Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2ef9980c4c4b052de1e67895a9bb0a643f1ab5a4a82ffa58691d5b2b2722f2
+oid sha256:ae134784f1ac2fc665cb9bb3babb6353a6ed06c55e341969b4e4b34fd85472db
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5f4ce8ea3c6c9b93f4242af9f205f1f1d3a31166ee4bc56df745948df5416a
+oid sha256:68aa9325e73d1d3b771d0e7b711b5f9c8c847aa0992b631c072df47d104b7a00
 size 41459700

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": 0.0351173391862232,
+  "epoch": 0.0702346783724464,
   "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": 29.097,
       "eval_steps_per_second": 14.549,
       "step": 13
+    },
+    {
+      "epoch": 0.03781867296977883,
+      "grad_norm": 0.21262897551059723,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.1952,
+      "step": 14
+    },
+    {
+      "epoch": 0.04052000675333446,
+      "grad_norm": 0.2228931188583374,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2496,
+      "step": 15
+    },
+    {
+      "epoch": 0.04322134053689009,
+      "grad_norm": 0.1923513263463974,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.3136,
+      "step": 16
+    },
+    {
+      "epoch": 0.04592267432044572,
+      "grad_norm": 0.19064629077911377,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 1.1784,
+      "step": 17
+    },
+    {
+      "epoch": 0.04862400810400135,
+      "grad_norm": 0.1903553009033203,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3337,
+      "step": 18
+    },
+    {
+      "epoch": 0.05132534188755698,
+      "grad_norm": 0.18997488915920258,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 1.1441,
+      "step": 19
+    },
+    {
+      "epoch": 0.05402667567111261,
+      "grad_norm": 0.2513015568256378,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.1431,
+      "step": 20
+    },
+    {
+      "epoch": 0.05672800945466824,
+      "grad_norm": 0.20887787640094757,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 1.1726,
+      "step": 21
+    },
+    {
+      "epoch": 0.059429343238223874,
+      "grad_norm": 0.22922278940677643,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2364,
+      "step": 22
+    },
+    {
+      "epoch": 0.062130677021779504,
+      "grad_norm": 0.2258031815290451,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 1.0899,
+      "step": 23
+    },
+    {
+      "epoch": 0.06483201080533513,
+      "grad_norm": 0.237678661942482,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.091,
+      "step": 24
+    },
+    {
+      "epoch": 0.06753334458889076,
+      "grad_norm": 0.22877460718154907,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.1396,
+      "step": 25
+    },
+    {
+      "epoch": 0.0702346783724464,
+      "grad_norm": 0.2620464563369751,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1179,
+      "step": 26
+    },
+    {
+      "epoch": 0.0702346783724464,
+      "eval_loss": 1.2547305822372437,
+      "eval_runtime": 21.5256,
+      "eval_samples_per_second": 28.989,
+      "eval_steps_per_second": 14.494,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4855972292919296e+16,
+  "total_flos": 3.006047179505664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null