Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9902761dfb3698eca87f5ead41ea9eea52e5996bd1b9c30ab8e82247d2abf729
+oid sha256:0e7120592ab41efdac3c7f60c7fa5ac7f25bc4345bdd718bec0a2d6afa57382e
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d2a4ad63afe748b055da23cfae531cd1b4bd259fd254d6d65b869b3309a3793
+oid sha256:520def964098f33d083a8a9e0c76683d0c1e5903d751486cced50b6b9c54dbc7
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf0e7c8e6f58ca05bfa9a01c0e15652940b7d2d941987650d7e5fe4b9d6deb1
+oid sha256:5d893120bfba3bcdf26c7a5f485519018e7cecd593a2d8ea3432449ab1d8daeb
 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": 1.6236809492111206,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 1.6063587665557861,
+  "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": 43.723,
       "eval_steps_per_second": 5.471,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 1.6032,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.6063587665557861,
+      "eval_runtime": 143.5371,
+      "eval_samples_per_second": 43.71,
+      "eval_steps_per_second": 5.469,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.556878282198221e+16,
+  "total_flos": 7.153237888539034e+16,
   "trial_name": null,
   "trial_params": null
 }