Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d6edeefc5e39b52b62387edba6ef071a4f89f1db5efa493654f7648a8cf166
+oid sha256:ead136bbf9b65dca7b1c78813f2fe22665ec908ddc047e684b2d2e4777a70e9f
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15f159c27281d7fcf3ce0f96593576e1cc66aa55eb22fcfb9758cd28f0f4e8f
+oid sha256:d372bbd3f56d3335d7dd2bce3cba1adcc2cbbdb04dc132eb0477cdbabe38a806
 size 591203178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+oid sha256:7682299c566684ea51cf26f0c86b6ffaa3c0bc63cbdf84674b29a2c62ac72143
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721fbab3fb8bec5f97cdbed7b104a2d545aa7387136ca9cabeed23ace817187d
+oid sha256:ec7445dd881aa0e896fdc6ef61cf9c541f4299feaa6850ba7cac238afd6649f3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.6722689075630255,
+  "epoch": 10.0,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -304,6 +304,154 @@
       "eval_samples_per_second": 11.93,
       "eval_steps_per_second": 11.93,
       "step": 200
+    },
+    {
+      "epoch": 6.840336134453781,
+      "grad_norm": 0.30396485328674316,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0185,
+      "step": 205
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.3928929269313812,
+      "learning_rate": 2.5505514088095655e-05,
+      "loss": 0.0184,
+      "step": 210
+    },
+    {
+      "epoch": 7.168067226890757,
+      "grad_norm": 0.22996097803115845,
+      "learning_rate": 2.3012467102424373e-05,
+      "loss": 0.0121,
+      "step": 215
+    },
+    {
+      "epoch": 7.336134453781512,
+      "grad_norm": 0.19302956759929657,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0122,
+      "step": 220
+    },
+    {
+      "epoch": 7.504201680672269,
+      "grad_norm": 0.1985304355621338,
+      "learning_rate": 1.8308451630064484e-05,
+      "loss": 0.0134,
+      "step": 225
+    },
+    {
+      "epoch": 7.6722689075630255,
+      "grad_norm": 0.13862721621990204,
+      "learning_rate": 1.611340004271339e-05,
+      "loss": 0.0123,
+      "step": 230
+    },
+    {
+      "epoch": 7.840336134453781,
+      "grad_norm": 0.1474885195493698,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0117,
+      "step": 235
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.28437599539756775,
+      "learning_rate": 1.2074320832556556e-05,
+      "loss": 0.0113,
+      "step": 240
+    },
+    {
+      "epoch": 8.168067226890756,
+      "grad_norm": 0.12733525037765503,
+      "learning_rate": 1.0243960175257606e-05,
+      "loss": 0.0096,
+      "step": 245
+    },
+    {
+      "epoch": 8.336134453781513,
+      "grad_norm": 0.17934471368789673,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0098,
+      "step": 250
+    },
+    {
+      "epoch": 8.504201680672269,
+      "grad_norm": 0.20203900337219238,
+      "learning_rate": 6.992542605231739e-06,
+      "loss": 0.0097,
+      "step": 255
+    },
+    {
+      "epoch": 8.672268907563025,
+      "grad_norm": 0.14116302132606506,
+      "learning_rate": 5.582487460349805e-06,
+      "loss": 0.0099,
+      "step": 260
+    },
+    {
+      "epoch": 8.840336134453782,
+      "grad_norm": 0.17721185088157654,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0095,
+      "step": 265
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.14386144280433655,
+      "learning_rate": 3.2175242080234313e-06,
+      "loss": 0.0092,
+      "step": 270
+    },
+    {
+      "epoch": 9.168067226890756,
+      "grad_norm": 0.13240846991539001,
+      "learning_rate": 2.2706183876134045e-06,
+      "loss": 0.0083,
+      "step": 275
+    },
+    {
+      "epoch": 9.336134453781513,
+      "grad_norm": 0.12592285871505737,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0092,
+      "step": 280
+    },
+    {
+      "epoch": 9.504201680672269,
+      "grad_norm": 0.10958818346261978,
+      "learning_rate": 8.639676646793382e-07,
+      "loss": 0.0076,
+      "step": 285
+    },
+    {
+      "epoch": 9.672268907563025,
+      "grad_norm": 0.11822710186243057,
+      "learning_rate": 4.089824229369155e-07,
+      "loss": 0.0093,
+      "step": 290
+    },
+    {
+      "epoch": 9.840336134453782,
+      "grad_norm": 0.14177332818508148,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0087,
+      "step": 295
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.15116795897483826,
+      "learning_rate": 3.384599811889766e-09,
+      "loss": 0.0095,
+      "step": 300
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.1007455587387085,
+      "eval_runtime": 1.6871,
+      "eval_samples_per_second": 11.855,
+      "eval_steps_per_second": 11.855,
+      "step": 300
     }
   ],
   "logging_steps": 5,
@@ -318,12 +466,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.5938794643456e+16,
+  "total_flos": 3.884520534294528e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null