Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd33ba4a92b1ea7818ca3cfa18d030062a0b9338abc8b3f3e0373e8c7a3c37e
+oid sha256:64c51374648cea66dac66ba85d77d1ac62e0c2ec61602e86d20f11056105f55d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327df515cdbf2c5eb2e59908ad5fc08e3caab978385788e421dc232ca584f339
+oid sha256:3567bf2dd83347566b7b67fb84352cee0cab12465558af4c8eecc871ed339c76
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ef8b0c3aee1d1d0cc4dc64cf03e5b412da43485b3f017b29d3890940c4d8ff
+oid sha256:7d6e1a7976a44bff385e32c37ee7d621edd09f73147a5382f8eaf0fe3822ec41
 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": 6.9802749064934e-05,
+  "epoch": 0.000139605498129868,
   "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": 33.159,
       "eval_steps_per_second": 16.58,
       "step": 3
+    },
+    {
+      "epoch": 9.307033208657868e-05,
+      "grad_norm": 2.3003463745117188,
+      "learning_rate": 8e-05,
+      "loss": 4.8424,
+      "step": 4
+    },
+    {
+      "epoch": 0.00011633791510822335,
+      "grad_norm": 3.3803586959838867,
+      "learning_rate": 0.0001,
+      "loss": 5.8717,
+      "step": 5
+    },
+    {
+      "epoch": 0.000139605498129868,
+      "grad_norm": 3.241140604019165,
+      "learning_rate": 0.00012,
+      "loss": 4.9592,
+      "step": 6
+    },
+    {
+      "epoch": 0.000139605498129868,
+      "eval_loss": 4.933403015136719,
+      "eval_runtime": 545.6418,
+      "eval_samples_per_second": 33.166,
+      "eval_steps_per_second": 16.584,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 535542450094080.0,
+  "total_flos": 1029889327104000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null