Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7059756bfeede504d28706991204da1f13ee0ef04ab6f49b39d02176b7974e0b
+oid sha256:02b53164836d05f641d757086fd84b35a896b3fab683ed37c0921bc168b77e68
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d83a9051e0ccaf58d0a5fa1f0d8d9cbd5bdc50eba3b7fa82f0a2da7d928e34
+oid sha256:8777f4b6293e3c86024b506390458c658174076b1804b6e8790f83808a1e420b
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e3c19f7b2892f9204c2db9ed620b572aab049411a4232f39c90287c803cca
+oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35459df988092e3ff9e3c1b91118d006576bed7e1956fe6101d7671fcd8c5396
+oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.036325532658050996,
+  "epoch": 0.07265106531610199,
   "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": 11.344,
       "eval_steps_per_second": 2.837,
       "step": 13
+    },
+    {
+      "epoch": 0.039119804400977995,
+      "grad_norm": 28.11492347717285,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 35.8233,
+      "step": 14
+    },
+    {
+      "epoch": 0.041914076143904994,
+      "grad_norm": 19.98900604248047,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 31.6706,
+      "step": 15
+    },
+    {
+      "epoch": 0.04470834788683199,
+      "grad_norm": 24.489959716796875,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 35.4651,
+      "step": 16
+    },
+    {
+      "epoch": 0.04750261962975899,
+      "grad_norm": 25.26296615600586,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 34.7415,
+      "step": 17
+    },
+    {
+      "epoch": 0.050296891372685996,
+      "grad_norm": 22.68831443786621,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 34.8815,
+      "step": 18
+    },
+    {
+      "epoch": 0.053091163115612995,
+      "grad_norm": 23.189281463623047,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 32.5742,
+      "step": 19
+    },
+    {
+      "epoch": 0.055885434858539994,
+      "grad_norm": 21.66847038269043,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 34.393,
+      "step": 20
+    },
+    {
+      "epoch": 0.05867970660146699,
+      "grad_norm": 21.759904861450195,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 35.1236,
+      "step": 21
+    },
+    {
+      "epoch": 0.06147397834439399,
+      "grad_norm": 24.153629302978516,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 34.0533,
+      "step": 22
+    },
+    {
+      "epoch": 0.064268250087321,
+      "grad_norm": 20.246461868286133,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 33.2113,
+      "step": 23
+    },
+    {
+      "epoch": 0.067062521830248,
+      "grad_norm": 24.22486114501953,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 31.9,
+      "step": 24
+    },
+    {
+      "epoch": 0.069856793573175,
+      "grad_norm": 20.538053512573242,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 34.0572,
+      "step": 25
+    },
+    {
+      "epoch": 0.07265106531610199,
+      "grad_norm": 21.71095848083496,
+      "learning_rate": 5e-05,
+      "loss": 31.9274,
+      "step": 26
+    },
+    {
+      "epoch": 0.07265106531610199,
+      "eval_loss": 1.0352919101715088,
+      "eval_runtime": 216.7154,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 2.782,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.925072315706245e+17,
+  "total_flos": 5.85014463141249e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null