873775482,
|
| 368 |
+
"learning_rate": 1.9561275101245886e-05,
|
| 369 |
+
"loss": 0.09576749801635742,
|
| 370 |
+
"step": 1175
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.7570977917981072,
|
| 374 |
+
"grad_norm": 2.705754041671753,
|
| 375 |
+
"learning_rate": 1.95200476519392e-05,
|
| 376 |
+
"loss": 0.09259629249572754,
|
| 377 |
+
"step": 1200
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.7728706624605678,
|
| 381 |
+
"grad_norm": 0.5176487565040588,
|
| 382 |
+
"learning_rate": 1.9477016568300233e-05,
|
| 383 |
+
"loss": 0.1117174243927002,
|
| 384 |
+
"step": 1225
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.7886435331230284,
|
| 388 |
+
"grad_norm": 0.12397055327892303,
|
| 389 |
+
"learning_rate": 1.9432190002844868e-05,
|
| 390 |
+
"loss": 0.03809569358825684,
|
| 391 |
+
"step": 1250
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.804416403785489,
|
| 395 |
+
"grad_norm": 2.5329222679138184,
|
| 396 |
+
"learning_rate": 1.93855764482546e-05,
|
| 397 |
+
"loss": 0.08740017890930175,
|
| 398 |
+
"step": 1275
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.8201892744479495,
|
| 402 |
+
"grad_norm": 3.738490104675293,
|
| 403 |
+
"learning_rate": 1.933718473576751e-05,
|
| 404 |
+
"loss": 0.10855884552001953,
|
| 405 |
+
"step": 1300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.8359621451104101,
|
| 409 |
+
"grad_norm": 2.956233024597168,
|
| 410 |
+
"learning_rate": 1.9287024033505156e-05,
|
| 411 |
+
"loss": 0.12295740127563476,
|
| 412 |
+
"step": 1325
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.8517350157728707,
|
| 416 |
+
"grad_norm": 10.139039039611816,
|
| 417 |
+
"learning_rate": 1.9235103844735587e-05,
|
| 418 |
+
"loss": 0.048102741241455076,
|
| 419 |
+
"step": 1350
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.8675078864353313,
|
| 423 |
+
"grad_norm": 0.056244589388370514,
|
| 424 |
+
"learning_rate": 1.9181434006072906e-05,
|
| 425 |
+
"loss": 0.04849647045135498,
|
| 426 |
+
"step": 1375
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.8832807570977917,
|
| 430 |
+
"grad_norm": 0.053447045385837555,
|
| 431 |
+
"learning_rate": 1.9126024685613664e-05,
|
| 432 |
+
"loss": 0.05115017414093018,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.8990536277602523,
|
| 437 |
+
"grad_norm": 0.036403946578502655,
|
| 438 |
+
"learning_rate": 1.9068886381010424e-05,
|
| 439 |
+
"loss": 0.06353372573852539,
|
| 440 |
+
"step": 1425
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.9148264984227129,
|
| 444 |
+
"grad_norm": 0.26306140422821045,
|
| 445 |
+
"learning_rate": 1.9010029917482943e-05,
|
| 446 |
+
"loss": 0.0969051742553711,
|
| 447 |
+
"step": 1450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.9305993690851735,
|
| 451 |
+
"grad_norm": 1.315486192703247,
|
| 452 |
+
"learning_rate": 1.894946644576724e-05,
|
| 453 |
+
"loss": 0.09260586738586425,
|
| 454 |
+
"step": 1475
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.9463722397476341,
|
| 458 |
+
"grad_norm": 2.3364198207855225,
|
| 459 |
+
"learning_rate": 1.8887207440003028e-05,
|
| 460 |
+
"loss": 0.08708816528320312,
|
| 461 |
+
"step": 1500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.9463722397476341,
|
| 465 |
+
"eval_accuracy": 0.9741324921135647,
|
| 466 |
+
"eval_f1": 0.9746913580246913,
|
| 467 |
+
"eval_loss": 0.09679784625768661,
|
| 468 |
+
"eval_precision": 0.9540785498489426,
|
| 469 |
+
"eval_recall": 0.9962145110410094,
|
| 470 |
+
"eval_runtime": 61.8073,
|
| 471 |
+
"eval_samples_per_second": 51.288,
|
| 472 |
+
"eval_steps_per_second": 3.22,
|
| 473 |
+
"step": 1500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.9621451104100947,
|
| 477 |
+
"grad_norm": 0.30046138167381287,
|
| 478 |
+
"learning_rate": 1.8823264695559876e-05,
|
| 479 |
+
"loss": 0.1200937271118164,
|
| 480 |
+
"step": 1525
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.9779179810725552,
|
| 484 |
+
"grad_norm": 0.6962589025497437,
|
| 485 |
+
"learning_rate": 1.8757650326802474e-05,
|
| 486 |
+
"loss": 0.09418746948242188,
|
| 487 |
+
"step": 1550
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.9936908517350158,
|
| 491 |
+
"grad_norm": 0.043801840394735336,
|
| 492 |
+
"learning_rate": 1.8690376764795512e-05,
|
| 493 |
+
"loss": 0.06756117820739746,
|
| 494 |
+
"step": 1575
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.0094637223974763,
|
| 498 |
+
"grad_norm": 0.4039168059825897,
|
| 499 |
+
"learning_rate": 1.8621456754948524e-05,
|
| 500 |
+
"loss": 0.12740618705749512,
|
| 501 |
+
"step": 1600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.025236593059937,
|
| 505 |
+
"grad_norm": 0.14026908576488495,
|
| 506 |
+
"learning_rate": 1.8550903354601182e-05,
|
| 507 |
+
"loss": 0.03949842691421509,
|
| 508 |
+
"step": 1625
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.0410094637223974,
|
| 512 |
+
"grad_norm": 4.512003421783447,
|
| 513 |
+
"learning_rate": 1.847872993054952e-05,
|
| 514 |
+
"loss": 0.16327035903930665,
|
| 515 |
+
"step": 1650
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.0567823343848581,
|
| 519 |
+
"grad_norm": 19.02384376525879,
|
| 520 |
+
"learning_rate": 1.840495015651348e-05,
|
| 521 |
+
"loss": 0.05400698184967041,
|
| 522 |
+
"step": 1675
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.0725552050473186,
|
| 526 |
+
"grad_norm": 2.6894822120666504,
|
| 527 |
+
"learning_rate": 1.8329578010546364e-05,
|
| 528 |
+
"loss": 0.10054654121398926,
|
| 529 |
+
"step": 1700
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.088328075709779,
|
| 533 |
+
"grad_norm": 4.580667972564697,
|
| 534 |
+
"learning_rate": 1.825262777238659e-05,
|
| 535 |
+
"loss": 0.08389140129089355,
|
| 536 |
+
"step": 1725
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.1041009463722398,
|
| 540 |
+
"grad_norm": 0.07508229464292526,
|
| 541 |
+
"learning_rate": 1.817411402075229e-05,
|
| 542 |
+
"loss": 0.10561941146850586,
|
| 543 |
+
"step": 1750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.1198738170347002,
|
| 547 |
+
"grad_norm": 0.15733584761619568,
|
| 548 |
+
"learning_rate": 1.809405163057931e-05,
|
| 549 |
+
"loss": 0.0838914966583252,
|
| 550 |
+
"step": 1775
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.135646687697161,
|
| 554 |
+
"grad_norm": 3.2914106845855713,
|
| 555 |
+
"learning_rate": 1.8012455770203038e-05,
|
| 556 |
+
"loss": 0.06280827522277832,
|
| 557 |
+
"step": 1800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.1514195583596214,
|
| 561 |
+
"grad_norm": 0.14646464586257935,
|
| 562 |
+
"learning_rate": 1.7929341898484653e-05,
|
| 563 |
+
"loss": 0.08718341827392578,
|
| 564 |
+
"step": 1825
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.167192429022082,
|
| 568 |
+
"grad_norm": 1.474497675895691,
|
| 569 |
+
"learning_rate": 1.784472576188237e-05,
|
| 570 |
+
"loss": 0.07045670986175537,
|
| 571 |
+
"step": 1850
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.1829652996845426,
|
| 575 |
+
"grad_norm": 0.09543656557798386,
|
| 576 |
+
"learning_rate": 1.775862339146815e-05,
|
| 577 |
+
"loss": 0.054620800018310545,
|
| 578 |
+
"step": 1875
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.1987381703470033,
|
| 582 |
+
"grad_norm": 0.031090043485164642,
|
| 583 |
+
"learning_rate": 1.7671051099890538e-05,
|
| 584 |
+
"loss": 0.06679238319396973,
|
| 585 |
+
"step": 1900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.2145110410094637,
|
| 589 |
+
"grad_norm": 0.08794307708740234,
|
| 590 |
+
"learning_rate": 1.758202547828409e-05,
|
| 591 |
+
"loss": 0.038062283992767336,
|
| 592 |
+
"step": 1925
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.2302839116719242,
|
| 596 |
+
"grad_norm": 5.799429893493652,
|
| 597 |
+
"learning_rate": 1.74915633931261e-05,
|
| 598 |
+
"loss": 0.11424206733703614,
|
| 599 |
+
"step": 1950
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.2460567823343849,
|
| 603 |
+
"grad_norm": 0.22451771795749664,
|
| 604 |
+
"learning_rate": 1.739968198304114e-05,
|
| 605 |
+
"loss": 0.04508783340454101,
|
| 606 |
+
"step": 1975
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.2618296529968454,
|
| 610 |
+
"grad_norm": 0.07231876999139786,
|
| 611 |
+
"learning_rate": 1.7306398655554023e-05,
|
| 612 |
+
"loss": 0.04203261852264404,
|
| 613 |
+
"step": 2000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.2618296529968454,
|
| 617 |
+
"eval_accuracy": 0.9804416403785489,
|
| 618 |
+
"eval_f1": 0.980649188514357,
|
| 619 |
+
"eval_loss": 0.08355643600225449,
|
| 620 |
+
"eval_precision": 0.9703520691785052,
|
| 621 |
+
"eval_recall": 0.9911671924290221,
|
| 622 |
+
"eval_runtime": 61.6587,
|
| 623 |
+
"eval_samples_per_second": 51.412,
|
| 624 |
+
"eval_steps_per_second": 3.227,
|
| 625 |
+
"step": 2000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.277602523659306,
|
| 629 |
+
"grad_norm": 0.096407450735569,
|
| 630 |
+
"learning_rate": 1.721173108379184e-05,
|
| 631 |
+
"loss": 0.13708463668823243,
|
| 632 |
+
"step": 2025
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.2933753943217665,
|
| 636 |
+
"grad_norm": 0.1677226722240448,
|
| 637 |
+
"learning_rate": 1.711569720313568e-05,
|
| 638 |
+
"loss": 0.06809837341308594,
|
| 639 |
+
"step": 2050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.3091482649842272,
|
| 643 |
+
"grad_norm": 0.2626091241836548,
|
| 644 |
+
"learning_rate": 1.701831520782264e-05,
|
| 645 |
+
"loss": 0.08504070281982422,
|
| 646 |
+
"step": 2075
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3249211356466877,
|
| 650 |
+
"grad_norm": 2.335200786590576,
|
| 651 |
+
"learning_rate": 1.6919603547498832e-05,
|
| 652 |
+
"loss": 0.06117515563964844,
|
| 653 |
+
"step": 2100
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.3406940063091484,
|
| 657 |
+
"grad_norm": 0.04033582657575607,
|
| 658 |
+
"learning_rate": 1.6819580923723957e-05,
|
| 659 |
+
"loss": 0.058640117645263674,
|
| 660 |
+
"step": 2125
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.3564668769716088,
|
| 664 |
+
"grad_norm": 0.030620798468589783,
|
| 665 |
+
"learning_rate": 1.671826628642819e-05,
|
| 666 |
+
"loss": 0.046917934417724606,
|
| 667 |
+
"step": 2150
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.3722397476340693,
|
| 671 |
+
"grad_norm": 0.08066167682409286,
|
| 672 |
+
"learning_rate": 1.6615678830321987e-05,
|
| 673 |
+
"loss": 0.04496946811676025,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.38801261829653,
|
| 678 |
+
"grad_norm": 4.896634578704834,
|
| 679 |
+
"learning_rate": 1.651183799125952e-05,
|
| 680 |
+
"loss": 0.085579833984375,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.4037854889589905,
|
| 685 |
+
"grad_norm": 5.254743576049805,
|
| 686 |
+
"learning_rate": 1.640676344255643e-05,
|
| 687 |
+
"loss": 0.06547237396240234,
|
| 688 |
+
"step": 2225
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4195583596214512,
|
| 692 |
+
"grad_norm": 0.19317586719989777,
|
| 693 |
+
"learning_rate": 1.6300475091262615e-05,
|
| 694 |
+
"loss": 0.09360321044921875,
|
| 695 |
+
"step": 2250
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.4353312302839116,
|
| 699 |
+
"grad_norm": 2.6724467277526855,
|
| 700 |
+
"learning_rate": 1.6192993074390658e-05,
|
| 701 |
+
"loss": 0.08104397773742676,
|
| 702 |
+
"step": 2275
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.4511041009463723,
|
| 706 |
+
"grad_norm": 2.7021729946136475,
|
| 707 |
+
"learning_rate": 1.6084337755100795e-05,
|
| 708 |
+
"loss": 0.06326522827148437,
|
| 709 |
+
"step": 2300
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.4668769716088328,
|
| 713 |
+
"grad_norm": 6.612598896026611,
|
| 714 |
+
"learning_rate": 1.597452971884296e-05,
|
| 715 |
+
"loss": 0.09769298553466797,
|
| 716 |
+
"step": 2325
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.4826498422712935,
|
| 720 |
+
"grad_norm": 0.03583915904164314,
|
| 721 |
+
"learning_rate": 1.5863589769456725e-05,
|
| 722 |
+
"loss": 0.035602734088897706,
|
| 723 |
+
"step": 2350
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.498422712933754,
|
| 727 |
+
"grad_norm": 7.2366533279418945,
|
| 728 |
+
"learning_rate": 1.575153892522991e-05,
|
| 729 |
+
"loss": 0.05557059288024902,
|
| 730 |
+
"step": 2375
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5141955835962144,
|
| 734 |
+
"grad_norm": 3.2834980487823486,
|
| 735 |
+
"learning_rate": 1.5638398414916504e-05,
|
| 736 |
+
"loss": 0.059678325653076174,
|
| 737 |
+
"step": 2400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5299684542586751,
|
| 741 |
+
"grad_norm": 0.7327181100845337,
|
| 742 |
+
"learning_rate": 1.552418967371476e-05,
|
| 743 |
+
"loss": 0.10861465454101563,
|
| 744 |
+
"step": 2425
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5457413249211358,
|
| 748 |
+
"grad_norm": 7.32216215133667,
|
| 749 |
+
"learning_rate": 1.540893433920614e-05,
|
| 750 |
+
"loss": 0.062454757690429685,
|
| 751 |
+
"step": 2450
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5615141955835963,
|
| 755 |
+
"grad_norm": 0.4157012701034546,
|
| 756 |
+
"learning_rate": 1.5292654247255976e-05,
|
| 757 |
+
"loss": 0.06408432960510253,
|
| 758 |
+
"step": 2475
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.5772870662460567,
|
| 762 |
+
"grad_norm": 0.392075777053833,
|
| 763 |
+
"learning_rate": 1.5175371427876462e-05,
|
| 764 |
+
"loss": 0.06900923252105713,
|
| 765 |
+
"step": 2500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.5772870662460567,
|
| 769 |
+
"eval_accuracy": 0.9826498422712934,
|
| 770 |
+
"eval_f1": 0.9827532141737222,
|
| 771 |
+
"eval_loss": 0.06640289723873138,
|
| 772 |
+
"eval_precision": 0.976932668329177,
|
| 773 |
+
"eval_recall": 0.9886435331230284,
|
| 774 |
+
"eval_runtime": 61.7792,
|
| 775 |
+
"eval_samples_per_second": 51.312,
|
| 776 |
+
"eval_steps_per_second": 3.221,
|
| 777 |
+
"step": 2500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.5930599369085172,
|
| 781 |
+
"grad_norm": 0.26480409502983093,
|
| 782 |
+
"learning_rate": 1.5057108101052978e-05,
|
| 783 |
+
"loss": 0.05798190116882324,
|
| 784 |
+
"step": 2525
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.608832807570978,
|
| 788 |
+
"grad_norm": 0.012628897093236446,
|
| 789 |
+
"learning_rate": 1.4937886672534355e-05,
|
| 790 |
+
"loss": 0.055150442123413086,
|
| 791 |
+
"step": 2550
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.6246056782334386,
|
| 795 |
+
"grad_norm": 0.14921313524246216,
|
| 796 |
+
"learning_rate": 1.4817729729587951e-05,
|
| 797 |
+
"loss": 0.09480400085449218,
|
| 798 |
+
"step": 2575
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.640378548895899,
|
| 802 |
+
"grad_norm": 0.17945820093154907,
|
| 803 |
+
"learning_rate": 1.4696660036720366e-05,
|
| 804 |
+
"loss": 0.05116183757781982,
|
| 805 |
+
"step": 2600
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.6561514195583595,
|
| 809 |
+
"grad_norm": 8.4946928024292,
|
| 810 |
+
"learning_rate": 1.4574700531364538e-05,
|
| 811 |
+
"loss": 0.09039234161376954,
|
| 812 |
+
"step": 2625
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.6719242902208202,
|
| 816 |
+
"grad_norm": 3.404548406600952,
|
| 817 |
+
"learning_rate": 1.445187431953413e-05,
|
| 818 |
+
"loss": 0.06744499206542968,
|
| 819 |
+
"step": 2650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.687697160883281,
|
| 823 |
+
"grad_norm": 0.278082937002182,
|
| 824 |
+
"learning_rate": 1.4328204671445906e-05,
|
| 825 |
+
"loss": 0.041944122314453124,
|
| 826 |
+
"step": 2675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.7034700315457414,
|
| 830 |
+
"grad_norm": 0.44028154015541077,
|
| 831 |
+
"learning_rate": 1.4203715017111077e-05,
|
| 832 |
+
"loss": 0.04837804317474365,
|
| 833 |
+
"step": 2700
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.7192429022082019,
|
| 837 |
+
"grad_norm": 0.15768413245677948,
|
| 838 |
+
"learning_rate": 1.4078428941896308e-05,
|
| 839 |
+
"loss": 0.07240730285644531,
|
| 840 |
+
"step": 2725
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.7350157728706623,
|
| 844 |
+
"grad_norm": 0.1066892072558403,
|
| 845 |
+
"learning_rate": 1.3952370182055332e-05,
|
| 846 |
+
"loss": 0.06457790374755859,
|
| 847 |
+
"step": 2750
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.750788643533123,
|
| 851 |
+
"grad_norm": 0.10634296387434006,
|
| 852 |
+
"learning_rate": 1.3825562620231962e-05,
|
| 853 |
+
"loss": 0.045800242424011234,
|
| 854 |
+
"step": 2775
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.7665615141955837,
|
| 858 |
+
"grad_norm": 0.2797156274318695,
|
| 859 |
+
"learning_rate": 1.3698030280935365e-05,
|
| 860 |
+
"loss": 0.11092280387878418,
|
| 861 |
+
"step": 2800
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.7823343848580442,
|
| 865 |
+
"grad_norm": 0.26426321268081665,
|
| 866 |
+
"learning_rate": 1.356979732598847e-05,
|
| 867 |
+
"loss": 0.08435035705566406,
|
| 868 |
+
"step": 2825
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.7981072555205047,
|
| 872 |
+
"grad_norm": 0.0386803112924099,
|
| 873 |
+
"learning_rate": 1.3440888049950352e-05,
|
| 874 |
+
"loss": 0.03943867206573486,
|
| 875 |
+
"step": 2850
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.8138801261829653,
|
| 879 |
+
"grad_norm": 14.358352661132812,
|
| 880 |
+
"learning_rate": 1.3311326875513473e-05,
|
| 881 |
+
"loss": 0.08121340751647949,
|
| 882 |
+
"step": 2875
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.8296529968454258,
|
| 886 |
+
"grad_norm": 0.07305670529603958,
|
| 887 |
+
"learning_rate": 1.3181138348876637e-05,
|
| 888 |
+
"loss": 0.07142277717590333,
|
| 889 |
+
"step": 2900
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.8454258675078865,
|
| 893 |
+
"grad_norm": 0.3266024887561798,
|
| 894 |
+
"learning_rate": 1.305034713509457e-05,
|
| 895 |
+
"loss": 0.13324432373046874,
|
| 896 |
+
"step": 2925
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.861198738170347,
|
| 900 |
+
"grad_norm": 0.12339621037244797,
|
| 901 |
+
"learning_rate": 1.2918978013404961e-05,
|
| 902 |
+
"loss": 0.07635130405426026,
|
| 903 |
+
"step": 2950
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.8769716088328074,
|
| 907 |
+
"grad_norm": 5.140288829803467,
|
| 908 |
+
"learning_rate": 1.2787055872533867e-05,
|
| 909 |
+
"loss": 0.07312902927398682,
|
| 910 |
+
"step": 2975
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.8927444794952681,
|
| 914 |
+
"grad_norm": 0.10617490112781525,
|
| 915 |
+
"learning_rate": 1.2654605705980394e-05,
|
| 916 |
+
"loss": 0.059698452949523924,
|
| 917 |
+
"step": 3000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.8927444794952681,
|
| 921 |
+
"eval_accuracy": 0.9842271293375394,
|
| 922 |
+
"eval_f1": 0.9843456480901691,
|
| 923 |
+
"eval_loss": 0.058110740035772324,
|
| 924 |
+
"eval_precision": 0.9770043505282784,
|
| 925 |
+
"eval_recall": 0.9917981072555205,
|
| 926 |
+
"eval_runtime": 61.7383,
|
| 927 |
+
"eval_samples_per_second": 51.346,
|
| 928 |
+
"eval_steps_per_second": 3.223,
|
| 929 |
+
"step": 3000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.9085173501577288,
|
| 933 |
+
"grad_norm": 10.687918663024902,
|
| 934 |
+
"learning_rate": 1.2521652607281511e-05,
|
| 935 |
+
"loss": 0.03478496789932251,
|
| 936 |
+
"step": 3025
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.9242902208201893,
|
| 940 |
+
"grad_norm": 1.6226224899291992,
|
| 941 |
+
"learning_rate": 1.2388221765257922e-05,
|
| 942 |
+
"loss": 0.1072312068939209,
|
| 943 |
+
"step": 3050
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 1.9400630914826498,
|
| 947 |
+
"grad_norm": 0.016946569085121155,
|
| 948 |
+
"learning_rate": 1.2254338459241878e-05,
|
| 949 |
+
"loss": 0.06870736122131348,
|
| 950 |
+
"step": 3075
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.9558359621451105,
|
| 954 |
+
"grad_norm": 0.2077740579843521,
|
| 955 |
+
"learning_rate": 1.2120028054287853e-05,
|
| 956 |
+
"loss": 0.03881378889083862,
|
| 957 |
+
"step": 3100
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.971608832807571,
|
| 961 |
+
"grad_norm": 6.051036357879639,
|
| 962 |
+
"learning_rate": 1.198531599636696e-05,
|
| 963 |
+
"loss": 0.056483187675476075,
|
| 964 |
+
"step": 3125
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.9873817034700316,
|
| 968 |
+
"grad_norm": 0.1817459762096405,
|
| 969 |
+
"learning_rate": 1.1850227807546056e-05,
|
| 970 |
+
"loss": 0.058626165390014646,
|
| 971 |
+
"step": 3150
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.003154574132492,
|
| 975 |
+
"grad_norm": 5.438782215118408,
|
| 976 |
+
"learning_rate": 1.1714789081152414e-05,
|
| 977 |
+
"loss": 0.11380620002746582,
|
| 978 |
+
"step": 3175
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.0189274447949526,
|
| 982 |
+
"grad_norm": 0.15936319530010223,
|
| 983 |
+
"learning_rate": 1.1579025476924912e-05,
|
| 984 |
+
"loss": 0.08106419563293457,
|
| 985 |
+
"step": 3200
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.034700315457413,
|
| 989 |
+
"grad_norm": 0.5057512521743774,
|
| 990 |
+
"learning_rate": 1.1442962716152626e-05,
|
| 991 |
+
"loss": 0.0851284122467041,
|
| 992 |
+
"step": 3225
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.050473186119874,
|
| 996 |
+
"grad_norm": 0.15072333812713623,
|
| 997 |
+
"learning_rate": 1.1306626576801762e-05,
|
| 998 |
+
"loss": 0.023667290210723876,
|
| 999 |
+
"step": 3250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.0662460567823344,
|
| 1003 |
+
"grad_norm": 2.5816566944122314,
|
| 1004 |
+
"learning_rate": 1.1170042888631865e-05,
|
| 1005 |
+
"loss": 0.06661013126373291,
|
| 1006 |
+
"step": 3275
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.082018927444795,
|
| 1010 |
+
"grad_norm": 0.13092197477817535,
|
| 1011 |
+
"learning_rate": 1.103323752830219e-05,
|
| 1012 |
+
"loss": 0.04503594875335693,
|
| 1013 |
+
"step": 3300
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.0977917981072554,
|
| 1017 |
+
"grad_norm": 0.07164567708969116,
|
| 1018 |
+
"learning_rate": 1.0896236414469217e-05,
|
| 1019 |
+
"loss": 0.07453893184661865,
|
| 1020 |
+
"step": 3325
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.1135646687697163,
|
| 1024 |
+
"grad_norm": 0.14045630395412445,
|
| 1025 |
+
"learning_rate": 1.075906550287618e-05,
|
| 1026 |
+
"loss": 0.026728599071502684,
|
| 1027 |
+
"step": 3350
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.1293375394321767,
|
| 1031 |
+
"grad_norm": 0.5751485228538513,
|
| 1032 |
+
"learning_rate": 1.0621750781435597e-05,
|
| 1033 |
+
"loss": 0.05079428195953369,
|
| 1034 |
+
"step": 3375
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.145110410094637,
|
| 1038 |
+
"grad_norm": 0.03341040015220642,
|
| 1039 |
+
"learning_rate": 1.048431826530569e-05,
|
| 1040 |
+
"loss": 0.04085897445678711,
|
| 1041 |
+
"step": 3400
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.1608832807570977,
|
| 1045 |
+
"grad_norm": 0.10071541368961334,
|
| 1046 |
+
"learning_rate": 1.0346793991961636e-05,
|
| 1047 |
+
"loss": 0.03663242816925049,
|
| 1048 |
+
"step": 3425
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.176656151419558,
|
| 1052 |
+
"grad_norm": 0.07808862626552582,
|
| 1053 |
+
"learning_rate": 1.0209204016262617e-05,
|
| 1054 |
+
"loss": 0.06059022903442383,
|
| 1055 |
+
"step": 3450
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.192429022082019,
|
| 1059 |
+
"grad_norm": 0.06014140322804451,
|
| 1060 |
+
"learning_rate": 1.0071574405515545e-05,
|
| 1061 |
+
"loss": 0.06725450515747071,
|
| 1062 |
+
"step": 3475
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.2082018927444795,
|
| 1066 |
+
"grad_norm": 0.09061481803655624,
|
| 1067 |
+
"learning_rate": 9.93393123453644e-06,
|
| 1068 |
+
"loss": 0.05748389720916748,
|
| 1069 |
+
"step": 3500
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.2082018927444795,
|
| 1073 |
+
"eval_accuracy": 0.9845425867507887,
|
| 1074 |
+
"eval_f1": 0.9846827133479212,
|
| 1075 |
+
"eval_loss": 0.06573859602212906,
|
| 1076 |
+
"eval_precision": 0.9758364312267658,
|
| 1077 |
+
"eval_recall": 0.9936908517350158,
|
| 1078 |
+
"eval_runtime": 61.8577,
|
| 1079 |
+
"eval_samples_per_second": 51.247,
|
| 1080 |
+
"eval_steps_per_second": 3.217,
|
| 1081 |
+
"step": 3500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.22397476340694,
|
| 1085 |
+
"grad_norm": 3.2926270961761475,
|
| 1086 |
+
"learning_rate": 9.796300580710401e-06,
|
| 1087 |
+
"loss": 0.025270357131958007,
|
| 1088 |
+
"step": 3525
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.2397476340694005,
|
| 1092 |
+
"grad_norm": 0.0203135684132576,
|
| 1093 |
+
"learning_rate": 9.658708519051078e-06,
|
| 1094 |
+
"loss": 0.04098672866821289,
|
| 1095 |
+
"step": 3550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.2555205047318614,
|
| 1099 |
+
"grad_norm": 0.14016003906726837,
|
| 1100 |
+
"learning_rate": 9.521181117260576e-06,
|
| 1101 |
+
"loss": 0.06318954467773437,
|
| 1102 |
+
"step": 3575
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.271293375394322,
|
| 1106 |
+
"grad_norm": 0.07816111296415329,
|
| 1107 |
+
"learning_rate": 9.38374443079078e-06,
|
| 1108 |
+
"loss": 0.037233128547668456,
|
| 1109 |
+
"step": 3600
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.2870662460567823,
|
| 1113 |
+
"grad_norm": 6.195209503173828,
|
| 1114 |
+
"learning_rate": 9.246424497906963e-06,
|
| 1115 |
+
"loss": 0.06284498691558837,
|
| 1116 |
+
"step": 3625
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.302839116719243,
|
| 1120 |
+
"grad_norm": 0.15709596872329712,
|
| 1121 |
+
"learning_rate": 9.10924733475469e-06,
|
| 1122 |
+
"loss": 0.05046053886413574,
|
| 1123 |
+
"step": 3650
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.3186119873817033,
|
| 1127 |
+
"grad_norm": 0.19976438581943512,
|
| 1128 |
+
"learning_rate": 8.972238930430877e-06,
|
| 1129 |
+
"loss": 0.06076451301574707,
|
| 1130 |
+
"step": 3675
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.334384858044164,
|
| 1134 |
+
"grad_norm": 7.717970371246338,
|
| 1135 |
+
"learning_rate": 8.83542524205999e-06,
|
| 1136 |
+
"loss": 0.03615053176879883,
|
| 1137 |
+
"step": 3700
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.3501577287066246,
|
| 1141 |
+
"grad_norm": 0.01149569358676672,
|
| 1142 |
+
"learning_rate": 8.698832189876313e-06,
|
| 1143 |
+
"loss": 0.03155425548553467,
|
| 1144 |
+
"step": 3725
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.365930599369085,
|
| 1148 |
+
"grad_norm": 1.0143169164657593,
|
| 1149 |
+
"learning_rate": 8.562485652313168e-06,
|
| 1150 |
+
"loss": 0.06221479415893555,
|
| 1151 |
+
"step": 3750
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.3817034700315456,
|
| 1155 |
+
"grad_norm": 0.015622946433722973,
|
| 1156 |
+
"learning_rate": 8.42641146110011e-06,
|
| 1157 |
+
"loss": 0.08546380996704102,
|
| 1158 |
+
"step": 3775
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.3974763406940065,
|
| 1162 |
+
"grad_norm": 0.09111537784337997,
|
| 1163 |
+
"learning_rate": 8.290635396368916e-06,
|
| 1164 |
+
"loss": 0.04558982849121094,
|
| 1165 |
+
"step": 3800
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.413249211356467,
|
| 1169 |
+
"grad_norm": 0.0180280152708292,
|
| 1170 |
+
"learning_rate": 8.15518318176938e-06,
|
| 1171 |
+
"loss": 0.023930015563964843,
|
| 1172 |
+
"step": 3825
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.4290220820189274,
|
| 1176 |
+
"grad_norm": 0.0328361876308918,
|
| 1177 |
+
"learning_rate": 8.020080479595818e-06,
|
| 1178 |
+
"loss": 0.09591865539550781,
|
| 1179 |
+
"step": 3850
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.444794952681388,
|
| 1183 |
+
"grad_norm": 0.1508016139268875,
|
| 1184 |
+
"learning_rate": 7.885352885925139e-06,
|
| 1185 |
+
"loss": 0.05319097995758057,
|
| 1186 |
+
"step": 3875
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.4605678233438484,
|
| 1190 |
+
"grad_norm": 0.052676063030958176,
|
| 1191 |
+
"learning_rate": 7.75102592576756e-06,
|
| 1192 |
+
"loss": 0.06353373527526855,
|
| 1193 |
+
"step": 3900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.4763406940063093,
|
| 1197 |
+
"grad_norm": 0.10492721945047379,
|
| 1198 |
+
"learning_rate": 7.617125048230678e-06,
|
| 1199 |
+
"loss": 0.044883527755737306,
|
| 1200 |
+
"step": 3925
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.4921135646687698,
|
| 1204 |
+
"grad_norm": 0.761692225933075,
|
| 1205 |
+
"learning_rate": 7.483675621697999e-06,
|
| 1206 |
+
"loss": 0.07111676692962647,
|
| 1207 |
+
"step": 3950
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.5078864353312302,
|
| 1211 |
+
"grad_norm": 0.36902672052383423,
|
| 1212 |
+
"learning_rate": 7.350702929022739e-06,
|
| 1213 |
+
"loss": 0.026499390602111816,
|
| 1214 |
+
"step": 3975
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.5236593059936907,
|
| 1218 |
+
"grad_norm": 0.01817493699491024,
|
| 1219 |
+
"learning_rate": 7.2182321627378e-06,
|
| 1220 |
+
"loss": 0.025588753223419188,
|
| 1221 |
+
"step": 4000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.5236593059936907,
|
| 1225 |
+
"eval_accuracy": 0.9851735015772871,
|
| 1226 |
+
"eval_f1": 0.9852895148669797,
|
| 1227 |
+
"eval_loss": 0.06328697502613068,
|
| 1228 |
+
"eval_precision": 0.977639751552795,
|
| 1229 |
+
"eval_recall": 0.9930599369085173,
|
| 1230 |
+
"eval_runtime": 61.6662,
|
| 1231 |
+
"eval_samples_per_second": 51.406,
|
| 1232 |
+
"eval_steps_per_second": 3.227,
|
| 1233 |
+
"step": 4000
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.5394321766561516,
|
| 1237 |
+
"grad_norm": 13.168465614318848,
|
| 1238 |
+
"learning_rate": 7.0862884202829075e-06,
|
| 1239 |
+
"loss": 0.041892838478088376,
|
| 1240 |
+
"step": 4025
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 2.555205047318612,
|
| 1244 |
+
"grad_norm": 5.61896276473999,
|
| 1245 |
+
"learning_rate": 6.954896699249725e-06,
|
| 1246 |
+
"loss": 0.07447029113769531,
|
| 1247 |
+
"step": 4050
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 2.5709779179810726,
|
| 1251 |
+
"grad_norm": 0.027618594467639923,
|
| 1252 |
+
"learning_rate": 6.824081892645902e-06,
|
| 1253 |
+
"loss": 0.046046819686889645,
|
| 1254 |
+
"step": 4075
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.586750788643533,
|
| 1258 |
+
"grad_norm": 0.049199484288692474,
|
| 1259 |
+
"learning_rate": 6.693868784178934e-06,
|
| 1260 |
+
"loss": 0.045093264579772946,
|
| 1261 |
+
"step": 4100
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.6025236593059935,
|
| 1265 |
+
"grad_norm": 0.1187095046043396,
|
| 1266 |
+
"learning_rate": 6.564282043560731e-06,
|
| 1267 |
+
"loss": 0.07267766952514648,
|
| 1268 |
+
"step": 4125
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 2.6182965299684544,
|
| 1272 |
+
"grad_norm": 0.08217153698205948,
|
| 1273 |
+
"learning_rate": 6.435346221833788e-06,
|
| 1274 |
+
"loss": 0.028906166553497314,
|
| 1275 |
+
"step": 4150
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.634069400630915,
|
| 1279 |
+
"grad_norm": 0.07539000362157822,
|
| 1280 |
+
"learning_rate": 6.307085746719808e-06,
|
| 1281 |
+
"loss": 0.0493446683883667,
|
| 1282 |
+
"step": 4175
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 2.6498422712933754,
|
| 1286 |
+
"grad_norm": 0.10210157185792923,
|
| 1287 |
+
"learning_rate": 6.179524917991746e-06,
|
| 1288 |
+
"loss": 0.07266830444335938,
|
| 1289 |
+
"step": 4200
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.665615141955836,
|
| 1293 |
+
"grad_norm": 0.36085325479507446,
|
| 1294 |
+
"learning_rate": 6.05268790287003e-06,
|
| 1295 |
+
"loss": 0.048619318008422854,
|
| 1296 |
+
"step": 4225
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.6813880126182967,
|
| 1300 |
+
"grad_norm": 0.10123010724782944,
|
| 1301 |
+
"learning_rate": 5.926598731443951e-06,
|
| 1302 |
+
"loss": 0.014012279510498047,
|
| 1303 |
+
"step": 4250
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 2.697160883280757,
|
| 1307 |
+
"grad_norm": 0.03025141730904579,
|
| 1308 |
+
"learning_rate": 5.801281292118985e-06,
|
| 1309 |
+
"loss": 0.036032071113586424,
|
| 1310 |
+
"step": 4275
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 2.7129337539432177,
|
| 1314 |
+
"grad_norm": 0.07237054407596588,
|
| 1315 |
+
"learning_rate": 5.676759327090997e-06,
|
| 1316 |
+
"loss": 0.026038434505462647,
|
| 1317 |
+
"step": 4300
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 2.728706624605678,
|
| 1321 |
+
"grad_norm": 0.028059201315045357,
|
| 1322 |
+
"learning_rate": 5.553056427848136e-06,
|
| 1323 |
+
"loss": 0.023030064105987548,
|
| 1324 |
+
"step": 4325
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 2.7444794952681386,
|
| 1328 |
+
"grad_norm": 8.2833890914917,
|
| 1329 |
+
"learning_rate": 5.430196030701236e-06,
|
| 1330 |
+
"loss": 0.046771907806396486,
|
| 1331 |
+
"step": 4350
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 2.7602523659305995,
|
| 1335 |
+
"grad_norm": 0.07120615243911743,
|
| 1336 |
+
"learning_rate": 5.308201412343714e-06,
|
| 1337 |
+
"loss": 0.06948490142822265,
|
| 1338 |
+
"step": 4375
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.77602523659306,
|
| 1342 |
+
"grad_norm": 0.032343458384275436,
|
| 1343 |
+
"learning_rate": 5.187095685441592e-06,
|
| 1344 |
+
"loss": 0.06183769702911377,
|
| 1345 |
+
"step": 4400
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 2.7917981072555205,
|
| 1349 |
+
"grad_norm": 2.7497501373291016,
|
| 1350 |
+
"learning_rate": 5.066901794254707e-06,
|
| 1351 |
+
"loss": 0.06815167903900146,
|
| 1352 |
+
"step": 4425
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 2.807570977917981,
|
| 1356 |
+
"grad_norm": 6.535846710205078,
|
| 1357 |
+
"learning_rate": 4.947642510289735e-06,
|
| 1358 |
+
"loss": 0.04611932754516602,
|
| 1359 |
+
"step": 4450
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.823343848580442,
|
| 1363 |
+
"grad_norm": 19.74146842956543,
|
| 1364 |
+
"learning_rate": 4.829340427985988e-06,
|
| 1365 |
+
"loss": 0.017079710960388184,
|
| 1366 |
+
"step": 4475
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 2.8391167192429023,
|
| 1370 |
+
"grad_norm": 17.29274559020996,
|
| 1371 |
+
"learning_rate": 4.71201796043478e-06,
|
| 1372 |
+
"loss": 0.04784326076507568,
|
| 1373 |
+
"step": 4500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.8391167192429023,
|
| 1377 |
+
"eval_accuracy": 0.9823343848580441,
|
| 1378 |
+
"eval_f1": 0.9825978868862648,
|
| 1379 |
+
"eval_loss": 0.07868093252182007,
|
| 1380 |
+
"eval_precision": 0.968156766687079,
|
| 1381 |
+
"eval_recall": 0.9974763406940063,
|
| 1382 |
+
"eval_runtime": 61.7337,
|
| 1383 |
+
"eval_samples_per_second": 51.35,
|
| 1384 |
+
"eval_steps_per_second": 3.224,
|
| 1385 |
+
"step": 4500
|
| 1386 |
+
}
|
| 1387 |
+
],
|
| 1388 |
+
"logging_steps": 25,
|
| 1389 |
+
"max_steps": 6340,
|
| 1390 |
+
"num_input_tokens_seen": 0,
|
| 1391 |
+
"num_train_epochs": 4,
|
| 1392 |
+
"save_steps": 500,
|
| 1393 |
+
"stateful_callbacks": {
|
| 1394 |
+
"EarlyStoppingCallback": {
|
| 1395 |
+
"args": {
|
| 1396 |
+
"early_stopping_patience": 2,
|
| 1397 |
+
"early_stopping_threshold": 0.0
|
| 1398 |
+
},
|
| 1399 |
+
"attributes": {
|
| 1400 |
+
"early_stopping_patience_counter": 1
|
| 1401 |
+
}
|
| 1402 |
+
},
|
| 1403 |
+
"TrainerControl": {
|
| 1404 |
+
"args": {
|
| 1405 |
+
"should_epoch_stop": false,
|
| 1406 |
+
"should_evaluate": false,
|
| 1407 |
+
"should_log": false,
|
| 1408 |
+
"should_save": true,
|
| 1409 |
+
"should_training_stop": false
|
| 1410 |
+
},
|
| 1411 |
+
"attributes": {}
|
| 1412 |
+
}
|
| 1413 |
+
},
|
| 1414 |
+
"total_flos": 1.889453110751232e+16,
|
| 1415 |
+
"train_batch_size": 16,
|
| 1416 |
+
"trial_name": null,
|
| 1417 |
+
"trial_params": null
|
| 1418 |
+
}
|
checkpoint-4500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:828868299f9c3bb1e27941873d6c50b8aa4a9047279d9f7fe0a8c9ebc165d240
|
| 3 |
+
size 5201
|