Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09fffe8fae8950f4496f6a2aee71c7105ced7d76955e83714e9b16e33f79b722
+oid sha256:9301125f1d936d792834b6f3b7dd68274f67f2991fef52d5090e7141b5981bca
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a9bb092b6ff38142e49693a566468722edc02c64e1fd4baba1995381d1eb15
+oid sha256:de3d0ee449148724e442012f1a6031a865363101af76f0bdb53394451312564c
 size 37965300

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": 0.01869431867971374,
+  "epoch": 0.03738863735942748,
   "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": 16.322,
       "eval_steps_per_second": 8.172,
       "step": 8
+    },
+    {
+      "epoch": 0.02103110851467796,
+      "grad_norm": 0.6885388493537903,
+      "learning_rate": 9e-05,
+      "loss": 2.4027,
+      "step": 9
+    },
+    {
+      "epoch": 0.023367898349642178,
+      "grad_norm": 0.5526238083839417,
+      "learning_rate": 0.0001,
+      "loss": 1.8518,
+      "step": 10
+    },
+    {
+      "epoch": 0.025704688184606396,
+      "grad_norm": 1.0618926286697388,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 2.0879,
+      "step": 11
+    },
+    {
+      "epoch": 0.028041478019570614,
+      "grad_norm": 0.857267439365387,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.8582,
+      "step": 12
+    },
+    {
+      "epoch": 0.030378267854534832,
+      "grad_norm": 0.7300710082054138,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.7029,
+      "step": 13
+    },
+    {
+      "epoch": 0.032715057689499054,
+      "grad_norm": 0.8072000741958618,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.1175,
+      "step": 14
+    },
+    {
+      "epoch": 0.03505184752446327,
+      "grad_norm": 0.7812466621398926,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.4707,
+      "step": 15
+    },
+    {
+      "epoch": 0.03738863735942748,
+      "grad_norm": 1.0912774801254272,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.6905,
+      "step": 16
+    },
+    {
+      "epoch": 0.03738863735942748,
+      "eval_loss": 2.0501091480255127,
+      "eval_runtime": 44.2225,
+      "eval_samples_per_second": 16.304,
+      "eval_steps_per_second": 8.163,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8360120555667456.0,
+  "total_flos": 1.6720241111334912e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null