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:e3918008d62488d2bd26d66266b364458d9ff81d1139818221b1750a7d40d5ed
+oid sha256:ba70748dd59c881c6918db0d4d2048ce549d2bd938d9e691456748855fd7a439
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c5d58d9af6c0e63ad21eb3e625ead9af64c627e5dc44292e9a913bcee0d8f8
+oid sha256:e88ddebd2a88cf51e08f0bfd4e520e7c9d815362d3ebebc1bddeb07aab417aca
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429f01f3893a251df4a874c77ce3fc47dcc07b93cbb24ce2ef43a56f0bbd83b7
+oid sha256:84cacbdbb0b72a95fd5620124a96c0ed5a18674aa4e52f454d365e2e6e3e2d1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06487187804086929,
+  "epoch": 0.12974375608173858,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 1.353,
       "eval_steps_per_second": 0.679,
       "step": 25
+    },
+    {
+      "epoch": 0.06746675316250406,
+      "grad_norm": 22.732812881469727,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.6565,
+      "step": 26
+    },
+    {
+      "epoch": 0.07006162828413882,
+      "grad_norm": 9.80388355255127,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.2933,
+      "step": 27
+    },
+    {
+      "epoch": 0.07265650340577359,
+      "grad_norm": 14.081550598144531,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.4886,
+      "step": 28
+    },
+    {
+      "epoch": 0.07525137852740837,
+      "grad_norm": 16.663516998291016,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.7272,
+      "step": 29
+    },
+    {
+      "epoch": 0.07784625364904314,
+      "grad_norm": 15.300065040588379,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4666,
+      "step": 30
+    },
+    {
+      "epoch": 0.08044112877067791,
+      "grad_norm": 40.297645568847656,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5482,
+      "step": 31
+    },
+    {
+      "epoch": 0.08303600389231268,
+      "grad_norm": 11.791970252990723,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 1.3021,
+      "step": 32
+    },
+    {
+      "epoch": 0.08563087901394745,
+      "grad_norm": 34.81112289428711,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.5804,
+      "step": 33
+    },
+    {
+      "epoch": 0.08822575413558223,
+      "grad_norm": 12.368243217468262,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.5155,
+      "step": 34
+    },
+    {
+      "epoch": 0.090820629257217,
+      "grad_norm": 19.11678123474121,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.9189,
+      "step": 35
+    },
+    {
+      "epoch": 0.09341550437885177,
+      "grad_norm": 40.73845291137695,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 4.2073,
+      "step": 36
+    },
+    {
+      "epoch": 0.09601037950048653,
+      "grad_norm": 30.314462661743164,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.1171,
+      "step": 37
+    },
+    {
+      "epoch": 0.09860525462212132,
+      "grad_norm": 13.374330520629883,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.3863,
+      "step": 38
+    },
+    {
+      "epoch": 0.10120012974375608,
+      "grad_norm": 21.539278030395508,
+      "learning_rate": 5e-05,
+      "loss": 1.2575,
+      "step": 39
+    },
+    {
+      "epoch": 0.10379500486539085,
+      "grad_norm": 8.351127624511719,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.2764,
+      "step": 40
+    },
+    {
+      "epoch": 0.10638987998702562,
+      "grad_norm": 29.027982711791992,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.042,
+      "step": 41
+    },
+    {
+      "epoch": 0.10898475510866039,
+      "grad_norm": 10.286849021911621,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3774,
+      "step": 42
+    },
+    {
+      "epoch": 0.11157963023029517,
+      "grad_norm": 2.650897264480591,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0587,
+      "step": 43
+    },
+    {
+      "epoch": 0.11417450535192994,
+      "grad_norm": 14.90556526184082,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.6228,
+      "step": 44
+    },
+    {
+      "epoch": 0.11676938047356471,
+      "grad_norm": 3.8510780334472656,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.101,
+      "step": 45
+    },
+    {
+      "epoch": 0.11936425559519948,
+      "grad_norm": 25.16055679321289,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.8737,
+      "step": 46
+    },
+    {
+      "epoch": 0.12195913071683426,
+      "grad_norm": 33.220306396484375,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.9121,
+      "step": 47
+    },
+    {
+      "epoch": 0.12455400583846903,
+      "grad_norm": 30.670238494873047,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5032,
+      "step": 48
+    },
+    {
+      "epoch": 0.1271488809601038,
+      "grad_norm": 24.66783905029297,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.5967,
+      "step": 49
+    },
+    {
+      "epoch": 0.12974375608173858,
+      "grad_norm": 48.0320930480957,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 3.6341,
+      "step": 50
+    },
+    {
+      "epoch": 0.12974375608173858,
+      "eval_loss": 0.18054018914699554,
+      "eval_runtime": 239.9435,
+      "eval_samples_per_second": 1.354,
+      "eval_steps_per_second": 0.679,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.28697269714944e+16,
+  "total_flos": 6.57394539429888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null