Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006304006e68a27ec56834cb86516974beff5725be5d9024ce7657b123f22e21
+oid sha256:f62b7097e3f425b2e90deca4728016392a46c248054749cc43054539be64c051
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11811bd6edfcafb436d8e2ab81047ab8e1d29da65b9b874f477c9ab00cc077b3
+oid sha256:c869498b43610764b7aced71b0286197cf0b54651ed26aae56f721cd838dddb0
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69643525a1dcd2f373b7ea4a257c5e640f4084d4d8c20a273325deef81388c53
+oid sha256:16bf024688e8bd952a2153706e4c60bcffda672499b07a3e6985258247927051
 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": 0.01531745423910546,
+  "epoch": 0.03063490847821092,
   "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": 13.322,
       "eval_steps_per_second": 6.666,
       "step": 25
+    },
+    {
+      "epoch": 0.015930152408669677,
+      "grad_norm": 4.183315277099609,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 1.7487,
+      "step": 26
+    },
+    {
+      "epoch": 0.016542850578233896,
+      "grad_norm": 3.80495285987854,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5895,
+      "step": 27
+    },
+    {
+      "epoch": 0.017155548747798115,
+      "grad_norm": 4.383512496948242,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 1.7426,
+      "step": 28
+    },
+    {
+      "epoch": 0.017768246917362333,
+      "grad_norm": 3.543182134628296,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 1.3334,
+      "step": 29
+    },
+    {
+      "epoch": 0.018380945086926552,
+      "grad_norm": 5.36271858215332,
+      "learning_rate": 0.000138268343236509,
+      "loss": 2.0307,
+      "step": 30
+    },
+    {
+      "epoch": 0.01899364325649077,
+      "grad_norm": 4.558619022369385,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 1.5612,
+      "step": 31
+    },
+    {
+      "epoch": 0.01960634142605499,
+      "grad_norm": 4.2172393798828125,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 1.6558,
+      "step": 32
+    },
+    {
+      "epoch": 0.020219039595619208,
+      "grad_norm": 3.8163092136383057,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.2329,
+      "step": 33
+    },
+    {
+      "epoch": 0.020831737765183427,
+      "grad_norm": 4.494469165802002,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 1.6348,
+      "step": 34
+    },
+    {
+      "epoch": 0.021444435934747645,
+      "grad_norm": 4.1140031814575195,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 1.7624,
+      "step": 35
+    },
+    {
+      "epoch": 0.022057134104311864,
+      "grad_norm": 5.299776554107666,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 2.5285,
+      "step": 36
+    },
+    {
+      "epoch": 0.022669832273876082,
+      "grad_norm": 3.846937656402588,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 1.5106,
+      "step": 37
+    },
+    {
+      "epoch": 0.0232825304434403,
+      "grad_norm": 4.549310207366943,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 1.9129,
+      "step": 38
+    },
+    {
+      "epoch": 0.02389522861300452,
+      "grad_norm": 5.004308700561523,
+      "learning_rate": 0.0001,
+      "loss": 1.7608,
+      "step": 39
+    },
+    {
+      "epoch": 0.02450792678256874,
+      "grad_norm": 3.4253933429718018,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 1.4814,
+      "step": 40
+    },
+    {
+      "epoch": 0.025120624952132957,
+      "grad_norm": 4.386419773101807,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 1.3271,
+      "step": 41
+    },
+    {
+      "epoch": 0.025733323121697176,
+      "grad_norm": 4.444244861602783,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.7585,
+      "step": 42
+    },
+    {
+      "epoch": 0.02634602129126139,
+      "grad_norm": 3.8281044960021973,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.4,
+      "step": 43
+    },
+    {
+      "epoch": 0.02695871946082561,
+      "grad_norm": 4.207068920135498,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 1.7096,
+      "step": 44
+    },
+    {
+      "epoch": 0.027571417630389828,
+      "grad_norm": 4.072748184204102,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.5046,
+      "step": 45
+    },
+    {
+      "epoch": 0.028184115799954047,
+      "grad_norm": 4.015542030334473,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 1.1774,
+      "step": 46
+    },
+    {
+      "epoch": 0.028796813969518265,
+      "grad_norm": 3.9917783737182617,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.5171,
+      "step": 47
+    },
+    {
+      "epoch": 0.029409512139082484,
+      "grad_norm": 4.313107013702393,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.7398,
+      "step": 48
+    },
+    {
+      "epoch": 0.030022210308646703,
+      "grad_norm": 4.4379448890686035,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 1.2932,
+      "step": 49
+    },
+    {
+      "epoch": 0.03063490847821092,
+      "grad_norm": 4.202969551086426,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 1.8661,
+      "step": 50
+    },
+    {
+      "epoch": 0.03063490847821092,
+      "eval_loss": 1.6266911029815674,
+      "eval_runtime": 103.2244,
+      "eval_samples_per_second": 13.32,
+      "eval_steps_per_second": 6.665,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9837753453772800.0,
+  "total_flos": 1.96755069075456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null