Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6314a5cb0f4718027886d05b0a19087b2ecf53b4b085f7d375f42ecade679a25
+oid sha256:b9384b0c003008c18564efaf8289f01d14db89bb5c20b5f8820deed7e05b464e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c5680eb551217c18c8e47c95e590d34220b8841d6b77216f65bb1eab8f6f06
+oid sha256:1c91889ae4f7129c68b11b8ddc1a112a23fd732243a74cd14b3edaeeaad07b65
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025412960609911054,
+  "epoch": 0.05082592121982211,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 5.1815,
       "step": 9
+    },
+    {
+      "epoch": 0.030495552731893267,
+      "grad_norm": 1.0094770193099976,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.1039,
+      "step": 12
+    },
+    {
+      "epoch": 0.03811944091486658,
+      "grad_norm": 0.7473834753036499,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.0451,
+      "step": 15
+    },
+    {
+      "epoch": 0.04066073697585769,
+      "eval_loss": 4.955931663513184,
+      "eval_runtime": 14.087,
+      "eval_samples_per_second": 11.784,
+      "eval_steps_per_second": 5.892,
+      "step": 16
+    },
+    {
+      "epoch": 0.045743329097839895,
+      "grad_norm": 0.9738025665283203,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.8306,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709500842311680.0,
+  "total_flos": 7419001684623360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null