Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063d193c3df2179061ec7ebbc4e7cf6b6f614dafc7d4f9b8a3f0585b06f9ac82
+oid sha256:fd024e0cd393bf4fcadf29aac216d5e5d1236638ba4f5a0fb699ba0349bf6979
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0711079114d77e0068ff3f195cdaf260f56ddf64fe6bd6d2dbe75b818fc2cd60
+oid sha256:d202601fb541ed82fcd80d39dd0ee1e3a668c0e9a75de79ec140d2837a1ae752
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d23ddc432877538e1482ac7028d4be4d6733be4d7e298176c8e6b45a4685c3
+oid sha256:4ad1deb19dfc06efe6bedbf0434079d14d5dbfdf0a49f0d422ad00ca8a5d0b31
 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": 0.0007341936576963262,
+  "epoch": 0.0014683873153926524,
   "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": 8.1,
       "eval_steps_per_second": 4.05,
       "step": 10
+    },
+    {
+      "epoch": 0.0008471465281111456,
+      "grad_norm": 22.757177352905273,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.6793,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011295287041481943,
+      "grad_norm": 14.26730728149414,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.5892,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011295287041481943,
+      "eval_loss": 1.6451387405395508,
+      "eval_runtime": 919.4827,
+      "eval_samples_per_second": 8.109,
+      "eval_steps_per_second": 4.054,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014119108801852428,
+      "grad_norm": 7.687915802001953,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.1298,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null