Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7be9a0c9b109d1beb0f66c5b8277e133bea76fd1cd9dbf321f2d9882116bc9
+oid sha256:5a4d1808905c58959540b1c054f7627e02bdaab4c7db0c923c3f1a3a43375bd9
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5292140616dff997e23de6744dbd35051326e4ef1ddc5d7b6c45c53d4dd42bf9
+oid sha256:ee7a34b1343c3145f94b87f53765eb821698cf1026718ab0b3ee6f68d0f5f40b
 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": 2.2463176250457764,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 2.2307546138763428,
+  "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": 30.467,
       "eval_steps_per_second": 3.812,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 2.231,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 2.2307546138763428,
+      "eval_runtime": 206.164,
+      "eval_samples_per_second": 30.432,
+      "eval_steps_per_second": 3.808,
+      "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
 }