Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3568542bbd4dbba8b0040e310b96c5f8889068e5326518b7afdfc79c5c513e0
+oid sha256:a5ed8578a08f2a4cba821f7df6f499e74bc7591efcc1e82204d60ce576f5aab0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b941fd13a28befeeb1e66a359dd41fafb62e609d87f132e0070c23fd6e73fd3
+oid sha256:682d8f07f809efd9354197e793c20195b3bfe9b3e9eb30f452326cfe7d92dcc3
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ae40147066520ba06d8488dffecb1617761bf0f5a71e5b8f891ada27bea484
+oid sha256:fd93ad71d1e4da2e65f4e2c9390e9d7b7bc2ea6079b0f1bd60a10893bb8881fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b80765e20485e55a4536ea4722ca0ff9932fa89aed6198907323185f55ec4c0
+oid sha256:bedc6307a5e33c9ada0599345089662b71de7faf79562d8c952efe37fda8ce81
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00735564545788893,
+  "epoch": 0.01471129091577786,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 11.031,
       "eval_steps_per_second": 1.387,
       "step": 5
+    },
+    {
+      "epoch": 0.008826774549466716,
+      "grad_norm": 1.0511504411697388,
+      "learning_rate": 3e-05,
+      "loss": 9.7365,
+      "step": 6
+    },
+    {
+      "epoch": 0.013240161824200073,
+      "grad_norm": 1.3530985116958618,
+      "learning_rate": 4.5e-05,
+      "loss": 9.7514,
+      "step": 9
+    },
+    {
+      "epoch": 0.01471129091577786,
+      "eval_loss": 2.3896217346191406,
+      "eval_runtime": 103.8136,
+      "eval_samples_per_second": 11.029,
+      "eval_steps_per_second": 1.387,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534646443540480.0,
+  "total_flos": 1.306929288708096e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null