Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e7a1cc2f984491337cc93f8f078db449938995279d3456ad481ad5c2a60fca
+oid sha256:96b25093c2ddcfc392d555be93b382a35b05845daad2edfe7e7ddcf5bd8c58d4
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a7ed62fc316ebe2e945b7ad07627243752f56f599729a81d6413e2af2686b8
+oid sha256:f987a0e8ca33db7f01839de2164ccf4db663a66e6f7689a9ed004b586e621276
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e1f0fd2d004d6caaae844aa17b92356b2e2f60ef5bfaf5353e49ccd0051ffa
+oid sha256:2c88366e4cedd829c09c5fe7059b8e2e98aca6c5ecd80e83fa5290e51d4813d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981bbea8034bbbae85baf44fc3a7f5bd1463eae4931e71f483cdca42e7a37e82
+oid sha256:e37fdc46c9ceacc4f09fb079980eedde483f3261a807a717ac38bb84282cfbc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cca749a55d863ce18a73bc0ef2f3abbffa81b687698aff70716c9f05ebb977e
+oid sha256:18dd44bba8ec82bdc5a999dd503ca41e696d9d7a9a02f9a40556aba1f7d284e1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce143f3192cb1b2e626d251c64dac68350718e07c33521f586159568d189c078
+oid sha256:3c9f53c748ab56977e5d0b2dabfb603fcb816a36a8711e81b4f65d5a8fb7d27c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2976190476190476,
+  "epoch": 0.44642857142857145,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 0.3176,
       "step": 50
+    },
+    {
+      "epoch": 0.30357142857142855,
+      "grad_norm": 0.8264537453651428,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2985,
+      "step": 51
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 0.6697880029678345,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.335,
+      "step": 52
+    },
+    {
+      "epoch": 0.31547619047619047,
+      "grad_norm": 0.6313273310661316,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.3323,
+      "step": 53
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.7156944274902344,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2925,
+      "step": 54
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "eval_loss": 0.30814456939697266,
+      "eval_runtime": 0.7272,
+      "eval_samples_per_second": 776.911,
+      "eval_steps_per_second": 24.751,
+      "step": 54
+    },
+    {
+      "epoch": 0.3273809523809524,
+      "grad_norm": 0.8110126852989197,
+      "learning_rate": 5e-05,
+      "loss": 0.2934,
+      "step": 55
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5642712712287903,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3237,
+      "step": 56
+    },
+    {
+      "epoch": 0.3392857142857143,
+      "grad_norm": 0.5082366466522217,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.2284,
+      "step": 57
+    },
+    {
+      "epoch": 0.34523809523809523,
+      "grad_norm": 0.5590605735778809,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.2723,
+      "step": 58
+    },
+    {
+      "epoch": 0.35119047619047616,
+      "grad_norm": 0.7834331393241882,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.2732,
+      "step": 59
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.5841456651687622,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2316,
+      "step": 60
+    },
+    {
+      "epoch": 0.3630952380952381,
+      "grad_norm": 0.5144384503364563,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.2676,
+      "step": 61
+    },
+    {
+      "epoch": 0.36904761904761907,
+      "grad_norm": 0.5047840476036072,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.2311,
+      "step": 62
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.5553379058837891,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.2693,
+      "step": 63
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 0.2591702938079834,
+      "eval_runtime": 0.7281,
+      "eval_samples_per_second": 776.028,
+      "eval_steps_per_second": 24.723,
+      "step": 63
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.5578157901763916,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2313,
+      "step": 64
+    },
+    {
+      "epoch": 0.3869047619047619,
+      "grad_norm": 0.5519534945487976,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1994,
+      "step": 65
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.5156115889549255,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2438,
+      "step": 66
+    },
+    {
+      "epoch": 0.39880952380952384,
+      "grad_norm": 0.5865421891212463,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.2964,
+      "step": 67
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 0.4177829921245575,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.2274,
+      "step": 68
+    },
+    {
+      "epoch": 0.4107142857142857,
+      "grad_norm": 0.442807674407959,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.2507,
+      "step": 69
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.4709461033344269,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2241,
+      "step": 70
+    },
+    {
+      "epoch": 0.4226190476190476,
+      "grad_norm": 0.36320897936820984,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.203,
+      "step": 71
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.4016166031360626,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.2008,
+      "step": 72
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "eval_loss": 0.2299022376537323,
+      "eval_runtime": 0.725,
+      "eval_samples_per_second": 779.359,
+      "eval_steps_per_second": 24.829,
+      "step": 72
+    },
+    {
+      "epoch": 0.43452380952380953,
+      "grad_norm": 0.5135464668273926,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.2505,
+      "step": 73
+    },
+    {
+      "epoch": 0.44047619047619047,
+      "grad_norm": 0.4497532844543457,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2021,
+      "step": 74
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 0.44834592938423157,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1972,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2776751721676800.0,
+  "total_flos": 4165127582515200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null