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:f3fe8d2d252bcb7825648c599d9c2cf4a14e9f23980cfd2ce035d405347d5fc6
+oid sha256:c5dd7277a03b1dde412da1312fa81a008520731bdee539a1466671803d6b1bac
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc181ef29b270906a69e2b6578d2b9c825f7218325796535bf3a5d4986babd10
+oid sha256:20d10b4dca925886c89aac3606f62530fdd86a3f94d00dcc68368a807ab70d35
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a85d4d74a92d9100cfbb70681d5fdf5283462de79b77166854c267737fd306c9
+oid sha256:3a07c66a8bbda035c71637231362589b93f6d10c6d5ad4f8f3c1facfda53ac13
 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": 0.0005141828777101723,
+  "epoch": 0.0010283657554203446,
   "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": 15.362,
       "eval_steps_per_second": 7.684,
       "step": 3
+    },
+    {
+      "epoch": 0.0006855771702802296,
+      "grad_norm": 0.5301584601402283,
+      "learning_rate": 8e-05,
+      "loss": 4.1981,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008569714628502871,
+      "grad_norm": 0.9308584928512573,
+      "learning_rate": 0.0001,
+      "loss": 4.4825,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010283657554203446,
+      "grad_norm": 0.6746999621391296,
+      "learning_rate": 0.00012,
+      "loss": 4.6614,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010283657554203446,
+      "eval_loss": 1.2453702688217163,
+      "eval_runtime": 159.9636,
+      "eval_samples_per_second": 15.36,
+      "eval_steps_per_second": 7.683,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1274012762112000.0,
+  "total_flos": 2632959708364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null