Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cc30988e06e076ad7015710af5705a8a331318f493e51c9707525a0728b74b
+oid sha256:256fe138d73ad3ec74b96ef8843480fe21ccb859d7fc6c2d8ccec51ac0404bee
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13499993dc923abc67babfacde62bbd3376d22ad5857c78a7f265ccc3f84611e
+oid sha256:576458bcfc6604668b1c8689b7dd544f23b2b3a1df0803a8b6df0ccbf587e177
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678b9545597981e0561935b4560b5685ae06bb237af557617b5c6286a1739a94
+oid sha256:7ee9fdb1704839af779f9e11eba2b04b9cf92c65f7a157de690cfa6725f06d4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03368421052631579,
+  "epoch": 0.05052631578947368,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 10.701,
       "eval_steps_per_second": 5.351,
       "step": 20
+    },
+    {
+      "epoch": 0.03536842105263158,
+      "grad_norm": 1.4428808689117432,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5744,
+      "step": 21
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "grad_norm": 1.6106152534484863,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4784,
+      "step": 24
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 1.6619267463684082,
+      "eval_runtime": 23.3713,
+      "eval_samples_per_second": 10.697,
+      "eval_steps_per_second": 5.348,
+      "step": 25
+    },
+    {
+      "epoch": 0.04547368421052632,
+      "grad_norm": 1.8915555477142334,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4925,
+      "step": 27
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 2.1500985622406006,
+      "learning_rate": 0.0,
+      "loss": 1.5562,
+      "step": 30
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "eval_loss": 1.603967308998108,
+      "eval_runtime": 23.3786,
+      "eval_samples_per_second": 10.694,
+      "eval_steps_per_second": 5.347,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26955844272128e+16,
+  "total_flos": 1.90433766408192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null