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:ea6bdd512b452453660585d30153162352467b53d2e6261384fe01df7cbd1850
+oid sha256:3bc9850308d17106843bd00f406fc21810abd1e5cad894893a4b00b7dbe1fc69
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f671a9c6178272d0c5fbebd114ee9501977e17a80ed1a6f89d3e9b3ef6cfab12
+oid sha256:9de03504bc28b265e80f7b3ff8e9ea668b18cc527b33bfa2733b6a290676f067
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac1dc3983b561a2e67713344020212ad2d548b0aadea565dfabe85aaba31313
+oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
 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": 0.0019086070838685997,
+  "epoch": 0.0038172141677371993,
   "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": 28.083,
       "eval_steps_per_second": 14.042,
       "step": 10
+    },
+    {
+      "epoch": 0.0022022389429253073,
+      "grad_norm": 1.071268081665039,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.8653,
+      "step": 15
+    },
+    {
+      "epoch": 0.0029363185905670764,
+      "grad_norm": 1.1812461614608765,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.9802,
+      "step": 20
+    },
+    {
+      "epoch": 0.0029363185905670764,
+      "eval_loss": 2.9501028060913086,
+      "eval_runtime": 102.1663,
+      "eval_samples_per_second": 28.072,
+      "eval_steps_per_second": 14.036,
+      "step": 20
+    },
+    {
+      "epoch": 0.0036703982382088455,
+      "grad_norm": 1.3783600330352783,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.7701,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 171398465323008.0,
+  "total_flos": 329441206075392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null