Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc16025718ab1cb4777bcb1aed244af010678663b1fca7fc513df159c35e6ab
+oid sha256:88c02662bc21fd5ce451b0e879ebbc1acc30bf97d842bc4a1696230233d98068
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1aa39e856be778685752f25761e3f9bd3e178c9bff03d7aaeadf451da2a594
+oid sha256:77a4d35b335c67f000c032e1e7e1356ec5a1f7e69f977817962a63dddf11c9ac
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f561a82bea27cf9bdf3a7a427edf3fc8517d927c408784a51f4efc3089462a9
+oid sha256:14fe42ed1c83d00f96dc49bc31a9b32fbb3ae79e41e2f931dcb67ac68061c4e3
 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": 0.8583690987124464,
+  "epoch": 1.7167381974248928,
   "eval_steps": 4,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,229 @@
       "learning_rate": 0.000138268343236509,
       "loss": 3.4839,
       "step": 25
+    },
+    {
+      "epoch": 0.8927038626609443,
+      "grad_norm": 5.970047473907471,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2252,
+      "step": 26
+    },
+    {
+      "epoch": 0.927038626609442,
+      "grad_norm": 6.384853839874268,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 3.4018,
+      "step": 27
+    },
+    {
+      "epoch": 0.9613733905579399,
+      "grad_norm": 6.741840839385986,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 3.4371,
+      "step": 28
+    },
+    {
+      "epoch": 0.9613733905579399,
+      "eval_loss": 0.4020407199859619,
+      "eval_runtime": 8.0743,
+      "eval_samples_per_second": 6.069,
+      "eval_steps_per_second": 1.61,
+      "step": 28
+    },
+    {
+      "epoch": 0.9957081545064378,
+      "grad_norm": 5.92246675491333,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 2.4705,
+      "step": 29
+    },
+    {
+      "epoch": 1.0300429184549356,
+      "grad_norm": 6.4705681800842285,
+      "learning_rate": 0.0001,
+      "loss": 2.5391,
+      "step": 30
+    },
+    {
+      "epoch": 1.0643776824034334,
+      "grad_norm": 7.236270427703857,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 3.4479,
+      "step": 31
+    },
+    {
+      "epoch": 1.0987124463519313,
+      "grad_norm": 5.484566688537598,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.1396,
+      "step": 32
+    },
+    {
+      "epoch": 1.0987124463519313,
+      "eval_loss": 0.3587982654571533,
+      "eval_runtime": 8.0769,
+      "eval_samples_per_second": 6.067,
+      "eval_steps_per_second": 1.61,
+      "step": 32
+    },
+    {
+      "epoch": 1.1330472103004292,
+      "grad_norm": 6.789762020111084,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 2.4319,
+      "step": 33
+    },
+    {
+      "epoch": 1.167381974248927,
+      "grad_norm": 5.139922142028809,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.5539,
+      "step": 34
+    },
+    {
+      "epoch": 1.201716738197425,
+      "grad_norm": 5.432690143585205,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.9336,
+      "step": 35
+    },
+    {
+      "epoch": 1.2360515021459229,
+      "grad_norm": 4.705223560333252,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.6073,
+      "step": 36
+    },
+    {
+      "epoch": 1.2360515021459229,
+      "eval_loss": 0.3393373191356659,
+      "eval_runtime": 8.0747,
+      "eval_samples_per_second": 6.068,
+      "eval_steps_per_second": 1.61,
+      "step": 36
+    },
+    {
+      "epoch": 1.2703862660944205,
+      "grad_norm": 8.144052505493164,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 2.4886,
+      "step": 37
+    },
+    {
+      "epoch": 1.3047210300429184,
+      "grad_norm": 5.885042667388916,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1173,
+      "step": 38
+    },
+    {
+      "epoch": 1.3390557939914163,
+      "grad_norm": 5.44212532043457,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 1.5208,
+      "step": 39
+    },
+    {
+      "epoch": 1.3733905579399142,
+      "grad_norm": 8.440479278564453,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.2822,
+      "step": 40
+    },
+    {
+      "epoch": 1.3733905579399142,
+      "eval_loss": 0.3231399357318878,
+      "eval_runtime": 8.0758,
+      "eval_samples_per_second": 6.068,
+      "eval_steps_per_second": 1.61,
+      "step": 40
+    },
+    {
+      "epoch": 1.407725321888412,
+      "grad_norm": 6.7061991691589355,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 2.4418,
+      "step": 41
+    },
+    {
+      "epoch": 1.44206008583691,
+      "grad_norm": 5.881109714508057,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.252,
+      "step": 42
+    },
+    {
+      "epoch": 1.4763948497854078,
+      "grad_norm": 5.9437479972839355,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 1.8867,
+      "step": 43
+    },
+    {
+      "epoch": 1.5107296137339055,
+      "grad_norm": 5.992803573608398,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.7314,
+      "step": 44
+    },
+    {
+      "epoch": 1.5107296137339055,
+      "eval_loss": 0.31934094429016113,
+      "eval_runtime": 8.0874,
+      "eval_samples_per_second": 6.059,
+      "eval_steps_per_second": 1.607,
+      "step": 44
+    },
+    {
+      "epoch": 1.5450643776824036,
+      "grad_norm": 6.900696754455566,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.8172,
+      "step": 45
+    },
+    {
+      "epoch": 1.5793991416309012,
+      "grad_norm": 4.783636569976807,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.6444,
+      "step": 46
+    },
+    {
+      "epoch": 1.613733905579399,
+      "grad_norm": 7.204476356506348,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 2.3282,
+      "step": 47
+    },
+    {
+      "epoch": 1.648068669527897,
+      "grad_norm": 5.65119743347168,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.7266,
+      "step": 48
+    },
+    {
+      "epoch": 1.648068669527897,
+      "eval_loss": 0.3161769509315491,
+      "eval_runtime": 8.1044,
+      "eval_samples_per_second": 6.046,
+      "eval_steps_per_second": 1.604,
+      "step": 48
+    },
+    {
+      "epoch": 1.6824034334763949,
+      "grad_norm": 5.6475605964660645,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 1.6549,
+      "step": 49
+    },
+    {
+      "epoch": 1.7167381974248928,
+      "grad_norm": 9.571765899658203,
+      "learning_rate": 0.0,
+      "loss": 3.696,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -252,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.306916403806208e+17,
+  "total_flos": 2.6089318710981427e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null