Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e994efb89cd80579f66f7f5871b40ae99e52484522d525feb5f4fac73228c3f
+oid sha256:597b3719171309cb2eaca5c9bc8be2163e1fa5b3ef34d384323ee3742c86af79
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c310e1566bb354267c99b077019d72d8cee92fcd6b2efef9453a0bb00828a33
+oid sha256:e812917aa5966e1d0b98b636f937c1ca891f65e516cf0f032d43ab9d7ec08da2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 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": 8.389965601141036e-05,
+  "epoch": 0.00016779931202282072,
   "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": 31.713,
       "eval_steps_per_second": 15.857,
       "step": 3
+    },
+    {
+      "epoch": 0.00011186620801521381,
+      "grad_norm": 0.5257006287574768,
+      "learning_rate": 8e-05,
+      "loss": 1.5193,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013983276001901726,
+      "grad_norm": 0.6386916041374207,
+      "learning_rate": 0.0001,
+      "loss": 1.5173,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016779931202282072,
+      "grad_norm": 0.7082046270370483,
+      "learning_rate": 0.00012,
+      "loss": 1.5421,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016779931202282072,
+      "eval_loss": 1.4413247108459473,
+      "eval_runtime": 474.1367,
+      "eval_samples_per_second": 31.755,
+      "eval_steps_per_second": 15.877,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 494346877009920.0,
+  "total_flos": 988693754019840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null