Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6862b73efe84209bb4b29eeac9fe8e1f25516df4c33bf47023aa695433d4e4
+oid sha256:626c396850af2765e152700b776e8c6b84ea992a0b23a7e023b5b83d69cca321
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d475523a61a14c6e218c4dc240c05158e73a7584593cc9af3c40470764d3dc16
+oid sha256:460c8b3c4770f25987d801dfbab0fa9a8eab15cd2ab87fdea88200e85b89a2c5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ffd8689bfc9d36d10f4de88ee95f4060bd8e23db4bb3e43f2a175fdee90af5
+oid sha256:48b571a1cda1c18e0b76f3cd6c89bae53eb9d1241ef187c71a1c58bcd4925246
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7e91af1a79d7676619e959cc4b5dde54a9e2ec825d24c1c34fe5387a27894f
+oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009321401938851604,
+  "epoch": 0.018642803877703208,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 4.412,
       "eval_steps_per_second": 2.207,
       "step": 25
+    },
+    {
+      "epoch": 0.009694258016405667,
+      "grad_norm": 18.933256149291992,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 3.038,
+      "step": 26
+    },
+    {
+      "epoch": 0.010067114093959731,
+      "grad_norm": 8.585943222045898,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.5117,
+      "step": 27
+    },
+    {
+      "epoch": 0.010439970171513796,
+      "grad_norm": 10.232223510742188,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 2.5074,
+      "step": 28
+    },
+    {
+      "epoch": 0.01081282624906786,
+      "grad_norm": 8.64398193359375,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 2.9964,
+      "step": 29
+    },
+    {
+      "epoch": 0.011185682326621925,
+      "grad_norm": 11.656851768493652,
+      "learning_rate": 0.000138268343236509,
+      "loss": 2.8767,
+      "step": 30
+    },
+    {
+      "epoch": 0.011558538404175988,
+      "grad_norm": 7.217341423034668,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 1.8044,
+      "step": 31
+    },
+    {
+      "epoch": 0.011931394481730051,
+      "grad_norm": 8.281699180603027,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 2.0798,
+      "step": 32
+    },
+    {
+      "epoch": 0.012304250559284116,
+      "grad_norm": 12.387796401977539,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 3.5874,
+      "step": 33
+    },
+    {
+      "epoch": 0.01267710663683818,
+      "grad_norm": 9.76694107055664,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 2.8491,
+      "step": 34
+    },
+    {
+      "epoch": 0.013049962714392245,
+      "grad_norm": 7.733439922332764,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.16,
+      "step": 35
+    },
+    {
+      "epoch": 0.013422818791946308,
+      "grad_norm": 6.12880277633667,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 2.0449,
+      "step": 36
+    },
+    {
+      "epoch": 0.013795674869500374,
+      "grad_norm": 6.441651821136475,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 1.8501,
+      "step": 37
+    },
+    {
+      "epoch": 0.014168530947054437,
+      "grad_norm": 15.817225456237793,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 2.776,
+      "step": 38
+    },
+    {
+      "epoch": 0.0145413870246085,
+      "grad_norm": 8.889180183410645,
+      "learning_rate": 0.0001,
+      "loss": 2.1201,
+      "step": 39
+    },
+    {
+      "epoch": 0.014914243102162566,
+      "grad_norm": 4.129387855529785,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 1.448,
+      "step": 40
+    },
+    {
+      "epoch": 0.015287099179716629,
+      "grad_norm": 9.360006332397461,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 2.4102,
+      "step": 41
+    },
+    {
+      "epoch": 0.015659955257270694,
+      "grad_norm": 11.799320220947266,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.9307,
+      "step": 42
+    },
+    {
+      "epoch": 0.01603281133482476,
+      "grad_norm": 6.900726318359375,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.3355,
+      "step": 43
+    },
+    {
+      "epoch": 0.01640566741237882,
+      "grad_norm": 6.313440322875977,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 1.6515,
+      "step": 44
+    },
+    {
+      "epoch": 0.016778523489932886,
+      "grad_norm": 8.934613227844238,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.0291,
+      "step": 45
+    },
+    {
+      "epoch": 0.01715137956748695,
+      "grad_norm": 9.353364944458008,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 1.9863,
+      "step": 46
+    },
+    {
+      "epoch": 0.017524235645041013,
+      "grad_norm": 8.81008243560791,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.7731,
+      "step": 47
+    },
+    {
+      "epoch": 0.017897091722595078,
+      "grad_norm": 11.235795974731445,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6917,
+      "step": 48
+    },
+    {
+      "epoch": 0.018269947800149143,
+      "grad_norm": 8.671363830566406,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 2.321,
+      "step": 49
+    },
+    {
+      "epoch": 0.018642803877703208,
+      "grad_norm": 6.4699578285217285,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 1.7027,
+      "step": 50
+    },
+    {
+      "epoch": 0.018642803877703208,
+      "eval_loss": 0.25740864872932434,
+      "eval_runtime": 511.7924,
+      "eval_samples_per_second": 4.414,
+      "eval_steps_per_second": 2.208,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null