Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df89d04fc8d1af43de62b00d358fdf57c879ced367e684436a5f7d4958686a7
+oid sha256:b51edb95931c50c7eccffe73d0c373447c32b5551b695812216e3bd9d18b2928
 size 36220072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d1f1fc3c9075aae38759c7933fedb202bff9149ce93c9ca1737be12aff8664
+oid sha256:481a7a996369d8d39cb2ff983ba7d20de9cdb194073610ec25fb97d5046a40c3
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77dc5450e83556f8e451ff05af90acfe581ab9bd5a4f5edaabb4bced8b60c871
+oid sha256:ba08bf9c96258aa66309cebbe094ba794b566e771cd04cb308d30904cb3fcb21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
+oid sha256:4ac116b8169c53ab649a7f15f2f32735f2c71ec2f803f70de8c655a513ee9cfc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016304569355561897,
+  "epoch": 0.032609138711123795,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 25.227,
       "eval_steps_per_second": 12.618,
       "step": 100
+    },
+    {
+      "epoch": 0.017119797823339993,
+      "grad_norm": 0.23096653819084167,
+      "learning_rate": 8.606012236719073e-05,
+      "loss": 0.6521,
+      "step": 105
+    },
+    {
+      "epoch": 0.017935026291118084,
+      "grad_norm": 0.21091365814208984,
+      "learning_rate": 8.463621767547998e-05,
+      "loss": 0.6747,
+      "step": 110
+    },
+    {
+      "epoch": 0.01875025475889618,
+      "grad_norm": 0.16294293105602264,
+      "learning_rate": 8.315613291203976e-05,
+      "loss": 0.6636,
+      "step": 115
+    },
+    {
+      "epoch": 0.019565483226674275,
+      "grad_norm": 0.17157024145126343,
+      "learning_rate": 8.162226877976887e-05,
+      "loss": 0.7743,
+      "step": 120
+    },
+    {
+      "epoch": 0.02038071169445237,
+      "grad_norm": 0.1470104157924652,
+      "learning_rate": 8.003711321189895e-05,
+      "loss": 0.7405,
+      "step": 125
+    },
+    {
+      "epoch": 0.021195940162230465,
+      "grad_norm": 0.13396376371383667,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.6663,
+      "step": 130
+    },
+    {
+      "epoch": 0.02201116863000856,
+      "grad_norm": 0.18456505239009857,
+      "learning_rate": 7.672329130639005e-05,
+      "loss": 0.755,
+      "step": 135
+    },
+    {
+      "epoch": 0.022826397097786656,
+      "grad_norm": 0.1341053545475006,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6231,
+      "step": 140
+    },
+    {
+      "epoch": 0.02364162556556475,
+      "grad_norm": 0.15663418173789978,
+      "learning_rate": 7.323615860218843e-05,
+      "loss": 0.7846,
+      "step": 145
+    },
+    {
+      "epoch": 0.024456854033342846,
+      "grad_norm": 0.16723978519439697,
+      "learning_rate": 7.143462807015271e-05,
+      "loss": 0.6989,
+      "step": 150
+    },
+    {
+      "epoch": 0.025272082501120938,
+      "grad_norm": 0.19980840384960175,
+      "learning_rate": 6.959833049300377e-05,
+      "loss": 0.7202,
+      "step": 155
+    },
+    {
+      "epoch": 0.026087310968899033,
+      "grad_norm": 0.16260208189487457,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.7097,
+      "step": 160
+    },
+    {
+      "epoch": 0.026902539436677128,
+      "grad_norm": 0.2040923684835434,
+      "learning_rate": 6.583339969007363e-05,
+      "loss": 0.6251,
+      "step": 165
+    },
+    {
+      "epoch": 0.027717767904455223,
+      "grad_norm": 0.140736386179924,
+      "learning_rate": 6.391087319582264e-05,
+      "loss": 0.7478,
+      "step": 170
+    },
+    {
+      "epoch": 0.02853299637223332,
+      "grad_norm": 0.23201903700828552,
+      "learning_rate": 6.19657832143779e-05,
+      "loss": 0.6886,
+      "step": 175
+    },
+    {
+      "epoch": 0.029348224840011414,
+      "grad_norm": 0.20656245946884155,
+      "learning_rate": 6.0001284688802226e-05,
+      "loss": 0.6724,
+      "step": 180
+    },
+    {
+      "epoch": 0.03016345330778951,
+      "grad_norm": 0.1894981861114502,
+      "learning_rate": 5.8020564042888015e-05,
+      "loss": 0.7793,
+      "step": 185
+    },
+    {
+      "epoch": 0.030978681775567604,
+      "grad_norm": 0.1519327610731125,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.6349,
+      "step": 190
+    },
+    {
+      "epoch": 0.0317939102433457,
+      "grad_norm": 0.16416174173355103,
+      "learning_rate": 5.402332843583631e-05,
+      "loss": 0.7005,
+      "step": 195
+    },
+    {
+      "epoch": 0.032609138711123795,
+      "grad_norm": 0.13308531045913696,
+      "learning_rate": 5.201329700547076e-05,
+      "loss": 0.6768,
+      "step": 200
+    },
+    {
+      "epoch": 0.032609138711123795,
+      "eval_loss": 0.7349870204925537,
+      "eval_runtime": 102.1982,
+      "eval_samples_per_second": 25.274,
+      "eval_steps_per_second": 12.642,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9513908708573184.0,
+  "total_flos": 1.8669553072472064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null