Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1821f299dc2fcf71f600a87f36c0f7301b7366857f8996841060fabf479967d0
+oid sha256:abcf0fd4ade9ab84b0f49d1db851ad88ab83483942653328f72bdd074b5c1d48
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77913755060bd0ef5183053ca735be7a91f0f51ea616e51ae21a7169568ac2fa
+oid sha256:f7b9b315658403d6df6dc4b553be4d4ef10c86556a796992e1cc2b1b6f65d821
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313f56ae2c1e0da8e12142d22545bec21fabdaaa831671aaab809f1bcb08d8a7
+oid sha256:79640f134089a5b6b53d3d1590ef6b452050436bae87c8a0c3b40ada6d34201d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0939323902130127,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.0908570289611816,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 10.3,
       "eval_steps_per_second": 1.292,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.9365,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.0908570289611816,
+      "eval_runtime": 187.4782,
+      "eval_samples_per_second": 10.295,
+      "eval_steps_per_second": 1.291,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.555051176866857e+17,
+  "total_flos": 1.696258635822121e+17,
   "trial_name": null,
   "trial_params": null
 }