Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bafbc247ce2c8953c6683f90d87f8bd8ba37cf8ae0a314ca9b696b213130d6e
+oid sha256:385b9b5f02bffd7fc21b5b6099caf720ae559e7d2c40f610dadf97aa98914ee6
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89cd32755e389b4400e83f3821ea5ace462c4e5fb0ddcdffabfe08ffe0d174ff
+oid sha256:d38e59bc166d16c5098bd04f0c12f6dd5bc1d2edb5232c6c8d36feee70c1003a
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d9372711d9e99428275dc2ac133f7557aed0f81e715109fa05ba4f94426d2d
+oid sha256:d7212374cd916676c44e1c9a2f0614a7d23ee62995154c5af0a7ae8272789312
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
+oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8955456614494324,
-  "best_model_checkpoint": "./outputs/checkpoint-3500",
-  "epoch": 4.666666666666667,
+  "best_metric": 0.8900671601295471,
+  "best_model_checkpoint": "./outputs/checkpoint-3600",
+  "epoch": 4.8,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,20 @@
       "eval_samples_per_second": 2.424,
       "eval_steps_per_second": 0.304,
       "step": 3500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 0.0002,
+      "loss": 0.6882,
+      "step": 3600
+    },
+    {
+      "epoch": 4.8,
+      "eval_loss": 0.8900671601295471,
+      "eval_runtime": 776.8193,
+      "eval_samples_per_second": 2.484,
+      "eval_steps_per_second": 0.312,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
@@ -504,7 +518,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 9.06455971769303e+17,
+  "total_flos": 9.323259516653568e+17,
   "trial_name": null,
   "trial_params": null
 }