Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c07143a84790b9628bda128f8d12efab4e288b4abe06fea2b661188b3c1a265
+oid sha256:53429a7f4d0f48fb455f3106eff57e472ec624476411582ddf5c7f3fc4221cad
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ec1a57c1a5594ab279522989d3291b319f492458443f3c893c559860499bb6
+oid sha256:01f2613385de80be0d5eecfaf23c9e11ede7eec3363769f981e8fc141fe22827
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dbae792495e95810206d2c804457e79c27be925d89161ab25f0ce9dcf664a2e
+oid sha256:7d214d3425777f2829fbb4e3b87893c734ef24ce11510f3020ded0f9a12a813a
 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": 0.0024904119141305973,
+  "epoch": 0.0049808238282611945,
   "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": 1.5551,
       "step": 25
+    },
+    {
+      "epoch": 0.002590028390695821,
+      "grad_norm": 0.7066437602043152,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.5937,
+      "step": 26
+    },
+    {
+      "epoch": 0.002689644867261045,
+      "grad_norm": 0.684407651424408,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.4366,
+      "step": 27
+    },
+    {
+      "epoch": 0.002689644867261045,
+      "eval_loss": 0.8160959482192993,
+      "eval_runtime": 883.6722,
+      "eval_samples_per_second": 9.567,
+      "eval_steps_per_second": 1.196,
+      "step": 27
+    },
+    {
+      "epoch": 0.002789261343826269,
+      "grad_norm": 0.7681823372840881,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4063,
+      "step": 28
+    },
+    {
+      "epoch": 0.002888877820391493,
+      "grad_norm": 0.7006301879882812,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.2299,
+      "step": 29
+    },
+    {
+      "epoch": 0.0029884942969567166,
+      "grad_norm": 0.8284811973571777,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.7102,
+      "step": 30
+    },
+    {
+      "epoch": 0.0030881107735219403,
+      "grad_norm": 0.8312244415283203,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.4079,
+      "step": 31
+    },
+    {
+      "epoch": 0.0031877272500871645,
+      "grad_norm": 0.6091031432151794,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.2915,
+      "step": 32
+    },
+    {
+      "epoch": 0.0032873437266523883,
+      "grad_norm": 0.7346383929252625,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.4389,
+      "step": 33
+    },
+    {
+      "epoch": 0.003386960203217612,
+      "grad_norm": 0.8104448914527893,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.65,
+      "step": 34
+    },
+    {
+      "epoch": 0.0034865766797828363,
+      "grad_norm": 0.9100492596626282,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.857,
+      "step": 35
+    },
+    {
+      "epoch": 0.00358619315634806,
+      "grad_norm": 0.6399231553077698,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.803,
+      "step": 36
+    },
+    {
+      "epoch": 0.00358619315634806,
+      "eval_loss": 0.7986570596694946,
+      "eval_runtime": 883.7392,
+      "eval_samples_per_second": 9.566,
+      "eval_steps_per_second": 1.196,
+      "step": 36
+    },
+    {
+      "epoch": 0.003685809632913284,
+      "grad_norm": 0.6590905785560608,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.5133,
+      "step": 37
+    },
+    {
+      "epoch": 0.0037854261094785076,
+      "grad_norm": 0.7415932416915894,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.6611,
+      "step": 38
+    },
+    {
+      "epoch": 0.0038850425860437318,
+      "grad_norm": 0.9437408447265625,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.8239,
+      "step": 39
+    },
+    {
+      "epoch": 0.003984659062608955,
+      "grad_norm": 0.7338345050811768,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.5454,
+      "step": 40
+    },
+    {
+      "epoch": 0.004084275539174179,
+      "grad_norm": 0.6436401605606079,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.6553,
+      "step": 41
+    },
+    {
+      "epoch": 0.0041838920157394035,
+      "grad_norm": 0.6931898593902588,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.7065,
+      "step": 42
+    },
+    {
+      "epoch": 0.004283508492304627,
+      "grad_norm": 0.6704197525978088,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.4526,
+      "step": 43
+    },
+    {
+      "epoch": 0.004383124968869851,
+      "grad_norm": 0.6947505474090576,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.6123,
+      "step": 44
+    },
+    {
+      "epoch": 0.004482741445435075,
+      "grad_norm": 0.7843073010444641,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.562,
+      "step": 45
+    },
+    {
+      "epoch": 0.004482741445435075,
+      "eval_loss": 0.7821637392044067,
+      "eval_runtime": 884.1235,
+      "eval_samples_per_second": 9.562,
+      "eval_steps_per_second": 1.196,
+      "step": 45
+    },
+    {
+      "epoch": 0.004582357922000299,
+      "grad_norm": 0.7678735852241516,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.6434,
+      "step": 46
+    },
+    {
+      "epoch": 0.004681974398565523,
+      "grad_norm": 0.6877706050872803,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.4048,
+      "step": 47
+    },
+    {
+      "epoch": 0.004781590875130747,
+      "grad_norm": 0.584237813949585,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.3832,
+      "step": 48
+    },
+    {
+      "epoch": 0.00488120735169597,
+      "grad_norm": 0.8516788482666016,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.8079,
+      "step": 49
+    },
+    {
+      "epoch": 0.0049808238282611945,
+      "grad_norm": 0.7160507440567017,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.6585,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.237393280794624e+16,
+  "total_flos": 6.411308261965824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null