Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404d3e3a29eaf7b6b0dd131a8a9666d398ae2331ec64cd76b072b50d3ae59c19
+oid sha256:a31e2f5c31dc335792099b64f2e6f882ea2442117476d24dcf2d3cf439458cf8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0321786a26f289a046c061ead002998940b88adb8a8e831e207423040608176
+oid sha256:ad6b792fef084274d6705de4dba8d5cc1d968f394a86d8ce4cf1c597d1f3bba3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa014f64af74d746e93c1a07b7e2f52716b1d821d9b3a781023ca063a03bade
+oid sha256:e84eeacc9cc39c5001a9a09968de294bed9003c08f0a64569ec38b952acb061d
 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": 0.25657472738935216,
+  "epoch": 0.38486209108402825,
   "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": 20.807,
       "eval_steps_per_second": 10.467,
       "step": 100
+    },
+    {
+      "epoch": 0.28223220012828737,
+      "grad_norm": 5.021260738372803,
+      "learning_rate": 0.0002,
+      "loss": 4.0535,
+      "step": 110
+    },
+    {
+      "epoch": 0.3078896728672226,
+      "grad_norm": 3.946540355682373,
+      "learning_rate": 0.0002,
+      "loss": 4.2911,
+      "step": 120
+    },
+    {
+      "epoch": 0.3335471456061578,
+      "grad_norm": 5.100417137145996,
+      "learning_rate": 0.0002,
+      "loss": 4.1604,
+      "step": 130
+    },
+    {
+      "epoch": 0.359204618345093,
+      "grad_norm": 3.0885791778564453,
+      "learning_rate": 0.0002,
+      "loss": 3.846,
+      "step": 140
+    },
+    {
+      "epoch": 0.38486209108402825,
+      "grad_norm": 3.596226453781128,
+      "learning_rate": 0.0002,
+      "loss": 4.1906,
+      "step": 150
+    },
+    {
+      "epoch": 0.38486209108402825,
+      "eval_loss": 0.9527939558029175,
+      "eval_runtime": 7.9098,
+      "eval_samples_per_second": 20.86,
+      "eval_steps_per_second": 10.493,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.512320862145741e+16,
+  "total_flos": 3.843810200754586e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null