Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4033782c38746d2cfb86a6806fd9104a14271f43ec1cc2ae8850ebca3a72a4
+oid sha256:e8996a8c9ae397e747b91aa4fbe0e5e5cbd8b4d01c11fd2f92b48513013c93c4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa618e488300a30b81d9e0a901c38572cab13d028754949d3ce9e5ce8ac0ea27
+oid sha256:2f2da546a0529aea45eb5a6daf25a9fedd4bb3076b756ebe67614c218c02b9c2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311559792ec8fdab1dc40bdff8a028cd7746aae77c5ae9f277018ecf6bf02bc1
+oid sha256:cbe94f3c099526d2d0ffee989f862b44e24dbf9220e583fff14c71db11059188
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5340639352798462,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.5129507780075073,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 15.538,
       "eval_steps_per_second": 1.949,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.2762,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.5129507780075073,
+      "eval_runtime": 93.3176,
+      "eval_samples_per_second": 15.549,
+      "eval_steps_per_second": 1.95,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.169574007504896e+16,
+  "total_flos": 1.753797686280192e+16,
   "trial_name": null,
   "trial_params": null
 }