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:ee267d4ee25168e4ae3fac806dfdd7183a8a79ca8ce06a4e834348c224c31e07
+oid sha256:072e641b94bc4510d00a4910d7689a9ee7062526f66f3d194da1c0ab736fbde3
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc357898dbfa3bb93e59fbb1a513d22ae3b9f4eb7db7b656899c881a3bbd0c6
+oid sha256:2bea845d7a9987451f62de6f4cce4dcbe2f085ff22bee7dfca722b65c16d1925
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e21865ea381293737aa0b639ba095a1ee30d7ac3d35a7d8ed003d9466e6584
+oid sha256:7c4ea7e49d5eaa0e0787ac4831b35d7bdc9f51e1e5a9e2150add586c2d26b7bc
 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": 0.028421202216853774,
+  "epoch": 0.05684240443370755,
   "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": 1.9019,
       "step": 25
+    },
+    {
+      "epoch": 0.029558050305527925,
+      "grad_norm": 0.9514207243919373,
+      "learning_rate": 0.0001,
+      "loss": 1.9525,
+      "step": 26
+    },
+    {
+      "epoch": 0.030694898394202075,
+      "grad_norm": 0.8910967111587524,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.7485,
+      "step": 27
+    },
+    {
+      "epoch": 0.031831746482876226,
+      "grad_norm": 1.0070226192474365,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.0128,
+      "step": 28
+    },
+    {
+      "epoch": 0.03296859457155037,
+      "grad_norm": 0.8559178709983826,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.5326,
+      "step": 29
+    },
+    {
+      "epoch": 0.03410544266022453,
+      "grad_norm": 0.8095901012420654,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.6773,
+      "step": 30
+    },
+    {
+      "epoch": 0.03524229074889868,
+      "grad_norm": 1.0621888637542725,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.6565,
+      "step": 31
+    },
+    {
+      "epoch": 0.03637913883757283,
+      "grad_norm": 1.2069458961486816,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.6746,
+      "step": 32
+    },
+    {
+      "epoch": 0.03751598692624698,
+      "grad_norm": 1.1669138669967651,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.9012,
+      "step": 33
+    },
+    {
+      "epoch": 0.03865283501492113,
+      "grad_norm": 0.8983680605888367,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.9007,
+      "step": 34
+    },
+    {
+      "epoch": 0.039789683103595284,
+      "grad_norm": 1.0233827829360962,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.4926,
+      "step": 35
+    },
+    {
+      "epoch": 0.04092653119226943,
+      "grad_norm": 0.7972369194030762,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.6314,
+      "step": 36
+    },
+    {
+      "epoch": 0.042063379280943586,
+      "grad_norm": 1.2082093954086304,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.5206,
+      "step": 37
+    },
+    {
+      "epoch": 0.04320022736961773,
+      "grad_norm": 1.1588741540908813,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.7528,
+      "step": 38
+    },
+    {
+      "epoch": 0.04433707545829189,
+      "grad_norm": 1.1021286249160767,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.8891,
+      "step": 39
+    },
+    {
+      "epoch": 0.045473923546966034,
+      "grad_norm": 0.8373359441757202,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.7719,
+      "step": 40
+    },
+    {
+      "epoch": 0.04661077163564019,
+      "grad_norm": 1.1442703008651733,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.8333,
+      "step": 41
+    },
+    {
+      "epoch": 0.047747619724314336,
+      "grad_norm": 0.8961570858955383,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.7535,
+      "step": 42
+    },
+    {
+      "epoch": 0.04888446781298849,
+      "grad_norm": 0.8508850932121277,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.667,
+      "step": 43
+    },
+    {
+      "epoch": 0.05002131590166264,
+      "grad_norm": 1.1900713443756104,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.8957,
+      "step": 44
+    },
+    {
+      "epoch": 0.05115816399033679,
+      "grad_norm": 0.7741867899894714,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.9832,
+      "step": 45
+    },
+    {
+      "epoch": 0.052295012079010945,
+      "grad_norm": 0.8075515031814575,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.8664,
+      "step": 46
+    },
+    {
+      "epoch": 0.05343186016768509,
+      "grad_norm": 0.9421095252037048,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.6778,
+      "step": 47
+    },
+    {
+      "epoch": 0.05456870825635925,
+      "grad_norm": 0.6307845115661621,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.8083,
+      "step": 48
+    },
+    {
+      "epoch": 0.055705556345033394,
+      "grad_norm": 1.0674786567687988,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.5506,
+      "step": 49
+    },
+    {
+      "epoch": 0.05684240443370755,
+      "grad_norm": 1.3023602962493896,
+      "learning_rate": 0.0,
+      "loss": 1.6605,
+      "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": 3.70943843106816e+16,
+  "total_flos": 7.455971246447002e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null