Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219f98fdea6e4bad0d5a53ad00e1054a61d0dffc2598a9723d873e9d3148952a
+oid sha256:3b85b1ad9db21848888ac0dd6347e20bfc73203a61643a0085dac4f15c7e9946
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6354f1284b1e2e5df27cc4d3ed4a8ecc2c746d9760ac7fdeb1e11034224d1de2
+oid sha256:792e30d5f2f1b82f4e857782e3bdf9907c528122fdc8d184217586edb9f6e339
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e17e59518a33349d3e7ccb2a3d6202e23618632431c2022d3d7024a72198bc7
+oid sha256:ad97e92012eab34b088960899e55a1e0fd6af3e7e6f80ae09df5b37044f193ea
 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": 0.0632577754348972,
+  "epoch": 0.06958355297838692,
   "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": 7.115,
       "eval_steps_per_second": 0.89,
       "step": 90
+    },
+    {
+      "epoch": 0.06536636794939378,
+      "grad_norm": 0.21016551554203033,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.6601,
+      "step": 93
+    },
+    {
+      "epoch": 0.06747496046389036,
+      "grad_norm": 0.18210528790950775,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.7114,
+      "step": 96
+    },
+    {
+      "epoch": 0.06958355297838692,
+      "grad_norm": 0.20607209205627441,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.684,
+      "step": 99
+    },
+    {
+      "epoch": 0.06958355297838692,
+      "eval_loss": 0.7085462808609009,
+      "eval_runtime": 336.9563,
+      "eval_samples_per_second": 7.114,
+      "eval_steps_per_second": 0.89,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.379938820784128e+17,
+  "total_flos": 2.6179327028625408e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null