Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee7894d4aca123e23ba91f91f7c665f60e2e515ea1b07fc759ba6921c3a4d39
+oid sha256:04ee1664bd29ace74cd834abf6756c1c6ad85e31fbf6b86e8e410e92077635c6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045b4d334a6dbdfb7e3597f9a65f037170ed834e1072d8e6ab5d53b64f7b359a
+oid sha256:b31db628080555eedcc22be53e02e0d4a14ffe0bf6a0862b41c6b5703441cc5a
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d585dc7c13382f351b584df6888cf4cf487689fda9286b06d48d18af07a1be
+oid sha256:866fac83e501a78c2e403a48d4ac843b9f01dc29bc6df7eeed2838bc1ca90679
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
+oid sha256:fbf1d1277664600b4e977089813b848af48515edea03c4bdcf1a506540fabd37
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13143483023001096,
+  "epoch": 0.1533406352683461,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 9.413,
       "eval_steps_per_second": 4.755,
       "step": 30
+    },
+    {
+      "epoch": 0.13581599123767799,
+      "grad_norm": 0.0801151692867279,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0121,
+      "step": 31
+    },
+    {
+      "epoch": 0.140197152245345,
+      "grad_norm": 0.050880130380392075,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0048,
+      "step": 32
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 0.12199495732784271,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0158,
+      "step": 33
+    },
+    {
+      "epoch": 0.14895947426067907,
+      "grad_norm": 0.04026995226740837,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.008,
+      "step": 34
+    },
+    {
+      "epoch": 0.1533406352683461,
+      "grad_norm": 0.054878607392311096,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0049,
+      "step": 35
+    },
+    {
+      "epoch": 0.1533406352683461,
+      "eval_loss": 0.015133237466216087,
+      "eval_runtime": 10.3131,
+      "eval_samples_per_second": 9.406,
+      "eval_steps_per_second": 4.751,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -292,7 +335,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.219477097775104e+16,
+  "total_flos": 2.589389947404288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null