Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95153b98fb168b4884240ffc2ef45079aa37a623b9bc59dde30695a9aa9b586
+oid sha256:d766fd1c2a16786101f6b7ed2db6bd78a3e2f0f5de27acf0a4b730edab294a7c
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f1e6f1eca8d4a2792a172490c37f10cc37bec5301fd0ff7ab82fb95e4d075a
+oid sha256:f1646feb21e642470f92d73a8b704388bf212d1c8d85fe98c12fe5e344b74acc
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb18e53aadef196cfd29560c4fbd21def93e501db51849971530281d527a19db
+oid sha256:8f95045d1f21410fb7316f4de3466d481fa3a3005a7312e8d8f0a63351bf3a0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009106930542789925,
+  "epoch": 0.0012142574057053233,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 30.122,
       "eval_steps_per_second": 3.765,
       "step": 27
+    },
+    {
+      "epoch": 0.0010118811714211029,
+      "grad_norm": 0.26121965050697327,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.7908,
+      "step": 30
+    },
+    {
+      "epoch": 0.001113069288563213,
+      "grad_norm": 0.22511965036392212,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.6791,
+      "step": 33
+    },
+    {
+      "epoch": 0.0012142574057053233,
+      "grad_norm": 0.2881379723548889,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.8729,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012142574057053233,
+      "eval_loss": 0.8234006762504578,
+      "eval_runtime": 1657.9322,
+      "eval_samples_per_second": 30.118,
+      "eval_steps_per_second": 3.765,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8490747439349760.0,
+  "total_flos": 1.1037971671154688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null