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:be3cb80b21de3a7061ea6a8b8aec6c1663a6055ae1eeae3400de929c197239ce
+oid sha256:51fac471c6130082ce8eb45711e0dcfd7a548658f06c1d263fed4509ce9056d9
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8238e8748fbc6b599496ef00505acc11892101f0a04143c2974bfbb4a1277212
+oid sha256:f4d250c6653dfa36c4f1c7ddcf988a98e5e5356af5dc24d407bbf01301d56ba7
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c43432f565aef530341d7cc48096f083d9fa5416d7585b979637cc324b8eefd
+oid sha256:b1a140be1f7d123ea9b7ad3e11cb880da31c48a32364dcc354c332d562e270fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a5e32ef43f1e5dcf3a02d7a877bcd517d98ac810aa46ac3eb2edaf28f847a7f
+oid sha256:3c4124609480e436091ddd8cf6353f844959c53776732ecdabe8e758275813f6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4308f530d8fcba647c33e505f76738d6105a4a84e1ca8ac4f3bdb3576ecd60ce
+oid sha256:c97e433f6b45ddae1a13ef0715194087b1045cef8b790ba97a7723677e3f3117
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4474b0eafad3150c96539dc0c61a8588ef903f62fb89096a2eef3b4ef508dba2
+oid sha256:70a785605b24bc322b5f87cff2d745b8f0b821661528ac974fff3682225a8d93
 size 15024

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": 0.13636363636363635,
+  "epoch": 0.20454545454545456,
   "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": 60.492,
       "eval_steps_per_second": 8.175,
       "step": 6
+    },
+    {
+      "epoch": 0.1590909090909091,
+      "grad_norm": 4.6825079917907715,
+      "learning_rate": 0.00014,
+      "loss": 2.9952,
+      "step": 7
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 4.181937217712402,
+      "learning_rate": 0.00016,
+      "loss": 2.3997,
+      "step": 8
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "grad_norm": 3.558675765991211,
+      "learning_rate": 0.00018,
+      "loss": 1.8518,
+      "step": 9
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "eval_loss": 1.6439586877822876,
+      "eval_runtime": 1.2232,
+      "eval_samples_per_second": 60.497,
+      "eval_steps_per_second": 8.175,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4940970105765888.0,
+  "total_flos": 7411455158648832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null