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:a0884a18520e98bc234cf5efb85a6dab006f9cfdeefc1fe69f0b1bfac06ae772
+oid sha256:e3a65323ea06d846ff00e0fe49dbc64106a4fef984c945f0f33a032e5714c670
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16aa49dc4208e36e7d3beeb4d278e4525e5d63486e3c2c46d3d3d54978554fc4
+oid sha256:21fafe7b723436e07f85fe900384d83380f6f89264eb8afbbf3a64329addbde3
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c100084e23227ee0bf91d5e993c945c41c64c3e875956ba2527580e2a582e39
+oid sha256:f393bd09a8d9d50ab18ca1ed3e45ac21376e06098dc37d54550156e9be1fe94f
 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": 0.16339869281045752,
+  "epoch": 0.2178649237472767,
   "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": 1.8198,
       "step": 75
+    },
+    {
+      "epoch": 0.1655773420479303,
+      "grad_norm": 1.8424410820007324,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.7089,
+      "step": 76
+    },
+    {
+      "epoch": 0.16775599128540306,
+      "grad_norm": 1.5348371267318726,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.8777,
+      "step": 77
+    },
+    {
+      "epoch": 0.16993464052287582,
+      "grad_norm": 1.4218686819076538,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8016,
+      "step": 78
+    },
+    {
+      "epoch": 0.1721132897603486,
+      "grad_norm": 1.4566261768341064,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.7037,
+      "step": 79
+    },
+    {
+      "epoch": 0.17429193899782136,
+      "grad_norm": 1.4800132513046265,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7889,
+      "step": 80
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 1.4129917621612549,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.8648,
+      "step": 81
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "eval_loss": 0.884328305721283,
+      "eval_runtime": 63.6367,
+      "eval_samples_per_second": 6.081,
+      "eval_steps_per_second": 0.77,
+      "step": 81
+    },
+    {
+      "epoch": 0.1786492374727669,
+      "grad_norm": 2.1455793380737305,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9025,
+      "step": 82
+    },
+    {
+      "epoch": 0.18082788671023964,
+      "grad_norm": 1.6186474561691284,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.0026,
+      "step": 83
+    },
+    {
+      "epoch": 0.1830065359477124,
+      "grad_norm": 1.6770442724227905,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.9087,
+      "step": 84
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.7015310525894165,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9845,
+      "step": 85
+    },
+    {
+      "epoch": 0.18736383442265794,
+      "grad_norm": 1.4738478660583496,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.8843,
+      "step": 86
+    },
+    {
+      "epoch": 0.1895424836601307,
+      "grad_norm": 1.548987627029419,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.9916,
+      "step": 87
+    },
+    {
+      "epoch": 0.19172113289760348,
+      "grad_norm": 1.4082995653152466,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7131,
+      "step": 88
+    },
+    {
+      "epoch": 0.19389978213507625,
+      "grad_norm": 1.434032678604126,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.8378,
+      "step": 89
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 1.4525424242019653,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.606,
+      "step": 90
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "eval_loss": 0.8813257217407227,
+      "eval_runtime": 63.7104,
+      "eval_samples_per_second": 6.074,
+      "eval_steps_per_second": 0.769,
+      "step": 90
+    },
+    {
+      "epoch": 0.19825708061002179,
+      "grad_norm": 1.4912457466125488,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6441,
+      "step": 91
+    },
+    {
+      "epoch": 0.20043572984749455,
+      "grad_norm": 1.4377028942108154,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8356,
+      "step": 92
+    },
+    {
+      "epoch": 0.20261437908496732,
+      "grad_norm": 1.555307388305664,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.7871,
+      "step": 93
+    },
+    {
+      "epoch": 0.2047930283224401,
+      "grad_norm": 1.4429875612258911,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.716,
+      "step": 94
+    },
+    {
+      "epoch": 0.20697167755991286,
+      "grad_norm": 1.669837236404419,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7517,
+      "step": 95
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 1.4851337671279907,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7941,
+      "step": 96
+    },
+    {
+      "epoch": 0.2113289760348584,
+      "grad_norm": 1.3839343786239624,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.7239,
+      "step": 97
+    },
+    {
+      "epoch": 0.21350762527233116,
+      "grad_norm": 1.7010775804519653,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.8666,
+      "step": 98
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 1.3769611120224,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.6545,
+      "step": 99
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "eval_loss": 0.8808857798576355,
+      "eval_runtime": 63.6882,
+      "eval_samples_per_second": 6.076,
+      "eval_steps_per_second": 0.769,
+      "step": 99
+    },
+    {
+      "epoch": 0.2178649237472767,
+      "grad_norm": 1.4309481382369995,
+      "learning_rate": 0.0,
+      "loss": 1.7055,
+      "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": 9.71211823644672e+16,
+  "total_flos": 1.294949098192896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null