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:f62596848930c90aaf8a295cae429766e8f4c7f862b19d5b38814ef218aeaca2
+oid sha256:5bfc9e23aa98ecb5eef7e6cd643b85995e400654f9cf8bafcb582105241a19f8
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f21bf57e66f285c4215b016f8596a14795a81a9d0cadf68fb458fdd2e43646
+oid sha256:f700dd587a1db32e7d427471baccb888c10d2b8fbb327b5be34689801fe8b05b
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ee49ee3ed199338edc0410425a9b650e38ae892510c32bbfe9d82fa579332e
+oid sha256:714e36bd11f88532014eca46aee4ac4835aa96e5731ff37263d6ad201c24acac
 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": 0.0544069640914037,
+  "epoch": 0.08161044613710555,
   "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": 15.975,
       "eval_steps_per_second": 8.008,
       "step": 100
+    },
+    {
+      "epoch": 0.05984766050054407,
+      "grad_norm": 0.21035900712013245,
+      "learning_rate": 0.0002,
+      "loss": 0.2442,
+      "step": 110
+    },
+    {
+      "epoch": 0.06528835690968444,
+      "grad_norm": 0.41095128655433655,
+      "learning_rate": 0.0002,
+      "loss": 0.1617,
+      "step": 120
+    },
+    {
+      "epoch": 0.07072905331882481,
+      "grad_norm": 0.19263286888599396,
+      "learning_rate": 0.0002,
+      "loss": 0.1611,
+      "step": 130
+    },
+    {
+      "epoch": 0.07616974972796518,
+      "grad_norm": 0.24695733189582825,
+      "learning_rate": 0.0002,
+      "loss": 0.1977,
+      "step": 140
+    },
+    {
+      "epoch": 0.08161044613710555,
+      "grad_norm": 0.3113032579421997,
+      "learning_rate": 0.0002,
+      "loss": 0.219,
+      "step": 150
+    },
+    {
+      "epoch": 0.08161044613710555,
+      "eval_loss": 0.09649600088596344,
+      "eval_runtime": 24.2365,
+      "eval_samples_per_second": 15.968,
+      "eval_steps_per_second": 8.004,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5233894521503744e+16,
+  "total_flos": 2.262621331075891e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null