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:d619e343dfecde2988040ea07b4f89fde22d508a3d76de6ab3a91bfa66f40aa7
+oid sha256:ef4d192cfc242dd8372b7ad57c249c1fd3098a3cf926dd428375c30fdd90eddf
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e06027212782b579b1f6b3be3d17dbed0233f022f2d131708636d7b76ba3d4a
+oid sha256:79eb212786114a9f66c6f285246faba3325b41f5748437ab4dc139119a9d5930
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bec4c1f1d75c428cae448860d0e82372daea77c9bfeca935247ba856aa1b113
+oid sha256:b98d64ccfef59fa4d35911acd01105b39447563e4e6c140c23789ee7fcb1e6ab
 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": 1.8929505348205566,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.2727272727272725,
+  "best_metric": 1.8908874988555908,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.4147727272727275,
   "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": 27.766,
       "eval_steps_per_second": 3.48,
       "step": 1600
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0002,
+      "loss": 1.9964,
+      "step": 1700
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 1.8908874988555908,
+      "eval_runtime": 53.6745,
+      "eval_samples_per_second": 27.797,
+      "eval_steps_per_second": 3.484,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.85395148399616e+16,
+  "total_flos": 5.153298119165952e+16,
   "trial_name": null,
   "trial_params": null
 }