Training in progress, step 2500

.gitattributes

@@ -32,5 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

{checkpoint-1000 → checkpoint-2000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850031ce3243a80d3659b496331db88ba7151ffeacf08604ac7171638cef7b44
+oid sha256:613d8fa70e254c004e083c947d84f82b9a9af60135de2c32941968d039eef6b3
 size 2265828101

{checkpoint-500 → checkpoint-2000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de718e31c9f491c0dfba691cef2fadf6de01ce7e4513429474a72b167fc8394
+oid sha256:5720cd89747751c7c694b6d0850b33d8d7cb5b110874811ddebb3863d2d1efff
 size 1134425553

{checkpoint-500 → checkpoint-2000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e197e1d8eee50ea05047e5b4ef2d4ecafd2134a21154c71e42b26344bf3a700
+oid sha256:c47ea06035da0f03affb7446f943fc4b8c01009a413e5b1c44c006b293b9f6f6
 size 14575

{checkpoint-500 → checkpoint-2000}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57891f859dc5fbae9d30bcda05aba26f7dc6d900c47dc4de4abfa58a72b670d1
+oid sha256:e447d7d1f92db78968e506c9d447a6cd713bb7af4075f3660bdec681ecbc7740
 size 557

{checkpoint-1000 → checkpoint-2000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcab0ffe66d73213bb723e7ed3816ba449fe7bd0b2f3ceae044473cf432e3783
+oid sha256:d5ddf4069c5d951aba1b5e1ba075edf7cf23ab79e49bb15ca733c224e0645616
 size 627

{checkpoint-1000 → checkpoint-2000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.8311511798105226,
-  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-1000",
-  "epoch": 0.4154549231408392,
-  "global_step": 1000,
+  "best_metric": 0.8337166846278812,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-2000",
+  "epoch": 0.8309098462816784,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,11 +42,47 @@
       "eval_samples_per_second": 54.764,
       "eval_steps_per_second": 3.443,
       "step": 1000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.3793103448275864e-05,
+      "loss": 0.3819,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.8102330668639719,
+      "eval_f1": 0.8102330668639719,
+      "eval_loss": 0.8744572997093201,
+      "eval_precision": 0.8102330668639719,
+      "eval_recall": 0.8102330668639719,
+      "eval_runtime": 34.6123,
+      "eval_samples_per_second": 59.285,
+      "eval_steps_per_second": 3.727,
+      "step": 1500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.171582883257167e-05,
+      "loss": 0.3361,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "eval_accuracy": 0.8337166846278812,
+      "eval_f1": 0.8337166846278812,
+      "eval_loss": 0.6990912556648254,
+      "eval_precision": 0.8337166846278812,
+      "eval_recall": 0.8337166846278812,
+      "eval_runtime": 38.6559,
+      "eval_samples_per_second": 53.084,
+      "eval_steps_per_second": 3.337,
+      "step": 2000
     }
   ],
   "max_steps": 12035,
   "num_train_epochs": 5,
-  "total_flos": 1669033433088000.0,
+  "total_flos": 3338066866176000.0,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-500 → checkpoint-2500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e752df9708b3ee64f9cfb6d6199f3b86de73e8b6d9cae131372a7ef9fae1bee2
+oid sha256:249b736b0ee96830be7e13d95931eda8b17d72ed799b1d53bf204baa5ec28678
 size 2265828101

{checkpoint-1000 → checkpoint-2500}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c23af0358fb05f012a6b62f08cda0f0f77800ae18932f19ad494e52ef62d8e
+oid sha256:9a13afdc894a855563bdc308de94030cb3ee880f8e35ef0b0686b90e4be049c5
 size 1134425553

{checkpoint-1000 → checkpoint-2500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77afc8dc240a230df75727f986b17d934e998fdd9251c9afa1179522f006116
+oid sha256:7c9591d44de932d974bc8f226917be3716a00b069a491eca25e99d763d7d1202
 size 14575

{checkpoint-1000 → checkpoint-2500}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549c363f84648ad8593fc1d45abed2e334ff664013812020536a7e08d3a19ed2
+oid sha256:0657c6296ff60320a3cd6258c348ecc016115157a70e0b03987126ec22d4801f
 size 557

{checkpoint-500 → checkpoint-2500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aceb2a9a45ec8c783f35e02c2288f9a94bec6c4f26a9fd6c2cbd758327dadb4
+oid sha256:36e6282265457b125586a29b2d41aff2b5860b72c24a97a3146a6d4661533245
 size 627

checkpoint-2500/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.8337166846278812,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-2000",
+  "epoch": 1.038637307852098,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.793934358122144e-05,
+      "loss": 0.7223,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.7741471103890881,
+      "eval_f1": 0.7741471103890881,
+      "eval_loss": 0.7764509916305542,
+      "eval_precision": 0.7741471103890881,
+      "eval_recall": 0.7741471103890881,
+      "eval_runtime": 33.2902,
+      "eval_samples_per_second": 61.64,
+      "eval_steps_per_second": 3.875,
+      "step": 500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.5870378063980065e-05,
+      "loss": 0.4469,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.8311511798105226,
+      "eval_f1": 0.8311511798105226,
+      "eval_loss": 0.5913723707199097,
+      "eval_precision": 0.8311511798105226,
+      "eval_recall": 0.8311511798105226,
+      "eval_runtime": 37.4699,
+      "eval_samples_per_second": 54.764,
+      "eval_steps_per_second": 3.443,
+      "step": 1000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.3793103448275864e-05,
+      "loss": 0.3819,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.8102330668639719,
+      "eval_f1": 0.8102330668639719,
+      "eval_loss": 0.8744572997093201,
+      "eval_precision": 0.8102330668639719,
+      "eval_recall": 0.8102330668639719,
+      "eval_runtime": 34.6123,
+      "eval_samples_per_second": 59.285,
+      "eval_steps_per_second": 3.727,
+      "step": 1500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.171582883257167e-05,
+      "loss": 0.3361,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "eval_accuracy": 0.8337166846278812,
+      "eval_f1": 0.8337166846278812,
+      "eval_loss": 0.6990912556648254,
+      "eval_precision": 0.8337166846278812,
+      "eval_recall": 0.8337166846278812,
+      "eval_runtime": 38.6559,
+      "eval_samples_per_second": 53.084,
+      "eval_steps_per_second": 3.337,
+      "step": 2000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.964270876609888e-05,
+      "loss": 0.2784,
+      "step": 2500
+    },
+    {
+      "epoch": 1.04,
+      "eval_accuracy": 0.8119380418523106,
+      "eval_f1": 0.8119380418523107,
+      "eval_loss": 0.7512525320053101,
+      "eval_precision": 0.8119380418523106,
+      "eval_recall": 0.8119380418523106,
+      "eval_runtime": 33.6314,
+      "eval_samples_per_second": 61.014,
+      "eval_steps_per_second": 3.836,
+      "step": 2500
+    }
+  ],
+  "max_steps": 12035,
+  "num_train_epochs": 5,
+  "total_flos": 4171123178466048.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/trainer_state.json

@@ -1,34 +0,0 @@
-{
-  "best_metric": 0.7741471103890881,
-  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_ml384-v2/checkpoint-500",
-  "epoch": 0.2077274615704196,
-  "global_step": 500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.21,
-      "learning_rate": 4.793934358122144e-05,
-      "loss": 0.7223,
-      "step": 500
-    },
-    {
-      "epoch": 0.21,
-      "eval_accuracy": 0.7741471103890881,
-      "eval_f1": 0.7741471103890881,
-      "eval_loss": 0.7764509916305542,
-      "eval_precision": 0.7741471103890881,
-      "eval_recall": 0.7741471103890881,
-      "eval_runtime": 33.2902,
-      "eval_samples_per_second": 61.64,
-      "eval_steps_per_second": 3.875,
-      "step": 500
-    }
-  ],
-  "max_steps": 12035,
-  "num_train_epochs": 5,
-  "total_flos": 834516716544000.0,
-  "trial_name": null,
-  "trial_params": null
-}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b1a29b3ccb13877c06b9c50bf20c54e7d085e260a305e3376c872a9cfa9e2e
+oid sha256:9a13afdc894a855563bdc308de94030cb3ee880f8e35ef0b0686b90e4be049c5
 size 1134425553

runs/Feb09_15-43-15_f1c8d3a96fe7/events.out.tfevents.1675957409.f1c8d3a96fe7.143.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643429707a800789d4f201880cd98c1a2057b31f9dc89474acd274f39e537fbf
-size 6516
+oid sha256:0f05a519a608fafd274f915fc85bdff10be90a22cf289b452daf5700ae30a1f1
+size 7774