Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f6dd24fb6b8d65d6ca6e147e13f882e74de4de00a5b23d765cd916fdd2c6f4
+oid sha256:4ac636223cdcd3ab27a9c4560861e021fdaf6b7c116171efc10d9c8e93df67ae
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b921305cc0391c9e4262d537d3bee4b505ae46dce8bd69ca4a3d391c0ca4b
+oid sha256:ddd3f3d13565885d23c59ff5b5f5873f5c5586042ae31336783737f09c801ed2
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4389d0522691aea38b51577fd0aac356c793ab874359c7cf5c20c3958607abf
+oid sha256:be55bbd185d3b184a97f2de34a3f525f05f10c2c723bb4e6abdc315e689b1502
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0038741456125300938,
+  "epoch": 0.004427594985748679,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 6.649,
       "eval_steps_per_second": 0.831,
       "step": 35
+    },
+    {
+      "epoch": 0.003984835487173811,
+      "grad_norm": 2.5431346893310547,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.0104,
+      "step": 36
+    },
+    {
+      "epoch": 0.004316905111104961,
+      "grad_norm": 1.9325594902038574,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.9858,
+      "step": 39
+    },
+    {
+      "epoch": 0.004427594985748679,
+      "eval_loss": 0.3066931962966919,
+      "eval_runtime": 2292.1204,
+      "eval_samples_per_second": 6.638,
+      "eval_steps_per_second": 0.83,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.6467926646784e+16,
+  "total_flos": 1.10249059024896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null