Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e31caa0549662895406b35f60ee272ab02940a6d1169d24cf30843d63008545
+oid sha256:2791b511c4630b21fd991533625ec1ec52da3e5cc1609da7a4c2cfedc1bcba6d
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a691ecd73b2e1973b2873ff3d47ecc200e0a85a6854d7fd2dc11400647afb9e
+oid sha256:a884f4320934e16da5143deade141b5396382f6dfdc0784d68105ea5d71bc6b2
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d35c87f5d0e8ea62bc673d149da7d93d79a8b9b3951cb1475638c45526807b
+oid sha256:fec363189963dc133232a1202530bba3901933ae6ee2483645557d8ee2922117
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd12c7442104c6bee1178cd38829bd00c01ded478e430b03fe72cfaff700e4be
+oid sha256:16a7801db1aa9f181cf78d5699e3a7862ab42bf9c452e31cb54501196abe18a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.290030211480363,
+  "epoch": 2.5438066465256797,
   "eval_steps": 21,
-  "global_step": 189,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -528,6 +528,63 @@
       "eval_samples_per_second": 540.238,
       "eval_steps_per_second": 69.459,
       "step": 189
+    },
+    {
+      "epoch": 2.326283987915408,
+      "grad_norm": 0.17823714017868042,
+      "learning_rate": 1.3390009847968504e-05,
+      "loss": 10.1773,
+      "step": 192
+    },
+    {
+      "epoch": 2.3625377643504533,
+      "grad_norm": 0.21689902245998383,
+      "learning_rate": 1.2075907148663579e-05,
+      "loss": 10.1772,
+      "step": 195
+    },
+    {
+      "epoch": 2.3987915407854983,
+      "grad_norm": 0.3612368106842041,
+      "learning_rate": 1.0820770952526155e-05,
+      "loss": 10.1826,
+      "step": 198
+    },
+    {
+      "epoch": 2.4350453172205437,
+      "grad_norm": 0.19127142429351807,
+      "learning_rate": 9.62655281559679e-06,
+      "loss": 10.1821,
+      "step": 201
+    },
+    {
+      "epoch": 2.471299093655589,
+      "grad_norm": 0.21965357661247253,
+      "learning_rate": 8.49510957510633e-06,
+      "loss": 10.1765,
+      "step": 204
+    },
+    {
+      "epoch": 2.5075528700906347,
+      "grad_norm": 0.1769980639219284,
+      "learning_rate": 7.4282004623615396e-06,
+      "loss": 10.1756,
+      "step": 207
+    },
+    {
+      "epoch": 2.5438066465256797,
+      "grad_norm": 0.20193351805210114,
+      "learning_rate": 6.427484367393699e-06,
+      "loss": 10.178,
+      "step": 210
+    },
+    {
+      "epoch": 2.5438066465256797,
+      "eval_loss": 10.170087814331055,
+      "eval_runtime": 0.2628,
+      "eval_samples_per_second": 532.826,
+      "eval_steps_per_second": 68.506,
+      "step": 210
     }
   ],
   "logging_steps": 3,
@@ -547,7 +604,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21083074854912.0,
+  "total_flos": 23425638727680.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null