Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6449d869a889422bd45e490658479cac07bbac74e192cf35619200772b822312
+oid sha256:1cbc530940d6c2df5b55e29d4ab95f0564af9dc46c43239982c6fd7ec8ee831e
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641b226c4bdb10a1f194faca483fbfad08534eb22188c410e2912fbb38e11c16
+oid sha256:e5a777ceddbe7d3237539c0eb8ae5a407386ad9929365b8965154c021ca8b2f9
 size 800394282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e7b25842a40c68c62230743f873fcd5131561f7e91ed4137fa3f9f0aeff4fc
+oid sha256:2b4e781b368eb5018b4757b50c9c5d62a21f25ba32812d340cebe277cbd458e4
 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": 0.04575611988103409,
+  "epoch": 0.06863417982155114,
   "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": 7.778,
       "eval_steps_per_second": 3.893,
       "step": 50
+    },
+    {
+      "epoch": 0.04667124227865477,
+      "grad_norm": 15.607521057128906,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9073,
+      "step": 51
+    },
+    {
+      "epoch": 0.04758636467627545,
+      "grad_norm": 14.263496398925781,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.6026,
+      "step": 52
+    },
+    {
+      "epoch": 0.048501487073896135,
+      "grad_norm": 7.130948066711426,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.4088,
+      "step": 53
+    },
+    {
+      "epoch": 0.04941660947151681,
+      "grad_norm": 8.556685447692871,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6188,
+      "step": 54
+    },
+    {
+      "epoch": 0.050331731869137496,
+      "grad_norm": 5.391532897949219,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.4404,
+      "step": 55
+    },
+    {
+      "epoch": 0.05124685426675818,
+      "grad_norm": 5.243240833282471,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.3264,
+      "step": 56
+    },
+    {
+      "epoch": 0.05216197666437886,
+      "grad_norm": 3.5227527618408203,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3415,
+      "step": 57
+    },
+    {
+      "epoch": 0.05307709906199954,
+      "grad_norm": 4.664560317993164,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.4925,
+      "step": 58
+    },
+    {
+      "epoch": 0.053992221459620224,
+      "grad_norm": 5.512412071228027,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.5046,
+      "step": 59
+    },
+    {
+      "epoch": 0.05490734385724091,
+      "grad_norm": 3.448622703552246,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.35,
+      "step": 60
+    },
+    {
+      "epoch": 0.055822466254861584,
+      "grad_norm": 2.99069881439209,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.3607,
+      "step": 61
+    },
+    {
+      "epoch": 0.05673758865248227,
+      "grad_norm": 4.074262619018555,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.4701,
+      "step": 62
+    },
+    {
+      "epoch": 0.05765271105010295,
+      "grad_norm": 5.847626686096191,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4466,
+      "step": 63
+    },
+    {
+      "epoch": 0.058567833447723636,
+      "grad_norm": 3.9188435077667236,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.4807,
+      "step": 64
+    },
+    {
+      "epoch": 0.05948295584534431,
+      "grad_norm": 4.037470817565918,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.3334,
+      "step": 65
+    },
+    {
+      "epoch": 0.060398078242964996,
+      "grad_norm": 7.9875712394714355,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6476,
+      "step": 66
+    },
+    {
+      "epoch": 0.06131320064058568,
+      "grad_norm": 2.264742612838745,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2031,
+      "step": 67
+    },
+    {
+      "epoch": 0.06222832303820636,
+      "grad_norm": 0.013100137002766132,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0001,
+      "step": 68
+    },
+    {
+      "epoch": 0.06314344543582705,
+      "grad_norm": 2.0209121704101562,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0288,
+      "step": 69
+    },
+    {
+      "epoch": 0.06405856783344772,
+      "grad_norm": 0.24793341755867004,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0045,
+      "step": 70
+    },
+    {
+      "epoch": 0.0649736902310684,
+      "grad_norm": 0.009124662727117538,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0001,
+      "step": 71
+    },
+    {
+      "epoch": 0.06588881262868909,
+      "grad_norm": 5.83003568649292,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1107,
+      "step": 72
+    },
+    {
+      "epoch": 0.06680393502630977,
+      "grad_norm": 2.5844852924346924,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0796,
+      "step": 73
+    },
+    {
+      "epoch": 0.06771905742393045,
+      "grad_norm": 1.5514365434646606,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.011,
+      "step": 74
+    },
+    {
+      "epoch": 0.06863417982155114,
+      "grad_norm": 0.07357123494148254,
+      "learning_rate": 0.0,
+      "loss": 0.0006,
+      "step": 75
+    },
+    {
+      "epoch": 0.06863417982155114,
+      "eval_loss": 0.1349995732307434,
+      "eval_runtime": 118.4018,
+      "eval_samples_per_second": 7.779,
+      "eval_steps_per_second": 3.894,
+      "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": 7.71809951612928e+16,
+  "total_flos": 1.157714927419392e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null