Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a94add137b221d96b68d0f888aa9182c190c010aa20acf953d98c765bfdfb06
+oid sha256:6fab1195235870bcf95a354529b1db00a0882fcfbaf1a95e3175a2a3ac359b6c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88804253bade42e82dc89264a79f804b77f22f6cbb817ccb5d5681964680545d
+oid sha256:11b05842f5ff6566d67baaa7097909cba1d43982e763d3d0abfbbdeb383f1700
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583fb097eb53d60e58b366a55e9484a1c52dd01d47e9e06682ea5f86f43bfe3b
+oid sha256:7fbb720d588995189d4ceaa52bf3b2901004d4b1bde22e597ed455e10d0c207b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7ee3ad8033dc89ac477e4347a2567ff89d6c0358e1d7a1b0f70057a3434847
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020300446609825416,
+  "epoch": 0.04060089321965083,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 2.663507823075358e-05,
       "loss": 0.3224,
       "step": 25
+    },
+    {
+      "epoch": 0.021112464474218433,
+      "grad_norm": 12.095660209655762,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7587,
+      "step": 26
+    },
+    {
+      "epoch": 0.02192448233861145,
+      "grad_norm": 52.95034408569336,
+      "learning_rate": 2.3364921769246423e-05,
+      "loss": 1.1537,
+      "step": 27
+    },
+    {
+      "epoch": 0.022736500203004467,
+      "grad_norm": 38.27907180786133,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 1.3037,
+      "step": 28
+    },
+    {
+      "epoch": 0.023548518067397484,
+      "grad_norm": 16.03143310546875,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 0.2728,
+      "step": 29
+    },
+    {
+      "epoch": 0.024360535931790498,
+      "grad_norm": 28.440916061401367,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.025172553796183515,
+      "grad_norm": 10.148262023925781,
+      "learning_rate": 1.6964013367420966e-05,
+      "loss": 0.4135,
+      "step": 31
+    },
+    {
+      "epoch": 0.025984571660576532,
+      "grad_norm": 10.048409461975098,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.3585,
+      "step": 32
+    },
+    {
+      "epoch": 0.02679658952496955,
+      "grad_norm": 20.693401336669922,
+      "learning_rate": 1.3942782744524973e-05,
+      "loss": 0.2969,
+      "step": 33
+    },
+    {
+      "epoch": 0.027608607389362567,
+      "grad_norm": 5.649575710296631,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1936,
+      "step": 34
+    },
+    {
+      "epoch": 0.028420625253755584,
+      "grad_norm": 143.23516845703125,
+      "learning_rate": 1.1110744174509952e-05,
+      "loss": 0.2887,
+      "step": 35
+    },
+    {
+      "epoch": 0.029232643118148598,
+      "grad_norm": 8.527986526489258,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.1778,
+      "step": 36
+    },
+    {
+      "epoch": 0.030044660982541615,
+      "grad_norm": 7.967432022094727,
+      "learning_rate": 8.51635462249828e-06,
+      "loss": 0.1517,
+      "step": 37
+    },
+    {
+      "epoch": 0.030856678846934632,
+      "grad_norm": 10.487667083740234,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.4037,
+      "step": 38
+    },
+    {
+      "epoch": 0.031668696711327646,
+      "grad_norm": 21.77398109436035,
+      "learning_rate": 6.204004813025568e-06,
+      "loss": 0.3575,
+      "step": 39
+    },
+    {
+      "epoch": 0.032480714575720666,
+      "grad_norm": 6.412965774536133,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.1561,
+      "step": 40
+    },
+    {
+      "epoch": 0.03329273244011368,
+      "grad_norm": 8.57004165649414,
+      "learning_rate": 4.213259692436367e-06,
+      "loss": 0.1964,
+      "step": 41
+    },
+    {
+      "epoch": 0.0341047503045067,
+      "grad_norm": 14.712817192077637,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.4709,
+      "step": 42
+    },
+    {
+      "epoch": 0.034916768168899714,
+      "grad_norm": 3.917064666748047,
+      "learning_rate": 2.578181461682794e-06,
+      "loss": 0.0741,
+      "step": 43
+    },
+    {
+      "epoch": 0.035728786033292735,
+      "grad_norm": 11.043051719665527,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.219,
+      "step": 44
+    },
+    {
+      "epoch": 0.03654080389768575,
+      "grad_norm": 17.34823226928711,
+      "learning_rate": 1.3267467626223606e-06,
+      "loss": 0.7905,
+      "step": 45
+    },
+    {
+      "epoch": 0.03735282176207876,
+      "grad_norm": 24.177156448364258,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.3314,
+      "step": 46
+    },
+    {
+      "epoch": 0.03816483962647178,
+      "grad_norm": 4.842467308044434,
+      "learning_rate": 4.803679899192392e-07,
+      "loss": 0.1427,
+      "step": 47
+    },
+    {
+      "epoch": 0.0389768574908648,
+      "grad_norm": 15.299854278564453,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.4962,
+      "step": 48
+    },
+    {
+      "epoch": 0.03978887535525782,
+      "grad_norm": 6.606536388397217,
+      "learning_rate": 5.352691903491303e-08,
+      "loss": 0.3002,
+      "step": 49
+    },
+    {
+      "epoch": 0.04060089321965083,
+      "grad_norm": 39.760929107666016,
+      "learning_rate": 0.0,
+      "loss": 0.4597,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.86502613041152e+16,
+  "total_flos": 3.73005226082304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null