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:d6448faeda30c8457234317531e0f63f671d53cef0b8cd716e5f84085792cf9e
+oid sha256:9627328aafd748011d659280faaeab7a1761e4eae297ec92f7a758aba468558f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ac5af3b979faf59eef78731e19c2deff60c7dc74e7f35247679274ec17ad3c
+oid sha256:aa7346d4df08278a0a86671b7df1ec22929ff28fe89115680e91c52371099ea8
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd5f0c683b24122f71cab5bd06de91824040ac71c51e9af08973667cfe3173f9
+oid sha256:7326c74479803f52eb9c234f3a12a772f8b37142d6e1db37bee4bc52e8584588
 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": 0.07720020586721564,
+  "epoch": 0.1029336078229542,
   "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": 4.5835,
       "step": 75
+    },
+    {
+      "epoch": 0.0782295419454452,
+      "grad_norm": 0.3594980537891388,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.6926,
+      "step": 76
+    },
+    {
+      "epoch": 0.07925887802367473,
+      "grad_norm": 0.30547279119491577,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 4.7796,
+      "step": 77
+    },
+    {
+      "epoch": 0.08028821410190427,
+      "grad_norm": 0.35963600873947144,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.5412,
+      "step": 78
+    },
+    {
+      "epoch": 0.08131755018013381,
+      "grad_norm": 0.26262137293815613,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 4.5385,
+      "step": 79
+    },
+    {
+      "epoch": 0.08234688625836335,
+      "grad_norm": 0.3326081931591034,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.7268,
+      "step": 80
+    },
+    {
+      "epoch": 0.08337622233659289,
+      "grad_norm": 0.29198020696640015,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 4.7795,
+      "step": 81
+    },
+    {
+      "epoch": 0.08337622233659289,
+      "eval_loss": 2.3745617866516113,
+      "eval_runtime": 226.9222,
+      "eval_samples_per_second": 3.605,
+      "eval_steps_per_second": 0.454,
+      "step": 81
+    },
+    {
+      "epoch": 0.08440555841482245,
+      "grad_norm": 0.36414095759391785,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.7554,
+      "step": 82
+    },
+    {
+      "epoch": 0.08543489449305199,
+      "grad_norm": 0.3461471199989319,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 4.788,
+      "step": 83
+    },
+    {
+      "epoch": 0.08646423057128153,
+      "grad_norm": 0.36194470524787903,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 5.0131,
+      "step": 84
+    },
+    {
+      "epoch": 0.08749356664951106,
+      "grad_norm": 0.3344295918941498,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.9249,
+      "step": 85
+    },
+    {
+      "epoch": 0.0885229027277406,
+      "grad_norm": 0.29325899481773376,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.4008,
+      "step": 86
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 0.31407222151756287,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 4.6769,
+      "step": 87
+    },
+    {
+      "epoch": 0.0905815748841997,
+      "grad_norm": 0.44068512320518494,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.9277,
+      "step": 88
+    },
+    {
+      "epoch": 0.09161091096242924,
+      "grad_norm": 0.3176312744617462,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 4.8676,
+      "step": 89
+    },
+    {
+      "epoch": 0.09264024704065878,
+      "grad_norm": 0.3227611780166626,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.7992,
+      "step": 90
+    },
+    {
+      "epoch": 0.09264024704065878,
+      "eval_loss": 2.3742470741271973,
+      "eval_runtime": 226.8864,
+      "eval_samples_per_second": 3.605,
+      "eval_steps_per_second": 0.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.09366958311888832,
+      "grad_norm": 0.3470034897327423,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.8775,
+      "step": 91
+    },
+    {
+      "epoch": 0.09469891919711786,
+      "grad_norm": 0.3345381021499634,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.6053,
+      "step": 92
+    },
+    {
+      "epoch": 0.0957282552753474,
+      "grad_norm": 0.2730475962162018,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 4.6352,
+      "step": 93
+    },
+    {
+      "epoch": 0.09675759135357695,
+      "grad_norm": 0.3089372515678406,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 4.7786,
+      "step": 94
+    },
+    {
+      "epoch": 0.09778692743180649,
+      "grad_norm": 0.3256579339504242,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 4.6533,
+      "step": 95
+    },
+    {
+      "epoch": 0.09881626351003603,
+      "grad_norm": 0.4511566460132599,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.9058,
+      "step": 96
+    },
+    {
+      "epoch": 0.09984559958826557,
+      "grad_norm": 0.2858843207359314,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 4.4558,
+      "step": 97
+    },
+    {
+      "epoch": 0.10087493566649511,
+      "grad_norm": 0.38588446378707886,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.9628,
+      "step": 98
+    },
+    {
+      "epoch": 0.10190427174472465,
+      "grad_norm": 0.29587432742118835,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 4.683,
+      "step": 99
+    },
+    {
+      "epoch": 0.10190427174472465,
+      "eval_loss": 2.3742330074310303,
+      "eval_runtime": 226.8851,
+      "eval_samples_per_second": 3.605,
+      "eval_steps_per_second": 0.454,
+      "step": 99
+    },
+    {
+      "epoch": 0.1029336078229542,
+      "grad_norm": 0.36477580666542053,
+      "learning_rate": 0.0,
+      "loss": 4.9429,
+      "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": 8.952465627650458e+16,
+  "total_flos": 1.1925729759461376e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null