Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325b2b894485530b2287933ab115bfbae5fe92df6c4e61958abe20ed1f3a76ae
+oid sha256:de869d995ec5d6d4a239aa4f5034ce2e007d6d43454be80f15e05a8a851896d2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abec5afcd1f089d05f8ec3f6f4d77925c7920cf0ec9b9f972533b9d696f45ac5
+oid sha256:77f2eceb5007b5510ee40c75cfcbf241bc33a1849fc3d32b39d4c02c39b6581d
 size 51244020

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": 0.03492863140218304,
+  "epoch": 0.06985726280436608,
   "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": 39.062,
       "eval_steps_per_second": 19.562,
       "step": 13
+    },
+    {
+      "epoch": 0.037615449202350965,
+      "grad_norm": 6.086618423461914,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.6493,
+      "step": 14
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "grad_norm": 7.451858043670654,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.6744,
+      "step": 15
+    },
+    {
+      "epoch": 0.04298908480268682,
+      "grad_norm": 6.979912757873535,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 3.4717,
+      "step": 16
+    },
+    {
+      "epoch": 0.04567590260285474,
+      "grad_norm": 7.578520774841309,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 3.2947,
+      "step": 17
+    },
+    {
+      "epoch": 0.04836272040302267,
+      "grad_norm": 8.897782325744629,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.2721,
+      "step": 18
+    },
+    {
+      "epoch": 0.051049538203190595,
+      "grad_norm": 7.789557456970215,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 3.0338,
+      "step": 19
+    },
+    {
+      "epoch": 0.05373635600335852,
+      "grad_norm": 8.348186492919922,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.9377,
+      "step": 20
+    },
+    {
+      "epoch": 0.05642317380352645,
+      "grad_norm": 9.296662330627441,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.9852,
+      "step": 21
+    },
+    {
+      "epoch": 0.05910999160369437,
+      "grad_norm": 8.833761215209961,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.8072,
+      "step": 22
+    },
+    {
+      "epoch": 0.0617968094038623,
+      "grad_norm": 8.135382652282715,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 2.5832,
+      "step": 23
+    },
+    {
+      "epoch": 0.06448362720403022,
+      "grad_norm": 7.976484298706055,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.44,
+      "step": 24
+    },
+    {
+      "epoch": 0.06717044500419815,
+      "grad_norm": 1.7394722700119019,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.4148,
+      "step": 25
+    },
+    {
+      "epoch": 0.06985726280436608,
+      "grad_norm": 1.333323359489441,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.3852,
+      "step": 26
+    },
+    {
+      "epoch": 0.06985726280436608,
+      "eval_loss": 2.4600071907043457,
+      "eval_runtime": 16.0246,
+      "eval_samples_per_second": 39.127,
+      "eval_steps_per_second": 19.595,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9937675364597760.0,
+  "total_flos": 1.987535072919552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null