Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2821aed8ad53a1b4125cce904f99586c69649435ced6b40b75870d96cf717833
+oid sha256:ec4a3a9d12c7287677af4951eddac9adb9340d68b150314ad87d0c660a35dd2b
 size 267832560

run-2/checkpoint-358/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "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,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-358/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab8d805b7d889653e707cf4269cc759409ed4a774caa0242bccac9cf99af7fe
+size 267832560

run-2/checkpoint-358/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a217a9ca79d256629ba1b782a716ea4b66b002640e58a9e7ada71ace204bec
+size 535727290

run-2/checkpoint-358/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aad66c97cda0beeed0352e0d7e23c584325cc090ac81cefe685a5b181a34504
+size 14244

run-2/checkpoint-358/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d7acee23d36db7caa2d340e785866a997e1423d9a4dd472714c390c48de63d
+size 1064

run-2/checkpoint-358/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-358/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-358/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.5979160666465759,
+  "best_model_checkpoint": "./results/run-2/checkpoint-179",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 358,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6590277777777779,
+      "eval_loss": 0.5979160666465759,
+      "eval_runtime": 5.582,
+      "eval_samples_per_second": 171.087,
+      "eval_steps_per_second": 21.498,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6805555555555555,
+      "eval_loss": 0.6209200620651245,
+      "eval_runtime": 5.8307,
+      "eval_samples_per_second": 163.789,
+      "eval_steps_per_second": 20.581,
+      "step": 358
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 358,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.581247532366931e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 16
+  }
+}

run-2/checkpoint-358/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c633ed7e3612a5e5d297d29173201510ab737bc2800b9f5e33be1dfb865b9d
+size 4920

run-3/checkpoint-358/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace8a2f152db9071b6bb464dff88f04f38ab58371107db9738b74a4595b1799f
+oid sha256:ec4a3a9d12c7287677af4951eddac9adb9340d68b150314ad87d0c660a35dd2b
 size 267832560

run-3/checkpoint-358/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568502e6ceb7c9740d8f210dc5d855d7bd4328b4cbe611d5634991b99dfb0c52
+oid sha256:5b0eb509d873e9b3e555d32d9a3ef9063c9fd76787f41f94d2dd01afca01fdb0
 size 535727290

run-3/checkpoint-358/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35231d0c05fbe203dd82f0d3a925b7c7eb38b282236e1ecdf1abe67df1c64f19
-size 14308
+oid sha256:8f2ae4a8beabf1c06a06b7e7f5b02f42854f9adbd6183588a6c21079892c97c5
+size 14244

run-3/checkpoint-358/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19253e2e95a48d950a6a6544c603ce6076563125502f693fa6d0e553c4861f0
+oid sha256:4a0e3f4f8f555ed5802a704ebe2e676addbc36a2a54819697bfa5f1577040a03
 size 1064

run-3/checkpoint-358/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6492276787757874,
+  "best_metric": 0.6891506910324097,
   "best_model_checkpoint": "./results/run-3/checkpoint-358",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6294507575757575,
-      "eval_loss": 0.6492276787757874,
-      "eval_runtime": 5.5974,
-      "eval_samples_per_second": 170.616,
-      "eval_steps_per_second": 10.719,
+      "eval_accuracy": 0.5336805555555555,
+      "eval_loss": 0.6891506910324097,
+      "eval_runtime": 5.7933,
+      "eval_samples_per_second": 164.844,
+      "eval_steps_per_second": 20.713,
       "step": 358
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1074,
+  "max_steps": 358,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.648944513471952e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 1.2695590597784586e-06,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 8,
-    "seed": 17
+    "seed": 34
   }
 }

run-3/checkpoint-358/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d942e96edd825810bea99d8e9ba8c3e79dee5d5f647f4c147e0b3268db47d468
+oid sha256:b811fcee375e3abae0a37f9eac47b06f438a2a81e05b09dcc65ce086d972aaed
 size 4920

runs/Mar09_20-46-55_12ef847df42e/events.out.tfevents.1710018271.12ef847df42e.11821.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee9fddbbb4976dd7480dd903fda82b23823664ad6b055172004a29ba8075cdf
+size 5116

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c633ed7e3612a5e5d297d29173201510ab737bc2800b9f5e33be1dfb865b9d
+oid sha256:b811fcee375e3abae0a37f9eac47b06f438a2a81e05b09dcc65ce086d972aaed
 size 4920