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:c762abe9038151e6d53cb10984c3db079075cfdfc059b429b0d916aa77f80170
+oid sha256:1711a0d72318b672a70c19d535b1fb6138361c95f07d71c57278c5ceb6da3588
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4960e64c55eee7c0a441a0781ba54fb1cdbe6c854f601223880c728d4d6ea822
+oid sha256:fa535dff21234cf20b9cbfd3454b638e02522bba421c5bbef25b7da07e583bf7
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f06e4e3501885e23eb91ccbc32fb470395776e1149f3e0c2bcce4afcffc46f7
+oid sha256:d09c38a9eb4786fc71c12622543a615c7037da9af86371f9b173f630a430f9b7
 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": 0.001264942128897603,
+  "epoch": 0.002529884257795206,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 11.259,
       "eval_steps_per_second": 1.409,
       "step": 5
+    },
+    {
+      "epoch": 0.0015179305546771235,
+      "grad_norm": 16.133859634399414,
+      "learning_rate": 6e-05,
+      "loss": 7.1644,
+      "step": 6
+    },
+    {
+      "epoch": 0.002276895832015685,
+      "grad_norm": 13.156013488769531,
+      "learning_rate": 9e-05,
+      "loss": 5.3902,
+      "step": 9
+    },
+    {
+      "epoch": 0.002529884257795206,
+      "eval_loss": 4.7294020652771,
+      "eval_runtime": 591.5744,
+      "eval_samples_per_second": 11.255,
+      "eval_steps_per_second": 1.408,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7816411317534720.0,
+  "total_flos": 1.563282263506944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null