Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ec8e52d76ad414a54087b70e9e9bee8fac07b2af8447466292c7011adcd9a5
+oid sha256:d8797afc38c093cbbed5ce36062dc7f470d5fc9a31709c394900518ebdaeda04
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2072414236d691945b915be5086ba840b75dd501f22440a262dcddc0be393aa8
+oid sha256:1e39b50c9bb4932e57d872e42ff662f73cc0c625d174a9836ad30ba8db143040
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8fd9ed02254558172e0c1adf5c8f86e2a18c8ac4fa8869ed49936c433ecbe81
+oid sha256:75457ff9047a61e3f41ba81a128623afe5b1ae5c7463bc37a9196ea84fd005fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021329920546045967,
+  "epoch": 0.003199488081906895,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 15.859,
       "eval_steps_per_second": 7.929,
       "step": 100
+    },
+    {
+      "epoch": 0.002346291260065056,
+      "grad_norm": 1.068565845489502,
+      "learning_rate": 0.0002,
+      "loss": 1.2693,
+      "step": 110
+    },
+    {
+      "epoch": 0.0025595904655255157,
+      "grad_norm": 1.0892726182937622,
+      "learning_rate": 0.0002,
+      "loss": 1.1557,
+      "step": 120
+    },
+    {
+      "epoch": 0.0027728896709859757,
+      "grad_norm": 0.9760802984237671,
+      "learning_rate": 0.0002,
+      "loss": 1.1244,
+      "step": 130
+    },
+    {
+      "epoch": 0.0029861888764464353,
+      "grad_norm": 0.9369367361068726,
+      "learning_rate": 0.0002,
+      "loss": 1.0671,
+      "step": 140
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "grad_norm": 1.3040567636489868,
+      "learning_rate": 0.0002,
+      "loss": 1.1157,
+      "step": 150
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "eval_loss": 0.28656837344169617,
+      "eval_runtime": 1243.9267,
+      "eval_samples_per_second": 15.869,
+      "eval_steps_per_second": 7.935,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.649073511923712e+16,
+  "total_flos": 5.5408925343744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null