Training in progress, epoch 1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3177ff1c7e1d1101ce097a0a91a4094cbd59106da386a1ceac5a62de3d8739
+oid sha256:3e6f069568448c8fce2fa03ec208a0b0f68a8f7e40e04e1d73018957f54f92bd
 size 98725415

run-7/checkpoint-54/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-7/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7affee6c74a209a215adfc1cf91c03f18db9d1f0b0d06405f4c2c6b4c4a58a0d
-size 197593757
+oid sha256:339a115bb38bd69746afe85ca9371cbc31832d07456f413509dce1d09604e074
+size 197314895

run-7/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6661f5999e1c5c7999b499b44f5346398c83de755ebd402d96dea238ff07741e
-size 14244
+oid sha256:37c16d7946d4e194042471be305a40029c40c0c40b897e3016a632e29bc647a5
+size 14575

run-7/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fa37b3310a22da1eccfa6bbf7e5cd4e64e78d627fcb2a1f6592110f94c1f59
-size 1064
+oid sha256:7716f0ca59791bba06370213e53d00fec6c4dd89ac3ccfa7a275e8518f6b6875
+size 627

run-7/checkpoint-54/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-7/checkpoint-54/trainer_state.json

@@ -1,8 +1,7 @@
 {
   "best_metric": 0.0,
-  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-7/checkpoint-27",
-  "epoch": 2.0,
-  "eval_steps": 500,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-7/checkpoint-54",
+  "epoch": 1.0,
   "global_step": 54,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
@@ -10,35 +9,22 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 6280937.5,
+      "eval_loss": 2132439.5,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.387,
-      "eval_samples_per_second": 436.946,
-      "eval_steps_per_second": 27.649,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 4771995.0,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.5044,
-      "eval_samples_per_second": 416.474,
-      "eval_steps_per_second": 26.354,
+      "eval_runtime": 2.549,
+      "eval_samples_per_second": 409.176,
+      "eval_steps_per_second": 25.892,
       "step": 54
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 54,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 500,
+  "max_steps": 162,
+  "num_train_epochs": 3,
   "total_flos": 0,
-  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.206489808409032e-06,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 32,
-    "seed": 16
+    "learning_rate": 3.4814075855726228e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 4
   }
 }

run-7/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22468bd7237c8b7fe66ae992798d3ed4e0e539e83c4a1a754bb4a56380dff61d
-size 4920
+oid sha256:7e097bc98bc61507a9a41c640eb6b06d5e0287c9fab94077dd6aff831c20bb6d
+size 3643

runs/Mar10_12-23-35_f87fe01c66be/1710074990.5515924/events.out.tfevents.1710074990.f87fe01c66be.29486.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc5e2b41d6e6812abef4fb9eda1887a32a632e3dbdc2c1a454f1f723a5ec7ad
+size 5884

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:a7cd82f132bca56808e5fe552bcb4ae5d8eb81af293ae5b567a3e8f037ff5f86
-size 5937
+oid sha256:1ae7c5b5a8701301169c71ca47519e30594669dc05774823469c40bffe835a83
+size 6291

runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710074990.f87fe01c66be.29486.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093b1b71b04d280e35528af801a20c21bf6b6e96cdde570c6e95fca5a25c49af
+size 4604

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fd04e0f847400a111a7560c3c5fd1dfed25dd0b3761344b9022de98be9df8d
+oid sha256:7e097bc98bc61507a9a41c640eb6b06d5e0287c9fab94077dd6aff831c20bb6d
 size 3643