Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b5365252881d51306fc0ce8115599af984c81de921547bda834957af698565
+oid sha256:015f0e3f80bcda6dbce2a91c7abee03b2701e3b8b0462ce04dba9cfda1d0699f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f129befd59a461792352a1f287cf309e663bd75b968f37821837de38fe0258
+oid sha256:85fd1e1794458e6fbac328aceefb16be5af6c3d4173fd2e61831b73c458b1bb2
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
+oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12886597938144329,
+  "epoch": 0.1718213058419244,
   "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": 3.5721239031346067e-06,
       "loss": 2.3856,
       "step": 75
+    },
+    {
+      "epoch": 0.13058419243986255,
+      "grad_norm": 0.9107049703598022,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 2.1619,
+      "step": 76
+    },
+    {
+      "epoch": 0.1323024054982818,
+      "grad_norm": 0.886493980884552,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 2.364,
+      "step": 77
+    },
+    {
+      "epoch": 0.13402061855670103,
+      "grad_norm": 0.8511906266212463,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 2.3702,
+      "step": 78
+    },
+    {
+      "epoch": 0.13573883161512026,
+      "grad_norm": 0.8737676739692688,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 2.3266,
+      "step": 79
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 0.9273460507392883,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 2.4682,
+      "step": 80
+    },
+    {
+      "epoch": 0.13917525773195877,
+      "grad_norm": 0.9046407341957092,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 2.3845,
+      "step": 81
+    },
+    {
+      "epoch": 0.13917525773195877,
+      "eval_loss": 2.2980504035949707,
+      "eval_runtime": 53.8703,
+      "eval_samples_per_second": 9.096,
+      "eval_steps_per_second": 1.151,
+      "step": 81
+    },
+    {
+      "epoch": 0.140893470790378,
+      "grad_norm": 0.9387871623039246,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 2.2462,
+      "step": 82
+    },
+    {
+      "epoch": 0.14261168384879724,
+      "grad_norm": 0.9409812688827515,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 2.2848,
+      "step": 83
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 0.7702521681785583,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 2.1991,
+      "step": 84
+    },
+    {
+      "epoch": 0.14604810996563575,
+      "grad_norm": 1.0706955194473267,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 2.3964,
+      "step": 85
+    },
+    {
+      "epoch": 0.14776632302405499,
+      "grad_norm": 1.0983765125274658,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 2.2446,
+      "step": 86
+    },
+    {
+      "epoch": 0.14948453608247422,
+      "grad_norm": 0.9635602831840515,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 2.4293,
+      "step": 87
+    },
+    {
+      "epoch": 0.15120274914089346,
+      "grad_norm": 0.7959424257278442,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 2.3489,
+      "step": 88
+    },
+    {
+      "epoch": 0.15292096219931273,
+      "grad_norm": 0.8272770643234253,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 2.3465,
+      "step": 89
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 0.8438785672187805,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 2.3952,
+      "step": 90
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "eval_loss": 2.294905424118042,
+      "eval_runtime": 53.8933,
+      "eval_samples_per_second": 9.092,
+      "eval_steps_per_second": 1.15,
+      "step": 90
+    },
+    {
+      "epoch": 0.1563573883161512,
+      "grad_norm": 0.7433553338050842,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 2.2177,
+      "step": 91
+    },
+    {
+      "epoch": 0.15807560137457044,
+      "grad_norm": 0.8562928438186646,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 2.2728,
+      "step": 92
+    },
+    {
+      "epoch": 0.15979381443298968,
+      "grad_norm": 0.8268380165100098,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 2.1367,
+      "step": 93
+    },
+    {
+      "epoch": 0.16151202749140894,
+      "grad_norm": 0.8015822172164917,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 2.2379,
+      "step": 94
+    },
+    {
+      "epoch": 0.16323024054982818,
+      "grad_norm": 0.9183565378189087,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 2.3487,
+      "step": 95
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.8422606587409973,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 2.2636,
+      "step": 96
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.7898986339569092,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 2.3046,
+      "step": 97
+    },
+    {
+      "epoch": 0.16838487972508592,
+      "grad_norm": 0.8091641068458557,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 2.2416,
+      "step": 98
+    },
+    {
+      "epoch": 0.17010309278350516,
+      "grad_norm": 0.8988981246948242,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 2.2703,
+      "step": 99
+    },
+    {
+      "epoch": 0.17010309278350516,
+      "eval_loss": 2.294187545776367,
+      "eval_runtime": 53.8764,
+      "eval_samples_per_second": 9.095,
+      "eval_steps_per_second": 1.151,
+      "step": 99
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "grad_norm": 1.0704481601715088,
+      "learning_rate": 0.0,
+      "loss": 2.1572,
+      "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": 5.56415462670336e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null