Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961e487b7bebf8ebd09cae159f8aa8ea9fd3d2f7e1b34e32126b4407bf684bd0
+oid sha256:938dbfba8684577edfdd37d5229677bab0aadd77e905a4224b6c7e3436c5f576
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c228dd7e1bc064c4dcb107b8707b8353db118905672038dc81eeaf3bdc7da58
+oid sha256:6560ce7ea2806fcd4e6a2588729f69ccdb111b2836de036daa2297534ba7fcd5
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65b8c9bbc8133be40882ae18c1bb51b7d11f6505cc9545ca7866cac311eff5c
+oid sha256:926b0216261745d538fa9693c7e914f79ff3ad174c16127c670efa4c3175eb4b
 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": 0.00622245268343272,
+  "epoch": 0.00933367902514908,
   "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": 34.592,
       "eval_steps_per_second": 17.296,
       "step": 6
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 3.9347140789031982,
+      "learning_rate": 0.00014,
+      "loss": 5.1717,
+      "step": 7
+    },
+    {
+      "epoch": 0.008296603577910292,
+      "grad_norm": 4.398954391479492,
+      "learning_rate": 0.00016,
+      "loss": 5.3014,
+      "step": 8
+    },
+    {
+      "epoch": 0.00933367902514908,
+      "grad_norm": 4.081755638122559,
+      "learning_rate": 0.00018,
+      "loss": 4.6584,
+      "step": 9
+    },
+    {
+      "epoch": 0.00933367902514908,
+      "eval_loss": 1.1290069818496704,
+      "eval_runtime": 11.721,
+      "eval_samples_per_second": 34.639,
+      "eval_steps_per_second": 17.319,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 573720861081600.0,
+  "total_flos": 849106874400768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null