Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321c691282333574ae3ecfaac8058bd49f9bec725ef06e38a74bd79d46540459
+oid sha256:0f17a8842bd1dda8817521c87dca7399f6b82c2feb14dca8cf129cb37c7f19f0
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3bece3f1734101ab0d8e91bc4e0dd89a6c2c183c7b697ab6eea4ca99735d89
+oid sha256:f0460150bc9761f35800218de11f1ece2a43cc8e686546af08a8463710e5137c
 size 535874874

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189e0d8819c0e53e229fbb1c3c52bec727218a1a7a06af8e13193a34e6249e58
+oid sha256:232ad4134ceeb1880defec30bd4e24accc658768c7d22234560a854be95a4e10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5639930963516235,
+  "best_metric": 0.5796988010406494,
   "best_model_checkpoint": "/kaggle/working/results/checkpoint-2000",
   "epoch": 0.09845911485255747,
   "eval_steps": 2000,
@@ -10,45 +10,45 @@
   "log_history": [
     {
       "epoch": 0.024614778713139367,
-      "grad_norm": 16.002241134643555,
-      "learning_rate": 7.901540885147443e-05,
-      "loss": 0.6917,
+      "grad_norm": 5.313698768615723,
+      "learning_rate": 7.803081770294886e-05,
+      "loss": 0.4406,
       "step": 500
     },
     {
       "epoch": 0.049229557426278735,
-      "grad_norm": 4.50161075592041,
-      "learning_rate": 7.803081770294886e-05,
-      "loss": 0.7013,
+      "grad_norm": 4.412301540374756,
+      "learning_rate": 7.60616354058977e-05,
+      "loss": 0.4528,
       "step": 1000
     },
     {
       "epoch": 0.07384433613941811,
-      "grad_norm": 5.799191474914551,
-      "learning_rate": 7.704622655442329e-05,
-      "loss": 0.6597,
+      "grad_norm": 12.368891716003418,
+      "learning_rate": 7.409245310884655e-05,
+      "loss": 0.4101,
       "step": 1500
     },
     {
       "epoch": 0.09845911485255747,
-      "grad_norm": 4.640450954437256,
-      "learning_rate": 7.60616354058977e-05,
-      "loss": 0.6615,
+      "grad_norm": 6.372128486633301,
+      "learning_rate": 7.21232708117954e-05,
+      "loss": 0.4215,
       "step": 2000
     },
     {
       "epoch": 0.09845911485255747,
-      "eval_loss": 0.5639930963516235,
-      "eval_runtime": 250.2708,
-      "eval_samples_per_second": 113.941,
-      "eval_steps_per_second": 1.782,
+      "eval_loss": 0.5796988010406494,
+      "eval_runtime": 249.9087,
+      "eval_samples_per_second": 114.106,
+      "eval_steps_per_second": 1.785,
       "step": 2000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 40626,
+  "max_steps": 20313,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 2000,
   "stateful_callbacks": {
     "TrainerControl": {

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767e084587bf938119ad3da54ed8e841827f12fa1412f0a5d94c3b189a2d5c5e
+oid sha256:847456b1bcbfbb9e8249408ddaf4758461104fe8cd1038a47b32746b92b87822
 size 5240