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:a52fede561c5b0071b97c88f7f1accfbd096449b7e3dfa04a2d96442205c54e2
+oid sha256:a5210c6ca9944bce13b58d4ba79c6a80e67cd770ae5cbe56d34838a9a59bc8c1
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a3dfab0a0748ebcb8a48cc9d467b8cb27f6fb930c7a0f252d18ac6338061ce
+oid sha256:4a20706f6b61074e3d7948fd2b9eac6d9dd7755f7605ead2ee3ef2a2ea16ae2c
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b8ba95982c7e1d308216fc72a1f7f09b31cf15039a4666dbb57145c56bfcaf
+oid sha256:59b4b203078662e2df510d692bb756008dd90565b970954bedd8618557f6d690
 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": 0.001134301270417423,
+  "epoch": 0.0017014519056261343,
   "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": 29.901,
       "eval_steps_per_second": 14.951,
       "step": 50
+    },
+    {
+      "epoch": 0.0011569872958257714,
+      "grad_norm": 10.760135650634766,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.619,
+      "step": 51
+    },
+    {
+      "epoch": 0.0011796733212341198,
+      "grad_norm": 10.61867618560791,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.6049,
+      "step": 52
+    },
+    {
+      "epoch": 0.0012023593466424683,
+      "grad_norm": 9.48973560333252,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 2.4759,
+      "step": 53
+    },
+    {
+      "epoch": 0.0012250453720508167,
+      "grad_norm": 8.987316131591797,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3972,
+      "step": 54
+    },
+    {
+      "epoch": 0.0012477313974591652,
+      "grad_norm": 8.111326217651367,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.3231,
+      "step": 55
+    },
+    {
+      "epoch": 0.0012704174228675136,
+      "grad_norm": 6.617386817932129,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 2.1985,
+      "step": 56
+    },
+    {
+      "epoch": 0.001293103448275862,
+      "grad_norm": 4.567836761474609,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1746,
+      "step": 57
+    },
+    {
+      "epoch": 0.0013157894736842105,
+      "grad_norm": 2.5743725299835205,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 2.0999,
+      "step": 58
+    },
+    {
+      "epoch": 0.001338475499092559,
+      "grad_norm": 2.6298258304595947,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0759,
+      "step": 59
+    },
+    {
+      "epoch": 0.0013611615245009074,
+      "grad_norm": 2.5134525299072266,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0232,
+      "step": 60
+    },
+    {
+      "epoch": 0.0013838475499092558,
+      "grad_norm": 2.05859637260437,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 2.0579,
+      "step": 61
+    },
+    {
+      "epoch": 0.0014065335753176043,
+      "grad_norm": 1.8161320686340332,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 2.0462,
+      "step": 62
+    },
+    {
+      "epoch": 0.0014292196007259527,
+      "grad_norm": 1.8273543119430542,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.037,
+      "step": 63
+    },
+    {
+      "epoch": 0.0014519056261343012,
+      "grad_norm": 1.3664026260375977,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 2.032,
+      "step": 64
+    },
+    {
+      "epoch": 0.0014745916515426498,
+      "grad_norm": 1.3599556684494019,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 2.0063,
+      "step": 65
+    },
+    {
+      "epoch": 0.0014972776769509983,
+      "grad_norm": 1.333756446838379,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9905,
+      "step": 66
+    },
+    {
+      "epoch": 0.0015199637023593467,
+      "grad_norm": 1.4712531566619873,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0231,
+      "step": 67
+    },
+    {
+      "epoch": 0.0015426497277676952,
+      "grad_norm": 1.438612937927246,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.9859,
+      "step": 68
+    },
+    {
+      "epoch": 0.0015653357531760436,
+      "grad_norm": 1.5220595598220825,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9783,
+      "step": 69
+    },
+    {
+      "epoch": 0.001588021778584392,
+      "grad_norm": 1.3201245069503784,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 2.011,
+      "step": 70
+    },
+    {
+      "epoch": 0.0016107078039927405,
+      "grad_norm": 1.3130794763565063,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.0053,
+      "step": 71
+    },
+    {
+      "epoch": 0.001633393829401089,
+      "grad_norm": 1.6226977109909058,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.978,
+      "step": 72
+    },
+    {
+      "epoch": 0.0016560798548094374,
+      "grad_norm": 1.4479483366012573,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 2.0057,
+      "step": 73
+    },
+    {
+      "epoch": 0.0016787658802177858,
+      "grad_norm": 1.4476728439331055,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 2.0159,
+      "step": 74
+    },
+    {
+      "epoch": 0.0017014519056261343,
+      "grad_norm": 1.5175923109054565,
+      "learning_rate": 0.0,
+      "loss": 1.9565,
+      "step": 75
+    },
+    {
+      "epoch": 0.0017014519056261343,
+      "eval_loss": 1.9482790231704712,
+      "eval_runtime": 1240.3995,
+      "eval_samples_per_second": 29.926,
+      "eval_steps_per_second": 14.963,
+      "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": 9788035851878400.0,
+  "total_flos": 1.46820537778176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null