Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f37ef39944e005a0cdaaaf0880b73609ef29f3a56957e8b1d5fe7745487f25
+oid sha256:188af341dcab673b3dc15725529c6fcaafeadb71a059ceedc74e75cf0f120776
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fb6b551666af67a667f6fed63048959a49575423b58556cc2b385d3e42cfb42
+oid sha256:0e5f736b3ffdc10592c59792ef439ef4e861775d5c1f68bfaa07cf312804eb26
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91963eadbc40670a98d15120d3356a5907c79c2001467d26be64e710331f4a8
+oid sha256:b51d9ae0875b04393be6dae46814772fdaaf8f8726dc39e7773be45bb868070e
 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": 0.004256994774538914,
+  "epoch": 0.006385492161808372,
   "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": 133.635,
       "eval_steps_per_second": 66.824,
       "step": 50
+    },
+    {
+      "epoch": 0.004342134670029692,
+      "grad_norm": 0.30174604058265686,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3665,
+      "step": 51
+    },
+    {
+      "epoch": 0.004427274565520471,
+      "grad_norm": 0.28722646832466125,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 10.3836,
+      "step": 52
+    },
+    {
+      "epoch": 0.004512414461011249,
+      "grad_norm": 0.26923665404319763,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 10.3838,
+      "step": 53
+    },
+    {
+      "epoch": 0.004597554356502028,
+      "grad_norm": 0.23828227818012238,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3684,
+      "step": 54
+    },
+    {
+      "epoch": 0.004682694251992805,
+      "grad_norm": 0.15467457473278046,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3714,
+      "step": 55
+    },
+    {
+      "epoch": 0.004767834147483584,
+      "grad_norm": 0.19631482660770416,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 10.3534,
+      "step": 56
+    },
+    {
+      "epoch": 0.004852974042974362,
+      "grad_norm": 0.14511145651340485,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3593,
+      "step": 57
+    },
+    {
+      "epoch": 0.004938113938465141,
+      "grad_norm": 0.15094733238220215,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 10.3621,
+      "step": 58
+    },
+    {
+      "epoch": 0.005023253833955919,
+      "grad_norm": 0.1429455578327179,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3636,
+      "step": 59
+    },
+    {
+      "epoch": 0.005108393729446697,
+      "grad_norm": 0.19595345854759216,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3623,
+      "step": 60
+    },
+    {
+      "epoch": 0.005193533624937475,
+      "grad_norm": 0.16804875433444977,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 10.3713,
+      "step": 61
+    },
+    {
+      "epoch": 0.005278673520428254,
+      "grad_norm": 0.18887090682983398,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 10.3459,
+      "step": 62
+    },
+    {
+      "epoch": 0.005363813415919032,
+      "grad_norm": 0.19332559406757355,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.364,
+      "step": 63
+    },
+    {
+      "epoch": 0.005448953311409811,
+      "grad_norm": 0.1675790250301361,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 10.3672,
+      "step": 64
+    },
+    {
+      "epoch": 0.005534093206900588,
+      "grad_norm": 0.1676328331232071,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 10.361,
+      "step": 65
+    },
+    {
+      "epoch": 0.005619233102391367,
+      "grad_norm": 0.1370442807674408,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3716,
+      "step": 66
+    },
+    {
+      "epoch": 0.005704372997882145,
+      "grad_norm": 0.19722534716129303,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3465,
+      "step": 67
+    },
+    {
+      "epoch": 0.0057895128933729235,
+      "grad_norm": 0.18959833681583405,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 10.3577,
+      "step": 68
+    },
+    {
+      "epoch": 0.005874652788863702,
+      "grad_norm": 0.17572325468063354,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.372,
+      "step": 69
+    },
+    {
+      "epoch": 0.0059597926843544795,
+      "grad_norm": 0.2337626963853836,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 10.346,
+      "step": 70
+    },
+    {
+      "epoch": 0.006044932579845258,
+      "grad_norm": 0.19222278892993927,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.363,
+      "step": 71
+    },
+    {
+      "epoch": 0.0061300724753360365,
+      "grad_norm": 0.1720466911792755,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3667,
+      "step": 72
+    },
+    {
+      "epoch": 0.006215212370826815,
+      "grad_norm": 0.15600402653217316,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 10.3616,
+      "step": 73
+    },
+    {
+      "epoch": 0.006300352266317593,
+      "grad_norm": 0.14834241569042206,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 10.3698,
+      "step": 74
+    },
+    {
+      "epoch": 0.006385492161808372,
+      "grad_norm": 0.16144375503063202,
+      "learning_rate": 0.0,
+      "loss": 10.374,
+      "step": 75
+    },
+    {
+      "epoch": 0.006385492161808372,
+      "eval_loss": 10.360559463500977,
+      "eval_runtime": 74.232,
+      "eval_samples_per_second": 133.244,
+      "eval_steps_per_second": 66.629,
+      "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": 5733592989696.0,
+  "total_flos": 8767452217344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null