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:ca54dff7b11a5c1072bcaa4d00c6cd636e78f6c075739710b4e3c7d28e6a398b
+oid sha256:3093ef7158b1bad6f89b97833dce5215132082e48c6f46f7a9faa4ed62df4180
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9104d59f0693dfd7e87ed440eb48ed9377bb5b20e205207a3498abc2ba6d663
+oid sha256:8ec6f52b77d972b31db4926239c97abf4b9f2e4a8622c4af27e54f8032f3b5ae
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c682b407b21541d71a29dc7003999c781bae916db960904cb9bf02cf91709a8b
+oid sha256:52355d530a9ba3c18873a09f4ff948fbf5a3c45f4e36f78fd66ecd368202fbdf
 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": 0.0016355287161099578,
+  "epoch": 0.0032710574322199156,
   "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": 7.059,
       "eval_steps_per_second": 3.531,
       "step": 10
+    },
+    {
+      "epoch": 0.0018871485185884128,
+      "grad_norm": 0.7861143350601196,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.8466,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025161980247845506,
+      "grad_norm": 0.4665175974369049,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7658,
+      "step": 20
+    },
+    {
+      "epoch": 0.0025161980247845506,
+      "eval_loss": 0.8983107805252075,
+      "eval_runtime": 473.2366,
+      "eval_samples_per_second": 7.073,
+      "eval_steps_per_second": 3.537,
+      "step": 20
+    },
+    {
+      "epoch": 0.003145247530980688,
+      "grad_norm": 0.6117036938667297,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8343,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3652889390088192.0,
+  "total_flos": 7352017886380032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null