Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8772894d12f78b8fc6af826e5276f655e373807dd07b22aed0543e66cbef5292
+oid sha256:59883a5df0306e04c612084052aa37f416dfcc9178b9c054b1de8e889aec2c92
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af22a61da37ba89fb906663ab84e4be41468f2ac1684b76b88311f42c59c536f
+oid sha256:c1382e857c0f30cd4afb0807c80b329a12c4d5b1c7551c7c50aebd85fed0520d
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad35aae38bdb55d17557911fb95298bbafabf6ae7c3c9106d36788ba438d412a
+oid sha256:e72e660d2935c3030eb90699f9f4e4de0d820a63f2e88dc6bcfdd931a8509c09
 size 14244

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1130100472399276e-05,
+  "epoch": 1.5565050236199638e-05,
   "eval_steps": 500,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -10,9 +10,9 @@
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 1.776742935180664,
+      "grad_norm": 2.555440902709961,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 3.5415,
+      "loss": 3.6397,
       "step": 20
     }
   ],
@@ -21,8 +21,8 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 184619525971968.0,
-  "train_batch_size": 2,
+  "total_flos": 195453774950400.0,
+  "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null
 }