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:af03696eb7ebf496a2f3071895b47c1b493fe6a3b2efa91a15b26781f6f4db0f
+oid sha256:bb2e812288d309133aae30a4e2ab39ce4311efe5165e9d48d0dfef65d381d95c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1d7d5be86b7f5014ecf5f0b4221f25d696fed448ab1ffc75974caea9b4aca3
+oid sha256:227f4b5077da6653384f19dcc642331f62c758409736889932db9fb4421f63d4
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68167c8d678477ffebb09a051524db7dc0a47c6ca5fdd9731dea2d4cf533e2d
+oid sha256:0211afb67fcb6f9ca60d62990174660fae3a84e1870561d0f6869ce76b4d3984
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d334bd1b13cd7760eff044b538d4dfa8741682e468a17c5d3030193ddce227de
+oid sha256:f222c17478fb114ecaf51e861347c79cb7813e276551b6f859323a82ab647ad8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e108a8669fed0b2412fe70b3d74e1fb045fa29dbdcfc8bdea1ed862bcde354
+oid sha256:09c8e018d20cd6d9a718036ab145aeb574c16648c33b4debe4b130f9c0651622
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e8f1adbd80f39ab0112d83af61b731937afc180931e7ce4fe124b11969a609
+oid sha256:fe940586a81b5a518b2ed6f22a0bf0191b6f987cf05456fafe7ff74873ed1c6d
 size 15024

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": 0.20408163265306123,
+  "epoch": 0.272108843537415,
   "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": 0.7707,
       "step": 75
+    },
+    {
+      "epoch": 0.20680272108843537,
+      "grad_norm": 0.1923210769891739,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7343,
+      "step": 76
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 0.15001152455806732,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6671,
+      "step": 77
+    },
+    {
+      "epoch": 0.21224489795918366,
+      "grad_norm": 0.18915919959545135,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7056,
+      "step": 78
+    },
+    {
+      "epoch": 0.21496598639455783,
+      "grad_norm": 0.19046439230442047,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.83,
+      "step": 79
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 0.17637431621551514,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7493,
+      "step": 80
+    },
+    {
+      "epoch": 0.22040816326530613,
+      "grad_norm": 0.153495192527771,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.7012,
+      "step": 81
+    },
+    {
+      "epoch": 0.22040816326530613,
+      "eval_loss": 0.7618221640586853,
+      "eval_runtime": 32.195,
+      "eval_samples_per_second": 38.422,
+      "eval_steps_per_second": 1.211,
+      "step": 81
+    },
+    {
+      "epoch": 0.22312925170068026,
+      "grad_norm": 0.16720904409885406,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7049,
+      "step": 82
+    },
+    {
+      "epoch": 0.22585034013605443,
+      "grad_norm": 0.16498345136642456,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.6583,
+      "step": 83
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.17059318721294403,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.812,
+      "step": 84
+    },
+    {
+      "epoch": 0.23129251700680273,
+      "grad_norm": 0.14581593871116638,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7116,
+      "step": 85
+    },
+    {
+      "epoch": 0.23401360544217686,
+      "grad_norm": 0.18653877079486847,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9057,
+      "step": 86
+    },
+    {
+      "epoch": 0.23673469387755103,
+      "grad_norm": 0.17196914553642273,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.7439,
+      "step": 87
+    },
+    {
+      "epoch": 0.23945578231292516,
+      "grad_norm": 0.17426681518554688,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8396,
+      "step": 88
+    },
+    {
+      "epoch": 0.24217687074829933,
+      "grad_norm": 0.18171295523643494,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.7002,
+      "step": 89
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.17335541546344757,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7719,
+      "step": 90
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "eval_loss": 0.7605471014976501,
+      "eval_runtime": 32.1868,
+      "eval_samples_per_second": 38.432,
+      "eval_steps_per_second": 1.212,
+      "step": 90
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 0.1640811711549759,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7349,
+      "step": 91
+    },
+    {
+      "epoch": 0.2503401360544218,
+      "grad_norm": 0.20482207834720612,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.7466,
+      "step": 92
+    },
+    {
+      "epoch": 0.2530612244897959,
+      "grad_norm": 0.16231241822242737,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5886,
+      "step": 93
+    },
+    {
+      "epoch": 0.25578231292517006,
+      "grad_norm": 0.16183051466941833,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7642,
+      "step": 94
+    },
+    {
+      "epoch": 0.2585034013605442,
+      "grad_norm": 0.1630152016878128,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6387,
+      "step": 95
+    },
+    {
+      "epoch": 0.2612244897959184,
+      "grad_norm": 0.1637643575668335,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6792,
+      "step": 96
+    },
+    {
+      "epoch": 0.2639455782312925,
+      "grad_norm": 0.1643003672361374,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.7333,
+      "step": 97
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.1853807270526886,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7241,
+      "step": 98
+    },
+    {
+      "epoch": 0.2693877551020408,
+      "grad_norm": 0.16440825164318085,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6817,
+      "step": 99
+    },
+    {
+      "epoch": 0.2693877551020408,
+      "eval_loss": 0.7603068947792053,
+      "eval_runtime": 32.195,
+      "eval_samples_per_second": 38.422,
+      "eval_steps_per_second": 1.211,
+      "step": 99
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.19654084742069244,
+      "learning_rate": 0.0,
+      "loss": 0.8268,
+      "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": 2.5782671256426906e+17,
+  "total_flos": 3.4409949730072166e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null