Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c971aaaa5ffce9411893aed10cf446ee6fce7a454b02adc089816fd7d2c806
+oid sha256:f680424ffa5568e24254ea407ddc5c197e30e7cf4556b2ec4f7895c746446371
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d0ac8bf6da91e158be329792e800e3a6f85927b609ef6c47183756494c64d6
+oid sha256:918d631cbc6eecaf056cd2b8806360f341e211c539121dfd64f8b9d97ee6482b
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7811fd10b647108ec516898922bc7b00af159e4d1b4b6288ac43758dee69a5b
+oid sha256:5fd658cec9622954e85e5fe0ba5a170bd144a31d594124a29fc9c7983d5adc53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12708018154311648,
+  "epoch": 0.14523449319213314,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 17.567,
       "eval_steps_per_second": 2.209,
       "step": 63
+    },
+    {
+      "epoch": 0.13313161875945537,
+      "grad_norm": 0.0818275585770607,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.3878,
+      "step": 66
+    },
+    {
+      "epoch": 0.13918305597579425,
+      "grad_norm": 0.07330054044723511,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.3035,
+      "step": 69
+    },
+    {
+      "epoch": 0.14523449319213314,
+      "grad_norm": 0.08352211117744446,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.2734,
+      "step": 72
+    },
+    {
+      "epoch": 0.14523449319213314,
+      "eval_loss": 1.3066270351409912,
+      "eval_runtime": 47.5418,
+      "eval_samples_per_second": 17.564,
+      "eval_steps_per_second": 2.209,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.034964927755059e+16,
+  "total_flos": 4.611388488862925e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null