Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754e6d0c8b95b78534629a453335fe1dc85084eeed008ac125be58b33ee35367
+oid sha256:07cd658deed4152b4fb8a7f91d7be81dc965feaabeda4a4323c1f4673916564e
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab13fd93fb68dddc6c3824e90e38d5ae241adf08342c0e417e20c8a5f3025b37
+oid sha256:172478bc9fb12c145cf132494a3826cc171c86e2549f424b65342c8ed470fa57
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4887eda634f542d0c8496ee30ab1130b0b9a4766dc9d31a2130fdb8d2444505
+oid sha256:2b2ca29d141327e8ea4b65cb34013d406e6299309d494d75934267332233dda3
 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": 1.6240431070327759,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 1.5974311828613281,
+  "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": 21.369,
       "eval_steps_per_second": 2.674,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 1.5992,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.5974311828613281,
+      "eval_runtime": 291.7,
+      "eval_samples_per_second": 21.508,
+      "eval_steps_per_second": 2.691,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.557572892531098e+16,
+  "total_flos": 7.153994046622925e+16,
   "trial_name": null,
   "trial_params": null
 }