Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a0fa8ff10e2b47c91f216fca7ae09ce7d67db73074f8e58c5084d72a1497e5
+oid sha256:dc6f62f3a4fb689c7ba8051e72971e6b48b8d501ffe4ec2fa67f6313b0ba71ec
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c036e462fc01b009e149797ee73941675bd15cf7f6ca35412a8358dceba4e3
+oid sha256:bf715e2a13c84448a3ff9e9018304d4beccc087840b59ab29bbea95f48c66616
 size 136814

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f435e2cf5af084ff87f38ac364aa32f5f9250d67a5fd3cb62ee9bb2e9e48da7
+oid sha256:1f0769ac9f6e5a775e3172601984970ae5aeb6570d2e59f38a58d84854e22367
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfdc610d6111b3c5b2c5f58f7b4bc723b1377af735ffdde336defa263ece09d
+oid sha256:4b69f085dcd7d3c6e07acfbd354d973bf19c16d6283ab3f9fe7eafe320fa66a1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4ecc45073a35262869a0d9392090bbde50163f9775b63db54f8daf68eadbe7
+oid sha256:2997d603631ca8d1209b6aeca1ac3d249bd00d50d014e5ffdd28c52cc649ef27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.512,
+  "epoch": 0.768,
   "eval_steps": 16,
-  "global_step": 32,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -255,6 +255,126 @@
       "eval_samples_per_second": 131.72,
       "eval_steps_per_second": 33.551,
       "step": 32
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 1.6445367336273193,
+      "learning_rate": 0.0001563320058063622,
+      "loss": 88.6368,
+      "step": 33
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 1.6764920949935913,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 88.6352,
+      "step": 34
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6223012208938599,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 88.6562,
+      "step": 35
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 1.6213066577911377,
+      "learning_rate": 0.00013653410243663952,
+      "loss": 88.6551,
+      "step": 36
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 1.6623308658599854,
+      "learning_rate": 0.00012947551744109043,
+      "loss": 88.6895,
+      "step": 37
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 1.8002474308013916,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 88.674,
+      "step": 38
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 1.8450833559036255,
+      "learning_rate": 0.00011490422661761744,
+      "loss": 88.5731,
+      "step": 39
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.9053994417190552,
+      "learning_rate": 0.00010747300935864243,
+      "loss": 88.6383,
+      "step": 40
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 1.9040968418121338,
+      "learning_rate": 0.0001,
+      "loss": 88.6602,
+      "step": 41
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 2.163938522338867,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 88.5704,
+      "step": 42
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 2.156372547149658,
+      "learning_rate": 8.509577338238255e-05,
+      "loss": 88.4837,
+      "step": 43
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 2.1990439891815186,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 88.6662,
+      "step": 44
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.474072217941284,
+      "learning_rate": 7.052448255890957e-05,
+      "loss": 88.5809,
+      "step": 45
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 2.7647547721862793,
+      "learning_rate": 6.34658975633605e-05,
+      "loss": 88.6076,
+      "step": 46
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.5142226219177246,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 88.7863,
+      "step": 47
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.5332900285720825,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 88.6006,
+      "step": 48
+    },
+    {
+      "epoch": 0.768,
+      "eval_loss": 11.07020378112793,
+      "eval_runtime": 0.612,
+      "eval_samples_per_second": 173.197,
+      "eval_steps_per_second": 44.116,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -274,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 958314577920.0,
+  "total_flos": 1437471866880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null