Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a966cf10c84aa4a7e80b0775b6cdc149da8909cd9f44cf54ace1ef0c8e41bfb
+oid sha256:fc2ff3e07a55039bf491ac6d11c571b9f8580e7f7c90e71425bac40d3c935abe
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f429d7faddde2086f1ae058ab3059a0f5dfdd208b3984bf077faefd14482f7b8
+oid sha256:592959534e61fa6899a83b12046d6eec2d5d1cd67dfa8eafc07da0a30d6fb876
 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": 0.0005693950177935943,
+  "epoch": 0.0011387900355871886,
   "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": 7.995,
       "eval_steps_per_second": 3.998,
       "step": 10
+    },
+    {
+      "epoch": 0.0006569942513003011,
+      "grad_norm": 0.32256799936294556,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.3154,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008759923350670682,
+      "grad_norm": 0.2605501413345337,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2963,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008759923350670682,
+      "eval_loss": 0.2871706783771515,
+      "eval_runtime": 1205.8712,
+      "eval_samples_per_second": 7.973,
+      "eval_steps_per_second": 3.986,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010949904188338351,
+      "grad_norm": 0.24902136623859406,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.248,
+      "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