Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9297ffddbd1a28198089268a1ffedecfc9487af51640095ef4fdd325f16eeb84
+oid sha256:07e62ac60d9843fe1f10a62bfdeab4d7b3b595d3803d1b2c746ad5f9b0a77ec8
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ee64d67fdd9152201dc6423349a9c1f35d14ac73cea6d7b65236053c678c6f
+oid sha256:cc3b912d5cdd4e89fe9a82bfd072cb9c15c71075f6f1ad5fd633ecf1d242aa87
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7f1807a79f764cdbf1638aa0e0db1154794499b1015a5180c25c186b8d6d94
+oid sha256:55f5b8fc91a819fc39bd479452495c8f8f43e1c210ee91583af5c241cfc6079a
 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": 0.05350454788657036,
+  "epoch": 0.08025682182985554,
   "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": 21.164,
       "eval_steps_per_second": 10.596,
       "step": 100
+    },
+    {
+      "epoch": 0.05885500267522739,
+      "grad_norm": 0.5722771883010864,
+      "learning_rate": 0.0002,
+      "loss": 0.9267,
+      "step": 110
+    },
+    {
+      "epoch": 0.06420545746388442,
+      "grad_norm": 0.5415870547294617,
+      "learning_rate": 0.0002,
+      "loss": 0.9077,
+      "step": 120
+    },
+    {
+      "epoch": 0.06955591225254147,
+      "grad_norm": 0.5300649404525757,
+      "learning_rate": 0.0002,
+      "loss": 0.8924,
+      "step": 130
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 0.5958105325698853,
+      "learning_rate": 0.0002,
+      "loss": 0.9126,
+      "step": 140
+    },
+    {
+      "epoch": 0.08025682182985554,
+      "grad_norm": 0.5649930238723755,
+      "learning_rate": 0.0002,
+      "loss": 0.8239,
+      "step": 150
+    },
+    {
+      "epoch": 0.08025682182985554,
+      "eval_loss": 0.8727919459342957,
+      "eval_runtime": 37.1914,
+      "eval_samples_per_second": 21.161,
+      "eval_steps_per_second": 10.594,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1662041726976e+16,
+  "total_flos": 4.7493062590464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null