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:a884df52d5d497f0cf99ab33bbb9939e2bfc7c572f77288c619db14b3807ea12
+oid sha256:e72f73dfc4300734c8ed35095c7b97ed64373aec4f2048b40ddb819133e97290
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befb75f8f7c52ae837b85545c28d514e0bade4a0a4bf5eabe9463024129283f3
+oid sha256:c88065eff5f6420a776d19c46d8f6f9c5cad71429c3a3c84678d263ec21177ff
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
+oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
 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": 0.010105263157894737,
+  "epoch": 0.015157894736842105,
   "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": 96.916,
       "eval_steps_per_second": 48.458,
       "step": 6
+    },
+    {
+      "epoch": 0.011789473684210527,
+      "grad_norm": 24.055999755859375,
+      "learning_rate": 0.00014,
+      "loss": 9.1365,
+      "step": 7
+    },
+    {
+      "epoch": 0.013473684210526317,
+      "grad_norm": 63.981239318847656,
+      "learning_rate": 0.00016,
+      "loss": 12.1075,
+      "step": 8
+    },
+    {
+      "epoch": 0.015157894736842105,
+      "grad_norm": 32.312252044677734,
+      "learning_rate": 0.00018,
+      "loss": 13.2968,
+      "step": 9
+    },
+    {
+      "epoch": 0.015157894736842105,
+      "eval_loss": 2.880253791809082,
+      "eval_runtime": 2.5756,
+      "eval_samples_per_second": 97.064,
+      "eval_steps_per_second": 48.532,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52637139468288.0,
+  "total_flos": 78955709202432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null