samtuckervegan commited on Apr 5, 2025

Commit

ef20ec2

verified ·

1 Parent(s): 767288b

Upload folder using huggingface_hub

Browse files

Files changed (22) hide show

README.md +28 -0
checkpoint-2660/config.json +51 -0
checkpoint-2660/model.safetensors +3 -0
checkpoint-2660/optimizer.pt +3 -0
checkpoint-2660/rng_state_0.pth +3 -0
checkpoint-2660/rng_state_1.pth +3 -0
checkpoint-2660/rng_state_2.pth +3 -0
checkpoint-2660/rng_state_3.pth +3 -0
checkpoint-2660/scheduler.pt +3 -0
checkpoint-2660/trainer_state.json +836 -0
checkpoint-2660/training_args.bin +3 -0
config.json +51 -0
merges.txt +0 -0
model.safetensors +3 -0
runs/Apr04_20-25-23_r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5/events.out.tfevents.1743798325.r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5.215.0 +2 -2
runs/Apr04_20-25-23_r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5/events.out.tfevents.1743823465.r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5.215.1 +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 Viewed

	@@ -0,0 +1,28 @@

+---
+tags:
+- autotrain
+- text-regression
+base_model: allenai/longformer-base-4096
+widget:
+- text: "I love AutoTrain"
+datasets:
+- open-paws/animal_alignment_feedback
+---
+# Model Trained Using AutoTrain
+- Problem type: Text Regression
+## Validation Metrics
+loss: 0.02979499101638794
+mse: 0.02978423796594143
+mae: 0.13353775441646576
+r2: 0.4564886689186096
+rmse: 0.17258110547201114
+explained_variance: 0.4599541425704956

checkpoint-2660/config.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "_num_labels": 1,
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "target"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "target": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "regression",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-2660/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b757e785ceb97089596df3ab0d8407e60f9f602e1aa5592c6ac434f519a9bb6
+size 594675108

checkpoint-2660/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdedff0299a1733a38a28894ece31a2914f3cf038581416256bfeafba738b2f
+size 1189510202

checkpoint-2660/rng_state_0.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7134aa323d647c6a04cf45c68effc37f1de6c1e4cf6c1fe76f46129e8d8b5cb
+size 15024

checkpoint-2660/rng_state_1.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d6c1d17c4269edd54eaa0a0fc711e20393a1a96ca5d2bc3ae08e65f949b10e
+size 15024

checkpoint-2660/rng_state_2.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:454f8523d491f4da2280f1c910d95b8d013dba257b451fb5f067deb713bdd2b9
+size 15024

checkpoint-2660/rng_state_3.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40b2c195e7999220ef5b96144decd7aaa71ef16248a586f7c2887d9dc9e28a50
+size 15024

checkpoint-2660/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:02f8af646547f678442386e7abe40bb64d6bb97e948be87a493edf7aff4da709
+size 1064

checkpoint-2660/trainer_state.json ADDED Viewed

	@@ -0,0 +1,836 @@

+{
+  "best_metric": 0.02979499101638794,
+  "best_model_checkpoint": "rationality-longformer/checkpoint-2660",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2660,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03759398496240601,
+      "grad_norm": 8.561731338500977,
+      "learning_rate": 4.06015037593985e-06,
+      "loss": 0.4701,
+      "step": 25
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "grad_norm": 1.9625297784805298,
+      "learning_rate": 8.1203007518797e-06,
+      "loss": 0.1076,
+      "step": 50
+    },
+    {
+      "epoch": 0.11278195488721804,
+      "grad_norm": 3.9176547527313232,
+      "learning_rate": 1.2349624060150378e-05,
+      "loss": 0.0607,
+      "step": 75
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 2.470714807510376,
+      "learning_rate": 1.6578947368421053e-05,
+      "loss": 0.058,
+      "step": 100
+    },
+    {
+      "epoch": 0.18796992481203006,
+      "grad_norm": 2.0074236392974854,
+      "learning_rate": 2.080827067669173e-05,
+      "loss": 0.0492,
+      "step": 125
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 0.8747868537902832,
+      "learning_rate": 2.5037593984962406e-05,
+      "loss": 0.0477,
+      "step": 150
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.7500576376914978,
+      "learning_rate": 2.9266917293233085e-05,
+      "loss": 0.05,
+      "step": 175
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 2.4127628803253174,
+      "learning_rate": 3.349624060150376e-05,
+      "loss": 0.0496,
+      "step": 200
+    },
+    {
+      "epoch": 0.3383458646616541,
+      "grad_norm": 2.8459553718566895,
+      "learning_rate": 3.772556390977444e-05,
+      "loss": 0.0477,
+      "step": 225
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 1.2854725122451782,
+      "learning_rate": 4.178571428571429e-05,
+      "loss": 0.0437,
+      "step": 250
+    },
+    {
+      "epoch": 0.41353383458646614,
+      "grad_norm": 1.851727843284607,
+      "learning_rate": 4.488721804511278e-05,
+      "loss": 0.0514,
+      "step": 275
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.6419578194618225,
+      "learning_rate": 4.441729323308271e-05,
+      "loss": 0.0435,
+      "step": 300
+    },
+    {
+      "epoch": 0.48872180451127817,
+      "grad_norm": 1.3216092586517334,
+      "learning_rate": 4.3947368421052636e-05,
+      "loss": 0.0431,
+      "step": 325
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.3820026218891144,
+      "learning_rate": 4.347744360902256e-05,
+      "loss": 0.0418,
+      "step": 350
+    },
+    {
+      "epoch": 0.5639097744360902,
+      "grad_norm": 1.4153975248336792,
+      "learning_rate": 4.3007518796992484e-05,
+      "loss": 0.0428,
+      "step": 375
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 1.5775055885314941,
+      "learning_rate": 4.253759398496241e-05,
+      "loss": 0.0406,
+      "step": 400
+    },
+    {
+      "epoch": 0.6390977443609023,
+      "grad_norm": 0.9211301207542419,
+      "learning_rate": 4.206766917293233e-05,
+      "loss": 0.0404,
+      "step": 425
+    },
+    {
+      "epoch": 0.6766917293233082,
+      "grad_norm": 0.47279754281044006,
+      "learning_rate": 4.159774436090226e-05,
+      "loss": 0.039,
+      "step": 450
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.9095789790153503,
+      "learning_rate": 4.112781954887218e-05,
+      "loss": 0.0412,
+      "step": 475
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 2.03822922706604,
+      "learning_rate": 4.067669172932331e-05,
+      "loss": 0.0384,
+      "step": 500
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.6165791749954224,
+      "learning_rate": 4.0206766917293236e-05,
+      "loss": 0.0408,
+      "step": 525
+    },
+    {
+      "epoch": 0.8270676691729323,
+      "grad_norm": 0.4518881142139435,
+      "learning_rate": 3.973684210526316e-05,
+      "loss": 0.0359,
+      "step": 550
+    },
+    {
+      "epoch": 0.8646616541353384,
+      "grad_norm": 1.102316975593567,
+      "learning_rate": 3.9266917293233084e-05,
+      "loss": 0.0369,
+      "step": 575
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 0.7155941128730774,
+      "learning_rate": 3.879699248120301e-05,
+      "loss": 0.0378,
+      "step": 600
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "grad_norm": 0.4525124132633209,
+      "learning_rate": 3.832706766917294e-05,
+      "loss": 0.0378,
+      "step": 625
+    },
+    {
+      "epoch": 0.9774436090225563,
+      "grad_norm": 1.2457730770111084,
+      "learning_rate": 3.785714285714286e-05,
+      "loss": 0.0374,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "eval_explained_variance": 0.4046803116798401,
+      "eval_loss": 0.03266496956348419,
+      "eval_mae": 0.14023803174495697,
+      "eval_mse": 0.03265844285488129,
+      "eval_r2": 0.40403932332992554,
+      "eval_rmse": 0.18071647090091508,
+      "eval_runtime": 332.2508,
+      "eval_samples_per_second": 64.033,
+      "eval_steps_per_second": 1.002,
+      "step": 665
+    },
+    {
+      "epoch": 1.0150375939849625,
+      "grad_norm": 0.41502645611763,
+      "learning_rate": 3.738721804511278e-05,
+      "loss": 0.0357,
+      "step": 675
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 1.5358161926269531,
+      "learning_rate": 3.6917293233082705e-05,
+      "loss": 0.0355,
+      "step": 700
+    },
+    {
+      "epoch": 1.0902255639097744,
+      "grad_norm": 0.5753918290138245,
+      "learning_rate": 3.6447368421052636e-05,
+      "loss": 0.0352,
+      "step": 725
+    },
+    {
+      "epoch": 1.1278195488721805,
+      "grad_norm": 0.45865878462791443,
+      "learning_rate": 3.597744360902256e-05,
+      "loss": 0.0356,
+      "step": 750
+    },
+    {
+      "epoch": 1.1654135338345863,
+      "grad_norm": 0.2906554043292999,
+      "learning_rate": 3.5507518796992485e-05,
+      "loss": 0.0362,
+      "step": 775
+    },
+    {
+      "epoch": 1.2030075187969924,
+      "grad_norm": 0.9988584518432617,
+      "learning_rate": 3.503759398496241e-05,
+      "loss": 0.0365,
+      "step": 800
+    },
+    {
+      "epoch": 1.2406015037593985,
+      "grad_norm": 0.5174156427383423,
+      "learning_rate": 3.456766917293233e-05,
+      "loss": 0.0329,
+      "step": 825
+    },
+    {
+      "epoch": 1.2781954887218046,
+      "grad_norm": 0.8101080656051636,
+      "learning_rate": 3.409774436090226e-05,
+      "loss": 0.0362,
+      "step": 850
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.5714322924613953,
+      "learning_rate": 3.362781954887218e-05,
+      "loss": 0.0342,
+      "step": 875
+    },
+    {
+      "epoch": 1.3533834586466165,
+      "grad_norm": 0.39708998799324036,
+      "learning_rate": 3.3157894736842106e-05,
+      "loss": 0.0362,
+      "step": 900
+    },
+    {
+      "epoch": 1.3909774436090225,
+      "grad_norm": 0.9136710166931152,
+      "learning_rate": 3.268796992481204e-05,
+      "loss": 0.0367,
+      "step": 925
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.491678237915039,
+      "learning_rate": 3.2218045112781954e-05,
+      "loss": 0.0377,
+      "step": 950
+    },
+    {
+      "epoch": 1.4661654135338344,
+      "grad_norm": 1.0554755926132202,
+      "learning_rate": 3.174812030075188e-05,
+      "loss": 0.0388,
+      "step": 975
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "grad_norm": 0.531471312046051,
+      "learning_rate": 3.12781954887218e-05,
+      "loss": 0.0339,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5413533834586466,
+      "grad_norm": 0.40952593088150024,
+      "learning_rate": 3.0808270676691734e-05,
+      "loss": 0.0356,
+      "step": 1025
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.8983538746833801,
+      "learning_rate": 3.0338345864661658e-05,
+      "loss": 0.0355,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6165413533834587,
+      "grad_norm": 0.47667157649993896,
+      "learning_rate": 2.986842105263158e-05,
+      "loss": 0.0359,
+      "step": 1075
+    },
+    {
+      "epoch": 1.6541353383458648,
+      "grad_norm": 0.4042755961418152,
+      "learning_rate": 2.9398496240601503e-05,
+      "loss": 0.0334,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6917293233082706,
+      "grad_norm": 0.42199933528900146,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.0337,
+      "step": 1125
+    },
+    {
+      "epoch": 1.7293233082706767,
+      "grad_norm": 0.5914226174354553,
+      "learning_rate": 2.8458646616541355e-05,
+      "loss": 0.0345,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7669172932330826,
+      "grad_norm": 0.399776428937912,
+      "learning_rate": 2.798872180451128e-05,
+      "loss": 0.0347,
+      "step": 1175
+    },
+    {
+      "epoch": 1.8045112781954886,
+      "grad_norm": 0.3664228320121765,
+      "learning_rate": 2.7518796992481204e-05,
+      "loss": 0.0354,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 1.385761022567749,
+      "learning_rate": 2.704887218045113e-05,
+      "loss": 0.035,
+      "step": 1225
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "grad_norm": 0.46149659156799316,
+      "learning_rate": 2.6578947368421055e-05,
+      "loss": 0.0351,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9172932330827068,
+      "grad_norm": 0.7903790473937988,
+      "learning_rate": 2.610902255639098e-05,
+      "loss": 0.0347,
+      "step": 1275
+    },
+    {
+      "epoch": 1.954887218045113,
+      "grad_norm": 1.550508737564087,
+      "learning_rate": 2.5639097744360904e-05,
+      "loss": 0.0352,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9924812030075187,
+      "grad_norm": 0.6421409249305725,
+      "learning_rate": 2.516917293233083e-05,
+      "loss": 0.0334,
+      "step": 1325
+    },
+    {
+      "epoch": 2.0,
+      "eval_explained_variance": 0.42286986112594604,
+      "eval_loss": 0.031812477856874466,
+      "eval_mae": 0.13803428411483765,
+      "eval_mse": 0.031806670129299164,
+      "eval_r2": 0.419582724571228,
+      "eval_rmse": 0.178344246134545,
+      "eval_runtime": 331.4448,
+      "eval_samples_per_second": 64.189,
+      "eval_steps_per_second": 1.005,
+      "step": 1330
+    },
+    {
+      "epoch": 2.030075187969925,
+      "grad_norm": 0.5215243697166443,
+      "learning_rate": 2.4699248120300756e-05,
+      "loss": 0.0341,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0676691729323307,
+      "grad_norm": 0.9907874464988708,
+      "learning_rate": 2.4229323308270677e-05,
+      "loss": 0.033,
+      "step": 1375
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.48371124267578125,
+      "learning_rate": 2.37593984962406e-05,
+      "loss": 0.0332,
+      "step": 1400
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.013298749923706,
+      "learning_rate": 2.328947368421053e-05,
+      "loss": 0.0325,
+      "step": 1425
+    },
+    {
+      "epoch": 2.180451127819549,
+      "grad_norm": 0.35832202434539795,
+      "learning_rate": 2.2819548872180453e-05,
+      "loss": 0.032,
+      "step": 1450
+    },
+    {
+      "epoch": 2.218045112781955,
+      "grad_norm": 0.9879142045974731,
+      "learning_rate": 2.2349624060150377e-05,
+      "loss": 0.0328,
+      "step": 1475
+    },
+    {
+      "epoch": 2.255639097744361,
+      "grad_norm": 0.8283109068870544,
+      "learning_rate": 2.18796992481203e-05,
+      "loss": 0.0338,
+      "step": 1500
+    },
+    {
+      "epoch": 2.293233082706767,
+      "grad_norm": 0.7954843044281006,
+      "learning_rate": 2.1409774436090226e-05,
+      "loss": 0.0343,
+      "step": 1525
+    },
+    {
+      "epoch": 2.3308270676691727,
+      "grad_norm": 0.4207070767879486,
+      "learning_rate": 2.093984962406015e-05,
+      "loss": 0.0309,
+      "step": 1550
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.5190187692642212,
+      "learning_rate": 2.0469924812030077e-05,
+      "loss": 0.0318,
+      "step": 1575
+    },
+    {
+      "epoch": 2.406015037593985,
+      "grad_norm": 0.48805102705955505,
+      "learning_rate": 2e-05,
+      "loss": 0.0314,
+      "step": 1600
+    },
+    {
+      "epoch": 2.443609022556391,
+      "grad_norm": 0.3888954818248749,
+      "learning_rate": 1.9530075187969926e-05,
+      "loss": 0.0322,
+      "step": 1625
+    },
+    {
+      "epoch": 2.481203007518797,
+      "grad_norm": 0.2552517056465149,
+      "learning_rate": 1.906015037593985e-05,
+      "loss": 0.0327,
+      "step": 1650
+    },
+    {
+      "epoch": 2.518796992481203,
+      "grad_norm": 1.5835086107254028,
+      "learning_rate": 1.8590225563909774e-05,
+      "loss": 0.0327,
+      "step": 1675
+    },
+    {
+      "epoch": 2.556390977443609,
+      "grad_norm": 0.40399572253227234,
+      "learning_rate": 1.81203007518797e-05,
+      "loss": 0.0336,
+      "step": 1700
+    },
+    {
+      "epoch": 2.593984962406015,
+      "grad_norm": 0.8116436004638672,
+      "learning_rate": 1.7650375939849626e-05,
+      "loss": 0.032,
+      "step": 1725
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.9888351559638977,
+      "learning_rate": 1.718045112781955e-05,
+      "loss": 0.0325,
+      "step": 1750
+    },
+    {
+      "epoch": 2.6691729323308273,
+      "grad_norm": 0.3143177330493927,
+      "learning_rate": 1.6710526315789475e-05,
+      "loss": 0.0308,
+      "step": 1775
+    },
+    {
+      "epoch": 2.706766917293233,
+      "grad_norm": 0.4308098256587982,
+      "learning_rate": 1.62406015037594e-05,
+      "loss": 0.0314,
+      "step": 1800
+    },
+    {
+      "epoch": 2.744360902255639,
+      "grad_norm": 0.29963594675064087,
+      "learning_rate": 1.5770676691729323e-05,
+      "loss": 0.0317,
+      "step": 1825
+    },
+    {
+      "epoch": 2.781954887218045,
+      "grad_norm": 0.48776674270629883,
+      "learning_rate": 1.5300751879699247e-05,
+      "loss": 0.0322,
+      "step": 1850
+    },
+    {
+      "epoch": 2.819548872180451,
+      "grad_norm": 0.5826253294944763,
+      "learning_rate": 1.4830827067669175e-05,
+      "loss": 0.0307,
+      "step": 1875
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.4405226409435272,
+      "learning_rate": 1.4360902255639098e-05,
+      "loss": 0.0333,
+      "step": 1900
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.5225655436515808,
+      "learning_rate": 1.3890977443609024e-05,
+      "loss": 0.0311,
+      "step": 1925
+    },
+    {
+      "epoch": 2.932330827067669,
+      "grad_norm": 0.41791537404060364,
+      "learning_rate": 1.3421052631578948e-05,
+      "loss": 0.0324,
+      "step": 1950
+    },
+    {
+      "epoch": 2.969924812030075,
+      "grad_norm": 0.5451214909553528,
+      "learning_rate": 1.2951127819548874e-05,
+      "loss": 0.0306,
+      "step": 1975
+    },
+    {
+      "epoch": 3.0,
+      "eval_explained_variance": 0.45663392543792725,
+      "eval_loss": 0.030168164521455765,
+      "eval_mae": 0.13527624309062958,
+      "eval_mse": 0.03015773557126522,
+      "eval_r2": 0.4496729373931885,
+      "eval_rmse": 0.1736598271658279,
+      "eval_runtime": 332.1496,
+      "eval_samples_per_second": 64.052,
+      "eval_steps_per_second": 1.003,
+      "step": 1995
+    },
+    {
+      "epoch": 3.007518796992481,
+      "grad_norm": 0.2819690704345703,
+      "learning_rate": 1.2481203007518796e-05,
+      "loss": 0.0306,
+      "step": 2000
+    },
+    {
+      "epoch": 3.045112781954887,
+      "grad_norm": 0.41735702753067017,
+      "learning_rate": 1.2011278195488724e-05,
+      "loss": 0.0293,
+      "step": 2025
+    },
+    {
+      "epoch": 3.082706766917293,
+      "grad_norm": 0.4255701005458832,
+      "learning_rate": 1.1541353383458646e-05,
+      "loss": 0.0309,
+      "step": 2050
+    },
+    {
+      "epoch": 3.1203007518796992,
+      "grad_norm": 0.47187066078186035,
+      "learning_rate": 1.107142857142857e-05,
+      "loss": 0.0303,
+      "step": 2075
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.23569606244564056,
+      "learning_rate": 1.0601503759398497e-05,
+      "loss": 0.0309,
+      "step": 2100
+    },
+    {
+      "epoch": 3.1954887218045114,
+      "grad_norm": 0.3127480745315552,
+      "learning_rate": 1.0131578947368421e-05,
+      "loss": 0.0292,
+      "step": 2125
+    },
+    {
+      "epoch": 3.2330827067669174,
+      "grad_norm": 0.2915782332420349,
+      "learning_rate": 9.661654135338345e-06,
+      "loss": 0.0298,
+      "step": 2150
+    },
+    {
+      "epoch": 3.2706766917293235,
+      "grad_norm": 0.4635418951511383,
+      "learning_rate": 9.191729323308271e-06,
+      "loss": 0.0296,
+      "step": 2175
+    },
+    {
+      "epoch": 3.308270676691729,
+      "grad_norm": 0.30249276757240295,
+      "learning_rate": 8.721804511278195e-06,
+      "loss": 0.0322,
+      "step": 2200
+    },
+    {
+      "epoch": 3.345864661654135,
+      "grad_norm": 0.3594088852405548,
+      "learning_rate": 8.25187969924812e-06,
+      "loss": 0.0287,
+      "step": 2225
+    },
+    {
+      "epoch": 3.3834586466165413,
+      "grad_norm": 0.5810452699661255,
+      "learning_rate": 7.781954887218045e-06,
+      "loss": 0.0292,
+      "step": 2250
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.4130695164203644,
+      "learning_rate": 7.31203007518797e-06,
+      "loss": 0.0297,
+      "step": 2275
+    },
+    {
+      "epoch": 3.4586466165413534,
+      "grad_norm": 0.5884249210357666,
+      "learning_rate": 6.842105263157895e-06,
+      "loss": 0.0295,
+      "step": 2300
+    },
+    {
+      "epoch": 3.4962406015037595,
+      "grad_norm": 0.6940419673919678,
+      "learning_rate": 6.37218045112782e-06,
+      "loss": 0.0311,
+      "step": 2325
+    },
+    {
+      "epoch": 3.5338345864661656,
+      "grad_norm": 0.36135807633399963,
+      "learning_rate": 5.902255639097744e-06,
+      "loss": 0.0317,
+      "step": 2350
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.36453500390052795,
+      "learning_rate": 5.432330827067669e-06,
+      "loss": 0.0297,
+      "step": 2375
+    },
+    {
+      "epoch": 3.6090225563909772,
+      "grad_norm": 0.25037509202957153,
+      "learning_rate": 4.962406015037594e-06,
+      "loss": 0.0289,
+      "step": 2400
+    },
+    {
+      "epoch": 3.6466165413533833,
+      "grad_norm": 0.6295666098594666,
+      "learning_rate": 4.4924812030075186e-06,
+      "loss": 0.0295,
+      "step": 2425
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.7680342197418213,
+      "learning_rate": 4.022556390977444e-06,
+      "loss": 0.0307,
+      "step": 2450
+    },
+    {
+      "epoch": 3.7218045112781954,
+      "grad_norm": 0.4914247691631317,
+      "learning_rate": 3.5526315789473683e-06,
+      "loss": 0.0303,
+      "step": 2475
+    },
+    {
+      "epoch": 3.7593984962406015,
+      "grad_norm": 0.2644283175468445,
+      "learning_rate": 3.0827067669172934e-06,
+      "loss": 0.0284,
+      "step": 2500
+    },
+    {
+      "epoch": 3.7969924812030076,
+      "grad_norm": 0.3956184387207031,
+      "learning_rate": 2.612781954887218e-06,
+      "loss": 0.0301,
+      "step": 2525
+    },
+    {
+      "epoch": 3.8345864661654137,
+      "grad_norm": 0.8803111910820007,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.0288,
+      "step": 2550
+    },
+    {
+      "epoch": 3.8721804511278197,
+      "grad_norm": 0.3685418665409088,
+      "learning_rate": 1.6729323308270676e-06,
+      "loss": 0.0294,
+      "step": 2575
+    },
+    {
+      "epoch": 3.909774436090226,
+      "grad_norm": 0.6178150177001953,
+      "learning_rate": 1.2030075187969925e-06,
+      "loss": 0.0301,
+      "step": 2600
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.31244605779647827,
+      "learning_rate": 7.330827067669173e-07,
+      "loss": 0.0299,
+      "step": 2625
+    },
+    {
+      "epoch": 3.9849624060150375,
+      "grad_norm": 0.2659818232059479,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.0283,
+      "step": 2650
+    },
+    {
+      "epoch": 4.0,
+      "eval_explained_variance": 0.4599541425704956,
+      "eval_loss": 0.02979499101638794,
+      "eval_mae": 0.13353775441646576,
+      "eval_mse": 0.02978423796594143,
+      "eval_r2": 0.4564886689186096,
+      "eval_rmse": 0.17258110547201114,
+      "eval_runtime": 331.6411,
+      "eval_samples_per_second": 64.151,
+      "eval_steps_per_second": 1.004,
+      "step": 2660
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.945729038555546e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2660/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c893b5c5e95351eb46deca0dacee023fd60d03f2085e784e9e9a52174b7f22cb
+size 5368

config.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "_num_labels": 1,
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "target"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "target": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "regression",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b757e785ceb97089596df3ab0d8407e60f9f602e1aa5592c6ac434f519a9bb6
+size 594675108

runs/Apr04_20-25-23_r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5/events.out.tfevents.1743798325.r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5.215.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a90a9bc84b66d085161e1e3c3897a7062dc71d5ece865a09084674d43be371
-size 28635

 version https://git-lfs.github.com/spec/v1
+oid sha256:1ac5958b6ec1e2843c9b429cde49b4424c0899267ca4346eea53a49a8a8fd195
+size 30143

runs/Apr04_20-25-23_r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5/events.out.tfevents.1743823465.r-samtuckervegan-autotrain-advanced-dhhsgzmo-ec501-hxdb5.215.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a901963b93157fb256b89a93b18596f1df0cce658bb2274e35ce939ebbb2f9
+size 609

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c893b5c5e95351eb46deca0dacee023fd60d03f2085e784e9e9a52174b7f22cb
+size 5368

training_params.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+    "data_path": "open-paws/animal_alignment_feedback",
+    "model": "allenai/longformer-base-4096",
+    "lr": 4.5e-05,
+    "epochs": 4,
+    "max_seq_length": 4096,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "test",
+    "text_column": "text",
+    "target_column": "rating_rationality",
+    "logging_steps": -1,
+    "project_name": "rationality-longformer",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "samtuckervegan",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff