Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585c2aed84c5bd9ff4f9ac86e9ad06100cbc828e79bdfcaeca78b4927a2cf8e1
+oid sha256:fe98fdb395c9aef482bd73af6217491bad126e0a423730728c03984f83574264
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bd3d471c2108e4c0b2a47411e5cb8c8b6747e4d231ab4fd5e4c641f2ce540d
+oid sha256:cdc087f95012abf1acaf4e8a51b83a57044078de1a7af6ae258d85ec696d479e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.006876790830945559,
+  "epoch": 0.013753581661891117,
   "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": 17.675,
       "eval_steps_per_second": 8.838,
       "step": 3
+    },
+    {
+      "epoch": 0.009169054441260744,
+      "grad_norm": 7.868908882141113,
+      "learning_rate": 8e-05,
+      "loss": 2.4937,
+      "step": 4
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "grad_norm": 7.792079925537109,
+      "learning_rate": 0.0001,
+      "loss": 2.3419,
+      "step": 5
+    },
+    {
+      "epoch": 0.013753581661891117,
+      "grad_norm": 5.8552398681640625,
+      "learning_rate": 0.00012,
+      "loss": 2.4592,
+      "step": 6
+    },
+    {
+      "epoch": 0.013753581661891117,
+      "eval_loss": 0.5591138601303101,
+      "eval_runtime": 10.4237,
+      "eval_samples_per_second": 17.652,
+      "eval_steps_per_second": 8.826,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1051603079528448.0,
+  "total_flos": 2103206159056896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null