Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e680ee2c2476949628f7366695a0c32f59d6d93f0e585487f6c56f203a1aa0b
+oid sha256:da4c62198e7b465902173595bc22987ef6fc9493f08cec2e7ec2be45b77e2064
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d5c65e3da72264dba66d43a8b1a1d24d93be612b9801906a9aebaae0005042
+oid sha256:eaf663b4d90aae738fac12e02253702079c68627849435b5e3530263f9b5e305
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62577c705b5e0903a8d1b61ec40f0dd9672c14fc3d9beee0560e32a4d664d0c
+oid sha256:29dfce459bfef11512041671bca91604f66b1ddbefa3947517889259b1e8c185
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.973684210526316,
+  "epoch": 2.6315789473684212,
   "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": 3.5721239031346067e-06,
       "loss": 11.9336,
       "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.12733624875545502,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 11.9317,
+      "step": 76
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.11955931782722473,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 11.9332,
+      "step": 77
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.12203284353017807,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 11.9336,
+      "step": 78
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.11557573080062866,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 11.935,
+      "step": 79
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.11184758692979813,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 11.9334,
+      "step": 80
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.11658318340778351,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 11.9318,
+      "step": 81
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "eval_loss": 11.934183120727539,
+      "eval_runtime": 0.2378,
+      "eval_samples_per_second": 134.56,
+      "eval_steps_per_second": 16.82,
+      "step": 81
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.12175559997558594,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 11.9295,
+      "step": 82
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.12202810496091843,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 11.9312,
+      "step": 83
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.11515302211046219,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 11.9304,
+      "step": 84
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.12328758090734482,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 11.9333,
+      "step": 85
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.11292904615402222,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 11.9314,
+      "step": 86
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.11836957186460495,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 11.9333,
+      "step": 87
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.12082057446241379,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 11.9331,
+      "step": 88
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.12002652883529663,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 11.9315,
+      "step": 89
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.11815308779478073,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 11.9319,
+      "step": 90
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "eval_loss": 11.934161186218262,
+      "eval_runtime": 0.2374,
+      "eval_samples_per_second": 134.795,
+      "eval_steps_per_second": 16.849,
+      "step": 90
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.12135819345712662,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 11.9338,
+      "step": 91
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.11574351787567139,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 11.9336,
+      "step": 92
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.11911027133464813,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 11.9317,
+      "step": 93
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.11090245842933655,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 11.9326,
+      "step": 94
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12132039666175842,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 11.9294,
+      "step": 95
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.11585205793380737,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 11.9326,
+      "step": 96
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.11518601328134537,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 11.9329,
+      "step": 97
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.13855737447738647,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 11.9338,
+      "step": 98
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.11981800943613052,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 11.9323,
+      "step": 99
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "eval_loss": 11.93415641784668,
+      "eval_runtime": 0.2375,
+      "eval_samples_per_second": 134.725,
+      "eval_steps_per_second": 16.841,
+      "step": 99
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.12501810491085052,
+      "learning_rate": 0.0,
+      "loss": 11.9326,
+      "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": 56022859776.0,
+  "total_flos": 74572234752.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null