Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec16bdaaf5daf2ec37b042762ed155e5e0ed431374c2b01f006ea5e6238e1b4
+oid sha256:4ceeb629b387b0bfeb320d7e83f81907ee94f4a12c87e9f8e70ad348fb320047
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e75ed04d3c40660e8f606ba7d84940d6e873761b0b2f3d852f30818c373a5fbb
+oid sha256:b20864bf3d5ef793bdef44670b0889ba2b5ad259d12e0e15d32e588f60e04288
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50472c366712a8f99da169476292927ca298784b15671d3e8321b2e18ced05a
+oid sha256:199f083e96c17188a9b5a33fc6986dd23571a3e63eb408d502604fa647872b0d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3999289274215698,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.4775956284153007,
+  "best_metric": 1.388107180595398,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.550455373406193,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,13 +483,27 @@
       "eval_samples_per_second": 47.086,
       "eval_steps_per_second": 5.891,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.373,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.388107180595398,
+      "eval_runtime": 133.2079,
+      "eval_samples_per_second": 47.099,
+      "eval_steps_per_second": 5.893,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0244258420626227e+17,
+  "total_flos": 2.0839850145502003e+17,
   "trial_name": null,
   "trial_params": null
 }