Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed3ffbc346190ce3c98c8fead063538fbb8b39a927967522055cce14970beef
+oid sha256:8d338142b06b2a03489eab655c92cf5de925106fdc455ff6dbeb22d7f89867fe
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603e1a77b078786e3a0766730c5d4307e63a5dc657b5d84f05b3a3e0794ec585
+oid sha256:47e3641f4831c09067ac87e5b3b529c9c95895c089f77ee7e4c749737ee27314
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdacbad4cb5c5b201b8278a06f6d380ea7579ea2ad463c9cc04eb0e18aa64385
+oid sha256:7113b4ddb953686a19c918f6a7688101b24bc7cc26d2b0fb2a2b9afb4381aaed
 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": 0.01158860453887011,
+  "epoch": 0.017382906808305166,
   "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": 2.623,
       "eval_steps_per_second": 1.312,
       "step": 6
+    },
+    {
+      "epoch": 0.013520038628681796,
+      "grad_norm": 0.21218383312225342,
+      "learning_rate": 0.00014,
+      "loss": 1.4562,
+      "step": 7
+    },
+    {
+      "epoch": 0.01545147271849348,
+      "grad_norm": 0.19916756451129913,
+      "learning_rate": 0.00016,
+      "loss": 1.1486,
+      "step": 8
+    },
+    {
+      "epoch": 0.017382906808305166,
+      "grad_norm": 0.2508490979671478,
+      "learning_rate": 0.00018,
+      "loss": 1.2576,
+      "step": 9
+    },
+    {
+      "epoch": 0.017382906808305166,
+      "eval_loss": 1.288987159729004,
+      "eval_runtime": 83.0971,
+      "eval_samples_per_second": 2.623,
+      "eval_steps_per_second": 1.312,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7841498422837248.0,
+  "total_flos": 1.1762247634255872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null