Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884bedbae1a91614009bbf344cf6b55e2be6e5bc6ed78b977df7fa55fb56eeee
+oid sha256:3ca9de97e186b636a7aab469ea42cc3299e04e2cd7b95b7e090cbe514aa78ff5
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7567215f964d0f2d9b63bc7e69c29357b8fc81b3123be1599921529d5023211f
+oid sha256:fcd4e635c95b672009a050d508c24fe72980ea6982467d3d0fabd2dc3118c038
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8c6fc31ac199e6c243ffe062905a7862052130540b4f8afa1589a29fe97b6d
+oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
 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": 0.004590314436538903,
+  "epoch": 0.009180628873077806,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 340.923,
       "eval_steps_per_second": 170.461,
       "step": 10
+    },
+    {
+      "epoch": 0.005508377323846684,
+      "grad_norm": 1.4708709716796875,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 44.2587,
+      "step": 12
+    },
+    {
+      "epoch": 0.006885471654808354,
+      "grad_norm": 1.4738435745239258,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 44.2408,
+      "step": 15
+    },
+    {
+      "epoch": 0.006885471654808354,
+      "eval_loss": 11.058080673217773,
+      "eval_runtime": 2.7188,
+      "eval_samples_per_second": 337.648,
+      "eval_steps_per_second": 168.824,
+      "step": 15
+    },
+    {
+      "epoch": 0.008262565985770026,
+      "grad_norm": 1.3765307664871216,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.2229,
+      "step": 18
+    },
+    {
+      "epoch": 0.009180628873077806,
+      "eval_loss": 11.050945281982422,
+      "eval_runtime": 2.5585,
+      "eval_samples_per_second": 358.808,
+      "eval_steps_per_second": 179.404,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 18717081600.0,
+  "total_flos": 37434163200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null