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:b379a89108bfea261b8c5b40f2e49d828297e570458e0c3bbb02d55b92fda1cf
+oid sha256:3b77ab7cd69b55ace93a9356100711a8dfd9575d6938ab2c5f85ef9af1ef490e
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f85e7a99d8ab69bfb16b81bd980168c63b81a3c6f318002923552cb48d287b4
+oid sha256:1e5ed5ed976375e59a4bf3965bb8cf4b9920430e85458e13a72daef17ae7ea92
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702a344e17a212831b89fea87f60fdc4faad5fb3a254785a9d18a6464fba8380
+oid sha256:1473756068390812fdf419e99ba029eb15e6d51d9ff05c81c9ce7588fca7349c
 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": 0.00012084105373398856,
+  "epoch": 0.00024168210746797713,
   "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": 28.434,
       "eval_steps_per_second": 14.217,
       "step": 3
+    },
+    {
+      "epoch": 0.0001611214049786514,
+      "grad_norm": 2.364299774169922,
+      "learning_rate": 8e-05,
+      "loss": 1.3598,
+      "step": 4
+    },
+    {
+      "epoch": 0.00020140175622331428,
+      "grad_norm": 2.242465019226074,
+      "learning_rate": 0.0001,
+      "loss": 1.1288,
+      "step": 5
+    },
+    {
+      "epoch": 0.00024168210746797713,
+      "grad_norm": 2.6861603260040283,
+      "learning_rate": 0.00012,
+      "loss": 1.2543,
+      "step": 6
+    },
+    {
+      "epoch": 0.00024168210746797713,
+      "eval_loss": 1.0420364141464233,
+      "eval_runtime": 368.0677,
+      "eval_samples_per_second": 28.402,
+      "eval_steps_per_second": 14.201,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 573327424880640.0,
+  "total_flos": 1146654849761280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null