Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b044e52c3b59ff7fdae2531e3135c2036842592ae84bd45e99c04c6a9aebb9
+oid sha256:25600371bdd03a1fd40a7dd0d7482ca2e6a346bda9e2c8489220051b54cfb2ab
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41938fb73ccec05ca574eb60bdc917842fa31d5cb2a544e416d67ea215e44661
+oid sha256:bcce5769b25a6d282be01e06acd047d9b72055092cfa6f06476f94a869831694
 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": 2.439748525619507,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 2.421973943710327,
+  "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": 30.666,
       "eval_steps_per_second": 3.837,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 2.4189,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 2.421973943710327,
+      "eval_runtime": 204.4873,
+      "eval_samples_per_second": 30.682,
+      "eval_steps_per_second": 3.839,
+      "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
 }