Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873a2cc5cbf5b5ae7d27ad99fe88d1bab140b1d84ea7f7f494720c2688ad10c8
+oid sha256:088222b7157efd608f9ad45231e7fe83323c57fae9849904ed7da742e94b83d6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ceff8d64bfd804acec134de2bee37c59051f28ead5ed2bb0c1ac06f9755fa3
+oid sha256:26ed48d4e035ed471a45b1805e53807376433bcbefd325c69b8e7eb1668d6307
 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": 0.14985014985014986,
+  "epoch": 0.1998001998001998,
   "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": 1.5303,
       "step": 75
+    },
+    {
+      "epoch": 0.15184815184815184,
+      "grad_norm": 2.8635425567626953,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 1.4636,
+      "step": 76
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 2.4772164821624756,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 1.5795,
+      "step": 77
+    },
+    {
+      "epoch": 0.15584415584415584,
+      "grad_norm": 2.625244379043579,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 1.4901,
+      "step": 78
+    },
+    {
+      "epoch": 0.15784215784215785,
+      "grad_norm": 2.5218544006347656,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 1.4865,
+      "step": 79
+    },
+    {
+      "epoch": 0.15984015984015984,
+      "grad_norm": 2.3090908527374268,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 1.5131,
+      "step": 80
+    },
+    {
+      "epoch": 0.16183816183816183,
+      "grad_norm": 2.3675246238708496,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 1.7521,
+      "step": 81
+    },
+    {
+      "epoch": 0.16183816183816183,
+      "eval_loss": 1.5376331806182861,
+      "eval_runtime": 46.3321,
+      "eval_samples_per_second": 9.108,
+      "eval_steps_per_second": 1.144,
+      "step": 81
+    },
+    {
+      "epoch": 0.16383616383616384,
+      "grad_norm": 2.7707293033599854,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.4751,
+      "step": 82
+    },
+    {
+      "epoch": 0.16583416583416583,
+      "grad_norm": 2.4699959754943848,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 1.6698,
+      "step": 83
+    },
+    {
+      "epoch": 0.16783216783216784,
+      "grad_norm": 2.3290224075317383,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 1.5948,
+      "step": 84
+    },
+    {
+      "epoch": 0.16983016983016982,
+      "grad_norm": 2.5773816108703613,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.5975,
+      "step": 85
+    },
+    {
+      "epoch": 0.17182817182817184,
+      "grad_norm": 2.2209627628326416,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 1.595,
+      "step": 86
+    },
+    {
+      "epoch": 0.17382617382617382,
+      "grad_norm": 2.361018180847168,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 1.4577,
+      "step": 87
+    },
+    {
+      "epoch": 0.17582417582417584,
+      "grad_norm": 1.918518304824829,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 1.4867,
+      "step": 88
+    },
+    {
+      "epoch": 0.17782217782217782,
+      "grad_norm": 2.2241179943084717,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 1.5054,
+      "step": 89
+    },
+    {
+      "epoch": 0.1798201798201798,
+      "grad_norm": 2.1097564697265625,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 1.5649,
+      "step": 90
+    },
+    {
+      "epoch": 0.1798201798201798,
+      "eval_loss": 1.5333300828933716,
+      "eval_runtime": 46.3494,
+      "eval_samples_per_second": 9.105,
+      "eval_steps_per_second": 1.143,
+      "step": 90
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 1.8790652751922607,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 1.6425,
+      "step": 91
+    },
+    {
+      "epoch": 0.1838161838161838,
+      "grad_norm": 2.1999900341033936,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 1.5697,
+      "step": 92
+    },
+    {
+      "epoch": 0.18581418581418582,
+      "grad_norm": 2.25212025642395,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 1.4504,
+      "step": 93
+    },
+    {
+      "epoch": 0.1878121878121878,
+      "grad_norm": 2.006225347518921,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 1.5105,
+      "step": 94
+    },
+    {
+      "epoch": 0.18981018981018982,
+      "grad_norm": 2.291072368621826,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 1.5825,
+      "step": 95
+    },
+    {
+      "epoch": 0.1918081918081918,
+      "grad_norm": 2.1801528930664062,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 1.6127,
+      "step": 96
+    },
+    {
+      "epoch": 0.1938061938061938,
+      "grad_norm": 2.0899884700775146,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 1.6214,
+      "step": 97
+    },
+    {
+      "epoch": 0.1958041958041958,
+      "grad_norm": 1.8839422464370728,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 1.548,
+      "step": 98
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 1.9306854009628296,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 1.6523,
+      "step": 99
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "eval_loss": 1.5328097343444824,
+      "eval_runtime": 46.3646,
+      "eval_samples_per_second": 9.102,
+      "eval_steps_per_second": 1.143,
+      "step": 99
+    },
+    {
+      "epoch": 0.1998001998001998,
+      "grad_norm": 2.3619418144226074,
+      "learning_rate": 0.0,
+      "loss": 1.5468,
+      "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