Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc896c70d6094782d316ed4ff72f355a62338eb7a17610edb8898dde5fe8c59
+oid sha256:96f8a76cbb60b5451580ffdde7d9a4462ff9b3bf8c4a7c8aac66e1154437aaa8
 size 470641664

run-7/checkpoint-211/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-211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f8a76cbb60b5451580ffdde7d9a4462ff9b3bf8c4a7c8aac66e1154437aaa8
+size 470641664

run-7/checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21ac6fae2e880655a31337b75429914255084f24150f2c8d21fe8b5ecd94e31
+size 941404410

run-7/checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f2124cf661d0c5e91b248d7b992e08ce477b7cbe2d55d456e3baf296b2568a
+size 14244

run-7/checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05e1b9e776411945bd9a7215273c7bf636a1849153394596b41511f80ec94c4
+size 1064

run-7/checkpoint-211/sentencepiece.bpe.model

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

run-7/checkpoint-211/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-211/tokenizer.json

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

run-7/checkpoint-211/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-211/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.8119266055045872,
+  "best_model_checkpoint": "microsoft/Multilingual-MiniLM-L12-H384-finetuned-sst2/run-7/checkpoint-211",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 211,
+  "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
+    }
+  ],
+  "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-211/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.1709640058.0db4763e2117.1712.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08850a0f9f7a31306538d37531136d86da117630ecc54e5602af77639c56ec9
+size 4993

runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640098.0db4763e2117.1712.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9d6e61b3e5d56cee62a79beff424a83e68d6cb521bb8d6aeb2728502c3ddc8
+size 5202

runs/Mar05_10-49-50_0db4763e2117/events.out.tfevents.1709640171.0db4763e2117.1712.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d848b7502d36c6837eda863dd406becaba07f489f4da5856d361f2712c63221e
+size 5671

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6a6f9969049103e5698f1db819dd1df7a7e024a2e35a83b61a6fb789d6e160
+oid sha256:6c94191c0ad987493b022bf2df16f9d29bf8c5807f2f4ddb0c28f593979ff2cf
 size 4984