Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07bbd897bbde140aacddd599f09911637db46aebac7b34499bdc65e02d67f99
+oid sha256:20920ab18906b5fa73f7d3693314c5c793cdc6f413b5a29ed65223545fc9f3d4
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902197173f381c49562d5281b09067e3150f307cd6675ab3e3baf10e03090284
+oid sha256:9a3cd302c87437cb41469bea150e2f77b2cc4e815063eb4e2162ecd368806335
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e0861aebd8f70471b6ac1f8c0c2719b7ec5eff68f23ec0b15040ecc5439eef
+oid sha256:6c432173c3e03ab35f379f99e76ec96a95398876df77ad2334860facd5d9a0fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00031127597208892115,
+  "epoch": 0.0006225519441778423,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 50.347,
       "eval_steps_per_second": 25.174,
       "step": 3
+    },
+    {
+      "epoch": 0.0004150346294518949,
+      "grad_norm": 1.0456353425979614,
+      "learning_rate": 8e-05,
+      "loss": 1.9339,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005187932868148687,
+      "grad_norm": 1.2975083589553833,
+      "learning_rate": 0.0001,
+      "loss": 2.0544,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006225519441778423,
+      "grad_norm": 1.0521240234375,
+      "learning_rate": 0.00012,
+      "loss": 2.1387,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006225519441778423,
+      "eval_loss": 2.0402276515960693,
+      "eval_runtime": 80.8247,
+      "eval_samples_per_second": 50.207,
+      "eval_steps_per_second": 25.104,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 33389311426560.0,
+  "total_flos": 71230531043328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null