Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6719ae4d336055a31e9e475e7250664eb71c516ce05477ce99cfab156df01ee8
+oid sha256:f6d720a608c5e53080a8325eca6e3a801091a412083a6756e13d4984c102bc70
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdf77831ee6f08a6a3f76ac1f0ea46bdc77db7176e6d4ec7609b07df0e05036
+oid sha256:17d88a93debff029f855385dc7dc0b0b94413c9f396957e196d9d6334a74296e
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b06c02318ef50c2326a25d38e83c97e0565c4ad34b185cd827a3069bf65c6d6
+oid sha256:7fa5a9e7fe9b733f4d7378c2f4295e39738bd784ce49157561d991d047aeb2c0
 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": 0.00909090909090909,
+  "epoch": 0.01818181818181818,
   "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": 20.475,
       "eval_steps_per_second": 10.311,
       "step": 3
+    },
+    {
+      "epoch": 0.012121212121212121,
+      "grad_norm": 2.01965069770813,
+      "learning_rate": 8e-05,
+      "loss": 1.8594,
+      "step": 4
+    },
+    {
+      "epoch": 0.015151515151515152,
+      "grad_norm": 2.7054171562194824,
+      "learning_rate": 0.0001,
+      "loss": 1.9402,
+      "step": 5
+    },
+    {
+      "epoch": 0.01818181818181818,
+      "grad_norm": 1.8634957075119019,
+      "learning_rate": 0.00012,
+      "loss": 1.6187,
+      "step": 6
+    },
+    {
+      "epoch": 0.01818181818181818,
+      "eval_loss": 1.6859822273254395,
+      "eval_runtime": 6.9262,
+      "eval_samples_per_second": 20.069,
+      "eval_steps_per_second": 10.107,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 246014599495680.0,
+  "total_flos": 492029198991360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null