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:caa54fa47de1e940d1adaaee20abecd512ea9c833261f0b8a67b342aafa6944a
+oid sha256:33fe65c0e937d9dfe7876c43290b2f801790033378b1aa935dd888767c0d8840
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe7e6500c0c0ed51ccfa3bd58a9a207c984269fd8eb0e7c82eb8a6f8773fce4
+oid sha256:8c5c8af01fb68a8d63dc7c01bb76d3c0b966bb0101fd7f756710e1b572c95a0f
 size 49846260

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de8521edc9f01b0e59501941e38f71bd8fb86482ccf9bf75c30ca2d3099d6e2
+oid sha256:582f196f4d63ab94921242b3722aa87da7ed90d76395ded941d5c7905c87f5ce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22be1aa3e5649a7a84f897cac79ae7d5bf6b6f206ebba28de9cbccd7db5a00f6
+oid sha256:9c34451b9d575e5a4e8015e31b24170db1390190083092379b564ad7e1ac9475
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e408485025eed3f57974d0a63597ce057d33e889fcf6b7bb9563c5405504205
+oid sha256:4c7871c494508e55f881b9e8ecf04d8c9e09fb8fdb360ed9aa2a5b7d8f82ea03
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f114352ba5ba18ba27793d67c608e9e3ec96a3453b8abb82003b8a0ecf1d26ad
+oid sha256:b3d8ad5e52356323e48f11c2fc575a33b6855e6a88e71799fcabb63afd2cdec4
 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": 0.0025162507863283707,
+  "epoch": 0.003774376179492556,
   "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": 34.032,
       "eval_steps_per_second": 4.254,
       "step": 6
+    },
+    {
+      "epoch": 0.002935625917383099,
+      "grad_norm": 0.8932392597198486,
+      "learning_rate": 0.00014,
+      "loss": 2.427,
+      "step": 7
+    },
+    {
+      "epoch": 0.003355001048437828,
+      "grad_norm": 2.029635190963745,
+      "learning_rate": 0.00016,
+      "loss": 2.0816,
+      "step": 8
+    },
+    {
+      "epoch": 0.003774376179492556,
+      "grad_norm": 3.7211058139801025,
+      "learning_rate": 0.00018,
+      "loss": 2.3502,
+      "step": 9
+    },
+    {
+      "epoch": 0.003774376179492556,
+      "eval_loss": 1.9476796388626099,
+      "eval_runtime": 118.531,
+      "eval_samples_per_second": 33.881,
+      "eval_steps_per_second": 4.235,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3415246060322816e+16,
+  "total_flos": 2.0122869090484224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null