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:c172e63c865bb0bbd0c610d68b6a821d0a63fbdc51b20752fc36799506522b03
+oid sha256:a8d4646abd9deaabf947784d14c2a509cd03609478ec8a5c21e6acac526e9944
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15497b6ccc1f04d3826a1b323fc6e3cac20f25733722c8eccea24411f15f8105
+oid sha256:764b67931b25f8610024d8757ac09509891ea6f7166bba7adc0096acaa55e6d8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d58a77b7e7abf4f99c2b253ea7d0012eb34f29163a114391e783f09fc5bd6f
+oid sha256:9ec542b26c32a374ce73f946e51924ebdfeffaac8414b3ea2a0214b7121e428a
 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": 0.0005652542557123291,
+  "epoch": 0.0011305085114246582,
   "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": 12.38,
       "eval_steps_per_second": 6.19,
       "step": 10
+    },
+    {
+      "epoch": 0.0006522164488988412,
+      "grad_norm": 0.6922943592071533,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.3912,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008696219318651216,
+      "grad_norm": 0.5230913758277893,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3014,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008696219318651216,
+      "eval_loss": 1.3218823671340942,
+      "eval_runtime": 782.2744,
+      "eval_samples_per_second": 12.379,
+      "eval_steps_per_second": 6.19,
+      "step": 20
+    },
+    {
+      "epoch": 0.001087027414831402,
+      "grad_norm": 0.6538348197937012,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2247,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2218271705137152.0,
+  "total_flos": 4518701621575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null