Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f450d5ec238678dd53c81fa4760afc43aa1ffac31a2d444d17525b1dcc3c52cd
+oid sha256:c6b7224c96325fdb23a2226d1febe7c2c5c9b5c55b076eadc164126d96ef7df1
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a135c56bd4b58247709c2526b74e6a9391f2c7d0369c1ca7f306fd289ac187e
+oid sha256:d31b2fe81050c36ba30c6ac20a7091e3a16b90a8d8e9c5bb202fe93433602980
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22eafc848cda5c1757f4581f969ead3b635c07c9c3eee6774c9e5ff8cf8e1bbf
+oid sha256:911e72134441cd7a162f9396575524d703f25ba390bc65bdb98456ed840ba960
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030690537084398978,
+  "epoch": 0.04092071611253197,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 155.223,
       "eval_steps_per_second": 38.963,
       "step": 27
+    },
+    {
+      "epoch": 0.03410059676044331,
+      "grad_norm": 1.4229531288146973,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 44.0237,
+      "step": 30
+    },
+    {
+      "epoch": 0.03751065643648764,
+      "grad_norm": 1.3927640914916992,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 43.9566,
+      "step": 33
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "grad_norm": 1.352387547492981,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 43.9265,
+      "step": 36
+    },
+    {
+      "epoch": 0.04092071611253197,
+      "eval_loss": 10.977602005004883,
+      "eval_runtime": 4.7507,
+      "eval_samples_per_second": 155.978,
+      "eval_steps_per_second": 39.152,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 244061306880.0,
+  "total_flos": 318520688640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null