Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890ec17581b2d3e2218b3314258908e89499abe8847c271e1f942a1d0c6afb69
+oid sha256:1761880b7969ef66b071b703e0c3d2ba90d87643918048f0090744b3b14b94a8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e20a52c1043677bfaf4dcf210a126172678b2166359b0d34276dba8184b79c
+oid sha256:0768ef8978e02bcdb002e60129fa2bce4c72f01cab1b44a994df6853c7a40bec
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e25af4ad979edcd35c6e8dee487b45cb449dcc9624c1de4f1bb73ea2f5a2504
+oid sha256:e123003f79e00b7def3919bd047a2baaf72817678a4719a30825ff7849483f16
 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": 1.0227272727272727,
+  "epoch": 1.125,
   "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": 8.68,
       "eval_steps_per_second": 1.114,
       "step": 90
+    },
+    {
+      "epoch": 1.0568181818181819,
+      "grad_norm": 1.373210072517395,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.8497,
+      "step": 93
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 1.4251350164413452,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.8534,
+      "step": 96
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 1.5110843181610107,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 1.7715,
+      "step": 99
+    },
+    {
+      "epoch": 1.125,
+      "eval_loss": 1.9205644130706787,
+      "eval_runtime": 17.0633,
+      "eval_samples_per_second": 8.674,
+      "eval_steps_per_second": 1.114,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1276990228135936e+17,
+  "total_flos": 2.351391404678185e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null