Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0843b4710339e355417ea5c3d53e3337c4f9936f1130190471aa2d6600d680f9
+oid sha256:f13ca984f6d0c413fcfb6e715029a085579b9c1b2c0e546010574da49a2e2a8e
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5677ea3c757bcb95119e1c11bd30652bb06e348d9c588bb71ad4692ace505290
+oid sha256:169fc32d17e4ed1984b6ee832a6769f2dcf9d412e11026b72652bd6e13e9ac3b
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee8294c77ae09d993d18def2f554dbd035f7a1f5357c532a97ac81d6a6020db7
+oid sha256:3e061a416a5ce38cee7c74c0c90c474c049a77d62acf119a1f9c67d4ddcc3141
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0657030223390276,
+  "epoch": 0.1314060446780552,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 7.5821,
       "step": 25
+    },
+    {
+      "epoch": 0.0683311432325887,
+      "grad_norm": 4.332574844360352,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 7.2888,
+      "step": 26
+    },
+    {
+      "epoch": 0.07095926412614981,
+      "grad_norm": 4.837662696838379,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 6.845,
+      "step": 27
+    },
+    {
+      "epoch": 0.07095926412614981,
+      "eval_loss": 7.245150089263916,
+      "eval_runtime": 7.8267,
+      "eval_samples_per_second": 41.013,
+      "eval_steps_per_second": 5.238,
+      "step": 27
+    },
+    {
+      "epoch": 0.0735873850197109,
+      "grad_norm": 4.511839866638184,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 7.7317,
+      "step": 28
+    },
+    {
+      "epoch": 0.07621550591327202,
+      "grad_norm": 3.5038013458251953,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 7.1144,
+      "step": 29
+    },
+    {
+      "epoch": 0.07884362680683311,
+      "grad_norm": 3.6477413177490234,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 6.769,
+      "step": 30
+    },
+    {
+      "epoch": 0.08147174770039421,
+      "grad_norm": 3.408693790435791,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 6.6021,
+      "step": 31
+    },
+    {
+      "epoch": 0.08409986859395532,
+      "grad_norm": 4.711971282958984,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 7.4735,
+      "step": 32
+    },
+    {
+      "epoch": 0.08672798948751642,
+      "grad_norm": 5.069206237792969,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 7.4584,
+      "step": 33
+    },
+    {
+      "epoch": 0.08935611038107753,
+      "grad_norm": 4.098939418792725,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 7.27,
+      "step": 34
+    },
+    {
+      "epoch": 0.09198423127463863,
+      "grad_norm": 3.993582010269165,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 6.6474,
+      "step": 35
+    },
+    {
+      "epoch": 0.09461235216819974,
+      "grad_norm": 4.524712562561035,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 7.0525,
+      "step": 36
+    },
+    {
+      "epoch": 0.09461235216819974,
+      "eval_loss": 7.079109191894531,
+      "eval_runtime": 7.8096,
+      "eval_samples_per_second": 41.103,
+      "eval_steps_per_second": 5.25,
+      "step": 36
+    },
+    {
+      "epoch": 0.09724047306176084,
+      "grad_norm": 3.9363136291503906,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 7.2766,
+      "step": 37
+    },
+    {
+      "epoch": 0.09986859395532194,
+      "grad_norm": 3.650977849960327,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 6.9182,
+      "step": 38
+    },
+    {
+      "epoch": 0.10249671484888305,
+      "grad_norm": 3.0577781200408936,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 6.5284,
+      "step": 39
+    },
+    {
+      "epoch": 0.10512483574244415,
+      "grad_norm": 3.7681539058685303,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 6.9426,
+      "step": 40
+    },
+    {
+      "epoch": 0.10775295663600526,
+      "grad_norm": 3.7199325561523438,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 7.1631,
+      "step": 41
+    },
+    {
+      "epoch": 0.11038107752956636,
+      "grad_norm": 4.243125915527344,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 7.092,
+      "step": 42
+    },
+    {
+      "epoch": 0.11300919842312747,
+      "grad_norm": 4.146131992340088,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 7.5549,
+      "step": 43
+    },
+    {
+      "epoch": 0.11563731931668857,
+      "grad_norm": 3.312317132949829,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 7.0711,
+      "step": 44
+    },
+    {
+      "epoch": 0.11826544021024968,
+      "grad_norm": 3.4535398483276367,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 7.2084,
+      "step": 45
+    },
+    {
+      "epoch": 0.11826544021024968,
+      "eval_loss": 6.981412410736084,
+      "eval_runtime": 7.8222,
+      "eval_samples_per_second": 41.037,
+      "eval_steps_per_second": 5.241,
+      "step": 45
+    },
+    {
+      "epoch": 0.12089356110381078,
+      "grad_norm": 3.1890342235565186,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 6.7782,
+      "step": 46
+    },
+    {
+      "epoch": 0.12352168199737187,
+      "grad_norm": 3.076508045196533,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 6.8948,
+      "step": 47
+    },
+    {
+      "epoch": 0.12614980289093297,
+      "grad_norm": 4.208280563354492,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 7.0109,
+      "step": 48
+    },
+    {
+      "epoch": 0.1287779237844941,
+      "grad_norm": 2.896726369857788,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 6.866,
+      "step": 49
+    },
+    {
+      "epoch": 0.1314060446780552,
+      "grad_norm": 5.758768558502197,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 6.5004,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12488779235328.0,
+  "total_flos": 24163072868352.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null