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:f07dece5cb593f7a4bde202867ba6f00417be8f3d6848abf6e17478a5bc142cc
+oid sha256:c797c217e7809fb98485351f78d3fa0c138a03aeda375d0fb621e6eb9134d3ea
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8aae07029699d419290367b7ff26890b46e62d5ca2f4511cad4e54cb573caa
+oid sha256:faf36c41e93a91ec5afaa2739cfe9da8fcf6b213fa8a9f5f53019f8f0519b00b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
+oid sha256:a098dffa38fa9c01aae74eebd50d55d442f41711e114eb99ba341d13be3779bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033819488480236735,
+  "epoch": 0.0050729232720355105,
   "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": 0.00013090169943749476,
       "loss": 5.4754,
       "step": 18
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 8.004790306091309,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.4139,
+      "step": 21
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 1.8566102981567383,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.0694,
+      "step": 24
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "eval_loss": 1.2690829038619995,
+      "eval_runtime": 171.0213,
+      "eval_samples_per_second": 14.56,
+      "eval_steps_per_second": 7.28,
+      "step": 24
+    },
+    {
+      "epoch": 0.004565630944831959,
+      "grad_norm": 1.8657628297805786,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.266,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "grad_norm": 1.5890346765518188,
+      "learning_rate": 0.0,
+      "loss": 4.968,
+      "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": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null