Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad7bd33c9bc1294fe9ae75b8834798f38b5db21dbbc5563118b571f9adc3ca5
+oid sha256:b5af3a07781f05de7535bdcf0582e305d5484ef5a3dd809c0985be305a58663d
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d62f85d126070644e734def17eb54fb6a2d5916f51a9857f5c03f384a3175b43
+oid sha256:ae5fe98bc3b6549d7fbd42ad73dcba05fcce41ebfa79595ae6e0215c34472adc
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e71f2298c2ac93c79dce17bfd0f83400414376a51976e549dc65124bfe5c3ec
+oid sha256:a730a343a863d4216549392bfe668d1a20b027b7071c0dc0f4c8937109e105f0
 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": 0.0032803017877644745,
+  "epoch": 0.004920452681646712,
   "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": 43.631,
       "eval_steps_per_second": 21.816,
       "step": 100
+    },
+    {
+      "epoch": 0.0036083319665409217,
+      "grad_norm": 27.118141174316406,
+      "learning_rate": 0.0002,
+      "loss": 1.5655,
+      "step": 110
+    },
+    {
+      "epoch": 0.003936362145317369,
+      "grad_norm": 26.091899871826172,
+      "learning_rate": 0.0002,
+      "loss": 1.4447,
+      "step": 120
+    },
+    {
+      "epoch": 0.0042643923240938165,
+      "grad_norm": 41.93053436279297,
+      "learning_rate": 0.0002,
+      "loss": 1.7189,
+      "step": 130
+    },
+    {
+      "epoch": 0.004592422502870264,
+      "grad_norm": 27.1080379486084,
+      "learning_rate": 0.0002,
+      "loss": 1.6945,
+      "step": 140
+    },
+    {
+      "epoch": 0.004920452681646712,
+      "grad_norm": 19.277257919311523,
+      "learning_rate": 0.0002,
+      "loss": 1.6047,
+      "step": 150
+    },
+    {
+      "epoch": 0.004920452681646712,
+      "eval_loss": 1.4655190706253052,
+      "eval_runtime": 293.6017,
+      "eval_samples_per_second": 43.719,
+      "eval_steps_per_second": 21.86,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6897821559029760.0,
+  "total_flos": 1.041211453341696e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null