Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214b94649ff2ced36793acbca6ed4fe167f7be1d1536100c8905969c296cf62c
+oid sha256:5d349ce962d07d63fd419a1d0d3a9a4b343f8322dfeb153c6c47b771050f025e
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363d19baeb208a5659c6a7642f5c256da96a8492abf8f5a429782c09ad73885d
+oid sha256:006b2a45f69345baf7dba60090536847d80a4c3a920cbaa974df732008239db1
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba60c260384233e5cb0e7bbfabb0bd75f441fc8b78b5fed933e9ca48341a17ab
+oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018298261665141813,
+  "epoch": 0.036596523330283626,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 2.2091,
       "step": 9
+    },
+    {
+      "epoch": 0.021957913998170174,
+      "grad_norm": 1.420807957649231,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.0462,
+      "step": 12
+    },
+    {
+      "epoch": 0.027447392497712716,
+      "grad_norm": 1.335792064666748,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.234,
+      "step": 15
+    },
+    {
+      "epoch": 0.0292772186642269,
+      "eval_loss": 2.0752601623535156,
+      "eval_runtime": 32.8407,
+      "eval_samples_per_second": 7.034,
+      "eval_steps_per_second": 3.532,
+      "step": 16
+    },
+    {
+      "epoch": 0.03293687099725526,
+      "grad_norm": 0.8707695603370667,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.0026,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709438431068160.0,
+  "total_flos": 7418876862136320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null