Training in progress, step 22, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0d34daa653cc4bbf179297ff452cf8497dd860a87d859ceaa58cbd5f9b91fb
+oid sha256:c9d4e4abf2aca225dbc82bbe4834a3cfd41d268fe73f137b810fd7be7ff04b40
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a63875dc55d86a3c4c111467e1aa918a8dde4f6319abb10d2aaae6375a00fc
+oid sha256:e660d6b7bd584cd4268f3829b97f79b9e6d43de012dbd48dc62bfbb7c516c9ef
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b534877ba1f0b48dec1fc63df154003dca34fc8076dd09eab46f1a2c707f9a
+oid sha256:701fccec381f2498ceeea2bd3e9b562a216ce20d81b47c360654e2466c05612f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bfa0bb279f2101788d08b0135f42a939bc4867be11fd447a266649f4c2aa9b2
+oid sha256:3d9d76acc0f7ff5f02f45dbdf1e293d52c5b3bc9838ed623c7f1b8796ab90aaa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25958702064896755,
+  "epoch": 0.5191740412979351,
   "eval_steps": 9,
-  "global_step": 11,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "learning_rate": 9.089646803833589e-05,
       "loss": 179.1345,
       "step": 10
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "eval_loss": 11.090907096862793,
+      "eval_runtime": 0.9027,
+      "eval_samples_per_second": 316.838,
+      "eval_steps_per_second": 39.882,
+      "step": 18
+    },
+    {
+      "epoch": 0.471976401179941,
+      "grad_norm": 17.81786346435547,
+      "learning_rate": 5.951955545823342e-05,
+      "loss": 177.9139,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3394970320896.0,
+  "total_flos": 6789940641792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null