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:ae172d2734c66040ac55778c98d76ebc491fc9ea60ec62aaa8198ad0503d75d7
+oid sha256:d6244d3685ce4b6078cb80166ed0c3846fbe007bb4a8f41323d613e0f9daa45f
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded3806f8a30d4d9740432361b62c83d7f43945a2543c9aee45ed86e26b3bf0f
+oid sha256:77bf5c90bbb20efb14f063d818c72ed0d888d57726f834edeb298ac6d5e4ac67
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92aa0a05c9aabc0ef384311d2608437e22cac86912823f431f99de4cfcca89f7
+oid sha256:d53097652422fc6111bc7ea547c0aadcae71d7fb269583209c6ffeff381a08a4
 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": 0.04167148975575877,
+  "epoch": 0.04583863873133465,
   "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": 24.823,
       "eval_steps_per_second": 3.105,
       "step": 90
+    },
+    {
+      "epoch": 0.04306053941428406,
+      "grad_norm": 0.46824368834495544,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 1.6405,
+      "step": 93
+    },
+    {
+      "epoch": 0.04444958907280935,
+      "grad_norm": 0.49031543731689453,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.6011,
+      "step": 96
+    },
+    {
+      "epoch": 0.04583863873133465,
+      "grad_norm": 0.48956042528152466,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 1.5216,
+      "step": 99
+    },
+    {
+      "epoch": 0.04583863873133465,
+      "eval_loss": 1.633582353591919,
+      "eval_runtime": 146.5701,
+      "eval_samples_per_second": 24.821,
+      "eval_steps_per_second": 3.104,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.030717272621056e+16,
+  "total_flos": 5.533788999883162e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null