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:ee97ef86a4f69f8e34a9bfa98b8854c80b5a601d0111a07676d630dbd386547a
+oid sha256:7bf162339f3135f6c5ed90a060d2d79f85b36626e257970c88057b1a65da69f9
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab56024ea862d7cb98a856194ca2734e293352d7fe3bf2409c95ff2429cc7de
+oid sha256:10aa383a023c17cad9877a4d4abc9ab7b16a1c3b9e9ee65842c28010c0766e1d
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18fa07ce0ede053c012cd0f103ac58158a0fb0159fe2f193784ec459cec5a774
+oid sha256:d4ecfc1ad6d81e3bbf19abf3e6a0b2e7c9e56e00d5f9c0b58ed923d5654a2070
 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": 0.0008925914906277894,
+  "epoch": 0.0017851829812555787,
   "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": 5.051,
       "eval_steps_per_second": 2.525,
       "step": 3
+    },
+    {
+      "epoch": 0.0011901219875037191,
+      "grad_norm": 2.5385518074035645,
+      "learning_rate": 8e-05,
+      "loss": 4.4757,
+      "step": 4
+    },
+    {
+      "epoch": 0.001487652484379649,
+      "grad_norm": 1.6990153789520264,
+      "learning_rate": 0.0001,
+      "loss": 3.1968,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017851829812555787,
+      "grad_norm": 2.8810431957244873,
+      "learning_rate": 0.00012,
+      "loss": 4.7495,
+      "step": 6
+    },
+    {
+      "epoch": 0.0017851829812555787,
+      "eval_loss": 3.694185256958008,
+      "eval_runtime": 280.1724,
+      "eval_samples_per_second": 5.054,
+      "eval_steps_per_second": 2.527,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1080837210636288.0,
+  "total_flos": 1904332228263936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null