Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-774/config.json +85 -0
- checkpoint-774/model.safetensors +3 -0
- checkpoint-774/optimizer.pt +3 -0
- checkpoint-774/rng_state.pth +3 -0
- checkpoint-774/scheduler.pt +3 -0
- checkpoint-774/trainer_state.json +544 -0
- checkpoint-774/training_args.bin +3 -0
- config.json +85 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr14_22-22-07_r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq/events.out.tfevents.1744669329.r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq.136.0 +2 -2
- runs/Apr14_22-22-07_r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq/events.out.tfevents.1744673038.r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq.136.1 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- autotrain
|
| 6 |
+
- text-classification
|
| 7 |
+
base_model: FacebookAI/roberta-base
|
| 8 |
+
widget:
|
| 9 |
+
- text: "I love AutoTrain"
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Trained Using AutoTrain
|
| 13 |
+
|
| 14 |
+
- Problem type: Text Classification
|
| 15 |
+
|
| 16 |
+
## Validation Metrics
|
| 17 |
+
loss: 1.0832968950271606
|
| 18 |
+
|
| 19 |
+
f1_macro: 0.41533378210893174
|
| 20 |
+
|
| 21 |
+
f1_micro: 0.6531007751937985
|
| 22 |
+
|
| 23 |
+
f1_weighted: 0.6340857128792562
|
| 24 |
+
|
| 25 |
+
precision_macro: 0.43774810378738616
|
| 26 |
+
|
| 27 |
+
precision_micro: 0.6531007751937985
|
| 28 |
+
|
| 29 |
+
precision_weighted: 0.6386639752005375
|
| 30 |
+
|
| 31 |
+
recall_macro: 0.4299005706500963
|
| 32 |
+
|
| 33 |
+
recall_micro: 0.6531007751937985
|
| 34 |
+
|
| 35 |
+
recall_weighted: 0.6531007751937985
|
| 36 |
+
|
| 37 |
+
accuracy: 0.6531007751937985
|
checkpoint-774/config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
+
"_num_labels": 26,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Unknown",
|
| 16 |
+
"1": "apology-baiting",
|
| 17 |
+
"2": "apology-baiting ",
|
| 18 |
+
"3": "apology_baiting",
|
| 19 |
+
"4": "blame_shifting",
|
| 20 |
+
"5": "contradictory-statements",
|
| 21 |
+
"6": "control",
|
| 22 |
+
"7": "deflection",
|
| 23 |
+
"8": "dismissiveness",
|
| 24 |
+
"9": "extreme_control",
|
| 25 |
+
"10": "gaslighting",
|
| 26 |
+
"11": "gaslighting ",
|
| 27 |
+
"12": "guilt-tripping",
|
| 28 |
+
"13": "guilt-tripping ",
|
| 29 |
+
"14": "insults",
|
| 30 |
+
"15": "manipulation",
|
| 31 |
+
"16": "mockery",
|
| 32 |
+
"17": "non_abusive",
|
| 33 |
+
"18": "obscure language",
|
| 34 |
+
"19": "obscure-formal",
|
| 35 |
+
"20": "obscure_formal",
|
| 36 |
+
"21": "physical_threat",
|
| 37 |
+
"22": "projection",
|
| 38 |
+
"23": "recovery-phase",
|
| 39 |
+
"24": "suicidal_threat",
|
| 40 |
+
"25": "suicidal_threat "
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 3072,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"Unknown": 0,
|
| 46 |
+
"apology-baiting": 1,
|
| 47 |
+
"apology-baiting ": 2,
|
| 48 |
+
"apology_baiting": 3,
|
| 49 |
+
"blame_shifting": 4,
|
| 50 |
+
"contradictory-statements": 5,
|
| 51 |
+
"control": 6,
|
| 52 |
+
"deflection": 7,
|
| 53 |
+
"dismissiveness": 8,
|
| 54 |
+
"extreme_control": 9,
|
| 55 |
+
"gaslighting": 10,
|
| 56 |
+
"gaslighting ": 11,
|
| 57 |
+
"guilt-tripping": 12,
|
| 58 |
+
"guilt-tripping ": 13,
|
| 59 |
+
"insults": 14,
|
| 60 |
+
"manipulation": 15,
|
| 61 |
+
"mockery": 16,
|
| 62 |
+
"non_abusive": 17,
|
| 63 |
+
"obscure language": 18,
|
| 64 |
+
"obscure-formal": 19,
|
| 65 |
+
"obscure_formal": 20,
|
| 66 |
+
"physical_threat": 21,
|
| 67 |
+
"projection": 22,
|
| 68 |
+
"recovery-phase": 23,
|
| 69 |
+
"suicidal_threat": 24,
|
| 70 |
+
"suicidal_threat ": 25
|
| 71 |
+
},
|
| 72 |
+
"layer_norm_eps": 1e-05,
|
| 73 |
+
"max_position_embeddings": 514,
|
| 74 |
+
"model_type": "roberta",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_hidden_layers": 12,
|
| 77 |
+
"pad_token_id": 1,
|
| 78 |
+
"position_embedding_type": "absolute",
|
| 79 |
+
"problem_type": "single_label_classification",
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.48.0",
|
| 82 |
+
"type_vocab_size": 1,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"vocab_size": 50265
|
| 85 |
+
}
|
checkpoint-774/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39aca7da0e7eff911ebec52496ec531cb9889e8a9fd59cc55da2d6b4b1d8e08
|
| 3 |
+
size 498686648
|
checkpoint-774/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2fa1a746553f6b51c9b20897fa53b9667dd9fa401e88c3666c1620dd7c6add6
|
| 3 |
+
size 997487482
|
checkpoint-774/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e43b900ac96f77c4b789931c37dd2a1c30c2e43f335cc5efbea859605f6e539f
|
| 3 |
+
size 13990
|
checkpoint-774/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1961bf4e3a8bd07630d05ed86c09a75c5fc9754cd2f557dc59a19d03edff4f2
|
| 3 |
+
size 1064
|
checkpoint-774/trainer_state.json
ADDED
|
@@ -0,0 +1,544 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0832968950271606,
|
| 3 |
+
"best_model_checkpoint": "Tether2/checkpoint-774",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 774,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.046511627906976744,
|
| 13 |
+
"grad_norm": 3.96823787689209,
|
| 14 |
+
"learning_rate": 7.692307692307694e-06,
|
| 15 |
+
"loss": 3.2522,
|
| 16 |
+
"step": 12
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.09302325581395349,
|
| 20 |
+
"grad_norm": 5.03609561920166,
|
| 21 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 22 |
+
"loss": 3.2157,
|
| 23 |
+
"step": 24
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13953488372093023,
|
| 27 |
+
"grad_norm": 6.75431489944458,
|
| 28 |
+
"learning_rate": 2.307692307692308e-05,
|
| 29 |
+
"loss": 3.1114,
|
| 30 |
+
"step": 36
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.18604651162790697,
|
| 34 |
+
"grad_norm": 22.154630661010742,
|
| 35 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 36 |
+
"loss": 2.9807,
|
| 37 |
+
"step": 48
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.23255813953488372,
|
| 41 |
+
"grad_norm": 9.958882331848145,
|
| 42 |
+
"learning_rate": 3.846153846153846e-05,
|
| 43 |
+
"loss": 2.8858,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27906976744186046,
|
| 48 |
+
"grad_norm": 8.20565128326416,
|
| 49 |
+
"learning_rate": 4.615384615384616e-05,
|
| 50 |
+
"loss": 2.7925,
|
| 51 |
+
"step": 72
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.32558139534883723,
|
| 55 |
+
"grad_norm": 9.204078674316406,
|
| 56 |
+
"learning_rate": 4.9568965517241384e-05,
|
| 57 |
+
"loss": 2.8233,
|
| 58 |
+
"step": 84
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.37209302325581395,
|
| 62 |
+
"grad_norm": 10.973845481872559,
|
| 63 |
+
"learning_rate": 4.870689655172414e-05,
|
| 64 |
+
"loss": 2.8384,
|
| 65 |
+
"step": 96
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4186046511627907,
|
| 69 |
+
"grad_norm": 9.10534381866455,
|
| 70 |
+
"learning_rate": 4.78448275862069e-05,
|
| 71 |
+
"loss": 2.6588,
|
| 72 |
+
"step": 108
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.46511627906976744,
|
| 76 |
+
"grad_norm": 7.395918846130371,
|
| 77 |
+
"learning_rate": 4.698275862068966e-05,
|
| 78 |
+
"loss": 2.5407,
|
| 79 |
+
"step": 120
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5116279069767442,
|
| 83 |
+
"grad_norm": 12.590022087097168,
|
| 84 |
+
"learning_rate": 4.612068965517242e-05,
|
| 85 |
+
"loss": 2.4686,
|
| 86 |
+
"step": 132
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5581395348837209,
|
| 90 |
+
"grad_norm": 8.628605842590332,
|
| 91 |
+
"learning_rate": 4.5258620689655176e-05,
|
| 92 |
+
"loss": 2.3784,
|
| 93 |
+
"step": 144
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6046511627906976,
|
| 97 |
+
"grad_norm": 12.470245361328125,
|
| 98 |
+
"learning_rate": 4.4396551724137933e-05,
|
| 99 |
+
"loss": 2.2395,
|
| 100 |
+
"step": 156
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6511627906976745,
|
| 104 |
+
"grad_norm": 10.687325477600098,
|
| 105 |
+
"learning_rate": 4.353448275862069e-05,
|
| 106 |
+
"loss": 2.3603,
|
| 107 |
+
"step": 168
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6976744186046512,
|
| 111 |
+
"grad_norm": 12.147785186767578,
|
| 112 |
+
"learning_rate": 4.267241379310345e-05,
|
| 113 |
+
"loss": 2.3779,
|
| 114 |
+
"step": 180
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7441860465116279,
|
| 118 |
+
"grad_norm": 8.938596725463867,
|
| 119 |
+
"learning_rate": 4.1810344827586205e-05,
|
| 120 |
+
"loss": 2.0315,
|
| 121 |
+
"step": 192
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7906976744186046,
|
| 125 |
+
"grad_norm": 16.89861488342285,
|
| 126 |
+
"learning_rate": 4.094827586206897e-05,
|
| 127 |
+
"loss": 1.8416,
|
| 128 |
+
"step": 204
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8372093023255814,
|
| 132 |
+
"grad_norm": 25.249252319335938,
|
| 133 |
+
"learning_rate": 4.0086206896551726e-05,
|
| 134 |
+
"loss": 2.2595,
|
| 135 |
+
"step": 216
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8837209302325582,
|
| 139 |
+
"grad_norm": 19.04043960571289,
|
| 140 |
+
"learning_rate": 3.922413793103448e-05,
|
| 141 |
+
"loss": 2.0284,
|
| 142 |
+
"step": 228
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.9302325581395349,
|
| 146 |
+
"grad_norm": 19.253995895385742,
|
| 147 |
+
"learning_rate": 3.8362068965517246e-05,
|
| 148 |
+
"loss": 1.9197,
|
| 149 |
+
"step": 240
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9767441860465116,
|
| 153 |
+
"grad_norm": 11.264032363891602,
|
| 154 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 155 |
+
"loss": 1.9238,
|
| 156 |
+
"step": 252
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.0,
|
| 160 |
+
"eval_accuracy": 0.5155038759689923,
|
| 161 |
+
"eval_f1_macro": 0.25891991433400224,
|
| 162 |
+
"eval_f1_micro": 0.5155038759689923,
|
| 163 |
+
"eval_f1_weighted": 0.46535411334465737,
|
| 164 |
+
"eval_loss": 1.7225582599639893,
|
| 165 |
+
"eval_precision_macro": 0.2992259890948827,
|
| 166 |
+
"eval_precision_micro": 0.5155038759689923,
|
| 167 |
+
"eval_precision_weighted": 0.4992061498287774,
|
| 168 |
+
"eval_recall_macro": 0.27495621077215004,
|
| 169 |
+
"eval_recall_micro": 0.5155038759689923,
|
| 170 |
+
"eval_recall_weighted": 0.5155038759689923,
|
| 171 |
+
"eval_runtime": 69.7638,
|
| 172 |
+
"eval_samples_per_second": 7.396,
|
| 173 |
+
"eval_steps_per_second": 0.473,
|
| 174 |
+
"step": 258
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0232558139534884,
|
| 178 |
+
"grad_norm": 11.877735137939453,
|
| 179 |
+
"learning_rate": 3.663793103448276e-05,
|
| 180 |
+
"loss": 1.6197,
|
| 181 |
+
"step": 264
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.069767441860465,
|
| 185 |
+
"grad_norm": 15.443757057189941,
|
| 186 |
+
"learning_rate": 3.5775862068965524e-05,
|
| 187 |
+
"loss": 1.7034,
|
| 188 |
+
"step": 276
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.1162790697674418,
|
| 192 |
+
"grad_norm": 20.39283561706543,
|
| 193 |
+
"learning_rate": 3.4913793103448275e-05,
|
| 194 |
+
"loss": 1.4275,
|
| 195 |
+
"step": 288
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.1627906976744187,
|
| 199 |
+
"grad_norm": 21.803442001342773,
|
| 200 |
+
"learning_rate": 3.405172413793103e-05,
|
| 201 |
+
"loss": 1.4556,
|
| 202 |
+
"step": 300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.2093023255813953,
|
| 206 |
+
"grad_norm": 28.840351104736328,
|
| 207 |
+
"learning_rate": 3.3189655172413796e-05,
|
| 208 |
+
"loss": 1.6046,
|
| 209 |
+
"step": 312
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.255813953488372,
|
| 213 |
+
"grad_norm": 12.907221794128418,
|
| 214 |
+
"learning_rate": 3.232758620689655e-05,
|
| 215 |
+
"loss": 1.579,
|
| 216 |
+
"step": 324
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.302325581395349,
|
| 220 |
+
"grad_norm": 14.40406322479248,
|
| 221 |
+
"learning_rate": 3.146551724137931e-05,
|
| 222 |
+
"loss": 1.385,
|
| 223 |
+
"step": 336
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.3488372093023255,
|
| 227 |
+
"grad_norm": 18.017547607421875,
|
| 228 |
+
"learning_rate": 3.060344827586207e-05,
|
| 229 |
+
"loss": 1.4536,
|
| 230 |
+
"step": 348
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3953488372093024,
|
| 234 |
+
"grad_norm": 39.87833023071289,
|
| 235 |
+
"learning_rate": 2.974137931034483e-05,
|
| 236 |
+
"loss": 1.5883,
|
| 237 |
+
"step": 360
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.441860465116279,
|
| 241 |
+
"grad_norm": 19.605663299560547,
|
| 242 |
+
"learning_rate": 2.8879310344827588e-05,
|
| 243 |
+
"loss": 1.5453,
|
| 244 |
+
"step": 372
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.4883720930232558,
|
| 248 |
+
"grad_norm": 12.39608383178711,
|
| 249 |
+
"learning_rate": 2.8017241379310345e-05,
|
| 250 |
+
"loss": 1.3432,
|
| 251 |
+
"step": 384
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.5348837209302326,
|
| 255 |
+
"grad_norm": 20.467025756835938,
|
| 256 |
+
"learning_rate": 2.7155172413793105e-05,
|
| 257 |
+
"loss": 1.4855,
|
| 258 |
+
"step": 396
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.5813953488372094,
|
| 262 |
+
"grad_norm": 12.10073184967041,
|
| 263 |
+
"learning_rate": 2.6293103448275862e-05,
|
| 264 |
+
"loss": 1.1955,
|
| 265 |
+
"step": 408
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.627906976744186,
|
| 269 |
+
"grad_norm": 21.128217697143555,
|
| 270 |
+
"learning_rate": 2.543103448275862e-05,
|
| 271 |
+
"loss": 1.3656,
|
| 272 |
+
"step": 420
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6744186046511627,
|
| 276 |
+
"grad_norm": 27.748998641967773,
|
| 277 |
+
"learning_rate": 2.456896551724138e-05,
|
| 278 |
+
"loss": 1.403,
|
| 279 |
+
"step": 432
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.7209302325581395,
|
| 283 |
+
"grad_norm": 33.165916442871094,
|
| 284 |
+
"learning_rate": 2.370689655172414e-05,
|
| 285 |
+
"loss": 1.2075,
|
| 286 |
+
"step": 444
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.7674418604651163,
|
| 290 |
+
"grad_norm": 23.034250259399414,
|
| 291 |
+
"learning_rate": 2.2844827586206897e-05,
|
| 292 |
+
"loss": 1.3793,
|
| 293 |
+
"step": 456
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.8139534883720931,
|
| 297 |
+
"grad_norm": 26.05168342590332,
|
| 298 |
+
"learning_rate": 2.1982758620689654e-05,
|
| 299 |
+
"loss": 1.1603,
|
| 300 |
+
"step": 468
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8604651162790697,
|
| 304 |
+
"grad_norm": 30.397899627685547,
|
| 305 |
+
"learning_rate": 2.1120689655172415e-05,
|
| 306 |
+
"loss": 1.246,
|
| 307 |
+
"step": 480
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.9069767441860463,
|
| 311 |
+
"grad_norm": 26.444442749023438,
|
| 312 |
+
"learning_rate": 2.0258620689655172e-05,
|
| 313 |
+
"loss": 1.5224,
|
| 314 |
+
"step": 492
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.9534883720930232,
|
| 318 |
+
"grad_norm": 12.157238006591797,
|
| 319 |
+
"learning_rate": 1.9396551724137932e-05,
|
| 320 |
+
"loss": 1.2578,
|
| 321 |
+
"step": 504
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.0,
|
| 325 |
+
"grad_norm": 7.6723833084106445,
|
| 326 |
+
"learning_rate": 1.8534482758620693e-05,
|
| 327 |
+
"loss": 1.0881,
|
| 328 |
+
"step": 516
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.0,
|
| 332 |
+
"eval_accuracy": 0.6337209302325582,
|
| 333 |
+
"eval_f1_macro": 0.38147868610651525,
|
| 334 |
+
"eval_f1_micro": 0.6337209302325582,
|
| 335 |
+
"eval_f1_weighted": 0.606852249582538,
|
| 336 |
+
"eval_loss": 1.1795549392700195,
|
| 337 |
+
"eval_precision_macro": 0.4036122122616632,
|
| 338 |
+
"eval_precision_micro": 0.6337209302325582,
|
| 339 |
+
"eval_precision_weighted": 0.6131562523466949,
|
| 340 |
+
"eval_recall_macro": 0.39422572999423094,
|
| 341 |
+
"eval_recall_micro": 0.6337209302325582,
|
| 342 |
+
"eval_recall_weighted": 0.6337209302325582,
|
| 343 |
+
"eval_runtime": 71.7188,
|
| 344 |
+
"eval_samples_per_second": 7.195,
|
| 345 |
+
"eval_steps_per_second": 0.46,
|
| 346 |
+
"step": 516
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.046511627906977,
|
| 350 |
+
"grad_norm": 24.36311149597168,
|
| 351 |
+
"learning_rate": 1.767241379310345e-05,
|
| 352 |
+
"loss": 0.9298,
|
| 353 |
+
"step": 528
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.0930232558139537,
|
| 357 |
+
"grad_norm": 16.763669967651367,
|
| 358 |
+
"learning_rate": 1.6810344827586207e-05,
|
| 359 |
+
"loss": 0.9922,
|
| 360 |
+
"step": 540
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.13953488372093,
|
| 364 |
+
"grad_norm": 26.640941619873047,
|
| 365 |
+
"learning_rate": 1.5948275862068967e-05,
|
| 366 |
+
"loss": 0.9947,
|
| 367 |
+
"step": 552
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.186046511627907,
|
| 371 |
+
"grad_norm": 34.96234893798828,
|
| 372 |
+
"learning_rate": 1.5086206896551724e-05,
|
| 373 |
+
"loss": 0.8946,
|
| 374 |
+
"step": 564
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.2325581395348837,
|
| 378 |
+
"grad_norm": 24.793346405029297,
|
| 379 |
+
"learning_rate": 1.4224137931034485e-05,
|
| 380 |
+
"loss": 0.9729,
|
| 381 |
+
"step": 576
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.2790697674418605,
|
| 385 |
+
"grad_norm": 8.405088424682617,
|
| 386 |
+
"learning_rate": 1.336206896551724e-05,
|
| 387 |
+
"loss": 0.8749,
|
| 388 |
+
"step": 588
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.3255813953488373,
|
| 392 |
+
"grad_norm": 25.962703704833984,
|
| 393 |
+
"learning_rate": 1.25e-05,
|
| 394 |
+
"loss": 0.9156,
|
| 395 |
+
"step": 600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.3720930232558137,
|
| 399 |
+
"grad_norm": 5.019805431365967,
|
| 400 |
+
"learning_rate": 1.163793103448276e-05,
|
| 401 |
+
"loss": 0.7937,
|
| 402 |
+
"step": 612
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.4186046511627906,
|
| 406 |
+
"grad_norm": 28.168231964111328,
|
| 407 |
+
"learning_rate": 1.0775862068965516e-05,
|
| 408 |
+
"loss": 0.9856,
|
| 409 |
+
"step": 624
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.4651162790697674,
|
| 413 |
+
"grad_norm": 21.698854446411133,
|
| 414 |
+
"learning_rate": 9.913793103448277e-06,
|
| 415 |
+
"loss": 0.7219,
|
| 416 |
+
"step": 636
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.511627906976744,
|
| 420 |
+
"grad_norm": 18.83635139465332,
|
| 421 |
+
"learning_rate": 9.051724137931036e-06,
|
| 422 |
+
"loss": 0.9052,
|
| 423 |
+
"step": 648
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.558139534883721,
|
| 427 |
+
"grad_norm": 14.555943489074707,
|
| 428 |
+
"learning_rate": 8.189655172413793e-06,
|
| 429 |
+
"loss": 0.8442,
|
| 430 |
+
"step": 660
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.604651162790698,
|
| 434 |
+
"grad_norm": 28.036245346069336,
|
| 435 |
+
"learning_rate": 7.3275862068965514e-06,
|
| 436 |
+
"loss": 0.8283,
|
| 437 |
+
"step": 672
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.6511627906976747,
|
| 441 |
+
"grad_norm": 17.01114845275879,
|
| 442 |
+
"learning_rate": 6.465517241379311e-06,
|
| 443 |
+
"loss": 0.8232,
|
| 444 |
+
"step": 684
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.697674418604651,
|
| 448 |
+
"grad_norm": 19.991779327392578,
|
| 449 |
+
"learning_rate": 5.603448275862069e-06,
|
| 450 |
+
"loss": 0.7628,
|
| 451 |
+
"step": 696
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.744186046511628,
|
| 455 |
+
"grad_norm": 26.620668411254883,
|
| 456 |
+
"learning_rate": 4.741379310344828e-06,
|
| 457 |
+
"loss": 0.7945,
|
| 458 |
+
"step": 708
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.7906976744186047,
|
| 462 |
+
"grad_norm": 16.948158264160156,
|
| 463 |
+
"learning_rate": 3.8793103448275865e-06,
|
| 464 |
+
"loss": 0.7642,
|
| 465 |
+
"step": 720
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.8372093023255816,
|
| 469 |
+
"grad_norm": 5.877094745635986,
|
| 470 |
+
"learning_rate": 3.017241379310345e-06,
|
| 471 |
+
"loss": 0.6525,
|
| 472 |
+
"step": 732
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.883720930232558,
|
| 476 |
+
"grad_norm": 9.920417785644531,
|
| 477 |
+
"learning_rate": 2.1551724137931035e-06,
|
| 478 |
+
"loss": 0.7873,
|
| 479 |
+
"step": 744
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.9302325581395348,
|
| 483 |
+
"grad_norm": 25.48910140991211,
|
| 484 |
+
"learning_rate": 1.293103448275862e-06,
|
| 485 |
+
"loss": 0.689,
|
| 486 |
+
"step": 756
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.9767441860465116,
|
| 490 |
+
"grad_norm": 11.988759994506836,
|
| 491 |
+
"learning_rate": 4.3103448275862073e-07,
|
| 492 |
+
"loss": 0.7837,
|
| 493 |
+
"step": 768
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.0,
|
| 497 |
+
"eval_accuracy": 0.6531007751937985,
|
| 498 |
+
"eval_f1_macro": 0.41533378210893174,
|
| 499 |
+
"eval_f1_micro": 0.6531007751937985,
|
| 500 |
+
"eval_f1_weighted": 0.6340857128792562,
|
| 501 |
+
"eval_loss": 1.0832968950271606,
|
| 502 |
+
"eval_precision_macro": 0.43774810378738616,
|
| 503 |
+
"eval_precision_micro": 0.6531007751937985,
|
| 504 |
+
"eval_precision_weighted": 0.6386639752005375,
|
| 505 |
+
"eval_recall_macro": 0.4299005706500963,
|
| 506 |
+
"eval_recall_micro": 0.6531007751937985,
|
| 507 |
+
"eval_recall_weighted": 0.6531007751937985,
|
| 508 |
+
"eval_runtime": 74.0841,
|
| 509 |
+
"eval_samples_per_second": 6.965,
|
| 510 |
+
"eval_steps_per_second": 0.445,
|
| 511 |
+
"step": 774
|
| 512 |
+
}
|
| 513 |
+
],
|
| 514 |
+
"logging_steps": 12,
|
| 515 |
+
"max_steps": 774,
|
| 516 |
+
"num_input_tokens_seen": 0,
|
| 517 |
+
"num_train_epochs": 3,
|
| 518 |
+
"save_steps": 500,
|
| 519 |
+
"stateful_callbacks": {
|
| 520 |
+
"EarlyStoppingCallback": {
|
| 521 |
+
"args": {
|
| 522 |
+
"early_stopping_patience": 5,
|
| 523 |
+
"early_stopping_threshold": 0.01
|
| 524 |
+
},
|
| 525 |
+
"attributes": {
|
| 526 |
+
"early_stopping_patience_counter": 0
|
| 527 |
+
}
|
| 528 |
+
},
|
| 529 |
+
"TrainerControl": {
|
| 530 |
+
"args": {
|
| 531 |
+
"should_epoch_stop": false,
|
| 532 |
+
"should_evaluate": false,
|
| 533 |
+
"should_log": false,
|
| 534 |
+
"should_save": true,
|
| 535 |
+
"should_training_stop": true
|
| 536 |
+
},
|
| 537 |
+
"attributes": {}
|
| 538 |
+
}
|
| 539 |
+
},
|
| 540 |
+
"total_flos": 406791552950784.0,
|
| 541 |
+
"train_batch_size": 8,
|
| 542 |
+
"trial_name": null,
|
| 543 |
+
"trial_params": null
|
| 544 |
+
}
|
checkpoint-774/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27bad31138bf3585430c2bd1140340798b9cabd9b4236a7390b1572b2dcce89a
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
+
"_num_labels": 26,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"RobertaForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Unknown",
|
| 16 |
+
"1": "apology-baiting",
|
| 17 |
+
"2": "apology-baiting ",
|
| 18 |
+
"3": "apology_baiting",
|
| 19 |
+
"4": "blame_shifting",
|
| 20 |
+
"5": "contradictory-statements",
|
| 21 |
+
"6": "control",
|
| 22 |
+
"7": "deflection",
|
| 23 |
+
"8": "dismissiveness",
|
| 24 |
+
"9": "extreme_control",
|
| 25 |
+
"10": "gaslighting",
|
| 26 |
+
"11": "gaslighting ",
|
| 27 |
+
"12": "guilt-tripping",
|
| 28 |
+
"13": "guilt-tripping ",
|
| 29 |
+
"14": "insults",
|
| 30 |
+
"15": "manipulation",
|
| 31 |
+
"16": "mockery",
|
| 32 |
+
"17": "non_abusive",
|
| 33 |
+
"18": "obscure language",
|
| 34 |
+
"19": "obscure-formal",
|
| 35 |
+
"20": "obscure_formal",
|
| 36 |
+
"21": "physical_threat",
|
| 37 |
+
"22": "projection",
|
| 38 |
+
"23": "recovery-phase",
|
| 39 |
+
"24": "suicidal_threat",
|
| 40 |
+
"25": "suicidal_threat "
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 3072,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"Unknown": 0,
|
| 46 |
+
"apology-baiting": 1,
|
| 47 |
+
"apology-baiting ": 2,
|
| 48 |
+
"apology_baiting": 3,
|
| 49 |
+
"blame_shifting": 4,
|
| 50 |
+
"contradictory-statements": 5,
|
| 51 |
+
"control": 6,
|
| 52 |
+
"deflection": 7,
|
| 53 |
+
"dismissiveness": 8,
|
| 54 |
+
"extreme_control": 9,
|
| 55 |
+
"gaslighting": 10,
|
| 56 |
+
"gaslighting ": 11,
|
| 57 |
+
"guilt-tripping": 12,
|
| 58 |
+
"guilt-tripping ": 13,
|
| 59 |
+
"insults": 14,
|
| 60 |
+
"manipulation": 15,
|
| 61 |
+
"mockery": 16,
|
| 62 |
+
"non_abusive": 17,
|
| 63 |
+
"obscure language": 18,
|
| 64 |
+
"obscure-formal": 19,
|
| 65 |
+
"obscure_formal": 20,
|
| 66 |
+
"physical_threat": 21,
|
| 67 |
+
"projection": 22,
|
| 68 |
+
"recovery-phase": 23,
|
| 69 |
+
"suicidal_threat": 24,
|
| 70 |
+
"suicidal_threat ": 25
|
| 71 |
+
},
|
| 72 |
+
"layer_norm_eps": 1e-05,
|
| 73 |
+
"max_position_embeddings": 514,
|
| 74 |
+
"model_type": "roberta",
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_hidden_layers": 12,
|
| 77 |
+
"pad_token_id": 1,
|
| 78 |
+
"position_embedding_type": "absolute",
|
| 79 |
+
"problem_type": "single_label_classification",
|
| 80 |
+
"torch_dtype": "float32",
|
| 81 |
+
"transformers_version": "4.48.0",
|
| 82 |
+
"type_vocab_size": 1,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"vocab_size": 50265
|
| 85 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39aca7da0e7eff911ebec52496ec531cb9889e8a9fd59cc55da2d6b4b1d8e08
|
| 3 |
+
size 498686648
|
runs/Apr14_22-22-07_r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq/events.out.tfevents.1744669329.r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq.136.0
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:b639bf6114eec0611a4504a38ba6fc31f6711a71f26e8f9395b51d0a2bc0b059
|
| 3 |
+
size 22780
|
runs/Apr14_22-22-07_r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq/events.out.tfevents.1744673038.r-samanthastorm-tether1-5-p1dgqvdd-38c3a-096bq.136.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57d5b9d7634bb5b74a15014ff642702860495bc260e9896f38ded9b36bf3e410
|
| 3 |
+
size 921
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27bad31138bf3585430c2bd1140340798b9cabd9b4236a7390b1572b2dcce89a
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "Tether2/autotrain-data",
|
| 3 |
+
"model": "FacebookAI/roberta-base",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 8,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"text_column": "autotrain_text",
|
| 18 |
+
"target_column": "autotrain_label",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "Tether2",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "SamanthaStorm",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|