Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6b7e2b9ce07e8266d62f2d54da9830cb7d99a14e805bd011de4622c1c47413e
+oid sha256:b88237d6a4c2d9e1c3b3aa12d72453a5ae2298b70dab9becd8a6d02243ef95f1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce2fe05c1da90f9e4998d76fc519a7b52eb50373bbbd1354875457594f5719b
+oid sha256:a4d331755c83ae8973c424d6b1c771daba0336743be0dac332fcdb82a2a20b33
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca77415e638cf3b9d32978f227902748bb049cf3a40192fa31a73b897a1b66c8
+oid sha256:f821cd4a85f081d11b51cd13f90ea849d7c4ecdb1f73ca599d9604f19ebea037
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2453196048736572,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 2.2294440269470215,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 1.238615664845173,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,27 @@
       "eval_samples_per_second": 30.405,
       "eval_steps_per_second": 3.804,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 2.2304,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 2.2294440269470215,
+      "eval_runtime": 205.8333,
+      "eval_samples_per_second": 30.481,
+      "eval_steps_per_second": 3.814,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.70673370653696e+16,
+  "total_flos": 5.002024074356736e+16,
   "trial_name": null,
   "trial_params": null
 }