Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de977090b0f7f86c39a6a69aa672fb68dc774cc34751b11a20af31b7dbc29d7
+oid sha256:f1beb0da4515f5da56181512c2e131f81c497c822d82fd1727e65295753af60c
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef933f8d359ddc8e97dce6bcca79b9bd36349e712aae4cd22aa175241cdc2cd
+oid sha256:c3879eca3ab8b82d82345db5aab468e91b47a3d84f8ce57a341f671ca3adc8dd
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2cd65a01328b31c8d063a55a5aac044d6279fb50d856f7a96e8f6595391d70e
+oid sha256:489170294b902ef280b862c983779b4583bf15b49a5cacb6b40477cd029e37ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006833635152219223,
+  "epoch": 0.013667270304438445,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 3.1356,
       "step": 25
+    },
+    {
+      "epoch": 0.007106980558307992,
+      "grad_norm": 0.9289854168891907,
+      "learning_rate": 0.0001,
+      "loss": 3.0933,
+      "step": 26
+    },
+    {
+      "epoch": 0.0073803259643967604,
+      "grad_norm": 1.1718719005584717,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 3.101,
+      "step": 27
+    },
+    {
+      "epoch": 0.00765367137048553,
+      "grad_norm": 0.9577802419662476,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 3.1211,
+      "step": 28
+    },
+    {
+      "epoch": 0.007927016776574298,
+      "grad_norm": 1.1697319746017456,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 3.1352,
+      "step": 29
+    },
+    {
+      "epoch": 0.008200362182663068,
+      "grad_norm": 1.2574468851089478,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 3.0314,
+      "step": 30
+    },
+    {
+      "epoch": 0.008473707588751836,
+      "grad_norm": 1.2412081956863403,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 3.0771,
+      "step": 31
+    },
+    {
+      "epoch": 0.008747052994840606,
+      "grad_norm": 0.9908276200294495,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.1798,
+      "step": 32
+    },
+    {
+      "epoch": 0.009020398400929374,
+      "grad_norm": 1.9833407402038574,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 3.1328,
+      "step": 33
+    },
+    {
+      "epoch": 0.009293743807018143,
+      "grad_norm": 1.302556037902832,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.1284,
+      "step": 34
+    },
+    {
+      "epoch": 0.009567089213106911,
+      "grad_norm": 1.1386475563049316,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 3.0847,
+      "step": 35
+    },
+    {
+      "epoch": 0.009840434619195681,
+      "grad_norm": 1.1478960514068604,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 3.1663,
+      "step": 36
+    },
+    {
+      "epoch": 0.010113780025284451,
+      "grad_norm": 1.2641170024871826,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 3.0924,
+      "step": 37
+    },
+    {
+      "epoch": 0.010387125431373219,
+      "grad_norm": 1.2993226051330566,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.0908,
+      "step": 38
+    },
+    {
+      "epoch": 0.010660470837461989,
+      "grad_norm": 0.7408443689346313,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 3.1104,
+      "step": 39
+    },
+    {
+      "epoch": 0.010933816243550757,
+      "grad_norm": 1.1869138479232788,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 3.0775,
+      "step": 40
+    },
+    {
+      "epoch": 0.011207161649639526,
+      "grad_norm": 1.3214056491851807,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 3.0865,
+      "step": 41
+    },
+    {
+      "epoch": 0.011480507055728294,
+      "grad_norm": 1.411237359046936,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 3.0958,
+      "step": 42
+    },
+    {
+      "epoch": 0.011753852461817064,
+      "grad_norm": 1.0202186107635498,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 3.1997,
+      "step": 43
+    },
+    {
+      "epoch": 0.012027197867905832,
+      "grad_norm": 1.3209668397903442,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.0356,
+      "step": 44
+    },
+    {
+      "epoch": 0.012300543273994602,
+      "grad_norm": 0.9961850047111511,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.1217,
+      "step": 45
+    },
+    {
+      "epoch": 0.01257388868008337,
+      "grad_norm": 1.1770366430282593,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 3.1282,
+      "step": 46
+    },
+    {
+      "epoch": 0.01284723408617214,
+      "grad_norm": 1.0524556636810303,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 3.1751,
+      "step": 47
+    },
+    {
+      "epoch": 0.013120579492260908,
+      "grad_norm": 0.8674744367599487,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.0894,
+      "step": 48
+    },
+    {
+      "epoch": 0.013393924898349677,
+      "grad_norm": 1.242981195449829,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.0561,
+      "step": 49
+    },
+    {
+      "epoch": 0.013667270304438445,
+      "grad_norm": 1.4760891199111938,
+      "learning_rate": 0.0,
+      "loss": 3.0578,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.853644166751846e+16,
+  "total_flos": 7.688115974465126e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null