Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7216b527085c06e90140267c3e5d84eb52827853e613284cb8fb9a523a31f61a
+oid sha256:d8877a7b1f4c82876b018da316748c1adaa6326bf6a7b738a693efc9c185d375
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a339e73c62ddc2cd90c9f3491b94e92652a34a3349214b157f6d17c675313018
+oid sha256:2bf5693ee9edc0989bf7721d91f2074b99fc95c3bdd748ef07281ef4f06be017
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3cf0264db6980cb80699468405c8df7edfa0696cd7ccd104b172a4e8bc5068e
+oid sha256:42b0e7ad5a4c8c7c4899c2b11572bcb8aac0cc3715280669681a4088db95e5d4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a418ca3f356f0b3b6587bb06530eb1c1e9527bce6a7f5d287e435f5b0f5186
+oid sha256:4bdfd87c4e8df753b36c815eedd271bd85b12f9be313db78ae1e3961dbbaa6c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10214f027a4c2de1f78cdcca8bc9a83b8afb3b4e2daa4f27037df6142383959e
+oid sha256:45887842c2a5bbc248cc4996770459b9bf2186a9d0bc8b3a34bd51ae0f56802b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78ed4897faea6a3cb8e851c0ab597152dac14cd8abb916119eafb1801ef8a7c
+oid sha256:77ab05e1a1b77aca22e9d9e9239956b52e7720c74966e07bf0b841f354076400
 size 15024

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": 1.0,
+  "epoch": 1.3333333333333333,
   "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": 0.3466,
       "step": 75
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.959816575050354,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2593,
+      "step": 76
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.9306586980819702,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.3772,
+      "step": 77
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.1471374034881592,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3527,
+      "step": 78
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.9034615159034729,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.3257,
+      "step": 79
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.8599056601524353,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3808,
+      "step": 80
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.8893074989318848,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.3187,
+      "step": 81
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.3070451021194458,
+      "eval_runtime": 6.8264,
+      "eval_samples_per_second": 36.916,
+      "eval_steps_per_second": 1.172,
+      "step": 81
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 0.8692622780799866,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.335,
+      "step": 82
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 0.8228186964988708,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.2741,
+      "step": 83
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.8581228256225586,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.34,
+      "step": 84
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.8180541396141052,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3043,
+      "step": 85
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 0.8261634111404419,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.335,
+      "step": 86
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.3771291971206665,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.3469,
+      "step": 87
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.7941247820854187,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.251,
+      "step": 88
+    },
+    {
+      "epoch": 1.1866666666666668,
+      "grad_norm": 0.915990948677063,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.2688,
+      "step": 89
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.8738386034965515,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3568,
+      "step": 90
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.3071597218513489,
+      "eval_runtime": 6.8205,
+      "eval_samples_per_second": 36.948,
+      "eval_steps_per_second": 1.173,
+      "step": 90
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.9354806542396545,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3609,
+      "step": 91
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.8699689507484436,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3332,
+      "step": 92
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.0410078763961792,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.3301,
+      "step": 93
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 0.8241610527038574,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.3493,
+      "step": 94
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.8889489769935608,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2898,
+      "step": 95
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.792635977268219,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.3201,
+      "step": 96
+    },
+    {
+      "epoch": 1.2933333333333334,
+      "grad_norm": 1.05978262424469,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2334,
+      "step": 97
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 0.9526124596595764,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3014,
+      "step": 98
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.9465766549110413,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.2909,
+      "step": 99
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.3063599765300751,
+      "eval_runtime": 6.824,
+      "eval_samples_per_second": 36.928,
+      "eval_steps_per_second": 1.172,
+      "step": 99
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.8943014144897461,
+      "learning_rate": 0.0,
+      "loss": 0.3156,
+      "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": 3.96656470130688e+17,
+  "total_flos": 5.28875293507584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null