Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2855649e5bb107a813e6f448299336efe52aed126c9cc7e08463a2a8f37f6137
+oid sha256:ef76f3233d26c968753efea4502e9caef436d5f9f5b6035bf0d24ea237b871d9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf6ac9bfdf1996ae3cdfca4b991b1b82790f3f6017bf649beb66206affe4d73
+oid sha256:907bd4dff1dd504bca97aa8897ec4a9a37ca8ec9ac0903090de2f786c153a52c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a090bc482ef5f1b83af8f13fdd6e9fe2b0babec66f75c50ea84e39461e78f9
+oid sha256:dae627a7d2298122bff578106eebf3a91e3c4a65f4b6f1686a626ab036cc9c37
 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": 0.0008504003968535185,
+  "epoch": 0.001700800793707037,
   "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": 13.795,
       "eval_steps_per_second": 6.898,
       "step": 3
+    },
+    {
+      "epoch": 0.0011338671958046915,
+      "grad_norm": 0.6751747727394104,
+      "learning_rate": 8e-05,
+      "loss": 2.2244,
+      "step": 4
+    },
+    {
+      "epoch": 0.0014173339947558643,
+      "grad_norm": 0.6359903216362,
+      "learning_rate": 0.0001,
+      "loss": 1.922,
+      "step": 5
+    },
+    {
+      "epoch": 0.001700800793707037,
+      "grad_norm": 1.8159571886062622,
+      "learning_rate": 0.00012,
+      "loss": 2.3929,
+      "step": 6
+    },
+    {
+      "epoch": 0.001700800793707037,
+      "eval_loss": 0.5036287307739258,
+      "eval_runtime": 107.8228,
+      "eval_samples_per_second": 13.782,
+      "eval_steps_per_second": 6.891,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488624772612096.0,
+  "total_flos": 977249545224192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null