Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8118388fa6ff19afafac585e8639907fc1f3859c118bca21a0d4c2d76fa5e294
+oid sha256:16faa2f0e020ee34ef0aa4e8c4370d6469571f45d9b61d0b313b4b3b10a52b85
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0c022ae7754def1254f2e4fd15c271a2e72b92d7dce0efd48e7ef33b568d74
+oid sha256:ddf9acfa7a494a322e8af18a537bb7e42cba478e17a05556b452f627b00dbdd1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7e17e7cef471fd5aa3ed407c6d9c6e3776323cfd2063fbf6c63d9529450116
+oid sha256:6ae592f5b56869a5199b46dcaab343cbe5455d328d9aa29d6d21e369bab3be64
 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": 0.0016453795684992082,
+  "epoch": 0.002468069352748812,
   "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": 15.694,
       "eval_steps_per_second": 7.847,
       "step": 100
+    },
+    {
+      "epoch": 0.001809917525349129,
+      "grad_norm": 2.9922564029693604,
+      "learning_rate": 0.0002,
+      "loss": 2.9806,
+      "step": 110
+    },
+    {
+      "epoch": 0.0019744554821990497,
+      "grad_norm": 2.0195345878601074,
+      "learning_rate": 0.0002,
+      "loss": 3.0699,
+      "step": 120
+    },
+    {
+      "epoch": 0.0021389934390489704,
+      "grad_norm": 1.5428060293197632,
+      "learning_rate": 0.0002,
+      "loss": 2.9836,
+      "step": 130
+    },
+    {
+      "epoch": 0.0023035313958988915,
+      "grad_norm": 2.2752511501312256,
+      "learning_rate": 0.0002,
+      "loss": 2.7856,
+      "step": 140
+    },
+    {
+      "epoch": 0.002468069352748812,
+      "grad_norm": 2.081397771835327,
+      "learning_rate": 0.0002,
+      "loss": 2.8102,
+      "step": 150
+    },
+    {
+      "epoch": 0.002468069352748812,
+      "eval_loss": 0.7075520753860474,
+      "eval_runtime": 1631.1511,
+      "eval_samples_per_second": 15.688,
+      "eval_steps_per_second": 7.844,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.03691032018944e+16,
+  "total_flos": 6.087027522011136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null