Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9b9c2b9350eea1cdf5f12b81616a5e1bff185eb40142cabbd7f6984481fea3
+oid sha256:3c3626c9ef6b2fdee7d5fcb8854eb566998227cc068b92c454f7288ed8c9d1e8
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6cec7f405a96980b18daffe1664b3539966efc366fa4fe31a85c4a81be4947
+oid sha256:7c64d86a65472b6fbfeb09a70bb1c78b99c89b5fefd64944787366fbc9a7dd2d
 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": 0.03328340822100183,
+  "epoch": 0.04992511233150274,
   "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": 4.291,
       "eval_steps_per_second": 2.147,
       "step": 50
+    },
+    {
+      "epoch": 0.03394907638542187,
+      "grad_norm": 2.3751840591430664,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0587,
+      "step": 51
+    },
+    {
+      "epoch": 0.034614744549841904,
+      "grad_norm": 3.929506778717041,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 0.243,
+      "step": 52
+    },
+    {
+      "epoch": 0.03528041271426194,
+      "grad_norm": 4.9729132652282715,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 0.3327,
+      "step": 53
+    },
+    {
+      "epoch": 0.03594608087868198,
+      "grad_norm": 4.64143180847168,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.3707,
+      "step": 54
+    },
+    {
+      "epoch": 0.036611749043102014,
+      "grad_norm": 3.2200844287872314,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.2981,
+      "step": 55
+    },
+    {
+      "epoch": 0.03727741720752205,
+      "grad_norm": 2.6393558979034424,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 0.1529,
+      "step": 56
+    },
+    {
+      "epoch": 0.03794308537194209,
+      "grad_norm": 4.790804862976074,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.2654,
+      "step": 57
+    },
+    {
+      "epoch": 0.038608753536362124,
+      "grad_norm": 1.2065534591674805,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 0.0551,
+      "step": 58
+    },
+    {
+      "epoch": 0.03927442170078216,
+      "grad_norm": 3.567166328430176,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.3295,
+      "step": 59
+    },
+    {
+      "epoch": 0.0399400898652022,
+      "grad_norm": 1.8716219663619995,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.1449,
+      "step": 60
+    },
+    {
+      "epoch": 0.040605758029622234,
+      "grad_norm": 2.8182613849639893,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 0.1724,
+      "step": 61
+    },
+    {
+      "epoch": 0.04127142619404227,
+      "grad_norm": 4.6796112060546875,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 0.2599,
+      "step": 62
+    },
+    {
+      "epoch": 0.04193709435846231,
+      "grad_norm": 3.623056411743164,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0858,
+      "step": 63
+    },
+    {
+      "epoch": 0.042602762522882344,
+      "grad_norm": 1.3320046663284302,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 0.0667,
+      "step": 64
+    },
+    {
+      "epoch": 0.04326843068730238,
+      "grad_norm": 2.166306495666504,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 0.1206,
+      "step": 65
+    },
+    {
+      "epoch": 0.04393409885172242,
+      "grad_norm": 2.2918238639831543,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0988,
+      "step": 66
+    },
+    {
+      "epoch": 0.044599767016142454,
+      "grad_norm": 3.8302066326141357,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.3119,
+      "step": 67
+    },
+    {
+      "epoch": 0.04526543518056249,
+      "grad_norm": 3.98258638381958,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 0.2715,
+      "step": 68
+    },
+    {
+      "epoch": 0.04593110334498253,
+      "grad_norm": 4.596426010131836,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.5579,
+      "step": 69
+    },
+    {
+      "epoch": 0.046596771509402564,
+      "grad_norm": 2.9032671451568604,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 0.1493,
+      "step": 70
+    },
+    {
+      "epoch": 0.0472624396738226,
+      "grad_norm": 7.22641134262085,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.4988,
+      "step": 71
+    },
+    {
+      "epoch": 0.04792810783824263,
+      "grad_norm": 5.318079948425293,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.3443,
+      "step": 72
+    },
+    {
+      "epoch": 0.048593776002662674,
+      "grad_norm": 2.0902915000915527,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 0.1034,
+      "step": 73
+    },
+    {
+      "epoch": 0.04925944416708271,
+      "grad_norm": 3.0144219398498535,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 0.3192,
+      "step": 74
+    },
+    {
+      "epoch": 0.04992511233150274,
+      "grad_norm": 4.522768974304199,
+      "learning_rate": 0.0,
+      "loss": 0.0828,
+      "step": 75
+    },
+    {
+      "epoch": 0.04992511233150274,
+      "eval_loss": 0.2045978456735611,
+      "eval_runtime": 294.7269,
+      "eval_samples_per_second": 4.292,
+      "eval_steps_per_second": 2.148,
+      "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": 6.6109411688448e+16,
+  "total_flos": 9.9164117532672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null