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:a79ca9f8f3e9574cc290bc1a64bb65f09530779b2a90128b9c90cbb14274236c
+oid sha256:91200de5c41a9b8b040b53a5d95af8e355789566e586733887251fbff96c1e88
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91780d9c2518ce43ba4d4684215b49fee7c5e44b4535d0a7decd7a0050148739
+oid sha256:795bead6b80ca3e5c644ecbda42f33abb449048f6ecceb0b599505e1024a334d
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
+oid sha256:63606c73c93c05d27e7758139a39e39228c390bd2d751703d97059d8f583fa7f
 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": 0.001007543985592121,
+  "epoch": 0.0015113159783881815,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 1.8519,
       "step": 18
+    },
+    {
+      "epoch": 0.0010579211848717272,
+      "grad_norm": 1.3882564306259155,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.7061,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012090527827105452,
+      "grad_norm": 1.8157745599746704,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7379,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012090527827105452,
+      "eval_loss": 1.7392501831054688,
+      "eval_runtime": 478.4663,
+      "eval_samples_per_second": 17.468,
+      "eval_steps_per_second": 8.734,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013601843805493635,
+      "grad_norm": 1.3854663372039795,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.6428,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015113159783881815,
+      "grad_norm": 1.552529215812683,
+      "learning_rate": 0.0,
+      "loss": 1.5177,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null