Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18915cb1aeb24cd4be198a5aa739b317616f8273646af8eca6cbea5ae9279fb3
+oid sha256:8ef7cec7dc4418b8ab30a029a10a252efdf25ffe926a6e56104f83781a59ae1f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ddeba8a41d762d37136b49e39e939ae270d226a0fd42621e6a94c45a873d7a
+oid sha256:45d06c687280cb8ad20299e8ad3aca9d470ff3aac0f14d13562a403038b85d04
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c031411eb4bfcead7feb84c4a628477e310fe2fc58a2fbd615313c54c2e802e
+oid sha256:f5c3c915a3bb8b4192b1fe9ab2e40a6b8012bb6b2e4c94a894df47ee8a987a0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00025593448077292216,
+  "epoch": 0.0005118689615458443,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 26.605,
       "eval_steps_per_second": 13.302,
       "step": 3
+    },
+    {
+      "epoch": 0.00034124597436389616,
+      "grad_norm": 0.8051307201385498,
+      "learning_rate": 8e-05,
+      "loss": 2.9916,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004265574679548702,
+      "grad_norm": 0.902753472328186,
+      "learning_rate": 0.0001,
+      "loss": 3.1378,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005118689615458443,
+      "grad_norm": 0.9318247437477112,
+      "learning_rate": 0.00012,
+      "loss": 2.9882,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005118689615458443,
+      "eval_loss": 3.082014799118042,
+      "eval_runtime": 185.7657,
+      "eval_samples_per_second": 26.571,
+      "eval_steps_per_second": 13.286,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 700324742430720.0,
+  "total_flos": 1359453911777280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null