Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22678cf8f5a483d1adaa94d4c1c590c68a3535c16487f612fe34b457ece5ad2
+oid sha256:3b3a729cb391d7779461c47e9f062df8fe45438c3b8f82ba4fa45b3a7147069a
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97458465def973762a0a0280c975d603829cfb740a7e39f98001397274b3e6a
+oid sha256:435b8c5b579e0af4e805a5165e650f2efd6399d579488612f8b64ac61b0c9b56
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979a16ef10bf9de12bbc2c602e98625ee2d1c3e490e23418d4ea005f588ea800
+oid sha256:c14058322a79c5b5614ce41abe5d63a27d35880ee1f450d491ed1c4eacf6fa41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
+oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012633534602879703,
+  "epoch": 0.01579191825359963,
   "eval_steps": 17,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,6 +201,56 @@
       "eval_samples_per_second": 32.556,
       "eval_steps_per_second": 4.072,
       "step": 68
+    },
+    {
+      "epoch": 0.012819321876451463,
+      "grad_norm": 0.9416138529777527,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 0.7452,
+      "step": 69
+    },
+    {
+      "epoch": 0.013376683697166745,
+      "grad_norm": 0.9427577257156372,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.7362,
+      "step": 72
+    },
+    {
+      "epoch": 0.013934045517882025,
+      "grad_norm": 0.8998479247093201,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 0.6653,
+      "step": 75
+    },
+    {
+      "epoch": 0.014491407338597306,
+      "grad_norm": 0.9068602919578552,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 0.7179,
+      "step": 78
+    },
+    {
+      "epoch": 0.015048769159312587,
+      "grad_norm": 0.8577080368995667,
+      "learning_rate": 6.932495846462261e-05,
+      "loss": 0.7525,
+      "step": 81
+    },
+    {
+      "epoch": 0.015606130980027869,
+      "grad_norm": 1.0340560674667358,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.7724,
+      "step": 84
+    },
+    {
+      "epoch": 0.01579191825359963,
+      "eval_loss": 0.7278433442115784,
+      "eval_runtime": 278.2156,
+      "eval_samples_per_second": 32.586,
+      "eval_steps_per_second": 4.076,
+      "step": 85
     }
   ],
   "logging_steps": 3,
@@ -220,7 +270,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.44475083358208e+16,
+  "total_flos": 3.016050502061261e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null