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:f419290ce554dfd97cad9342e0c4958138ba78e34b1f7cd2b46e584b39bc671a
+oid sha256:026bcb141bbd9c2dacda3d05278a8a0a59f4da5842f584bb1ed176d2fae6f3f8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2588b164845f367ad8a9e2f3565ebf62aef372d96030d414b86de82714c9b5e2
+oid sha256:e8b3012336bbc59237b4804077c8cb2b56a46e57f25653858b6ca3a12ef9c078
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfaa76e23b5ee2e9cd9f372437b6e2eeffe609e58ae8d131d3303166f82dc47
+oid sha256:35678f2e164dea4ebbafdb4df13644ad3b9d103a7e957de1eef9bc9540a6bd78
 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": 0.0006124636349716736,
+  "epoch": 0.0012249272699433472,
   "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": 13.391,
       "eval_steps_per_second": 6.695,
       "step": 10
+    },
+    {
+      "epoch": 0.0007066888095827003,
+      "grad_norm": 1.8582125902175903,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.0211,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009422517461102671,
+      "grad_norm": 1.7657477855682373,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.9053,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009422517461102671,
+      "eval_loss": 1.795223593711853,
+      "eval_runtime": 667.8705,
+      "eval_samples_per_second": 13.383,
+      "eval_steps_per_second": 6.691,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011778146826378337,
+      "grad_norm": 1.6993805170059204,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6659,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2589389947404288.0,
+  "total_flos": 5225019001012224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null