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:d25bf26788c3ba171d8211d066f734206cd2d661ac2be329bce9e48241133891
+oid sha256:24857cf0c8edaa59c8dfe422e71ac9c0ba62e19c0a47e15bbbe509803105f964
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720d0e33f13a3597a8bdb9c55279bf0d722a538dfb559bb3f3002959fb0f8042
+oid sha256:dd7cec636a5c9f4a170b1b8695c3fdf4ed84ec297eb38a4595c7d3f9ede13de0
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491662e8f35f09eb653f00811e1da59294f0d74199187a5660ef5da1adec39c0
+oid sha256:33b18bb018d6f0723e725784b3dab518122397063a13aa6bbd1ff4e3d8e34477
 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": 0.007909827961241843,
+  "epoch": 0.015819655922483685,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 5.526,
       "eval_steps_per_second": 2.768,
       "step": 10
+    },
+    {
+      "epoch": 0.009491793553490212,
+      "grad_norm": 0.9624531865119934,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.9168,
+      "step": 12
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 1.5339550971984863,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.8234,
+      "step": 15
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "eval_loss": 2.461575508117676,
+      "eval_runtime": 96.3641,
+      "eval_samples_per_second": 5.531,
+      "eval_steps_per_second": 2.771,
+      "step": 15
+    },
+    {
+      "epoch": 0.014237690330235317,
+      "grad_norm": 1.5237758159637451,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.411,
+      "step": 18
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "eval_loss": 2.0676076412200928,
+      "eval_runtime": 96.4467,
+      "eval_samples_per_second": 5.526,
+      "eval_steps_per_second": 2.768,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1646346004070400.0,
+  "total_flos": 3292692008140800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null