Upload Egide toxicity model (fine-tuned xlm-roberta-base)
Browse files- checkpoint-2541/config.json +47 -0
- checkpoint-2541/model.safetensors +3 -0
- checkpoint-2541/optimizer.pt +3 -0
- checkpoint-2541/rng_state.pth +3 -0
- checkpoint-2541/scheduler.pt +3 -0
- checkpoint-2541/trainer_state.json +1988 -0
- checkpoint-2541/training_args.bin +3 -0
- checkpoint-2772/config.json +47 -0
- checkpoint-2772/model.safetensors +3 -0
- checkpoint-2772/optimizer.pt +3 -0
- checkpoint-2772/rng_state.pth +3 -0
- checkpoint-2772/scheduler.pt +3 -0
- checkpoint-2772/trainer_state.json +2165 -0
- checkpoint-2772/training_args.bin +3 -0
- config.json +19 -17
- model.safetensors +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +3 -44
- training_args.bin +3 -0
checkpoint-2541/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 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": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"is_decoder": false,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-05,
|
| 34 |
+
"max_position_embeddings": 514,
|
| 35 |
+
"model_type": "xlm-roberta",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"output_past": true,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "multi_label_classification",
|
| 42 |
+
"tie_word_embeddings": true,
|
| 43 |
+
"transformers_version": "5.2.0",
|
| 44 |
+
"type_vocab_size": 1,
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 250002
|
| 47 |
+
}
|
checkpoint-2541/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47d8f48f3b17e6c17dbd049c2736b1ddf98058adb360d4c1f92c380e087e94e
|
| 3 |
+
size 1112217288
|
checkpoint-2541/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fab0675b977533c1512823c9f590db3431b6642f554e3a4f2a953a57e03f598
|
| 3 |
+
size 2224549003
|
checkpoint-2541/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f18857b07b781cd0a12064717467b9415271e56890e9d2d435830c7ae60deb6f
|
| 3 |
+
size 14455
|
checkpoint-2541/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ac575a5c787b9d9e11400adb9503fed9d62fdd5f3509e8ed9dc598f5377a3b
|
| 3 |
+
size 1465
|
checkpoint-2541/trainer_state.json
ADDED
|
@@ -0,0 +1,1988 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2541,
|
| 3 |
+
"best_metric": 0.9725158562367865,
|
| 4 |
+
"best_model_checkpoint": "/Users/loule/Documents/Projets Dev/Git/Egide/apps/ai-service/../../models/egide-toxicity-model/checkpoint-2541",
|
| 5 |
+
"epoch": 11.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2541,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04329004329004329,
|
| 14 |
+
"grad_norm": 1.9666005373001099,
|
| 15 |
+
"learning_rate": 6.474820143884893e-07,
|
| 16 |
+
"loss": 0.6904128551483154,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08658008658008658,
|
| 21 |
+
"grad_norm": 1.5532240867614746,
|
| 22 |
+
"learning_rate": 1.366906474820144e-06,
|
| 23 |
+
"loss": 0.6828486442565918,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12987012987012986,
|
| 28 |
+
"grad_norm": 1.9879132509231567,
|
| 29 |
+
"learning_rate": 2.0863309352517987e-06,
|
| 30 |
+
"loss": 0.6761202335357666,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.17316017316017315,
|
| 35 |
+
"grad_norm": 1.8693434000015259,
|
| 36 |
+
"learning_rate": 2.805755395683453e-06,
|
| 37 |
+
"loss": 0.6731895923614502,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21645021645021645,
|
| 42 |
+
"grad_norm": 2.021498918533325,
|
| 43 |
+
"learning_rate": 3.525179856115108e-06,
|
| 44 |
+
"loss": 0.6719329357147217,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2597402597402597,
|
| 49 |
+
"grad_norm": 8.98990249633789,
|
| 50 |
+
"learning_rate": 4.244604316546763e-06,
|
| 51 |
+
"loss": 0.6427541255950928,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.30303030303030304,
|
| 56 |
+
"grad_norm": 5.401233196258545,
|
| 57 |
+
"learning_rate": 4.9640287769784175e-06,
|
| 58 |
+
"loss": 0.61961669921875,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3463203463203463,
|
| 63 |
+
"grad_norm": 8.536731719970703,
|
| 64 |
+
"learning_rate": 5.683453237410073e-06,
|
| 65 |
+
"loss": 0.6018109321594238,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.38961038961038963,
|
| 70 |
+
"grad_norm": 5.487812042236328,
|
| 71 |
+
"learning_rate": 6.402877697841727e-06,
|
| 72 |
+
"loss": 0.5745875358581543,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4329004329004329,
|
| 77 |
+
"grad_norm": 4.356001377105713,
|
| 78 |
+
"learning_rate": 7.122302158273382e-06,
|
| 79 |
+
"loss": 0.5471229076385498,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.47619047619047616,
|
| 84 |
+
"grad_norm": 6.982844829559326,
|
| 85 |
+
"learning_rate": 7.841726618705036e-06,
|
| 86 |
+
"loss": 0.5099374771118164,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5194805194805194,
|
| 91 |
+
"grad_norm": 1.8694194555282593,
|
| 92 |
+
"learning_rate": 8.561151079136692e-06,
|
| 93 |
+
"loss": 0.5038644790649414,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5627705627705628,
|
| 98 |
+
"grad_norm": 3.096836805343628,
|
| 99 |
+
"learning_rate": 9.280575539568346e-06,
|
| 100 |
+
"loss": 0.5061714172363281,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6060606060606061,
|
| 105 |
+
"grad_norm": 1.9763317108154297,
|
| 106 |
+
"learning_rate": 1e-05,
|
| 107 |
+
"loss": 0.5091361999511719,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6493506493506493,
|
| 112 |
+
"grad_norm": 6.211313247680664,
|
| 113 |
+
"learning_rate": 1.0719424460431655e-05,
|
| 114 |
+
"loss": 0.48816370964050293,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6926406926406926,
|
| 119 |
+
"grad_norm": 1.5845985412597656,
|
| 120 |
+
"learning_rate": 1.143884892086331e-05,
|
| 121 |
+
"loss": 0.4852591037750244,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7359307359307359,
|
| 126 |
+
"grad_norm": 4.810131549835205,
|
| 127 |
+
"learning_rate": 1.2158273381294966e-05,
|
| 128 |
+
"loss": 0.4814936637878418,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7792207792207793,
|
| 133 |
+
"grad_norm": 2.836341142654419,
|
| 134 |
+
"learning_rate": 1.287769784172662e-05,
|
| 135 |
+
"loss": 0.5129002571105957,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.8225108225108225,
|
| 140 |
+
"grad_norm": 1.2342458963394165,
|
| 141 |
+
"learning_rate": 1.3597122302158274e-05,
|
| 142 |
+
"loss": 0.4621418952941895,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8658008658008658,
|
| 147 |
+
"grad_norm": 2.936840295791626,
|
| 148 |
+
"learning_rate": 1.4316546762589929e-05,
|
| 149 |
+
"loss": 0.4222285270690918,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.9090909090909091,
|
| 154 |
+
"grad_norm": 2.36641526222229,
|
| 155 |
+
"learning_rate": 1.5035971223021583e-05,
|
| 156 |
+
"loss": 0.4732527732849121,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.9523809523809523,
|
| 161 |
+
"grad_norm": 2.6311023235321045,
|
| 162 |
+
"learning_rate": 1.5755395683453238e-05,
|
| 163 |
+
"loss": 0.47931723594665526,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9956709956709957,
|
| 168 |
+
"grad_norm": 1.7854502201080322,
|
| 169 |
+
"learning_rate": 1.6474820143884892e-05,
|
| 170 |
+
"loss": 0.4703701019287109,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0,
|
| 175 |
+
"eval_f1_hate": 0.0,
|
| 176 |
+
"eval_f1_identity_attack": 0.0,
|
| 177 |
+
"eval_f1_insult": 0.0,
|
| 178 |
+
"eval_f1_macro": 0.12619502868068835,
|
| 179 |
+
"eval_f1_micro": 0.4937655860349127,
|
| 180 |
+
"eval_f1_sexual": 0.0,
|
| 181 |
+
"eval_f1_threat": 0.0,
|
| 182 |
+
"eval_f1_toxicity": 0.7571701720841301,
|
| 183 |
+
"eval_loss": 0.45029428601264954,
|
| 184 |
+
"eval_runtime": 3.1166,
|
| 185 |
+
"eval_samples_per_second": 104.28,
|
| 186 |
+
"eval_steps_per_second": 13.155,
|
| 187 |
+
"step": 231
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.0389610389610389,
|
| 191 |
+
"grad_norm": 2.7693347930908203,
|
| 192 |
+
"learning_rate": 1.7194244604316546e-05,
|
| 193 |
+
"loss": 0.41036128997802734,
|
| 194 |
+
"step": 240
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0822510822510822,
|
| 198 |
+
"grad_norm": 3.0557188987731934,
|
| 199 |
+
"learning_rate": 1.7913669064748204e-05,
|
| 200 |
+
"loss": 0.4664168357849121,
|
| 201 |
+
"step": 250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.1255411255411256,
|
| 205 |
+
"grad_norm": 2.9418742656707764,
|
| 206 |
+
"learning_rate": 1.863309352517986e-05,
|
| 207 |
+
"loss": 0.46143579483032227,
|
| 208 |
+
"step": 260
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.1688311688311688,
|
| 212 |
+
"grad_norm": 3.2120885848999023,
|
| 213 |
+
"learning_rate": 1.9352517985611513e-05,
|
| 214 |
+
"loss": 0.4405516147613525,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.2121212121212122,
|
| 219 |
+
"grad_norm": 4.124722480773926,
|
| 220 |
+
"learning_rate": 1.9991980753809144e-05,
|
| 221 |
+
"loss": 0.44314141273498536,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.2554112554112553,
|
| 226 |
+
"grad_norm": 4.181340217590332,
|
| 227 |
+
"learning_rate": 1.9911788291900563e-05,
|
| 228 |
+
"loss": 0.39984827041625975,
|
| 229 |
+
"step": 290
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2987012987012987,
|
| 233 |
+
"grad_norm": 4.350127696990967,
|
| 234 |
+
"learning_rate": 1.9831595829991984e-05,
|
| 235 |
+
"loss": 0.42529864311218263,
|
| 236 |
+
"step": 300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.341991341991342,
|
| 240 |
+
"grad_norm": 4.975383758544922,
|
| 241 |
+
"learning_rate": 1.9751403368083402e-05,
|
| 242 |
+
"loss": 0.4305525302886963,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.3852813852813852,
|
| 247 |
+
"grad_norm": 2.471064805984497,
|
| 248 |
+
"learning_rate": 1.967121090617482e-05,
|
| 249 |
+
"loss": 0.40537114143371583,
|
| 250 |
+
"step": 320
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.4285714285714286,
|
| 254 |
+
"grad_norm": 6.418680667877197,
|
| 255 |
+
"learning_rate": 1.959101844426624e-05,
|
| 256 |
+
"loss": 0.3864774703979492,
|
| 257 |
+
"step": 330
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.4718614718614718,
|
| 261 |
+
"grad_norm": 2.3995094299316406,
|
| 262 |
+
"learning_rate": 1.951082598235766e-05,
|
| 263 |
+
"loss": 0.35166306495666505,
|
| 264 |
+
"step": 340
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.5151515151515151,
|
| 268 |
+
"grad_norm": 5.420963764190674,
|
| 269 |
+
"learning_rate": 1.943063352044908e-05,
|
| 270 |
+
"loss": 0.3708444118499756,
|
| 271 |
+
"step": 350
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.5584415584415585,
|
| 275 |
+
"grad_norm": 6.72929048538208,
|
| 276 |
+
"learning_rate": 1.93504410585405e-05,
|
| 277 |
+
"loss": 0.3743911266326904,
|
| 278 |
+
"step": 360
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.601731601731602,
|
| 282 |
+
"grad_norm": 3.1479010581970215,
|
| 283 |
+
"learning_rate": 1.9270248596631917e-05,
|
| 284 |
+
"loss": 0.3563019514083862,
|
| 285 |
+
"step": 370
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.645021645021645,
|
| 289 |
+
"grad_norm": 9.571167945861816,
|
| 290 |
+
"learning_rate": 1.919005613472334e-05,
|
| 291 |
+
"loss": 0.33117449283599854,
|
| 292 |
+
"step": 380
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.6883116883116882,
|
| 296 |
+
"grad_norm": 4.24497127532959,
|
| 297 |
+
"learning_rate": 1.9109863672814757e-05,
|
| 298 |
+
"loss": 0.3223949670791626,
|
| 299 |
+
"step": 390
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.7316017316017316,
|
| 303 |
+
"grad_norm": 2.9281415939331055,
|
| 304 |
+
"learning_rate": 1.9029671210906175e-05,
|
| 305 |
+
"loss": 0.32130889892578124,
|
| 306 |
+
"step": 400
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.774891774891775,
|
| 310 |
+
"grad_norm": 15.57435131072998,
|
| 311 |
+
"learning_rate": 1.8949478748997596e-05,
|
| 312 |
+
"loss": 0.31391539573669436,
|
| 313 |
+
"step": 410
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.8181818181818183,
|
| 317 |
+
"grad_norm": 5.047284126281738,
|
| 318 |
+
"learning_rate": 1.8869286287089015e-05,
|
| 319 |
+
"loss": 0.28419616222381594,
|
| 320 |
+
"step": 420
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.8614718614718615,
|
| 324 |
+
"grad_norm": 5.080146789550781,
|
| 325 |
+
"learning_rate": 1.8789093825180436e-05,
|
| 326 |
+
"loss": 0.33582773208618166,
|
| 327 |
+
"step": 430
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.9047619047619047,
|
| 331 |
+
"grad_norm": 6.664261817932129,
|
| 332 |
+
"learning_rate": 1.8708901363271854e-05,
|
| 333 |
+
"loss": 0.38676986694335935,
|
| 334 |
+
"step": 440
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.948051948051948,
|
| 338 |
+
"grad_norm": 44.62375259399414,
|
| 339 |
+
"learning_rate": 1.8628708901363272e-05,
|
| 340 |
+
"loss": 0.3767754554748535,
|
| 341 |
+
"step": 450
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.9913419913419914,
|
| 345 |
+
"grad_norm": 5.366123199462891,
|
| 346 |
+
"learning_rate": 1.8548516439454694e-05,
|
| 347 |
+
"loss": 0.35468668937683107,
|
| 348 |
+
"step": 460
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.0,
|
| 352 |
+
"eval_f1_hate": 0.7941176470588235,
|
| 353 |
+
"eval_f1_identity_attack": 0.6972477064220184,
|
| 354 |
+
"eval_f1_insult": 0.6732673267326733,
|
| 355 |
+
"eval_f1_macro": 0.5105760349375467,
|
| 356 |
+
"eval_f1_micro": 0.7580993520518359,
|
| 357 |
+
"eval_f1_sexual": 0.0,
|
| 358 |
+
"eval_f1_threat": 0.0,
|
| 359 |
+
"eval_f1_toxicity": 0.8988235294117647,
|
| 360 |
+
"eval_loss": 0.28017890453338623,
|
| 361 |
+
"eval_runtime": 2.5637,
|
| 362 |
+
"eval_samples_per_second": 126.768,
|
| 363 |
+
"eval_steps_per_second": 15.992,
|
| 364 |
+
"step": 462
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.034632034632035,
|
| 368 |
+
"grad_norm": 4.787834167480469,
|
| 369 |
+
"learning_rate": 1.846832397754611e-05,
|
| 370 |
+
"loss": 0.2688360929489136,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0779220779220777,
|
| 375 |
+
"grad_norm": 5.352668762207031,
|
| 376 |
+
"learning_rate": 1.838813151563753e-05,
|
| 377 |
+
"loss": 0.2794922113418579,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.121212121212121,
|
| 382 |
+
"grad_norm": 7.183356761932373,
|
| 383 |
+
"learning_rate": 1.830793905372895e-05,
|
| 384 |
+
"loss": 0.2400437116622925,
|
| 385 |
+
"step": 490
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.1645021645021645,
|
| 389 |
+
"grad_norm": 3.194124221801758,
|
| 390 |
+
"learning_rate": 1.822774659182037e-05,
|
| 391 |
+
"loss": 0.2642167806625366,
|
| 392 |
+
"step": 500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.207792207792208,
|
| 396 |
+
"grad_norm": 4.878069877624512,
|
| 397 |
+
"learning_rate": 1.814755412991179e-05,
|
| 398 |
+
"loss": 0.23577990531921386,
|
| 399 |
+
"step": 510
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.2510822510822512,
|
| 403 |
+
"grad_norm": 4.87581729888916,
|
| 404 |
+
"learning_rate": 1.806736166800321e-05,
|
| 405 |
+
"loss": 0.2429830551147461,
|
| 406 |
+
"step": 520
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.2943722943722946,
|
| 410 |
+
"grad_norm": 12.465156555175781,
|
| 411 |
+
"learning_rate": 1.7987169206094627e-05,
|
| 412 |
+
"loss": 0.2490438461303711,
|
| 413 |
+
"step": 530
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.3376623376623376,
|
| 417 |
+
"grad_norm": 1.1159459352493286,
|
| 418 |
+
"learning_rate": 1.790697674418605e-05,
|
| 419 |
+
"loss": 0.238852858543396,
|
| 420 |
+
"step": 540
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.380952380952381,
|
| 424 |
+
"grad_norm": 6.159651279449463,
|
| 425 |
+
"learning_rate": 1.7826784282277466e-05,
|
| 426 |
+
"loss": 0.23801960945129394,
|
| 427 |
+
"step": 550
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.4242424242424243,
|
| 431 |
+
"grad_norm": 5.769070625305176,
|
| 432 |
+
"learning_rate": 1.7746591820368885e-05,
|
| 433 |
+
"loss": 0.2144552230834961,
|
| 434 |
+
"step": 560
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.4675324675324677,
|
| 438 |
+
"grad_norm": 11.144370079040527,
|
| 439 |
+
"learning_rate": 1.7666399358460306e-05,
|
| 440 |
+
"loss": 0.209763765335083,
|
| 441 |
+
"step": 570
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.5108225108225106,
|
| 445 |
+
"grad_norm": 8.017593383789062,
|
| 446 |
+
"learning_rate": 1.7586206896551724e-05,
|
| 447 |
+
"loss": 0.20393669605255127,
|
| 448 |
+
"step": 580
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.554112554112554,
|
| 452 |
+
"grad_norm": 8.491714477539062,
|
| 453 |
+
"learning_rate": 1.7506014434643146e-05,
|
| 454 |
+
"loss": 0.21084864139556886,
|
| 455 |
+
"step": 590
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.5974025974025974,
|
| 459 |
+
"grad_norm": 10.802801132202148,
|
| 460 |
+
"learning_rate": 1.7425821972734564e-05,
|
| 461 |
+
"loss": 0.19502675533294678,
|
| 462 |
+
"step": 600
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.6406926406926408,
|
| 466 |
+
"grad_norm": 7.383920192718506,
|
| 467 |
+
"learning_rate": 1.7345629510825982e-05,
|
| 468 |
+
"loss": 0.17343367338180543,
|
| 469 |
+
"step": 610
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.683982683982684,
|
| 473 |
+
"grad_norm": 14.915983200073242,
|
| 474 |
+
"learning_rate": 1.7265437048917403e-05,
|
| 475 |
+
"loss": 0.20925779342651368,
|
| 476 |
+
"step": 620
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.7272727272727275,
|
| 480 |
+
"grad_norm": 11.076672554016113,
|
| 481 |
+
"learning_rate": 1.718524458700882e-05,
|
| 482 |
+
"loss": 0.18709557056427,
|
| 483 |
+
"step": 630
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.7705627705627704,
|
| 487 |
+
"grad_norm": 1.3212802410125732,
|
| 488 |
+
"learning_rate": 1.710505212510024e-05,
|
| 489 |
+
"loss": 0.12550430297851561,
|
| 490 |
+
"step": 640
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.813852813852814,
|
| 494 |
+
"grad_norm": 39.46677017211914,
|
| 495 |
+
"learning_rate": 1.702485966319166e-05,
|
| 496 |
+
"loss": 0.20734634399414062,
|
| 497 |
+
"step": 650
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.857142857142857,
|
| 501 |
+
"grad_norm": 21.644838333129883,
|
| 502 |
+
"learning_rate": 1.694466720128308e-05,
|
| 503 |
+
"loss": 0.20593829154968263,
|
| 504 |
+
"step": 660
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.9004329004329006,
|
| 508 |
+
"grad_norm": 1.596218228340149,
|
| 509 |
+
"learning_rate": 1.68644747393745e-05,
|
| 510 |
+
"loss": 0.21429204940795898,
|
| 511 |
+
"step": 670
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.9437229437229435,
|
| 515 |
+
"grad_norm": 6.069190502166748,
|
| 516 |
+
"learning_rate": 1.678428227746592e-05,
|
| 517 |
+
"loss": 0.17528226375579833,
|
| 518 |
+
"step": 680
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.987012987012987,
|
| 522 |
+
"grad_norm": 2.579589366912842,
|
| 523 |
+
"learning_rate": 1.670408981555734e-05,
|
| 524 |
+
"loss": 0.1867051124572754,
|
| 525 |
+
"step": 690
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.0,
|
| 529 |
+
"eval_f1_hate": 0.9078014184397163,
|
| 530 |
+
"eval_f1_identity_attack": 0.7768595041322314,
|
| 531 |
+
"eval_f1_insult": 0.8369565217391305,
|
| 532 |
+
"eval_f1_macro": 0.7266940390440862,
|
| 533 |
+
"eval_f1_micro": 0.8838709677419355,
|
| 534 |
+
"eval_f1_sexual": 0.0,
|
| 535 |
+
"eval_f1_threat": 0.8717948717948718,
|
| 536 |
+
"eval_f1_toxicity": 0.9667519181585678,
|
| 537 |
+
"eval_loss": 0.16751155257225037,
|
| 538 |
+
"eval_runtime": 2.697,
|
| 539 |
+
"eval_samples_per_second": 120.505,
|
| 540 |
+
"eval_steps_per_second": 15.202,
|
| 541 |
+
"step": 693
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.0303030303030303,
|
| 545 |
+
"grad_norm": 12.631734848022461,
|
| 546 |
+
"learning_rate": 1.6623897353648758e-05,
|
| 547 |
+
"loss": 0.1437455415725708,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.0735930735930737,
|
| 552 |
+
"grad_norm": 0.43667536973953247,
|
| 553 |
+
"learning_rate": 1.6543704891740176e-05,
|
| 554 |
+
"loss": 0.10637929439544677,
|
| 555 |
+
"step": 710
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.116883116883117,
|
| 559 |
+
"grad_norm": 16.54327964782715,
|
| 560 |
+
"learning_rate": 1.6463512429831598e-05,
|
| 561 |
+
"loss": 0.1611637830734253,
|
| 562 |
+
"step": 720
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.16017316017316,
|
| 566 |
+
"grad_norm": 11.03506851196289,
|
| 567 |
+
"learning_rate": 1.6383319967923016e-05,
|
| 568 |
+
"loss": 0.10024868249893189,
|
| 569 |
+
"step": 730
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.2034632034632033,
|
| 573 |
+
"grad_norm": 0.4897419512271881,
|
| 574 |
+
"learning_rate": 1.6303127506014437e-05,
|
| 575 |
+
"loss": 0.13905807733535766,
|
| 576 |
+
"step": 740
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.2467532467532467,
|
| 580 |
+
"grad_norm": 24.316959381103516,
|
| 581 |
+
"learning_rate": 1.6222935044105855e-05,
|
| 582 |
+
"loss": 0.14806885719299318,
|
| 583 |
+
"step": 750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.29004329004329,
|
| 587 |
+
"grad_norm": 12.093938827514648,
|
| 588 |
+
"learning_rate": 1.6142742582197277e-05,
|
| 589 |
+
"loss": 0.13683819770812988,
|
| 590 |
+
"step": 760
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.3333333333333335,
|
| 594 |
+
"grad_norm": 11.699234962463379,
|
| 595 |
+
"learning_rate": 1.6062550120288695e-05,
|
| 596 |
+
"loss": 0.11938896179199218,
|
| 597 |
+
"step": 770
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.3766233766233764,
|
| 601 |
+
"grad_norm": 0.7831173539161682,
|
| 602 |
+
"learning_rate": 1.5982357658380113e-05,
|
| 603 |
+
"loss": 0.153947913646698,
|
| 604 |
+
"step": 780
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.41991341991342,
|
| 608 |
+
"grad_norm": 10.696303367614746,
|
| 609 |
+
"learning_rate": 1.5902165196471534e-05,
|
| 610 |
+
"loss": 0.170080304145813,
|
| 611 |
+
"step": 790
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.463203463203463,
|
| 615 |
+
"grad_norm": 4.8850507736206055,
|
| 616 |
+
"learning_rate": 1.5821972734562952e-05,
|
| 617 |
+
"loss": 0.11064658164978028,
|
| 618 |
+
"step": 800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.5064935064935066,
|
| 622 |
+
"grad_norm": 5.002935409545898,
|
| 623 |
+
"learning_rate": 1.5741780272654374e-05,
|
| 624 |
+
"loss": 0.18166909217834473,
|
| 625 |
+
"step": 810
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.54978354978355,
|
| 629 |
+
"grad_norm": 0.8856028914451599,
|
| 630 |
+
"learning_rate": 1.5661587810745792e-05,
|
| 631 |
+
"loss": 0.06949449777603149,
|
| 632 |
+
"step": 820
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.5930735930735933,
|
| 636 |
+
"grad_norm": 0.8279700875282288,
|
| 637 |
+
"learning_rate": 1.558139534883721e-05,
|
| 638 |
+
"loss": 0.16245560646057128,
|
| 639 |
+
"step": 830
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.6363636363636362,
|
| 643 |
+
"grad_norm": 1.2465356588363647,
|
| 644 |
+
"learning_rate": 1.550120288692863e-05,
|
| 645 |
+
"loss": 0.11454813480377198,
|
| 646 |
+
"step": 840
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.6796536796536796,
|
| 650 |
+
"grad_norm": 0.49412283301353455,
|
| 651 |
+
"learning_rate": 1.542101042502005e-05,
|
| 652 |
+
"loss": 0.18175532817840576,
|
| 653 |
+
"step": 850
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.722943722943723,
|
| 657 |
+
"grad_norm": 19.483863830566406,
|
| 658 |
+
"learning_rate": 1.534081796311147e-05,
|
| 659 |
+
"loss": 0.1303969979286194,
|
| 660 |
+
"step": 860
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.7662337662337664,
|
| 664 |
+
"grad_norm": 0.5482262969017029,
|
| 665 |
+
"learning_rate": 1.526062550120289e-05,
|
| 666 |
+
"loss": 0.18206866979598998,
|
| 667 |
+
"step": 870
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.8095238095238093,
|
| 671 |
+
"grad_norm": 56.418704986572266,
|
| 672 |
+
"learning_rate": 1.5180433039294307e-05,
|
| 673 |
+
"loss": 0.11589281558990479,
|
| 674 |
+
"step": 880
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.8528138528138527,
|
| 678 |
+
"grad_norm": 1.1338515281677246,
|
| 679 |
+
"learning_rate": 1.5100240577385727e-05,
|
| 680 |
+
"loss": 0.16329562664031982,
|
| 681 |
+
"step": 890
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.896103896103896,
|
| 685 |
+
"grad_norm": 6.882433891296387,
|
| 686 |
+
"learning_rate": 1.5020048115477147e-05,
|
| 687 |
+
"loss": 0.17075834274291993,
|
| 688 |
+
"step": 900
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.9393939393939394,
|
| 692 |
+
"grad_norm": 7.5362162590026855,
|
| 693 |
+
"learning_rate": 1.4939855653568566e-05,
|
| 694 |
+
"loss": 0.13381673097610475,
|
| 695 |
+
"step": 910
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.982683982683983,
|
| 699 |
+
"grad_norm": 1.186409831047058,
|
| 700 |
+
"learning_rate": 1.4859663191659985e-05,
|
| 701 |
+
"loss": 0.09673304557800293,
|
| 702 |
+
"step": 920
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.0,
|
| 706 |
+
"eval_f1_hate": 0.9076923076923077,
|
| 707 |
+
"eval_f1_identity_attack": 0.8,
|
| 708 |
+
"eval_f1_insult": 0.9019607843137255,
|
| 709 |
+
"eval_f1_macro": 0.8549086601070185,
|
| 710 |
+
"eval_f1_micro": 0.9085037674919269,
|
| 711 |
+
"eval_f1_sexual": 0.6666666666666666,
|
| 712 |
+
"eval_f1_threat": 0.8918918918918919,
|
| 713 |
+
"eval_f1_toxicity": 0.9612403100775194,
|
| 714 |
+
"eval_loss": 0.13372334837913513,
|
| 715 |
+
"eval_runtime": 2.6455,
|
| 716 |
+
"eval_samples_per_second": 122.852,
|
| 717 |
+
"eval_steps_per_second": 15.498,
|
| 718 |
+
"step": 924
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.025974025974026,
|
| 722 |
+
"grad_norm": 3.63419246673584,
|
| 723 |
+
"learning_rate": 1.4779470729751404e-05,
|
| 724 |
+
"loss": 0.0814066231250763,
|
| 725 |
+
"step": 930
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.06926406926407,
|
| 729 |
+
"grad_norm": 4.606685161590576,
|
| 730 |
+
"learning_rate": 1.4699278267842824e-05,
|
| 731 |
+
"loss": 0.09704769253730774,
|
| 732 |
+
"step": 940
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.112554112554113,
|
| 736 |
+
"grad_norm": 1.3340409994125366,
|
| 737 |
+
"learning_rate": 1.4619085805934244e-05,
|
| 738 |
+
"loss": 0.06881680488586425,
|
| 739 |
+
"step": 950
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.1558441558441555,
|
| 743 |
+
"grad_norm": 22.688732147216797,
|
| 744 |
+
"learning_rate": 1.4538893344025662e-05,
|
| 745 |
+
"loss": 0.08566259145736695,
|
| 746 |
+
"step": 960
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 4.199134199134199,
|
| 750 |
+
"grad_norm": 0.7076430916786194,
|
| 751 |
+
"learning_rate": 1.4458700882117083e-05,
|
| 752 |
+
"loss": 0.06713258028030396,
|
| 753 |
+
"step": 970
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.242424242424242,
|
| 757 |
+
"grad_norm": 0.3430556058883667,
|
| 758 |
+
"learning_rate": 1.4378508420208502e-05,
|
| 759 |
+
"loss": 0.07058375477790832,
|
| 760 |
+
"step": 980
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.285714285714286,
|
| 764 |
+
"grad_norm": 0.47648629546165466,
|
| 765 |
+
"learning_rate": 1.4298315958299921e-05,
|
| 766 |
+
"loss": 0.05376957654953003,
|
| 767 |
+
"step": 990
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 4.329004329004329,
|
| 771 |
+
"grad_norm": 30.782028198242188,
|
| 772 |
+
"learning_rate": 1.4218123496391341e-05,
|
| 773 |
+
"loss": 0.0664408564567566,
|
| 774 |
+
"step": 1000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.372294372294372,
|
| 778 |
+
"grad_norm": 5.640874862670898,
|
| 779 |
+
"learning_rate": 1.4137931034482759e-05,
|
| 780 |
+
"loss": 0.10812230110168457,
|
| 781 |
+
"step": 1010
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 4.415584415584416,
|
| 785 |
+
"grad_norm": 1.3343350887298584,
|
| 786 |
+
"learning_rate": 1.405773857257418e-05,
|
| 787 |
+
"loss": 0.09118871688842774,
|
| 788 |
+
"step": 1020
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 4.458874458874459,
|
| 792 |
+
"grad_norm": 3.0995726585388184,
|
| 793 |
+
"learning_rate": 1.3977546110665599e-05,
|
| 794 |
+
"loss": 0.09201886057853699,
|
| 795 |
+
"step": 1030
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.5021645021645025,
|
| 799 |
+
"grad_norm": 43.72480010986328,
|
| 800 |
+
"learning_rate": 1.3897353648757017e-05,
|
| 801 |
+
"loss": 0.12083396911621094,
|
| 802 |
+
"step": 1040
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.545454545454545,
|
| 806 |
+
"grad_norm": 8.080801010131836,
|
| 807 |
+
"learning_rate": 1.3817161186848438e-05,
|
| 808 |
+
"loss": 0.07746089696884155,
|
| 809 |
+
"step": 1050
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.588744588744589,
|
| 813 |
+
"grad_norm": 7.748966217041016,
|
| 814 |
+
"learning_rate": 1.3736968724939856e-05,
|
| 815 |
+
"loss": 0.08128405213356019,
|
| 816 |
+
"step": 1060
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 4.632034632034632,
|
| 820 |
+
"grad_norm": 7.703828811645508,
|
| 821 |
+
"learning_rate": 1.3656776263031278e-05,
|
| 822 |
+
"loss": 0.07613251209259034,
|
| 823 |
+
"step": 1070
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 4.675324675324675,
|
| 827 |
+
"grad_norm": 12.483865737915039,
|
| 828 |
+
"learning_rate": 1.3576583801122696e-05,
|
| 829 |
+
"loss": 0.06644371151924133,
|
| 830 |
+
"step": 1080
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 4.7186147186147185,
|
| 834 |
+
"grad_norm": 5.6639404296875,
|
| 835 |
+
"learning_rate": 1.3496391339214114e-05,
|
| 836 |
+
"loss": 0.07161596417427063,
|
| 837 |
+
"step": 1090
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.761904761904762,
|
| 841 |
+
"grad_norm": 3.5330121517181396,
|
| 842 |
+
"learning_rate": 1.3416198877305535e-05,
|
| 843 |
+
"loss": 0.10294915437698364,
|
| 844 |
+
"step": 1100
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 4.805194805194805,
|
| 848 |
+
"grad_norm": 12.56156063079834,
|
| 849 |
+
"learning_rate": 1.3336006415396953e-05,
|
| 850 |
+
"loss": 0.11282093524932861,
|
| 851 |
+
"step": 1110
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 4.848484848484849,
|
| 855 |
+
"grad_norm": 1.3351284265518188,
|
| 856 |
+
"learning_rate": 1.3255813953488372e-05,
|
| 857 |
+
"loss": 0.085838782787323,
|
| 858 |
+
"step": 1120
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 4.891774891774892,
|
| 862 |
+
"grad_norm": 19.801355361938477,
|
| 863 |
+
"learning_rate": 1.3175621491579793e-05,
|
| 864 |
+
"loss": 0.07634471654891968,
|
| 865 |
+
"step": 1130
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 4.935064935064935,
|
| 869 |
+
"grad_norm": 0.30149272084236145,
|
| 870 |
+
"learning_rate": 1.3095429029671211e-05,
|
| 871 |
+
"loss": 0.046724116802215575,
|
| 872 |
+
"step": 1140
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.978354978354979,
|
| 876 |
+
"grad_norm": 4.291561603546143,
|
| 877 |
+
"learning_rate": 1.3015236567762633e-05,
|
| 878 |
+
"loss": 0.04501450061798096,
|
| 879 |
+
"step": 1150
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 5.0,
|
| 883 |
+
"eval_f1_hate": 0.935251798561151,
|
| 884 |
+
"eval_f1_identity_attack": 0.8849557522123894,
|
| 885 |
+
"eval_f1_insult": 0.94,
|
| 886 |
+
"eval_f1_macro": 0.9110801721442771,
|
| 887 |
+
"eval_f1_micro": 0.944386149003148,
|
| 888 |
+
"eval_f1_sexual": 0.8148148148148148,
|
| 889 |
+
"eval_f1_threat": 0.9090909090909091,
|
| 890 |
+
"eval_f1_toxicity": 0.982367758186398,
|
| 891 |
+
"eval_loss": 0.09442197531461716,
|
| 892 |
+
"eval_runtime": 2.5423,
|
| 893 |
+
"eval_samples_per_second": 127.835,
|
| 894 |
+
"eval_steps_per_second": 16.127,
|
| 895 |
+
"step": 1155
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 5.021645021645021,
|
| 899 |
+
"grad_norm": 16.437841415405273,
|
| 900 |
+
"learning_rate": 1.293504410585405e-05,
|
| 901 |
+
"loss": 0.057061117887496945,
|
| 902 |
+
"step": 1160
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 5.064935064935065,
|
| 906 |
+
"grad_norm": 1.009265422821045,
|
| 907 |
+
"learning_rate": 1.2854851643945469e-05,
|
| 908 |
+
"loss": 0.06116377115249634,
|
| 909 |
+
"step": 1170
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 5.108225108225108,
|
| 913 |
+
"grad_norm": 0.22976772487163544,
|
| 914 |
+
"learning_rate": 1.277465918203689e-05,
|
| 915 |
+
"loss": 0.03162805736064911,
|
| 916 |
+
"step": 1180
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 5.151515151515151,
|
| 920 |
+
"grad_norm": 0.16043254733085632,
|
| 921 |
+
"learning_rate": 1.2694466720128308e-05,
|
| 922 |
+
"loss": 0.05421352982521057,
|
| 923 |
+
"step": 1190
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 5.194805194805195,
|
| 927 |
+
"grad_norm": 0.7127373814582825,
|
| 928 |
+
"learning_rate": 1.2614274258219728e-05,
|
| 929 |
+
"loss": 0.048463857173919676,
|
| 930 |
+
"step": 1200
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.238095238095238,
|
| 934 |
+
"grad_norm": 0.1292610466480255,
|
| 935 |
+
"learning_rate": 1.2534081796311148e-05,
|
| 936 |
+
"loss": 0.05593010187149048,
|
| 937 |
+
"step": 1210
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 5.2813852813852815,
|
| 941 |
+
"grad_norm": 1.4257301092147827,
|
| 942 |
+
"learning_rate": 1.2453889334402568e-05,
|
| 943 |
+
"loss": 0.05451661944389343,
|
| 944 |
+
"step": 1220
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 5.324675324675325,
|
| 948 |
+
"grad_norm": 12.879122734069824,
|
| 949 |
+
"learning_rate": 1.2373696872493987e-05,
|
| 950 |
+
"loss": 0.05459271669387818,
|
| 951 |
+
"step": 1230
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 5.367965367965368,
|
| 955 |
+
"grad_norm": 0.27403524518013,
|
| 956 |
+
"learning_rate": 1.2293504410585405e-05,
|
| 957 |
+
"loss": 0.05355905294418335,
|
| 958 |
+
"step": 1240
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 5.411255411255412,
|
| 962 |
+
"grad_norm": 16.353090286254883,
|
| 963 |
+
"learning_rate": 1.2213311948676825e-05,
|
| 964 |
+
"loss": 0.05738970637321472,
|
| 965 |
+
"step": 1250
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 5.454545454545454,
|
| 969 |
+
"grad_norm": 1.0312873125076294,
|
| 970 |
+
"learning_rate": 1.2133119486768245e-05,
|
| 971 |
+
"loss": 0.04536194503307343,
|
| 972 |
+
"step": 1260
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 5.4978354978354975,
|
| 976 |
+
"grad_norm": 0.17286163568496704,
|
| 977 |
+
"learning_rate": 1.2052927024859665e-05,
|
| 978 |
+
"loss": 0.03271396160125732,
|
| 979 |
+
"step": 1270
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 5.541125541125541,
|
| 983 |
+
"grad_norm": 0.15860261023044586,
|
| 984 |
+
"learning_rate": 1.1972734562951083e-05,
|
| 985 |
+
"loss": 0.02813169062137604,
|
| 986 |
+
"step": 1280
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 5.584415584415584,
|
| 990 |
+
"grad_norm": 0.13466164469718933,
|
| 991 |
+
"learning_rate": 1.1892542101042504e-05,
|
| 992 |
+
"loss": 0.032718077301979065,
|
| 993 |
+
"step": 1290
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.627705627705628,
|
| 997 |
+
"grad_norm": 2.681539535522461,
|
| 998 |
+
"learning_rate": 1.1812349639133922e-05,
|
| 999 |
+
"loss": 0.0269508421421051,
|
| 1000 |
+
"step": 1300
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 5.670995670995671,
|
| 1004 |
+
"grad_norm": 0.10189682245254517,
|
| 1005 |
+
"learning_rate": 1.1732157177225342e-05,
|
| 1006 |
+
"loss": 0.031834939122200014,
|
| 1007 |
+
"step": 1310
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 5.714285714285714,
|
| 1011 |
+
"grad_norm": 0.0732518881559372,
|
| 1012 |
+
"learning_rate": 1.1651964715316762e-05,
|
| 1013 |
+
"loss": 0.02767125368118286,
|
| 1014 |
+
"step": 1320
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.757575757575758,
|
| 1018 |
+
"grad_norm": 8.737700462341309,
|
| 1019 |
+
"learning_rate": 1.157177225340818e-05,
|
| 1020 |
+
"loss": 0.04246579110622406,
|
| 1021 |
+
"step": 1330
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 5.800865800865801,
|
| 1025 |
+
"grad_norm": 0.08001670241355896,
|
| 1026 |
+
"learning_rate": 1.1491579791499601e-05,
|
| 1027 |
+
"loss": 0.06979098916053772,
|
| 1028 |
+
"step": 1340
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 5.8441558441558445,
|
| 1032 |
+
"grad_norm": 4.200087070465088,
|
| 1033 |
+
"learning_rate": 1.141138732959102e-05,
|
| 1034 |
+
"loss": 0.050935995578765866,
|
| 1035 |
+
"step": 1350
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 5.887445887445887,
|
| 1039 |
+
"grad_norm": 0.5274473428726196,
|
| 1040 |
+
"learning_rate": 1.1331194867682438e-05,
|
| 1041 |
+
"loss": 0.030669301748275757,
|
| 1042 |
+
"step": 1360
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 5.93073593073593,
|
| 1046 |
+
"grad_norm": 0.44906026124954224,
|
| 1047 |
+
"learning_rate": 1.1251002405773859e-05,
|
| 1048 |
+
"loss": 0.022448521852493287,
|
| 1049 |
+
"step": 1370
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.974025974025974,
|
| 1053 |
+
"grad_norm": 10.393362045288086,
|
| 1054 |
+
"learning_rate": 1.1170809943865277e-05,
|
| 1055 |
+
"loss": 0.03214894533157349,
|
| 1056 |
+
"step": 1380
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 6.0,
|
| 1060 |
+
"eval_f1_hate": 0.927536231884058,
|
| 1061 |
+
"eval_f1_identity_attack": 0.9090909090909091,
|
| 1062 |
+
"eval_f1_insult": 0.9603960396039604,
|
| 1063 |
+
"eval_f1_macro": 0.9342784803472953,
|
| 1064 |
+
"eval_f1_micro": 0.9556025369978859,
|
| 1065 |
+
"eval_f1_sexual": 0.8888888888888888,
|
| 1066 |
+
"eval_f1_threat": 0.935064935064935,
|
| 1067 |
+
"eval_f1_toxicity": 0.9846938775510204,
|
| 1068 |
+
"eval_loss": 0.0945809856057167,
|
| 1069 |
+
"eval_runtime": 2.5403,
|
| 1070 |
+
"eval_samples_per_second": 127.939,
|
| 1071 |
+
"eval_steps_per_second": 16.14,
|
| 1072 |
+
"step": 1386
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 6.017316017316017,
|
| 1076 |
+
"grad_norm": 1.5638502836227417,
|
| 1077 |
+
"learning_rate": 1.1090617481956699e-05,
|
| 1078 |
+
"loss": 0.015108948945999146,
|
| 1079 |
+
"step": 1390
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 6.0606060606060606,
|
| 1083 |
+
"grad_norm": 0.08260394632816315,
|
| 1084 |
+
"learning_rate": 1.1010425020048117e-05,
|
| 1085 |
+
"loss": 0.037759020924568176,
|
| 1086 |
+
"step": 1400
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 6.103896103896104,
|
| 1090 |
+
"grad_norm": 0.16305118799209595,
|
| 1091 |
+
"learning_rate": 1.0930232558139535e-05,
|
| 1092 |
+
"loss": 0.06289060115814209,
|
| 1093 |
+
"step": 1410
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 6.147186147186147,
|
| 1097 |
+
"grad_norm": 17.280921936035156,
|
| 1098 |
+
"learning_rate": 1.0850040096230956e-05,
|
| 1099 |
+
"loss": 0.03346436619758606,
|
| 1100 |
+
"step": 1420
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 6.190476190476191,
|
| 1104 |
+
"grad_norm": 0.057965584099292755,
|
| 1105 |
+
"learning_rate": 1.0769847634322374e-05,
|
| 1106 |
+
"loss": 0.028430098295211793,
|
| 1107 |
+
"step": 1430
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 6.233766233766234,
|
| 1111 |
+
"grad_norm": 42.3648796081543,
|
| 1112 |
+
"learning_rate": 1.0689655172413792e-05,
|
| 1113 |
+
"loss": 0.04611627459526062,
|
| 1114 |
+
"step": 1440
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 6.2770562770562774,
|
| 1118 |
+
"grad_norm": 0.19590164721012115,
|
| 1119 |
+
"learning_rate": 1.0609462710505214e-05,
|
| 1120 |
+
"loss": 0.01396958827972412,
|
| 1121 |
+
"step": 1450
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 6.32034632034632,
|
| 1125 |
+
"grad_norm": 0.054590217769145966,
|
| 1126 |
+
"learning_rate": 1.0529270248596632e-05,
|
| 1127 |
+
"loss": 0.021274125576019286,
|
| 1128 |
+
"step": 1460
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 6.363636363636363,
|
| 1132 |
+
"grad_norm": 0.05328702554106712,
|
| 1133 |
+
"learning_rate": 1.0449077786688053e-05,
|
| 1134 |
+
"loss": 0.034597578644752505,
|
| 1135 |
+
"step": 1470
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 6.406926406926407,
|
| 1139 |
+
"grad_norm": 3.127825975418091,
|
| 1140 |
+
"learning_rate": 1.0368885324779472e-05,
|
| 1141 |
+
"loss": 0.023499704897403717,
|
| 1142 |
+
"step": 1480
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 6.45021645021645,
|
| 1146 |
+
"grad_norm": 0.6553439497947693,
|
| 1147 |
+
"learning_rate": 1.028869286287089e-05,
|
| 1148 |
+
"loss": 0.01829185485839844,
|
| 1149 |
+
"step": 1490
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.4935064935064934,
|
| 1153 |
+
"grad_norm": 0.09214723855257034,
|
| 1154 |
+
"learning_rate": 1.0208500400962311e-05,
|
| 1155 |
+
"loss": 0.025910788774490358,
|
| 1156 |
+
"step": 1500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.536796536796537,
|
| 1160 |
+
"grad_norm": 0.1844961792230606,
|
| 1161 |
+
"learning_rate": 1.012830793905373e-05,
|
| 1162 |
+
"loss": 0.03210195004940033,
|
| 1163 |
+
"step": 1510
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 6.58008658008658,
|
| 1167 |
+
"grad_norm": 0.07900078594684601,
|
| 1168 |
+
"learning_rate": 1.0048115477145149e-05,
|
| 1169 |
+
"loss": 0.0339710533618927,
|
| 1170 |
+
"step": 1520
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 6.623376623376624,
|
| 1174 |
+
"grad_norm": 7.394096374511719,
|
| 1175 |
+
"learning_rate": 9.967923015236569e-06,
|
| 1176 |
+
"loss": 0.02919152081012726,
|
| 1177 |
+
"step": 1530
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 6.666666666666667,
|
| 1181 |
+
"grad_norm": 0.18829531967639923,
|
| 1182 |
+
"learning_rate": 9.887730553327989e-06,
|
| 1183 |
+
"loss": 0.019558291137218475,
|
| 1184 |
+
"step": 1540
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 6.70995670995671,
|
| 1188 |
+
"grad_norm": 8.413188934326172,
|
| 1189 |
+
"learning_rate": 9.807538091419407e-06,
|
| 1190 |
+
"loss": 0.04265648126602173,
|
| 1191 |
+
"step": 1550
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 6.753246753246753,
|
| 1195 |
+
"grad_norm": 0.06360296159982681,
|
| 1196 |
+
"learning_rate": 9.727345629510826e-06,
|
| 1197 |
+
"loss": 0.01586664468050003,
|
| 1198 |
+
"step": 1560
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 6.796536796536796,
|
| 1202 |
+
"grad_norm": 0.11153659969568253,
|
| 1203 |
+
"learning_rate": 9.647153167602246e-06,
|
| 1204 |
+
"loss": 0.04314278066158295,
|
| 1205 |
+
"step": 1570
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 6.83982683982684,
|
| 1209 |
+
"grad_norm": 0.05194525793194771,
|
| 1210 |
+
"learning_rate": 9.566960705693666e-06,
|
| 1211 |
+
"loss": 0.051305174827575684,
|
| 1212 |
+
"step": 1580
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.883116883116883,
|
| 1216 |
+
"grad_norm": 0.10274208337068558,
|
| 1217 |
+
"learning_rate": 9.486768243785086e-06,
|
| 1218 |
+
"loss": 0.027199384570121766,
|
| 1219 |
+
"step": 1590
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 6.926406926406926,
|
| 1223 |
+
"grad_norm": 0.10585841536521912,
|
| 1224 |
+
"learning_rate": 9.406575781876505e-06,
|
| 1225 |
+
"loss": 0.012706747651100159,
|
| 1226 |
+
"step": 1600
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 6.96969696969697,
|
| 1230 |
+
"grad_norm": 0.12696118652820587,
|
| 1231 |
+
"learning_rate": 9.326383319967924e-06,
|
| 1232 |
+
"loss": 0.02097606360912323,
|
| 1233 |
+
"step": 1610
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 7.0,
|
| 1237 |
+
"eval_f1_hate": 0.9343065693430657,
|
| 1238 |
+
"eval_f1_identity_attack": 0.9259259259259259,
|
| 1239 |
+
"eval_f1_insult": 0.9547738693467337,
|
| 1240 |
+
"eval_f1_macro": 0.9392695086064378,
|
| 1241 |
+
"eval_f1_micro": 0.9567053854276664,
|
| 1242 |
+
"eval_f1_sexual": 0.9333333333333333,
|
| 1243 |
+
"eval_f1_threat": 0.9,
|
| 1244 |
+
"eval_f1_toxicity": 0.9872773536895675,
|
| 1245 |
+
"eval_loss": 0.096724733710289,
|
| 1246 |
+
"eval_runtime": 2.4451,
|
| 1247 |
+
"eval_samples_per_second": 132.916,
|
| 1248 |
+
"eval_steps_per_second": 16.768,
|
| 1249 |
+
"step": 1617
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 7.012987012987013,
|
| 1253 |
+
"grad_norm": 8.285896301269531,
|
| 1254 |
+
"learning_rate": 9.246190858059343e-06,
|
| 1255 |
+
"loss": 0.013265588879585266,
|
| 1256 |
+
"step": 1620
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 7.0562770562770565,
|
| 1260 |
+
"grad_norm": 55.716766357421875,
|
| 1261 |
+
"learning_rate": 9.165998396150763e-06,
|
| 1262 |
+
"loss": 0.05298206806182861,
|
| 1263 |
+
"step": 1630
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 7.0995670995671,
|
| 1267 |
+
"grad_norm": 0.0616360642015934,
|
| 1268 |
+
"learning_rate": 9.085805934242183e-06,
|
| 1269 |
+
"loss": 0.013892856240272523,
|
| 1270 |
+
"step": 1640
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 7.142857142857143,
|
| 1274 |
+
"grad_norm": 0.11775124818086624,
|
| 1275 |
+
"learning_rate": 9.005613472333601e-06,
|
| 1276 |
+
"loss": 0.02527049481868744,
|
| 1277 |
+
"step": 1650
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 7.186147186147186,
|
| 1281 |
+
"grad_norm": 0.12172091752290726,
|
| 1282 |
+
"learning_rate": 8.92542101042502e-06,
|
| 1283 |
+
"loss": 0.016150999069213866,
|
| 1284 |
+
"step": 1660
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 7.229437229437229,
|
| 1288 |
+
"grad_norm": 233.70913696289062,
|
| 1289 |
+
"learning_rate": 8.84522854851644e-06,
|
| 1290 |
+
"loss": 0.03750343322753906,
|
| 1291 |
+
"step": 1670
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 7.2727272727272725,
|
| 1295 |
+
"grad_norm": 0.19130665063858032,
|
| 1296 |
+
"learning_rate": 8.76503608660786e-06,
|
| 1297 |
+
"loss": 0.047661423683166504,
|
| 1298 |
+
"step": 1680
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 7.316017316017316,
|
| 1302 |
+
"grad_norm": 0.5913139581680298,
|
| 1303 |
+
"learning_rate": 8.684843624699278e-06,
|
| 1304 |
+
"loss": 0.058721184730529785,
|
| 1305 |
+
"step": 1690
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 7.359307359307359,
|
| 1309 |
+
"grad_norm": 0.11178971081972122,
|
| 1310 |
+
"learning_rate": 8.604651162790698e-06,
|
| 1311 |
+
"loss": 0.019251981377601625,
|
| 1312 |
+
"step": 1700
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 7.402597402597403,
|
| 1316 |
+
"grad_norm": 0.7590028643608093,
|
| 1317 |
+
"learning_rate": 8.524458700882118e-06,
|
| 1318 |
+
"loss": 0.04656476080417633,
|
| 1319 |
+
"step": 1710
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 7.445887445887446,
|
| 1323 |
+
"grad_norm": 0.11145845055580139,
|
| 1324 |
+
"learning_rate": 8.444266238973538e-06,
|
| 1325 |
+
"loss": 0.04233784377574921,
|
| 1326 |
+
"step": 1720
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 7.489177489177489,
|
| 1330 |
+
"grad_norm": 0.06500884890556335,
|
| 1331 |
+
"learning_rate": 8.364073777064956e-06,
|
| 1332 |
+
"loss": 0.017232677340507506,
|
| 1333 |
+
"step": 1730
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 7.532467532467533,
|
| 1337 |
+
"grad_norm": 0.2547213137149811,
|
| 1338 |
+
"learning_rate": 8.283881315156376e-06,
|
| 1339 |
+
"loss": 0.032582181692123416,
|
| 1340 |
+
"step": 1740
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 7.575757575757576,
|
| 1344 |
+
"grad_norm": 0.12454051524400711,
|
| 1345 |
+
"learning_rate": 8.203688853247795e-06,
|
| 1346 |
+
"loss": 0.011076736450195312,
|
| 1347 |
+
"step": 1750
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 7.619047619047619,
|
| 1351 |
+
"grad_norm": 0.07941589504480362,
|
| 1352 |
+
"learning_rate": 8.123496391339215e-06,
|
| 1353 |
+
"loss": 0.03252111673355103,
|
| 1354 |
+
"step": 1760
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 7.662337662337662,
|
| 1358 |
+
"grad_norm": 0.06445322930812836,
|
| 1359 |
+
"learning_rate": 8.043303929430633e-06,
|
| 1360 |
+
"loss": 0.02210572212934494,
|
| 1361 |
+
"step": 1770
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 7.705627705627705,
|
| 1365 |
+
"grad_norm": 0.09489136934280396,
|
| 1366 |
+
"learning_rate": 7.963111467522053e-06,
|
| 1367 |
+
"loss": 0.02158440500497818,
|
| 1368 |
+
"step": 1780
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 7.748917748917749,
|
| 1372 |
+
"grad_norm": 1.2053515911102295,
|
| 1373 |
+
"learning_rate": 7.882919005613473e-06,
|
| 1374 |
+
"loss": 0.010548257827758789,
|
| 1375 |
+
"step": 1790
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 7.792207792207792,
|
| 1379 |
+
"grad_norm": 0.10824225842952728,
|
| 1380 |
+
"learning_rate": 7.802726543704892e-06,
|
| 1381 |
+
"loss": 0.02837684452533722,
|
| 1382 |
+
"step": 1800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 7.8354978354978355,
|
| 1386 |
+
"grad_norm": 0.19801065325737,
|
| 1387 |
+
"learning_rate": 7.72253408179631e-06,
|
| 1388 |
+
"loss": 0.03580955862998962,
|
| 1389 |
+
"step": 1810
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 7.878787878787879,
|
| 1393 |
+
"grad_norm": 0.045844487845897675,
|
| 1394 |
+
"learning_rate": 7.64234161988773e-06,
|
| 1395 |
+
"loss": 0.008237843215465546,
|
| 1396 |
+
"step": 1820
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 7.922077922077922,
|
| 1400 |
+
"grad_norm": 0.06215677782893181,
|
| 1401 |
+
"learning_rate": 7.562149157979151e-06,
|
| 1402 |
+
"loss": 0.017115187644958497,
|
| 1403 |
+
"step": 1830
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 7.965367965367966,
|
| 1407 |
+
"grad_norm": 1.7800884246826172,
|
| 1408 |
+
"learning_rate": 7.481956696070571e-06,
|
| 1409 |
+
"loss": 0.02911553680896759,
|
| 1410 |
+
"step": 1840
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 8.0,
|
| 1414 |
+
"eval_f1_hate": 0.948905109489051,
|
| 1415 |
+
"eval_f1_identity_attack": 0.9259259259259259,
|
| 1416 |
+
"eval_f1_insult": 0.9603960396039604,
|
| 1417 |
+
"eval_f1_macro": 0.9664512006521,
|
| 1418 |
+
"eval_f1_micro": 0.9693121693121693,
|
| 1419 |
+
"eval_f1_sexual": 1.0,
|
| 1420 |
+
"eval_f1_threat": 0.9736842105263158,
|
| 1421 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1422 |
+
"eval_loss": 0.07348332554101944,
|
| 1423 |
+
"eval_runtime": 2.4382,
|
| 1424 |
+
"eval_samples_per_second": 133.294,
|
| 1425 |
+
"eval_steps_per_second": 16.815,
|
| 1426 |
+
"step": 1848
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 8.008658008658008,
|
| 1430 |
+
"grad_norm": 0.5656646490097046,
|
| 1431 |
+
"learning_rate": 7.401764234161989e-06,
|
| 1432 |
+
"loss": 0.008289340138435363,
|
| 1433 |
+
"step": 1850
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 8.051948051948052,
|
| 1437 |
+
"grad_norm": 0.05726471543312073,
|
| 1438 |
+
"learning_rate": 7.3215717722534086e-06,
|
| 1439 |
+
"loss": 0.007889867573976517,
|
| 1440 |
+
"step": 1860
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 8.095238095238095,
|
| 1444 |
+
"grad_norm": 0.039329830557107925,
|
| 1445 |
+
"learning_rate": 7.241379310344828e-06,
|
| 1446 |
+
"loss": 0.009552600979804992,
|
| 1447 |
+
"step": 1870
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 8.13852813852814,
|
| 1451 |
+
"grad_norm": 0.051925044506788254,
|
| 1452 |
+
"learning_rate": 7.161186848436248e-06,
|
| 1453 |
+
"loss": 0.009062138944864273,
|
| 1454 |
+
"step": 1880
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 8.181818181818182,
|
| 1458 |
+
"grad_norm": 1.3687405586242676,
|
| 1459 |
+
"learning_rate": 7.080994386527666e-06,
|
| 1460 |
+
"loss": 0.039984285831451416,
|
| 1461 |
+
"step": 1890
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 8.225108225108226,
|
| 1465 |
+
"grad_norm": 0.07175378501415253,
|
| 1466 |
+
"learning_rate": 7.000801924619086e-06,
|
| 1467 |
+
"loss": 0.009197700768709183,
|
| 1468 |
+
"step": 1900
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 8.268398268398268,
|
| 1472 |
+
"grad_norm": 3.0823709964752197,
|
| 1473 |
+
"learning_rate": 6.920609462710506e-06,
|
| 1474 |
+
"loss": 0.010183989256620406,
|
| 1475 |
+
"step": 1910
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 8.311688311688311,
|
| 1479 |
+
"grad_norm": 0.0992533341050148,
|
| 1480 |
+
"learning_rate": 6.8404170008019255e-06,
|
| 1481 |
+
"loss": 0.008255717903375625,
|
| 1482 |
+
"step": 1920
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 8.354978354978355,
|
| 1486 |
+
"grad_norm": 0.058967746794223785,
|
| 1487 |
+
"learning_rate": 6.7602245388933444e-06,
|
| 1488 |
+
"loss": 0.016507762670516967,
|
| 1489 |
+
"step": 1930
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 8.398268398268398,
|
| 1493 |
+
"grad_norm": 0.7071771025657654,
|
| 1494 |
+
"learning_rate": 6.680032076984763e-06,
|
| 1495 |
+
"loss": 0.018038202822208405,
|
| 1496 |
+
"step": 1940
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 8.441558441558442,
|
| 1500 |
+
"grad_norm": 0.05050427466630936,
|
| 1501 |
+
"learning_rate": 6.599839615076183e-06,
|
| 1502 |
+
"loss": 0.03205050230026245,
|
| 1503 |
+
"step": 1950
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 8.484848484848484,
|
| 1507 |
+
"grad_norm": 0.05392308533191681,
|
| 1508 |
+
"learning_rate": 6.519647153167603e-06,
|
| 1509 |
+
"loss": 0.03979974389076233,
|
| 1510 |
+
"step": 1960
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 8.528138528138529,
|
| 1514 |
+
"grad_norm": 5.338536739349365,
|
| 1515 |
+
"learning_rate": 6.439454691259022e-06,
|
| 1516 |
+
"loss": 0.010501711070537567,
|
| 1517 |
+
"step": 1970
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 8.571428571428571,
|
| 1521 |
+
"grad_norm": 0.0416489876806736,
|
| 1522 |
+
"learning_rate": 6.359262229350442e-06,
|
| 1523 |
+
"loss": 0.008546990901231765,
|
| 1524 |
+
"step": 1980
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 8.614718614718615,
|
| 1528 |
+
"grad_norm": 0.03366857394576073,
|
| 1529 |
+
"learning_rate": 6.279069767441861e-06,
|
| 1530 |
+
"loss": 0.007867447286844253,
|
| 1531 |
+
"step": 1990
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 8.658008658008658,
|
| 1535 |
+
"grad_norm": 0.0408504493534565,
|
| 1536 |
+
"learning_rate": 6.19887730553328e-06,
|
| 1537 |
+
"loss": 0.009638544172048569,
|
| 1538 |
+
"step": 2000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 8.7012987012987,
|
| 1542 |
+
"grad_norm": 0.5971854329109192,
|
| 1543 |
+
"learning_rate": 6.118684843624699e-06,
|
| 1544 |
+
"loss": 0.02221200317144394,
|
| 1545 |
+
"step": 2010
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 8.744588744588745,
|
| 1549 |
+
"grad_norm": 0.16346342861652374,
|
| 1550 |
+
"learning_rate": 6.038492381716119e-06,
|
| 1551 |
+
"loss": 0.016023994982242586,
|
| 1552 |
+
"step": 2020
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 8.787878787878787,
|
| 1556 |
+
"grad_norm": 104.31558990478516,
|
| 1557 |
+
"learning_rate": 5.958299919807539e-06,
|
| 1558 |
+
"loss": 0.028461986780166627,
|
| 1559 |
+
"step": 2030
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 8.831168831168831,
|
| 1563 |
+
"grad_norm": 0.04544289410114288,
|
| 1564 |
+
"learning_rate": 5.8781074578989585e-06,
|
| 1565 |
+
"loss": 0.007379808276891708,
|
| 1566 |
+
"step": 2040
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 8.874458874458874,
|
| 1570 |
+
"grad_norm": 0.07683689892292023,
|
| 1571 |
+
"learning_rate": 5.797914995990377e-06,
|
| 1572 |
+
"loss": 0.008033422380685806,
|
| 1573 |
+
"step": 2050
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 8.917748917748918,
|
| 1577 |
+
"grad_norm": 0.09097876399755478,
|
| 1578 |
+
"learning_rate": 5.717722534081796e-06,
|
| 1579 |
+
"loss": 0.007979495823383332,
|
| 1580 |
+
"step": 2060
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 8.96103896103896,
|
| 1584 |
+
"grad_norm": 0.04881996661424637,
|
| 1585 |
+
"learning_rate": 5.637530072173216e-06,
|
| 1586 |
+
"loss": 0.014459139108657837,
|
| 1587 |
+
"step": 2070
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 9.0,
|
| 1591 |
+
"eval_f1_hate": 0.9496402877697842,
|
| 1592 |
+
"eval_f1_identity_attack": 0.9272727272727272,
|
| 1593 |
+
"eval_f1_insult": 0.970873786407767,
|
| 1594 |
+
"eval_f1_macro": 0.9617095463461544,
|
| 1595 |
+
"eval_f1_micro": 0.9676746611053181,
|
| 1596 |
+
"eval_f1_sexual": 1.0,
|
| 1597 |
+
"eval_f1_threat": 0.935064935064935,
|
| 1598 |
+
"eval_f1_toxicity": 0.9874055415617129,
|
| 1599 |
+
"eval_loss": 0.06829648464918137,
|
| 1600 |
+
"eval_runtime": 2.5638,
|
| 1601 |
+
"eval_samples_per_second": 126.766,
|
| 1602 |
+
"eval_steps_per_second": 15.992,
|
| 1603 |
+
"step": 2079
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 9.004329004329005,
|
| 1607 |
+
"grad_norm": 0.10560577362775803,
|
| 1608 |
+
"learning_rate": 5.557337610264636e-06,
|
| 1609 |
+
"loss": 0.01639609634876251,
|
| 1610 |
+
"step": 2080
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 9.047619047619047,
|
| 1614 |
+
"grad_norm": 0.06842140108346939,
|
| 1615 |
+
"learning_rate": 5.477145148356055e-06,
|
| 1616 |
+
"loss": 0.027546045184135438,
|
| 1617 |
+
"step": 2090
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 9.090909090909092,
|
| 1621 |
+
"grad_norm": 0.380849689245224,
|
| 1622 |
+
"learning_rate": 5.396952686447474e-06,
|
| 1623 |
+
"loss": 0.00970921739935875,
|
| 1624 |
+
"step": 2100
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 9.134199134199134,
|
| 1628 |
+
"grad_norm": 0.06947353482246399,
|
| 1629 |
+
"learning_rate": 5.3167602245388936e-06,
|
| 1630 |
+
"loss": 0.006932146847248077,
|
| 1631 |
+
"step": 2110
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 9.177489177489177,
|
| 1635 |
+
"grad_norm": 0.05276697501540184,
|
| 1636 |
+
"learning_rate": 5.236567762630313e-06,
|
| 1637 |
+
"loss": 0.0077086232602596285,
|
| 1638 |
+
"step": 2120
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 9.220779220779221,
|
| 1642 |
+
"grad_norm": 0.03769112378358841,
|
| 1643 |
+
"learning_rate": 5.156375300721732e-06,
|
| 1644 |
+
"loss": 0.031344258785247804,
|
| 1645 |
+
"step": 2130
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 9.264069264069263,
|
| 1649 |
+
"grad_norm": 0.0876459851861,
|
| 1650 |
+
"learning_rate": 5.076182838813152e-06,
|
| 1651 |
+
"loss": 0.015288634598255158,
|
| 1652 |
+
"step": 2140
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 9.307359307359308,
|
| 1656 |
+
"grad_norm": 0.043145306408405304,
|
| 1657 |
+
"learning_rate": 4.995990376904572e-06,
|
| 1658 |
+
"loss": 0.011774497479200364,
|
| 1659 |
+
"step": 2150
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 9.35064935064935,
|
| 1663 |
+
"grad_norm": 0.038514334708452225,
|
| 1664 |
+
"learning_rate": 4.915797914995991e-06,
|
| 1665 |
+
"loss": 0.006795006990432739,
|
| 1666 |
+
"step": 2160
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 9.393939393939394,
|
| 1670 |
+
"grad_norm": 0.08487548679113388,
|
| 1671 |
+
"learning_rate": 4.8356054530874105e-06,
|
| 1672 |
+
"loss": 0.009026169031858444,
|
| 1673 |
+
"step": 2170
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 9.437229437229437,
|
| 1677 |
+
"grad_norm": 0.04390149191021919,
|
| 1678 |
+
"learning_rate": 4.7554129911788294e-06,
|
| 1679 |
+
"loss": 0.006690967828035355,
|
| 1680 |
+
"step": 2180
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 9.480519480519481,
|
| 1684 |
+
"grad_norm": 0.038950540125370026,
|
| 1685 |
+
"learning_rate": 4.675220529270249e-06,
|
| 1686 |
+
"loss": 0.0060188788920640945,
|
| 1687 |
+
"step": 2190
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 9.523809523809524,
|
| 1691 |
+
"grad_norm": 0.642978847026825,
|
| 1692 |
+
"learning_rate": 4.595028067361668e-06,
|
| 1693 |
+
"loss": 0.022261470556259155,
|
| 1694 |
+
"step": 2200
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 9.567099567099568,
|
| 1698 |
+
"grad_norm": 0.052926789969205856,
|
| 1699 |
+
"learning_rate": 4.514835605453088e-06,
|
| 1700 |
+
"loss": 0.03473313748836517,
|
| 1701 |
+
"step": 2210
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 9.61038961038961,
|
| 1705 |
+
"grad_norm": 0.22621260583400726,
|
| 1706 |
+
"learning_rate": 4.434643143544507e-06,
|
| 1707 |
+
"loss": 0.006864982843399048,
|
| 1708 |
+
"step": 2220
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 9.653679653679653,
|
| 1712 |
+
"grad_norm": 0.0267812330275774,
|
| 1713 |
+
"learning_rate": 4.354450681635927e-06,
|
| 1714 |
+
"loss": 0.007071622461080551,
|
| 1715 |
+
"step": 2230
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 9.696969696969697,
|
| 1719 |
+
"grad_norm": 0.060379091650247574,
|
| 1720 |
+
"learning_rate": 4.2742582197273455e-06,
|
| 1721 |
+
"loss": 0.007905981689691543,
|
| 1722 |
+
"step": 2240
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 9.74025974025974,
|
| 1726 |
+
"grad_norm": 0.043072640895843506,
|
| 1727 |
+
"learning_rate": 4.194065757818765e-06,
|
| 1728 |
+
"loss": 0.008212245255708694,
|
| 1729 |
+
"step": 2250
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 9.783549783549784,
|
| 1733 |
+
"grad_norm": 0.06793437898159027,
|
| 1734 |
+
"learning_rate": 4.113873295910184e-06,
|
| 1735 |
+
"loss": 0.00838496834039688,
|
| 1736 |
+
"step": 2260
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 9.826839826839826,
|
| 1740 |
+
"grad_norm": 0.21440571546554565,
|
| 1741 |
+
"learning_rate": 4.033680834001604e-06,
|
| 1742 |
+
"loss": 0.01173497959971428,
|
| 1743 |
+
"step": 2270
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 9.87012987012987,
|
| 1747 |
+
"grad_norm": 0.07421120256185532,
|
| 1748 |
+
"learning_rate": 3.953488372093024e-06,
|
| 1749 |
+
"loss": 0.008673172444105148,
|
| 1750 |
+
"step": 2280
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 9.913419913419913,
|
| 1754 |
+
"grad_norm": 0.05863242223858833,
|
| 1755 |
+
"learning_rate": 3.873295910184443e-06,
|
| 1756 |
+
"loss": 0.006766989827156067,
|
| 1757 |
+
"step": 2290
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 9.956709956709958,
|
| 1761 |
+
"grad_norm": 0.7983549237251282,
|
| 1762 |
+
"learning_rate": 3.793103448275862e-06,
|
| 1763 |
+
"loss": 0.007381130754947662,
|
| 1764 |
+
"step": 2300
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 10.0,
|
| 1768 |
+
"grad_norm": 0.03677091374993324,
|
| 1769 |
+
"learning_rate": 3.712910986367282e-06,
|
| 1770 |
+
"loss": 0.00792955756187439,
|
| 1771 |
+
"step": 2310
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 10.0,
|
| 1775 |
+
"eval_f1_hate": 0.9496402877697842,
|
| 1776 |
+
"eval_f1_identity_attack": 0.9357798165137615,
|
| 1777 |
+
"eval_f1_insult": 0.9702970297029703,
|
| 1778 |
+
"eval_f1_macro": 0.9654802455677491,
|
| 1779 |
+
"eval_f1_micro": 0.9704641350210971,
|
| 1780 |
+
"eval_f1_sexual": 1.0,
|
| 1781 |
+
"eval_f1_threat": 0.9473684210526315,
|
| 1782 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1783 |
+
"eval_loss": 0.06511212140321732,
|
| 1784 |
+
"eval_runtime": 2.45,
|
| 1785 |
+
"eval_samples_per_second": 132.655,
|
| 1786 |
+
"eval_steps_per_second": 16.735,
|
| 1787 |
+
"step": 2310
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 10.043290043290042,
|
| 1791 |
+
"grad_norm": 0.03262697532773018,
|
| 1792 |
+
"learning_rate": 3.632718524458701e-06,
|
| 1793 |
+
"loss": 0.017550432682037355,
|
| 1794 |
+
"step": 2320
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 10.086580086580087,
|
| 1798 |
+
"grad_norm": 0.15889312326908112,
|
| 1799 |
+
"learning_rate": 3.5525260625501205e-06,
|
| 1800 |
+
"loss": 0.009385860711336135,
|
| 1801 |
+
"step": 2330
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 10.12987012987013,
|
| 1805 |
+
"grad_norm": 0.03570404648780823,
|
| 1806 |
+
"learning_rate": 3.47233360064154e-06,
|
| 1807 |
+
"loss": 0.006462970376014709,
|
| 1808 |
+
"step": 2340
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 10.173160173160174,
|
| 1812 |
+
"grad_norm": 0.05796288326382637,
|
| 1813 |
+
"learning_rate": 3.3921411387329597e-06,
|
| 1814 |
+
"loss": 0.034926030039787295,
|
| 1815 |
+
"step": 2350
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 10.216450216450216,
|
| 1819 |
+
"grad_norm": 0.04328539967536926,
|
| 1820 |
+
"learning_rate": 3.3119486768243786e-06,
|
| 1821 |
+
"loss": 0.007092902064323425,
|
| 1822 |
+
"step": 2360
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 10.25974025974026,
|
| 1826 |
+
"grad_norm": 0.03778962790966034,
|
| 1827 |
+
"learning_rate": 3.2317562149157984e-06,
|
| 1828 |
+
"loss": 0.014847326278686523,
|
| 1829 |
+
"step": 2370
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 10.303030303030303,
|
| 1833 |
+
"grad_norm": 0.20529219508171082,
|
| 1834 |
+
"learning_rate": 3.1515637530072173e-06,
|
| 1835 |
+
"loss": 0.016094820201396944,
|
| 1836 |
+
"step": 2380
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 10.346320346320347,
|
| 1840 |
+
"grad_norm": 0.06534869968891144,
|
| 1841 |
+
"learning_rate": 3.071371291098637e-06,
|
| 1842 |
+
"loss": 0.006908760219812393,
|
| 1843 |
+
"step": 2390
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 10.38961038961039,
|
| 1847 |
+
"grad_norm": 0.05771664157509804,
|
| 1848 |
+
"learning_rate": 2.991178829190056e-06,
|
| 1849 |
+
"loss": 0.00651869922876358,
|
| 1850 |
+
"step": 2400
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 10.432900432900432,
|
| 1854 |
+
"grad_norm": 0.07073244452476501,
|
| 1855 |
+
"learning_rate": 2.9109863672814758e-06,
|
| 1856 |
+
"loss": 0.01936003863811493,
|
| 1857 |
+
"step": 2410
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 10.476190476190476,
|
| 1861 |
+
"grad_norm": 0.027323178946971893,
|
| 1862 |
+
"learning_rate": 2.830793905372895e-06,
|
| 1863 |
+
"loss": 0.010300172865390778,
|
| 1864 |
+
"step": 2420
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 10.519480519480519,
|
| 1868 |
+
"grad_norm": 0.10109654068946838,
|
| 1869 |
+
"learning_rate": 2.7506014434643145e-06,
|
| 1870 |
+
"loss": 0.00660090297460556,
|
| 1871 |
+
"step": 2430
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 10.562770562770563,
|
| 1875 |
+
"grad_norm": 0.025898031890392303,
|
| 1876 |
+
"learning_rate": 2.670408981555734e-06,
|
| 1877 |
+
"loss": 0.008827462792396545,
|
| 1878 |
+
"step": 2440
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 10.606060606060606,
|
| 1882 |
+
"grad_norm": 0.03746366500854492,
|
| 1883 |
+
"learning_rate": 2.5902165196471536e-06,
|
| 1884 |
+
"loss": 0.006242872774600982,
|
| 1885 |
+
"step": 2450
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 10.64935064935065,
|
| 1889 |
+
"grad_norm": 0.027787530794739723,
|
| 1890 |
+
"learning_rate": 2.5100240577385725e-06,
|
| 1891 |
+
"loss": 0.008383957296609878,
|
| 1892 |
+
"step": 2460
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 10.692640692640692,
|
| 1896 |
+
"grad_norm": 0.08420351892709732,
|
| 1897 |
+
"learning_rate": 2.4298315958299923e-06,
|
| 1898 |
+
"loss": 0.007070781290531158,
|
| 1899 |
+
"step": 2470
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 10.735930735930737,
|
| 1903 |
+
"grad_norm": 0.03632546588778496,
|
| 1904 |
+
"learning_rate": 2.3496391339214116e-06,
|
| 1905 |
+
"loss": 0.033319640159606936,
|
| 1906 |
+
"step": 2480
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 10.779220779220779,
|
| 1910 |
+
"grad_norm": 0.3003116548061371,
|
| 1911 |
+
"learning_rate": 2.269446672012831e-06,
|
| 1912 |
+
"loss": 0.006795042008161545,
|
| 1913 |
+
"step": 2490
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 10.822510822510823,
|
| 1917 |
+
"grad_norm": 0.030215242877602577,
|
| 1918 |
+
"learning_rate": 2.1892542101042503e-06,
|
| 1919 |
+
"loss": 0.007315768301486969,
|
| 1920 |
+
"step": 2500
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 10.865800865800866,
|
| 1924 |
+
"grad_norm": 0.03005411848425865,
|
| 1925 |
+
"learning_rate": 2.1090617481956697e-06,
|
| 1926 |
+
"loss": 0.007162563502788544,
|
| 1927 |
+
"step": 2510
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 10.909090909090908,
|
| 1931 |
+
"grad_norm": 0.03618185967206955,
|
| 1932 |
+
"learning_rate": 2.0288692862870895e-06,
|
| 1933 |
+
"loss": 0.006317664682865143,
|
| 1934 |
+
"step": 2520
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 10.952380952380953,
|
| 1938 |
+
"grad_norm": 0.0410848893225193,
|
| 1939 |
+
"learning_rate": 1.948676824378509e-06,
|
| 1940 |
+
"loss": 0.0280388206243515,
|
| 1941 |
+
"step": 2530
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 10.995670995670995,
|
| 1945 |
+
"grad_norm": 0.11858250945806503,
|
| 1946 |
+
"learning_rate": 1.8684843624699282e-06,
|
| 1947 |
+
"loss": 0.009880727529525757,
|
| 1948 |
+
"step": 2540
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 11.0,
|
| 1952 |
+
"eval_f1_hate": 0.9565217391304348,
|
| 1953 |
+
"eval_f1_identity_attack": 0.9444444444444444,
|
| 1954 |
+
"eval_f1_insult": 0.9702970297029703,
|
| 1955 |
+
"eval_f1_macro": 0.9680712587829715,
|
| 1956 |
+
"eval_f1_micro": 0.9725158562367865,
|
| 1957 |
+
"eval_f1_sexual": 1.0,
|
| 1958 |
+
"eval_f1_threat": 0.9473684210526315,
|
| 1959 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1960 |
+
"eval_loss": 0.061376653611660004,
|
| 1961 |
+
"eval_runtime": 2.5087,
|
| 1962 |
+
"eval_samples_per_second": 129.551,
|
| 1963 |
+
"eval_steps_per_second": 16.343,
|
| 1964 |
+
"step": 2541
|
| 1965 |
+
}
|
| 1966 |
+
],
|
| 1967 |
+
"logging_steps": 10,
|
| 1968 |
+
"max_steps": 2772,
|
| 1969 |
+
"num_input_tokens_seen": 0,
|
| 1970 |
+
"num_train_epochs": 12,
|
| 1971 |
+
"save_steps": 500,
|
| 1972 |
+
"stateful_callbacks": {
|
| 1973 |
+
"TrainerControl": {
|
| 1974 |
+
"args": {
|
| 1975 |
+
"should_epoch_stop": false,
|
| 1976 |
+
"should_evaluate": false,
|
| 1977 |
+
"should_log": false,
|
| 1978 |
+
"should_save": true,
|
| 1979 |
+
"should_training_stop": false
|
| 1980 |
+
},
|
| 1981 |
+
"attributes": {}
|
| 1982 |
+
}
|
| 1983 |
+
},
|
| 1984 |
+
"total_flos": 1332113335838208.0,
|
| 1985 |
+
"train_batch_size": 8,
|
| 1986 |
+
"trial_name": null,
|
| 1987 |
+
"trial_params": null
|
| 1988 |
+
}
|
checkpoint-2541/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a69174491030931c18f76759e2267cecfc7446af536f338aa4983fbf2de13b9
|
| 3 |
+
size 5265
|
checkpoint-2772/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 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": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"is_decoder": false,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-05,
|
| 34 |
+
"max_position_embeddings": 514,
|
| 35 |
+
"model_type": "xlm-roberta",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"output_past": true,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "multi_label_classification",
|
| 42 |
+
"tie_word_embeddings": true,
|
| 43 |
+
"transformers_version": "5.2.0",
|
| 44 |
+
"type_vocab_size": 1,
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 250002
|
| 47 |
+
}
|
checkpoint-2772/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1212bfb8edecdc0b19b88680bba6cbe8595f45ef2a8c900cff6ecc3ea49da3
|
| 3 |
+
size 1112217288
|
checkpoint-2772/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e1568d8f22869b57551b0298e76b88414e9ab89a74b008e44f9c240c39794c6
|
| 3 |
+
size 2224549003
|
checkpoint-2772/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2324c9b9aecc9bce74c28230a402aa08935690df2032dcf4cba833a84a3ff4a
|
| 3 |
+
size 14455
|
checkpoint-2772/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:230d3da5f0a00ff2e9e230856b29111dccf072a6d721ac733c8a2ea08088b01c
|
| 3 |
+
size 1465
|
checkpoint-2772/trainer_state.json
ADDED
|
@@ -0,0 +1,2165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2772,
|
| 3 |
+
"best_metric": 0.9789915966386554,
|
| 4 |
+
"best_model_checkpoint": "/Users/loule/Documents/Projets Dev/Git/Egide/apps/ai-service/../../models/egide-toxicity-model/checkpoint-2772",
|
| 5 |
+
"epoch": 12.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2772,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04329004329004329,
|
| 14 |
+
"grad_norm": 1.9666005373001099,
|
| 15 |
+
"learning_rate": 6.474820143884893e-07,
|
| 16 |
+
"loss": 0.6904128551483154,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08658008658008658,
|
| 21 |
+
"grad_norm": 1.5532240867614746,
|
| 22 |
+
"learning_rate": 1.366906474820144e-06,
|
| 23 |
+
"loss": 0.6828486442565918,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.12987012987012986,
|
| 28 |
+
"grad_norm": 1.9879132509231567,
|
| 29 |
+
"learning_rate": 2.0863309352517987e-06,
|
| 30 |
+
"loss": 0.6761202335357666,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.17316017316017315,
|
| 35 |
+
"grad_norm": 1.8693434000015259,
|
| 36 |
+
"learning_rate": 2.805755395683453e-06,
|
| 37 |
+
"loss": 0.6731895923614502,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21645021645021645,
|
| 42 |
+
"grad_norm": 2.021498918533325,
|
| 43 |
+
"learning_rate": 3.525179856115108e-06,
|
| 44 |
+
"loss": 0.6719329357147217,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2597402597402597,
|
| 49 |
+
"grad_norm": 8.98990249633789,
|
| 50 |
+
"learning_rate": 4.244604316546763e-06,
|
| 51 |
+
"loss": 0.6427541255950928,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.30303030303030304,
|
| 56 |
+
"grad_norm": 5.401233196258545,
|
| 57 |
+
"learning_rate": 4.9640287769784175e-06,
|
| 58 |
+
"loss": 0.61961669921875,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3463203463203463,
|
| 63 |
+
"grad_norm": 8.536731719970703,
|
| 64 |
+
"learning_rate": 5.683453237410073e-06,
|
| 65 |
+
"loss": 0.6018109321594238,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.38961038961038963,
|
| 70 |
+
"grad_norm": 5.487812042236328,
|
| 71 |
+
"learning_rate": 6.402877697841727e-06,
|
| 72 |
+
"loss": 0.5745875358581543,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4329004329004329,
|
| 77 |
+
"grad_norm": 4.356001377105713,
|
| 78 |
+
"learning_rate": 7.122302158273382e-06,
|
| 79 |
+
"loss": 0.5471229076385498,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.47619047619047616,
|
| 84 |
+
"grad_norm": 6.982844829559326,
|
| 85 |
+
"learning_rate": 7.841726618705036e-06,
|
| 86 |
+
"loss": 0.5099374771118164,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5194805194805194,
|
| 91 |
+
"grad_norm": 1.8694194555282593,
|
| 92 |
+
"learning_rate": 8.561151079136692e-06,
|
| 93 |
+
"loss": 0.5038644790649414,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5627705627705628,
|
| 98 |
+
"grad_norm": 3.096836805343628,
|
| 99 |
+
"learning_rate": 9.280575539568346e-06,
|
| 100 |
+
"loss": 0.5061714172363281,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6060606060606061,
|
| 105 |
+
"grad_norm": 1.9763317108154297,
|
| 106 |
+
"learning_rate": 1e-05,
|
| 107 |
+
"loss": 0.5091361999511719,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6493506493506493,
|
| 112 |
+
"grad_norm": 6.211313247680664,
|
| 113 |
+
"learning_rate": 1.0719424460431655e-05,
|
| 114 |
+
"loss": 0.48816370964050293,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.6926406926406926,
|
| 119 |
+
"grad_norm": 1.5845985412597656,
|
| 120 |
+
"learning_rate": 1.143884892086331e-05,
|
| 121 |
+
"loss": 0.4852591037750244,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7359307359307359,
|
| 126 |
+
"grad_norm": 4.810131549835205,
|
| 127 |
+
"learning_rate": 1.2158273381294966e-05,
|
| 128 |
+
"loss": 0.4814936637878418,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7792207792207793,
|
| 133 |
+
"grad_norm": 2.836341142654419,
|
| 134 |
+
"learning_rate": 1.287769784172662e-05,
|
| 135 |
+
"loss": 0.5129002571105957,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.8225108225108225,
|
| 140 |
+
"grad_norm": 1.2342458963394165,
|
| 141 |
+
"learning_rate": 1.3597122302158274e-05,
|
| 142 |
+
"loss": 0.4621418952941895,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8658008658008658,
|
| 147 |
+
"grad_norm": 2.936840295791626,
|
| 148 |
+
"learning_rate": 1.4316546762589929e-05,
|
| 149 |
+
"loss": 0.4222285270690918,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.9090909090909091,
|
| 154 |
+
"grad_norm": 2.36641526222229,
|
| 155 |
+
"learning_rate": 1.5035971223021583e-05,
|
| 156 |
+
"loss": 0.4732527732849121,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.9523809523809523,
|
| 161 |
+
"grad_norm": 2.6311023235321045,
|
| 162 |
+
"learning_rate": 1.5755395683453238e-05,
|
| 163 |
+
"loss": 0.47931723594665526,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9956709956709957,
|
| 168 |
+
"grad_norm": 1.7854502201080322,
|
| 169 |
+
"learning_rate": 1.6474820143884892e-05,
|
| 170 |
+
"loss": 0.4703701019287109,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0,
|
| 175 |
+
"eval_f1_hate": 0.0,
|
| 176 |
+
"eval_f1_identity_attack": 0.0,
|
| 177 |
+
"eval_f1_insult": 0.0,
|
| 178 |
+
"eval_f1_macro": 0.12619502868068835,
|
| 179 |
+
"eval_f1_micro": 0.4937655860349127,
|
| 180 |
+
"eval_f1_sexual": 0.0,
|
| 181 |
+
"eval_f1_threat": 0.0,
|
| 182 |
+
"eval_f1_toxicity": 0.7571701720841301,
|
| 183 |
+
"eval_loss": 0.45029428601264954,
|
| 184 |
+
"eval_runtime": 3.1166,
|
| 185 |
+
"eval_samples_per_second": 104.28,
|
| 186 |
+
"eval_steps_per_second": 13.155,
|
| 187 |
+
"step": 231
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.0389610389610389,
|
| 191 |
+
"grad_norm": 2.7693347930908203,
|
| 192 |
+
"learning_rate": 1.7194244604316546e-05,
|
| 193 |
+
"loss": 0.41036128997802734,
|
| 194 |
+
"step": 240
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.0822510822510822,
|
| 198 |
+
"grad_norm": 3.0557188987731934,
|
| 199 |
+
"learning_rate": 1.7913669064748204e-05,
|
| 200 |
+
"loss": 0.4664168357849121,
|
| 201 |
+
"step": 250
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.1255411255411256,
|
| 205 |
+
"grad_norm": 2.9418742656707764,
|
| 206 |
+
"learning_rate": 1.863309352517986e-05,
|
| 207 |
+
"loss": 0.46143579483032227,
|
| 208 |
+
"step": 260
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.1688311688311688,
|
| 212 |
+
"grad_norm": 3.2120885848999023,
|
| 213 |
+
"learning_rate": 1.9352517985611513e-05,
|
| 214 |
+
"loss": 0.4405516147613525,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.2121212121212122,
|
| 219 |
+
"grad_norm": 4.124722480773926,
|
| 220 |
+
"learning_rate": 1.9991980753809144e-05,
|
| 221 |
+
"loss": 0.44314141273498536,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.2554112554112553,
|
| 226 |
+
"grad_norm": 4.181340217590332,
|
| 227 |
+
"learning_rate": 1.9911788291900563e-05,
|
| 228 |
+
"loss": 0.39984827041625975,
|
| 229 |
+
"step": 290
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.2987012987012987,
|
| 233 |
+
"grad_norm": 4.350127696990967,
|
| 234 |
+
"learning_rate": 1.9831595829991984e-05,
|
| 235 |
+
"loss": 0.42529864311218263,
|
| 236 |
+
"step": 300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.341991341991342,
|
| 240 |
+
"grad_norm": 4.975383758544922,
|
| 241 |
+
"learning_rate": 1.9751403368083402e-05,
|
| 242 |
+
"loss": 0.4305525302886963,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.3852813852813852,
|
| 247 |
+
"grad_norm": 2.471064805984497,
|
| 248 |
+
"learning_rate": 1.967121090617482e-05,
|
| 249 |
+
"loss": 0.40537114143371583,
|
| 250 |
+
"step": 320
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.4285714285714286,
|
| 254 |
+
"grad_norm": 6.418680667877197,
|
| 255 |
+
"learning_rate": 1.959101844426624e-05,
|
| 256 |
+
"loss": 0.3864774703979492,
|
| 257 |
+
"step": 330
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.4718614718614718,
|
| 261 |
+
"grad_norm": 2.3995094299316406,
|
| 262 |
+
"learning_rate": 1.951082598235766e-05,
|
| 263 |
+
"loss": 0.35166306495666505,
|
| 264 |
+
"step": 340
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.5151515151515151,
|
| 268 |
+
"grad_norm": 5.420963764190674,
|
| 269 |
+
"learning_rate": 1.943063352044908e-05,
|
| 270 |
+
"loss": 0.3708444118499756,
|
| 271 |
+
"step": 350
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.5584415584415585,
|
| 275 |
+
"grad_norm": 6.72929048538208,
|
| 276 |
+
"learning_rate": 1.93504410585405e-05,
|
| 277 |
+
"loss": 0.3743911266326904,
|
| 278 |
+
"step": 360
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.601731601731602,
|
| 282 |
+
"grad_norm": 3.1479010581970215,
|
| 283 |
+
"learning_rate": 1.9270248596631917e-05,
|
| 284 |
+
"loss": 0.3563019514083862,
|
| 285 |
+
"step": 370
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.645021645021645,
|
| 289 |
+
"grad_norm": 9.571167945861816,
|
| 290 |
+
"learning_rate": 1.919005613472334e-05,
|
| 291 |
+
"loss": 0.33117449283599854,
|
| 292 |
+
"step": 380
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.6883116883116882,
|
| 296 |
+
"grad_norm": 4.24497127532959,
|
| 297 |
+
"learning_rate": 1.9109863672814757e-05,
|
| 298 |
+
"loss": 0.3223949670791626,
|
| 299 |
+
"step": 390
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.7316017316017316,
|
| 303 |
+
"grad_norm": 2.9281415939331055,
|
| 304 |
+
"learning_rate": 1.9029671210906175e-05,
|
| 305 |
+
"loss": 0.32130889892578124,
|
| 306 |
+
"step": 400
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.774891774891775,
|
| 310 |
+
"grad_norm": 15.57435131072998,
|
| 311 |
+
"learning_rate": 1.8949478748997596e-05,
|
| 312 |
+
"loss": 0.31391539573669436,
|
| 313 |
+
"step": 410
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.8181818181818183,
|
| 317 |
+
"grad_norm": 5.047284126281738,
|
| 318 |
+
"learning_rate": 1.8869286287089015e-05,
|
| 319 |
+
"loss": 0.28419616222381594,
|
| 320 |
+
"step": 420
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.8614718614718615,
|
| 324 |
+
"grad_norm": 5.080146789550781,
|
| 325 |
+
"learning_rate": 1.8789093825180436e-05,
|
| 326 |
+
"loss": 0.33582773208618166,
|
| 327 |
+
"step": 430
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.9047619047619047,
|
| 331 |
+
"grad_norm": 6.664261817932129,
|
| 332 |
+
"learning_rate": 1.8708901363271854e-05,
|
| 333 |
+
"loss": 0.38676986694335935,
|
| 334 |
+
"step": 440
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.948051948051948,
|
| 338 |
+
"grad_norm": 44.62375259399414,
|
| 339 |
+
"learning_rate": 1.8628708901363272e-05,
|
| 340 |
+
"loss": 0.3767754554748535,
|
| 341 |
+
"step": 450
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.9913419913419914,
|
| 345 |
+
"grad_norm": 5.366123199462891,
|
| 346 |
+
"learning_rate": 1.8548516439454694e-05,
|
| 347 |
+
"loss": 0.35468668937683107,
|
| 348 |
+
"step": 460
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.0,
|
| 352 |
+
"eval_f1_hate": 0.7941176470588235,
|
| 353 |
+
"eval_f1_identity_attack": 0.6972477064220184,
|
| 354 |
+
"eval_f1_insult": 0.6732673267326733,
|
| 355 |
+
"eval_f1_macro": 0.5105760349375467,
|
| 356 |
+
"eval_f1_micro": 0.7580993520518359,
|
| 357 |
+
"eval_f1_sexual": 0.0,
|
| 358 |
+
"eval_f1_threat": 0.0,
|
| 359 |
+
"eval_f1_toxicity": 0.8988235294117647,
|
| 360 |
+
"eval_loss": 0.28017890453338623,
|
| 361 |
+
"eval_runtime": 2.5637,
|
| 362 |
+
"eval_samples_per_second": 126.768,
|
| 363 |
+
"eval_steps_per_second": 15.992,
|
| 364 |
+
"step": 462
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.034632034632035,
|
| 368 |
+
"grad_norm": 4.787834167480469,
|
| 369 |
+
"learning_rate": 1.846832397754611e-05,
|
| 370 |
+
"loss": 0.2688360929489136,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0779220779220777,
|
| 375 |
+
"grad_norm": 5.352668762207031,
|
| 376 |
+
"learning_rate": 1.838813151563753e-05,
|
| 377 |
+
"loss": 0.2794922113418579,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.121212121212121,
|
| 382 |
+
"grad_norm": 7.183356761932373,
|
| 383 |
+
"learning_rate": 1.830793905372895e-05,
|
| 384 |
+
"loss": 0.2400437116622925,
|
| 385 |
+
"step": 490
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.1645021645021645,
|
| 389 |
+
"grad_norm": 3.194124221801758,
|
| 390 |
+
"learning_rate": 1.822774659182037e-05,
|
| 391 |
+
"loss": 0.2642167806625366,
|
| 392 |
+
"step": 500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.207792207792208,
|
| 396 |
+
"grad_norm": 4.878069877624512,
|
| 397 |
+
"learning_rate": 1.814755412991179e-05,
|
| 398 |
+
"loss": 0.23577990531921386,
|
| 399 |
+
"step": 510
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.2510822510822512,
|
| 403 |
+
"grad_norm": 4.87581729888916,
|
| 404 |
+
"learning_rate": 1.806736166800321e-05,
|
| 405 |
+
"loss": 0.2429830551147461,
|
| 406 |
+
"step": 520
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.2943722943722946,
|
| 410 |
+
"grad_norm": 12.465156555175781,
|
| 411 |
+
"learning_rate": 1.7987169206094627e-05,
|
| 412 |
+
"loss": 0.2490438461303711,
|
| 413 |
+
"step": 530
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.3376623376623376,
|
| 417 |
+
"grad_norm": 1.1159459352493286,
|
| 418 |
+
"learning_rate": 1.790697674418605e-05,
|
| 419 |
+
"loss": 0.238852858543396,
|
| 420 |
+
"step": 540
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.380952380952381,
|
| 424 |
+
"grad_norm": 6.159651279449463,
|
| 425 |
+
"learning_rate": 1.7826784282277466e-05,
|
| 426 |
+
"loss": 0.23801960945129394,
|
| 427 |
+
"step": 550
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.4242424242424243,
|
| 431 |
+
"grad_norm": 5.769070625305176,
|
| 432 |
+
"learning_rate": 1.7746591820368885e-05,
|
| 433 |
+
"loss": 0.2144552230834961,
|
| 434 |
+
"step": 560
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.4675324675324677,
|
| 438 |
+
"grad_norm": 11.144370079040527,
|
| 439 |
+
"learning_rate": 1.7666399358460306e-05,
|
| 440 |
+
"loss": 0.209763765335083,
|
| 441 |
+
"step": 570
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.5108225108225106,
|
| 445 |
+
"grad_norm": 8.017593383789062,
|
| 446 |
+
"learning_rate": 1.7586206896551724e-05,
|
| 447 |
+
"loss": 0.20393669605255127,
|
| 448 |
+
"step": 580
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.554112554112554,
|
| 452 |
+
"grad_norm": 8.491714477539062,
|
| 453 |
+
"learning_rate": 1.7506014434643146e-05,
|
| 454 |
+
"loss": 0.21084864139556886,
|
| 455 |
+
"step": 590
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.5974025974025974,
|
| 459 |
+
"grad_norm": 10.802801132202148,
|
| 460 |
+
"learning_rate": 1.7425821972734564e-05,
|
| 461 |
+
"loss": 0.19502675533294678,
|
| 462 |
+
"step": 600
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.6406926406926408,
|
| 466 |
+
"grad_norm": 7.383920192718506,
|
| 467 |
+
"learning_rate": 1.7345629510825982e-05,
|
| 468 |
+
"loss": 0.17343367338180543,
|
| 469 |
+
"step": 610
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.683982683982684,
|
| 473 |
+
"grad_norm": 14.915983200073242,
|
| 474 |
+
"learning_rate": 1.7265437048917403e-05,
|
| 475 |
+
"loss": 0.20925779342651368,
|
| 476 |
+
"step": 620
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.7272727272727275,
|
| 480 |
+
"grad_norm": 11.076672554016113,
|
| 481 |
+
"learning_rate": 1.718524458700882e-05,
|
| 482 |
+
"loss": 0.18709557056427,
|
| 483 |
+
"step": 630
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.7705627705627704,
|
| 487 |
+
"grad_norm": 1.3212802410125732,
|
| 488 |
+
"learning_rate": 1.710505212510024e-05,
|
| 489 |
+
"loss": 0.12550430297851561,
|
| 490 |
+
"step": 640
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.813852813852814,
|
| 494 |
+
"grad_norm": 39.46677017211914,
|
| 495 |
+
"learning_rate": 1.702485966319166e-05,
|
| 496 |
+
"loss": 0.20734634399414062,
|
| 497 |
+
"step": 650
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.857142857142857,
|
| 501 |
+
"grad_norm": 21.644838333129883,
|
| 502 |
+
"learning_rate": 1.694466720128308e-05,
|
| 503 |
+
"loss": 0.20593829154968263,
|
| 504 |
+
"step": 660
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.9004329004329006,
|
| 508 |
+
"grad_norm": 1.596218228340149,
|
| 509 |
+
"learning_rate": 1.68644747393745e-05,
|
| 510 |
+
"loss": 0.21429204940795898,
|
| 511 |
+
"step": 670
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.9437229437229435,
|
| 515 |
+
"grad_norm": 6.069190502166748,
|
| 516 |
+
"learning_rate": 1.678428227746592e-05,
|
| 517 |
+
"loss": 0.17528226375579833,
|
| 518 |
+
"step": 680
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.987012987012987,
|
| 522 |
+
"grad_norm": 2.579589366912842,
|
| 523 |
+
"learning_rate": 1.670408981555734e-05,
|
| 524 |
+
"loss": 0.1867051124572754,
|
| 525 |
+
"step": 690
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.0,
|
| 529 |
+
"eval_f1_hate": 0.9078014184397163,
|
| 530 |
+
"eval_f1_identity_attack": 0.7768595041322314,
|
| 531 |
+
"eval_f1_insult": 0.8369565217391305,
|
| 532 |
+
"eval_f1_macro": 0.7266940390440862,
|
| 533 |
+
"eval_f1_micro": 0.8838709677419355,
|
| 534 |
+
"eval_f1_sexual": 0.0,
|
| 535 |
+
"eval_f1_threat": 0.8717948717948718,
|
| 536 |
+
"eval_f1_toxicity": 0.9667519181585678,
|
| 537 |
+
"eval_loss": 0.16751155257225037,
|
| 538 |
+
"eval_runtime": 2.697,
|
| 539 |
+
"eval_samples_per_second": 120.505,
|
| 540 |
+
"eval_steps_per_second": 15.202,
|
| 541 |
+
"step": 693
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.0303030303030303,
|
| 545 |
+
"grad_norm": 12.631734848022461,
|
| 546 |
+
"learning_rate": 1.6623897353648758e-05,
|
| 547 |
+
"loss": 0.1437455415725708,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.0735930735930737,
|
| 552 |
+
"grad_norm": 0.43667536973953247,
|
| 553 |
+
"learning_rate": 1.6543704891740176e-05,
|
| 554 |
+
"loss": 0.10637929439544677,
|
| 555 |
+
"step": 710
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.116883116883117,
|
| 559 |
+
"grad_norm": 16.54327964782715,
|
| 560 |
+
"learning_rate": 1.6463512429831598e-05,
|
| 561 |
+
"loss": 0.1611637830734253,
|
| 562 |
+
"step": 720
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.16017316017316,
|
| 566 |
+
"grad_norm": 11.03506851196289,
|
| 567 |
+
"learning_rate": 1.6383319967923016e-05,
|
| 568 |
+
"loss": 0.10024868249893189,
|
| 569 |
+
"step": 730
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.2034632034632033,
|
| 573 |
+
"grad_norm": 0.4897419512271881,
|
| 574 |
+
"learning_rate": 1.6303127506014437e-05,
|
| 575 |
+
"loss": 0.13905807733535766,
|
| 576 |
+
"step": 740
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.2467532467532467,
|
| 580 |
+
"grad_norm": 24.316959381103516,
|
| 581 |
+
"learning_rate": 1.6222935044105855e-05,
|
| 582 |
+
"loss": 0.14806885719299318,
|
| 583 |
+
"step": 750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.29004329004329,
|
| 587 |
+
"grad_norm": 12.093938827514648,
|
| 588 |
+
"learning_rate": 1.6142742582197277e-05,
|
| 589 |
+
"loss": 0.13683819770812988,
|
| 590 |
+
"step": 760
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.3333333333333335,
|
| 594 |
+
"grad_norm": 11.699234962463379,
|
| 595 |
+
"learning_rate": 1.6062550120288695e-05,
|
| 596 |
+
"loss": 0.11938896179199218,
|
| 597 |
+
"step": 770
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.3766233766233764,
|
| 601 |
+
"grad_norm": 0.7831173539161682,
|
| 602 |
+
"learning_rate": 1.5982357658380113e-05,
|
| 603 |
+
"loss": 0.153947913646698,
|
| 604 |
+
"step": 780
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.41991341991342,
|
| 608 |
+
"grad_norm": 10.696303367614746,
|
| 609 |
+
"learning_rate": 1.5902165196471534e-05,
|
| 610 |
+
"loss": 0.170080304145813,
|
| 611 |
+
"step": 790
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.463203463203463,
|
| 615 |
+
"grad_norm": 4.8850507736206055,
|
| 616 |
+
"learning_rate": 1.5821972734562952e-05,
|
| 617 |
+
"loss": 0.11064658164978028,
|
| 618 |
+
"step": 800
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.5064935064935066,
|
| 622 |
+
"grad_norm": 5.002935409545898,
|
| 623 |
+
"learning_rate": 1.5741780272654374e-05,
|
| 624 |
+
"loss": 0.18166909217834473,
|
| 625 |
+
"step": 810
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.54978354978355,
|
| 629 |
+
"grad_norm": 0.8856028914451599,
|
| 630 |
+
"learning_rate": 1.5661587810745792e-05,
|
| 631 |
+
"loss": 0.06949449777603149,
|
| 632 |
+
"step": 820
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.5930735930735933,
|
| 636 |
+
"grad_norm": 0.8279700875282288,
|
| 637 |
+
"learning_rate": 1.558139534883721e-05,
|
| 638 |
+
"loss": 0.16245560646057128,
|
| 639 |
+
"step": 830
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.6363636363636362,
|
| 643 |
+
"grad_norm": 1.2465356588363647,
|
| 644 |
+
"learning_rate": 1.550120288692863e-05,
|
| 645 |
+
"loss": 0.11454813480377198,
|
| 646 |
+
"step": 840
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.6796536796536796,
|
| 650 |
+
"grad_norm": 0.49412283301353455,
|
| 651 |
+
"learning_rate": 1.542101042502005e-05,
|
| 652 |
+
"loss": 0.18175532817840576,
|
| 653 |
+
"step": 850
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.722943722943723,
|
| 657 |
+
"grad_norm": 19.483863830566406,
|
| 658 |
+
"learning_rate": 1.534081796311147e-05,
|
| 659 |
+
"loss": 0.1303969979286194,
|
| 660 |
+
"step": 860
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.7662337662337664,
|
| 664 |
+
"grad_norm": 0.5482262969017029,
|
| 665 |
+
"learning_rate": 1.526062550120289e-05,
|
| 666 |
+
"loss": 0.18206866979598998,
|
| 667 |
+
"step": 870
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.8095238095238093,
|
| 671 |
+
"grad_norm": 56.418704986572266,
|
| 672 |
+
"learning_rate": 1.5180433039294307e-05,
|
| 673 |
+
"loss": 0.11589281558990479,
|
| 674 |
+
"step": 880
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.8528138528138527,
|
| 678 |
+
"grad_norm": 1.1338515281677246,
|
| 679 |
+
"learning_rate": 1.5100240577385727e-05,
|
| 680 |
+
"loss": 0.16329562664031982,
|
| 681 |
+
"step": 890
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.896103896103896,
|
| 685 |
+
"grad_norm": 6.882433891296387,
|
| 686 |
+
"learning_rate": 1.5020048115477147e-05,
|
| 687 |
+
"loss": 0.17075834274291993,
|
| 688 |
+
"step": 900
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.9393939393939394,
|
| 692 |
+
"grad_norm": 7.5362162590026855,
|
| 693 |
+
"learning_rate": 1.4939855653568566e-05,
|
| 694 |
+
"loss": 0.13381673097610475,
|
| 695 |
+
"step": 910
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.982683982683983,
|
| 699 |
+
"grad_norm": 1.186409831047058,
|
| 700 |
+
"learning_rate": 1.4859663191659985e-05,
|
| 701 |
+
"loss": 0.09673304557800293,
|
| 702 |
+
"step": 920
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.0,
|
| 706 |
+
"eval_f1_hate": 0.9076923076923077,
|
| 707 |
+
"eval_f1_identity_attack": 0.8,
|
| 708 |
+
"eval_f1_insult": 0.9019607843137255,
|
| 709 |
+
"eval_f1_macro": 0.8549086601070185,
|
| 710 |
+
"eval_f1_micro": 0.9085037674919269,
|
| 711 |
+
"eval_f1_sexual": 0.6666666666666666,
|
| 712 |
+
"eval_f1_threat": 0.8918918918918919,
|
| 713 |
+
"eval_f1_toxicity": 0.9612403100775194,
|
| 714 |
+
"eval_loss": 0.13372334837913513,
|
| 715 |
+
"eval_runtime": 2.6455,
|
| 716 |
+
"eval_samples_per_second": 122.852,
|
| 717 |
+
"eval_steps_per_second": 15.498,
|
| 718 |
+
"step": 924
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.025974025974026,
|
| 722 |
+
"grad_norm": 3.63419246673584,
|
| 723 |
+
"learning_rate": 1.4779470729751404e-05,
|
| 724 |
+
"loss": 0.0814066231250763,
|
| 725 |
+
"step": 930
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.06926406926407,
|
| 729 |
+
"grad_norm": 4.606685161590576,
|
| 730 |
+
"learning_rate": 1.4699278267842824e-05,
|
| 731 |
+
"loss": 0.09704769253730774,
|
| 732 |
+
"step": 940
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 4.112554112554113,
|
| 736 |
+
"grad_norm": 1.3340409994125366,
|
| 737 |
+
"learning_rate": 1.4619085805934244e-05,
|
| 738 |
+
"loss": 0.06881680488586425,
|
| 739 |
+
"step": 950
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 4.1558441558441555,
|
| 743 |
+
"grad_norm": 22.688732147216797,
|
| 744 |
+
"learning_rate": 1.4538893344025662e-05,
|
| 745 |
+
"loss": 0.08566259145736695,
|
| 746 |
+
"step": 960
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 4.199134199134199,
|
| 750 |
+
"grad_norm": 0.7076430916786194,
|
| 751 |
+
"learning_rate": 1.4458700882117083e-05,
|
| 752 |
+
"loss": 0.06713258028030396,
|
| 753 |
+
"step": 970
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.242424242424242,
|
| 757 |
+
"grad_norm": 0.3430556058883667,
|
| 758 |
+
"learning_rate": 1.4378508420208502e-05,
|
| 759 |
+
"loss": 0.07058375477790832,
|
| 760 |
+
"step": 980
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.285714285714286,
|
| 764 |
+
"grad_norm": 0.47648629546165466,
|
| 765 |
+
"learning_rate": 1.4298315958299921e-05,
|
| 766 |
+
"loss": 0.05376957654953003,
|
| 767 |
+
"step": 990
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 4.329004329004329,
|
| 771 |
+
"grad_norm": 30.782028198242188,
|
| 772 |
+
"learning_rate": 1.4218123496391341e-05,
|
| 773 |
+
"loss": 0.0664408564567566,
|
| 774 |
+
"step": 1000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.372294372294372,
|
| 778 |
+
"grad_norm": 5.640874862670898,
|
| 779 |
+
"learning_rate": 1.4137931034482759e-05,
|
| 780 |
+
"loss": 0.10812230110168457,
|
| 781 |
+
"step": 1010
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 4.415584415584416,
|
| 785 |
+
"grad_norm": 1.3343350887298584,
|
| 786 |
+
"learning_rate": 1.405773857257418e-05,
|
| 787 |
+
"loss": 0.09118871688842774,
|
| 788 |
+
"step": 1020
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 4.458874458874459,
|
| 792 |
+
"grad_norm": 3.0995726585388184,
|
| 793 |
+
"learning_rate": 1.3977546110665599e-05,
|
| 794 |
+
"loss": 0.09201886057853699,
|
| 795 |
+
"step": 1030
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.5021645021645025,
|
| 799 |
+
"grad_norm": 43.72480010986328,
|
| 800 |
+
"learning_rate": 1.3897353648757017e-05,
|
| 801 |
+
"loss": 0.12083396911621094,
|
| 802 |
+
"step": 1040
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.545454545454545,
|
| 806 |
+
"grad_norm": 8.080801010131836,
|
| 807 |
+
"learning_rate": 1.3817161186848438e-05,
|
| 808 |
+
"loss": 0.07746089696884155,
|
| 809 |
+
"step": 1050
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 4.588744588744589,
|
| 813 |
+
"grad_norm": 7.748966217041016,
|
| 814 |
+
"learning_rate": 1.3736968724939856e-05,
|
| 815 |
+
"loss": 0.08128405213356019,
|
| 816 |
+
"step": 1060
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 4.632034632034632,
|
| 820 |
+
"grad_norm": 7.703828811645508,
|
| 821 |
+
"learning_rate": 1.3656776263031278e-05,
|
| 822 |
+
"loss": 0.07613251209259034,
|
| 823 |
+
"step": 1070
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 4.675324675324675,
|
| 827 |
+
"grad_norm": 12.483865737915039,
|
| 828 |
+
"learning_rate": 1.3576583801122696e-05,
|
| 829 |
+
"loss": 0.06644371151924133,
|
| 830 |
+
"step": 1080
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 4.7186147186147185,
|
| 834 |
+
"grad_norm": 5.6639404296875,
|
| 835 |
+
"learning_rate": 1.3496391339214114e-05,
|
| 836 |
+
"loss": 0.07161596417427063,
|
| 837 |
+
"step": 1090
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.761904761904762,
|
| 841 |
+
"grad_norm": 3.5330121517181396,
|
| 842 |
+
"learning_rate": 1.3416198877305535e-05,
|
| 843 |
+
"loss": 0.10294915437698364,
|
| 844 |
+
"step": 1100
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 4.805194805194805,
|
| 848 |
+
"grad_norm": 12.56156063079834,
|
| 849 |
+
"learning_rate": 1.3336006415396953e-05,
|
| 850 |
+
"loss": 0.11282093524932861,
|
| 851 |
+
"step": 1110
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 4.848484848484849,
|
| 855 |
+
"grad_norm": 1.3351284265518188,
|
| 856 |
+
"learning_rate": 1.3255813953488372e-05,
|
| 857 |
+
"loss": 0.085838782787323,
|
| 858 |
+
"step": 1120
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 4.891774891774892,
|
| 862 |
+
"grad_norm": 19.801355361938477,
|
| 863 |
+
"learning_rate": 1.3175621491579793e-05,
|
| 864 |
+
"loss": 0.07634471654891968,
|
| 865 |
+
"step": 1130
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 4.935064935064935,
|
| 869 |
+
"grad_norm": 0.30149272084236145,
|
| 870 |
+
"learning_rate": 1.3095429029671211e-05,
|
| 871 |
+
"loss": 0.046724116802215575,
|
| 872 |
+
"step": 1140
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.978354978354979,
|
| 876 |
+
"grad_norm": 4.291561603546143,
|
| 877 |
+
"learning_rate": 1.3015236567762633e-05,
|
| 878 |
+
"loss": 0.04501450061798096,
|
| 879 |
+
"step": 1150
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 5.0,
|
| 883 |
+
"eval_f1_hate": 0.935251798561151,
|
| 884 |
+
"eval_f1_identity_attack": 0.8849557522123894,
|
| 885 |
+
"eval_f1_insult": 0.94,
|
| 886 |
+
"eval_f1_macro": 0.9110801721442771,
|
| 887 |
+
"eval_f1_micro": 0.944386149003148,
|
| 888 |
+
"eval_f1_sexual": 0.8148148148148148,
|
| 889 |
+
"eval_f1_threat": 0.9090909090909091,
|
| 890 |
+
"eval_f1_toxicity": 0.982367758186398,
|
| 891 |
+
"eval_loss": 0.09442197531461716,
|
| 892 |
+
"eval_runtime": 2.5423,
|
| 893 |
+
"eval_samples_per_second": 127.835,
|
| 894 |
+
"eval_steps_per_second": 16.127,
|
| 895 |
+
"step": 1155
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 5.021645021645021,
|
| 899 |
+
"grad_norm": 16.437841415405273,
|
| 900 |
+
"learning_rate": 1.293504410585405e-05,
|
| 901 |
+
"loss": 0.057061117887496945,
|
| 902 |
+
"step": 1160
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 5.064935064935065,
|
| 906 |
+
"grad_norm": 1.009265422821045,
|
| 907 |
+
"learning_rate": 1.2854851643945469e-05,
|
| 908 |
+
"loss": 0.06116377115249634,
|
| 909 |
+
"step": 1170
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 5.108225108225108,
|
| 913 |
+
"grad_norm": 0.22976772487163544,
|
| 914 |
+
"learning_rate": 1.277465918203689e-05,
|
| 915 |
+
"loss": 0.03162805736064911,
|
| 916 |
+
"step": 1180
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 5.151515151515151,
|
| 920 |
+
"grad_norm": 0.16043254733085632,
|
| 921 |
+
"learning_rate": 1.2694466720128308e-05,
|
| 922 |
+
"loss": 0.05421352982521057,
|
| 923 |
+
"step": 1190
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 5.194805194805195,
|
| 927 |
+
"grad_norm": 0.7127373814582825,
|
| 928 |
+
"learning_rate": 1.2614274258219728e-05,
|
| 929 |
+
"loss": 0.048463857173919676,
|
| 930 |
+
"step": 1200
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.238095238095238,
|
| 934 |
+
"grad_norm": 0.1292610466480255,
|
| 935 |
+
"learning_rate": 1.2534081796311148e-05,
|
| 936 |
+
"loss": 0.05593010187149048,
|
| 937 |
+
"step": 1210
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 5.2813852813852815,
|
| 941 |
+
"grad_norm": 1.4257301092147827,
|
| 942 |
+
"learning_rate": 1.2453889334402568e-05,
|
| 943 |
+
"loss": 0.05451661944389343,
|
| 944 |
+
"step": 1220
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 5.324675324675325,
|
| 948 |
+
"grad_norm": 12.879122734069824,
|
| 949 |
+
"learning_rate": 1.2373696872493987e-05,
|
| 950 |
+
"loss": 0.05459271669387818,
|
| 951 |
+
"step": 1230
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 5.367965367965368,
|
| 955 |
+
"grad_norm": 0.27403524518013,
|
| 956 |
+
"learning_rate": 1.2293504410585405e-05,
|
| 957 |
+
"loss": 0.05355905294418335,
|
| 958 |
+
"step": 1240
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 5.411255411255412,
|
| 962 |
+
"grad_norm": 16.353090286254883,
|
| 963 |
+
"learning_rate": 1.2213311948676825e-05,
|
| 964 |
+
"loss": 0.05738970637321472,
|
| 965 |
+
"step": 1250
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 5.454545454545454,
|
| 969 |
+
"grad_norm": 1.0312873125076294,
|
| 970 |
+
"learning_rate": 1.2133119486768245e-05,
|
| 971 |
+
"loss": 0.04536194503307343,
|
| 972 |
+
"step": 1260
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 5.4978354978354975,
|
| 976 |
+
"grad_norm": 0.17286163568496704,
|
| 977 |
+
"learning_rate": 1.2052927024859665e-05,
|
| 978 |
+
"loss": 0.03271396160125732,
|
| 979 |
+
"step": 1270
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 5.541125541125541,
|
| 983 |
+
"grad_norm": 0.15860261023044586,
|
| 984 |
+
"learning_rate": 1.1972734562951083e-05,
|
| 985 |
+
"loss": 0.02813169062137604,
|
| 986 |
+
"step": 1280
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 5.584415584415584,
|
| 990 |
+
"grad_norm": 0.13466164469718933,
|
| 991 |
+
"learning_rate": 1.1892542101042504e-05,
|
| 992 |
+
"loss": 0.032718077301979065,
|
| 993 |
+
"step": 1290
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.627705627705628,
|
| 997 |
+
"grad_norm": 2.681539535522461,
|
| 998 |
+
"learning_rate": 1.1812349639133922e-05,
|
| 999 |
+
"loss": 0.0269508421421051,
|
| 1000 |
+
"step": 1300
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 5.670995670995671,
|
| 1004 |
+
"grad_norm": 0.10189682245254517,
|
| 1005 |
+
"learning_rate": 1.1732157177225342e-05,
|
| 1006 |
+
"loss": 0.031834939122200014,
|
| 1007 |
+
"step": 1310
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 5.714285714285714,
|
| 1011 |
+
"grad_norm": 0.0732518881559372,
|
| 1012 |
+
"learning_rate": 1.1651964715316762e-05,
|
| 1013 |
+
"loss": 0.02767125368118286,
|
| 1014 |
+
"step": 1320
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 5.757575757575758,
|
| 1018 |
+
"grad_norm": 8.737700462341309,
|
| 1019 |
+
"learning_rate": 1.157177225340818e-05,
|
| 1020 |
+
"loss": 0.04246579110622406,
|
| 1021 |
+
"step": 1330
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 5.800865800865801,
|
| 1025 |
+
"grad_norm": 0.08001670241355896,
|
| 1026 |
+
"learning_rate": 1.1491579791499601e-05,
|
| 1027 |
+
"loss": 0.06979098916053772,
|
| 1028 |
+
"step": 1340
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 5.8441558441558445,
|
| 1032 |
+
"grad_norm": 4.200087070465088,
|
| 1033 |
+
"learning_rate": 1.141138732959102e-05,
|
| 1034 |
+
"loss": 0.050935995578765866,
|
| 1035 |
+
"step": 1350
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 5.887445887445887,
|
| 1039 |
+
"grad_norm": 0.5274473428726196,
|
| 1040 |
+
"learning_rate": 1.1331194867682438e-05,
|
| 1041 |
+
"loss": 0.030669301748275757,
|
| 1042 |
+
"step": 1360
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 5.93073593073593,
|
| 1046 |
+
"grad_norm": 0.44906026124954224,
|
| 1047 |
+
"learning_rate": 1.1251002405773859e-05,
|
| 1048 |
+
"loss": 0.022448521852493287,
|
| 1049 |
+
"step": 1370
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 5.974025974025974,
|
| 1053 |
+
"grad_norm": 10.393362045288086,
|
| 1054 |
+
"learning_rate": 1.1170809943865277e-05,
|
| 1055 |
+
"loss": 0.03214894533157349,
|
| 1056 |
+
"step": 1380
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 6.0,
|
| 1060 |
+
"eval_f1_hate": 0.927536231884058,
|
| 1061 |
+
"eval_f1_identity_attack": 0.9090909090909091,
|
| 1062 |
+
"eval_f1_insult": 0.9603960396039604,
|
| 1063 |
+
"eval_f1_macro": 0.9342784803472953,
|
| 1064 |
+
"eval_f1_micro": 0.9556025369978859,
|
| 1065 |
+
"eval_f1_sexual": 0.8888888888888888,
|
| 1066 |
+
"eval_f1_threat": 0.935064935064935,
|
| 1067 |
+
"eval_f1_toxicity": 0.9846938775510204,
|
| 1068 |
+
"eval_loss": 0.0945809856057167,
|
| 1069 |
+
"eval_runtime": 2.5403,
|
| 1070 |
+
"eval_samples_per_second": 127.939,
|
| 1071 |
+
"eval_steps_per_second": 16.14,
|
| 1072 |
+
"step": 1386
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 6.017316017316017,
|
| 1076 |
+
"grad_norm": 1.5638502836227417,
|
| 1077 |
+
"learning_rate": 1.1090617481956699e-05,
|
| 1078 |
+
"loss": 0.015108948945999146,
|
| 1079 |
+
"step": 1390
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 6.0606060606060606,
|
| 1083 |
+
"grad_norm": 0.08260394632816315,
|
| 1084 |
+
"learning_rate": 1.1010425020048117e-05,
|
| 1085 |
+
"loss": 0.037759020924568176,
|
| 1086 |
+
"step": 1400
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 6.103896103896104,
|
| 1090 |
+
"grad_norm": 0.16305118799209595,
|
| 1091 |
+
"learning_rate": 1.0930232558139535e-05,
|
| 1092 |
+
"loss": 0.06289060115814209,
|
| 1093 |
+
"step": 1410
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 6.147186147186147,
|
| 1097 |
+
"grad_norm": 17.280921936035156,
|
| 1098 |
+
"learning_rate": 1.0850040096230956e-05,
|
| 1099 |
+
"loss": 0.03346436619758606,
|
| 1100 |
+
"step": 1420
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 6.190476190476191,
|
| 1104 |
+
"grad_norm": 0.057965584099292755,
|
| 1105 |
+
"learning_rate": 1.0769847634322374e-05,
|
| 1106 |
+
"loss": 0.028430098295211793,
|
| 1107 |
+
"step": 1430
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 6.233766233766234,
|
| 1111 |
+
"grad_norm": 42.3648796081543,
|
| 1112 |
+
"learning_rate": 1.0689655172413792e-05,
|
| 1113 |
+
"loss": 0.04611627459526062,
|
| 1114 |
+
"step": 1440
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 6.2770562770562774,
|
| 1118 |
+
"grad_norm": 0.19590164721012115,
|
| 1119 |
+
"learning_rate": 1.0609462710505214e-05,
|
| 1120 |
+
"loss": 0.01396958827972412,
|
| 1121 |
+
"step": 1450
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 6.32034632034632,
|
| 1125 |
+
"grad_norm": 0.054590217769145966,
|
| 1126 |
+
"learning_rate": 1.0529270248596632e-05,
|
| 1127 |
+
"loss": 0.021274125576019286,
|
| 1128 |
+
"step": 1460
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 6.363636363636363,
|
| 1132 |
+
"grad_norm": 0.05328702554106712,
|
| 1133 |
+
"learning_rate": 1.0449077786688053e-05,
|
| 1134 |
+
"loss": 0.034597578644752505,
|
| 1135 |
+
"step": 1470
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 6.406926406926407,
|
| 1139 |
+
"grad_norm": 3.127825975418091,
|
| 1140 |
+
"learning_rate": 1.0368885324779472e-05,
|
| 1141 |
+
"loss": 0.023499704897403717,
|
| 1142 |
+
"step": 1480
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 6.45021645021645,
|
| 1146 |
+
"grad_norm": 0.6553439497947693,
|
| 1147 |
+
"learning_rate": 1.028869286287089e-05,
|
| 1148 |
+
"loss": 0.01829185485839844,
|
| 1149 |
+
"step": 1490
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.4935064935064934,
|
| 1153 |
+
"grad_norm": 0.09214723855257034,
|
| 1154 |
+
"learning_rate": 1.0208500400962311e-05,
|
| 1155 |
+
"loss": 0.025910788774490358,
|
| 1156 |
+
"step": 1500
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 6.536796536796537,
|
| 1160 |
+
"grad_norm": 0.1844961792230606,
|
| 1161 |
+
"learning_rate": 1.012830793905373e-05,
|
| 1162 |
+
"loss": 0.03210195004940033,
|
| 1163 |
+
"step": 1510
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 6.58008658008658,
|
| 1167 |
+
"grad_norm": 0.07900078594684601,
|
| 1168 |
+
"learning_rate": 1.0048115477145149e-05,
|
| 1169 |
+
"loss": 0.0339710533618927,
|
| 1170 |
+
"step": 1520
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 6.623376623376624,
|
| 1174 |
+
"grad_norm": 7.394096374511719,
|
| 1175 |
+
"learning_rate": 9.967923015236569e-06,
|
| 1176 |
+
"loss": 0.02919152081012726,
|
| 1177 |
+
"step": 1530
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 6.666666666666667,
|
| 1181 |
+
"grad_norm": 0.18829531967639923,
|
| 1182 |
+
"learning_rate": 9.887730553327989e-06,
|
| 1183 |
+
"loss": 0.019558291137218475,
|
| 1184 |
+
"step": 1540
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 6.70995670995671,
|
| 1188 |
+
"grad_norm": 8.413188934326172,
|
| 1189 |
+
"learning_rate": 9.807538091419407e-06,
|
| 1190 |
+
"loss": 0.04265648126602173,
|
| 1191 |
+
"step": 1550
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 6.753246753246753,
|
| 1195 |
+
"grad_norm": 0.06360296159982681,
|
| 1196 |
+
"learning_rate": 9.727345629510826e-06,
|
| 1197 |
+
"loss": 0.01586664468050003,
|
| 1198 |
+
"step": 1560
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 6.796536796536796,
|
| 1202 |
+
"grad_norm": 0.11153659969568253,
|
| 1203 |
+
"learning_rate": 9.647153167602246e-06,
|
| 1204 |
+
"loss": 0.04314278066158295,
|
| 1205 |
+
"step": 1570
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 6.83982683982684,
|
| 1209 |
+
"grad_norm": 0.05194525793194771,
|
| 1210 |
+
"learning_rate": 9.566960705693666e-06,
|
| 1211 |
+
"loss": 0.051305174827575684,
|
| 1212 |
+
"step": 1580
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 6.883116883116883,
|
| 1216 |
+
"grad_norm": 0.10274208337068558,
|
| 1217 |
+
"learning_rate": 9.486768243785086e-06,
|
| 1218 |
+
"loss": 0.027199384570121766,
|
| 1219 |
+
"step": 1590
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 6.926406926406926,
|
| 1223 |
+
"grad_norm": 0.10585841536521912,
|
| 1224 |
+
"learning_rate": 9.406575781876505e-06,
|
| 1225 |
+
"loss": 0.012706747651100159,
|
| 1226 |
+
"step": 1600
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 6.96969696969697,
|
| 1230 |
+
"grad_norm": 0.12696118652820587,
|
| 1231 |
+
"learning_rate": 9.326383319967924e-06,
|
| 1232 |
+
"loss": 0.02097606360912323,
|
| 1233 |
+
"step": 1610
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 7.0,
|
| 1237 |
+
"eval_f1_hate": 0.9343065693430657,
|
| 1238 |
+
"eval_f1_identity_attack": 0.9259259259259259,
|
| 1239 |
+
"eval_f1_insult": 0.9547738693467337,
|
| 1240 |
+
"eval_f1_macro": 0.9392695086064378,
|
| 1241 |
+
"eval_f1_micro": 0.9567053854276664,
|
| 1242 |
+
"eval_f1_sexual": 0.9333333333333333,
|
| 1243 |
+
"eval_f1_threat": 0.9,
|
| 1244 |
+
"eval_f1_toxicity": 0.9872773536895675,
|
| 1245 |
+
"eval_loss": 0.096724733710289,
|
| 1246 |
+
"eval_runtime": 2.4451,
|
| 1247 |
+
"eval_samples_per_second": 132.916,
|
| 1248 |
+
"eval_steps_per_second": 16.768,
|
| 1249 |
+
"step": 1617
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 7.012987012987013,
|
| 1253 |
+
"grad_norm": 8.285896301269531,
|
| 1254 |
+
"learning_rate": 9.246190858059343e-06,
|
| 1255 |
+
"loss": 0.013265588879585266,
|
| 1256 |
+
"step": 1620
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 7.0562770562770565,
|
| 1260 |
+
"grad_norm": 55.716766357421875,
|
| 1261 |
+
"learning_rate": 9.165998396150763e-06,
|
| 1262 |
+
"loss": 0.05298206806182861,
|
| 1263 |
+
"step": 1630
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 7.0995670995671,
|
| 1267 |
+
"grad_norm": 0.0616360642015934,
|
| 1268 |
+
"learning_rate": 9.085805934242183e-06,
|
| 1269 |
+
"loss": 0.013892856240272523,
|
| 1270 |
+
"step": 1640
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 7.142857142857143,
|
| 1274 |
+
"grad_norm": 0.11775124818086624,
|
| 1275 |
+
"learning_rate": 9.005613472333601e-06,
|
| 1276 |
+
"loss": 0.02527049481868744,
|
| 1277 |
+
"step": 1650
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 7.186147186147186,
|
| 1281 |
+
"grad_norm": 0.12172091752290726,
|
| 1282 |
+
"learning_rate": 8.92542101042502e-06,
|
| 1283 |
+
"loss": 0.016150999069213866,
|
| 1284 |
+
"step": 1660
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 7.229437229437229,
|
| 1288 |
+
"grad_norm": 233.70913696289062,
|
| 1289 |
+
"learning_rate": 8.84522854851644e-06,
|
| 1290 |
+
"loss": 0.03750343322753906,
|
| 1291 |
+
"step": 1670
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 7.2727272727272725,
|
| 1295 |
+
"grad_norm": 0.19130665063858032,
|
| 1296 |
+
"learning_rate": 8.76503608660786e-06,
|
| 1297 |
+
"loss": 0.047661423683166504,
|
| 1298 |
+
"step": 1680
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 7.316017316017316,
|
| 1302 |
+
"grad_norm": 0.5913139581680298,
|
| 1303 |
+
"learning_rate": 8.684843624699278e-06,
|
| 1304 |
+
"loss": 0.058721184730529785,
|
| 1305 |
+
"step": 1690
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 7.359307359307359,
|
| 1309 |
+
"grad_norm": 0.11178971081972122,
|
| 1310 |
+
"learning_rate": 8.604651162790698e-06,
|
| 1311 |
+
"loss": 0.019251981377601625,
|
| 1312 |
+
"step": 1700
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 7.402597402597403,
|
| 1316 |
+
"grad_norm": 0.7590028643608093,
|
| 1317 |
+
"learning_rate": 8.524458700882118e-06,
|
| 1318 |
+
"loss": 0.04656476080417633,
|
| 1319 |
+
"step": 1710
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 7.445887445887446,
|
| 1323 |
+
"grad_norm": 0.11145845055580139,
|
| 1324 |
+
"learning_rate": 8.444266238973538e-06,
|
| 1325 |
+
"loss": 0.04233784377574921,
|
| 1326 |
+
"step": 1720
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 7.489177489177489,
|
| 1330 |
+
"grad_norm": 0.06500884890556335,
|
| 1331 |
+
"learning_rate": 8.364073777064956e-06,
|
| 1332 |
+
"loss": 0.017232677340507506,
|
| 1333 |
+
"step": 1730
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 7.532467532467533,
|
| 1337 |
+
"grad_norm": 0.2547213137149811,
|
| 1338 |
+
"learning_rate": 8.283881315156376e-06,
|
| 1339 |
+
"loss": 0.032582181692123416,
|
| 1340 |
+
"step": 1740
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 7.575757575757576,
|
| 1344 |
+
"grad_norm": 0.12454051524400711,
|
| 1345 |
+
"learning_rate": 8.203688853247795e-06,
|
| 1346 |
+
"loss": 0.011076736450195312,
|
| 1347 |
+
"step": 1750
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 7.619047619047619,
|
| 1351 |
+
"grad_norm": 0.07941589504480362,
|
| 1352 |
+
"learning_rate": 8.123496391339215e-06,
|
| 1353 |
+
"loss": 0.03252111673355103,
|
| 1354 |
+
"step": 1760
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 7.662337662337662,
|
| 1358 |
+
"grad_norm": 0.06445322930812836,
|
| 1359 |
+
"learning_rate": 8.043303929430633e-06,
|
| 1360 |
+
"loss": 0.02210572212934494,
|
| 1361 |
+
"step": 1770
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 7.705627705627705,
|
| 1365 |
+
"grad_norm": 0.09489136934280396,
|
| 1366 |
+
"learning_rate": 7.963111467522053e-06,
|
| 1367 |
+
"loss": 0.02158440500497818,
|
| 1368 |
+
"step": 1780
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 7.748917748917749,
|
| 1372 |
+
"grad_norm": 1.2053515911102295,
|
| 1373 |
+
"learning_rate": 7.882919005613473e-06,
|
| 1374 |
+
"loss": 0.010548257827758789,
|
| 1375 |
+
"step": 1790
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 7.792207792207792,
|
| 1379 |
+
"grad_norm": 0.10824225842952728,
|
| 1380 |
+
"learning_rate": 7.802726543704892e-06,
|
| 1381 |
+
"loss": 0.02837684452533722,
|
| 1382 |
+
"step": 1800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 7.8354978354978355,
|
| 1386 |
+
"grad_norm": 0.19801065325737,
|
| 1387 |
+
"learning_rate": 7.72253408179631e-06,
|
| 1388 |
+
"loss": 0.03580955862998962,
|
| 1389 |
+
"step": 1810
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 7.878787878787879,
|
| 1393 |
+
"grad_norm": 0.045844487845897675,
|
| 1394 |
+
"learning_rate": 7.64234161988773e-06,
|
| 1395 |
+
"loss": 0.008237843215465546,
|
| 1396 |
+
"step": 1820
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 7.922077922077922,
|
| 1400 |
+
"grad_norm": 0.06215677782893181,
|
| 1401 |
+
"learning_rate": 7.562149157979151e-06,
|
| 1402 |
+
"loss": 0.017115187644958497,
|
| 1403 |
+
"step": 1830
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 7.965367965367966,
|
| 1407 |
+
"grad_norm": 1.7800884246826172,
|
| 1408 |
+
"learning_rate": 7.481956696070571e-06,
|
| 1409 |
+
"loss": 0.02911553680896759,
|
| 1410 |
+
"step": 1840
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 8.0,
|
| 1414 |
+
"eval_f1_hate": 0.948905109489051,
|
| 1415 |
+
"eval_f1_identity_attack": 0.9259259259259259,
|
| 1416 |
+
"eval_f1_insult": 0.9603960396039604,
|
| 1417 |
+
"eval_f1_macro": 0.9664512006521,
|
| 1418 |
+
"eval_f1_micro": 0.9693121693121693,
|
| 1419 |
+
"eval_f1_sexual": 1.0,
|
| 1420 |
+
"eval_f1_threat": 0.9736842105263158,
|
| 1421 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1422 |
+
"eval_loss": 0.07348332554101944,
|
| 1423 |
+
"eval_runtime": 2.4382,
|
| 1424 |
+
"eval_samples_per_second": 133.294,
|
| 1425 |
+
"eval_steps_per_second": 16.815,
|
| 1426 |
+
"step": 1848
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 8.008658008658008,
|
| 1430 |
+
"grad_norm": 0.5656646490097046,
|
| 1431 |
+
"learning_rate": 7.401764234161989e-06,
|
| 1432 |
+
"loss": 0.008289340138435363,
|
| 1433 |
+
"step": 1850
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 8.051948051948052,
|
| 1437 |
+
"grad_norm": 0.05726471543312073,
|
| 1438 |
+
"learning_rate": 7.3215717722534086e-06,
|
| 1439 |
+
"loss": 0.007889867573976517,
|
| 1440 |
+
"step": 1860
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 8.095238095238095,
|
| 1444 |
+
"grad_norm": 0.039329830557107925,
|
| 1445 |
+
"learning_rate": 7.241379310344828e-06,
|
| 1446 |
+
"loss": 0.009552600979804992,
|
| 1447 |
+
"step": 1870
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 8.13852813852814,
|
| 1451 |
+
"grad_norm": 0.051925044506788254,
|
| 1452 |
+
"learning_rate": 7.161186848436248e-06,
|
| 1453 |
+
"loss": 0.009062138944864273,
|
| 1454 |
+
"step": 1880
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 8.181818181818182,
|
| 1458 |
+
"grad_norm": 1.3687405586242676,
|
| 1459 |
+
"learning_rate": 7.080994386527666e-06,
|
| 1460 |
+
"loss": 0.039984285831451416,
|
| 1461 |
+
"step": 1890
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 8.225108225108226,
|
| 1465 |
+
"grad_norm": 0.07175378501415253,
|
| 1466 |
+
"learning_rate": 7.000801924619086e-06,
|
| 1467 |
+
"loss": 0.009197700768709183,
|
| 1468 |
+
"step": 1900
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 8.268398268398268,
|
| 1472 |
+
"grad_norm": 3.0823709964752197,
|
| 1473 |
+
"learning_rate": 6.920609462710506e-06,
|
| 1474 |
+
"loss": 0.010183989256620406,
|
| 1475 |
+
"step": 1910
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 8.311688311688311,
|
| 1479 |
+
"grad_norm": 0.0992533341050148,
|
| 1480 |
+
"learning_rate": 6.8404170008019255e-06,
|
| 1481 |
+
"loss": 0.008255717903375625,
|
| 1482 |
+
"step": 1920
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 8.354978354978355,
|
| 1486 |
+
"grad_norm": 0.058967746794223785,
|
| 1487 |
+
"learning_rate": 6.7602245388933444e-06,
|
| 1488 |
+
"loss": 0.016507762670516967,
|
| 1489 |
+
"step": 1930
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 8.398268398268398,
|
| 1493 |
+
"grad_norm": 0.7071771025657654,
|
| 1494 |
+
"learning_rate": 6.680032076984763e-06,
|
| 1495 |
+
"loss": 0.018038202822208405,
|
| 1496 |
+
"step": 1940
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 8.441558441558442,
|
| 1500 |
+
"grad_norm": 0.05050427466630936,
|
| 1501 |
+
"learning_rate": 6.599839615076183e-06,
|
| 1502 |
+
"loss": 0.03205050230026245,
|
| 1503 |
+
"step": 1950
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 8.484848484848484,
|
| 1507 |
+
"grad_norm": 0.05392308533191681,
|
| 1508 |
+
"learning_rate": 6.519647153167603e-06,
|
| 1509 |
+
"loss": 0.03979974389076233,
|
| 1510 |
+
"step": 1960
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 8.528138528138529,
|
| 1514 |
+
"grad_norm": 5.338536739349365,
|
| 1515 |
+
"learning_rate": 6.439454691259022e-06,
|
| 1516 |
+
"loss": 0.010501711070537567,
|
| 1517 |
+
"step": 1970
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 8.571428571428571,
|
| 1521 |
+
"grad_norm": 0.0416489876806736,
|
| 1522 |
+
"learning_rate": 6.359262229350442e-06,
|
| 1523 |
+
"loss": 0.008546990901231765,
|
| 1524 |
+
"step": 1980
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 8.614718614718615,
|
| 1528 |
+
"grad_norm": 0.03366857394576073,
|
| 1529 |
+
"learning_rate": 6.279069767441861e-06,
|
| 1530 |
+
"loss": 0.007867447286844253,
|
| 1531 |
+
"step": 1990
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 8.658008658008658,
|
| 1535 |
+
"grad_norm": 0.0408504493534565,
|
| 1536 |
+
"learning_rate": 6.19887730553328e-06,
|
| 1537 |
+
"loss": 0.009638544172048569,
|
| 1538 |
+
"step": 2000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 8.7012987012987,
|
| 1542 |
+
"grad_norm": 0.5971854329109192,
|
| 1543 |
+
"learning_rate": 6.118684843624699e-06,
|
| 1544 |
+
"loss": 0.02221200317144394,
|
| 1545 |
+
"step": 2010
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 8.744588744588745,
|
| 1549 |
+
"grad_norm": 0.16346342861652374,
|
| 1550 |
+
"learning_rate": 6.038492381716119e-06,
|
| 1551 |
+
"loss": 0.016023994982242586,
|
| 1552 |
+
"step": 2020
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 8.787878787878787,
|
| 1556 |
+
"grad_norm": 104.31558990478516,
|
| 1557 |
+
"learning_rate": 5.958299919807539e-06,
|
| 1558 |
+
"loss": 0.028461986780166627,
|
| 1559 |
+
"step": 2030
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 8.831168831168831,
|
| 1563 |
+
"grad_norm": 0.04544289410114288,
|
| 1564 |
+
"learning_rate": 5.8781074578989585e-06,
|
| 1565 |
+
"loss": 0.007379808276891708,
|
| 1566 |
+
"step": 2040
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 8.874458874458874,
|
| 1570 |
+
"grad_norm": 0.07683689892292023,
|
| 1571 |
+
"learning_rate": 5.797914995990377e-06,
|
| 1572 |
+
"loss": 0.008033422380685806,
|
| 1573 |
+
"step": 2050
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 8.917748917748918,
|
| 1577 |
+
"grad_norm": 0.09097876399755478,
|
| 1578 |
+
"learning_rate": 5.717722534081796e-06,
|
| 1579 |
+
"loss": 0.007979495823383332,
|
| 1580 |
+
"step": 2060
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 8.96103896103896,
|
| 1584 |
+
"grad_norm": 0.04881996661424637,
|
| 1585 |
+
"learning_rate": 5.637530072173216e-06,
|
| 1586 |
+
"loss": 0.014459139108657837,
|
| 1587 |
+
"step": 2070
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 9.0,
|
| 1591 |
+
"eval_f1_hate": 0.9496402877697842,
|
| 1592 |
+
"eval_f1_identity_attack": 0.9272727272727272,
|
| 1593 |
+
"eval_f1_insult": 0.970873786407767,
|
| 1594 |
+
"eval_f1_macro": 0.9617095463461544,
|
| 1595 |
+
"eval_f1_micro": 0.9676746611053181,
|
| 1596 |
+
"eval_f1_sexual": 1.0,
|
| 1597 |
+
"eval_f1_threat": 0.935064935064935,
|
| 1598 |
+
"eval_f1_toxicity": 0.9874055415617129,
|
| 1599 |
+
"eval_loss": 0.06829648464918137,
|
| 1600 |
+
"eval_runtime": 2.5638,
|
| 1601 |
+
"eval_samples_per_second": 126.766,
|
| 1602 |
+
"eval_steps_per_second": 15.992,
|
| 1603 |
+
"step": 2079
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 9.004329004329005,
|
| 1607 |
+
"grad_norm": 0.10560577362775803,
|
| 1608 |
+
"learning_rate": 5.557337610264636e-06,
|
| 1609 |
+
"loss": 0.01639609634876251,
|
| 1610 |
+
"step": 2080
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 9.047619047619047,
|
| 1614 |
+
"grad_norm": 0.06842140108346939,
|
| 1615 |
+
"learning_rate": 5.477145148356055e-06,
|
| 1616 |
+
"loss": 0.027546045184135438,
|
| 1617 |
+
"step": 2090
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 9.090909090909092,
|
| 1621 |
+
"grad_norm": 0.380849689245224,
|
| 1622 |
+
"learning_rate": 5.396952686447474e-06,
|
| 1623 |
+
"loss": 0.00970921739935875,
|
| 1624 |
+
"step": 2100
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 9.134199134199134,
|
| 1628 |
+
"grad_norm": 0.06947353482246399,
|
| 1629 |
+
"learning_rate": 5.3167602245388936e-06,
|
| 1630 |
+
"loss": 0.006932146847248077,
|
| 1631 |
+
"step": 2110
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 9.177489177489177,
|
| 1635 |
+
"grad_norm": 0.05276697501540184,
|
| 1636 |
+
"learning_rate": 5.236567762630313e-06,
|
| 1637 |
+
"loss": 0.0077086232602596285,
|
| 1638 |
+
"step": 2120
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 9.220779220779221,
|
| 1642 |
+
"grad_norm": 0.03769112378358841,
|
| 1643 |
+
"learning_rate": 5.156375300721732e-06,
|
| 1644 |
+
"loss": 0.031344258785247804,
|
| 1645 |
+
"step": 2130
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 9.264069264069263,
|
| 1649 |
+
"grad_norm": 0.0876459851861,
|
| 1650 |
+
"learning_rate": 5.076182838813152e-06,
|
| 1651 |
+
"loss": 0.015288634598255158,
|
| 1652 |
+
"step": 2140
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 9.307359307359308,
|
| 1656 |
+
"grad_norm": 0.043145306408405304,
|
| 1657 |
+
"learning_rate": 4.995990376904572e-06,
|
| 1658 |
+
"loss": 0.011774497479200364,
|
| 1659 |
+
"step": 2150
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 9.35064935064935,
|
| 1663 |
+
"grad_norm": 0.038514334708452225,
|
| 1664 |
+
"learning_rate": 4.915797914995991e-06,
|
| 1665 |
+
"loss": 0.006795006990432739,
|
| 1666 |
+
"step": 2160
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 9.393939393939394,
|
| 1670 |
+
"grad_norm": 0.08487548679113388,
|
| 1671 |
+
"learning_rate": 4.8356054530874105e-06,
|
| 1672 |
+
"loss": 0.009026169031858444,
|
| 1673 |
+
"step": 2170
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 9.437229437229437,
|
| 1677 |
+
"grad_norm": 0.04390149191021919,
|
| 1678 |
+
"learning_rate": 4.7554129911788294e-06,
|
| 1679 |
+
"loss": 0.006690967828035355,
|
| 1680 |
+
"step": 2180
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 9.480519480519481,
|
| 1684 |
+
"grad_norm": 0.038950540125370026,
|
| 1685 |
+
"learning_rate": 4.675220529270249e-06,
|
| 1686 |
+
"loss": 0.0060188788920640945,
|
| 1687 |
+
"step": 2190
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 9.523809523809524,
|
| 1691 |
+
"grad_norm": 0.642978847026825,
|
| 1692 |
+
"learning_rate": 4.595028067361668e-06,
|
| 1693 |
+
"loss": 0.022261470556259155,
|
| 1694 |
+
"step": 2200
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 9.567099567099568,
|
| 1698 |
+
"grad_norm": 0.052926789969205856,
|
| 1699 |
+
"learning_rate": 4.514835605453088e-06,
|
| 1700 |
+
"loss": 0.03473313748836517,
|
| 1701 |
+
"step": 2210
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 9.61038961038961,
|
| 1705 |
+
"grad_norm": 0.22621260583400726,
|
| 1706 |
+
"learning_rate": 4.434643143544507e-06,
|
| 1707 |
+
"loss": 0.006864982843399048,
|
| 1708 |
+
"step": 2220
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 9.653679653679653,
|
| 1712 |
+
"grad_norm": 0.0267812330275774,
|
| 1713 |
+
"learning_rate": 4.354450681635927e-06,
|
| 1714 |
+
"loss": 0.007071622461080551,
|
| 1715 |
+
"step": 2230
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 9.696969696969697,
|
| 1719 |
+
"grad_norm": 0.060379091650247574,
|
| 1720 |
+
"learning_rate": 4.2742582197273455e-06,
|
| 1721 |
+
"loss": 0.007905981689691543,
|
| 1722 |
+
"step": 2240
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 9.74025974025974,
|
| 1726 |
+
"grad_norm": 0.043072640895843506,
|
| 1727 |
+
"learning_rate": 4.194065757818765e-06,
|
| 1728 |
+
"loss": 0.008212245255708694,
|
| 1729 |
+
"step": 2250
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 9.783549783549784,
|
| 1733 |
+
"grad_norm": 0.06793437898159027,
|
| 1734 |
+
"learning_rate": 4.113873295910184e-06,
|
| 1735 |
+
"loss": 0.00838496834039688,
|
| 1736 |
+
"step": 2260
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 9.826839826839826,
|
| 1740 |
+
"grad_norm": 0.21440571546554565,
|
| 1741 |
+
"learning_rate": 4.033680834001604e-06,
|
| 1742 |
+
"loss": 0.01173497959971428,
|
| 1743 |
+
"step": 2270
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 9.87012987012987,
|
| 1747 |
+
"grad_norm": 0.07421120256185532,
|
| 1748 |
+
"learning_rate": 3.953488372093024e-06,
|
| 1749 |
+
"loss": 0.008673172444105148,
|
| 1750 |
+
"step": 2280
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 9.913419913419913,
|
| 1754 |
+
"grad_norm": 0.05863242223858833,
|
| 1755 |
+
"learning_rate": 3.873295910184443e-06,
|
| 1756 |
+
"loss": 0.006766989827156067,
|
| 1757 |
+
"step": 2290
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 9.956709956709958,
|
| 1761 |
+
"grad_norm": 0.7983549237251282,
|
| 1762 |
+
"learning_rate": 3.793103448275862e-06,
|
| 1763 |
+
"loss": 0.007381130754947662,
|
| 1764 |
+
"step": 2300
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 10.0,
|
| 1768 |
+
"grad_norm": 0.03677091374993324,
|
| 1769 |
+
"learning_rate": 3.712910986367282e-06,
|
| 1770 |
+
"loss": 0.00792955756187439,
|
| 1771 |
+
"step": 2310
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 10.0,
|
| 1775 |
+
"eval_f1_hate": 0.9496402877697842,
|
| 1776 |
+
"eval_f1_identity_attack": 0.9357798165137615,
|
| 1777 |
+
"eval_f1_insult": 0.9702970297029703,
|
| 1778 |
+
"eval_f1_macro": 0.9654802455677491,
|
| 1779 |
+
"eval_f1_micro": 0.9704641350210971,
|
| 1780 |
+
"eval_f1_sexual": 1.0,
|
| 1781 |
+
"eval_f1_threat": 0.9473684210526315,
|
| 1782 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1783 |
+
"eval_loss": 0.06511212140321732,
|
| 1784 |
+
"eval_runtime": 2.45,
|
| 1785 |
+
"eval_samples_per_second": 132.655,
|
| 1786 |
+
"eval_steps_per_second": 16.735,
|
| 1787 |
+
"step": 2310
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 10.043290043290042,
|
| 1791 |
+
"grad_norm": 0.03262697532773018,
|
| 1792 |
+
"learning_rate": 3.632718524458701e-06,
|
| 1793 |
+
"loss": 0.017550432682037355,
|
| 1794 |
+
"step": 2320
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 10.086580086580087,
|
| 1798 |
+
"grad_norm": 0.15889312326908112,
|
| 1799 |
+
"learning_rate": 3.5525260625501205e-06,
|
| 1800 |
+
"loss": 0.009385860711336135,
|
| 1801 |
+
"step": 2330
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 10.12987012987013,
|
| 1805 |
+
"grad_norm": 0.03570404648780823,
|
| 1806 |
+
"learning_rate": 3.47233360064154e-06,
|
| 1807 |
+
"loss": 0.006462970376014709,
|
| 1808 |
+
"step": 2340
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 10.173160173160174,
|
| 1812 |
+
"grad_norm": 0.05796288326382637,
|
| 1813 |
+
"learning_rate": 3.3921411387329597e-06,
|
| 1814 |
+
"loss": 0.034926030039787295,
|
| 1815 |
+
"step": 2350
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 10.216450216450216,
|
| 1819 |
+
"grad_norm": 0.04328539967536926,
|
| 1820 |
+
"learning_rate": 3.3119486768243786e-06,
|
| 1821 |
+
"loss": 0.007092902064323425,
|
| 1822 |
+
"step": 2360
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 10.25974025974026,
|
| 1826 |
+
"grad_norm": 0.03778962790966034,
|
| 1827 |
+
"learning_rate": 3.2317562149157984e-06,
|
| 1828 |
+
"loss": 0.014847326278686523,
|
| 1829 |
+
"step": 2370
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 10.303030303030303,
|
| 1833 |
+
"grad_norm": 0.20529219508171082,
|
| 1834 |
+
"learning_rate": 3.1515637530072173e-06,
|
| 1835 |
+
"loss": 0.016094820201396944,
|
| 1836 |
+
"step": 2380
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 10.346320346320347,
|
| 1840 |
+
"grad_norm": 0.06534869968891144,
|
| 1841 |
+
"learning_rate": 3.071371291098637e-06,
|
| 1842 |
+
"loss": 0.006908760219812393,
|
| 1843 |
+
"step": 2390
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 10.38961038961039,
|
| 1847 |
+
"grad_norm": 0.05771664157509804,
|
| 1848 |
+
"learning_rate": 2.991178829190056e-06,
|
| 1849 |
+
"loss": 0.00651869922876358,
|
| 1850 |
+
"step": 2400
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 10.432900432900432,
|
| 1854 |
+
"grad_norm": 0.07073244452476501,
|
| 1855 |
+
"learning_rate": 2.9109863672814758e-06,
|
| 1856 |
+
"loss": 0.01936003863811493,
|
| 1857 |
+
"step": 2410
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 10.476190476190476,
|
| 1861 |
+
"grad_norm": 0.027323178946971893,
|
| 1862 |
+
"learning_rate": 2.830793905372895e-06,
|
| 1863 |
+
"loss": 0.010300172865390778,
|
| 1864 |
+
"step": 2420
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 10.519480519480519,
|
| 1868 |
+
"grad_norm": 0.10109654068946838,
|
| 1869 |
+
"learning_rate": 2.7506014434643145e-06,
|
| 1870 |
+
"loss": 0.00660090297460556,
|
| 1871 |
+
"step": 2430
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 10.562770562770563,
|
| 1875 |
+
"grad_norm": 0.025898031890392303,
|
| 1876 |
+
"learning_rate": 2.670408981555734e-06,
|
| 1877 |
+
"loss": 0.008827462792396545,
|
| 1878 |
+
"step": 2440
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 10.606060606060606,
|
| 1882 |
+
"grad_norm": 0.03746366500854492,
|
| 1883 |
+
"learning_rate": 2.5902165196471536e-06,
|
| 1884 |
+
"loss": 0.006242872774600982,
|
| 1885 |
+
"step": 2450
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 10.64935064935065,
|
| 1889 |
+
"grad_norm": 0.027787530794739723,
|
| 1890 |
+
"learning_rate": 2.5100240577385725e-06,
|
| 1891 |
+
"loss": 0.008383957296609878,
|
| 1892 |
+
"step": 2460
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 10.692640692640692,
|
| 1896 |
+
"grad_norm": 0.08420351892709732,
|
| 1897 |
+
"learning_rate": 2.4298315958299923e-06,
|
| 1898 |
+
"loss": 0.007070781290531158,
|
| 1899 |
+
"step": 2470
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 10.735930735930737,
|
| 1903 |
+
"grad_norm": 0.03632546588778496,
|
| 1904 |
+
"learning_rate": 2.3496391339214116e-06,
|
| 1905 |
+
"loss": 0.033319640159606936,
|
| 1906 |
+
"step": 2480
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 10.779220779220779,
|
| 1910 |
+
"grad_norm": 0.3003116548061371,
|
| 1911 |
+
"learning_rate": 2.269446672012831e-06,
|
| 1912 |
+
"loss": 0.006795042008161545,
|
| 1913 |
+
"step": 2490
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 10.822510822510823,
|
| 1917 |
+
"grad_norm": 0.030215242877602577,
|
| 1918 |
+
"learning_rate": 2.1892542101042503e-06,
|
| 1919 |
+
"loss": 0.007315768301486969,
|
| 1920 |
+
"step": 2500
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 10.865800865800866,
|
| 1924 |
+
"grad_norm": 0.03005411848425865,
|
| 1925 |
+
"learning_rate": 2.1090617481956697e-06,
|
| 1926 |
+
"loss": 0.007162563502788544,
|
| 1927 |
+
"step": 2510
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 10.909090909090908,
|
| 1931 |
+
"grad_norm": 0.03618185967206955,
|
| 1932 |
+
"learning_rate": 2.0288692862870895e-06,
|
| 1933 |
+
"loss": 0.006317664682865143,
|
| 1934 |
+
"step": 2520
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 10.952380952380953,
|
| 1938 |
+
"grad_norm": 0.0410848893225193,
|
| 1939 |
+
"learning_rate": 1.948676824378509e-06,
|
| 1940 |
+
"loss": 0.0280388206243515,
|
| 1941 |
+
"step": 2530
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 10.995670995670995,
|
| 1945 |
+
"grad_norm": 0.11858250945806503,
|
| 1946 |
+
"learning_rate": 1.8684843624699282e-06,
|
| 1947 |
+
"loss": 0.009880727529525757,
|
| 1948 |
+
"step": 2540
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 11.0,
|
| 1952 |
+
"eval_f1_hate": 0.9565217391304348,
|
| 1953 |
+
"eval_f1_identity_attack": 0.9444444444444444,
|
| 1954 |
+
"eval_f1_insult": 0.9702970297029703,
|
| 1955 |
+
"eval_f1_macro": 0.9680712587829715,
|
| 1956 |
+
"eval_f1_micro": 0.9725158562367865,
|
| 1957 |
+
"eval_f1_sexual": 1.0,
|
| 1958 |
+
"eval_f1_threat": 0.9473684210526315,
|
| 1959 |
+
"eval_f1_toxicity": 0.9897959183673469,
|
| 1960 |
+
"eval_loss": 0.061376653611660004,
|
| 1961 |
+
"eval_runtime": 2.5087,
|
| 1962 |
+
"eval_samples_per_second": 129.551,
|
| 1963 |
+
"eval_steps_per_second": 16.343,
|
| 1964 |
+
"step": 2541
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 11.03896103896104,
|
| 1968 |
+
"grad_norm": 0.03915450721979141,
|
| 1969 |
+
"learning_rate": 1.7882919005613475e-06,
|
| 1970 |
+
"loss": 0.006504032760858536,
|
| 1971 |
+
"step": 2550
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 11.082251082251082,
|
| 1975 |
+
"grad_norm": 0.03583554923534393,
|
| 1976 |
+
"learning_rate": 1.7080994386527669e-06,
|
| 1977 |
+
"loss": 0.0073525868356227875,
|
| 1978 |
+
"step": 2560
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 11.125541125541126,
|
| 1982 |
+
"grad_norm": 0.3565763533115387,
|
| 1983 |
+
"learning_rate": 1.6279069767441862e-06,
|
| 1984 |
+
"loss": 0.010951676219701768,
|
| 1985 |
+
"step": 2570
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 11.168831168831169,
|
| 1989 |
+
"grad_norm": 0.05878825485706329,
|
| 1990 |
+
"learning_rate": 1.5477145148356058e-06,
|
| 1991 |
+
"loss": 0.01697569489479065,
|
| 1992 |
+
"step": 2580
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 11.212121212121213,
|
| 1996 |
+
"grad_norm": 0.029903510585427284,
|
| 1997 |
+
"learning_rate": 1.4675220529270251e-06,
|
| 1998 |
+
"loss": 0.008652069419622422,
|
| 1999 |
+
"step": 2590
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 11.255411255411255,
|
| 2003 |
+
"grad_norm": 37.61043167114258,
|
| 2004 |
+
"learning_rate": 1.3873295910184445e-06,
|
| 2005 |
+
"loss": 0.02579624652862549,
|
| 2006 |
+
"step": 2600
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 11.2987012987013,
|
| 2010 |
+
"grad_norm": 0.04017391428351402,
|
| 2011 |
+
"learning_rate": 1.3071371291098638e-06,
|
| 2012 |
+
"loss": 0.00610797293484211,
|
| 2013 |
+
"step": 2610
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 11.341991341991342,
|
| 2017 |
+
"grad_norm": 0.028649600222706795,
|
| 2018 |
+
"learning_rate": 1.2269446672012832e-06,
|
| 2019 |
+
"loss": 0.011433736234903336,
|
| 2020 |
+
"step": 2620
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 11.385281385281385,
|
| 2024 |
+
"grad_norm": 0.03015207313001156,
|
| 2025 |
+
"learning_rate": 1.1467522052927025e-06,
|
| 2026 |
+
"loss": 0.0057866271585226055,
|
| 2027 |
+
"step": 2630
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 11.428571428571429,
|
| 2031 |
+
"grad_norm": 0.09629103541374207,
|
| 2032 |
+
"learning_rate": 1.0665597433841219e-06,
|
| 2033 |
+
"loss": 0.006508632749319077,
|
| 2034 |
+
"step": 2640
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 11.471861471861471,
|
| 2038 |
+
"grad_norm": 0.03100382722914219,
|
| 2039 |
+
"learning_rate": 9.863672814755414e-07,
|
| 2040 |
+
"loss": 0.006996200978755951,
|
| 2041 |
+
"step": 2650
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 11.515151515151516,
|
| 2045 |
+
"grad_norm": 0.03666034713387489,
|
| 2046 |
+
"learning_rate": 9.061748195669608e-07,
|
| 2047 |
+
"loss": 0.020520102977752686,
|
| 2048 |
+
"step": 2660
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 11.558441558441558,
|
| 2052 |
+
"grad_norm": 0.027687091380357742,
|
| 2053 |
+
"learning_rate": 8.259823576583801e-07,
|
| 2054 |
+
"loss": 0.009226586669683456,
|
| 2055 |
+
"step": 2670
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 11.601731601731602,
|
| 2059 |
+
"grad_norm": 0.8026447296142578,
|
| 2060 |
+
"learning_rate": 7.457898957497996e-07,
|
| 2061 |
+
"loss": 0.006435560435056687,
|
| 2062 |
+
"step": 2680
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 11.645021645021645,
|
| 2066 |
+
"grad_norm": 0.04445148631930351,
|
| 2067 |
+
"learning_rate": 6.65597433841219e-07,
|
| 2068 |
+
"loss": 0.02734784483909607,
|
| 2069 |
+
"step": 2690
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 11.688311688311689,
|
| 2073 |
+
"grad_norm": 0.07898417115211487,
|
| 2074 |
+
"learning_rate": 5.854049719326384e-07,
|
| 2075 |
+
"loss": 0.006259865313768387,
|
| 2076 |
+
"step": 2700
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 11.731601731601732,
|
| 2080 |
+
"grad_norm": 0.04267798736691475,
|
| 2081 |
+
"learning_rate": 5.052125100240578e-07,
|
| 2082 |
+
"loss": 0.00599234588444233,
|
| 2083 |
+
"step": 2710
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 11.774891774891774,
|
| 2087 |
+
"grad_norm": 0.03772784397006035,
|
| 2088 |
+
"learning_rate": 4.2502004811547716e-07,
|
| 2089 |
+
"loss": 0.007799781858921051,
|
| 2090 |
+
"step": 2720
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 11.818181818181818,
|
| 2094 |
+
"grad_norm": 0.023072121664881706,
|
| 2095 |
+
"learning_rate": 3.4482758620689656e-07,
|
| 2096 |
+
"loss": 0.0050474125891923904,
|
| 2097 |
+
"step": 2730
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 11.86147186147186,
|
| 2101 |
+
"grad_norm": 0.045962199568748474,
|
| 2102 |
+
"learning_rate": 2.6463512429831596e-07,
|
| 2103 |
+
"loss": 0.006433556228876114,
|
| 2104 |
+
"step": 2740
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 11.904761904761905,
|
| 2108 |
+
"grad_norm": 0.033537011593580246,
|
| 2109 |
+
"learning_rate": 1.8444266238973537e-07,
|
| 2110 |
+
"loss": 0.012848450243473053,
|
| 2111 |
+
"step": 2750
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 11.948051948051948,
|
| 2115 |
+
"grad_norm": 0.02839348092675209,
|
| 2116 |
+
"learning_rate": 1.0425020048115478e-07,
|
| 2117 |
+
"loss": 0.012602794170379638,
|
| 2118 |
+
"step": 2760
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 11.991341991341992,
|
| 2122 |
+
"grad_norm": 0.04493549466133118,
|
| 2123 |
+
"learning_rate": 2.405773857257418e-08,
|
| 2124 |
+
"loss": 0.006070166081190109,
|
| 2125 |
+
"step": 2770
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 12.0,
|
| 2129 |
+
"eval_f1_hate": 0.9635036496350365,
|
| 2130 |
+
"eval_f1_identity_attack": 0.9444444444444444,
|
| 2131 |
+
"eval_f1_insult": 0.9902912621359223,
|
| 2132 |
+
"eval_f1_macro": 0.9713713581913931,
|
| 2133 |
+
"eval_f1_micro": 0.9789915966386554,
|
| 2134 |
+
"eval_f1_sexual": 1.0,
|
| 2135 |
+
"eval_f1_threat": 0.935064935064935,
|
| 2136 |
+
"eval_f1_toxicity": 0.9949238578680203,
|
| 2137 |
+
"eval_loss": 0.05005016177892685,
|
| 2138 |
+
"eval_runtime": 2.6279,
|
| 2139 |
+
"eval_samples_per_second": 123.671,
|
| 2140 |
+
"eval_steps_per_second": 15.602,
|
| 2141 |
+
"step": 2772
|
| 2142 |
+
}
|
| 2143 |
+
],
|
| 2144 |
+
"logging_steps": 10,
|
| 2145 |
+
"max_steps": 2772,
|
| 2146 |
+
"num_input_tokens_seen": 0,
|
| 2147 |
+
"num_train_epochs": 12,
|
| 2148 |
+
"save_steps": 500,
|
| 2149 |
+
"stateful_callbacks": {
|
| 2150 |
+
"TrainerControl": {
|
| 2151 |
+
"args": {
|
| 2152 |
+
"should_epoch_stop": false,
|
| 2153 |
+
"should_evaluate": false,
|
| 2154 |
+
"should_log": false,
|
| 2155 |
+
"should_save": true,
|
| 2156 |
+
"should_training_stop": true
|
| 2157 |
+
},
|
| 2158 |
+
"attributes": {}
|
| 2159 |
+
}
|
| 2160 |
+
},
|
| 2161 |
+
"total_flos": 1453214548187136.0,
|
| 2162 |
+
"train_batch_size": 8,
|
| 2163 |
+
"trial_name": null,
|
| 2164 |
+
"trial_params": null
|
| 2165 |
+
}
|
checkpoint-2772/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a69174491030931c18f76759e2267cecfc7446af536f338aa4983fbf2de13b9
|
| 3 |
+
size 5265
|
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"XLMRobertaForSequenceClassification"
|
| 4 |
],
|
|
@@ -11,22 +12,23 @@
|
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
-
"0": "
|
| 15 |
-
"1": "
|
| 16 |
-
"2": "
|
| 17 |
-
"3": "
|
| 18 |
-
"4": "
|
| 19 |
-
"5": "
|
| 20 |
},
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
|
|
|
| 23 |
"label2id": {
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
},
|
| 31 |
"layer_norm_eps": 1e-05,
|
| 32 |
"max_position_embeddings": 514,
|
|
@@ -37,9 +39,9 @@
|
|
| 37 |
"pad_token_id": 1,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
"problem_type": "multi_label_classification",
|
| 40 |
-
"
|
|
|
|
| 41 |
"type_vocab_size": 1,
|
| 42 |
-
"use_cache":
|
| 43 |
-
"vocab_size": 250002
|
| 44 |
-
|
| 45 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
|
|
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 768,
|
| 14 |
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5"
|
| 21 |
},
|
| 22 |
"initializer_range": 0.02,
|
| 23 |
"intermediate_size": 3072,
|
| 24 |
+
"is_decoder": false,
|
| 25 |
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5
|
| 32 |
},
|
| 33 |
"layer_norm_eps": 1e-05,
|
| 34 |
"max_position_embeddings": 514,
|
|
|
|
| 39 |
"pad_token_id": 1,
|
| 40 |
"position_embedding_type": "absolute",
|
| 41 |
"problem_type": "multi_label_classification",
|
| 42 |
+
"tie_word_embeddings": true,
|
| 43 |
+
"transformers_version": "5.2.0",
|
| 44 |
"type_vocab_size": 1,
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 250002
|
| 47 |
+
}
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1212bfb8edecdc0b19b88680bba6cbe8595f45ef2a8c900cff6ecc3ea49da3
|
| 3 |
+
size 1112217288
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5b633524ba90477daaba16ec27580a08a2856ae0ee8c33d9f5f9358378d3b35
|
| 3 |
+
size 16781751
|
tokenizer_config.json
CHANGED
|
@@ -1,51 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
"content": "<s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<pad>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"250001": {
|
| 36 |
-
"content": "<mask>",
|
| 37 |
-
"lstrip": true,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
"bos_token": "<s>",
|
| 45 |
-
"clean_up_tokenization_spaces": false,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
-
"
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "<pad>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "<s>",
|
|
|
|
| 5 |
"cls_token": "<s>",
|
| 6 |
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
"mask_token": "<mask>",
|
| 9 |
"model_max_length": 512,
|
| 10 |
"pad_token": "<pad>",
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a69174491030931c18f76759e2267cecfc7446af536f338aa4983fbf2de13b9
|
| 3 |
+
size 5265
|