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:d55d919998e9d9c8c1709ae74113a59d5f533fe535dea5d1405489cfb4389f40
+oid sha256:9a63578432feeaae56e403d7c51f166c4ca29cf0f96171b1fb748b372e4f6324
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b608e31946c78a5702f0f002760931d4716fa529bfda13e3f704ae723c2c05d
+oid sha256:57af1a81090e3ef24500f9aca4e1d26c4133d992e4fecd1c6ce7f7741803dc38
 size 320194002

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": 0.008592910848549946,
+  "epoch": 0.017185821697099892,
   "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": 2.3687,
       "step": 9
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 0.5758622288703918,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.1657,
+      "step": 12
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 0.5426364541053772,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.3004,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "eval_loss": 2.197101593017578,
+      "eval_runtime": 58.59,
+      "eval_samples_per_second": 8.363,
+      "eval_steps_per_second": 4.182,
+      "step": 16
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.6157383322715759,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.209,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267291009515520.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null