Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb37fa8c8661828ff6be865a874daac2c60a922af2b4f295879968fe96b3288
+oid sha256:1a45e1d02b6d53f3dbc8ca37d3801da5bae3781d89efab78beb04decc1d1783a
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2092f1140a172e37adb0782f9a12c776949d90ea2cc58c852037c95f5cea359f
+oid sha256:7f43a8a9e448f5f6bc841346570b66224c3ec12978d0b1c076749483ed83e532
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5710b632f596fa570df2f2575c76e26fe0b3fdacd4ac49afac18b353777ba28e
+oid sha256:6ff51ad6df91d0e18c7363540ae4bd74313469b3ed151c6ae2ca115845dc21fc
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9567301869392395,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 0.9550666213035583,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 2.635,
       "eval_steps_per_second": 0.33,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 0.7669,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 0.9550666213035583,
+      "eval_runtime": 729.6316,
+      "eval_samples_per_second": 2.645,
+      "eval_steps_per_second": 0.332,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.884951923281101e+17,
+  "total_flos": 4.14342522878976e+17,
   "trial_name": null,
   "trial_params": null
 }