Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3986eeb5b19540ff3dad2d0e0d0680923917950d7620e355d58820aa9eb90a19
+oid sha256:980962321338eea91f3798b04c8d650505899fb5dfb27c8a722af3fbd631d2bd
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e87ebb496e0aec9354f49dea5efdad550e7b04728fe81377af53598826dc048
+oid sha256:01cdb925a3da299d05437cd36885e59d722e0a1c7d2bef203acf45714a11747c
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd0578355732197feccd0c4f23089b2634afe4910e80d28b8e06384faec8405
+oid sha256:e36fe9682fcfd251b6be642f1735ce4ef89b9ec6f7db76a985a41c7646af286a
 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": 0.00035601969975671986,
+  "epoch": 0.0007120393995134397,
   "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": 0.7708,
       "step": 9
+    },
+    {
+      "epoch": 0.0004272236397080638,
+      "grad_norm": 0.5753574371337891,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6591,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005340295496350798,
+      "grad_norm": 0.5155614614486694,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.633,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005696315196107518,
+      "eval_loss": 0.6322805285453796,
+      "eval_runtime": 991.9994,
+      "eval_samples_per_second": 17.883,
+      "eval_steps_per_second": 8.942,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006408354595620958,
+      "grad_norm": 0.4879243075847626,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6155,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1558212350312448.0,
+  "total_flos": 3141557157888000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null