Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f296deaac4384c2be1230221a99abd9620bdf6b5817fc869b62aab1965a4b0a
+oid sha256:208f9ebf9703f0e5fcd0ebbfc7e5f5189ca92fdadddda0cbd038fbb44bc6350f
 size 498612824

runs/Mar10_15-22-18_d09419a20441/events.out.tfevents.1710084185.d09419a20441.24137.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b3736d3bfd334331520a71d7aa75bdca143648a20fa9f0e8b302224c438c4b
-size 6796
+oid sha256:24b0f461deec982ac93cef5b241a922a6f711efbd9d1cb22044f2237823b17a5
+size 7342

runs/Mar10_15-39-45_d09419a20441/events.out.tfevents.1710085185.d09419a20441.36629.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f882824cedb13133248643bb5a03add2916ce9cc47858ad60b7cac545fc6445
+size 5158

tmp-checkpoint-2675/config.json

@@ -0,0 +1,28 @@
+{
+ "_name_or_path": "roberta-base",
+ "architectures": [
+ "RobertaForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.38.2",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 50265
+}

tmp-checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50816a000e025e5b4222994aafc1a734ae12008f418b256a91519adda6d4ca85
+size 498612824

tmp-checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f8defdf84131f885318b922418a9854043845a9f9836ae8804918fefa59760
+size 997345530

tmp-checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4514325d1cd6218f8ffac41df456f6df58def147da72679c5129fa36d1c85e
+size 14244

tmp-checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a113978a7c5fe803444afa83adccda9aab3ebb5099a00818e17eb47d7f66ccbd
+size 1064

tmp-checkpoint-2675/special_tokens_map.json

@@ -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>"
+}

tmp-checkpoint-2675/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+ "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": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "errors": "replace",
+ "mask_token": "<mask>",
+ "model_max_length": 512,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "tokenizer_class": "RobertaTokenizer",
+ "trim_offsets": true,
+ "unk_token": "<unk>"
+}

tmp-checkpoint-2675/trainer_state.json

@@ -0,0 +1,101 @@
+{
+ "best_metric": 0.6372231085109245,
+ "best_model_checkpoint": "roberta-base-finetuned-cola/checkpoint-1070",
+ "epoch": 5.0,
+ "eval_steps": 500,
+ "global_step": 2675,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.93,
+ "grad_norm": 16.3082275390625,
+ "learning_rate": 1.6261682242990654e-05,
+ "loss": 0.4777,
+ "step": 500
+ },
+ {
+ "epoch": 1.0,
+ "eval_loss": 0.43241721391677856,
+ "eval_matthews_correlation": 0.5493333540758192,
+ "eval_runtime": 1.2622,
+ "eval_samples_per_second": 826.355,
+ "eval_steps_per_second": 52.291,
+ "step": 535
+ },
+ {
+ "epoch": 1.87,
+ "grad_norm": 23.89521598815918,
+ "learning_rate": 1.2523364485981309e-05,
+ "loss": 0.3138,
+ "step": 1000
+ },
+ {
+ "epoch": 2.0,
+ "eval_loss": 0.4074053466320038,
+ "eval_matthews_correlation": 0.6372231085109245,
+ "eval_runtime": 1.315,
+ "eval_samples_per_second": 793.178,
+ "eval_steps_per_second": 50.191,
+ "step": 1070
+ },
+ {
+ "epoch": 2.8,
+ "grad_norm": 18.608760833740234,
+ "learning_rate": 8.785046728971963e-06,
+ "loss": 0.2262,
+ "step": 1500
+ },
+ {
+ "epoch": 3.0,
+ "eval_loss": 0.6061288714408875,
+ "eval_matthews_correlation": 0.576660981486724,
+ "eval_runtime": 1.3277,
+ "eval_samples_per_second": 785.578,
+ "eval_steps_per_second": 49.711,
+ "step": 1605
+ },
+ {
+ "epoch": 3.74,
+ "grad_norm": 2.4630796909332275,
+ "learning_rate": 5.046728971962617e-06,
+ "loss": 0.1786,
+ "step": 2000
+ },
+ {
+ "epoch": 4.0,
+ "eval_loss": 0.884406328201294,
+ "eval_matthews_correlation": 0.5855361143791362,
+ "eval_runtime": 1.2996,
+ "eval_samples_per_second": 802.571,
+ "eval_steps_per_second": 50.786,
+ "step": 2140
+ },
+ {
+ "epoch": 4.67,
+ "grad_norm": 0.05961179360747337,
+ "learning_rate": 1.308411214953271e-06,
+ "loss": 0.1253,
+ "step": 2500
+ },
+ {
+ "epoch": 5.0,
+ "eval_loss": 0.9215266704559326,
+ "eval_matthews_correlation": 0.6158197390467447,
+ "eval_runtime": 1.2999,
+ "eval_samples_per_second": 802.375,
+ "eval_steps_per_second": 50.773,
+ "step": 2675
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 2675,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 500,
+ "total_flos": 449687113048260.0,
+ "train_batch_size": 16,
+ "trial_name": null,
+ "trial_params": null
+}

tmp-checkpoint-2675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f59fe0b682b5ab5291019e04201cbbd5a4fbdcb480c63867e2a08aedf682af2
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f59fe0b682b5ab5291019e04201cbbd5a4fbdcb480c63867e2a08aedf682af2
+oid sha256:3bf0aada722587d583beb9ca32d87ee803e61f84e40d1f366d5b9e684ee28ef8
 size 4920