Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1875a1e1a0231a5d66224e761b7b5512717d15617f1545eac2af583852f74bdd
+oid sha256:3b85de12dc040b82cf018f2545bfc0787659228ba1cf3d255386cbaa8bf1f5ff
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8298ee01f6509009e8436e1c83527fe8cd81469ba8f6a80488cd8ebfd83a53f0
+oid sha256:5af6f631bf46131cea0edeae1d8c290d0e10226447d28b0fbb23359157dc93bc
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4f58d5f408c6018d9f8191cde9d7af64c8ada1d418fb9f6236d2673d276140
+oid sha256:8f2ab6814d2865483c1c38900809f8c2d9a70be01e4df08ef1f4b5a2c937cb23
 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": 0.004427415921668796,
+  "epoch": 0.008854831843337591,
   "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": 12.392,
       "eval_steps_per_second": 6.201,
       "step": 10
+    },
+    {
+      "epoch": 0.005108556832694764,
+      "grad_norm": 0.6932932138442993,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.1643,
+      "step": 15
+    },
+    {
+      "epoch": 0.006811409110259685,
+      "grad_norm": 0.40464410185813904,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.9458,
+      "step": 20
+    },
+    {
+      "epoch": 0.006811409110259685,
+      "eval_loss": 1.4234973192214966,
+      "eval_runtime": 99.937,
+      "eval_samples_per_second": 12.378,
+      "eval_steps_per_second": 6.194,
+      "step": 20
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "grad_norm": 0.7656698226928711,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7984,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2966081262059520.0,
+  "total_flos": 6220531535708160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null