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:a6479a61f78cbbb71b37baff6f524a2948b34aba06429ee80f6006fdd8191a47
+oid sha256:baaaa5f8fc5fb86c2a0355f35ded415535e9465522bcde9b32b470ad787b9fb4
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080422a2b9662b62c681d0fb4c5c530cf957b3b60f4859e7d75bc06bec002862
+oid sha256:d1a13bade6aa84cd22229c27985a95607536c889bb393661c28a8e128fb88ff3
 size 25784826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4105db75dc6a75e46fcdb66ea6bc0fb1b54935802136f485ae6ccfb2b46e435e
+oid sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
 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": 0.003631601920558708,
+  "epoch": 0.007263203841117416,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 6.784,
       "eval_steps_per_second": 3.393,
       "step": 13
+    },
+    {
+      "epoch": 0.003910955914447839,
+      "grad_norm": 8.404040336608887,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 18.8438,
+      "step": 14
+    },
+    {
+      "epoch": 0.0041903099083369704,
+      "grad_norm": 23.96065902709961,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 21.5391,
+      "step": 15
+    },
+    {
+      "epoch": 0.0044696639022261024,
+      "grad_norm": 8.518821716308594,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 17.5547,
+      "step": 16
+    },
+    {
+      "epoch": 0.004749017896115234,
+      "grad_norm": 9.683491706848145,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 18.3867,
+      "step": 17
+    },
+    {
+      "epoch": 0.005028371890004365,
+      "grad_norm": 12.909642219543457,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 20.334,
+      "step": 18
+    },
+    {
+      "epoch": 0.005307725883893497,
+      "grad_norm": 6.089707851409912,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 18.9375,
+      "step": 19
+    },
+    {
+      "epoch": 0.005587079877782628,
+      "grad_norm": 8.212544441223145,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 19.8164,
+      "step": 20
+    },
+    {
+      "epoch": 0.005866433871671759,
+      "grad_norm": 8.69490909576416,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 19.0977,
+      "step": 21
+    },
+    {
+      "epoch": 0.00614578786556089,
+      "grad_norm": 6.588229179382324,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 18.7383,
+      "step": 22
+    },
+    {
+      "epoch": 0.006425141859450022,
+      "grad_norm": 6.510587215423584,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 19.0391,
+      "step": 23
+    },
+    {
+      "epoch": 0.006704495853339153,
+      "grad_norm": 10.146479606628418,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 20.457,
+      "step": 24
+    },
+    {
+      "epoch": 0.006983849847228284,
+      "grad_norm": 6.790075302124023,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 19.5586,
+      "step": 25
+    },
+    {
+      "epoch": 0.007263203841117416,
+      "grad_norm": 6.229572296142578,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 19.375,
+      "step": 26
+    },
+    {
+      "epoch": 0.007263203841117416,
+      "eval_loss": 1.168168306350708,
+      "eval_runtime": 888.7918,
+      "eval_samples_per_second": 6.783,
+      "eval_steps_per_second": 3.392,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3385287656800256e+16,
+  "total_flos": 2.647045675627315e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null