Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a56b3bb97fbbf8130fca78041d9213b8f19c9b4c4bda5c8e0676b5f6084c49a
+oid sha256:be064b98d7ce84f0f87b29a8757eccb1399e97dd3a9ead375580f8385cb38ae0
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b2dd13a3198675b727210c336be6f4edc89e64fef47be25e22e587ffa315f6
+oid sha256:7dab75d1b881e4ead97c7b35c04bdfc0b13ee515650f0d93db5249be6c65f7b7
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
+oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12361178174794785,
+  "epoch": 0.18541767262192177,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 203.491,
       "eval_steps_per_second": 102.21,
       "step": 16
+    },
+    {
+      "epoch": 0.1313375181071946,
+      "grad_norm": 0.06664367020130157,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9275,
+      "step": 17
+    },
+    {
+      "epoch": 0.13906325446644133,
+      "grad_norm": 0.09336207807064056,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9289,
+      "step": 18
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 0.07334022969007492,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.9191,
+      "step": 19
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 0.054979972541332245,
+      "learning_rate": 5e-05,
+      "loss": 11.927,
+      "step": 20
+    },
+    {
+      "epoch": 0.16224046354418156,
+      "grad_norm": 0.059893086552619934,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9292,
+      "step": 21
+    },
+    {
+      "epoch": 0.1699661999034283,
+      "grad_norm": 0.062082719057798386,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9272,
+      "step": 22
+    },
+    {
+      "epoch": 0.17769193626267504,
+      "grad_norm": 0.06688153743743896,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.9169,
+      "step": 23
+    },
+    {
+      "epoch": 0.18541767262192177,
+      "grad_norm": 0.05168774351477623,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.92,
+      "step": 24
+    },
+    {
+      "epoch": 0.18541767262192177,
+      "eval_loss": 11.926448822021484,
+      "eval_runtime": 1.1157,
+      "eval_samples_per_second": 196.289,
+      "eval_steps_per_second": 98.593,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 95932121088.0,
+  "total_flos": 143898181632.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null