Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b54fc91b032adc0421ef275ef0827c315d221b1802a0245379cda6d97b75ee8
+oid sha256:5a05881bdf1012a256a250f440385ff6dbbfeb9c5f9ecbf954b0685d225f8bd9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36098ff8e16073afb6fb615c579b2825b0eaf6e017971891af5be8dcace1a72
+oid sha256:1a492ffd04f250ed7fd7b8366c097f86fdf996578ac8200fe4f9565e9200878d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648f45a51dce8568f52ab42a351156301c6415ad9c2a6dd729805890675d7412
+oid sha256:fc97e939198cbd2f5b1143080e8f0a9955c4dbcdf2c270e350d18b8c6745a5e0
 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": 0.002675513698630137,
+  "epoch": 0.004013270547945206,
   "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": 7.289,
       "eval_steps_per_second": 3.645,
       "step": 50
+    },
+    {
+      "epoch": 0.00272902397260274,
+      "grad_norm": 3.2952077388763428,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 7.3355,
+      "step": 51
+    },
+    {
+      "epoch": 0.0027825342465753423,
+      "grad_norm": 3.3396549224853516,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 6.6649,
+      "step": 52
+    },
+    {
+      "epoch": 0.0028360445205479453,
+      "grad_norm": 4.649153232574463,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 8.7628,
+      "step": 53
+    },
+    {
+      "epoch": 0.002889554794520548,
+      "grad_norm": 3.6606626510620117,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.8996,
+      "step": 54
+    },
+    {
+      "epoch": 0.0029430650684931507,
+      "grad_norm": 3.4278030395507812,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 7.3124,
+      "step": 55
+    },
+    {
+      "epoch": 0.0029965753424657533,
+      "grad_norm": 3.267777681350708,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 6.8136,
+      "step": 56
+    },
+    {
+      "epoch": 0.003050085616438356,
+      "grad_norm": 3.700079917907715,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.78,
+      "step": 57
+    },
+    {
+      "epoch": 0.0031035958904109587,
+      "grad_norm": 3.482595682144165,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 7.8277,
+      "step": 58
+    },
+    {
+      "epoch": 0.0031571061643835617,
+      "grad_norm": 3.9059576988220215,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.7461,
+      "step": 59
+    },
+    {
+      "epoch": 0.003210616438356164,
+      "grad_norm": 3.3149898052215576,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.1818,
+      "step": 60
+    },
+    {
+      "epoch": 0.003264126712328767,
+      "grad_norm": 2.8718600273132324,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 6.8146,
+      "step": 61
+    },
+    {
+      "epoch": 0.0033176369863013697,
+      "grad_norm": 3.4928603172302246,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 5.8661,
+      "step": 62
+    },
+    {
+      "epoch": 0.0033711472602739726,
+      "grad_norm": 3.289541482925415,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.6667,
+      "step": 63
+    },
+    {
+      "epoch": 0.003424657534246575,
+      "grad_norm": 3.2029364109039307,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 7.2747,
+      "step": 64
+    },
+    {
+      "epoch": 0.003478167808219178,
+      "grad_norm": 3.1482632160186768,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 7.4577,
+      "step": 65
+    },
+    {
+      "epoch": 0.0035316780821917806,
+      "grad_norm": 3.4329683780670166,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.6697,
+      "step": 66
+    },
+    {
+      "epoch": 0.0035851883561643836,
+      "grad_norm": 3.0778117179870605,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 7.5335,
+      "step": 67
+    },
+    {
+      "epoch": 0.003638698630136986,
+      "grad_norm": 3.8979506492614746,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 8.1609,
+      "step": 68
+    },
+    {
+      "epoch": 0.003692208904109589,
+      "grad_norm": 3.739900588989258,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 7.5071,
+      "step": 69
+    },
+    {
+      "epoch": 0.0037457191780821916,
+      "grad_norm": 3.5693302154541016,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 6.7223,
+      "step": 70
+    },
+    {
+      "epoch": 0.0037992294520547945,
+      "grad_norm": 4.022164821624756,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 7.1291,
+      "step": 71
+    },
+    {
+      "epoch": 0.003852739726027397,
+      "grad_norm": 3.5596697330474854,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.016,
+      "step": 72
+    },
+    {
+      "epoch": 0.00390625,
+      "grad_norm": 4.030635356903076,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 7.129,
+      "step": 73
+    },
+    {
+      "epoch": 0.003959760273972603,
+      "grad_norm": 2.96244740486145,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 6.2029,
+      "step": 74
+    },
+    {
+      "epoch": 0.004013270547945206,
+      "grad_norm": 3.192884683609009,
+      "learning_rate": 0.0,
+      "loss": 6.3423,
+      "step": 75
+    },
+    {
+      "epoch": 0.004013270547945206,
+      "eval_loss": 0.8689998984336853,
+      "eval_runtime": 2162.9086,
+      "eval_samples_per_second": 7.276,
+      "eval_steps_per_second": 3.638,
+      "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": 9.80187302854656e+16,
+  "total_flos": 1.442508980701102e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null