Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801066273382ad9bd75d81e1271ce2fcc67f368b0e7873ec6765f45d48d45687
+oid sha256:f24ce07b381e1cffb4d735cc54dfe6deaadf8ecc49f34a96c2828de0577a52e2
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d066ca19d6221b5c2563031e392a0fb4aaa990613a0ef497498eb2e5fd16bb
+oid sha256:9673953fd049a7e74ee943a31b5c7f8c3649986f2d30e1325a0c2fb4ba3bdf79
 size 800394282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65076d159784cf12fd935950cc80a50cd767edca11b9643742f5d1d58eb9d2d
+oid sha256:a921e14ff863e0c6d6d583f3af66c9bec88a7abe8a32c5895a333163b1fae11a
 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": 0.039012971813127864,
+  "epoch": 0.058519457719691796,
   "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": 3.342,
       "eval_steps_per_second": 1.671,
       "step": 50
+    },
+    {
+      "epoch": 0.03979323124939042,
+      "grad_norm": 0.2862579822540283,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.507,
+      "step": 51
+    },
+    {
+      "epoch": 0.04057349068565298,
+      "grad_norm": 0.3461783230304718,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.5549,
+      "step": 52
+    },
+    {
+      "epoch": 0.041353750121915535,
+      "grad_norm": 0.4043627977371216,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.6321,
+      "step": 53
+    },
+    {
+      "epoch": 0.042134009558178094,
+      "grad_norm": 0.37553367018699646,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.571,
+      "step": 54
+    },
+    {
+      "epoch": 0.04291426899444065,
+      "grad_norm": 0.36022651195526123,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.5375,
+      "step": 55
+    },
+    {
+      "epoch": 0.043694528430703206,
+      "grad_norm": 0.4114338457584381,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.6081,
+      "step": 56
+    },
+    {
+      "epoch": 0.044474787866965765,
+      "grad_norm": 0.3871912956237793,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6099,
+      "step": 57
+    },
+    {
+      "epoch": 0.045255047303228324,
+      "grad_norm": 0.40150532126426697,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.6333,
+      "step": 58
+    },
+    {
+      "epoch": 0.04603530673949088,
+      "grad_norm": 0.49420806765556335,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.773,
+      "step": 59
+    },
+    {
+      "epoch": 0.046815566175753436,
+      "grad_norm": 0.42875587940216064,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5722,
+      "step": 60
+    },
+    {
+      "epoch": 0.047595825612015995,
+      "grad_norm": 0.4141090512275696,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.6371,
+      "step": 61
+    },
+    {
+      "epoch": 0.048376085048278554,
+      "grad_norm": 0.42042094469070435,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.6135,
+      "step": 62
+    },
+    {
+      "epoch": 0.04915634448454111,
+      "grad_norm": 0.4620630145072937,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7216,
+      "step": 63
+    },
+    {
+      "epoch": 0.049936603920803666,
+      "grad_norm": 0.47221145033836365,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.6438,
+      "step": 64
+    },
+    {
+      "epoch": 0.050716863357066225,
+      "grad_norm": 0.4742897152900696,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.7366,
+      "step": 65
+    },
+    {
+      "epoch": 0.051497122793328784,
+      "grad_norm": 0.4719804525375366,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6938,
+      "step": 66
+    },
+    {
+      "epoch": 0.052277382229591336,
+      "grad_norm": 0.49254298210144043,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7749,
+      "step": 67
+    },
+    {
+      "epoch": 0.053057641665853895,
+      "grad_norm": 0.521112859249115,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.7219,
+      "step": 68
+    },
+    {
+      "epoch": 0.053837901102116455,
+      "grad_norm": 0.5138411521911621,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.832,
+      "step": 69
+    },
+    {
+      "epoch": 0.054618160538379014,
+      "grad_norm": 0.5415810942649841,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.8144,
+      "step": 70
+    },
+    {
+      "epoch": 0.055398419974641566,
+      "grad_norm": 0.6076228022575378,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9642,
+      "step": 71
+    },
+    {
+      "epoch": 0.056178679410904125,
+      "grad_norm": 0.5630006194114685,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7559,
+      "step": 72
+    },
+    {
+      "epoch": 0.056958938847166685,
+      "grad_norm": 0.608703076839447,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.8729,
+      "step": 73
+    },
+    {
+      "epoch": 0.05773919828342924,
+      "grad_norm": 0.569412887096405,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.7729,
+      "step": 74
+    },
+    {
+      "epoch": 0.058519457719691796,
+      "grad_norm": 0.6440850496292114,
+      "learning_rate": 0.0,
+      "loss": 0.8444,
+      "step": 75
+    },
+    {
+      "epoch": 0.058519457719691796,
+      "eval_loss": 0.7578212022781372,
+      "eval_runtime": 323.0666,
+      "eval_samples_per_second": 3.343,
+      "eval_steps_per_second": 1.671,
+      "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": 7.737394764919603e+16,
+  "total_flos": 1.163503502056489e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null