Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89038960725dcedab358bf4e42cef0ef273efef56179b14013fdfcdacd30faa
+oid sha256:ff04b50c808d3fa37ae2aafe3366f7cdd6fe06fa9c8eeb79d3aee582b0564be3
 size 437958648

run-1/checkpoint-716/config.json

@@ -9,52 +9,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9",
-    "10": "LABEL_10",
-    "11": "LABEL_11",
-    "12": "LABEL_12",
-    "13": "LABEL_13",
-    "14": "LABEL_14",
-    "15": "LABEL_15",
-    "16": "LABEL_16",
-    "17": "LABEL_17",
-    "18": "LABEL_18",
-    "19": "LABEL_19"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_10": 10,
-    "LABEL_11": 11,
-    "LABEL_12": 12,
-    "LABEL_13": 13,
-    "LABEL_14": 14,
-    "LABEL_15": 15,
-    "LABEL_16": 16,
-    "LABEL_17": 17,
-    "LABEL_18": 18,
-    "LABEL_19": 19,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5,
-    "LABEL_6": 6,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

run-1/checkpoint-716/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7fdfc662193895f3f4b389fe3b0ce5b12120d88dbba1ec6f2eaa4ed1f8dff07
-size 438014016
+oid sha256:ff04b50c808d3fa37ae2aafe3366f7cdd6fe06fa9c8eeb79d3aee582b0564be3
+size 437958648

run-1/checkpoint-716/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc97ee71cb62ad8b2189913d9d43d7aa11ae887597d2701a89391c32f343d59
-size 876149114
+oid sha256:03b6636cf9dd47d939432f16a2c04c867a83e9925455521525c4d6f818cc516f
+size 876038394

run-1/checkpoint-716/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99a95ea7c02dd38224148e653434fcbc40097afa206b069ae857a295aa754cb
-size 14244
+oid sha256:b4a70539f64bd19360d55b7be367a639d618987a43451ba51c97bd0803f5edf2
+size 14308

run-1/checkpoint-716/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f93594f0112c11a5c563da2362554620e206f28c4210265cbf7258f20c3a48
+oid sha256:2f8007babf50197cb874075e589d53343c142d82c0b75d9032f834bcab6dcdae
 size 1064

run-1/checkpoint-716/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.6204203963279724,
-  "best_model_checkpoint": "./results/run-1/checkpoint-716",
-  "epoch": 1.0,
+  "best_metric": 0.6921326518058777,
+  "best_model_checkpoint": "./results/run-1/checkpoint-537",
+  "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 716,
   "is_hyper_param_search": true,
@@ -9,34 +9,61 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.7,
-      "grad_norm": 7.824489116668701,
-      "learning_rate": 7.2003443241226645e-06,
-      "loss": 0.7899,
+      "epoch": 1.0,
+      "eval_accuracy": 0.4767361111111111,
+      "eval_loss": 0.7058395743370056,
+      "eval_runtime": 10.1923,
+      "eval_samples_per_second": 93.699,
+      "eval_steps_per_second": 11.774,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4767361111111111,
+      "eval_loss": 0.6963791847229004,
+      "eval_runtime": 10.2009,
+      "eval_samples_per_second": 93.619,
+      "eval_steps_per_second": 11.764,
+      "step": 358
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.733151912689209,
+      "learning_rate": 2.704726645687229e-05,
+      "loss": 0.7041,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6642361111111111,
-      "eval_loss": 0.6204203963279724,
-      "eval_runtime": 9.9873,
-      "eval_samples_per_second": 95.622,
-      "eval_steps_per_second": 12.015,
+      "epoch": 3.0,
+      "eval_accuracy": 0.523263888888889,
+      "eval_loss": 0.6921326518058777,
+      "eval_runtime": 10.2133,
+      "eval_samples_per_second": 93.505,
+      "eval_steps_per_second": 11.749,
+      "step": 537
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.523263888888889,
+      "eval_loss": 0.692633867263794,
+      "eval_runtime": 10.1892,
+      "eval_samples_per_second": 93.726,
+      "eval_steps_per_second": 11.777,
       "step": 716
     }
   ],
   "logging_steps": 500,
   "max_steps": 716,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 526307155968000.0,
-  "train_batch_size": 4,
+  "total_flos": 2103835998658560.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.3867808037369573e-05,
-    "num_train_epochs": 1,
-    "per_device_train_batch_size": 4,
-    "seed": 16
+    "learning_rate": 8.965667955148406e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 29
   }
 }

run-1/checkpoint-716/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f072c5bdb0ceff32b15753ea78f539fc94c829513d06b82d2b5fa7e4cae0d2
+oid sha256:5a33f4de412ad54537b01ce6640bfb1f21c50e4133cf454236326e784236cba2
 size 4920

runs/Mar09_23-14-00_aa189cdd2d19/events.out.tfevents.1710026870.aa189cdd2d19.2368.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355402d6361ab3208fec84733734b4b247a46780778753f8cb35cd17aa96df59
-size 5743
+oid sha256:c74b07016bedf79741b57d1b2b649342dc6272dfff02bd6535e5363f0c67d087
+size 6420