Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5eeff0a3f2e686ca9d8d42ab676758f1b8d07b69c84890406003b76fc3a7627
+oid sha256:af2997a4024dfdc97b8b4149e0db00eeccff5d122e74d84c9877509219f98af7
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e1d67018ae410f0815be5816adc69a79935c462180c5d1d8fe3c778aca571e
+oid sha256:5514aafb3c2b44765b5a4b12e85bc0743ab1397babfcf4432bcb103b76f7758e
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105f96f979368944b59d27d1e74fc1fa8227279f7d5146ad57761b7d32f1a2d9
+oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07881773399014778,
+  "epoch": 0.15763546798029557,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,70 @@
       "eval_samples_per_second": 5.85,
       "eval_steps_per_second": 2.942,
       "step": 8
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 0.4130725860595703,
+      "learning_rate": 9e-05,
+      "loss": 0.9186,
+      "step": 9
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.4786558151245117,
+      "learning_rate": 0.0001,
+      "loss": 0.6656,
+      "step": 10
+    },
+    {
+      "epoch": 0.10837438423645321,
+      "grad_norm": 0.45567965507507324,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.8369,
+      "step": 11
+    },
+    {
+      "epoch": 0.11822660098522167,
+      "grad_norm": 0.44564610719680786,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.6533,
+      "step": 12
+    },
+    {
+      "epoch": 0.12807881773399016,
+      "grad_norm": 0.4153067469596863,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.7473,
+      "step": 13
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.4901822805404663,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.42,
+      "step": 14
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 0.4641437828540802,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6957,
+      "step": 15
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "grad_norm": 0.5527058243751526,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.9599,
+      "step": 16
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "eval_loss": 0.6261801719665527,
+      "eval_runtime": 29.3343,
+      "eval_samples_per_second": 5.829,
+      "eval_steps_per_second": 2.932,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.473847637291827e+16,
+  "total_flos": 8.947695274583654e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null