Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746cb2a18d6d1f561bc3aff47b7aa22e3c682e3f2e4f762807089d6a6449cee2
+oid sha256:9339ac265e4e5acb74afd2f14e5d7538889f76e68e9728443988c0896d1fdb07
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783ace743b00db24851b4595cdf81cd62cd4c55c82088a2f436820a3d57cd7ef
+oid sha256:f81dcfd16243f5a7ec99dc53fa954776ce482af6cfe03098f02537d369e9e9ad
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047bd246ac1b276cbb1c42a59b852f224774db2a5ba632646833eafba7e996a8
+oid sha256:ea819ed76f7727bd45951b55dcca7d17137e32a2eac4731c6b283fda95326281
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18770530267480057,
+  "epoch": 0.28155795401220085,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 9.692,
       "eval_steps_per_second": 4.868,
       "step": 50
+    },
+    {
+      "epoch": 0.1914594087282966,
+      "grad_norm": 0.2194223254919052,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.006,
+      "step": 51
+    },
+    {
+      "epoch": 0.19521351478179258,
+      "grad_norm": 0.8518089056015015,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0223,
+      "step": 52
+    },
+    {
+      "epoch": 0.1989676208352886,
+      "grad_norm": 1.0204380750656128,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.027,
+      "step": 53
+    },
+    {
+      "epoch": 0.20272172688878462,
+      "grad_norm": 1.9320348501205444,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0502,
+      "step": 54
+    },
+    {
+      "epoch": 0.2064758329422806,
+      "grad_norm": 1.0254801511764526,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0232,
+      "step": 55
+    },
+    {
+      "epoch": 0.21022993899577663,
+      "grad_norm": 0.39294230937957764,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0112,
+      "step": 56
+    },
+    {
+      "epoch": 0.21398404504927265,
+      "grad_norm": 0.06195160001516342,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0033,
+      "step": 57
+    },
+    {
+      "epoch": 0.21773815110276865,
+      "grad_norm": 0.6369668841362,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.038,
+      "step": 58
+    },
+    {
+      "epoch": 0.22149225715626467,
+      "grad_norm": 0.4076542556285858,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0095,
+      "step": 59
+    },
+    {
+      "epoch": 0.22524636320976069,
+      "grad_norm": 0.6492363214492798,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0206,
+      "step": 60
+    },
+    {
+      "epoch": 0.22900046926325668,
+      "grad_norm": 0.630257248878479,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0199,
+      "step": 61
+    },
+    {
+      "epoch": 0.2327545753167527,
+      "grad_norm": 0.5601248145103455,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0139,
+      "step": 62
+    },
+    {
+      "epoch": 0.23650868137024872,
+      "grad_norm": 0.7685927152633667,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0222,
+      "step": 63
+    },
+    {
+      "epoch": 0.2402627874237447,
+      "grad_norm": 0.995885968208313,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0187,
+      "step": 64
+    },
+    {
+      "epoch": 0.24401689347724073,
+      "grad_norm": 0.505293071269989,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0163,
+      "step": 65
+    },
+    {
+      "epoch": 0.24777099953073675,
+      "grad_norm": 0.4831348955631256,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0372,
+      "step": 66
+    },
+    {
+      "epoch": 0.25152510558423274,
+      "grad_norm": 0.6265993118286133,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0232,
+      "step": 67
+    },
+    {
+      "epoch": 0.25527921163772876,
+      "grad_norm": 0.8600174188613892,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0164,
+      "step": 68
+    },
+    {
+      "epoch": 0.2590333176912248,
+      "grad_norm": 0.46614569425582886,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.022,
+      "step": 69
+    },
+    {
+      "epoch": 0.2627874237447208,
+      "grad_norm": 0.19857588410377502,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0041,
+      "step": 70
+    },
+    {
+      "epoch": 0.2665415297982168,
+      "grad_norm": 0.3438130021095276,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0181,
+      "step": 71
+    },
+    {
+      "epoch": 0.2702956358517128,
+      "grad_norm": 1.681471347808838,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0286,
+      "step": 72
+    },
+    {
+      "epoch": 0.2740497419052088,
+      "grad_norm": 0.05950739607214928,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0024,
+      "step": 73
+    },
+    {
+      "epoch": 0.27780384795870483,
+      "grad_norm": 0.18584494292736053,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0057,
+      "step": 74
+    },
+    {
+      "epoch": 0.28155795401220085,
+      "grad_norm": 0.41768908500671387,
+      "learning_rate": 0.0,
+      "loss": 0.0132,
+      "step": 75
+    },
+    {
+      "epoch": 0.28155795401220085,
+      "eval_loss": 0.022396452724933624,
+      "eval_runtime": 23.2271,
+      "eval_samples_per_second": 9.687,
+      "eval_steps_per_second": 4.865,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.99038693326848e+16,
+  "total_flos": 1.048558039990272e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null