Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4096439e3f4b06e464258b4c1cd582129ec5fd5c7585c510e9a8753c774aac89
+oid sha256:81bbed5abc56d6c28783c5061dbcdc35b6b6e7a888e23f88a7277ba7abb7f437
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b680918be4dc2d7256d4f2373a7a6529c70b4642a0a1ab803b286f609973726
+oid sha256:c07c5c4c0eb4484fa8eafb8a2f2a9954812d672c9a977058a6e3825e526ee348
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82070ffe55ccbf8a10ae05c44e293986e51c38a62e2b8b84945035270d2adeb
+oid sha256:f66f2426252eb191beb77c78c058090472268dcbf13daa8cf60071225acfe904
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0396746677246578,
+  "epoch": 0.05951200158698671,
   "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": 4.942,
       "eval_steps_per_second": 2.471,
       "step": 50
+    },
+    {
+      "epoch": 0.04046816107915096,
+      "grad_norm": 3.206982374191284,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.8024,
+      "step": 51
+    },
+    {
+      "epoch": 0.041261654433644115,
+      "grad_norm": 2.6523642539978027,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 2.9125,
+      "step": 52
+    },
+    {
+      "epoch": 0.04205514778813727,
+      "grad_norm": 2.145852565765381,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 2.7628,
+      "step": 53
+    },
+    {
+      "epoch": 0.04284864114263043,
+      "grad_norm": 1.956112027168274,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.829,
+      "step": 54
+    },
+    {
+      "epoch": 0.043642134497123584,
+      "grad_norm": 3.5577127933502197,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 2.9393,
+      "step": 55
+    },
+    {
+      "epoch": 0.04443562785161674,
+      "grad_norm": 2.462873697280884,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 2.9588,
+      "step": 56
+    },
+    {
+      "epoch": 0.0452291212061099,
+      "grad_norm": 1.5341908931732178,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.7976,
+      "step": 57
+    },
+    {
+      "epoch": 0.04602261456060305,
+      "grad_norm": 3.1381309032440186,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 2.8753,
+      "step": 58
+    },
+    {
+      "epoch": 0.04681610791509621,
+      "grad_norm": 3.1369926929473877,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 2.8046,
+      "step": 59
+    },
+    {
+      "epoch": 0.047609601269589366,
+      "grad_norm": 3.5989041328430176,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.0486,
+      "step": 60
+    },
+    {
+      "epoch": 0.04840309462408252,
+      "grad_norm": 3.038649559020996,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 2.8922,
+      "step": 61
+    },
+    {
+      "epoch": 0.04919658797857568,
+      "grad_norm": 3.415806293487549,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 2.7841,
+      "step": 62
+    },
+    {
+      "epoch": 0.049990081333068835,
+      "grad_norm": 1.7945884466171265,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.9487,
+      "step": 63
+    },
+    {
+      "epoch": 0.05078357468756199,
+      "grad_norm": 2.6868271827697754,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 2.8241,
+      "step": 64
+    },
+    {
+      "epoch": 0.05157706804205515,
+      "grad_norm": 2.454937219619751,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 2.7385,
+      "step": 65
+    },
+    {
+      "epoch": 0.052370561396548304,
+      "grad_norm": 2.422858953475952,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.9928,
+      "step": 66
+    },
+    {
+      "epoch": 0.05316405475104146,
+      "grad_norm": 2.9807822704315186,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 2.873,
+      "step": 67
+    },
+    {
+      "epoch": 0.05395754810553462,
+      "grad_norm": 2.892643451690674,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 2.8405,
+      "step": 68
+    },
+    {
+      "epoch": 0.05475104146002777,
+      "grad_norm": 2.1034739017486572,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.7657,
+      "step": 69
+    },
+    {
+      "epoch": 0.05554453481452093,
+      "grad_norm": 2.7781882286071777,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 2.9382,
+      "step": 70
+    },
+    {
+      "epoch": 0.056338028169014086,
+      "grad_norm": 1.8283110857009888,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 2.809,
+      "step": 71
+    },
+    {
+      "epoch": 0.05713152152350724,
+      "grad_norm": 3.2760870456695557,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.9855,
+      "step": 72
+    },
+    {
+      "epoch": 0.0579250148780004,
+      "grad_norm": 2.1711838245391846,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 2.914,
+      "step": 73
+    },
+    {
+      "epoch": 0.058718508232493555,
+      "grad_norm": 1.9169692993164062,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 2.868,
+      "step": 74
+    },
+    {
+      "epoch": 0.05951200158698671,
+      "grad_norm": 2.8653454780578613,
+      "learning_rate": 0.0,
+      "loss": 2.9482,
+      "step": 75
+    },
+    {
+      "epoch": 0.05951200158698671,
+      "eval_loss": 0.36626261472702026,
+      "eval_runtime": 214.2761,
+      "eval_samples_per_second": 4.956,
+      "eval_steps_per_second": 2.478,
+      "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": 6.53458201903104e+16,
+  "total_flos": 9.80187302854656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null