Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba58dc93bff7d474bda2138b54524c7ec47c469292cefdbcb2905f4725cf6d8
+oid sha256:8e39fa7366e0176c2f0ff17cf825f8811394006e05dcbe1f594bb07f69683c66
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fa66aa623b88ae46be8a238047701b7c34e4b85dc9dd7a8373614bdf691f3d
+oid sha256:b9066d7fbea094d406d6530a035ad337b10544a6be3f79f0ccf7c653458edbe5
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7538617595f4b9f0d75409fa08878af879758ed02f9a90ca1240366c78c8643d
+oid sha256:f54db14235b93c1ebd77e53415adacb86948650017692d4b2e79f3a92b610eb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013798813302056023,
+  "epoch": 0.027597626604112045,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 2.439,
       "eval_steps_per_second": 0.61,
       "step": 25
+    },
+    {
+      "epoch": 0.014350765834138263,
+      "grad_norm": 2.2478325366973877,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7773,
+      "step": 26
+    },
+    {
+      "epoch": 0.014902718366220506,
+      "grad_norm": 1.3889656066894531,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.7084,
+      "step": 27
+    },
+    {
+      "epoch": 0.015454670898302747,
+      "grad_norm": 1.7380234003067017,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.6869,
+      "step": 28
+    },
+    {
+      "epoch": 0.016006623430384986,
+      "grad_norm": 1.4783921241760254,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.5719,
+      "step": 29
+    },
+    {
+      "epoch": 0.016558575962467226,
+      "grad_norm": 1.596419334411621,
+      "learning_rate": 0.0001,
+      "loss": 0.4796,
+      "step": 30
+    },
+    {
+      "epoch": 0.016558575962467226,
+      "eval_loss": 0.5793518424034119,
+      "eval_runtime": 1251.2902,
+      "eval_samples_per_second": 2.439,
+      "eval_steps_per_second": 0.61,
+      "step": 30
+    },
+    {
+      "epoch": 0.017110528494549467,
+      "grad_norm": 1.5877236127853394,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.5925,
+      "step": 31
+    },
+    {
+      "epoch": 0.017662481026631708,
+      "grad_norm": 1.5007165670394897,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6137,
+      "step": 32
+    },
+    {
+      "epoch": 0.018214433558713952,
+      "grad_norm": 1.4610683917999268,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.4628,
+      "step": 33
+    },
+    {
+      "epoch": 0.018766386090796193,
+      "grad_norm": 0.7523146867752075,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4449,
+      "step": 34
+    },
+    {
+      "epoch": 0.019318338622878434,
+      "grad_norm": 1.2376327514648438,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4897,
+      "step": 35
+    },
+    {
+      "epoch": 0.019318338622878434,
+      "eval_loss": 0.5563785433769226,
+      "eval_runtime": 1251.5204,
+      "eval_samples_per_second": 2.439,
+      "eval_steps_per_second": 0.61,
+      "step": 35
+    },
+    {
+      "epoch": 0.019870291154960674,
+      "grad_norm": 1.0166033506393433,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.4334,
+      "step": 36
+    },
+    {
+      "epoch": 0.020422243687042915,
+      "grad_norm": 0.8759408593177795,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.3917,
+      "step": 37
+    },
+    {
+      "epoch": 0.020974196219125156,
+      "grad_norm": 1.4520206451416016,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5742,
+      "step": 38
+    },
+    {
+      "epoch": 0.021526148751207397,
+      "grad_norm": 1.113675594329834,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.5707,
+      "step": 39
+    },
+    {
+      "epoch": 0.022078101283289638,
+      "grad_norm": 1.3002536296844482,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5998,
+      "step": 40
+    },
+    {
+      "epoch": 0.022078101283289638,
+      "eval_loss": 0.5418702960014343,
+      "eval_runtime": 1251.8554,
+      "eval_samples_per_second": 2.438,
+      "eval_steps_per_second": 0.609,
+      "step": 40
+    },
+    {
+      "epoch": 0.02263005381537188,
+      "grad_norm": 1.0999929904937744,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.4751,
+      "step": 41
+    },
+    {
+      "epoch": 0.02318200634745412,
+      "grad_norm": 1.3158468008041382,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6463,
+      "step": 42
+    },
+    {
+      "epoch": 0.02373395887953636,
+      "grad_norm": 2.3532841205596924,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.7916,
+      "step": 43
+    },
+    {
+      "epoch": 0.0242859114116186,
+      "grad_norm": 1.268966794013977,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.4733,
+      "step": 44
+    },
+    {
+      "epoch": 0.02483786394370084,
+      "grad_norm": 1.0840526819229126,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.5932,
+      "step": 45
+    },
+    {
+      "epoch": 0.02483786394370084,
+      "eval_loss": 0.5364078879356384,
+      "eval_runtime": 1251.3181,
+      "eval_samples_per_second": 2.439,
+      "eval_steps_per_second": 0.61,
+      "step": 45
+    },
+    {
+      "epoch": 0.025389816475783082,
+      "grad_norm": 1.5335124731063843,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4034,
+      "step": 46
+    },
+    {
+      "epoch": 0.025941769007865323,
+      "grad_norm": 1.1978284120559692,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.4882,
+      "step": 47
+    },
+    {
+      "epoch": 0.026493721539947564,
+      "grad_norm": 1.2461581230163574,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.5497,
+      "step": 48
+    },
+    {
+      "epoch": 0.027045674072029804,
+      "grad_norm": 1.0206390619277954,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.4729,
+      "step": 49
+    },
+    {
+      "epoch": 0.027597626604112045,
+      "grad_norm": 1.3069730997085571,
+      "learning_rate": 0.0,
+      "loss": 0.415,
+      "step": 50
+    },
+    {
+      "epoch": 0.027597626604112045,
+      "eval_loss": 0.5334399342536926,
+      "eval_runtime": 1251.5092,
+      "eval_samples_per_second": 2.439,
+      "eval_steps_per_second": 0.61,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.23612542025728e+16,
+  "total_flos": 1.647225084051456e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null