Training in progress, epoch 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2ba822e752360bf57d581bdacae57f5f0ff5378731ad13da25390c55491a0b
+oid sha256:295e227f4e998576f2a46404ae9d148fa1bb1493bdc88784d107d552dda3652e
 size 218121344

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984b9b4320e3717a03a7acf569f155d3f3aca5b979bee6186150c4bdbc13bee5
+oid sha256:455000c25f92a494a25f90dc3bd7687b765861d9cec6e730d66f542d1c742e67
 size 109417018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af54e31c2af0df42e8dc59bd419d564e4a294d0e446d4524867f21f1c2327e5
+oid sha256:eda51522553149ac7f04823b2f24de1e4a29a13d19516c47586480c30dd68505
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97f1850100bfea8885c77fef8794528951b95c13de7201bc8afc00a3283c4c8
+oid sha256:030c8ec491c7b3efa0e75662d44f44352cd1301e27125b1e92d52f65f4a03185
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.0,
+  "epoch": 18.0,
   "eval_steps": 500,
-  "global_step": 25959,
+  "global_step": 27486,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1820,6 +1820,111 @@
       "learning_rate": 3.0892143808255656e-05,
       "loss": 0.1191,
       "step": 25900
+    },
+    {
+      "epoch": 17.026850032743944,
+      "grad_norm": 0.23988807201385498,
+      "learning_rate": 3.0226364846870843e-05,
+      "loss": 0.1123,
+      "step": 26000
+    },
+    {
+      "epoch": 17.092337917485267,
+      "grad_norm": 0.4619341790676117,
+      "learning_rate": 2.956058588548602e-05,
+      "loss": 0.1074,
+      "step": 26100
+    },
+    {
+      "epoch": 17.157825802226586,
+      "grad_norm": 0.42623019218444824,
+      "learning_rate": 2.88948069241012e-05,
+      "loss": 0.1035,
+      "step": 26200
+    },
+    {
+      "epoch": 17.22331368696791,
+      "grad_norm": 0.42678698897361755,
+      "learning_rate": 2.822902796271638e-05,
+      "loss": 0.1062,
+      "step": 26300
+    },
+    {
+      "epoch": 17.288801571709232,
+      "grad_norm": 0.18482163548469543,
+      "learning_rate": 2.756324900133156e-05,
+      "loss": 0.1105,
+      "step": 26400
+    },
+    {
+      "epoch": 17.354289456450555,
+      "grad_norm": 0.2510315179824829,
+      "learning_rate": 2.6897470039946737e-05,
+      "loss": 0.1113,
+      "step": 26500
+    },
+    {
+      "epoch": 17.419777341191878,
+      "grad_norm": 0.5647396445274353,
+      "learning_rate": 2.623169107856192e-05,
+      "loss": 0.1051,
+      "step": 26600
+    },
+    {
+      "epoch": 17.4852652259332,
+      "grad_norm": 0.6214593052864075,
+      "learning_rate": 2.55659121171771e-05,
+      "loss": 0.1108,
+      "step": 26700
+    },
+    {
+      "epoch": 17.550753110674524,
+      "grad_norm": 0.5379447937011719,
+      "learning_rate": 2.4900133155792276e-05,
+      "loss": 0.1137,
+      "step": 26800
+    },
+    {
+      "epoch": 17.616240995415847,
+      "grad_norm": 0.19992570579051971,
+      "learning_rate": 2.423435419440746e-05,
+      "loss": 0.1132,
+      "step": 26900
+    },
+    {
+      "epoch": 17.68172888015717,
+      "grad_norm": 0.24671415984630585,
+      "learning_rate": 2.3568575233022638e-05,
+      "loss": 0.1055,
+      "step": 27000
+    },
+    {
+      "epoch": 17.747216764898493,
+      "grad_norm": 0.2775340676307678,
+      "learning_rate": 2.2902796271637818e-05,
+      "loss": 0.1124,
+      "step": 27100
+    },
+    {
+      "epoch": 17.812704649639816,
+      "grad_norm": 0.4474336504936218,
+      "learning_rate": 2.2237017310252997e-05,
+      "loss": 0.1071,
+      "step": 27200
+    },
+    {
+      "epoch": 17.87819253438114,
+      "grad_norm": 0.4721475839614868,
+      "learning_rate": 2.1571238348868177e-05,
+      "loss": 0.11,
+      "step": 27300
+    },
+    {
+      "epoch": 17.94368041912246,
+      "grad_norm": 0.35053202509880066,
+      "learning_rate": 2.0905459387483356e-05,
+      "loss": 0.109,
+      "step": 27400
     }
   ],
   "logging_steps": 100,
@@ -1839,7 +1944,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.773467063287808e+16,
+  "total_flos": 1.0348376881627136e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null