Training in progress, step 88, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d061f16509b97db37465af203887c408d142f56fbef97970949953269f213ddb
+oid sha256:cb8d2805ba2cad5348e9b3cfdc88ed32afb33e84dbecb32032c02737872da7af
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311feaadd02a32da857ee33f738cb8a12e62ac3a64c9caaedea5a2e734360560
+oid sha256:750a93eaa56ca633c4714e2d4622cbfac37e9640ec4b5d5c20ce7e5872bbe1be
 size 407121750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a13afab82c6764e6c43688ad5acafed757d2d7046abda12e7a5d2c504454648
+oid sha256:c6d07ccd066181d5addf45054d55acd79f7fe6e60c4bf6c75268f796a07b3e71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916fdec13e6efc15b18e2a6b6d384a81cd69075368b316d9722fd8205c98017b
+oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5062289895194779,
+  "epoch": 0.5568518884714257,
   "eval_steps": 8,
-  "global_step": 80,
+  "global_step": 88,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,35 @@
       "eval_samples_per_second": 6.264,
       "eval_steps_per_second": 3.138,
       "step": 80
+    },
+    {
+      "epoch": 0.5125568518884714,
+      "grad_norm": 0.8669189810752869,
+      "learning_rate": 8.047222744854943e-06,
+      "loss": 0.685,
+      "step": 81
+    },
+    {
+      "epoch": 0.5315404389954519,
+      "grad_norm": 0.7252311110496521,
+      "learning_rate": 3.6037139304146762e-06,
+      "loss": 0.684,
+      "step": 84
+    },
+    {
+      "epoch": 0.5505240261024322,
+      "grad_norm": 0.9997105598449707,
+      "learning_rate": 9.0502382320653e-07,
+      "loss": 0.7458,
+      "step": 87
+    },
+    {
+      "epoch": 0.5568518884714257,
+      "eval_loss": 0.6707542538642883,
+      "eval_runtime": 85.059,
+      "eval_samples_per_second": 6.266,
+      "eval_steps_per_second": 3.139,
+      "step": 88
     }
   ],
   "logging_steps": 3,
@@ -296,7 +325,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.123319490904064e+17,
+  "total_flos": 2.3356514399944704e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null