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:fc3deec4fe36e5974424a38658824d1b7776c46aba3d070141199fe19a3250b5
+oid sha256:9a963797d3715d77e778460e48fe1580778d837d42b2e0ed9bc69db9d25ba626
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3bdadde63b88b54393f2eed4c8ade9ddf5cd4522f2f25f9c6c7bc522a56fcc
-size 100692937
+oid sha256:ba06d1e9b142190389519474ed2f14233e19aaef3b4e0e7a2ba43e5aa9fdbf42
+size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467d37ebfc59209d07aa391196b21ef2d3ff42c5702953852ddcb6ad1a4545cc
+oid sha256:78c3b6d15e752779cee5e9a6942923b5dafa23e30d7576be88fa9256bbf60f50
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d966f0842db2ea11a27285ca469b15da90babb80bd5bf4472e1f13256015639c
+oid sha256:4c061cc93bc8f89035440fff607b7c18ef87206a55525ba751b807a11abf6d3e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0639851093292236,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 2.0028491020202637,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 43.701,
       "eval_steps_per_second": 5.468,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.0347,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.0028491020202637,
+      "eval_runtime": 143.5409,
+      "eval_samples_per_second": 43.709,
+      "eval_steps_per_second": 5.469,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.190421429977088e+16,
+  "total_flos": 1.7869715412615168e+16,
   "trial_name": null,
   "trial_params": null
 }