Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f764b2d6dc09e96ec603b4f50cb1bf9427eb992c3ca7fac302a76ae49945ac
+oid sha256:69af10d130d9d9984eb5e4b353201f99e39a67aa1671a0a85777503fc38217a8
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5a772486f9b81fdcb396a8a803f575345256ca1b71681aec32b4fa8b969383
+oid sha256:eb610c61361b2687d0600b86bd4bf6b08886b63d5f841083cf3aca9031c8ae49
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9c01bb08fabdb4105f03cc42a9544dca7c722b687afb8cabdeaf14862f778a
+oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006936416184971098,
+  "epoch": 0.010404624277456647,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 21.506,
       "eval_steps_per_second": 10.783,
       "step": 6
+    },
+    {
+      "epoch": 0.008092485549132947,
+      "grad_norm": 7.412410736083984,
+      "learning_rate": 0.00014,
+      "loss": 4.4387,
+      "step": 7
+    },
+    {
+      "epoch": 0.009248554913294798,
+      "grad_norm": 7.8807220458984375,
+      "learning_rate": 0.00016,
+      "loss": 4.8257,
+      "step": 8
+    },
+    {
+      "epoch": 0.010404624277456647,
+      "grad_norm": 15.530240058898926,
+      "learning_rate": 0.00018,
+      "loss": 5.0285,
+      "step": 9
+    },
+    {
+      "epoch": 0.010404624277456647,
+      "eval_loss": 4.390628337860107,
+      "eval_runtime": 16.7613,
+      "eval_samples_per_second": 21.776,
+      "eval_steps_per_second": 10.918,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53422898282496.0,
+  "total_flos": 80134347423744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null