Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821773593319cef84468d10a244226341b7b8667c44dd2971a1cf23640daed44
+oid sha256:250e25595de8039a24da353593b9697e42ab62c683e50e1fdb2c921bdcea65fe
 size 775678032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52632d962d021592a4d35dcf054f881443ff2887ff0e4bbbc4353a2b8b9a91f6
+oid sha256:848021c2d95c74a21072d1e11aba29456852c7c3c07839655c28fa0dec26efd0
 size 1551478091

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55722c1d04d6be8d4523cc19c3a4a31a7e2280365d564803d84b6488532136d
+oid sha256:83751bc58126f0610181a63470d31f2fe231d46b448e44c86967f8f00d382a8c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b19a7500950d30fded81aead129a45d919e1761663c3b918dd44c1accdbcb20
+oid sha256:e059b4a74bd60b17378ac1812a5265766d977ce49f9d76f61e1ad80049716658
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 7.187783241271973,
-  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-1000",
-  "epoch": 0.1503250779811342,
+  "best_global_step": 2000,
+  "best_metric": 6.232546329498291,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-2000",
+  "epoch": 0.3006501559622684,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,42 @@
       "eval_samples_per_second": 70.07,
       "eval_steps_per_second": 1.096,
       "step": 1000
+    },
+    {
+      "epoch": 0.18790634747641774,
+      "grad_norm": 108.36956024169922,
+      "learning_rate": 2.3477443609022555e-05,
+      "loss": 58.785421875,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2254876169717013,
+      "grad_norm": 111.00702667236328,
+      "learning_rate": 2.8176691729323312e-05,
+      "loss": 56.1699921875,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26306888646698484,
+      "grad_norm": 102.0089111328125,
+      "learning_rate": 3.287593984962406e-05,
+      "loss": 54.32422265625,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3006501559622684,
+      "grad_norm": 107.5756607055664,
+      "learning_rate": 3.7575187969924814e-05,
+      "loss": 52.7279453125,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3006501559622684,
+      "eval_loss": 6.232546329498291,
+      "eval_runtime": 245.4165,
+      "eval_samples_per_second": 70.093,
+      "eval_steps_per_second": 1.096,
+      "step": 2000
     }
   ],
   "logging_steps": 250,
@@ -72,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6866686140416e+16,
+  "total_flos": 3.3733372280832e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null