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:a66d213b745195544a36ac012b4c999d6c854a18566f396ae46835381bf546b2
+oid sha256:9fff3559e53dde391b8802dcd0b91aeaba2a9ca68861ce223dfac2e52817db8c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b670b26c73c946f441920ba8994f6cd48b5106a2f14124709fc8ec3f59c86306
+oid sha256:f96467dfef3f2c8a12e2fd9863494b8d03493857efa0a86ec6ea98b880cba2ea
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131638f436e8bb37629738f74a854b725c3aac9ffafa78166e41b44b87de4404
+oid sha256:612906cee6cbeda245ebb143c518adf38f767584c780d170e9c1244e20fc752b
 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": 0.28901734104046245,
+  "epoch": 0.43352601156069365,
   "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": 4.006,
       "eval_steps_per_second": 2.003,
       "step": 50
+    },
+    {
+      "epoch": 0.2947976878612717,
+      "grad_norm": 15.533300399780273,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.235,
+      "step": 51
+    },
+    {
+      "epoch": 0.30057803468208094,
+      "grad_norm": 17.215396881103516,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 4.012,
+      "step": 52
+    },
+    {
+      "epoch": 0.3063583815028902,
+      "grad_norm": 18.76911163330078,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 4.2551,
+      "step": 53
+    },
+    {
+      "epoch": 0.31213872832369943,
+      "grad_norm": 22.53728675842285,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.7717,
+      "step": 54
+    },
+    {
+      "epoch": 0.3179190751445087,
+      "grad_norm": 20.796886444091797,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.5363,
+      "step": 55
+    },
+    {
+      "epoch": 0.3236994219653179,
+      "grad_norm": 21.427318572998047,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 3.6933,
+      "step": 56
+    },
+    {
+      "epoch": 0.32947976878612717,
+      "grad_norm": 18.019439697265625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.5195,
+      "step": 57
+    },
+    {
+      "epoch": 0.3352601156069364,
+      "grad_norm": 20.15680503845215,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 4.5915,
+      "step": 58
+    },
+    {
+      "epoch": 0.34104046242774566,
+      "grad_norm": 16.63870620727539,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.874,
+      "step": 59
+    },
+    {
+      "epoch": 0.3468208092485549,
+      "grad_norm": 16.888946533203125,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.5552,
+      "step": 60
+    },
+    {
+      "epoch": 0.35260115606936415,
+      "grad_norm": 12.754011154174805,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 3.1729,
+      "step": 61
+    },
+    {
+      "epoch": 0.3583815028901734,
+      "grad_norm": 15.254498481750488,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 3.6215,
+      "step": 62
+    },
+    {
+      "epoch": 0.36416184971098264,
+      "grad_norm": 14.381755828857422,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9965,
+      "step": 63
+    },
+    {
+      "epoch": 0.3699421965317919,
+      "grad_norm": 10.36881160736084,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.8034,
+      "step": 64
+    },
+    {
+      "epoch": 0.37572254335260113,
+      "grad_norm": 8.4619140625,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.9042,
+      "step": 65
+    },
+    {
+      "epoch": 0.3815028901734104,
+      "grad_norm": 12.096026420593262,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5585,
+      "step": 66
+    },
+    {
+      "epoch": 0.3872832369942196,
+      "grad_norm": 8.332564353942871,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6868,
+      "step": 67
+    },
+    {
+      "epoch": 0.3930635838150289,
+      "grad_norm": 12.302162170410156,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.9655,
+      "step": 68
+    },
+    {
+      "epoch": 0.3988439306358382,
+      "grad_norm": 10.966118812561035,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6503,
+      "step": 69
+    },
+    {
+      "epoch": 0.4046242774566474,
+      "grad_norm": 6.788025379180908,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.4754,
+      "step": 70
+    },
+    {
+      "epoch": 0.41040462427745666,
+      "grad_norm": 18.9864559173584,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.7405,
+      "step": 71
+    },
+    {
+      "epoch": 0.4161849710982659,
+      "grad_norm": 10.223641395568848,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5099,
+      "step": 72
+    },
+    {
+      "epoch": 0.42196531791907516,
+      "grad_norm": 8.91974925994873,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.581,
+      "step": 73
+    },
+    {
+      "epoch": 0.4277456647398844,
+      "grad_norm": 12.053977966308594,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 1.0495,
+      "step": 74
+    },
+    {
+      "epoch": 0.43352601156069365,
+      "grad_norm": 9.938634872436523,
+      "learning_rate": 0.0,
+      "loss": 0.6133,
+      "step": 75
+    },
+    {
+      "epoch": 0.43352601156069365,
+      "eval_loss": 1.9379535913467407,
+      "eval_runtime": 36.0904,
+      "eval_samples_per_second": 4.045,
+      "eval_steps_per_second": 2.023,
+      "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": 1.158181226985554e+17,
+  "total_flos": 1.7232841445002445e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null