Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1f2b2c3eb9955e151699367342543142a011e31420da24957aacd58764e220
+oid sha256:8177036542e0a92bf699dcaf0d502f1fab05b8f7f1a560a89b531b0108d51eac
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f1b5919677129947b16d151ff5209c3511f9cd24bc34cbb1dc305c47de6727
+oid sha256:a7849e9d3441b409ecd91cadbf47f4b399d4571e62cf4ba3cd4b7c40dbe86fc9
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25936d7c5564659764ea03391276bc1f2ec09b668311f6aed5a57a965d5055de
+oid sha256:28aa984a8995e23145e5379ede84981a1e489c4cf41652e1960df7f446e10019
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09278350515463918,
+  "epoch": 0.12371134020618557,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 6.804,
       "eval_steps_per_second": 0.861,
       "step": 27
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 2.0615859031677246,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.9618,
+      "step": 30
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 2.0000863075256348,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.0231,
+      "step": 33
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 1.8480544090270996,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.8036,
+      "step": 36
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "eval_loss": 0.727074146270752,
+      "eval_runtime": 72.0101,
+      "eval_samples_per_second": 6.805,
+      "eval_steps_per_second": 0.861,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.606577979916288e+16,
+  "total_flos": 1.2808770639888384e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null