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:e7e00262fed0eeed878ece671c0885e8d6bc3f98d981f69baedb78d4a47c8dcb
+oid sha256:ce06af45fd71af1c250463027f4204b51137a08e49f13d10bab0a7b80afaf166
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ca007e6058e2aeeb280cad035dddd3aee30db465160559d6ddb42d0b198c54
+oid sha256:7ddff391f28d3018c07f9cd75b0590d53d6ace739f10fdd4e07996043fbed4a3
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb641ed1c277039af8b8ba2d9d53cbbb8c158dbe992dc8c6e1ce8826e06e00b0
+oid sha256:17917bbbb57276591a226a85ea518396eb01a0200369b98ab651385e568363c9
 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": 0.007471235742391792,
+  "epoch": 0.009961647656522389,
   "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": 1.3527,
       "step": 75
+    },
+    {
+      "epoch": 0.007570852218957015,
+      "grad_norm": 0.8617198467254639,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4376,
+      "step": 76
+    },
+    {
+      "epoch": 0.007670468695522239,
+      "grad_norm": 0.8097233772277832,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4977,
+      "step": 77
+    },
+    {
+      "epoch": 0.0077700851720874636,
+      "grad_norm": 0.6698528528213501,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2981,
+      "step": 78
+    },
+    {
+      "epoch": 0.007869701648652687,
+      "grad_norm": 0.9840778708457947,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4803,
+      "step": 79
+    },
+    {
+      "epoch": 0.00796931812521791,
+      "grad_norm": 0.89268958568573,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8106,
+      "step": 80
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "grad_norm": 0.7866905927658081,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.6302,
+      "step": 81
+    },
+    {
+      "epoch": 0.008068934601783135,
+      "eval_loss": 0.7663864493370056,
+      "eval_runtime": 1983.5768,
+      "eval_samples_per_second": 4.262,
+      "eval_steps_per_second": 0.533,
+      "step": 81
+    },
+    {
+      "epoch": 0.008168551078348359,
+      "grad_norm": 0.6179813742637634,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2949,
+      "step": 82
+    },
+    {
+      "epoch": 0.008268167554913582,
+      "grad_norm": 0.5955004692077637,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3741,
+      "step": 83
+    },
+    {
+      "epoch": 0.008367784031478807,
+      "grad_norm": 0.6240610480308533,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3025,
+      "step": 84
+    },
+    {
+      "epoch": 0.00846740050804403,
+      "grad_norm": 0.7150053977966309,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4859,
+      "step": 85
+    },
+    {
+      "epoch": 0.008567016984609254,
+      "grad_norm": 0.7417619228363037,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4521,
+      "step": 86
+    },
+    {
+      "epoch": 0.008666633461174479,
+      "grad_norm": 0.6979576945304871,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.5195,
+      "step": 87
+    },
+    {
+      "epoch": 0.008766249937739702,
+      "grad_norm": 0.7996464371681213,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6097,
+      "step": 88
+    },
+    {
+      "epoch": 0.008865866414304925,
+      "grad_norm": 0.7870691418647766,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.6533,
+      "step": 89
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "grad_norm": 0.6725627183914185,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3191,
+      "step": 90
+    },
+    {
+      "epoch": 0.00896548289087015,
+      "eval_loss": 0.7657433152198792,
+      "eval_runtime": 1983.6936,
+      "eval_samples_per_second": 4.262,
+      "eval_steps_per_second": 0.533,
+      "step": 90
+    },
+    {
+      "epoch": 0.009065099367435374,
+      "grad_norm": 0.7659081816673279,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6397,
+      "step": 91
+    },
+    {
+      "epoch": 0.009164715844000597,
+      "grad_norm": 0.6460014581680298,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3172,
+      "step": 92
+    },
+    {
+      "epoch": 0.009264332320565822,
+      "grad_norm": 0.665287435054779,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.2986,
+      "step": 93
+    },
+    {
+      "epoch": 0.009363948797131046,
+      "grad_norm": 0.7975252866744995,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6436,
+      "step": 94
+    },
+    {
+      "epoch": 0.009463565273696269,
+      "grad_norm": 0.6706257462501526,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.5118,
+      "step": 95
+    },
+    {
+      "epoch": 0.009563181750261494,
+      "grad_norm": 0.7847915291786194,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3296,
+      "step": 96
+    },
+    {
+      "epoch": 0.009662798226826717,
+      "grad_norm": 0.6760066747665405,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.5437,
+      "step": 97
+    },
+    {
+      "epoch": 0.00976241470339194,
+      "grad_norm": 0.6760746836662292,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4752,
+      "step": 98
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "grad_norm": 0.6780611872673035,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4912,
+      "step": 99
+    },
+    {
+      "epoch": 0.009862031179957166,
+      "eval_loss": 0.7656309604644775,
+      "eval_runtime": 1983.1932,
+      "eval_samples_per_second": 4.263,
+      "eval_steps_per_second": 0.533,
+      "step": 99
+    },
+    {
+      "epoch": 0.009961647656522389,
+      "grad_norm": 0.7122662663459778,
+      "learning_rate": 0.0,
+      "loss": 1.5126,
+      "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": 9.648701542760448e+16,
+  "total_flos": 1.2886094823555072e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null