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:b391ceeab4f6074a6fc33ed80f0a543a631a80616a02b08f2891f16eaea1a026
+oid sha256:aa737ba6e1ba84b9ceecd09816b2c1a5186f4d1bbe8e3ff01be2085a4bd20f7f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6e96f20320a2db7d020eb241a63fa8064e16493c2282ef995876b23e7c45a8
+oid sha256:071ea6fc58a63f26fa4b63a6ea4e863606f1af18bbd834d26f859a775f1d396b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab2e71098167d0332b198cc3f92b905079c7bc7230441e24ab53063e6ed4e90
+oid sha256:cd1befccf01f149621d991f2f9679547f90ac16ba56a4f828c659ef826349a56
 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": 1.0592867136001587,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.2840909090909091,
+  "best_metric": 1.0460368394851685,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.42613636363636365,
   "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": 11.99,
       "eval_steps_per_second": 1.503,
       "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 1.201,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.0460368394851685,
+      "eval_runtime": 124.1855,
+      "eval_samples_per_second": 12.014,
+      "eval_steps_per_second": 1.506,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.11990315515904e+16,
+  "total_flos": 1.682558365114368e+16,
   "trial_name": null,
   "trial_params": null
 }