Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595293cceb94afedf599f0d85bc0ad86ff1749411d4e5d11c2f229a9da445069
+oid sha256:88d6f20e86144705b4827e731a2dcf85c85d2957d5607cbe94a64810edd095cc
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fc5ce169bd802e64e4ac3cda08cc18ec26e079ff29814bc87984f0abbef165
+oid sha256:d5070ff7bda8a670154dc665fd1d1a03cccff2fec04d5aa4046b9b0f1e5db335
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec4367c5db0e052c3886b64140df6b844088f9328f30af4f27b0230a998a502
+oid sha256:01514a7f961e8060556a2768677956d5009239d9691aa907112442408b67774e
 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": 0.014138272303124559,
+  "epoch": 0.028276544606249118,
   "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": 3.9988,
       "step": 25
+    },
+    {
+      "epoch": 0.01470380319524954,
+      "grad_norm": 0.8450819253921509,
+      "learning_rate": 0.0001,
+      "loss": 4.0739,
+      "step": 26
+    },
+    {
+      "epoch": 0.015269334087374523,
+      "grad_norm": 1.9969067573547363,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 3.9674,
+      "step": 27
+    },
+    {
+      "epoch": 0.015834864979499506,
+      "grad_norm": 0.7638323903083801,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 3.9486,
+      "step": 28
+    },
+    {
+      "epoch": 0.016400395871624486,
+      "grad_norm": 0.6288601756095886,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 3.8704,
+      "step": 29
+    },
+    {
+      "epoch": 0.01696592676374947,
+      "grad_norm": 1.469429612159729,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 4.1891,
+      "step": 30
+    },
+    {
+      "epoch": 0.017531457655874452,
+      "grad_norm": 1.1576073169708252,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 3.986,
+      "step": 31
+    },
+    {
+      "epoch": 0.018096988547999435,
+      "grad_norm": 0.9627673029899597,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.1144,
+      "step": 32
+    },
+    {
+      "epoch": 0.01866251944012442,
+      "grad_norm": 0.7569557428359985,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 4.0838,
+      "step": 33
+    },
+    {
+      "epoch": 0.019228050332249398,
+      "grad_norm": 0.7780810594558716,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.0803,
+      "step": 34
+    },
+    {
+      "epoch": 0.01979358122437438,
+      "grad_norm": 1.5027967691421509,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 3.9828,
+      "step": 35
+    },
+    {
+      "epoch": 0.020359112116499364,
+      "grad_norm": 0.9394671320915222,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 4.0787,
+      "step": 36
+    },
+    {
+      "epoch": 0.020924643008624347,
+      "grad_norm": 0.8779884576797485,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.0903,
+      "step": 37
+    },
+    {
+      "epoch": 0.021490173900749327,
+      "grad_norm": 1.4611361026763916,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.9183,
+      "step": 38
+    },
+    {
+      "epoch": 0.02205570479287431,
+      "grad_norm": 0.7395803928375244,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 4.1387,
+      "step": 39
+    },
+    {
+      "epoch": 0.022621235684999293,
+      "grad_norm": 0.8143374919891357,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 4.1567,
+      "step": 40
+    },
+    {
+      "epoch": 0.023186766577124276,
+      "grad_norm": 0.7555928826332092,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 4.0109,
+      "step": 41
+    },
+    {
+      "epoch": 0.023752297469249256,
+      "grad_norm": 0.749727189540863,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 4.0942,
+      "step": 42
+    },
+    {
+      "epoch": 0.02431782836137424,
+      "grad_norm": 2.71633243560791,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 3.978,
+      "step": 43
+    },
+    {
+      "epoch": 0.024883359253499222,
+      "grad_norm": 0.856410026550293,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.8863,
+      "step": 44
+    },
+    {
+      "epoch": 0.025448890145624205,
+      "grad_norm": 0.9397003054618835,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.8758,
+      "step": 45
+    },
+    {
+      "epoch": 0.02601442103774919,
+      "grad_norm": 0.8372579216957092,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 4.1118,
+      "step": 46
+    },
+    {
+      "epoch": 0.026579951929874168,
+      "grad_norm": 0.6836534142494202,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 4.0193,
+      "step": 47
+    },
+    {
+      "epoch": 0.02714548282199915,
+      "grad_norm": 0.7352842688560486,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 3.9597,
+      "step": 48
+    },
+    {
+      "epoch": 0.027711013714124134,
+      "grad_norm": 1.5941392183303833,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 4.1411,
+      "step": 49
+    },
+    {
+      "epoch": 0.028276544606249118,
+      "grad_norm": 1.6705574989318848,
+      "learning_rate": 0.0,
+      "loss": 4.1692,
+      "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": 4.11806271012864e+16,
+  "total_flos": 8.23612542025728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null