Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b87dc101dec6f0fc1343d0396af09cac18725cdafb90552a639f0e29a779e6d
+oid sha256:205550e43a72fb24397aedee76e31693a5be0f582b56ad69558c038bd716779e
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3176fa429bd8643d209a97d68f1158c971dffe737c6ad71ac2d9c97c780c0b58
+oid sha256:b28f4fa4fa3416ab2b69d386759599e343bd78a3c668820e807bd28c34d9cb3c
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0a7e302a41792c44ea039707b71433d9da812d1438c7dbfb736b340f8668a2
+oid sha256:c1f2e206ce39e403f72e4fdcf709009f64f769bff092502558ddde91f4c9ede5
 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": 0.02120665889089174,
+  "epoch": 0.04241331778178348,
   "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": 0.4836,
       "step": 25
+    },
+    {
+      "epoch": 0.02205492524652741,
+      "grad_norm": 0.6106640100479126,
+      "learning_rate": 0.0001,
+      "loss": 0.4531,
+      "step": 26
+    },
+    {
+      "epoch": 0.02290319160216308,
+      "grad_norm": 1.1405478715896606,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.4376,
+      "step": 27
+    },
+    {
+      "epoch": 0.02375145795779875,
+      "grad_norm": 0.7410005331039429,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.4823,
+      "step": 28
+    },
+    {
+      "epoch": 0.024599724313434417,
+      "grad_norm": 1.1606342792510986,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.4912,
+      "step": 29
+    },
+    {
+      "epoch": 0.025447990669070088,
+      "grad_norm": 1.0744168758392334,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.5038,
+      "step": 30
+    },
+    {
+      "epoch": 0.026296257024705758,
+      "grad_norm": 1.7132534980773926,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.5004,
+      "step": 31
+    },
+    {
+      "epoch": 0.02714452338034143,
+      "grad_norm": 1.147415280342102,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.466,
+      "step": 32
+    },
+    {
+      "epoch": 0.027992789735977096,
+      "grad_norm": 0.8624941110610962,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4736,
+      "step": 33
+    },
+    {
+      "epoch": 0.028841056091612766,
+      "grad_norm": 0.4240086078643799,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4587,
+      "step": 34
+    },
+    {
+      "epoch": 0.029689322447248437,
+      "grad_norm": 0.32580769062042236,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.4665,
+      "step": 35
+    },
+    {
+      "epoch": 0.030537588802884104,
+      "grad_norm": 7.6701531410217285,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.5514,
+      "step": 36
+    },
+    {
+      "epoch": 0.03138585515851978,
+      "grad_norm": 0.9737427234649658,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.4935,
+      "step": 37
+    },
+    {
+      "epoch": 0.032234121514155445,
+      "grad_norm": 0.7094717025756836,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4657,
+      "step": 38
+    },
+    {
+      "epoch": 0.03308238786979111,
+      "grad_norm": 0.39363011717796326,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.4559,
+      "step": 39
+    },
+    {
+      "epoch": 0.033930654225426786,
+      "grad_norm": 0.3725380599498749,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.4558,
+      "step": 40
+    },
+    {
+      "epoch": 0.03477892058106245,
+      "grad_norm": 1.143078088760376,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.4563,
+      "step": 41
+    },
+    {
+      "epoch": 0.03562718693669812,
+      "grad_norm": 0.5376627445220947,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.4571,
+      "step": 42
+    },
+    {
+      "epoch": 0.036475453292333794,
+      "grad_norm": 0.742919385433197,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.4705,
+      "step": 43
+    },
+    {
+      "epoch": 0.03732371964796946,
+      "grad_norm": 0.7047212719917297,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.4764,
+      "step": 44
+    },
+    {
+      "epoch": 0.038171986003605135,
+      "grad_norm": 1.3539237976074219,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.4871,
+      "step": 45
+    },
+    {
+      "epoch": 0.0390202523592408,
+      "grad_norm": 2.224294424057007,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.5089,
+      "step": 46
+    },
+    {
+      "epoch": 0.03986851871487647,
+      "grad_norm": 1.2979936599731445,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.4834,
+      "step": 47
+    },
+    {
+      "epoch": 0.04071678507051214,
+      "grad_norm": 0.9504252672195435,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.4433,
+      "step": 48
+    },
+    {
+      "epoch": 0.04156505142614781,
+      "grad_norm": 0.7085014581680298,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.4401,
+      "step": 49
+    },
+    {
+      "epoch": 0.04241331778178348,
+      "grad_norm": 1.5509270429611206,
+      "learning_rate": 0.0,
+      "loss": 0.4014,
+      "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": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null