Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346e6cf8810a70a39be4291afc346b53c918c3cf7d506748ade2a7e326054d9d
+oid sha256:cf7106fd24d86ced938a85e65ce3b96d739d5e0bca8cf74862446fec627ec6d8
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fb1965a8bd54c8d5fd4d7a2dd0af957c38ef401e7225b649137b0348bd3715
+oid sha256:f3b23ab603dc5084af19500627d223279963c2188296aefefffd83e13865e89d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a125448ed2516369b44b30100b1f18cd9f7f375067d6e1c9d8cd2ace51dbb90c
+oid sha256:ba07a639b2fd996fe5ba125d561445b8f28a56026f31d77915d6b10dc44487ed
 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": 0.20920502092050208,
+  "epoch": 0.2789400278940028,
   "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": 0.213,
       "step": 75
+    },
+    {
+      "epoch": 0.21199442119944212,
+      "grad_norm": 0.6184529662132263,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.1864,
+      "step": 76
+    },
+    {
+      "epoch": 0.21478382147838215,
+      "grad_norm": 0.8859326839447021,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.37,
+      "step": 77
+    },
+    {
+      "epoch": 0.2175732217573222,
+      "grad_norm": 0.6930046677589417,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2325,
+      "step": 78
+    },
+    {
+      "epoch": 0.2203626220362622,
+      "grad_norm": 0.6587538719177246,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2372,
+      "step": 79
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 0.5163601636886597,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.1806,
+      "step": 80
+    },
+    {
+      "epoch": 0.22594142259414227,
+      "grad_norm": 0.7977961301803589,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.2736,
+      "step": 81
+    },
+    {
+      "epoch": 0.22594142259414227,
+      "eval_loss": 0.23303189873695374,
+      "eval_runtime": 52.7206,
+      "eval_samples_per_second": 5.728,
+      "eval_steps_per_second": 0.721,
+      "step": 81
+    },
+    {
+      "epoch": 0.22873082287308227,
+      "grad_norm": 1.0265192985534668,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3048,
+      "step": 82
+    },
+    {
+      "epoch": 0.2315202231520223,
+      "grad_norm": 0.7465397715568542,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2165,
+      "step": 83
+    },
+    {
+      "epoch": 0.23430962343096234,
+      "grad_norm": 0.7663724422454834,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.2594,
+      "step": 84
+    },
+    {
+      "epoch": 0.23709902370990238,
+      "grad_norm": 0.858521580696106,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2692,
+      "step": 85
+    },
+    {
+      "epoch": 0.2398884239888424,
+      "grad_norm": 0.5936315059661865,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.2348,
+      "step": 86
+    },
+    {
+      "epoch": 0.24267782426778242,
+      "grad_norm": 0.5714499354362488,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.187,
+      "step": 87
+    },
+    {
+      "epoch": 0.24546722454672246,
+      "grad_norm": 0.7403538823127747,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1411,
+      "step": 88
+    },
+    {
+      "epoch": 0.2482566248256625,
+      "grad_norm": 0.9827370047569275,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2321,
+      "step": 89
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 0.9658119678497314,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.241,
+      "step": 90
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "eval_loss": 0.2301451861858368,
+      "eval_runtime": 52.756,
+      "eval_samples_per_second": 5.724,
+      "eval_steps_per_second": 0.72,
+      "step": 90
+    },
+    {
+      "epoch": 0.25383542538354253,
+      "grad_norm": 0.5446522235870361,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1993,
+      "step": 91
+    },
+    {
+      "epoch": 0.25662482566248257,
+      "grad_norm": 0.6010146737098694,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.179,
+      "step": 92
+    },
+    {
+      "epoch": 0.2594142259414226,
+      "grad_norm": 0.695270836353302,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.1544,
+      "step": 93
+    },
+    {
+      "epoch": 0.26220362622036264,
+      "grad_norm": 0.5995609164237976,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2263,
+      "step": 94
+    },
+    {
+      "epoch": 0.2649930264993027,
+      "grad_norm": 0.9947669506072998,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2255,
+      "step": 95
+    },
+    {
+      "epoch": 0.26778242677824265,
+      "grad_norm": 0.6095288991928101,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1982,
+      "step": 96
+    },
+    {
+      "epoch": 0.2705718270571827,
+      "grad_norm": 0.7338091731071472,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.1718,
+      "step": 97
+    },
+    {
+      "epoch": 0.2733612273361227,
+      "grad_norm": 1.0805656909942627,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3113,
+      "step": 98
+    },
+    {
+      "epoch": 0.27615062761506276,
+      "grad_norm": 0.7472536563873291,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2833,
+      "step": 99
+    },
+    {
+      "epoch": 0.27615062761506276,
+      "eval_loss": 0.2296682894229889,
+      "eval_runtime": 52.738,
+      "eval_samples_per_second": 5.726,
+      "eval_steps_per_second": 0.721,
+      "step": 99
+    },
+    {
+      "epoch": 0.2789400278940028,
+      "grad_norm": 0.7433314919471741,
+      "learning_rate": 0.0,
+      "loss": 0.2479,
+      "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": 9.775600008953856e+16,
+  "total_flos": 1.301297403789312e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null