Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbcfe453ae59ac86d2a90b3ebc6dabc4ad467b0068549383e4e8e2e6ad3e0f4
+oid sha256:e51db082527ba66bfb35b56b5ac8909224d533fa06789b243beaec2416ac1cca
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2507cbc50417d4ad67eefc38bf094a6fc564052db93b1f9610efe665905bae90
+oid sha256:79b842484f37cae4066c7702ac9e1baebb025305a46194f91bde657ae5765940
 size 335922386

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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027434842249657063,
+  "epoch": 0.05486968449931413,
   "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": 0.00018,
       "loss": 0.3779,
       "step": 9
+    },
+    {
+      "epoch": 0.03292181069958848,
+      "grad_norm": 1.0906153917312622,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.1599,
+      "step": 12
+    },
+    {
+      "epoch": 0.0411522633744856,
+      "grad_norm": 1.4689967632293701,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.1314,
+      "step": 15
+    },
+    {
+      "epoch": 0.0438957475994513,
+      "eval_loss": 0.175197035074234,
+      "eval_runtime": 19.8746,
+      "eval_samples_per_second": 7.749,
+      "eval_steps_per_second": 3.874,
+      "step": 16
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 1.8150358200073242,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.1141,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null