Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb29723e2376778e33b849e49b0704f44211e00dc6e8ee1a0ed8b0835a49b48
+oid sha256:49cb27e93648b513324ce6d2ae6d05439594fc84d641ffda20f5d012853f8181
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f4678766dd4bbb4b53b73a3808cce049d7c9dd496f04b17f2c98ee34927703
+oid sha256:3c44a892e4be01757e73ee6c5c2d0b3c226f4ba3f639985a52a9a35ef5c81dd5
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9812fa014f7f5539f3e2b7045d2bbadeeecf46f3ced408051b0714356bcc971
+oid sha256:82f299524aec0f09ca4f2de69dc662c32970e8fa30b7afcc6ba5da5e43e2404f
 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": 0.0016744668916033858,
+  "epoch": 0.0033489337832067717,
   "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": 4.7725,
       "step": 25
+    },
+    {
+      "epoch": 0.0017414455672675213,
+      "grad_norm": 3.8684911727905273,
+      "learning_rate": 0.0001,
+      "loss": 3.5878,
+      "step": 26
+    },
+    {
+      "epoch": 0.0018084242429316567,
+      "grad_norm": 4.367851257324219,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 7.1051,
+      "step": 27
+    },
+    {
+      "epoch": 0.001875402918595792,
+      "grad_norm": 4.9980268478393555,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 7.2694,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019423815942599275,
+      "grad_norm": 5.458781719207764,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 7.0591,
+      "step": 29
+    },
+    {
+      "epoch": 0.002009360269924063,
+      "grad_norm": 8.886860847473145,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.4029,
+      "step": 30
+    },
+    {
+      "epoch": 0.0020763389455881985,
+      "grad_norm": 3.7991790771484375,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 3.7206,
+      "step": 31
+    },
+    {
+      "epoch": 0.002143317621252334,
+      "grad_norm": 5.644777774810791,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.2581,
+      "step": 32
+    },
+    {
+      "epoch": 0.0022102962969164693,
+      "grad_norm": 3.7327921390533447,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.5899,
+      "step": 33
+    },
+    {
+      "epoch": 0.0022772749725806047,
+      "grad_norm": 5.269270896911621,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.5028,
+      "step": 34
+    },
+    {
+      "epoch": 0.00234425364824474,
+      "grad_norm": 5.034127235412598,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.2797,
+      "step": 35
+    },
+    {
+      "epoch": 0.0024112323239088755,
+      "grad_norm": 3.2906177043914795,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 4.7258,
+      "step": 36
+    },
+    {
+      "epoch": 0.002478210999573011,
+      "grad_norm": 7.394106388092041,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.7602,
+      "step": 37
+    },
+    {
+      "epoch": 0.0025451896752371464,
+      "grad_norm": 5.268815040588379,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 7.6848,
+      "step": 38
+    },
+    {
+      "epoch": 0.0026121683509012818,
+      "grad_norm": 6.3915228843688965,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 5.938,
+      "step": 39
+    },
+    {
+      "epoch": 0.002679147026565417,
+      "grad_norm": 4.054184436798096,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.9761,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027461257022295526,
+      "grad_norm": 15.989738464355469,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 8.2326,
+      "step": 41
+    },
+    {
+      "epoch": 0.002813104377893688,
+      "grad_norm": 4.472428798675537,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.3508,
+      "step": 42
+    },
+    {
+      "epoch": 0.0028800830535578234,
+      "grad_norm": 5.130801677703857,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 5.0871,
+      "step": 43
+    },
+    {
+      "epoch": 0.002947061729221959,
+      "grad_norm": 4.2026047706604,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.9424,
+      "step": 44
+    },
+    {
+      "epoch": 0.0030140404048860942,
+      "grad_norm": 3.842496156692505,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.4285,
+      "step": 45
+    },
+    {
+      "epoch": 0.0030810190805502296,
+      "grad_norm": 6.607271671295166,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.3277,
+      "step": 46
+    },
+    {
+      "epoch": 0.0031479977562143655,
+      "grad_norm": 5.300103664398193,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 7.2682,
+      "step": 47
+    },
+    {
+      "epoch": 0.003214976431878501,
+      "grad_norm": 4.57429838180542,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 4.5145,
+      "step": 48
+    },
+    {
+      "epoch": 0.0032819551075426363,
+      "grad_norm": 4.920131206512451,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 3.9698,
+      "step": 49
+    },
+    {
+      "epoch": 0.0033489337832067717,
+      "grad_norm": 3.9643123149871826,
+      "learning_rate": 0.0,
+      "loss": 5.5299,
+      "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": 3.26729100951552e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null