Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b04b5547bd7f762c4616a0f6168cd3a9e8c46661daeb0b8713e6aa7cd18f07e
+oid sha256:c38f58a474900ebd399b2ee2c4a5fe34102faf5c6f665f05ad7417a6b8816787
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d1ff353c116994b15aaf5fe0c2e12bd6d3910ee755042a1c771b1e71d4b5e2
+oid sha256:573ee7bb685c2fe6162092fe0241899f30b6406b6ae0a07c8c7714cedd2d4ee1
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17e8cae61c648514e623adf87a37717b1f670c09e19dae6f5c7cd9c42225ccf
+oid sha256:53e9c4120935f737facf6ce31be670439e9219f5faa5889c9e94b022c891890c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07423904974016332,
+  "epoch": 0.111358574610245,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 3.958,
       "eval_steps_per_second": 1.979,
       "step": 50
+    },
+    {
+      "epoch": 0.0757238307349666,
+      "grad_norm": 2.123660087585449,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1803,
+      "step": 51
+    },
+    {
+      "epoch": 0.07720861172976985,
+      "grad_norm": 2.3457491397857666,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.1052,
+      "step": 52
+    },
+    {
+      "epoch": 0.07869339272457312,
+      "grad_norm": 0.9634860157966614,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.1048,
+      "step": 53
+    },
+    {
+      "epoch": 0.0801781737193764,
+      "grad_norm": 1.2893617153167725,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1053,
+      "step": 54
+    },
+    {
+      "epoch": 0.08166295471417966,
+      "grad_norm": 1.0800879001617432,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1001,
+      "step": 55
+    },
+    {
+      "epoch": 0.08314773570898293,
+      "grad_norm": 1.4931827783584595,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0806,
+      "step": 56
+    },
+    {
+      "epoch": 0.08463251670378619,
+      "grad_norm": 3.529783248901367,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1045,
+      "step": 57
+    },
+    {
+      "epoch": 0.08611729769858946,
+      "grad_norm": 2.6875853538513184,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0877,
+      "step": 58
+    },
+    {
+      "epoch": 0.08760207869339272,
+      "grad_norm": 1.4070323705673218,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0469,
+      "step": 59
+    },
+    {
+      "epoch": 0.08908685968819599,
+      "grad_norm": 0.904192328453064,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.037,
+      "step": 60
+    },
+    {
+      "epoch": 0.09057164068299926,
+      "grad_norm": 1.2252767086029053,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0616,
+      "step": 61
+    },
+    {
+      "epoch": 0.09205642167780252,
+      "grad_norm": 0.8113102912902832,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0507,
+      "step": 62
+    },
+    {
+      "epoch": 0.0935412026726058,
+      "grad_norm": 0.6455811262130737,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0617,
+      "step": 63
+    },
+    {
+      "epoch": 0.09502598366740905,
+      "grad_norm": 0.48664721846580505,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0352,
+      "step": 64
+    },
+    {
+      "epoch": 0.09651076466221233,
+      "grad_norm": 3.366154909133911,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0314,
+      "step": 65
+    },
+    {
+      "epoch": 0.09799554565701558,
+      "grad_norm": 1.3770588636398315,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0382,
+      "step": 66
+    },
+    {
+      "epoch": 0.09948032665181886,
+      "grad_norm": 0.6862576007843018,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0242,
+      "step": 67
+    },
+    {
+      "epoch": 0.10096510764662213,
+      "grad_norm": 0.8646849393844604,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0473,
+      "step": 68
+    },
+    {
+      "epoch": 0.10244988864142539,
+      "grad_norm": 0.4752139151096344,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0625,
+      "step": 69
+    },
+    {
+      "epoch": 0.10393466963622866,
+      "grad_norm": 1.9038113355636597,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.051,
+      "step": 70
+    },
+    {
+      "epoch": 0.10541945063103192,
+      "grad_norm": 0.5322926044464111,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0765,
+      "step": 71
+    },
+    {
+      "epoch": 0.10690423162583519,
+      "grad_norm": 0.49304574728012085,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0655,
+      "step": 72
+    },
+    {
+      "epoch": 0.10838901262063845,
+      "grad_norm": 0.17058974504470825,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.027,
+      "step": 73
+    },
+    {
+      "epoch": 0.10987379361544172,
+      "grad_norm": 0.644688606262207,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0848,
+      "step": 74
+    },
+    {
+      "epoch": 0.111358574610245,
+      "grad_norm": 0.3389902114868164,
+      "learning_rate": 0.0,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 0.111358574610245,
+      "eval_loss": 0.11129310727119446,
+      "eval_runtime": 143.6519,
+      "eval_samples_per_second": 3.954,
+      "eval_steps_per_second": 1.977,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.478754782950195e+16,
+  "total_flos": 1.1208807043773235e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null