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:c6bf42c024524a653a2a536fcefea8c3e271baafe95c2cae794c8c1b847e1fe5
+oid sha256:3a203c5312b2f898e3e5b9f824d61a23668deeb9cd3c9fa4f6cc0323d06abb61
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e1ccc7edd9d6ad69df678dbf66bbe38c17088b87f701fa42cb19d02866cdef
+oid sha256:8d5b17f33e8c8d947db47fa9d75dbcdef35fc27c9b7dbd1fe823bb5680861112
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d860bd81034d5a919cbdd9990f5e289c3a6c9a5689d51cc2efcd7e7e03fca46e
+oid sha256:1af8d7dca6c9565d1b6e676b22355e3e8ad95ec63bcc7c1df5799573dcf447f2
 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": 0.0498960498960499,
+  "epoch": 0.07484407484407485,
   "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": 46.487,
       "eval_steps_per_second": 23.699,
       "step": 6
+    },
+    {
+      "epoch": 0.058212058212058215,
+      "grad_norm": 1.4396038055419922,
+      "learning_rate": 0.00014,
+      "loss": 3.4585,
+      "step": 7
+    },
+    {
+      "epoch": 0.06652806652806653,
+      "grad_norm": 2.0053093433380127,
+      "learning_rate": 0.00016,
+      "loss": 4.133,
+      "step": 8
+    },
+    {
+      "epoch": 0.07484407484407485,
+      "grad_norm": 1.6646336317062378,
+      "learning_rate": 0.00018,
+      "loss": 3.3301,
+      "step": 9
+    },
+    {
+      "epoch": 0.07484407484407485,
+      "eval_loss": 0.789121150970459,
+      "eval_runtime": 1.0966,
+      "eval_samples_per_second": 46.507,
+      "eval_steps_per_second": 23.709,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 216578817785856.0,
+  "total_flos": 321134109130752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null