Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4adcd0cffc35060cf9e42119642903104b91de094881d6eacc453ddee75c075
+oid sha256:602013ae87516812205f0ff9a7f72b136876fd4928114777f8049f7b9aec5d98
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1a8897859dc96238ddfb2a81eba57c602ea4755afe4f9c890c9ed98614f9fa
+oid sha256:4f9feed44f4cb2419614ccf223f5ac83b625a148c67b92e9b20111e9f28c32b1
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e33e75154a5b9937516cf6faaef89728f3828746b08c4b82a7e54d76694d767
+oid sha256:6a7eaefb7c8d3ff9aefbd8df87422c4e9c44a463b8ccfc3f0db11252f9faa01b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019777503090234856,
+  "epoch": 0.03955500618046971,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.77,
       "eval_steps_per_second": 1.385,
       "step": 5
+    },
+    {
+      "epoch": 0.023733003708281828,
+      "grad_norm": 78.57897186279297,
+      "learning_rate": 6e-05,
+      "loss": 144.2249,
+      "step": 6
+    },
+    {
+      "epoch": 0.0276885043263288,
+      "grad_norm": 94.01433563232422,
+      "learning_rate": 7e-05,
+      "loss": 131.2312,
+      "step": 7
+    },
+    {
+      "epoch": 0.031644004944375775,
+      "grad_norm": 93.0120620727539,
+      "learning_rate": 8e-05,
+      "loss": 114.7555,
+      "step": 8
+    },
+    {
+      "epoch": 0.035599505562422744,
+      "grad_norm": 103.75362396240234,
+      "learning_rate": 9e-05,
+      "loss": 117.9606,
+      "step": 9
+    },
+    {
+      "epoch": 0.03955500618046971,
+      "grad_norm": 101.03894805908203,
+      "learning_rate": 0.0001,
+      "loss": 109.0838,
+      "step": 10
+    },
+    {
+      "epoch": 0.03955500618046971,
+      "eval_loss": 3.0349903106689453,
+      "eval_runtime": 307.556,
+      "eval_samples_per_second": 2.77,
+      "eval_steps_per_second": 1.385,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.227665615224832e+16,
+  "total_flos": 1.0455331230449664e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null