Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc275252bc7400244bffd7fbad72a85e6e6e4c250e3304aa5f8ec36bbbeeed0
+oid sha256:f0e1668d042e4b91a8f74e8a0e088ecb9f27a48518b6b84386bdeeadedfc98a9
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587f268a314305a950d00720c76543c9a39905a77dcf1c9a87d75bb711fae467
+oid sha256:5a3ade91cf2913a5db09840e715a6867e232b6bc8339f8deae976693f715f7e3
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54966f2465e62f3f23221c1b18d8d6c1829302b329b674439c498e34e1b28ba
+oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
 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": 0.007936507936507936,
+  "epoch": 0.015873015873015872,
   "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": 328.764,
       "eval_steps_per_second": 164.382,
       "step": 3
+    },
+    {
+      "epoch": 0.010582010582010581,
+      "grad_norm": 0.36031121015548706,
+      "learning_rate": 8e-05,
+      "loss": 10.8367,
+      "step": 4
+    },
+    {
+      "epoch": 0.013227513227513227,
+      "grad_norm": 0.25945383310317993,
+      "learning_rate": 0.0001,
+      "loss": 10.8487,
+      "step": 5
+    },
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 0.3726327121257782,
+      "learning_rate": 0.00012,
+      "loss": 10.8405,
+      "step": 6
+    },
+    {
+      "epoch": 0.015873015873015872,
+      "eval_loss": 10.841897964477539,
+      "eval_runtime": 0.4974,
+      "eval_samples_per_second": 321.683,
+      "eval_steps_per_second": 160.841,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 369133092864.0,
+  "total_flos": 820295761920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null