Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb48ca30ff69695564f34f37e656a7a16deb4d1c8c7d5abc0a2b8291928c1b28
+oid sha256:674122f0c53ff1e2a5e2de83f33d0683e3ccaf48f1e4ab2d38973394b6c535ed
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae047aa8458eb5b8d4c22e0d740ed84f4c6ba0afa0a57f4fdf7b047b18a724b
+oid sha256:af50d468b48a4d8a8519ca5f16e35e1ff717a81d5a571a11de02d378d57cc0ab
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b91b616bd452b894e1aea50022754f9be4afc2c867b79623be361a63b980b2
+oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06471444750040446,
+  "epoch": 0.0970716712506067,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 368.412,
       "eval_steps_per_second": 184.489,
       "step": 100
+    },
+    {
+      "epoch": 0.07118589225044492,
+      "grad_norm": 2.4127416610717773,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 43.0536,
+      "step": 110
+    },
+    {
+      "epoch": 0.07765733700048535,
+      "grad_norm": 2.415632963180542,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 43.1203,
+      "step": 120
+    },
+    {
+      "epoch": 0.08412878175052581,
+      "grad_norm": 2.95827317237854,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 43.1074,
+      "step": 130
+    },
+    {
+      "epoch": 0.09060022650056625,
+      "grad_norm": 2.204678773880005,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 43.1137,
+      "step": 140
+    },
+    {
+      "epoch": 0.0970716712506067,
+      "grad_norm": 2.9308438301086426,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 43.1151,
+      "step": 150
+    },
+    {
+      "epoch": 0.0970716712506067,
+      "eval_loss": 10.771943092346191,
+      "eval_runtime": 1.7902,
+      "eval_samples_per_second": 363.654,
+      "eval_steps_per_second": 182.106,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1507000320000.0,
+  "total_flos": 2249650077696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null