Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f8a76cbb60b5451580ffdde7d9a4462ff9b3bf8c4a7c8aac66e1154437aaa8
+oid sha256:8a3fc766ab0093cf34f31cdc674b7f31d8e666c9892cc02763446c4f4b0dfed5
 size 470641664

run-7/checkpoint-422/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

run-7/checkpoint-422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384518faf29f2ffe6efdc41419dfdf97b113150f026ea9437da57a6432f3af0a
+size 470641664

run-7/checkpoint-422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d1793ccf32ebdf0459ee293815e211cba235329e32c5869fd86d6778c1743e
+size 941404410

run-7/checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77709b1896d23d26e08bd16aab08ecbe725beb573571c18284b077f90d605b1
+size 14244

run-7/checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4760cd37cffe0806df52ee69f4b3f5ceee92cae8b3f6189fd108ec74f4a725
+size 1064

run-7/checkpoint-422/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-7/checkpoint-422/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>"
+}

run-7/checkpoint-422/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
+size 17098273

run-7/checkpoint-422/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-7/checkpoint-422/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.8176605504587156,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-7/checkpoint-422",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 422,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.44363221526145935,
+      "eval_runtime": 0.9149,
+      "eval_samples_per_second": 953.157,
+      "eval_steps_per_second": 60.119,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.41796988248825073,
+      "eval_runtime": 1.0061,
+      "eval_samples_per_second": 866.703,
+      "eval_steps_per_second": 54.666,
+      "step": 422
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 422,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.7420099230252167e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 12
+  }
+}

run-7/checkpoint-422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c94191c0ad987493b022bf2df16f9d29bf8c5807f2f4ddb0c28f593979ff2cf
+size 4984

runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640474.0db4763e2117.1712.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3878cd5dc5d5e9c05adac758f2da622567958c09f5e0b8030028f88075aa1088
+size 4993

runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640514.0db4763e2117.1712.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187e739fc4ec06ea642ff38b8036fa69d1a2a77f7e618638ddb95c39655df138
+size 5204

runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640879.0db4763e2117.1712.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecebd526810631e1c913902a6ebef9faf73d204f01f333ff67a095b609a56a4
+size 6905

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c94191c0ad987493b022bf2df16f9d29bf8c5807f2f4ddb0c28f593979ff2cf
+oid sha256:f1e429b7a648ede63895839361e40497178ac098dbcde1deb4b4550ebe214f14
 size 4984