Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6bf3c217a67a65fc7bbef721c264cd8766ed3be946dcfbcb2899f69668b91e
+oid sha256:d174b3637de775d72604b2f466a7e2730c31f8bbe42288320db515c38494cafd
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2dddd3b5fcb52b2a50b908e5ba42d749de328c81ed452e72322304bc0948ad
+oid sha256:f4e5df9ecd18c0c5d4aee7cd4c5038c63f72caeac62b83817ba101e575cb0c0d
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4a3ee778160f42a22e93367025f5b4d76e7fc51b428625824d02549c0d97d5
+oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04449197860962567,
+  "epoch": 0.08898395721925134,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 28.184,
       "eval_steps_per_second": 14.121,
       "step": 13
+    },
+    {
+      "epoch": 0.047914438502673795,
+      "grad_norm": 0.8753724098205566,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9516,
+      "step": 14
+    },
+    {
+      "epoch": 0.051336898395721926,
+      "grad_norm": 0.8921568989753723,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.8387,
+      "step": 15
+    },
+    {
+      "epoch": 0.05475935828877005,
+      "grad_norm": 0.8636670708656311,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.8335,
+      "step": 16
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.7787020802497864,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.8278,
+      "step": 17
+    },
+    {
+      "epoch": 0.06160427807486631,
+      "grad_norm": 0.9087046980857849,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.8099,
+      "step": 18
+    },
+    {
+      "epoch": 0.06502673796791444,
+      "grad_norm": 0.7061587572097778,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.6824,
+      "step": 19
+    },
+    {
+      "epoch": 0.06844919786096257,
+      "grad_norm": 0.8060164451599121,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7852,
+      "step": 20
+    },
+    {
+      "epoch": 0.07187165775401069,
+      "grad_norm": 0.8172853589057922,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.6113,
+      "step": 21
+    },
+    {
+      "epoch": 0.07529411764705882,
+      "grad_norm": 1.1956216096878052,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.959,
+      "step": 22
+    },
+    {
+      "epoch": 0.07871657754010696,
+      "grad_norm": 0.8757884502410889,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.8671,
+      "step": 23
+    },
+    {
+      "epoch": 0.08213903743315508,
+      "grad_norm": 0.8951571583747864,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.5991,
+      "step": 24
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 1.3083561658859253,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9128,
+      "step": 25
+    },
+    {
+      "epoch": 0.08898395721925134,
+      "grad_norm": 0.9369482398033142,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5134,
+      "step": 26
+    },
+    {
+      "epoch": 0.08898395721925134,
+      "eval_loss": 0.6822815537452698,
+      "eval_runtime": 17.4703,
+      "eval_samples_per_second": 28.219,
+      "eval_steps_per_second": 14.138,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3748962364293120.0,
+  "total_flos": 7497924728586240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null