Training in progress, epoch 3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b35e92fe17a7df1309cb39c82347715641e7a685a9a2f58ee78dd0474f4e35a
+oid sha256:cab4a4f5f14e9779a531d01f28ac211f94f9ea6f55bf5a4fec89c6f08b5b7d4c
 size 98725415

run-6/checkpoint-108/config.json

@@ -24,7 +24,7 @@
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.27.2",
   "trigram_input": true,
   "true_hidden_size": 128,
   "type_vocab_size": 2,

run-6/checkpoint-108/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d3532e1669ab93372e384d32f8c22104d0c33def320b5a559a913baff36c3c
-size 197593757
+oid sha256:819a7169573fc8858df147ee50b93aadc5729bb70a760e546045b039c6720026
+size 197314895

run-6/checkpoint-108/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edba49d5088f31a87f108b80782cde6e503b7dc4af7a1e54fb9f388fadd4dce2
-size 14244
+oid sha256:495d2e26b9126cb3a2a89f1b6cb8610fba1d460a1709d58d3fd3ac4ac423972c
+size 14639

run-6/checkpoint-108/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7658662a43e3deed475c9f34113975ebc5ca5c0a3a605985a4756ed7b405d3
-size 1064
+oid sha256:20e6b74bdcbfe36bab807beca8b732c46b4c3bc1c464eded209f587fa46edd2e
+size 627

run-6/checkpoint-108/tokenizer_config.json

@@ -1,53 +1,11 @@
 {
-  "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": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "MobileBertTokenizer",

run-6/checkpoint-108/trainer_state.json

@@ -1,8 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-6/checkpoint-27",
-  "epoch": 4.0,
-  "eval_steps": 500,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-6/checkpoint-54",
+  "epoch": 2.0,
   "global_step": 108,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
@@ -10,53 +9,31 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 525302.3125,
+      "eval_loss": 3342482.75,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.4303,
-      "eval_samples_per_second": 429.167,
-      "eval_steps_per_second": 27.157,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 379292.46875,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 3.0784,
-      "eval_samples_per_second": 338.81,
-      "eval_steps_per_second": 21.44,
+      "eval_runtime": 2.3778,
+      "eval_samples_per_second": 438.637,
+      "eval_steps_per_second": 27.757,
       "step": 54
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 300663.59375,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.4571,
-      "eval_samples_per_second": 424.486,
-      "eval_steps_per_second": 26.861,
-      "step": 81
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 275189.75,
+      "epoch": 2.0,
+      "eval_loss": 2052998.375,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.4403,
-      "eval_samples_per_second": 427.398,
-      "eval_steps_per_second": 27.045,
+      "eval_runtime": 2.5321,
+      "eval_samples_per_second": 411.91,
+      "eval_steps_per_second": 26.065,
       "step": 108
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 108,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 500,
+  "max_steps": 270,
+  "num_train_epochs": 5,
   "total_flos": 0,
-  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.4530909133359774e-06,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "seed": 38
+    "learning_rate": 2.183143405028972e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
   }
 }

run-6/checkpoint-108/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7021ddbc9f735587e005cd15b2093198e20a0ab6b0d32428e98235a674189b5
-size 4920
+oid sha256:f3fd04e0f847400a111a7560c3c5fd1dfed25dd0b3761344b9022de98be9df8d
+size 3643

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074878.f87fe01c66be.29486.15

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5cf7a28dd027f28c399c9cf86152d1c66d0a704077cfa43c6e4841e85c80b8
-size 4603
+oid sha256:d70b150110c6fcbe4ecbbc60f47ea7751338b63ae5c916dbf951e7d14a43ec6b
+size 5267