Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011f2fa1804cf06633a00a7a340bc577f7cf2a2f2356ff8a1a852362b187f337
+oid sha256:071f712a2466325ef938fec4404141d66b258b617a7e37699fab1c1c09252b39
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28824361622dadb9e986b9630682f3ab9f714e086bbf31e90f3962656cf48498
+oid sha256:b222c8649ec91fc8d4c4327608dff65356dda1864ae529ef2b005dd6e3557d1a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94dedff251b37d3b090b8c13e70a9c3f92acb67b4b99bcf80e06219fec51151
+oid sha256:29922d3bb3e0be18777a427416821f3eaacd34db115be0a37f60e33dfb4697a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6474820143884892,
+  "epoch": 0.7122302158273381,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 12.076,
       "eval_steps_per_second": 1.548,
       "step": 90
+    },
+    {
+      "epoch": 0.6690647482014388,
+      "grad_norm": 2.176861047744751,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 4.1401,
+      "step": 93
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 1.9706419706344604,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 3.9663,
+      "step": 96
+    },
+    {
+      "epoch": 0.7122302158273381,
+      "grad_norm": 2.0750808715820312,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 4.1725,
+      "step": 99
+    },
+    {
+      "epoch": 0.7122302158273381,
+      "eval_loss": 1.0105128288269043,
+      "eval_runtime": 19.3722,
+      "eval_samples_per_second": 12.079,
+      "eval_steps_per_second": 1.549,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5398536021121434e+17,
+  "total_flos": 1.6910264443286323e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null