Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ea8f8c8eff114ea3233d2e67ff8d80c2ad0a57b0e4b37bc7074818a602ec8d
+oid sha256:f2d8e89073a24aa437ab053eec4b503bdc8990c6d9962e29bb74cfcb2f843bfc
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf499c072084c2341dfa8602e7474fc600a56fc835d277c955f4f54bd7384596
+oid sha256:e55af459c88a066d68a839cd62134908c3c2457dc37bde48728438e5165e7770
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed745fbc2286559d345cf5959b3e77a9c2b80395b42cf140b29bbcb6af79de6
+oid sha256:6cdaf8c69858d18dc44a05637dae968a115d8603c38f7640f3a45a768dfa5dec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024524831391784182,
+  "epoch": 0.049049662783568364,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 12.1632,
       "step": 9
+    },
+    {
+      "epoch": 0.029429797670141016,
+      "grad_norm": 3.8764777183532715,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 12.0141,
+      "step": 12
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "grad_norm": 3.6703200340270996,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.5903,
+      "step": 15
+    },
+    {
+      "epoch": 0.03923973022685469,
+      "eval_loss": 2.826849937438965,
+      "eval_runtime": 2.4615,
+      "eval_samples_per_second": 69.876,
+      "eval_steps_per_second": 34.938,
+      "step": 16
+    },
+    {
+      "epoch": 0.04414469650521153,
+      "grad_norm": 3.994386672973633,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.7024,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 56044717867008.0,
+  "total_flos": 120711700021248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null