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:e47c0bdd2b8b0f477ab781ef75d231a168393cea032b0b85432d8b5017d345b5
+oid sha256:924780a51bf6e60db07377ce44ae213e0452c4a39fcd125abf7c85d015596471
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c6aac068723de8b0d1c7754c9b5995f886051074a43f90783fe73983192b10
+oid sha256:4ca60e2e6a6fa91fac191e74aaa854b92a10bed2e2cc24f3237fc07f9e378510
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b89dd38db98ad38a01577cdd46c96a298f4583db1a347ee24c5352fb1155451
+oid sha256:fde104bab0adc1cc90c60a95e124ce8958368abce247283c13e815fc5610de65
 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": 0.01686719892049927,
+  "epoch": 0.02248959856066569,
   "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": 0.002,
       "step": 75
+    },
+    {
+      "epoch": 0.017092094906105925,
+      "grad_norm": 0.14664563536643982,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0057,
+      "step": 76
+    },
+    {
+      "epoch": 0.017316990891712583,
+      "grad_norm": 0.34025806188583374,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0177,
+      "step": 77
+    },
+    {
+      "epoch": 0.01754188687731924,
+      "grad_norm": 0.06838779151439667,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0017,
+      "step": 78
+    },
+    {
+      "epoch": 0.017766782862925896,
+      "grad_norm": 0.26176440715789795,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0083,
+      "step": 79
+    },
+    {
+      "epoch": 0.017991678848532554,
+      "grad_norm": 0.09657137840986252,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.002,
+      "step": 80
+    },
+    {
+      "epoch": 0.018216574834139212,
+      "grad_norm": 0.19221985340118408,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0046,
+      "step": 81
+    },
+    {
+      "epoch": 0.018216574834139212,
+      "eval_loss": 0.0055376277305185795,
+      "eval_runtime": 821.3874,
+      "eval_samples_per_second": 4.559,
+      "eval_steps_per_second": 0.571,
+      "step": 81
+    },
+    {
+      "epoch": 0.018441470819745866,
+      "grad_norm": 0.33126604557037354,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0095,
+      "step": 82
+    },
+    {
+      "epoch": 0.018666366805352524,
+      "grad_norm": 0.169240802526474,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0037,
+      "step": 83
+    },
+    {
+      "epoch": 0.018891262790959183,
+      "grad_norm": 0.241820827126503,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0044,
+      "step": 84
+    },
+    {
+      "epoch": 0.019116158776565837,
+      "grad_norm": 0.13180238008499146,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0033,
+      "step": 85
+    },
+    {
+      "epoch": 0.019341054762172495,
+      "grad_norm": 0.1824703961610794,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0062,
+      "step": 86
+    },
+    {
+      "epoch": 0.019565950747779153,
+      "grad_norm": 0.04633178561925888,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0012,
+      "step": 87
+    },
+    {
+      "epoch": 0.019790846733385808,
+      "grad_norm": 0.1503739207983017,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0056,
+      "step": 88
+    },
+    {
+      "epoch": 0.020015742718992466,
+      "grad_norm": 0.253187894821167,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0033,
+      "step": 89
+    },
+    {
+      "epoch": 0.020240638704599124,
+      "grad_norm": 0.07967644929885864,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0024,
+      "step": 90
+    },
+    {
+      "epoch": 0.020240638704599124,
+      "eval_loss": 0.004993786569684744,
+      "eval_runtime": 821.3337,
+      "eval_samples_per_second": 4.56,
+      "eval_steps_per_second": 0.571,
+      "step": 90
+    },
+    {
+      "epoch": 0.02046553469020578,
+      "grad_norm": 0.06979195773601532,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0033,
+      "step": 91
+    },
+    {
+      "epoch": 0.020690430675812437,
+      "grad_norm": 0.08530198037624359,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0031,
+      "step": 92
+    },
+    {
+      "epoch": 0.020915326661419095,
+      "grad_norm": 0.17425432801246643,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0109,
+      "step": 93
+    },
+    {
+      "epoch": 0.02114022264702575,
+      "grad_norm": 0.22065205872058868,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0095,
+      "step": 94
+    },
+    {
+      "epoch": 0.021365118632632407,
+      "grad_norm": 0.10856463760137558,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0047,
+      "step": 95
+    },
+    {
+      "epoch": 0.021590014618239065,
+      "grad_norm": 0.06562183052301407,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0012,
+      "step": 96
+    },
+    {
+      "epoch": 0.02181491060384572,
+      "grad_norm": 0.3388810455799103,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0057,
+      "step": 97
+    },
+    {
+      "epoch": 0.022039806589452378,
+      "grad_norm": 0.06389345973730087,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0012,
+      "step": 98
+    },
+    {
+      "epoch": 0.022264702575059036,
+      "grad_norm": 0.19869062304496765,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0014,
+      "step": 99
+    },
+    {
+      "epoch": 0.022264702575059036,
+      "eval_loss": 0.004959506914019585,
+      "eval_runtime": 821.4562,
+      "eval_samples_per_second": 4.559,
+      "eval_steps_per_second": 0.571,
+      "step": 99
+    },
+    {
+      "epoch": 0.02248959856066569,
+      "grad_norm": 0.058610107749700546,
+      "learning_rate": 0.0,
+      "loss": 0.0011,
+      "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": 1.097993179669463e+17,
+  "total_flos": 1.4652273850318848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null