Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f9103160b3378d7134332cfb7e24030224ae2908f5ebe9f030be03b7bf8a75
+oid sha256:f7a5bc27d15a98a1b7f008e2ae5b1fa71f8564b2203bc5f567718fee9c9b8de9
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e76d99be710552f21db7954243247cfbf3e106b529537b4e2c420cf1baeed41
+oid sha256:4dfc1b4acfe0978bca370fbc004221ea2fea4474ce49223be7246d9be15c336c
 size 10251668

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504a18916cff7ee231e2ca0fec451cfabf06384a204efb1af21153115c4762d1
+oid sha256:fd619ac5fe1b5a9993caa1b33027cbaba2affae2b385b5b8e1edc744130828b6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98e40b348031d95e8c181f06ff58b966babff966d0b0b227b2abd8980fdd5b7
+oid sha256:1ce9f7304e0a4744e6ea3362c37f41fa81110af8aa0741e1543ca9d0f005e0bc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec5ba450a531e51bce4dda507094f8312c48c4494b76e4535a2b99ebb9e2b10
+oid sha256:a2663b0191a48b0d84f57520e6d7470d2ed946f6d4e667618a3101ba08ea341a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae7517dfb7df0ee748fd80c4bbb46f58eb5cc33ecd067a405c2363bf77fe794
+oid sha256:21d803133439c81a4ccfa134ee0737fabb2479f40d1f31268b7cfb1fa6f46236
 size 15024

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": 0.026006111436187505,
+  "epoch": 0.05201222287237501,
   "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": 141.067,
       "eval_steps_per_second": 17.642,
       "step": 100
+    },
+    {
+      "epoch": 0.02730641700799688,
+      "grad_norm": 0.2048594206571579,
+      "learning_rate": 8.606012236719073e-05,
+      "loss": 2.473,
+      "step": 105
+    },
+    {
+      "epoch": 0.028606722579806256,
+      "grad_norm": 0.2099340707063675,
+      "learning_rate": 8.463621767547998e-05,
+      "loss": 2.5045,
+      "step": 110
+    },
+    {
+      "epoch": 0.02990702815161563,
+      "grad_norm": 0.18916481733322144,
+      "learning_rate": 8.315613291203976e-05,
+      "loss": 2.4466,
+      "step": 115
+    },
+    {
+      "epoch": 0.031207333723425004,
+      "grad_norm": 0.20611602067947388,
+      "learning_rate": 8.162226877976887e-05,
+      "loss": 2.4546,
+      "step": 120
+    },
+    {
+      "epoch": 0.03250763929523438,
+      "grad_norm": 0.21061871945858002,
+      "learning_rate": 8.003711321189895e-05,
+      "loss": 2.4797,
+      "step": 125
+    },
+    {
+      "epoch": 0.033807944867043756,
+      "grad_norm": 0.20406612753868103,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 2.5568,
+      "step": 130
+    },
+    {
+      "epoch": 0.03510825043885313,
+      "grad_norm": 0.21400322020053864,
+      "learning_rate": 7.672329130639005e-05,
+      "loss": 2.4747,
+      "step": 135
+    },
+    {
+      "epoch": 0.03640855601066251,
+      "grad_norm": 0.22233155369758606,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.5571,
+      "step": 140
+    },
+    {
+      "epoch": 0.03770886158247188,
+      "grad_norm": 0.21888834238052368,
+      "learning_rate": 7.323615860218843e-05,
+      "loss": 2.4723,
+      "step": 145
+    },
+    {
+      "epoch": 0.03900916715428126,
+      "grad_norm": 0.21492037177085876,
+      "learning_rate": 7.143462807015271e-05,
+      "loss": 2.4496,
+      "step": 150
+    },
+    {
+      "epoch": 0.04030947272609063,
+      "grad_norm": 0.229643777012825,
+      "learning_rate": 6.959833049300377e-05,
+      "loss": 2.4829,
+      "step": 155
+    },
+    {
+      "epoch": 0.0416097782979,
+      "grad_norm": 0.19544768333435059,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 2.4211,
+      "step": 160
+    },
+    {
+      "epoch": 0.04291008386970938,
+      "grad_norm": 0.2128247320652008,
+      "learning_rate": 6.583339969007363e-05,
+      "loss": 2.3166,
+      "step": 165
+    },
+    {
+      "epoch": 0.044210389441518755,
+      "grad_norm": 0.2158002257347107,
+      "learning_rate": 6.391087319582264e-05,
+      "loss": 2.4202,
+      "step": 170
+    },
+    {
+      "epoch": 0.045510695013328134,
+      "grad_norm": 0.23509222269058228,
+      "learning_rate": 6.19657832143779e-05,
+      "loss": 2.381,
+      "step": 175
+    },
+    {
+      "epoch": 0.046811000585137506,
+      "grad_norm": 0.21844059228897095,
+      "learning_rate": 6.0001284688802226e-05,
+      "loss": 2.4878,
+      "step": 180
+    },
+    {
+      "epoch": 0.048111306156946886,
+      "grad_norm": 0.22377453744411469,
+      "learning_rate": 5.8020564042888015e-05,
+      "loss": 2.3867,
+      "step": 185
+    },
+    {
+      "epoch": 0.04941161172875626,
+      "grad_norm": 0.22664517164230347,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 2.4527,
+      "step": 190
+    },
+    {
+      "epoch": 0.05071191730056563,
+      "grad_norm": 0.21447192132472992,
+      "learning_rate": 5.402332843583631e-05,
+      "loss": 2.3911,
+      "step": 195
+    },
+    {
+      "epoch": 0.05201222287237501,
+      "grad_norm": 0.22999480366706848,
+      "learning_rate": 5.201329700547076e-05,
+      "loss": 2.4612,
+      "step": 200
+    },
+    {
+      "epoch": 0.05201222287237501,
+      "eval_loss": 2.436123847961426,
+      "eval_runtime": 45.8777,
+      "eval_samples_per_second": 141.18,
+      "eval_steps_per_second": 17.656,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -182,7 +330,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6349734008586240.0,
+  "total_flos": 1.271906598649856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null