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:ddfe50bf09ba7871c44c7569e4941e75f21a85ba1e58e7892b025b4879963648
+oid sha256:d6e6e4e0c78085870f137fa0e5ff7d4bec55d1da745a93f8e2efffc408a66a95
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d0bb1bb9d5e00c1f564273bbf8e3ed21b2bfc59d8d84c406fad1c3011df4ea
+oid sha256:546a722907e232b88241287b5e97f1c9798542e1209f200daff0c42ebbb18dce
 size 127788180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a723cd15ad28bfdf1cba1cdefc053bca4108604fab148ca67a5671058ac8619
+oid sha256:c228b076b37c853548d34d0925740557e4fb7ff11d3cd9ec6f7b1f2b73899252
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4606211d79ec6e5c1b89b795b8f2363b0df0cb5249a5fadbeaa18d83976cad2
+oid sha256:c741a6ed6a336d3663e787f24df3773f55bf618c77403a4fccbb85aedbd11613
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a889341800fb9f1148c1c11c468fb69ebc66bb9e273710379737e48c96cb24
+oid sha256:06a135df0eb732e593f9c74befa41ae4526130d5d5362d161ec6a8094454d314
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca161f798089058e4f915ccd540bcd6d56917a28ef305d7e1c9b92574113137d
+oid sha256:18adbf267d2d28fc254cefa2939b1685ca9dc60c07f8e86aa923ec7e6ef08d9e
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202e9e072e98b7f812cf9150d83609c0e49cf1c63203a21bf29da80b6cb9833f
+oid sha256:dace29708dd5b17bc7ddcf8235f57a65322a3712963b4aebf0a2a6497f44fe15
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d296531b776444e796fda47250fdc6e78f0b6f5c56f2bc0a966950f5617d682
+oid sha256:3608bbbeb9341c3d1d095ea76a13e9264ae99d576979fbe6887ebb174f488043
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4baa7df823a184c4b5a0d265324c9c4cda707659f3fd8c5d474f5e2da08a0557
+oid sha256:06798e2ca8b6a26d48bcde8e56566edba28782eaf2442b4a9f40c4baefc6f6ee
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44206975f461b78b0afef8702ce47f6dacaa40e59ae9df8b34fc36ffd8e87135
+oid sha256:ba1831c4c1812a87d4aa1f026ba3d190ef16316cad9fbddeadc67b41a9d3e0fd
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001965923984272608,
+  "epoch": 0.003931847968545216,
   "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": 24.44,
       "eval_steps_per_second": 3.061,
       "step": 3
+    },
+    {
+      "epoch": 0.002621231979030144,
+      "grad_norm": 0.14074499905109406,
+      "learning_rate": 6e-05,
+      "loss": 0.6186,
+      "step": 4
+    },
+    {
+      "epoch": 0.00327653997378768,
+      "grad_norm": 0.1980854570865631,
+      "learning_rate": 8e-05,
+      "loss": 0.5757,
+      "step": 5
+    },
+    {
+      "epoch": 0.003931847968545216,
+      "grad_norm": 0.21592412889003754,
+      "learning_rate": 0.0001,
+      "loss": 0.5379,
+      "step": 6
+    },
+    {
+      "epoch": 0.003931847968545216,
+      "eval_loss": 0.8669220209121704,
+      "eval_runtime": 105.2477,
+      "eval_samples_per_second": 24.428,
+      "eval_steps_per_second": 3.059,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.053742363299021e+16,
+  "total_flos": 6.107484726598042e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null