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:fa407374750dbe06ea2b4be8dae0b6ebdcde965d24dd2c89ecf159dd94d6cd8b
+oid sha256:961161834d2a7e538f5f2105c26ccd5c33f54f3a44183926c84f95b435bc7d03
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b048ba8845797b948227c2cefe06f7b1a804d9e82638fd19ff5220b837582674
+oid sha256:139dc9495b911d5b50addc02efc4f0d294a19b6fa55087fcf946d5d51a32e600
 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": 0.007855874910299505,
+  "epoch": 0.01571174982059901,
   "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": 35.705,
       "eval_steps_per_second": 17.859,
       "step": 13
+    },
+    {
+      "epoch": 0.008460172980322544,
+      "grad_norm": 0.7668046355247498,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.9344,
+      "step": 14
+    },
+    {
+      "epoch": 0.009064471050345583,
+      "grad_norm": 0.8007228374481201,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.8764,
+      "step": 15
+    },
+    {
+      "epoch": 0.009668769120368622,
+      "grad_norm": 0.6990913152694702,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 2.4552,
+      "step": 16
+    },
+    {
+      "epoch": 0.010273067190391661,
+      "grad_norm": 0.6952396035194397,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 2.5646,
+      "step": 17
+    },
+    {
+      "epoch": 0.0108773652604147,
+      "grad_norm": 0.7194958925247192,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.2515,
+      "step": 18
+    },
+    {
+      "epoch": 0.01148166333043774,
+      "grad_norm": 0.7544381618499756,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 2.5523,
+      "step": 19
+    },
+    {
+      "epoch": 0.012085961400460777,
+      "grad_norm": 0.7936828136444092,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.4444,
+      "step": 20
+    },
+    {
+      "epoch": 0.012690259470483816,
+      "grad_norm": 0.7764612436294556,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.3171,
+      "step": 21
+    },
+    {
+      "epoch": 0.013294557540506855,
+      "grad_norm": 0.9252168536186218,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.5806,
+      "step": 22
+    },
+    {
+      "epoch": 0.013898855610529894,
+      "grad_norm": 0.8082977533340454,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 2.2255,
+      "step": 23
+    },
+    {
+      "epoch": 0.014503153680552933,
+      "grad_norm": 0.8068621158599854,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.1052,
+      "step": 24
+    },
+    {
+      "epoch": 0.015107451750575972,
+      "grad_norm": 0.876987874507904,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0828,
+      "step": 25
+    },
+    {
+      "epoch": 0.01571174982059901,
+      "grad_norm": 0.9265044331550598,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1888,
+      "step": 26
+    },
+    {
+      "epoch": 0.01571174982059901,
+      "eval_loss": 2.1405892372131348,
+      "eval_runtime": 77.9878,
+      "eval_samples_per_second": 35.736,
+      "eval_steps_per_second": 17.875,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1937056915718144e+16,
+  "total_flos": 2.3482020721065984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null