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:c5dd7277a03b1dde412da1312fa81a008520731bdee539a1466671803d6b1bac
+oid sha256:c5b9a4091ab8f2d87d8c49735719bacb8a8a047bddf883e6bca65ab1db3fac4a
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d10b4dca925886c89aac3606f62530fdd86a3f94d00dcc68368a807ab70d35
+oid sha256:3b7f89d8f1a73d04ef620d9b37f1ea46a6c5bf3c3478a4ed392ba0e620b72aea
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a07c66a8bbda035c71637231362589b93f6d10c6d5ad4f8f3c1facfda53ac13
+oid sha256:653a7d79cc851bf5423ac30748a3285a94a397664d2f1baf19c62f5e6cbf4c2d
 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": 0.0010283657554203446,
+  "epoch": 0.0015425486331305167,
   "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": 15.36,
       "eval_steps_per_second": 7.683,
       "step": 6
+    },
+    {
+      "epoch": 0.0011997600479904018,
+      "grad_norm": 0.6202865242958069,
+      "learning_rate": 0.00014,
+      "loss": 4.9219,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013711543405604593,
+      "grad_norm": 0.6713095903396606,
+      "learning_rate": 0.00016,
+      "loss": 4.8562,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "grad_norm": 0.7715242505073547,
+      "learning_rate": 0.00018,
+      "loss": 4.275,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015425486331305167,
+      "eval_loss": 1.2166459560394287,
+      "eval_runtime": 160.1929,
+      "eval_samples_per_second": 15.338,
+      "eval_steps_per_second": 7.672,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2632959708364800.0,
+  "total_flos": 3906972470476800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null