Training in progress, step 68, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b14a95c7f959dcbd54f89ee9ea99cc1dbf6d6e00e3dd380e71efa60af12ee96
+oid sha256:e86ee6e154e49069091d893455757e17295ee85019f64a663e52903b19cfc1cf
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e15873f91766aa485609b54a44fa78a3d3396e31ce52599854df27197085e2a
+oid sha256:8e1a75388d3fb482b018a16ca66ce2bf8d2b482576fc3daf3f841c59f4c236cb
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeaac88ea211375a529b1fd2970f1cc397730f5d948fdb30bae28e4d8b193fb4
+oid sha256:051417fc01d33b78aa641f032182ab64da1fcc15fe5a876899f334dcea2dc357
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86702c0a3caad6c51746e54805a7289de03dff9cc5abc148a58966cf1f4d339
+oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17278983589200636,
+  "epoch": 0.23038644785600848,
   "eval_steps": 50,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -380,6 +380,125 @@
       "learning_rate": 0.00013928754755265842,
       "loss": 10.3514,
       "step": 51
+    },
+    {
+      "epoch": 0.17617787188988884,
+      "grad_norm": 0.06112508103251457,
+      "learning_rate": 0.00013860360721173193,
+      "loss": 10.3511,
+      "step": 52
+    },
+    {
+      "epoch": 0.1795659078877713,
+      "grad_norm": 0.06208924576640129,
+      "learning_rate": 0.0001379002925959068,
+      "loss": 10.3505,
+      "step": 53
+    },
+    {
+      "epoch": 0.18295394388565378,
+      "grad_norm": 0.057701293379068375,
+      "learning_rate": 0.0001371778179416281,
+      "loss": 10.3505,
+      "step": 54
+    },
+    {
+      "epoch": 0.18634197988353626,
+      "grad_norm": 0.050447553396224976,
+      "learning_rate": 0.00013643640332167438,
+      "loss": 10.349,
+      "step": 55
+    },
+    {
+      "epoch": 0.18973001588141875,
+      "grad_norm": 0.05121852830052376,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 10.3496,
+      "step": 56
+    },
+    {
+      "epoch": 0.19311805187930123,
+      "grad_norm": 0.04376755282282829,
+      "learning_rate": 0.00013489766325354695,
+      "loss": 10.3488,
+      "step": 57
+    },
+    {
+      "epoch": 0.19650608787718368,
+      "grad_norm": 0.04570882394909859,
+      "learning_rate": 0.00013410080652050412,
+      "loss": 10.3493,
+      "step": 58
+    },
+    {
+      "epoch": 0.19989412387506617,
+      "grad_norm": 0.047347478568553925,
+      "learning_rate": 0.0001332859471092728,
+      "loss": 10.35,
+      "step": 59
+    },
+    {
+      "epoch": 0.20328215987294865,
+      "grad_norm": 0.048713624477386475,
+      "learning_rate": 0.00013245333323392333,
+      "loss": 10.3484,
+      "step": 60
+    },
+    {
+      "epoch": 0.20667019587083113,
+      "grad_norm": 0.04044219106435776,
+      "learning_rate": 0.0001316032185167079,
+      "loss": 10.3485,
+      "step": 61
+    },
+    {
+      "epoch": 0.2100582318687136,
+      "grad_norm": 0.03352762386202812,
+      "learning_rate": 0.00013073586191080457,
+      "loss": 10.3494,
+      "step": 62
+    },
+    {
+      "epoch": 0.2134462678665961,
+      "grad_norm": 0.03678755834698677,
+      "learning_rate": 0.00012985152762143778,
+      "loss": 10.3492,
+      "step": 63
+    },
+    {
+      "epoch": 0.21683430386447855,
+      "grad_norm": 0.035951532423496246,
+      "learning_rate": 0.00012895048502539882,
+      "loss": 10.3475,
+      "step": 64
+    },
+    {
+      "epoch": 0.22022233986236103,
+      "grad_norm": 0.04304710775613785,
+      "learning_rate": 0.00012803300858899104,
+      "loss": 10.349,
+      "step": 65
+    },
+    {
+      "epoch": 0.22361037586024352,
+      "grad_norm": 0.035194698721170425,
+      "learning_rate": 0.0001270993777844248,
+      "loss": 10.3468,
+      "step": 66
+    },
+    {
+      "epoch": 0.226998411858126,
+      "grad_norm": 0.029510466381907463,
+      "learning_rate": 0.0001261498770046874,
+      "loss": 10.3484,
+      "step": 67
+    },
+    {
+      "epoch": 0.23038644785600848,
+      "grad_norm": 0.02603858895599842,
+      "learning_rate": 0.00012518479547691435,
+      "loss": 10.3485,
+      "step": 68
     }
   ],
   "logging_steps": 1,
@@ -399,7 +518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21825075412992.0,
+  "total_flos": 29122375581696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null