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:e6163f042982e75779c199f6b2b158d8670064b2c7d82174ad1c816fc8d6242c
+oid sha256:181729fbae5b914f3c68e212801830b48ea63af37af65b6ab55903dedcbacffa
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632b154edcad557298796e69b74cff20326f7e6d35480c6eb8d916163b298446
+oid sha256:861ad631dcac34793b2cc17adb6b177ce25ac3ca92d62af75a2da6ebeb1c36e6
 size 17190970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7cec7fa95fb16b09232bf47470bd56c852288bce7d205fc837860a8a1d8db12
+oid sha256:b1ae6309517a2108e6bd10ea1fd8da0edc71a65cb14916086f3915020657220a
 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": 0.013036393264530146,
+  "epoch": 0.01955458989679522,
   "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": 5.796,
       "eval_steps_per_second": 2.898,
       "step": 6
+    },
+    {
+      "epoch": 0.015209125475285171,
+      "grad_norm": 29.270177841186523,
+      "learning_rate": 0.00014,
+      "loss": 19.651,
+      "step": 7
+    },
+    {
+      "epoch": 0.017381857686040194,
+      "grad_norm": 26.47623634338379,
+      "learning_rate": 0.00016,
+      "loss": 18.795,
+      "step": 8
+    },
+    {
+      "epoch": 0.01955458989679522,
+      "grad_norm": 28.52800941467285,
+      "learning_rate": 0.00018,
+      "loss": 17.5999,
+      "step": 9
+    },
+    {
+      "epoch": 0.01955458989679522,
+      "eval_loss": 3.6607913970947266,
+      "eval_runtime": 33.3485,
+      "eval_samples_per_second": 5.817,
+      "eval_steps_per_second": 2.909,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1081911388667904.0,
+  "total_flos": 1622867083001856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null