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:ddb862e4ff64ec4c23d818718ccd0f23c4f3b8fdb6877c3b4621e8031a24ca67
+oid sha256:2e394a046cee7ed331342927da84217c15ec393b0856ea7874da286101ed937d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4df3b702ecbb5f8d974dfa090c656b1eb36f8c498d34a5cc6f5c04b61d3163
+oid sha256:171a8f3032784f1965d01c46c25ba9bbd35a4525643787bc38f3e61af993208d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c731633bb2fd79a89aed1598c1c0b92ad1d2a7d2b9e08e485fa564f203a1372
+oid sha256:2c4d27121fab067bc2de3268a7564a068ae9e664d1d190e48cc49eafb04fd334
 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": 0.00535475234270415,
+  "epoch": 0.0107095046854083,
   "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": 6.251,
       "eval_steps_per_second": 3.129,
       "step": 10
+    },
+    {
+      "epoch": 0.006178560395427865,
+      "grad_norm": 1.4204341173171997,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.2185,
+      "step": 15
+    },
+    {
+      "epoch": 0.008238080527237153,
+      "grad_norm": 1.414536476135254,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2792,
+      "step": 20
+    },
+    {
+      "epoch": 0.008238080527237153,
+      "eval_loss": 0.06111093610525131,
+      "eval_runtime": 164.1088,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 3.12,
+      "step": 20
+    },
+    {
+      "epoch": 0.010297600659046443,
+      "grad_norm": 1.4574953317642212,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.2166,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4120590768144384.0,
+  "total_flos": 8241181536288768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null