Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e02d698cdcb9afcb39a6bd9d92bb08fd57c186ad27702b8cdee55e34eaacfb
+oid sha256:986ca8f2dfe583e46926200f09a3af58752155a9fda7be2238f2cbc962bc1a11
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd25054dd7aebb61935df46353fd4a971d97fe429421b8a0ff73792ebff25082
+oid sha256:104646c5cf152d3664af59952a9cf9c624467bb49a5f2ea29a8e43a17ec801fb
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b469005eea6d771b2d009bd17df29dc4706d685beea2957c450154df435ebb
+oid sha256:a21a5782810ab8b869b551c97aadeae2b3c46bdf2b56bb121039a082c741b4e3
 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": 0.013296398891966758,
+  "epoch": 0.019944598337950138,
   "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": 33.275,
       "eval_steps_per_second": 16.638,
       "step": 6
+    },
+    {
+      "epoch": 0.01551246537396122,
+      "grad_norm": 24.66731071472168,
+      "learning_rate": 0.00014,
+      "loss": 19.7873,
+      "step": 7
+    },
+    {
+      "epoch": 0.01772853185595568,
+      "grad_norm": 21.929731369018555,
+      "learning_rate": 0.00016,
+      "loss": 21.3106,
+      "step": 8
+    },
+    {
+      "epoch": 0.019944598337950138,
+      "grad_norm": 24.648714065551758,
+      "learning_rate": 0.00018,
+      "loss": 16.7503,
+      "step": 9
+    },
+    {
+      "epoch": 0.019944598337950138,
+      "eval_loss": 2.5536041259765625,
+      "eval_runtime": 5.6486,
+      "eval_samples_per_second": 33.637,
+      "eval_steps_per_second": 16.818,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 852677810454528.0,
+  "total_flos": 1279016715681792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null