Upload checkpoint and eval results at step 3500
Browse files- checkpoint-3500/config.json +37 -0
- checkpoint-3500/eval_results.json +12 -0
- checkpoint-3500/eval_step_003500.json +16 -0
- checkpoint-3500/model.safetensors +3 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/tokenizer.json +0 -0
- checkpoint-3500/tokenizer_config.json +17 -0
- checkpoint-3500/trainer_state.json +1114 -0
- checkpoint-3500/training_args.bin +3 -0
checkpoint-3500/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "benign",
|
| 16 |
+
"1": "malicious"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"is_decoder": false,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"benign": 0,
|
| 23 |
+
"malicious": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"transformers_version": "5.13.0",
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"vocab_size": 50265
|
| 37 |
+
}
|
checkpoint-3500/eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 3500,
|
| 3 |
+
"epoch": 2.2082018927444795,
|
| 4 |
+
"time": "2026-07-08 23:52:15",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.07981470227241516,
|
| 7 |
+
"eval_accuracy": 0.9820189274447949,
|
| 8 |
+
"eval_precision": 0.9769038701622972,
|
| 9 |
+
"eval_recall": 0.9873817034700315,
|
| 10 |
+
"eval_f1": 0.9821148415437716
|
| 11 |
+
}
|
| 12 |
+
}
|
checkpoint-3500/eval_step_003500.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 3500,
|
| 3 |
+
"epoch": 2.2082018927444795,
|
| 4 |
+
"time": "2026-07-08 23:52:15",
|
| 5 |
+
"metrics": {
|
| 6 |
+
"eval_loss": 0.07981470227241516,
|
| 7 |
+
"eval_accuracy": 0.9820189274447949,
|
| 8 |
+
"eval_precision": 0.9769038701622972,
|
| 9 |
+
"eval_recall": 0.9873817034700315,
|
| 10 |
+
"eval_f1": 0.9821148415437716,
|
| 11 |
+
"eval_runtime": 59.5362,
|
| 12 |
+
"eval_samples_per_second": 53.245,
|
| 13 |
+
"eval_steps_per_second": 3.343,
|
| 14 |
+
"epoch": 2.2082018927444795
|
| 15 |
+
}
|
| 16 |
+
}
|
checkpoint-3500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ef6e603e11cd1762c832332d3b03f99318d158ed5c3d9cce9247d7b2f613a5e
|
| 3 |
+
size 498612824
|
checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ef273ef171262b629827651041420b2b4528b4185f3b12f20122b7c382ab38
|
| 3 |
+
size 997348747
|
checkpoint-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c4bdd88d7e1b663ab130d70163fad141751cd6269f098a985be3ff62a84b8d
|
| 3 |
+
size 14645
|
checkpoint-3500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1b9358ab1cb9acff90f4d1d692ac08bbdb1986a66544aed9f6fe9b801b17b3
|
| 3 |
+
size 1383
|
checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4f51736128b8baf0a4929ac7db4de6c3ae88d9034a3ee3ee8962b8612a11361
|
| 3 |
+
size 1465
|
checkpoint-3500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 1000000000,
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|
checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,1114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2000,
|
| 3 |
+
"best_metric": 0.9834426741643236,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes_v3_1/checkpoint-2000",
|
| 5 |
+
"epoch": 2.2082018927444795,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 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": 2.571892738342285,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.6932622194290161,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015772870662460567,
|
| 21 |
+
"grad_norm": 2.436145544052124,
|
| 22 |
+
"learning_rate": 7.570977917981073e-07,
|
| 23 |
+
"loss": 0.7295282681783041,
|
| 24 |
+
"step": 25
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.031545741324921134,
|
| 28 |
+
"grad_norm": 5.32429838180542,
|
| 29 |
+
"learning_rate": 1.545741324921136e-06,
|
| 30 |
+
"loss": 0.7090779113769531,
|
| 31 |
+
"step": 50
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0473186119873817,
|
| 35 |
+
"grad_norm": 5.425052165985107,
|
| 36 |
+
"learning_rate": 2.3343848580441643e-06,
|
| 37 |
+
"loss": 0.6694438171386718,
|
| 38 |
+
"step": 75
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06309148264984227,
|
| 42 |
+
"grad_norm": 5.74971866607666,
|
| 43 |
+
"learning_rate": 3.1230283911671926e-06,
|
| 44 |
+
"loss": 0.6196812057495117,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07886435331230283,
|
| 49 |
+
"grad_norm": 4.759191989898682,
|
| 50 |
+
"learning_rate": 3.911671924290221e-06,
|
| 51 |
+
"loss": 0.43090095520019533,
|
| 52 |
+
"step": 125
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0946372239747634,
|
| 56 |
+
"grad_norm": 5.838165283203125,
|
| 57 |
+
"learning_rate": 4.70031545741325e-06,
|
| 58 |
+
"loss": 0.29434648513793943,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11041009463722397,
|
| 63 |
+
"grad_norm": 6.797428131103516,
|
| 64 |
+
"learning_rate": 5.4889589905362786e-06,
|
| 65 |
+
"loss": 0.1876709747314453,
|
| 66 |
+
"step": 175
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12618296529968454,
|
| 70 |
+
"grad_norm": 3.7547245025634766,
|
| 71 |
+
"learning_rate": 6.2776025236593065e-06,
|
| 72 |
+
"loss": 0.20350841522216798,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14195583596214512,
|
| 77 |
+
"grad_norm": 11.165263175964355,
|
| 78 |
+
"learning_rate": 7.066246056782335e-06,
|
| 79 |
+
"loss": 0.1446442985534668,
|
| 80 |
+
"step": 225
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15772870662460567,
|
| 84 |
+
"grad_norm": 4.109164237976074,
|
| 85 |
+
"learning_rate": 7.854889589905364e-06,
|
| 86 |
+
"loss": 0.17608392715454102,
|
| 87 |
+
"step": 250
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.17350157728706625,
|
| 91 |
+
"grad_norm": 0.37571197748184204,
|
| 92 |
+
"learning_rate": 8.643533123028391e-06,
|
| 93 |
+
"loss": 0.08311139106750488,
|
| 94 |
+
"step": 275
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1892744479495268,
|
| 98 |
+
"grad_norm": 0.21334795653820038,
|
| 99 |
+
"learning_rate": 9.43217665615142e-06,
|
| 100 |
+
"loss": 0.10653317451477051,
|
| 101 |
+
"step": 300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.20504731861198738,
|
| 105 |
+
"grad_norm": 0.21560309827327728,
|
| 106 |
+
"learning_rate": 1.022082018927445e-05,
|
| 107 |
+
"loss": 0.12078428268432617,
|
| 108 |
+
"step": 325
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.22082018927444794,
|
| 112 |
+
"grad_norm": 0.07722581177949905,
|
| 113 |
+
"learning_rate": 1.1009463722397478e-05,
|
| 114 |
+
"loss": 0.10522660255432129,
|
| 115 |
+
"step": 350
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.23659305993690852,
|
| 119 |
+
"grad_norm": 13.963035583496094,
|
| 120 |
+
"learning_rate": 1.1798107255520506e-05,
|
| 121 |
+
"loss": 0.10268622398376465,
|
| 122 |
+
"step": 375
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.25236593059936907,
|
| 126 |
+
"grad_norm": 1.7228655815124512,
|
| 127 |
+
"learning_rate": 1.2586750788643533e-05,
|
| 128 |
+
"loss": 0.1168508243560791,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.26813880126182965,
|
| 133 |
+
"grad_norm": 4.807567596435547,
|
| 134 |
+
"learning_rate": 1.3375394321766562e-05,
|
| 135 |
+
"loss": 0.1246561050415039,
|
| 136 |
+
"step": 425
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.28391167192429023,
|
| 140 |
+
"grad_norm": 0.10336830466985703,
|
| 141 |
+
"learning_rate": 1.4164037854889591e-05,
|
| 142 |
+
"loss": 0.06862223625183106,
|
| 143 |
+
"step": 450
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2996845425867508,
|
| 147 |
+
"grad_norm": 0.18726640939712524,
|
| 148 |
+
"learning_rate": 1.495268138801262e-05,
|
| 149 |
+
"loss": 0.10785533905029297,
|
| 150 |
+
"step": 475
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.31545741324921134,
|
| 154 |
+
"grad_norm": 7.849733829498291,
|
| 155 |
+
"learning_rate": 1.574132492113565e-05,
|
| 156 |
+
"loss": 0.08045989990234376,
|
| 157 |
+
"step": 500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.31545741324921134,
|
| 161 |
+
"eval_accuracy": 0.9766561514195583,
|
| 162 |
+
"eval_f1": 0.976932668329177,
|
| 163 |
+
"eval_loss": 0.11268972605466843,
|
| 164 |
+
"eval_precision": 0.9654959950708565,
|
| 165 |
+
"eval_recall": 0.9886435331230284,
|
| 166 |
+
"eval_runtime": 56.1856,
|
| 167 |
+
"eval_samples_per_second": 56.42,
|
| 168 |
+
"eval_steps_per_second": 3.542,
|
| 169 |
+
"step": 500
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.3312302839116719,
|
| 173 |
+
"grad_norm": 7.707481861114502,
|
| 174 |
+
"learning_rate": 1.6529968454258676e-05,
|
| 175 |
+
"loss": 0.12939174652099608,
|
| 176 |
+
"step": 525
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.3470031545741325,
|
| 180 |
+
"grad_norm": 1.8563039302825928,
|
| 181 |
+
"learning_rate": 1.7318611987381703e-05,
|
| 182 |
+
"loss": 0.14456929206848146,
|
| 183 |
+
"step": 550
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.3627760252365931,
|
| 187 |
+
"grad_norm": 9.819541931152344,
|
| 188 |
+
"learning_rate": 1.8107255520504733e-05,
|
| 189 |
+
"loss": 0.09543749809265137,
|
| 190 |
+
"step": 575
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.3785488958990536,
|
| 194 |
+
"grad_norm": 2.0916662216186523,
|
| 195 |
+
"learning_rate": 1.889589905362776e-05,
|
| 196 |
+
"loss": 0.11727660179138183,
|
| 197 |
+
"step": 600
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.3943217665615142,
|
| 201 |
+
"grad_norm": 4.153768539428711,
|
| 202 |
+
"learning_rate": 1.968454258675079e-05,
|
| 203 |
+
"loss": 0.1419176959991455,
|
| 204 |
+
"step": 625
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.41009463722397477,
|
| 208 |
+
"grad_norm": 0.3790145814418793,
|
| 209 |
+
"learning_rate": 1.999965897496297e-05,
|
| 210 |
+
"loss": 0.0911902904510498,
|
| 211 |
+
"step": 650
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.42586750788643535,
|
| 215 |
+
"grad_norm": 5.445947170257568,
|
| 216 |
+
"learning_rate": 1.9997575017301754e-05,
|
| 217 |
+
"loss": 0.14416172981262207,
|
| 218 |
+
"step": 675
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.4416403785488959,
|
| 222 |
+
"grad_norm": 0.33051055669784546,
|
| 223 |
+
"learning_rate": 1.999359695467383e-05,
|
| 224 |
+
"loss": 0.14161142349243164,
|
| 225 |
+
"step": 700
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.45741324921135645,
|
| 229 |
+
"grad_norm": 1.2220453023910522,
|
| 230 |
+
"learning_rate": 1.998772554074878e-05,
|
| 231 |
+
"loss": 0.13508522033691406,
|
| 232 |
+
"step": 725
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.47318611987381703,
|
| 236 |
+
"grad_norm": 16.0678768157959,
|
| 237 |
+
"learning_rate": 1.9979961887903783e-05,
|
| 238 |
+
"loss": 0.14012475967407226,
|
| 239 |
+
"step": 750
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.4889589905362776,
|
| 243 |
+
"grad_norm": 9.829991340637207,
|
| 244 |
+
"learning_rate": 1.9970307467012862e-05,
|
| 245 |
+
"loss": 0.08824824333190918,
|
| 246 |
+
"step": 775
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.5047318611987381,
|
| 250 |
+
"grad_norm": 0.48923227190971375,
|
| 251 |
+
"learning_rate": 1.9958764107168226e-05,
|
| 252 |
+
"loss": 0.14100438117980957,
|
| 253 |
+
"step": 800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.5205047318611987,
|
| 257 |
+
"grad_norm": 10.579341888427734,
|
| 258 |
+
"learning_rate": 1.994533399533373e-05,
|
| 259 |
+
"loss": 0.09922822952270507,
|
| 260 |
+
"step": 825
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.5362776025236593,
|
| 264 |
+
"grad_norm": 0.25369012355804443,
|
| 265 |
+
"learning_rate": 1.9930019675930546e-05,
|
| 266 |
+
"loss": 0.09808570861816407,
|
| 267 |
+
"step": 850
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.5520504731861199,
|
| 271 |
+
"grad_norm": 0.5847018361091614,
|
| 272 |
+
"learning_rate": 1.99128240503551e-05,
|
| 273 |
+
"loss": 0.08875894546508789,
|
| 274 |
+
"step": 875
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.5678233438485805,
|
| 278 |
+
"grad_norm": 0.4339558482170105,
|
| 279 |
+
"learning_rate": 1.9893750376429396e-05,
|
| 280 |
+
"loss": 0.11056282043457032,
|
| 281 |
+
"step": 900
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.583596214511041,
|
| 285 |
+
"grad_norm": 2.8855783939361572,
|
| 286 |
+
"learning_rate": 1.9872802267783777e-05,
|
| 287 |
+
"loss": 0.09730767250061036,
|
| 288 |
+
"step": 925
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.5993690851735016,
|
| 292 |
+
"grad_norm": 6.300772666931152,
|
| 293 |
+
"learning_rate": 1.9849983693172324e-05,
|
| 294 |
+
"loss": 0.10335501670837402,
|
| 295 |
+
"step": 950
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.6151419558359621,
|
| 299 |
+
"grad_norm": 0.1946100890636444,
|
| 300 |
+
"learning_rate": 1.9825298975720938e-05,
|
| 301 |
+
"loss": 0.06983193874359131,
|
| 302 |
+
"step": 975
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.6309148264984227,
|
| 306 |
+
"grad_norm": 0.05659753456711769,
|
| 307 |
+
"learning_rate": 1.97987527921083e-05,
|
| 308 |
+
"loss": 0.06307486057281494,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.6309148264984227,
|
| 313 |
+
"eval_accuracy": 0.9788643533123028,
|
| 314 |
+
"eval_f1": 0.9791860826343585,
|
| 315 |
+
"eval_loss": 0.10372021794319153,
|
| 316 |
+
"eval_precision": 0.9645042839657283,
|
| 317 |
+
"eval_recall": 0.9943217665615142,
|
| 318 |
+
"eval_runtime": 56.2004,
|
| 319 |
+
"eval_samples_per_second": 56.405,
|
| 320 |
+
"eval_steps_per_second": 3.541,
|
| 321 |
+
"step": 1000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6466876971608833,
|
| 325 |
+
"grad_norm": 0.0960870087146759,
|
| 326 |
+
"learning_rate": 1.977035017167984e-05,
|
| 327 |
+
"loss": 0.07478074073791503,
|
| 328 |
+
"step": 1025
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.6624605678233438,
|
| 332 |
+
"grad_norm": 2.863891124725342,
|
| 333 |
+
"learning_rate": 1.974009649549489e-05,
|
| 334 |
+
"loss": 0.07338234424591064,
|
| 335 |
+
"step": 1050
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.6782334384858044,
|
| 339 |
+
"grad_norm": 0.3583734631538391,
|
| 340 |
+
"learning_rate": 1.9707997495307232e-05,
|
| 341 |
+
"loss": 0.10608007431030274,
|
| 342 |
+
"step": 1075
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.694006309148265,
|
| 346 |
+
"grad_norm": 0.8535360097885132,
|
| 347 |
+
"learning_rate": 1.9674059252479156e-05,
|
| 348 |
+
"loss": 0.07668295860290528,
|
| 349 |
+
"step": 1100
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.7097791798107256,
|
| 353 |
+
"grad_norm": 0.4096319377422333,
|
| 354 |
+
"learning_rate": 1.9638288196829303e-05,
|
| 355 |
+
"loss": 0.07370511531829833,
|
| 356 |
+
"step": 1125
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.7255520504731862,
|
| 360 |
+
"grad_norm": 0.10992075502872467,
|
| 361 |
+
"learning_rate": 1.9600691105414523e-05,
|
| 362 |
+
"loss": 0.04484860897064209,
|
| 363 |
+
"step": 1150
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.7413249211356467,
|
| 367 |
+
"grad_norm": 4.087841510772705,
|
| 368 |
+
"learning_rate": 1.9561275101245886e-05,
|
| 369 |
+
"loss": 0.15258366584777833,
|
| 370 |
+
"step": 1175
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.7570977917981072,
|
| 374 |
+
"grad_norm": 2.7859838008880615,
|
| 375 |
+
"learning_rate": 1.95200476519392e-05,
|
| 376 |
+
"loss": 0.12657273292541504,
|
| 377 |
+
"step": 1200
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.7728706624605678,
|
| 381 |
+
"grad_norm": 0.08890348672866821,
|
| 382 |
+
"learning_rate": 1.9477016568300233e-05,
|
| 383 |
+
"loss": 0.058558349609375,
|
| 384 |
+
"step": 1225
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.7886435331230284,
|
| 388 |
+
"grad_norm": 2.4231088161468506,
|
| 389 |
+
"learning_rate": 1.9432190002844868e-05,
|
| 390 |
+
"loss": 0.08944664001464844,
|
| 391 |
+
"step": 1250
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.804416403785489,
|
| 395 |
+
"grad_norm": 0.15423132479190826,
|
| 396 |
+
"learning_rate": 1.93855764482546e-05,
|
| 397 |
+
"loss": 0.07989122390747071,
|
| 398 |
+
"step": 1275
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.8201892744479495,
|
| 402 |
+
"grad_norm": 0.1543116569519043,
|
| 403 |
+
"learning_rate": 1.933718473576751e-05,
|
| 404 |
+
"loss": 0.0904345703125,
|
| 405 |
+
"step": 1300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.8359621451104101,
|
| 409 |
+
"grad_norm": 0.2740912139415741,
|
| 410 |
+
"learning_rate": 1.9287024033505156e-05,
|
| 411 |
+
"loss": 0.08953811645507813,
|
| 412 |
+
"step": 1325
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.8517350157728707,
|
| 416 |
+
"grad_norm": 0.06053502485156059,
|
| 417 |
+
"learning_rate": 1.9235103844735587e-05,
|
| 418 |
+
"loss": 0.09112126350402833,
|
| 419 |
+
"step": 1350
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.8675078864353313,
|
| 423 |
+
"grad_norm": 3.397080898284912,
|
| 424 |
+
"learning_rate": 1.9181434006072906e-05,
|
| 425 |
+
"loss": 0.10066482543945313,
|
| 426 |
+
"step": 1375
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.8832807570977917,
|
| 430 |
+
"grad_norm": 0.24578048288822174,
|
| 431 |
+
"learning_rate": 1.9126024685613664e-05,
|
| 432 |
+
"loss": 0.06111194610595703,
|
| 433 |
+
"step": 1400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.8990536277602523,
|
| 437 |
+
"grad_norm": 0.09262054413557053,
|
| 438 |
+
"learning_rate": 1.9068886381010424e-05,
|
| 439 |
+
"loss": 0.07008316040039063,
|
| 440 |
+
"step": 1425
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.9148264984227129,
|
| 444 |
+
"grad_norm": 1.9535330533981323,
|
| 445 |
+
"learning_rate": 1.9010029917482943e-05,
|
| 446 |
+
"loss": 0.14111000061035156,
|
| 447 |
+
"step": 1450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.9305993690851735,
|
| 451 |
+
"grad_norm": 0.1983080357313156,
|
| 452 |
+
"learning_rate": 1.894946644576724e-05,
|
| 453 |
+
"loss": 0.07531814575195313,
|
| 454 |
+
"step": 1475
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.9463722397476341,
|
| 458 |
+
"grad_norm": 0.09421352297067642,
|
| 459 |
+
"learning_rate": 1.8887207440003028e-05,
|
| 460 |
+
"loss": 0.09356441497802734,
|
| 461 |
+
"step": 1500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.9463722397476341,
|
| 465 |
+
"eval_accuracy": 0.9782334384858045,
|
| 466 |
+
"eval_f1": 0.9782677165354331,
|
| 467 |
+
"eval_loss": 0.07328534126281738,
|
| 468 |
+
"eval_precision": 0.9767295597484277,
|
| 469 |
+
"eval_recall": 0.9798107255520505,
|
| 470 |
+
"eval_runtime": 55.7759,
|
| 471 |
+
"eval_samples_per_second": 56.835,
|
| 472 |
+
"eval_steps_per_second": 3.568,
|
| 473 |
+
"step": 1500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.9621451104100947,
|
| 477 |
+
"grad_norm": 0.23979413509368896,
|
| 478 |
+
"learning_rate": 1.8823264695559876e-05,
|
| 479 |
+
"loss": 0.04988880157470703,
|
| 480 |
+
"step": 1525
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.9779179810725552,
|
| 484 |
+
"grad_norm": 0.1378251314163208,
|
| 485 |
+
"learning_rate": 1.8757650326802474e-05,
|
| 486 |
+
"loss": 0.03976966857910156,
|
| 487 |
+
"step": 1550
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.9936908517350158,
|
| 491 |
+
"grad_norm": 0.06288843601942062,
|
| 492 |
+
"learning_rate": 1.8690376764795512e-05,
|
| 493 |
+
"loss": 0.08686065673828125,
|
| 494 |
+
"step": 1575
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.0094637223974763,
|
| 498 |
+
"grad_norm": 5.365837097167969,
|
| 499 |
+
"learning_rate": 1.8621456754948524e-05,
|
| 500 |
+
"loss": 0.05250164031982422,
|
| 501 |
+
"step": 1600
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.025236593059937,
|
| 505 |
+
"grad_norm": 0.18591798841953278,
|
| 506 |
+
"learning_rate": 1.8550903354601182e-05,
|
| 507 |
+
"loss": 0.05328141212463379,
|
| 508 |
+
"step": 1625
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.0410094637223974,
|
| 512 |
+
"grad_norm": 0.14107061922550201,
|
| 513 |
+
"learning_rate": 1.847872993054952e-05,
|
| 514 |
+
"loss": 0.0559916353225708,
|
| 515 |
+
"step": 1650
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.0567823343848581,
|
| 519 |
+
"grad_norm": 6.363674163818359,
|
| 520 |
+
"learning_rate": 1.840495015651348e-05,
|
| 521 |
+
"loss": 0.1134580421447754,
|
| 522 |
+
"step": 1675
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.0725552050473186,
|
| 526 |
+
"grad_norm": 0.072722889482975,
|
| 527 |
+
"learning_rate": 1.8329578010546364e-05,
|
| 528 |
+
"loss": 0.04161137580871582,
|
| 529 |
+
"step": 1700
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.088328075709779,
|
| 533 |
+
"grad_norm": 7.499703884124756,
|
| 534 |
+
"learning_rate": 1.825262777238659e-05,
|
| 535 |
+
"loss": 0.07552608013153077,
|
| 536 |
+
"step": 1725
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.1041009463722398,
|
| 540 |
+
"grad_norm": 0.034939683973789215,
|
| 541 |
+
"learning_rate": 1.817411402075229e-05,
|
| 542 |
+
"loss": 0.07142114162445068,
|
| 543 |
+
"step": 1750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.1198738170347002,
|
| 547 |
+
"grad_norm": 0.19647593796253204,
|
| 548 |
+
"learning_rate": 1.809405163057931e-05,
|
| 549 |
+
"loss": 0.09205500602722168,
|
| 550 |
+
"step": 1775
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.135646687697161,
|
| 554 |
+
"grad_norm": 0.1461659073829651,
|
| 555 |
+
"learning_rate": 1.8012455770203038e-05,
|
| 556 |
+
"loss": 0.06862086296081543,
|
| 557 |
+
"step": 1800
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.1514195583596214,
|
| 561 |
+
"grad_norm": 0.09000778943300247,
|
| 562 |
+
"learning_rate": 1.7929341898484653e-05,
|
| 563 |
+
"loss": 0.03869293212890625,
|
| 564 |
+
"step": 1825
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.167192429022082,
|
| 568 |
+
"grad_norm": 3.4395689964294434,
|
| 569 |
+
"learning_rate": 1.784472576188237e-05,
|
| 570 |
+
"loss": 0.10784174919128418,
|
| 571 |
+
"step": 1850
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.1829652996845426,
|
| 575 |
+
"grad_norm": 6.185035228729248,
|
| 576 |
+
"learning_rate": 1.775862339146815e-05,
|
| 577 |
+
"loss": 0.08741586685180663,
|
| 578 |
+
"step": 1875
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.1987381703470033,
|
| 582 |
+
"grad_norm": 0.03306306153535843,
|
| 583 |
+
"learning_rate": 1.7671051099890538e-05,
|
| 584 |
+
"loss": 0.03821196556091309,
|
| 585 |
+
"step": 1900
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.2145110410094637,
|
| 589 |
+
"grad_norm": 0.11795313656330109,
|
| 590 |
+
"learning_rate": 1.758202547828409e-05,
|
| 591 |
+
"loss": 0.05004812240600586,
|
| 592 |
+
"step": 1925
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.2302839116719242,
|
| 596 |
+
"grad_norm": 0.27102428674697876,
|
| 597 |
+
"learning_rate": 1.74915633931261e-05,
|
| 598 |
+
"loss": 0.09024031639099121,
|
| 599 |
+
"step": 1950
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.2460567823343849,
|
| 603 |
+
"grad_norm": 0.1362110674381256,
|
| 604 |
+
"learning_rate": 1.739968198304114e-05,
|
| 605 |
+
"loss": 0.0506083345413208,
|
| 606 |
+
"step": 1975
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.2618296529968454,
|
| 610 |
+
"grad_norm": 0.05871753394603729,
|
| 611 |
+
"learning_rate": 1.7306398655554023e-05,
|
| 612 |
+
"loss": 0.12149024963378906,
|
| 613 |
+
"step": 2000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.2618296529968454,
|
| 617 |
+
"eval_accuracy": 0.9832807570977918,
|
| 618 |
+
"eval_f1": 0.9834426741643236,
|
| 619 |
+
"eval_loss": 0.0678657591342926,
|
| 620 |
+
"eval_precision": 0.974009900990099,
|
| 621 |
+
"eval_recall": 0.9930599369085173,
|
| 622 |
+
"eval_runtime": 56.2139,
|
| 623 |
+
"eval_samples_per_second": 56.392,
|
| 624 |
+
"eval_steps_per_second": 3.54,
|
| 625 |
+
"step": 2000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.277602523659306,
|
| 629 |
+
"grad_norm": 14.435188293457031,
|
| 630 |
+
"learning_rate": 1.721173108379184e-05,
|
| 631 |
+
"loss": 0.09227321624755859,
|
| 632 |
+
"step": 2025
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.2933753943217665,
|
| 636 |
+
"grad_norm": 0.14022010564804077,
|
| 637 |
+
"learning_rate": 1.711569720313568e-05,
|
| 638 |
+
"loss": 0.07053103446960449,
|
| 639 |
+
"step": 2050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.3091482649842272,
|
| 643 |
+
"grad_norm": 0.17620061337947845,
|
| 644 |
+
"learning_rate": 1.701831520782264e-05,
|
| 645 |
+
"loss": 0.07794711112976074,
|
| 646 |
+
"step": 2075
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3249211356466877,
|
| 650 |
+
"grad_norm": 6.461155891418457,
|
| 651 |
+
"learning_rate": 1.6919603547498832e-05,
|
| 652 |
+
"loss": 0.05158097267150879,
|
| 653 |
+
"step": 2100
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.3406940063091484,
|
| 657 |
+
"grad_norm": 8.352033615112305,
|
| 658 |
+
"learning_rate": 1.6819580923723957e-05,
|
| 659 |
+
"loss": 0.04181491374969482,
|
| 660 |
+
"step": 2125
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.3564668769716088,
|
| 664 |
+
"grad_norm": 0.052411582320928574,
|
| 665 |
+
"learning_rate": 1.671826628642819e-05,
|
| 666 |
+
"loss": 0.049018054008483886,
|
| 667 |
+
"step": 2150
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.3722397476340693,
|
| 671 |
+
"grad_norm": 0.0428645983338356,
|
| 672 |
+
"learning_rate": 1.6615678830321987e-05,
|
| 673 |
+
"loss": 0.06123344898223877,
|
| 674 |
+
"step": 2175
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.38801261829653,
|
| 678 |
+
"grad_norm": 0.12796339392662048,
|
| 679 |
+
"learning_rate": 1.651183799125952e-05,
|
| 680 |
+
"loss": 0.06224549293518066,
|
| 681 |
+
"step": 2200
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.4037854889589905,
|
| 685 |
+
"grad_norm": 0.3184094727039337,
|
| 686 |
+
"learning_rate": 1.640676344255643e-05,
|
| 687 |
+
"loss": 0.04998977661132813,
|
| 688 |
+
"step": 2225
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4195583596214512,
|
| 692 |
+
"grad_norm": 0.08195166289806366,
|
| 693 |
+
"learning_rate": 1.6300475091262615e-05,
|
| 694 |
+
"loss": 0.07321974277496338,
|
| 695 |
+
"step": 2250
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.4353312302839116,
|
| 699 |
+
"grad_norm": 3.03761625289917,
|
| 700 |
+
"learning_rate": 1.6192993074390658e-05,
|
| 701 |
+
"loss": 0.08428791999816894,
|
| 702 |
+
"step": 2275
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.4511041009463723,
|
| 706 |
+
"grad_norm": 0.41116461157798767,
|
| 707 |
+
"learning_rate": 1.6084337755100795e-05,
|
| 708 |
+
"loss": 0.06157721996307373,
|
| 709 |
+
"step": 2300
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.4668769716088328,
|
| 713 |
+
"grad_norm": 4.645056247711182,
|
| 714 |
+
"learning_rate": 1.597452971884296e-05,
|
| 715 |
+
"loss": 0.09335646629333497,
|
| 716 |
+
"step": 2325
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.4826498422712935,
|
| 720 |
+
"grad_norm": 0.07679587602615356,
|
| 721 |
+
"learning_rate": 1.5863589769456725e-05,
|
| 722 |
+
"loss": 0.035682902336120606,
|
| 723 |
+
"step": 2350
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.498422712933754,
|
| 727 |
+
"grad_norm": 16.212730407714844,
|
| 728 |
+
"learning_rate": 1.575153892522991e-05,
|
| 729 |
+
"loss": 0.08860483169555664,
|
| 730 |
+
"step": 2375
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5141955835962144,
|
| 734 |
+
"grad_norm": 0.035901762545108795,
|
| 735 |
+
"learning_rate": 1.5638398414916504e-05,
|
| 736 |
+
"loss": 0.06739212989807129,
|
| 737 |
+
"step": 2400
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5299684542586751,
|
| 741 |
+
"grad_norm": 14.2339448928833,
|
| 742 |
+
"learning_rate": 1.552418967371476e-05,
|
| 743 |
+
"loss": 0.03637696027755737,
|
| 744 |
+
"step": 2425
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5457413249211358,
|
| 748 |
+
"grad_norm": 0.021874595433473587,
|
| 749 |
+
"learning_rate": 1.540893433920614e-05,
|
| 750 |
+
"loss": 0.03717231750488281,
|
| 751 |
+
"step": 2450
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5615141955835963,
|
| 755 |
+
"grad_norm": 0.048296067863702774,
|
| 756 |
+
"learning_rate": 1.5292654247255976e-05,
|
| 757 |
+
"loss": 0.02598174810409546,
|
| 758 |
+
"step": 2475
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.5772870662460567,
|
| 762 |
+
"grad_norm": 9.524810791015625,
|
| 763 |
+
"learning_rate": 1.5175371427876462e-05,
|
| 764 |
+
"loss": 0.06133613586425781,
|
| 765 |
+
"step": 2500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.5772870662460567,
|
| 769 |
+
"eval_accuracy": 0.9826498422712934,
|
| 770 |
+
"eval_f1": 0.9827963715983735,
|
| 771 |
+
"eval_loss": 0.07992753386497498,
|
| 772 |
+
"eval_precision": 0.9745657568238213,
|
| 773 |
+
"eval_recall": 0.9911671924290221,
|
| 774 |
+
"eval_runtime": 55.9735,
|
| 775 |
+
"eval_samples_per_second": 56.634,
|
| 776 |
+
"eval_steps_per_second": 3.555,
|
| 777 |
+
"step": 2500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.5930599369085172,
|
| 781 |
+
"grad_norm": 0.015798641368746758,
|
| 782 |
+
"learning_rate": 1.5057108101052978e-05,
|
| 783 |
+
"loss": 0.05316779613494873,
|
| 784 |
+
"step": 2525
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.608832807570978,
|
| 788 |
+
"grad_norm": 1.9981679916381836,
|
| 789 |
+
"learning_rate": 1.4937886672534355e-05,
|
| 790 |
+
"loss": 0.04096637725830078,
|
| 791 |
+
"step": 2550
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.6246056782334386,
|
| 795 |
+
"grad_norm": 14.948141098022461,
|
| 796 |
+
"learning_rate": 1.4817729729587951e-05,
|
| 797 |
+
"loss": 0.11973735809326172,
|
| 798 |
+
"step": 2575
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.640378548895899,
|
| 802 |
+
"grad_norm": 10.006237030029297,
|
| 803 |
+
"learning_rate": 1.4696660036720366e-05,
|
| 804 |
+
"loss": 0.07024142742156983,
|
| 805 |
+
"step": 2600
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.6561514195583595,
|
| 809 |
+
"grad_norm": 2.659205436706543,
|
| 810 |
+
"learning_rate": 1.4574700531364538e-05,
|
| 811 |
+
"loss": 0.05831857681274414,
|
| 812 |
+
"step": 2625
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.6719242902208202,
|
| 816 |
+
"grad_norm": 0.023404600098729134,
|
| 817 |
+
"learning_rate": 1.445187431953413e-05,
|
| 818 |
+
"loss": 0.012276544570922851,
|
| 819 |
+
"step": 2650
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.687697160883281,
|
| 823 |
+
"grad_norm": 0.05033299699425697,
|
| 824 |
+
"learning_rate": 1.4328204671445906e-05,
|
| 825 |
+
"loss": 0.04452509880065918,
|
| 826 |
+
"step": 2675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.7034700315457414,
|
| 830 |
+
"grad_norm": 0.008091382682323456,
|
| 831 |
+
"learning_rate": 1.4203715017111077e-05,
|
| 832 |
+
"loss": 0.03908012628555298,
|
| 833 |
+
"step": 2700
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.7192429022082019,
|
| 837 |
+
"grad_norm": 0.8330066800117493,
|
| 838 |
+
"learning_rate": 1.4078428941896308e-05,
|
| 839 |
+
"loss": 0.07871007442474365,
|
| 840 |
+
"step": 2725
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.7350157728706623,
|
| 844 |
+
"grad_norm": 0.20014899969100952,
|
| 845 |
+
"learning_rate": 1.3952370182055332e-05,
|
| 846 |
+
"loss": 0.05369951725006104,
|
| 847 |
+
"step": 2750
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.750788643533123,
|
| 851 |
+
"grad_norm": 5.281189918518066,
|
| 852 |
+
"learning_rate": 1.3825562620231962e-05,
|
| 853 |
+
"loss": 0.06861288547515869,
|
| 854 |
+
"step": 2775
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.7665615141955837,
|
| 858 |
+
"grad_norm": 13.993217468261719,
|
| 859 |
+
"learning_rate": 1.3698030280935365e-05,
|
| 860 |
+
"loss": 0.0692290210723877,
|
| 861 |
+
"step": 2800
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.7823343848580442,
|
| 865 |
+
"grad_norm": 0.19194826483726501,
|
| 866 |
+
"learning_rate": 1.356979732598847e-05,
|
| 867 |
+
"loss": 0.0943898868560791,
|
| 868 |
+
"step": 2825
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.7981072555205047,
|
| 872 |
+
"grad_norm": 0.24530774354934692,
|
| 873 |
+
"learning_rate": 1.3440888049950352e-05,
|
| 874 |
+
"loss": 0.05583916664123535,
|
| 875 |
+
"step": 2850
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.8138801261829653,
|
| 879 |
+
"grad_norm": 23.30782699584961,
|
| 880 |
+
"learning_rate": 1.3311326875513473e-05,
|
| 881 |
+
"loss": 0.06628149509429931,
|
| 882 |
+
"step": 2875
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.8296529968454258,
|
| 886 |
+
"grad_norm": 5.725240230560303,
|
| 887 |
+
"learning_rate": 1.3181138348876637e-05,
|
| 888 |
+
"loss": 0.08753268241882324,
|
| 889 |
+
"step": 2900
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.8454258675078865,
|
| 893 |
+
"grad_norm": 3.2451798915863037,
|
| 894 |
+
"learning_rate": 1.305034713509457e-05,
|
| 895 |
+
"loss": 0.04335375308990479,
|
| 896 |
+
"step": 2925
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.861198738170347,
|
| 900 |
+
"grad_norm": 8.147355079650879,
|
| 901 |
+
"learning_rate": 1.2918978013404961e-05,
|
| 902 |
+
"loss": 0.08735511779785156,
|
| 903 |
+
"step": 2950
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.8769716088328074,
|
| 907 |
+
"grad_norm": 0.31234487891197205,
|
| 908 |
+
"learning_rate": 1.2787055872533867e-05,
|
| 909 |
+
"loss": 0.04033580780029297,
|
| 910 |
+
"step": 2975
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.8927444794952681,
|
| 914 |
+
"grad_norm": 2.878502368927002,
|
| 915 |
+
"learning_rate": 1.2654605705980394e-05,
|
| 916 |
+
"loss": 0.07418310165405273,
|
| 917 |
+
"step": 3000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.8927444794952681,
|
| 921 |
+
"eval_accuracy": 0.9823343848580441,
|
| 922 |
+
"eval_f1": 0.982532751091703,
|
| 923 |
+
"eval_loss": 0.09431762993335724,
|
| 924 |
+
"eval_precision": 0.9716224552745218,
|
| 925 |
+
"eval_recall": 0.9936908517350158,
|
| 926 |
+
"eval_runtime": 55.9884,
|
| 927 |
+
"eval_samples_per_second": 56.619,
|
| 928 |
+
"eval_steps_per_second": 3.554,
|
| 929 |
+
"step": 3000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.9085173501577288,
|
| 933 |
+
"grad_norm": 32.33955001831055,
|
| 934 |
+
"learning_rate": 1.2521652607281511e-05,
|
| 935 |
+
"loss": 0.05197489261627197,
|
| 936 |
+
"step": 3025
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.9242902208201893,
|
| 940 |
+
"grad_norm": 5.458424091339111,
|
| 941 |
+
"learning_rate": 1.2388221765257922e-05,
|
| 942 |
+
"loss": 0.08039166450500489,
|
| 943 |
+
"step": 3050
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 1.9400630914826498,
|
| 947 |
+
"grad_norm": 0.032594233751297,
|
| 948 |
+
"learning_rate": 1.2254338459241878e-05,
|
| 949 |
+
"loss": 0.03573692560195923,
|
| 950 |
+
"step": 3075
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.9558359621451105,
|
| 954 |
+
"grad_norm": 13.031876564025879,
|
| 955 |
+
"learning_rate": 1.2120028054287853e-05,
|
| 956 |
+
"loss": 0.07872509479522705,
|
| 957 |
+
"step": 3100
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.971608832807571,
|
| 961 |
+
"grad_norm": 3.845304012298584,
|
| 962 |
+
"learning_rate": 1.198531599636696e-05,
|
| 963 |
+
"loss": 0.07527520656585693,
|
| 964 |
+
"step": 3125
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.9873817034700316,
|
| 968 |
+
"grad_norm": 0.061868082731962204,
|
| 969 |
+
"learning_rate": 1.1850227807546056e-05,
|
| 970 |
+
"loss": 0.08369281768798828,
|
| 971 |
+
"step": 3150
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.003154574132492,
|
| 975 |
+
"grad_norm": 0.2873733639717102,
|
| 976 |
+
"learning_rate": 1.1714789081152414e-05,
|
| 977 |
+
"loss": 0.06914769172668457,
|
| 978 |
+
"step": 3175
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.0189274447949526,
|
| 982 |
+
"grad_norm": 0.2408512681722641,
|
| 983 |
+
"learning_rate": 1.1579025476924912e-05,
|
| 984 |
+
"loss": 0.04823586940765381,
|
| 985 |
+
"step": 3200
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.034700315457413,
|
| 989 |
+
"grad_norm": 0.06181686371564865,
|
| 990 |
+
"learning_rate": 1.1442962716152626e-05,
|
| 991 |
+
"loss": 0.052933053970336916,
|
| 992 |
+
"step": 3225
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.050473186119874,
|
| 996 |
+
"grad_norm": 0.23159997165203094,
|
| 997 |
+
"learning_rate": 1.1306626576801762e-05,
|
| 998 |
+
"loss": 0.042997312545776364,
|
| 999 |
+
"step": 3250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.0662460567823344,
|
| 1003 |
+
"grad_norm": 0.11183202266693115,
|
| 1004 |
+
"learning_rate": 1.1170042888631865e-05,
|
| 1005 |
+
"loss": 0.030156188011169434,
|
| 1006 |
+
"step": 3275
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.082018927444795,
|
| 1010 |
+
"grad_norm": 0.020436838269233704,
|
| 1011 |
+
"learning_rate": 1.103323752830219e-05,
|
| 1012 |
+
"loss": 0.06210995674133301,
|
| 1013 |
+
"step": 3300
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.0977917981072554,
|
| 1017 |
+
"grad_norm": 0.09942680597305298,
|
| 1018 |
+
"learning_rate": 1.0896236414469217e-05,
|
| 1019 |
+
"loss": 0.06024267673492432,
|
| 1020 |
+
"step": 3325
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.1135646687697163,
|
| 1024 |
+
"grad_norm": 0.06319867074489594,
|
| 1025 |
+
"learning_rate": 1.075906550287618e-05,
|
| 1026 |
+
"loss": 0.09793594360351562,
|
| 1027 |
+
"step": 3350
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.1293375394321767,
|
| 1031 |
+
"grad_norm": 0.14570729434490204,
|
| 1032 |
+
"learning_rate": 1.0621750781435597e-05,
|
| 1033 |
+
"loss": 0.039036962985992435,
|
| 1034 |
+
"step": 3375
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.145110410094637,
|
| 1038 |
+
"grad_norm": 30.197425842285156,
|
| 1039 |
+
"learning_rate": 1.048431826530569e-05,
|
| 1040 |
+
"loss": 0.024112117290496827,
|
| 1041 |
+
"step": 3400
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.1608832807570977,
|
| 1045 |
+
"grad_norm": 0.0806874930858612,
|
| 1046 |
+
"learning_rate": 1.0346793991961636e-05,
|
| 1047 |
+
"loss": 0.09378963470458984,
|
| 1048 |
+
"step": 3425
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.176656151419558,
|
| 1052 |
+
"grad_norm": 0.041268810629844666,
|
| 1053 |
+
"learning_rate": 1.0209204016262617e-05,
|
| 1054 |
+
"loss": 0.028721425533294678,
|
| 1055 |
+
"step": 3450
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.192429022082019,
|
| 1059 |
+
"grad_norm": 0.027517961338162422,
|
| 1060 |
+
"learning_rate": 1.0071574405515545e-05,
|
| 1061 |
+
"loss": 0.019525480270385743,
|
| 1062 |
+
"step": 3475
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.2082018927444795,
|
| 1066 |
+
"grad_norm": 0.06598785519599915,
|
| 1067 |
+
"learning_rate": 9.93393123453644e-06,
|
| 1068 |
+
"loss": 0.07426059722900391,
|
| 1069 |
+
"step": 3500
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.2082018927444795,
|
| 1073 |
+
"eval_accuracy": 0.9820189274447949,
|
| 1074 |
+
"eval_f1": 0.9821148415437716,
|
| 1075 |
+
"eval_loss": 0.07981470227241516,
|
| 1076 |
+
"eval_precision": 0.9769038701622972,
|
| 1077 |
+
"eval_recall": 0.9873817034700315,
|
| 1078 |
+
"eval_runtime": 59.5362,
|
| 1079 |
+
"eval_samples_per_second": 53.245,
|
| 1080 |
+
"eval_steps_per_second": 3.343,
|
| 1081 |
+
"step": 3500
|
| 1082 |
+
}
|
| 1083 |
+
],
|
| 1084 |
+
"logging_steps": 25,
|
| 1085 |
+
"max_steps": 6340,
|
| 1086 |
+
"num_input_tokens_seen": 0,
|
| 1087 |
+
"num_train_epochs": 4,
|
| 1088 |
+
"save_steps": 500,
|
| 1089 |
+
"stateful_callbacks": {
|
| 1090 |
+
"EarlyStoppingCallback": {
|
| 1091 |
+
"args": {
|
| 1092 |
+
"early_stopping_patience": 2,
|
| 1093 |
+
"early_stopping_threshold": 0.0
|
| 1094 |
+
},
|
| 1095 |
+
"attributes": {
|
| 1096 |
+
"early_stopping_patience_counter": 1
|
| 1097 |
+
}
|
| 1098 |
+
},
|
| 1099 |
+
"TrainerControl": {
|
| 1100 |
+
"args": {
|
| 1101 |
+
"should_epoch_stop": false,
|
| 1102 |
+
"should_evaluate": false,
|
| 1103 |
+
"should_log": false,
|
| 1104 |
+
"should_save": true,
|
| 1105 |
+
"should_training_stop": false
|
| 1106 |
+
},
|
| 1107 |
+
"attributes": {}
|
| 1108 |
+
}
|
| 1109 |
+
},
|
| 1110 |
+
"total_flos": 1.466850711408384e+16,
|
| 1111 |
+
"train_batch_size": 16,
|
| 1112 |
+
"trial_name": null,
|
| 1113 |
+
"trial_params": null
|
| 1114 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc2d91b4b45762cdc84d5992a9a91e97b307eafcda062ebc5e2bf98dcfb03854
|
| 3 |
+
size 5201
|