Training in progress, step 157

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21467a9de9236441169d1f3d8f496f4b5960ab2f6126931d110f356d90b3457d
+oid sha256:c1d7e8d2dd07702b4bd327bc54d3ec6482e628f8402c7643ac9ea85019abc937
 size 265470032

run-2/checkpoint-157/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-157/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d7e8d2dd07702b4bd327bc54d3ec6482e628f8402c7643ac9ea85019abc937
+size 265470032

run-2/checkpoint-157/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d583f6d9ce7035a9bbce19c6b07b98037ad8b317c00ee4448dfd146071966726
+size 531000890

run-2/checkpoint-157/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f953383786304d481dbcabb856ff0a112d355759906bb4e4c4f966a22e5491
+size 14244

run-2/checkpoint-157/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b39bff513bd23ae499720a0b4be1f73cd2c8db11e70d80d1ebe34b0a98ff9e2
+size 1064

run-2/checkpoint-157/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-157/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-157/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 157,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 8.715664863586426,
+      "learning_rate": 1.4701513386718959e-05,
+      "loss": 3.8477,
+      "step": 100
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "eval_loss": 2.9882283210754395,
+      "eval_runtime": 3.592,
+      "eval_samples_per_second": 139.197,
+      "eval_steps_per_second": 4.454,
+      "step": 100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 157,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 313567440076800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.049364213534871e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 12
+  }
+}

run-2/checkpoint-157/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fb29d5e5fdea6fd35a82dd220c30b7f0a3ade055b8a015b599470bf6f5a85a
+size 5176

runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731925628.aa151f0a91fc.1516.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f0dbcdda8f0058b8940b4839889009e12d86b0295bfa7bd2185361ca7646bd
+size 5659

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf95a1b40d7940f8a3f7af89bc534a9cafc9dabe2afeba003b8c21fddf5340e
+oid sha256:f5fb29d5e5fdea6fd35a82dd220c30b7f0a3ade055b8a015b599470bf6f5a85a
 size 5176