Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5313c9de80553f97d62783c0e1495835981f083ae701770d222e18a973973d
+oid sha256:2c462f9ca2f271dec7936887a57a988fe43c6f141e08d404f47780fda1921f1b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458be46e7ac05a18391ea4dd140c46a5561fe6e1a242fde3488e581a747ed8ec
+oid sha256:dabe8c848817e7e95ad32f63be8edda0a3ab33ee3f00917dcfb2914eafa7069a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbf52846b0950d1b0204ef5064ad518cb02596007e36540f5b060f1237792f0
+oid sha256:d84f8729dd1de7f4282fffad9f7e569effad263825b832a900fab5a7e2e20f99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10148849797023005,
+  "epoch": 0.13531799729364005,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.0926,
       "step": 75
+    },
+    {
+      "epoch": 0.10284167794316644,
+      "grad_norm": 0.1009981706738472,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.009,
+      "step": 76
+    },
+    {
+      "epoch": 0.10419485791610285,
+      "grad_norm": 0.044376980513334274,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0047,
+      "step": 77
+    },
+    {
+      "epoch": 0.10554803788903924,
+      "grad_norm": 0.07079390436410904,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0048,
+      "step": 78
+    },
+    {
+      "epoch": 0.10690121786197564,
+      "grad_norm": 0.1579139083623886,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.006,
+      "step": 79
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 0.3575461208820343,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0312,
+      "step": 80
+    },
+    {
+      "epoch": 0.10960757780784844,
+      "grad_norm": 0.054556429386138916,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0069,
+      "step": 81
+    },
+    {
+      "epoch": 0.10960757780784844,
+      "eval_loss": 0.013904375955462456,
+      "eval_runtime": 32.5975,
+      "eval_samples_per_second": 19.112,
+      "eval_steps_per_second": 2.393,
+      "step": 81
+    },
+    {
+      "epoch": 0.11096075778078485,
+      "grad_norm": 0.059846166521310806,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0073,
+      "step": 82
+    },
+    {
+      "epoch": 0.11231393775372124,
+      "grad_norm": 0.07215581089258194,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0051,
+      "step": 83
+    },
+    {
+      "epoch": 0.11366711772665765,
+      "grad_norm": 0.1450567990541458,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0122,
+      "step": 84
+    },
+    {
+      "epoch": 0.11502029769959404,
+      "grad_norm": 0.03491105139255524,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0043,
+      "step": 85
+    },
+    {
+      "epoch": 0.11637347767253045,
+      "grad_norm": 0.5953935384750366,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0621,
+      "step": 86
+    },
+    {
+      "epoch": 0.11772665764546685,
+      "grad_norm": 0.4230695068836212,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0422,
+      "step": 87
+    },
+    {
+      "epoch": 0.11907983761840325,
+      "grad_norm": 0.033300649374723434,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0045,
+      "step": 88
+    },
+    {
+      "epoch": 0.12043301759133965,
+      "grad_norm": 0.30535688996315,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0485,
+      "step": 89
+    },
+    {
+      "epoch": 0.12178619756427606,
+      "grad_norm": 0.07103042304515839,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.004,
+      "step": 90
+    },
+    {
+      "epoch": 0.12178619756427606,
+      "eval_loss": 0.013438088819384575,
+      "eval_runtime": 32.5892,
+      "eval_samples_per_second": 19.117,
+      "eval_steps_per_second": 2.393,
+      "step": 90
+    },
+    {
+      "epoch": 0.12313937753721245,
+      "grad_norm": 0.11808881163597107,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0081,
+      "step": 91
+    },
+    {
+      "epoch": 0.12449255751014884,
+      "grad_norm": 0.033296674489974976,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0045,
+      "step": 92
+    },
+    {
+      "epoch": 0.12584573748308525,
+      "grad_norm": 0.19024379551410675,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0157,
+      "step": 93
+    },
+    {
+      "epoch": 0.12719891745602166,
+      "grad_norm": 0.7022133469581604,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0563,
+      "step": 94
+    },
+    {
+      "epoch": 0.12855209742895804,
+      "grad_norm": 0.110652394592762,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0102,
+      "step": 95
+    },
+    {
+      "epoch": 0.12990527740189445,
+      "grad_norm": 0.110796257853508,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0116,
+      "step": 96
+    },
+    {
+      "epoch": 0.13125845737483086,
+      "grad_norm": 0.03754672780632973,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0038,
+      "step": 97
+    },
+    {
+      "epoch": 0.13261163734776726,
+      "grad_norm": 0.07318272441625595,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0019,
+      "step": 98
+    },
+    {
+      "epoch": 0.13396481732070364,
+      "grad_norm": 0.4888281226158142,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0511,
+      "step": 99
+    },
+    {
+      "epoch": 0.13396481732070364,
+      "eval_loss": 0.013342314399778843,
+      "eval_runtime": 32.607,
+      "eval_samples_per_second": 19.106,
+      "eval_steps_per_second": 2.392,
+      "step": 99
+    },
+    {
+      "epoch": 0.13531799729364005,
+      "grad_norm": 0.3825893998146057,
+      "learning_rate": 0.0,
+      "loss": 0.0563,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null