Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4482580152cd3567e15d4fec9cc87a407443a19a5c7561f46a520dc35be21068
+oid sha256:fe050839eeb5c63659978257376f09285f8424cd3517187d72a49dc05ba07167
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef63f3247980b4eff47882c21dc74267b084a567ae5c80925fdc10e74b32bb5b
+oid sha256:72ed7aceccbc6395cc01410b9b754ac7bfec5b5a913936da6e61936080f40836
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00037604587759706683,
+  "epoch": 0.0007520917551941337,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 770.011,
       "eval_steps_per_second": 385.006,
       "step": 2
+    },
+    {
+      "epoch": 0.0005640688163956002,
+      "grad_norm": 0.046713195741176605,
+      "learning_rate": 3e-05,
+      "loss": 10.3632,
+      "step": 3
+    },
+    {
+      "epoch": 0.0007520917551941337,
+      "grad_norm": 0.039439644664525986,
+      "learning_rate": 4e-05,
+      "loss": 10.3627,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007520917551941337,
+      "eval_loss": 10.363784790039062,
+      "eval_runtime": 11.8982,
+      "eval_samples_per_second": 752.885,
+      "eval_steps_per_second": 376.443,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 103447265280.0,
+  "total_flos": 206894530560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null