Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a096e916474f8ea21aa59482cc27a566d1a44028fadf7d04673a93f1d8710
+oid sha256:7061014188b0e56289d328e5381ee08b1267e5bc3dee30353f02560973c001a8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee95bd330efa5ca4508af543427a83bfc0358f47926cda5cf5153bc280f6963
+oid sha256:b0aff1e6e2881de71e2df5d84e8b1a93a4781a0b438df70622836feb4c791797
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbad8ba2c5033686167702b52f4d733e73fc51970594ffd4d36a57cb85a15e30
+oid sha256:d2e8ce9096abd2ae0f6389d6d895fda3fff3592581063f313cd43523ff9a05ff
 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": 0.0030608340772860605,
+  "epoch": 0.00459125111592909,
   "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": 20.12,
       "eval_steps_per_second": 10.06,
       "step": 6
+    },
+    {
+      "epoch": 0.0035709730901670707,
+      "grad_norm": 3.282405376434326,
+      "learning_rate": 0.00014,
+      "loss": 4.1165,
+      "step": 7
+    },
+    {
+      "epoch": 0.004081112103048081,
+      "grad_norm": 3.7907450199127197,
+      "learning_rate": 0.00016,
+      "loss": 4.5457,
+      "step": 8
+    },
+    {
+      "epoch": 0.00459125111592909,
+      "grad_norm": 3.6256449222564697,
+      "learning_rate": 0.00018,
+      "loss": 3.8068,
+      "step": 9
+    },
+    {
+      "epoch": 0.00459125111592909,
+      "eval_loss": 0.9475084543228149,
+      "eval_runtime": 41.0737,
+      "eval_samples_per_second": 20.11,
+      "eval_steps_per_second": 10.055,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1927938979135488.0,
+  "total_flos": 2979542058663936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null