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:ebb2ccc24c2bf2a308b6a5fd2e6ba701ef21a964432e8a0ac42ee97b75fb30e4
+oid sha256:1ab7774cb1d61701c958ffed9d1a0170b3667c0268d1c47bae5213a129cd41dd
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa25fb8523b575c9a9f345630d25bbd60ed2d459bed242e4e2c3dd1a76892445
+oid sha256:42cdf57f88294312d1a72ec0172504f7ecefda9ad0bf3faf993ea39db1998ec1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fac8dc3559aa6a81370bb141163d5dc06aeeb8795a754c1c7ff70e9049a5afd
+oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
 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": 0.004246284501061571,
+  "epoch": 0.008492569002123142,
   "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": 8.987,
       "eval_steps_per_second": 4.494,
       "step": 3
+    },
+    {
+      "epoch": 0.005661712668082095,
+      "grad_norm": 0.3250284194946289,
+      "learning_rate": 8e-05,
+      "loss": 6.2793,
+      "step": 4
+    },
+    {
+      "epoch": 0.007077140835102618,
+      "grad_norm": 0.39584881067276,
+      "learning_rate": 0.0001,
+      "loss": 6.1844,
+      "step": 5
+    },
+    {
+      "epoch": 0.008492569002123142,
+      "grad_norm": 0.46705353260040283,
+      "learning_rate": 0.00012,
+      "loss": 6.5416,
+      "step": 6
+    },
+    {
+      "epoch": 0.008492569002123142,
+      "eval_loss": 1.5393693447113037,
+      "eval_runtime": 33.188,
+      "eval_samples_per_second": 8.979,
+      "eval_steps_per_second": 4.49,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899734583214080.0,
+  "total_flos": 3799469166428160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null