Training in progress, epoch 22, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759e11911622505bdb5a77d511b901f277ce0bbc06c416da623a53f9c0f0b663
+oid sha256:6753c78b7c0ef33c0e06df98fc2b17af826195a3d977ff76dfe9dc01bc829d36
 size 1227009528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c251d2bf032c0284e58db70391eefabbbff2c2fb3bc7e50e9d6ba42d7c0345d5
+oid sha256:017a44d3ac93ea4bfa9fd21994bffd93889bffa070c7758ab5420752aaad3c5b
 size 2454133690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db8bac039de345d3f184975bc589d15c0b93c070db1287ed5147dba9f5ba405
+oid sha256:bd02ebed0dfeff533894ca511f1b34ff916fe512d4945de5b16f69750a67af48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7adf3363afe258d5bb46d306ca21d84331e969bff032715bb85737194722fbc
+oid sha256:4565350eeb4b76edcdc222b4a803476b9ee67ea5c3c110e2c10f3af6e808474b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 34.54485321044922,
-  "best_model_checkpoint": "/kaggle/working/output/checkpoint-20880",
-  "epoch": 21.0,
+  "best_metric": 34.53865432739258,
+  "best_model_checkpoint": "/kaggle/working/output/checkpoint-28710",
+  "epoch": 22.0,
   "eval_steps": 500,
-  "global_step": 27405,
+  "global_step": 28710,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2093,6 +2093,105 @@
       "eval_samples_per_second": 26.452,
       "eval_steps_per_second": 3.324,
       "step": 27405
+    },
+    {
+      "epoch": 21.0727969348659,
+      "grad_norm": 2.287121534347534,
+      "learning_rate": 3.683572796934866e-05,
+      "loss": 32.9962,
+      "step": 27500
+    },
+    {
+      "epoch": 21.149425287356323,
+      "grad_norm": 2.5622124671936035,
+      "learning_rate": 3.678783524904214e-05,
+      "loss": 33.2565,
+      "step": 27600
+    },
+    {
+      "epoch": 21.226053639846743,
+      "grad_norm": 2.2134974002838135,
+      "learning_rate": 3.673994252873563e-05,
+      "loss": 33.7442,
+      "step": 27700
+    },
+    {
+      "epoch": 21.302681992337163,
+      "grad_norm": 2.574054002761841,
+      "learning_rate": 3.669204980842912e-05,
+      "loss": 33.7998,
+      "step": 27800
+    },
+    {
+      "epoch": 21.379310344827587,
+      "grad_norm": 2.8479721546173096,
+      "learning_rate": 3.6644157088122604e-05,
+      "loss": 33.2015,
+      "step": 27900
+    },
+    {
+      "epoch": 21.455938697318008,
+      "grad_norm": 4.845319747924805,
+      "learning_rate": 3.659626436781609e-05,
+      "loss": 33.7904,
+      "step": 28000
+    },
+    {
+      "epoch": 21.532567049808428,
+      "grad_norm": 2.353726863861084,
+      "learning_rate": 3.6548371647509584e-05,
+      "loss": 33.7207,
+      "step": 28100
+    },
+    {
+      "epoch": 21.60919540229885,
+      "grad_norm": 3.003556966781616,
+      "learning_rate": 3.650047892720307e-05,
+      "loss": 33.297,
+      "step": 28200
+    },
+    {
+      "epoch": 21.685823754789272,
+      "grad_norm": 4.815252304077148,
+      "learning_rate": 3.645258620689656e-05,
+      "loss": 33.3036,
+      "step": 28300
+    },
+    {
+      "epoch": 21.762452107279692,
+      "grad_norm": 3.0622081756591797,
+      "learning_rate": 3.640469348659004e-05,
+      "loss": 33.3661,
+      "step": 28400
+    },
+    {
+      "epoch": 21.839080459770116,
+      "grad_norm": 3.3728883266448975,
+      "learning_rate": 3.6356800766283525e-05,
+      "loss": 32.8782,
+      "step": 28500
+    },
+    {
+      "epoch": 21.915708812260537,
+      "grad_norm": 2.2338080406188965,
+      "learning_rate": 3.630890804597701e-05,
+      "loss": 33.0412,
+      "step": 28600
+    },
+    {
+      "epoch": 21.992337164750957,
+      "grad_norm": 3.717360019683838,
+      "learning_rate": 3.62610153256705e-05,
+      "loss": 33.0318,
+      "step": 28700
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 34.53865432739258,
+      "eval_runtime": 49.3318,
+      "eval_samples_per_second": 26.454,
+      "eval_steps_per_second": 3.324,
+      "step": 28710
     }
   ],
   "logging_steps": 100,
@@ -2107,7 +2206,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 5
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -2121,7 +2220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.955352896399053e+16,
+  "total_flos": 3.0960839867037696e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null