Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbcc302472d25aee76016eb179994f445fcdbd94a26ae33ee417737b2f5dc9b
+oid sha256:b87e447afcc6450cb13ca14e3644e9d76788c936457f95dbb88373e764323c93
 size 437958648

run-1/checkpoint-421/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-421/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87e447afcc6450cb13ca14e3644e9d76788c936457f95dbb88373e764323c93
+size 437958648

run-1/checkpoint-421/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c5e442e0335ad06aabd4219520f83d836f05aaa206cd49e9e9002039b902d6
+size 876038394

run-1/checkpoint-421/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c97730e8ef7fe003e00ca57e2d8c1d9608f1dba9d62d7a5a9a2c290c4a7efe
+size 14244

run-1/checkpoint-421/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007422cd206e459dbec437195dce03e54d6efd484d3f56073486061b06713d45
+size 1064

run-1/checkpoint-421/special_tokens_map.json

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

run-1/checkpoint-421/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-421/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.9231651376146789,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-421",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 421,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.24830688536167145,
+      "eval_runtime": 2.2848,
+      "eval_samples_per_second": 381.657,
+      "eval_steps_per_second": 24.072,
+      "step": 421
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1263,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.192522522297658e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 6
+  }
+}

run-1/checkpoint-421/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a42951e65bb3aa1e125b1b27e2a27b66ec94bb48bc4ff40d24214557a0e4b15
+size 4920

run-1/checkpoint-842/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8646788990825688,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-842",
-  "epoch": 1.0,
+  "best_metric": 0.9231651376146789,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-421",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 842,
   "is_hyper_param_search": true,
@@ -9,34 +9,43 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.59,
-      "grad_norm": 5.992064476013184,
-      "learning_rate": 2.846915930651389e-05,
-      "loss": 0.4119,
+      "epoch": 1.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.24830688536167145,
+      "eval_runtime": 2.2848,
+      "eval_samples_per_second": 381.657,
+      "eval_steps_per_second": 24.072,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.174437165260315,
+      "learning_rate": 3.136892070081642e-05,
+      "loss": 0.3128,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8646788990825688,
-      "eval_loss": 0.40675637125968933,
-      "eval_runtime": 2.35,
-      "eval_samples_per_second": 371.063,
-      "eval_steps_per_second": 23.404,
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.3306081295013428,
+      "eval_runtime": 2.3075,
+      "eval_samples_per_second": 377.901,
+      "eval_steps_per_second": 23.835,
       "step": 842
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1684,
+  "max_steps": 1263,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 62016097970400.0,
-  "train_batch_size": 8,
+  "total_flos": 145542552494040.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.0491608337980904e-05,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 8,
-    "seed": 26
+    "learning_rate": 5.192522522297658e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 6
   }
 }

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709497614.90708aaa767a.21824.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1778f90d52d065d9300ccfe56cd2b6065e60d4ee8042afbb97744bb1516d48d
+size 5691

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680d0afe4db5f1404c33bdba3d7f7d0610baba4265733865b13f9ea27d8c6125
+oid sha256:5a42951e65bb3aa1e125b1b27e2a27b66ec94bb48bc4ff40d24214557a0e4b15
 size 4920