Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4272aa05d63a04ec45fa8b6e1aed2e59c71e48336fa640a4a63a04b7be15f1fb
+oid sha256:f651e4a43d469920526a839771b6b65a90df844fdb3c29d87dca9330e796499a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60fe4ad6134c1edb8123ab60e4f9114994f5a144f02237e02c535e785c019e4d
+oid sha256:1a00eb4e1629585bcbf98ea1d7eab1f3d82907f270006832a2e324c318d85312
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4e9efa9a2bb2447b7f403caaaa71665b13ac41b45e6cb4a54ec29099c86e08
+oid sha256:f352ba085f8aae7dc9166c61c16535c303978ac30cf175d8e91e9ece2e494fc3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012152144853566655,
+  "epoch": 0.001620285980475554,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,35 @@
       "eval_samples_per_second": 7.771,
       "eval_steps_per_second": 3.887,
       "step": 30
+    },
+    {
+      "epoch": 0.001336735933892332,
+      "grad_norm": 1.4657238721847534,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 2.0548,
+      "step": 33
+    },
+    {
+      "epoch": 0.0014582573824279985,
+      "grad_norm": 1.554992437362671,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.1922,
+      "step": 36
+    },
+    {
+      "epoch": 0.001579778830963665,
+      "grad_norm": 1.369084358215332,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 1.8381,
+      "step": 39
+    },
+    {
+      "epoch": 0.001620285980475554,
+      "eval_loss": 1.891857385635376,
+      "eval_runtime": 335.6622,
+      "eval_samples_per_second": 7.743,
+      "eval_steps_per_second": 3.873,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -123,12 +152,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4729531432697856.0,
+  "total_flos": 6120570089373696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null