Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e43556cd58242ecc5a209ba010f0eb0099867d75370a4b194eafdbd4e67136d
+oid sha256:3ee42834e7af4ced4d7a95d28e1042e4222bf787ba987862a6f5e966dc13aa01
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e50496d6e6721a76298bacf374b175aaf00e74b62b4b0cc640ee77bee3ecc75
+oid sha256:ff5accf0f1453a3febbd0845f810dfd3c8f0929c83119b9ff73c2eaa01af04a5
 size 19859140

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": 0.00011885836540032983,
+  "epoch": 0.00023771673080065966,
   "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": 87.177,
       "eval_steps_per_second": 43.588,
       "step": 2
+    },
+    {
+      "epoch": 0.00017828754810049474,
+      "grad_norm": 0.19975675642490387,
+      "learning_rate": 3e-05,
+      "loss": 5.4583,
+      "step": 3
+    },
+    {
+      "epoch": 0.00023771673080065966,
+      "grad_norm": 0.20301611721515656,
+      "learning_rate": 4e-05,
+      "loss": 5.4742,
+      "step": 4
+    },
+    {
+      "epoch": 0.00023771673080065966,
+      "eval_loss": 5.463846206665039,
+      "eval_runtime": 325.4787,
+      "eval_samples_per_second": 87.072,
+      "eval_steps_per_second": 43.536,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259438606811136.0,
+  "total_flos": 559414495936512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null