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:a013899be0eb3a6d901b9fd448b1599c5e887d525014f6e71c255323d274cf63
+oid sha256:685aac9e1b1f32169d1698d77cea9e58509fb3fc98f2415a3eb8301aa56a4791
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03a3b0c64fc22d9775016c59439dd7e26bc1ddd34cff9a9d3622f8b5fda8560
+oid sha256:858b4634d866c24e03310c6a6bff0e7106dd6e2db723cad7bbb394ac33fe834d
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c66fbaf22e8a612dc4bdf54801b189d03c19522b7b1dda120d304a377a24941
+oid sha256:0b330b0b22c413d0628967a65ba9139f15aff3c277089406e9e20a5b04370e02
 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": 0.01436265709156194,
+  "epoch": 0.015798922800718134,
   "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": 23.095,
       "eval_steps_per_second": 2.888,
       "step": 90
+    },
+    {
+      "epoch": 0.014841412327947338,
+      "grad_norm": 0.5002412796020508,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.6392,
+      "step": 93
+    },
+    {
+      "epoch": 0.015320167564332734,
+      "grad_norm": 0.47195887565612793,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.6559,
+      "step": 96
+    },
+    {
+      "epoch": 0.015798922800718134,
+      "grad_norm": 0.513578474521637,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 1.7077,
+      "step": 99
+    },
+    {
+      "epoch": 0.015798922800718134,
+      "eval_loss": 1.6713879108428955,
+      "eval_runtime": 457.4203,
+      "eval_samples_per_second": 23.073,
+      "eval_steps_per_second": 2.886,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.075016755019776e+16,
+  "total_flos": 6.684164776525824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null