Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bd03dd513182e8db09d9fa1b8ec83a87d464fd5148a47ddccab17bc3c6fe90
+oid sha256:d5f17fa874a5de838861d15ae158a8b83d7079106f6c087926bf120de290261f
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcc55d6f922b5cc7d35e734ac5fd793151f9bc482b844f27500b5723dfa5d69
+oid sha256:de9626fff525ddfbf048282a33eca7a60e7b0acb104b386d1086aa42ca9267a1
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 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": 0.016817593790426907,
+  "epoch": 0.03363518758085381,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 144.431,
       "eval_steps_per_second": 72.215,
       "step": 10
+    },
+    {
+      "epoch": 0.019404915912031046,
+      "grad_norm": 0.009488558396697044,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.3807,
+      "step": 15
+    },
+    {
+      "epoch": 0.0258732212160414,
+      "grad_norm": 0.012411398813128471,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3786,
+      "step": 20
+    },
+    {
+      "epoch": 0.0258732212160414,
+      "eval_loss": 10.37958812713623,
+      "eval_runtime": 2.2895,
+      "eval_samples_per_second": 142.39,
+      "eval_steps_per_second": 71.195,
+      "step": 20
+    },
+    {
+      "epoch": 0.03234152652005175,
+      "grad_norm": 0.011458181776106358,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3788,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 336203612160.0,
+  "total_flos": 672407224320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null