Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4465989d6b7c811ef2c3517010e3ff250cdf63de512bfe49eb958ee717229d61
+oid sha256:b8219bf80ba13decae5e08235ea4784bb4bc37080b7680e90c515ffacf7e092a
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053f081ad9b7705387563322017e169eba99a9d0e4d99bf251ac5484b5d91699
+oid sha256:a65f7751332d556bcb67779dbffc71f81bca7402b299c492db83999ac8e1561f
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 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": 0.02619647355163728,
+  "epoch": 0.05239294710327456,
   "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": 72.232,
       "eval_steps_per_second": 36.289,
       "step": 10
+    },
+    {
+      "epoch": 0.030226700251889168,
+      "grad_norm": 0.01207203883677721,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.9282,
+      "step": 15
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "grad_norm": 0.006873443257063627,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9286,
+      "step": 20
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "eval_loss": 11.92874813079834,
+      "eval_runtime": 2.9679,
+      "eval_samples_per_second": 70.421,
+      "eval_steps_per_second": 35.379,
+      "step": 20
+    },
+    {
+      "epoch": 0.05037783375314862,
+      "grad_norm": 0.007669125683605671,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.9293,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2954035200.0,
+  "total_flos": 5848989696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null