Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fe2ae351a26428956ad8197aad5f7770937aa85743f87836e1b63483e09a97
+oid sha256:3c3f6ad851b3c4195818f60c81424d18340984ac6a7bbf4d8f6eb6977ed7adb9
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c496a8f5da9338b868753d4540661ed4db526043d0743bf915375d13b7bccca
+oid sha256:d9ae7d1c1f1369f8a786a8da4197cc465369b65469d364c1d69f57eaa9c6a0a4
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02778d82e51b54b5f033cecc109c4bb6bbe105f986998706dc99ddcab7146d99
+oid sha256:61630a9df826f43c43e9d9f3f658b33939478e91788026e7879f5a1c25f3bc5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26666666666666666,
+  "epoch": 0.5333333333333333,
   "eval_steps": 4,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "learning_rate": 5e-05,
       "loss": 7.5589,
       "step": 5
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_loss": 5.408405303955078,
+      "eval_runtime": 0.3751,
+      "eval_samples_per_second": 21.325,
+      "eval_steps_per_second": 10.663,
+      "step": 8
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 21.95160675048828,
+      "learning_rate": 0.0001,
+      "loss": 6.183,
+      "step": 10
     }
   ],
   "logging_steps": 5,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162149129256960.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null