Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5272bc19e1d27b3267527277e510625009ab11912ddd54d761d855ba34b18cc9
+oid sha256:d13fbc13144a990f465ef91f4e90defc1709ade1466caac0a6e90948ee83c458
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1498b4bc17a3b10f13c70972ed7d90f45d59dfb424b1668659c4ebefcab9c1
+oid sha256:2613027427580dae177656a8f4ac1ed333d6847300284c7c34a5de0382dfe7ec
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32802154ebe7e69068c60740824ef1cdff98b1ec9333bc015d9c498496cfe8db
+oid sha256:e3c4140fd6dce9e65319f7d658a1b225649f7fb6d3492d10c3e3d2622515091c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025130890052356022,
+  "epoch": 0.03769633507853403,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 88.599,
       "eval_steps_per_second": 44.738,
       "step": 6
+    },
+    {
+      "epoch": 0.02931937172774869,
+      "grad_norm": 9.638185501098633,
+      "learning_rate": 0.00014,
+      "loss": 9.8085,
+      "step": 7
+    },
+    {
+      "epoch": 0.033507853403141365,
+      "grad_norm": 7.506699085235596,
+      "learning_rate": 0.00016,
+      "loss": 8.8918,
+      "step": 8
+    },
+    {
+      "epoch": 0.03769633507853403,
+      "grad_norm": 8.663238525390625,
+      "learning_rate": 0.00018,
+      "loss": 9.3444,
+      "step": 9
+    },
+    {
+      "epoch": 0.03769633507853403,
+      "eval_loss": 8.99866771697998,
+      "eval_runtime": 1.1792,
+      "eval_samples_per_second": 85.653,
+      "eval_steps_per_second": 43.25,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 393351266304.0,
+  "total_flos": 590026899456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null