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:d6c14db16ae939563bfd7f77f481652adc40a1c44c519f3d7b2f0ffea59fa22d
+oid sha256:f9528ea6157193d8c73e8041097f2fcad9f26acadcce8593ebd87123769803a5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7157ace55e21441c39f0053e91d612267b4245a7059d9cb2d6a5b40e7ef3f38c
+oid sha256:c80eee6bbe3f8ebb191ead420c5440dbaecc13c3d0cf3d6dfc7a3e5102dea162
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96323bc0145b007148e0ac1a1191d65679d19bd7a42613934c93d5877e5a9c1a
+oid sha256:be1b2bd51912347ce0f2d2edd5252ab9151afcca2a501c58192068c28c41e72e
 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": 0.11355034065102196,
+  "epoch": 0.1514004542013626,
   "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": 0.6652,
       "step": 75
+    },
+    {
+      "epoch": 0.11506434519303559,
+      "grad_norm": 0.6131309866905212,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6047,
+      "step": 76
+    },
+    {
+      "epoch": 0.1165783497350492,
+      "grad_norm": 0.7499487996101379,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.6008,
+      "step": 77
+    },
+    {
+      "epoch": 0.11809235427706283,
+      "grad_norm": 0.6790719032287598,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.5155,
+      "step": 78
+    },
+    {
+      "epoch": 0.11960635881907646,
+      "grad_norm": 0.6743375062942505,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6428,
+      "step": 79
+    },
+    {
+      "epoch": 0.12112036336109008,
+      "grad_norm": 0.7786680459976196,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.5635,
+      "step": 80
+    },
+    {
+      "epoch": 0.12263436790310371,
+      "grad_norm": 0.739784300327301,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6186,
+      "step": 81
+    },
+    {
+      "epoch": 0.12263436790310371,
+      "eval_loss": 0.5935469269752502,
+      "eval_runtime": 113.3177,
+      "eval_samples_per_second": 4.907,
+      "eval_steps_per_second": 0.618,
+      "step": 81
+    },
+    {
+      "epoch": 0.12414837244511734,
+      "grad_norm": 0.7188571095466614,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6752,
+      "step": 82
+    },
+    {
+      "epoch": 0.12566237698713095,
+      "grad_norm": 0.7058334946632385,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.5593,
+      "step": 83
+    },
+    {
+      "epoch": 0.1271763815291446,
+      "grad_norm": 0.6624956727027893,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.5787,
+      "step": 84
+    },
+    {
+      "epoch": 0.1286903860711582,
+      "grad_norm": 0.6044244170188904,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6942,
+      "step": 85
+    },
+    {
+      "epoch": 0.13020439061317185,
+      "grad_norm": 0.7235444188117981,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6307,
+      "step": 86
+    },
+    {
+      "epoch": 0.13171839515518546,
+      "grad_norm": 0.702789843082428,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.4461,
+      "step": 87
+    },
+    {
+      "epoch": 0.1332323996971991,
+      "grad_norm": 0.8075714111328125,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4181,
+      "step": 88
+    },
+    {
+      "epoch": 0.13474640423921272,
+      "grad_norm": 0.7328047752380371,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.6952,
+      "step": 89
+    },
+    {
+      "epoch": 0.13626040878122633,
+      "grad_norm": 0.6701781749725342,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5725,
+      "step": 90
+    },
+    {
+      "epoch": 0.13626040878122633,
+      "eval_loss": 0.5923717617988586,
+      "eval_runtime": 112.5462,
+      "eval_samples_per_second": 4.94,
+      "eval_steps_per_second": 0.622,
+      "step": 90
+    },
+    {
+      "epoch": 0.13777441332323997,
+      "grad_norm": 0.6329877376556396,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6874,
+      "step": 91
+    },
+    {
+      "epoch": 0.1392884178652536,
+      "grad_norm": 0.6350424885749817,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6707,
+      "step": 92
+    },
+    {
+      "epoch": 0.14080242240726723,
+      "grad_norm": 0.657054603099823,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5518,
+      "step": 93
+    },
+    {
+      "epoch": 0.14231642694928084,
+      "grad_norm": 0.7105988264083862,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.5976,
+      "step": 94
+    },
+    {
+      "epoch": 0.14383043149129449,
+      "grad_norm": 0.6418373584747314,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5714,
+      "step": 95
+    },
+    {
+      "epoch": 0.1453444360333081,
+      "grad_norm": 0.7221312522888184,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6271,
+      "step": 96
+    },
+    {
+      "epoch": 0.1468584405753217,
+      "grad_norm": 0.7919607758522034,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5706,
+      "step": 97
+    },
+    {
+      "epoch": 0.14837244511733536,
+      "grad_norm": 0.8152292966842651,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6845,
+      "step": 98
+    },
+    {
+      "epoch": 0.14988644965934897,
+      "grad_norm": 0.622992753982544,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.6638,
+      "step": 99
+    },
+    {
+      "epoch": 0.14988644965934897,
+      "eval_loss": 0.5921109318733215,
+      "eval_runtime": 112.3907,
+      "eval_samples_per_second": 4.947,
+      "eval_steps_per_second": 0.623,
+      "step": 99
+    },
+    {
+      "epoch": 0.1514004542013626,
+      "grad_norm": 0.6544294357299805,
+      "learning_rate": 0.0,
+      "loss": 0.7035,
+      "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": 1.0275138877312205e+17,
+  "total_flos": 1.3724914745868288e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null