Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5c4fba58c6bf9390a0338353e80e91f548009bff8fd02ccc563c1546569e22
+oid sha256:03ff1d24dc08b8a25c2646f8e26c388e1283379e780176ed6477876bbe73dbd0
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cf4e040cee5763a4b906acfa31515b86ab8d763bf97cb77d72691896e9b9ff
+oid sha256:c1bf5ef5d71e8bb32c126db72ec5f530ec3327edac61ceb1e2de142e4123200c
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50dbb2327841dc1a7fe1a7d871fa34edd97692f38f48af326a03199ff55031f5
+oid sha256:aa7d14b07ebf6723d333e229fed51fa89ac2ed397877a31e17f66285a4d818d3
 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": 1.6322499513626099,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 1.6027921438217163,
+  "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": 11.318,
       "eval_steps_per_second": 1.416,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 1.5939,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.6027921438217163,
+      "eval_runtime": 555.8406,
+      "eval_samples_per_second": 11.287,
+      "eval_steps_per_second": 1.412,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.172858875396915e+17,
+  "total_flos": 4.434655082491576e+17,
   "trial_name": null,
   "trial_params": null
 }