Training in progress, step 217, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53edbf1c300db97f7cf757d113c0f32b09d47e4c871522e2a7fdffb0b7294fa5
+oid sha256:4a069365120e85adb14a02be1d6d1bcb7f57bd56552e43dae1279161a73ba747
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77201b64afa737acfe0f1a12b83c348c32769eda957cf5d48833dae0c011405
+oid sha256:038ad53f8bbc1f098ba079bddbf6a3f8098ff367610e685c65b90cc790e33514
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7954fa5892170562c4c3a384fdeff71992c4c66cf9afa61a87dcba009edcf0
+oid sha256:8da25d38ebcf1dfe8351fa92f64b9a44da3c87afd204df29f93fba4ad49762fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a7e20609bcc2282e67bffd32305d513fe0d2d1256b3de4e851bbc232952907
+oid sha256:a89729c98649b6d89eebc77276357ac5f2594b10fb1a49cf61a28a5fa2b4c3d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5091277890466532,
+  "epoch": 1.7606490872210954,
   "eval_steps": 31,
-  "global_step": 186,
+  "global_step": 217,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,84 @@
       "eval_samples_per_second": 15.494,
       "eval_steps_per_second": 1.937,
       "step": 186
+    },
+    {
+      "epoch": 1.5334685598377282,
+      "grad_norm": 15.1577730178833,
+      "learning_rate": 5.04363267749187e-05,
+      "loss": 1.6155,
+      "step": 189
+    },
+    {
+      "epoch": 1.5578093306288032,
+      "grad_norm": 4.470703125,
+      "learning_rate": 4.912737967813583e-05,
+      "loss": 1.6756,
+      "step": 192
+    },
+    {
+      "epoch": 1.5821501014198782,
+      "grad_norm": 5.094776630401611,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.5824,
+      "step": 195
+    },
+    {
+      "epoch": 1.6064908722109532,
+      "grad_norm": 3.8165762424468994,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.5824,
+      "step": 198
+    },
+    {
+      "epoch": 1.6308316430020284,
+      "grad_norm": 5.532138347625732,
+      "learning_rate": 4.52077123739888e-05,
+      "loss": 1.744,
+      "step": 201
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 4.430169582366943,
+      "learning_rate": 4.390653282974264e-05,
+      "loss": 1.6626,
+      "step": 204
+    },
+    {
+      "epoch": 1.6795131845841786,
+      "grad_norm": 3.9386327266693115,
+      "learning_rate": 4.260952944351947e-05,
+      "loss": 1.4812,
+      "step": 207
+    },
+    {
+      "epoch": 1.7038539553752536,
+      "grad_norm": 4.511838436126709,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7028,
+      "step": 210
+    },
+    {
+      "epoch": 1.7281947261663286,
+      "grad_norm": 4.205485820770264,
+      "learning_rate": 4.003160327914015e-05,
+      "loss": 1.761,
+      "step": 213
+    },
+    {
+      "epoch": 1.7525354969574036,
+      "grad_norm": 4.336887836456299,
+      "learning_rate": 3.875244728280676e-05,
+      "loss": 1.5719,
+      "step": 216
+    },
+    {
+      "epoch": 1.7606490872210954,
+      "eval_loss": 0.49112430214881897,
+      "eval_runtime": 13.4322,
+      "eval_samples_per_second": 15.485,
+      "eval_steps_per_second": 1.936,
+      "step": 217
     }
   ],
   "logging_steps": 3,
@@ -516,7 +594,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4718116806197248e+17,
+  "total_flos": 2.884265370640712e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null