Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c6b2007d17f2c05a1ff04511bd6c420c2fa1d7dac0716249ba3481abf3fe1b
+oid sha256:3b9979eaa45a61fd8cebcbeaa53ecd0411b03747b0f7cb88d56f45fa404f1050
 size 3380768360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313c9668e74d9a6b584989bb8166e2be73c567a816346feb31eeb827ebe378fb
+oid sha256:33cc08aed51b001f8c2bffba8429bca64232aa72d2436c4d76f03b9157a32060
 size 1855337587

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d391cbd422024319290b62fae06f5beac24520f574ab878e69073735038bbc28
+oid sha256:7e714f56ef384df6bb4ffceaa2247da8c000483c6f7f2f5dce28e97af82a6ac6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1437699680511182,
+  "epoch": 1.4313099041533546,
   "eval_steps": 500,
-  "global_step": 210,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -309,6 +309,48 @@
       "learning_rate": 8.087098307042959e-06,
       "loss": 0.2071,
       "step": 210
+    },
+    {
+      "epoch": 1.1916932907348243,
+      "grad_norm": 0.06395677477121353,
+      "learning_rate": 7.410974280025551e-06,
+      "loss": 0.205,
+      "step": 215
+    },
+    {
+      "epoch": 1.2396166134185305,
+      "grad_norm": 0.06315111368894577,
+      "learning_rate": 6.754974984940941e-06,
+      "loss": 0.232,
+      "step": 220
+    },
+    {
+      "epoch": 1.2875399361022364,
+      "grad_norm": 0.06133367493748665,
+      "learning_rate": 6.12084001399091e-06,
+      "loss": 0.2382,
+      "step": 225
+    },
+    {
+      "epoch": 1.3354632587859425,
+      "grad_norm": 0.05861750617623329,
+      "learning_rate": 5.5102509791201946e-06,
+      "loss": 0.205,
+      "step": 230
+    },
+    {
+      "epoch": 1.3833865814696487,
+      "grad_norm": 0.06707581132650375,
+      "learning_rate": 4.924827052683887e-06,
+      "loss": 0.2436,
+      "step": 235
+    },
+    {
+      "epoch": 1.4313099041533546,
+      "grad_norm": 0.06414289027452469,
+      "learning_rate": 4.366120673693442e-06,
+      "loss": 0.1972,
+      "step": 240
     }
   ],
   "logging_steps": 5,
@@ -328,7 +370,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.539219665713701e+18,
+  "total_flos": 2.7690417101519217e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null