Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64a77cd305793a306d4a33e936ab67e9df2f1685405dcd86d609a0fdaef61c4
+oid sha256:7c3d4df4846ce0403472729dc55ecbd3c6c369d9a6847d4dd14ba11a5cde8b60
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e512f1c5e5967c116b1cde07ebeaa2f00ec2d0b3079c1aa06f9a48d518db8531
+oid sha256:4dd7bd4ae7ba956596e02a432ed6d1276e6ae7d8a46d2bfed229f8aa1b43e094
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3310387cc5a341c03eeb1a25b13f50577e28bbc426c3d9fcdfd93c3cdb18279
+oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.4571887025123685e-05,
+  "epoch": 8.914377405024737e-05,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 25.114,
       "eval_steps_per_second": 12.557,
       "step": 3
+    },
+    {
+      "epoch": 5.9429182700164916e-05,
+      "grad_norm": 9.060395240783691,
+      "learning_rate": 8e-05,
+      "loss": 10.6533,
+      "step": 4
+    },
+    {
+      "epoch": 7.428647837520615e-05,
+      "grad_norm": 9.928213119506836,
+      "learning_rate": 0.0001,
+      "loss": 10.2667,
+      "step": 5
+    },
+    {
+      "epoch": 8.914377405024737e-05,
+      "grad_norm": 10.289470672607422,
+      "learning_rate": 0.00012,
+      "loss": 9.715,
+      "step": 6
+    },
+    {
+      "epoch": 8.914377405024737e-05,
+      "eval_loss": 2.4323079586029053,
+      "eval_runtime": 1127.6729,
+      "eval_samples_per_second": 25.131,
+      "eval_steps_per_second": 12.566,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 570056597569536.0,
+  "total_flos": 1099394866741248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null