Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623d44964634679f51782f72fac725504f858e11b7f80b1c785a61821398f079
+oid sha256:6157273021e0ff19574630eee80b638867f923006bf5ef26df6a0f45536d8a9b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5562da6f932a56bb017624b76dc514bba7d25edd54a00c07bc21e710d5f72a
+oid sha256:b27e98f9ad862a2b7b5bebd6b6b36aaa531a06e1cc4d392a6fad11843326a611
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2363b82feb180cfc02981d477371f95eb564639100a05b6f0935a6e396371e
+oid sha256:e9e557b1e77c85fe07b1ec3d978d1fe6eca72d96d47ae9e1632080936f73f36b
 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": 1.3022856712341309,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.2983750104904175,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 12.905,
       "eval_steps_per_second": 1.619,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 1.0494,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.2983750104904175,
+      "eval_runtime": 112.4723,
+      "eval_samples_per_second": 12.901,
+      "eval_steps_per_second": 1.618,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0180857681985536e+17,
+  "total_flos": 1.0816203102437376e+17,
   "trial_name": null,
   "trial_params": null
 }