Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09ea6ce50093c41f2f5fb8b4e6414b0c577151e86f47fe18188690e6492eb39
+oid sha256:fb1045a6588100f77da2fc367c78dce331d79e23ec98420f4290693e5657de94
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ca64088c14fde06f9661cede8c9942fee2ff16eb48934cb42c77609210f140
+oid sha256:4f72f392d6528b4317aef9fefb0c2d13f84965b56617fbc00a465411e33a0ab1
 size 60386772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf99753320d5a922d21785c9acff8aad90fb47892dad1f221c94717bf3a04b1
+oid sha256:b8d87e9c1f179372f9242367ad770c30c7bd7eeb48af101c530d591d3c29dd85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21226719b9e25fe4304ec632d533e056eb568a7272feb0ef7163c162da3912fa
+oid sha256:b00c955337268a520a0035ea66591799a038b74d25acad9619f1a1a47155f3ce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012270691453463402,
+  "epoch": 0.015338364316829254,
   "eval_steps": 20,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,36 @@
       "eval_samples_per_second": 5.074,
       "eval_steps_per_second": 0.66,
       "step": 200
+    },
+    {
+      "epoch": 0.013497760598809742,
+      "grad_norm": 0.8630465269088745,
+      "learning_rate": 0.00019912051051296735,
+      "loss": 1.64,
+      "step": 220
+    },
+    {
+      "epoch": 0.013497760598809742,
+      "eval_loss": 1.5652003288269043,
+      "eval_runtime": 19.9102,
+      "eval_samples_per_second": 5.023,
+      "eval_steps_per_second": 0.653,
+      "step": 220
+    },
+    {
+      "epoch": 0.014724829744156084,
+      "grad_norm": 0.7266297936439514,
+      "learning_rate": 0.00019903869753742944,
+      "loss": 1.6705,
+      "step": 240
+    },
+    {
+      "epoch": 0.014724829744156084,
+      "eval_loss": 1.5418590307235718,
+      "eval_runtime": 19.7135,
+      "eval_samples_per_second": 5.073,
+      "eval_steps_per_second": 0.659,
+      "step": 240
     }
   ],
   "logging_steps": 20,
@@ -164,7 +194,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 1.25490630177792e+16,
+  "total_flos": 1.568681283999744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null