Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2edd74f1af237443c1ee615c5b9855cef9079340b69f203e8de5b92d4f4fd5
+oid sha256:d19ee4c79dfa0cd8555549182186a14df743daf6e21d24b4a21011c22094a6db
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68b9e3b7603d430ba932d30eab076ddcde0f33693f4623541e705b025b8a65f
+oid sha256:b2cf3c991f99ae4959929db1ffcaed2fa37c4816f516b7e8f92f6a4e7d8c3342
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20c2190e118e996b514a3787fd9ec2b8fad8f8e5b5e6e65b3757eac6356c279
+oid sha256:15e6a41072925f3dd8dbbc32ab98519e2970544ec086a60aec53e511597d9906
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4438841342926025,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 2.42663836479187,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 0.8743169398907104,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,13 +161,27 @@
       "eval_samples_per_second": 30.617,
       "eval_steps_per_second": 3.831,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 2.4221,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 2.42663836479187,
+      "eval_runtime": 204.7233,
+      "eval_samples_per_second": 30.646,
+      "eval_steps_per_second": 3.834,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.13118620803072e+16,
+  "total_flos": 3.41664786505728e+16,
   "trial_name": null,
   "trial_params": null
 }