Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213f0be151a40200fde1958a663eb06caba6c37381ecb4947f2ba091790915eb
+oid sha256:607e6d188c272b16d578b8f8c78e1a6f3ba5f4ea2576f8a3592c544b4528e80d
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d50024db83edae7917e8527a7001b835cd3e2bc73ff5ff0d51013f505c3e35d
+oid sha256:bb9f4173ee9c95edc54b3ff02c25db56dfdd1cba793e8d18d83dfeec8c97b193
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7872bf1923164f321afe3cb8b99acb68831b19235f469d62438123cc50586006
+oid sha256:ac3c6fe1e3951058283a55e7cfcd33b71182bc4fe2888cbb45fcc91b68e90260
 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": 0.03422899195618689,
+  "epoch": 0.06845798391237377,
   "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": 1.0503,
       "step": 25
+    },
+    {
+      "epoch": 0.03559815163443437,
+      "grad_norm": 0.9960324168205261,
+      "learning_rate": 0.0001,
+      "loss": 0.8392,
+      "step": 26
+    },
+    {
+      "epoch": 0.03696731131268184,
+      "grad_norm": 1.3512423038482666,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.8133,
+      "step": 27
+    },
+    {
+      "epoch": 0.038336470990929315,
+      "grad_norm": 1.276644229888916,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.684,
+      "step": 28
+    },
+    {
+      "epoch": 0.039705630669176796,
+      "grad_norm": 1.1981127262115479,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.8897,
+      "step": 29
+    },
+    {
+      "epoch": 0.04107479034742427,
+      "grad_norm": 1.1705209016799927,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.813,
+      "step": 30
+    },
+    {
+      "epoch": 0.042443950025671744,
+      "grad_norm": 1.0239105224609375,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.7486,
+      "step": 31
+    },
+    {
+      "epoch": 0.04381310970391922,
+      "grad_norm": 0.9569729566574097,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.8043,
+      "step": 32
+    },
+    {
+      "epoch": 0.0451822693821667,
+      "grad_norm": 0.8030011057853699,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7549,
+      "step": 33
+    },
+    {
+      "epoch": 0.04655142906041417,
+      "grad_norm": 1.0001657009124756,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8386,
+      "step": 34
+    },
+    {
+      "epoch": 0.047920588738661646,
+      "grad_norm": 1.130332112312317,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.6993,
+      "step": 35
+    },
+    {
+      "epoch": 0.04928974841690912,
+      "grad_norm": 0.7636102437973022,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.6943,
+      "step": 36
+    },
+    {
+      "epoch": 0.0506589080951566,
+      "grad_norm": 0.8889525532722473,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.8767,
+      "step": 37
+    },
+    {
+      "epoch": 0.052028067773404074,
+      "grad_norm": 0.9144881963729858,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.765,
+      "step": 38
+    },
+    {
+      "epoch": 0.05339722745165155,
+      "grad_norm": 1.054382562637329,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.0028,
+      "step": 39
+    },
+    {
+      "epoch": 0.05476638712989902,
+      "grad_norm": 1.131859302520752,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.9122,
+      "step": 40
+    },
+    {
+      "epoch": 0.0561355468081465,
+      "grad_norm": 0.8449717164039612,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.8733,
+      "step": 41
+    },
+    {
+      "epoch": 0.057504706486393976,
+      "grad_norm": 1.1658316850662231,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.8213,
+      "step": 42
+    },
+    {
+      "epoch": 0.05887386616464145,
+      "grad_norm": 0.9214019775390625,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.867,
+      "step": 43
+    },
+    {
+      "epoch": 0.060243025842888924,
+      "grad_norm": 1.1125028133392334,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.9207,
+      "step": 44
+    },
+    {
+      "epoch": 0.061612185521136405,
+      "grad_norm": 0.6265993714332581,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.5684,
+      "step": 45
+    },
+    {
+      "epoch": 0.06298134519938388,
+      "grad_norm": 0.9214088320732117,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.5572,
+      "step": 46
+    },
+    {
+      "epoch": 0.06435050487763136,
+      "grad_norm": 0.7752699851989746,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6001,
+      "step": 47
+    },
+    {
+      "epoch": 0.06571966455587883,
+      "grad_norm": 0.8832862973213196,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.8986,
+      "step": 48
+    },
+    {
+      "epoch": 0.0670888242341263,
+      "grad_norm": 0.9648825526237488,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.9162,
+      "step": 49
+    },
+    {
+      "epoch": 0.06845798391237377,
+      "grad_norm": 0.7902650833129883,
+      "learning_rate": 0.0,
+      "loss": 0.7039,
+      "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": 3.83447180771328e+16,
+  "total_flos": 7.66894361542656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null