Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6956b010fb151b53d07a1e970a9fc53b98180058d62928ea228fb6724baf5000
+oid sha256:09dd58065250b95b56fb64892a7aeae29e49ec9b389bd0ef71db5562134d8a18
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714248c11491da7b9aa30fe14398d55c4bc0fb644d38384c5d37ea453ed4319d
+oid sha256:e88ea0bcbb7cf03b46fbb88b34ee44f94667c7b773e675672eccc87eeefd35e9
 size 141053442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea69299994decb17e18a83eb99fb67f098332a1a520d63888f0abaefddc18940
+oid sha256:92d632d83ca830ed7a5b151d4d141df872c3e2037ed131c64d64282604206c0d
 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": 0.006916346785627831,
+  "epoch": 0.010374520178441747,
   "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": 25.901,
       "eval_steps_per_second": 12.95,
       "step": 50
+    },
+    {
+      "epoch": 0.007054673721340388,
+      "grad_norm": 0.7963781356811523,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0457,
+      "step": 51
+    },
+    {
+      "epoch": 0.007193000657052945,
+      "grad_norm": 0.6593269109725952,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0371,
+      "step": 52
+    },
+    {
+      "epoch": 0.007331327592765501,
+      "grad_norm": 0.41870707273483276,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0441,
+      "step": 53
+    },
+    {
+      "epoch": 0.007469654528478058,
+      "grad_norm": 0.25951045751571655,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0695,
+      "step": 54
+    },
+    {
+      "epoch": 0.0076079814641906145,
+      "grad_norm": 0.14817692339420319,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1199,
+      "step": 55
+    },
+    {
+      "epoch": 0.007746308399903171,
+      "grad_norm": 0.13541370630264282,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.1298,
+      "step": 56
+    },
+    {
+      "epoch": 0.007884635335615727,
+      "grad_norm": 0.1340421736240387,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1753,
+      "step": 57
+    },
+    {
+      "epoch": 0.008022962271328284,
+      "grad_norm": 0.13916298747062683,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.1984,
+      "step": 58
+    },
+    {
+      "epoch": 0.008161289207040841,
+      "grad_norm": 0.15943610668182373,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.2099,
+      "step": 59
+    },
+    {
+      "epoch": 0.008299616142753397,
+      "grad_norm": 0.12862175703048706,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1788,
+      "step": 60
+    },
+    {
+      "epoch": 0.008437943078465954,
+      "grad_norm": 0.15144962072372437,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.1953,
+      "step": 61
+    },
+    {
+      "epoch": 0.008576270014178511,
+      "grad_norm": 0.15256360173225403,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.2154,
+      "step": 62
+    },
+    {
+      "epoch": 0.008714596949891068,
+      "grad_norm": 0.16836214065551758,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2344,
+      "step": 63
+    },
+    {
+      "epoch": 0.008852923885603624,
+      "grad_norm": 0.17673300206661224,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.2463,
+      "step": 64
+    },
+    {
+      "epoch": 0.008991250821316181,
+      "grad_norm": 0.15946948528289795,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.2361,
+      "step": 65
+    },
+    {
+      "epoch": 0.009129577757028738,
+      "grad_norm": 0.1620546281337738,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2735,
+      "step": 66
+    },
+    {
+      "epoch": 0.009267904692741294,
+      "grad_norm": 0.1820289045572281,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3154,
+      "step": 67
+    },
+    {
+      "epoch": 0.00940623162845385,
+      "grad_norm": 0.16451966762542725,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.2236,
+      "step": 68
+    },
+    {
+      "epoch": 0.009544558564166408,
+      "grad_norm": 0.16016404330730438,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2403,
+      "step": 69
+    },
+    {
+      "epoch": 0.009682885499878963,
+      "grad_norm": 0.16386066377162933,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.1931,
+      "step": 70
+    },
+    {
+      "epoch": 0.00982121243559152,
+      "grad_norm": 0.14483347535133362,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.1527,
+      "step": 71
+    },
+    {
+      "epoch": 0.009959539371304078,
+      "grad_norm": 0.1619541198015213,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2265,
+      "step": 72
+    },
+    {
+      "epoch": 0.010097866307016633,
+      "grad_norm": 0.1760704070329666,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.2726,
+      "step": 73
+    },
+    {
+      "epoch": 0.01023619324272919,
+      "grad_norm": 0.17598259449005127,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.2242,
+      "step": 74
+    },
+    {
+      "epoch": 0.010374520178441747,
+      "grad_norm": 0.22251029312610626,
+      "learning_rate": 0.0,
+      "loss": 0.327,
+      "step": 75
+    },
+    {
+      "epoch": 0.010374520178441747,
+      "eval_loss": 0.24053539335727692,
+      "eval_runtime": 468.1532,
+      "eval_samples_per_second": 26.009,
+      "eval_steps_per_second": 13.004,
+      "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": 9837211652456448.0,
+  "total_flos": 1.6149268660224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null