Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9d2c43484e0873fd4f2c1349a06ea53b92bbc1c2958671fab5a693e4895f50
+oid sha256:64f698b979ec3451370a5f9283ff0b5ea68b9621636fc78fa82ebc2e5af1abec
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3fa4e02a5b195bcec1b1249a84d254e50cb003006f7e9f008e8d689b77db78d
+oid sha256:2d6f07645e29cbec2cd651f851595d8792aec91109d28e0c2d71e0a398437d84
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
+oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
 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": 0.004338394793926247,
+  "epoch": 0.008676789587852495,
   "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": 8.111,
       "eval_steps_per_second": 4.056,
       "step": 10
+    },
+    {
+      "epoch": 0.005005840146837978,
+      "grad_norm": 1.1968896389007568,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2625,
+      "step": 15
+    },
+    {
+      "epoch": 0.006674453529117303,
+      "grad_norm": 1.6381624937057495,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0152,
+      "step": 20
+    },
+    {
+      "epoch": 0.006674453529117303,
+      "eval_loss": 1.1381220817565918,
+      "eval_runtime": 155.4963,
+      "eval_samples_per_second": 8.116,
+      "eval_steps_per_second": 4.058,
+      "step": 20
+    },
+    {
+      "epoch": 0.00834306691139663,
+      "grad_norm": 2.598337173461914,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8971,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4808867045179392.0,
+  "total_flos": 9617734090358784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null