Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b158fd653098d86c46de46c10ed9f58274466bc11b7d08ba4d3c4a6211456951
+oid sha256:45973f0aeacdf0b2c8f20999eb6d48d7842f158dff763df78bc7bed847bbeb91
 size 1340618660

run-7/checkpoint-500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-7/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96da04bc2f849a8495df7f16ba5da017333d1561097ce6e028cfc1cb5657424a
+size 1340618660

run-7/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938db9fd3dead3a848b3346659b738f058af723f440518be940784711c1eff95
+size 2681472237

run-7/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39308b250b2dde21cca6217a709d5456bcdcab3c796c6926f25c06b9c730de1
+size 14244

run-7/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d618c2e4277a4e8fdb40e633a50d70e6babf4a0fe1442beec89a937f479ad4
+size 1064

run-7/checkpoint-500/special_tokens_map.json

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

run-7/checkpoint-500/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-7/checkpoint-500/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6702412868632708,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 1.8788208961486816,
+      "learning_rate": 6.803739492468672e-05,
+      "loss": 0.7041,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1770153959360880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.292513881295444e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-7/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc6a77ed3744bd1e05c241a83fbade4f179d7bd9950fbccd7122c05f3bc9e6c
+size 5048

run-8/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9461766d71cc52d818864796c1ea2b597890ec358346b294c381abf16bdf82cf
+oid sha256:4e321703693466f243cb7d7ba6c0276ec41434f0be8d6b8369c9562d4e93865f
 size 1340618660

run-8/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e8bde458201cb88b3dda2faf9d7d4709af674b359a94f682f1f61df90161f1
+oid sha256:8afc0d3093b65c4c10a7c07d702061d03db8772154a96287da5fe52d20b48475
 size 2681472237

run-8/checkpoint-1000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15ef18f77678b087c8d8d016723a03f0d0f4e837051c67af83ea5404cfb3e09
+oid sha256:ee5d4f5bf9cb098c9058ef37d6ea26594c6643d7293de0cc233fefe6dc2e9266
 size 14244

run-8/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2213efd67cc97cffa04c26ac0b875fd692518dbd7931cbc0273bda3d0fccf497
+oid sha256:16808be7188ffc9bb43e089fe1c0825a817d8c24271c606c1cdfb25855f67ad1
 size 1064

run-8/checkpoint-1000/trainer_state.json

@@ -10,34 +10,34 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7653369307518005,
-      "eval_loss": 0.4685952365398407,
-      "eval_runtime": 9.0759,
-      "eval_samples_per_second": 328.672,
-      "eval_steps_per_second": 20.604,
+      "eval_accuracy": 0.7355011701583862,
+      "eval_loss": 0.5057289004325867,
+      "eval_runtime": 8.9445,
+      "eval_samples_per_second": 333.501,
+      "eval_steps_per_second": 20.907,
       "step": 373
     },
     {
       "epoch": 1.3404825737265416,
-      "grad_norm": 11.95083236694336,
-      "learning_rate": 1.278490707659754e-05,
-      "loss": 0.4881,
+      "grad_norm": 9.013686180114746,
+      "learning_rate": 4.893165718898667e-06,
+      "loss": 0.5478,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7707006335258484,
-      "eval_loss": 0.47391676902770996,
-      "eval_runtime": 9.0389,
-      "eval_samples_per_second": 330.018,
-      "eval_steps_per_second": 20.688,
+      "eval_accuracy": 0.749580979347229,
+      "eval_loss": 0.5003476142883301,
+      "eval_runtime": 8.893,
+      "eval_samples_per_second": 335.432,
+      "eval_steps_per_second": 21.028,
       "step": 746
     },
     {
       "epoch": 2.680965147453083,
-      "grad_norm": 15.537776947021484,
-      "learning_rate": 1.0805819293842502e-05,
-      "loss": 0.2385,
+      "grad_norm": 11.254767417907715,
+      "learning_rate": 4.135709725261102e-06,
+      "loss": 0.3974,
       "step": 1000
     }
   ],
@@ -46,11 +46,11 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 8968123585287756.0,
+  "total_flos": 5682657989448936.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.4763994859352575e-05,
+    "learning_rate": 5.650621712536231e-06,
     "per_device_train_batch_size": 32
   }
 }

run-8/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e6a33bf8c21d040f79b518acc997a1f817992f979b28f2a817ab72bcaeabb9
+oid sha256:5c55a7132d0d8acc89b6b133e0a078c01138b9e0b5f44720d7251d38281cbb49
 size 5048

run-8/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84157c5c45e1042099f88bc965875ace1cd7c98953b8ff27ad67b1cf72b8f02
+oid sha256:45973f0aeacdf0b2c8f20999eb6d48d7842f158dff763df78bc7bed847bbeb91
 size 1340618660

run-8/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c751026411b0d6187a0f16f90634f79a35b4955a8297a16a2c68ab30b7da4cc
+oid sha256:aaf8c63804f756dbf6a2dd21266673b1cd5db3e08da4f8be8116e766bb6fdc76
 size 2681472237

run-8/checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bbf563591c5fe3fe29dd3bd70b2dd79355243b58fe1d041144c9bfbba0d18a
+oid sha256:268959cd06affa51103f53408d4fbfdbd757b4027cad9ad299a004dbe705b408
 size 14244

run-8/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a716b0a7dd5d9fc9bf3d42178286c830bd227ae23513d8ebb2eb9d208dd3b1
+oid sha256:1c6cefecd557ebda0ed45508ce763e3ba73953939d89806202dc9a32c4800354
 size 1064

run-8/checkpoint-500/trainer_state.json

@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7653369307518005,
-      "eval_loss": 0.4685952365398407,
-      "eval_runtime": 9.0759,
-      "eval_samples_per_second": 328.672,
-      "eval_steps_per_second": 20.604,
+      "eval_accuracy": 0.7355011701583862,
+      "eval_loss": 0.5057289004325867,
+      "eval_runtime": 8.9445,
+      "eval_samples_per_second": 333.501,
+      "eval_steps_per_second": 20.907,
       "step": 373
     },
     {
       "epoch": 1.3404825737265416,
-      "grad_norm": 11.95083236694336,
-      "learning_rate": 1.278490707659754e-05,
-      "loss": 0.4881,
+      "grad_norm": 9.013686180114746,
+      "learning_rate": 4.893165718898667e-06,
+      "loss": 0.5478,
       "step": 500
     }
   ],
@@ -30,11 +30,11 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 6438983261740992.0,
+  "total_flos": 3137438263856976.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.4763994859352575e-05,
+    "learning_rate": 5.650621712536231e-06,
     "per_device_train_batch_size": 32
   }
 }

run-8/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e6a33bf8c21d040f79b518acc997a1f817992f979b28f2a817ab72bcaeabb9
+oid sha256:5c55a7132d0d8acc89b6b133e0a078c01138b9e0b5f44720d7251d38281cbb49
 size 5048

run-9/checkpoint-500/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6702412868632708,
+  "epoch": 1.3404825737265416,
   "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": true,
@@ -9,23 +9,32 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.6702412868632708,
-      "grad_norm": 15.942371368408203,
-      "learning_rate": 5.489232390518381e-06,
-      "loss": 0.5696,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7425410747528076,
+      "eval_loss": 0.48700496554374695,
+      "eval_runtime": 8.9854,
+      "eval_samples_per_second": 331.985,
+      "eval_steps_per_second": 20.812,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 33.510581970214844,
+      "learning_rate": 6.933164670907242e-06,
+      "loss": 0.5256,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7460,
+  "max_steps": 3730,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1796655667961520.0,
-  "train_batch_size": 16,
+  "total_flos": 3150700039191060.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.883573797883207e-06,
-    "per_device_train_batch_size": 16
+    "learning_rate": 8.006409976001242e-06,
+    "per_device_train_batch_size": 32
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da05404e8bdf5efeabed68f0c953ae9b437da82b1da4f9d80687c63c7ac975c6
+oid sha256:5c55a7132d0d8acc89b6b133e0a078c01138b9e0b5f44720d7251d38281cbb49
 size 5048