Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600d952c4ee4a0aadb5a852669229e453bc5bc055db09bddf09c3dab223afd08
+oid sha256:a71a756c10378d89178e2eb6ca9b32a3b826606e402bb33b1e9bbe0bdc301807
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590cb45cab18da958fd69303494fcd750a16d5a03f96111e42d9245bf038bb35
+oid sha256:fc9ca7cf0c61e7b1b93d373e4ec68bbb6860512dd30f5c4449cb9cfa8e1e8fe9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0160325f3cfb2789544f924daf3b9721842346abd05e8dbfa142d277b468e99a
+oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
 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": 0.0006197706848466068,
+  "epoch": 0.0012395413696932136,
   "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": 0.0552,
       "step": 25
+    },
+    {
+      "epoch": 0.000644561512240471,
+      "grad_norm": 0.26518455147743225,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0045,
+      "step": 26
+    },
+    {
+      "epoch": 0.0006693523396343353,
+      "grad_norm": 0.3753717541694641,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.003,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006693523396343353,
+      "eval_loss": 0.06290628761053085,
+      "eval_runtime": 3459.9356,
+      "eval_samples_per_second": 9.818,
+      "eval_steps_per_second": 1.227,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006941431670281996,
+      "grad_norm": 0.20908643305301666,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0015,
+      "step": 28
+    },
+    {
+      "epoch": 0.0007189339944220638,
+      "grad_norm": 0.05302276089787483,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.0007437248218159281,
+      "grad_norm": 0.017372814938426018,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0002,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007685156492097924,
+      "grad_norm": 6.220452308654785,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.4412,
+      "step": 31
+    },
+    {
+      "epoch": 0.0007933064766036566,
+      "grad_norm": 3.6316118240356445,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.2788,
+      "step": 32
+    },
+    {
+      "epoch": 0.0008180973039975209,
+      "grad_norm": 3.141017436981201,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.2178,
+      "step": 33
+    },
+    {
+      "epoch": 0.0008428881313913852,
+      "grad_norm": 0.36752939224243164,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0052,
+      "step": 34
+    },
+    {
+      "epoch": 0.0008676789587852494,
+      "grad_norm": 0.10909147560596466,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0014,
+      "step": 35
+    },
+    {
+      "epoch": 0.0008924697861791137,
+      "grad_norm": 0.14188747107982635,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0018,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008924697861791137,
+      "eval_loss": 0.01222518365830183,
+      "eval_runtime": 3459.2234,
+      "eval_samples_per_second": 9.82,
+      "eval_steps_per_second": 1.228,
+      "step": 36
+    },
+    {
+      "epoch": 0.0009172606135729779,
+      "grad_norm": 0.01495317555963993,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.0009420514409668423,
+      "grad_norm": 0.06873802840709686,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0011,
+      "step": 38
+    },
+    {
+      "epoch": 0.0009668422683607066,
+      "grad_norm": 0.04712967574596405,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0004,
+      "step": 39
+    },
+    {
+      "epoch": 0.0009916330957545707,
+      "grad_norm": 0.018527941778302193,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.001016423923148435,
+      "grad_norm": 0.004091004375368357,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.0010412147505422993,
+      "grad_norm": 0.0373254232108593,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.0010660055779361636,
+      "grad_norm": 0.0022029399406164885,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0010907964053300278,
+      "grad_norm": 0.10897021740674973,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.0011155872327238922,
+      "grad_norm": 0.0015826758462935686,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011155872327238922,
+      "eval_loss": 0.011905557475984097,
+      "eval_runtime": 3460.4198,
+      "eval_samples_per_second": 9.816,
+      "eval_steps_per_second": 1.227,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011403780601177565,
+      "grad_norm": 0.004921503830701113,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.0011651688875116207,
+      "grad_norm": 0.0008932303753681481,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.001189959714905485,
+      "grad_norm": 0.009026121348142624,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.0012147505422993492,
+      "grad_norm": 0.001327559701167047,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.0012395413696932136,
+      "grad_norm": 0.0029878842178732157,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0001,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6527352922112e+16,
+  "total_flos": 3.3054705844224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null