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:e37d2d86cf1c6c160dd036b58aac949cc31c1dee9d7c93eccaa890427e0218f3
+oid sha256:e74312a76f13634953fe0ce8e2e0a1a19a45cd2ae86bbc480e7ab3202d017284
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e618992b5beab51f0b3c580214680e281987f2f17986ca6d51edd314ed4f5d
+oid sha256:42e19e2ed410354f52ce60464b5d18d0f24966a9ec04da2b091ccf02fa795637
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
+oid sha256:04a94b83956618c5f6ad1eb1e148eb701d120c1b0cae59d7acf6b263a4a79491
 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": 18.559,
       "eval_steps_per_second": 9.28,
       "step": 6
+    },
+    {
+      "epoch": 0.01551246537396122,
+      "grad_norm": 3.381432294845581,
+      "learning_rate": 0.00014,
+      "loss": 3.2327,
+      "step": 7
+    },
+    {
+      "epoch": 0.01772853185595568,
+      "grad_norm": 3.1606369018554688,
+      "learning_rate": 0.00016,
+      "loss": 2.4294,
+      "step": 8
+    },
+    {
+      "epoch": 0.019944598337950138,
+      "grad_norm": 3.3392677307128906,
+      "learning_rate": 0.00018,
+      "loss": 1.9235,
+      "step": 9
+    },
+    {
+      "epoch": 0.019944598337950138,
+      "eval_loss": 0.42531922459602356,
+      "eval_runtime": 10.2258,
+      "eval_samples_per_second": 18.581,
+      "eval_steps_per_second": 9.29,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899734583214080.0,
+  "total_flos": 2849601874821120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null