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:d44015d5dc8781ee25ad4409ff45eeac4c22c15b56d4b5c091ad378aeabaa64d
+oid sha256:c2b4f7028c311d648827d6a28e7ad74eef01a9749588a7e5f2de1509e6a160c8
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152a58058fad5a204c9008bb28fb4230ae9fc15a43b3c80a2a0f5b2702e72d9a
+oid sha256:98718c8b559076c43c75f1f28e6f99b2a2aa6b00fef2df13b44159544f283bc3
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980332badefea92de1b7820ea616467dde6c51251c8eca0da066becd87234ae2
+oid sha256:60102adbf037789b2d2ff4d393263c3c0c7c2562e5ee5a7a17e97388a858bfad
 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": 0.000365586156470875,
+  "epoch": 0.00073117231294175,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 18.067,
       "eval_steps_per_second": 9.034,
       "step": 3
+    },
+    {
+      "epoch": 0.0004874482086278333,
+      "grad_norm": 0.7119388580322266,
+      "learning_rate": 8e-05,
+      "loss": 1.3815,
+      "step": 4
+    },
+    {
+      "epoch": 0.0006093102607847916,
+      "grad_norm": 0.48799067735671997,
+      "learning_rate": 0.0001,
+      "loss": 1.2123,
+      "step": 5
+    },
+    {
+      "epoch": 0.00073117231294175,
+      "grad_norm": 0.6031394004821777,
+      "learning_rate": 0.00012,
+      "loss": 1.3516,
+      "step": 6
+    },
+    {
+      "epoch": 0.00073117231294175,
+      "eval_loss": 1.4253041744232178,
+      "eval_runtime": 190.0245,
+      "eval_samples_per_second": 18.187,
+      "eval_steps_per_second": 9.094,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 78177292517376.0,
+  "total_flos": 162368222920704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null