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:a749cdf4d24baa110ba20cfc0ca7fbbf37b05dc3c2a952aa4ddc4ae0db097ec1
+oid sha256:8194fec3116eb2e199f793722c925eab40d37163c0f046e506933bebc55c0cd3
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761d32bed67767b0127b6570e0191c1b00ebfe661aeb40190906289f9ce19606
+oid sha256:697c9f4ceb0b184a8ed950fe01589f758b220099925d70caa340f4f584ff265e
 size 646253418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90fa2e74fb6b70727348f72b90cc3d3c851fe130fb42757becc3b35a98b248a5
+oid sha256:d254f9727d0c1e19a7f10d7c93ed64f408b4eb359863534c23e96ea9ee428c3b
 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": 0.010630381630700542,
+  "epoch": 0.021260763261401083,
   "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": 1.3153,
       "step": 25
+    },
+    {
+      "epoch": 0.011055596895928563,
+      "grad_norm": 1.0793734788894653,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2484,
+      "step": 26
+    },
+    {
+      "epoch": 0.011480812161156586,
+      "grad_norm": 1.228161334991455,
+      "learning_rate": 2.3364921769246423e-05,
+      "loss": 1.5068,
+      "step": 27
+    },
+    {
+      "epoch": 0.011906027426384608,
+      "grad_norm": 1.0020395517349243,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 1.1368,
+      "step": 28
+    },
+    {
+      "epoch": 0.01233124269161263,
+      "grad_norm": 1.053125023841858,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 1.2301,
+      "step": 29
+    },
+    {
+      "epoch": 0.01275645795684065,
+      "grad_norm": 1.2783164978027344,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 1.3891,
+      "step": 30
+    },
+    {
+      "epoch": 0.013181673222068672,
+      "grad_norm": 1.2294385433197021,
+      "learning_rate": 1.6964013367420966e-05,
+      "loss": 0.9806,
+      "step": 31
+    },
+    {
+      "epoch": 0.013606888487296694,
+      "grad_norm": 1.292421579360962,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.303,
+      "step": 32
+    },
+    {
+      "epoch": 0.014032103752524715,
+      "grad_norm": 1.4603465795516968,
+      "learning_rate": 1.3942782744524973e-05,
+      "loss": 1.5053,
+      "step": 33
+    },
+    {
+      "epoch": 0.014457319017752737,
+      "grad_norm": 1.2738758325576782,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.9182,
+      "step": 34
+    },
+    {
+      "epoch": 0.01488253428298076,
+      "grad_norm": 1.3574635982513428,
+      "learning_rate": 1.1110744174509952e-05,
+      "loss": 1.5063,
+      "step": 35
+    },
+    {
+      "epoch": 0.015307749548208781,
+      "grad_norm": 1.1556434631347656,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.9629,
+      "step": 36
+    },
+    {
+      "epoch": 0.015732964813436803,
+      "grad_norm": 1.3852201700210571,
+      "learning_rate": 8.51635462249828e-06,
+      "loss": 1.1668,
+      "step": 37
+    },
+    {
+      "epoch": 0.016158180078664822,
+      "grad_norm": 1.5002751350402832,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 1.3665,
+      "step": 38
+    },
+    {
+      "epoch": 0.016583395343892846,
+      "grad_norm": 1.466437816619873,
+      "learning_rate": 6.204004813025568e-06,
+      "loss": 1.4519,
+      "step": 39
+    },
+    {
+      "epoch": 0.01700861060912087,
+      "grad_norm": 1.4826688766479492,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 1.4133,
+      "step": 40
+    },
+    {
+      "epoch": 0.01743382587434889,
+      "grad_norm": 1.3776257038116455,
+      "learning_rate": 4.213259692436367e-06,
+      "loss": 0.8482,
+      "step": 41
+    },
+    {
+      "epoch": 0.01785904113957691,
+      "grad_norm": 1.4544354677200317,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.1721,
+      "step": 42
+    },
+    {
+      "epoch": 0.01828425640480493,
+      "grad_norm": 1.462998628616333,
+      "learning_rate": 2.578181461682794e-06,
+      "loss": 1.3665,
+      "step": 43
+    },
+    {
+      "epoch": 0.018709471670032955,
+      "grad_norm": 1.3934773206710815,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.9192,
+      "step": 44
+    },
+    {
+      "epoch": 0.019134686935260974,
+      "grad_norm": 1.8923271894454956,
+      "learning_rate": 1.3267467626223606e-06,
+      "loss": 1.3041,
+      "step": 45
+    },
+    {
+      "epoch": 0.019559902200488997,
+      "grad_norm": 2.7672951221466064,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 1.3151,
+      "step": 46
+    },
+    {
+      "epoch": 0.01998511746571702,
+      "grad_norm": 2.3164193630218506,
+      "learning_rate": 4.803679899192392e-07,
+      "loss": 1.276,
+      "step": 47
+    },
+    {
+      "epoch": 0.02041033273094504,
+      "grad_norm": 3.6176576614379883,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 1.7303,
+      "step": 48
+    },
+    {
+      "epoch": 0.020835547996173064,
+      "grad_norm": 3.728102684020996,
+      "learning_rate": 5.352691903491303e-08,
+      "loss": 1.0657,
+      "step": 49
+    },
+    {
+      "epoch": 0.021260763261401083,
+      "grad_norm": 5.55122709274292,
+      "learning_rate": 0.0,
+      "loss": 1.3532,
+      "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": 1.75751810777088e+16,
+  "total_flos": 3.51503621554176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null