Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1ab521862ead76ebb9df07437ff66ef9cd30a4cac01e587f8eb20c99795ae6
+oid sha256:22e1b51214a902356cef838d377f3142cdc7f60559783e0d1329a6beaed9836e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d69c16d9fc9d7386cf0bebc0ccc9d2ac684edd9db4cc28ca24c0a9a6cc75d0
+oid sha256:951f847f1d0ef4b5212b7730de68118dd2a81d95f0b08b415a01eff938d18bcf
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 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": 0.0033324446814182885,
+  "epoch": 0.004443259575224384,
   "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": 1.0196,
       "step": 75
+    },
+    {
+      "epoch": 0.003376877277170532,
+      "grad_norm": 2.326871871948242,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.7437,
+      "step": 76
+    },
+    {
+      "epoch": 0.003421309872922776,
+      "grad_norm": 2.7183380126953125,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6249,
+      "step": 77
+    },
+    {
+      "epoch": 0.00346574246867502,
+      "grad_norm": 2.6709814071655273,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.668,
+      "step": 78
+    },
+    {
+      "epoch": 0.003510175064427264,
+      "grad_norm": 2.335897207260132,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4872,
+      "step": 79
+    },
+    {
+      "epoch": 0.003554607660179508,
+      "grad_norm": 3.3873088359832764,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0067,
+      "step": 80
+    },
+    {
+      "epoch": 0.0035990402559317515,
+      "grad_norm": 3.065892457962036,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.8042,
+      "step": 81
+    },
+    {
+      "epoch": 0.0035990402559317515,
+      "eval_loss": 0.7969595789909363,
+      "eval_runtime": 2089.1579,
+      "eval_samples_per_second": 9.072,
+      "eval_steps_per_second": 1.134,
+      "step": 81
+    },
+    {
+      "epoch": 0.0036434728516839955,
+      "grad_norm": 3.0394890308380127,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8169,
+      "step": 82
+    },
+    {
+      "epoch": 0.003687905447436239,
+      "grad_norm": 2.319058418273926,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2704,
+      "step": 83
+    },
+    {
+      "epoch": 0.003732338043188483,
+      "grad_norm": 3.6886699199676514,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.8313,
+      "step": 84
+    },
+    {
+      "epoch": 0.0037767706389407268,
+      "grad_norm": 2.6520419120788574,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8752,
+      "step": 85
+    },
+    {
+      "epoch": 0.003821203234692971,
+      "grad_norm": 2.6148107051849365,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.7429,
+      "step": 86
+    },
+    {
+      "epoch": 0.0038656358304452144,
+      "grad_norm": 2.711278200149536,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.5209,
+      "step": 87
+    },
+    {
+      "epoch": 0.0039100684261974585,
+      "grad_norm": 2.5776398181915283,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6768,
+      "step": 88
+    },
+    {
+      "epoch": 0.0039545010219497025,
+      "grad_norm": 2.9126386642456055,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.8562,
+      "step": 89
+    },
+    {
+      "epoch": 0.0039989336177019465,
+      "grad_norm": 3.8028640747070312,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8226,
+      "step": 90
+    },
+    {
+      "epoch": 0.0039989336177019465,
+      "eval_loss": 0.7885631918907166,
+      "eval_runtime": 2088.9791,
+      "eval_samples_per_second": 9.073,
+      "eval_steps_per_second": 1.135,
+      "step": 90
+    },
+    {
+      "epoch": 0.00404336621345419,
+      "grad_norm": 3.353768825531006,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7805,
+      "step": 91
+    },
+    {
+      "epoch": 0.004087798809206434,
+      "grad_norm": 3.188265800476074,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.8433,
+      "step": 92
+    },
+    {
+      "epoch": 0.004132231404958678,
+      "grad_norm": 4.046318531036377,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.9672,
+      "step": 93
+    },
+    {
+      "epoch": 0.004176664000710922,
+      "grad_norm": 2.8643298149108887,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6082,
+      "step": 94
+    },
+    {
+      "epoch": 0.004221096596463165,
+      "grad_norm": 2.820201873779297,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5979,
+      "step": 95
+    },
+    {
+      "epoch": 0.004265529192215409,
+      "grad_norm": 3.394400119781494,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9704,
+      "step": 96
+    },
+    {
+      "epoch": 0.004309961787967653,
+      "grad_norm": 2.8901283740997314,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.7127,
+      "step": 97
+    },
+    {
+      "epoch": 0.004354394383719897,
+      "grad_norm": 4.210619926452637,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.9518,
+      "step": 98
+    },
+    {
+      "epoch": 0.004398826979472141,
+      "grad_norm": 4.082587718963623,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6261,
+      "step": 99
+    },
+    {
+      "epoch": 0.004398826979472141,
+      "eval_loss": 0.7863272428512573,
+      "eval_runtime": 2088.7224,
+      "eval_samples_per_second": 9.074,
+      "eval_steps_per_second": 1.135,
+      "step": 99
+    },
+    {
+      "epoch": 0.004443259575224384,
+      "grad_norm": 3.289276123046875,
+      "learning_rate": 0.0,
+      "loss": 0.7214,
+      "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