Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d8994feff4cbc7060da87779735a6aeba4788d92e28d0cea8977b9b5a33524
+oid sha256:7dfdf52e93d9a9dd45b882c99909704770c97c852a3e2e34fac8b9df61f312a2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003c768d239619ab2aa3e7e15c696fcce7fbd4b6e465e53738ae83157cf47d13
+oid sha256:f84ec4058968595761a54b4f9faafce1b74181be53dce64c59955af862b8257c
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
+oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028399781540142,
+  "epoch": 0.056799563080284,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 12.867,
       "eval_steps_per_second": 6.467,
       "step": 10
+    },
+    {
+      "epoch": 0.03276897870016385,
+      "grad_norm": 16.86937713623047,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1047,
+      "step": 15
+    },
+    {
+      "epoch": 0.04369197160021846,
+      "grad_norm": 8.117836952209473,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0811,
+      "step": 20
+    },
+    {
+      "epoch": 0.04369197160021846,
+      "eval_loss": 0.9471554160118103,
+      "eval_runtime": 15.0355,
+      "eval_samples_per_second": 12.836,
+      "eval_steps_per_second": 6.451,
+      "step": 20
+    },
+    {
+      "epoch": 0.054614964500273075,
+      "grad_norm": 12.76759147644043,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9381,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null