Training in progress, step 100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6024f4bad81a6e07a4fcbfe545ff7fb25f2aea8a39bb66bae006260e17bdf2
-size 879301
+oid sha256:3f61d1df1d8c134c6844f5beb1b85477f57db546ed287382ff7184c5f3874526
+size 335851

runs/Feb03_21-50-21_node1/1643898113.8571255/events.out.tfevents.1643898113.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c122d83d0e9250aa53376ac67f6c4566ff53841823e3cd142ddeb3f6572f1f
+size 5026

runs/Feb03_23-19-31_node1/1643901679.9672043/events.out.tfevents.1643901679.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3cbc6b795ef575e289844b598e3804edbd43737860694777bef48abc80b5e5
+size 5026

runs/Feb03_23-19-31_node1/events.out.tfevents.1643901679.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab4cc5759c4ceb2b4c3b984da65efd06bea994387ff9247362c176a1636e069
+size 4315

runs/Feb03_23-24-24_node1/1643901959.363402/events.out.tfevents.1643901959.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785f7239cbc5c1e3cc7b6cd0f1305ddc34ddafdee06caf809bd5d83ad8f412d1
+size 5026

runs/Feb03_23-28-03_node1/1643902199.098082/events.out.tfevents.1643902199.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2feb7a9ba7beb992bc356bae4953f53a755dad299a04dac93ae7a57dbb70f3
+size 5026

runs/Feb03_23-28-03_node1/events.out.tfevents.1643902199.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:032f0e760f36164130221e9afdf6800f185530468e276b1b0a3676b2f2abab01
+size 4315

runs/Feb03_23-46-10_node1/1643903312.1067505/events.out.tfevents.1643903312.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e564017ea3b07e75267569bd90c5b961fb32a204a0f625ae772f38852d8aa136
+size 5026

runs/Feb03_23-46-10_node1/events.out.tfevents.1643903312.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5edb96288483bfb1a1ffe1b0b3904482dcf22b1c9cf3d1388cc2a529037eaf0
+size 4315

runs/Feb03_23-53-32_node1/1643903758.2698698/events.out.tfevents.1643903758.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b30eafeb06e8ed4c2370e27a62626fb9b3594b39ac0568452e0f458aa1a9612
+size 5026

runs/Feb03_23-53-32_node1/events.out.tfevents.1643903758.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82c062283fcc895ca0d27251bcee9e4fc614cf8d73dbff2d0c417a6a64ce1a3
+size 4315

runs/Feb04_00-00-58_node1/1643904527.5367358/events.out.tfevents.1643904527.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cfc9ff1846815aacb5336c76943b09772af1613f5f6903e3102bb44848f708
+size 5026

runs/Feb04_00-14-40_node1/1643905042.645074/events.out.tfevents.1643905042.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef768e3c16be080d48d28ae1b717aca1af07bbe21e42371e1263a65f95d17f31
+size 5026

runs/Feb04_00-14-40_node1/events.out.tfevents.1643905042.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16692e0b45631f61b966e59ab53101773cdc9564581223a9211ab58331adb115
+size 4315

runs/Feb04_00-24-13_node1/1643905581.9784336/events.out.tfevents.1643905581.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f90bb890c94e8f4ab4005bcc7ac6703e54d505adce84d939e1ef37d0a64c01
+size 5026

runs/Feb04_00-24-13_node1/events.out.tfevents.1643905581.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbdda603a37ebc09a9b65b7051559edf1057a0d0c4ac93c2ba92e21c9e692f0c
+size 4315

runs/Feb04_00-27-21_node1/1643905785.244129/events.out.tfevents.1643905785.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2efa60b1f985da92298974afcb77f86218328849678de1f73fe03143e6ded96
+size 5026

runs/Feb04_00-32-00_node1/1643905999.3731616/events.out.tfevents.1643905999.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cb434486a52f5e461eeb6f97e697d9c677e6cfd458dacd80fb142663842274
+size 5026

runs/Feb04_00-32-00_node1/events.out.tfevents.1643905999.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da847f6dffd49abbe52f70c77157f034663cbca3ad9dc2823c4ce844cc46fd6c
+size 4315

runs/Feb04_00-40-43_node1/1643906511.0402398/events.out.tfevents.1643906511.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efc36fec2a437f996158c72f907a03b066fc93ab5539ae830361a1753a336e0
+size 5026

runs/Feb04_00-40-43_node1/events.out.tfevents.1643906511.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07711e7592c370d9e70a9df77c4d5b0d7d1097931339c55fe6d80f85947642f
+size 4315

runs/Feb04_00-42-24_node1/1643906667.1622097/events.out.tfevents.1643906667.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949546c552388e83fe6eaf3f0217b31fcaa0e54791897bc887f4f6c944328290
+size 5026

runs/Feb04_00-42-24_node1/events.out.tfevents.1643906667.node1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a08943f26bbec2dd8b45b8a72ff4dbb9fef905c6451eb5d380b6bbd6b15d2f
+size 4315

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da081c9720bfb809925b71d02252f7fd0cbb4bb98fadd1a670cf486e49034be2
+oid sha256:700eb53d4b0e56322345fdec13a767a3dadcb89a48ed96aaa80d35e9288455f0
 size 3183

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "compacter", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "cola", "eval_steps": 100, "evaluation_strategy": "steps", "factorized_phm": true, "factorized_phm_rule": false, "gradient_clip": false, "greater_is_better": true, "hypercomplex_adapters": true, "hypercomplex_division": 4, "hypercomplex_nonlinearity": "glorot-uniform", "learn_phm": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "non_linearity": "gelu_new", "normalize_phm_weight": false, "num_train_epochs": 20, "output_dir": "outputs/lora/t5-base/cola", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "phm_c_init": "normal", "phm_clamp": false, "phm_init_range": 0.0001, "predict_with_generate": true, "push_to_hub": true, "save_steps": 100, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "shared_phm_rule": false, "split_validation_test": true, "task_name": "cola", "test_dataset_config_name": ["en"], "test_dataset_name": "cola", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "use_bias_down_sampler": true, "use_bias_up_sampler": true, "warmup_steps": 0}
+{"dataset_config_name": ["en"], "delta_type": "soft_prompt", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "cola", "eval_steps": 100, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 20, "output_dir": "outputs/soft_prompt/t5-base/cola", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": true, "push_to_hub": true, "save_steps": 100, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "soft_token_num": 100, "split_validation_test": true, "task_name": "cola", "test_dataset_config_name": ["en"], "test_dataset_name": "cola", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}