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:ba34c655bc1124e1736c396082dfe181b44402c6c153cbfa81c5858285581b75
+oid sha256:61bb92f2b3fa5bdadf24509c85564a3375f73cf3eb46ab116e2e60d685df7b96
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ef3e93b3de54b04ecd000aa25fe4407f95761c07cef7445df1c833c7b97fdd
+oid sha256:8bea7337609143e20d54452d7aeb356b9d9d0a6ac687314bdd95face1416318b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d4c94e2cd3126bb9a7c65102f0c81057ba2db04d64baf90e527b4a953730fb
+oid sha256:173d6446fe668cbd3bc82545b050f9efc0e583ccfd02dffe440a7ae20e2104d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0820419325432999,
+  "epoch": 0.0902461257976299,
   "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": 4.521,
       "eval_steps_per_second": 0.565,
       "step": 90
+    },
+    {
+      "epoch": 0.08477666362807658,
+      "grad_norm": 8.610692024230957,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 3.7501,
+      "step": 93
+    },
+    {
+      "epoch": 0.08751139471285324,
+      "grad_norm": 6.748868942260742,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.6115,
+      "step": 96
+    },
+    {
+      "epoch": 0.0902461257976299,
+      "grad_norm": 11.375263214111328,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 3.4668,
+      "step": 99
+    },
+    {
+      "epoch": 0.0902461257976299,
+      "eval_loss": 0.8423946499824524,
+      "eval_runtime": 408.5316,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.565,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3765777055429427e+17,
+  "total_flos": 2.6050947926143795e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null