Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cb06c5c955207835cedd82dce3640a5af2c5465d203d0d5b267bdbeeabfbd7
+oid sha256:a7f20fbe590b00fd8eec3a3e977b7c5d6da1a1c909c896ddf1daee8c6cddb73c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6636d0399eaf78c9e41ae7842cd50d214b5883c216dfd5e48ed477a00a600f74
+oid sha256:ca8c7a89cf7ce1b0543d2a3b8d05c43777516dca35e76407e543ba45eed30e0c
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ffdcc5b1832c3e16f0bb82387dbece1778f0e28b9e9cbbe1b2e93e16bd6563
+oid sha256:4c03a033002c6e670c54b6b2ad460f1e0d728c01554c2bf50e8c65b929cb21ba
 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": 0.09942828734775043,
+  "epoch": 0.14914243102162567,
   "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": 3.955,
       "eval_steps_per_second": 1.977,
       "step": 50
+    },
+    {
+      "epoch": 0.10141685309470544,
+      "grad_norm": 2.9934873580932617,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3562,
+      "step": 51
+    },
+    {
+      "epoch": 0.10340541884166045,
+      "grad_norm": 5.5525593757629395,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.5301,
+      "step": 52
+    },
+    {
+      "epoch": 0.10539398458861546,
+      "grad_norm": 5.065361976623535,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.4447,
+      "step": 53
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 1.780224084854126,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3119,
+      "step": 54
+    },
+    {
+      "epoch": 0.10937111608252548,
+      "grad_norm": 3.8235836029052734,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4389,
+      "step": 55
+    },
+    {
+      "epoch": 0.11135968182948049,
+      "grad_norm": 1.9305553436279297,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.3498,
+      "step": 56
+    },
+    {
+      "epoch": 0.1133482475764355,
+      "grad_norm": 2.445384979248047,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.373,
+      "step": 57
+    },
+    {
+      "epoch": 0.1153368133233905,
+      "grad_norm": 2.479538917541504,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.379,
+      "step": 58
+    },
+    {
+      "epoch": 0.11732537907034551,
+      "grad_norm": 1.6293305158615112,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3281,
+      "step": 59
+    },
+    {
+      "epoch": 0.11931394481730052,
+      "grad_norm": 6.382621765136719,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.598,
+      "step": 60
+    },
+    {
+      "epoch": 0.12130251056425553,
+      "grad_norm": 1.330427885055542,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.3423,
+      "step": 61
+    },
+    {
+      "epoch": 0.12329107631121054,
+      "grad_norm": 1.5774134397506714,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.3544,
+      "step": 62
+    },
+    {
+      "epoch": 0.12527964205816555,
+      "grad_norm": 7.6486663818359375,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4753,
+      "step": 63
+    },
+    {
+      "epoch": 0.12726820780512055,
+      "grad_norm": 2.3662033081054688,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.3504,
+      "step": 64
+    },
+    {
+      "epoch": 0.12925677355207557,
+      "grad_norm": 1.8204327821731567,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.3515,
+      "step": 65
+    },
+    {
+      "epoch": 0.13124533929903057,
+      "grad_norm": 3.0716800689697266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3567,
+      "step": 66
+    },
+    {
+      "epoch": 0.1332339050459856,
+      "grad_norm": 4.364616394042969,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4377,
+      "step": 67
+    },
+    {
+      "epoch": 0.13522247079294059,
+      "grad_norm": 2.386531352996826,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.385,
+      "step": 68
+    },
+    {
+      "epoch": 0.1372110365398956,
+      "grad_norm": 2.996636390686035,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3809,
+      "step": 69
+    },
+    {
+      "epoch": 0.1391996022868506,
+      "grad_norm": 1.0868910551071167,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.3454,
+      "step": 70
+    },
+    {
+      "epoch": 0.14118816803380563,
+      "grad_norm": 3.6063108444213867,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.3435,
+      "step": 71
+    },
+    {
+      "epoch": 0.14317673378076062,
+      "grad_norm": 1.1441456079483032,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3604,
+      "step": 72
+    },
+    {
+      "epoch": 0.14516529952771565,
+      "grad_norm": 1.0978187322616577,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.3533,
+      "step": 73
+    },
+    {
+      "epoch": 0.14715386527467064,
+      "grad_norm": 0.8434990644454956,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.3439,
+      "step": 74
+    },
+    {
+      "epoch": 0.14914243102162567,
+      "grad_norm": 2.072181463241577,
+      "learning_rate": 0.0,
+      "loss": 0.3765,
+      "step": 75
+    },
+    {
+      "epoch": 0.14914243102162567,
+      "eval_loss": 0.3585718274116516,
+      "eval_runtime": 107.5295,
+      "eval_samples_per_second": 3.943,
+      "eval_steps_per_second": 1.972,
+      "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": 7.46010452164608e+16,
+  "total_flos": 1.119015678246912e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null