Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d96da531178d3c8a5f3f9ecfae2b3c5359b3d4a0a1021d5fbbda0739e929f4
+oid sha256:c17d0c6e6535a77f8088ed631f94b52d8b98f248ee344541cc7b8f5f23b746d6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24bbb63462b166845611afdf578e592a010d9646d58111b3c5aa65512f6c8613
+oid sha256:742a3f477b090039a3f37ff3ac1f8c2f943175fe3b042354e3615e0efe7d2a65
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
+oid sha256:c794a47edc9435384cbc7bbda79d6455642ccecbb17e631e8dfd483567816013
 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": 0.003594428635614797,
+  "epoch": 0.005391642953422196,
   "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": 8.84,
       "eval_steps_per_second": 4.426,
       "step": 6
+    },
+    {
+      "epoch": 0.00419350007488393,
+      "grad_norm": 0.3919077515602112,
+      "learning_rate": 0.00014,
+      "loss": 0.9973,
+      "step": 7
+    },
+    {
+      "epoch": 0.004792571514153063,
+      "grad_norm": 0.4294110834598541,
+      "learning_rate": 0.00016,
+      "loss": 0.9599,
+      "step": 8
+    },
+    {
+      "epoch": 0.005391642953422196,
+      "grad_norm": 0.28537315130233765,
+      "learning_rate": 0.00018,
+      "loss": 0.9995,
+      "step": 9
+    },
+    {
+      "epoch": 0.005391642953422196,
+      "eval_loss": 0.9368210434913635,
+      "eval_runtime": 79.5623,
+      "eval_samples_per_second": 8.836,
+      "eval_steps_per_second": 4.424,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1977387508039680.0,
+  "total_flos": 2966081262059520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null