Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed2c82186f0eb6457408b87f4b2e272f5a4397d94be3934dd60f96cfa04bd17
+oid sha256:cecd0404d3ccbc9c91770deaff7eb29aa0825de48fbcf2e4fcc6e30508522788
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efce45376183a728eb6c42126e71a694aaf95a67d6b7bcacb863d99cc4049245
+oid sha256:de2aeb0d028d81b0e5442795604c2213dcfe5bf667d91f861aa2933a5ac647c7
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7afc0abd82d7254faf4024835247231e6f83d118e050d2a5e1a94ae5d01c04
+oid sha256:c296ac81d2bf3d1344e432b93d2183f1d83398c4d0023c461042136570fadac1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025581990278843694,
+  "epoch": 0.03837298541826554,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 1.2307,
       "step": 50
+    },
+    {
+      "epoch": 0.026093630084420567,
+      "grad_norm": 1.6459299325942993,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.1249,
+      "step": 51
+    },
+    {
+      "epoch": 0.02660526988999744,
+      "grad_norm": 1.93509042263031,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.4258,
+      "step": 52
+    },
+    {
+      "epoch": 0.027116909695574315,
+      "grad_norm": 3.230286121368408,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.4488,
+      "step": 53
+    },
+    {
+      "epoch": 0.02762854950115119,
+      "grad_norm": 1.5479521751403809,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.0165,
+      "step": 54
+    },
+    {
+      "epoch": 0.02762854950115119,
+      "eval_loss": 0.7164188623428345,
+      "eval_runtime": 274.108,
+      "eval_samples_per_second": 6.005,
+      "eval_steps_per_second": 0.752,
+      "step": 54
+    },
+    {
+      "epoch": 0.028140189306728063,
+      "grad_norm": 2.426544666290283,
+      "learning_rate": 5e-05,
+      "loss": 1.5535,
+      "step": 55
+    },
+    {
+      "epoch": 0.028651829112304936,
+      "grad_norm": 1.6888998746871948,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2925,
+      "step": 56
+    },
+    {
+      "epoch": 0.02916346891788181,
+      "grad_norm": 1.6494107246398926,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0268,
+      "step": 57
+    },
+    {
+      "epoch": 0.029675108723458684,
+      "grad_norm": 2.0526039600372314,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3885,
+      "step": 58
+    },
+    {
+      "epoch": 0.030186748529035558,
+      "grad_norm": 2.0388901233673096,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.418,
+      "step": 59
+    },
+    {
+      "epoch": 0.03069838833461243,
+      "grad_norm": 2.1916987895965576,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.2828,
+      "step": 60
+    },
+    {
+      "epoch": 0.031210028140189305,
+      "grad_norm": 2.3835113048553467,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.5845,
+      "step": 61
+    },
+    {
+      "epoch": 0.03172166794576618,
+      "grad_norm": 2.7145097255706787,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.8305,
+      "step": 62
+    },
+    {
+      "epoch": 0.03223330775134305,
+      "grad_norm": 1.8284953832626343,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.3383,
+      "step": 63
+    },
+    {
+      "epoch": 0.03223330775134305,
+      "eval_loss": 0.708600640296936,
+      "eval_runtime": 274.0602,
+      "eval_samples_per_second": 6.006,
+      "eval_steps_per_second": 0.752,
+      "step": 63
+    },
+    {
+      "epoch": 0.03274494755691993,
+      "grad_norm": 2.4546236991882324,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.4384,
+      "step": 64
+    },
+    {
+      "epoch": 0.0332565873624968,
+      "grad_norm": 1.848671317100525,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.3614,
+      "step": 65
+    },
+    {
+      "epoch": 0.03376822716807368,
+      "grad_norm": 1.7728267908096313,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.3155,
+      "step": 66
+    },
+    {
+      "epoch": 0.03427986697365055,
+      "grad_norm": 2.5115482807159424,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.5332,
+      "step": 67
+    },
+    {
+      "epoch": 0.034791506779227425,
+      "grad_norm": 2.179997682571411,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.1482,
+      "step": 68
+    },
+    {
+      "epoch": 0.035303146584804296,
+      "grad_norm": 2.3714139461517334,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.2697,
+      "step": 69
+    },
+    {
+      "epoch": 0.03581478639038117,
+      "grad_norm": 2.672269344329834,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6706,
+      "step": 70
+    },
+    {
+      "epoch": 0.03632642619595804,
+      "grad_norm": 1.9255658388137817,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.1635,
+      "step": 71
+    },
+    {
+      "epoch": 0.03683806600153492,
+      "grad_norm": 1.1116821765899658,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.8958,
+      "step": 72
+    },
+    {
+      "epoch": 0.03683806600153492,
+      "eval_loss": 0.7018402814865112,
+      "eval_runtime": 274.1606,
+      "eval_samples_per_second": 6.004,
+      "eval_steps_per_second": 0.751,
+      "step": 72
+    },
+    {
+      "epoch": 0.03734970580711179,
+      "grad_norm": 1.3924734592437744,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.0895,
+      "step": 73
+    },
+    {
+      "epoch": 0.03786134561268867,
+      "grad_norm": 3.168287992477417,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6212,
+      "step": 74
+    },
+    {
+      "epoch": 0.03837298541826554,
+      "grad_norm": 2.118021249771118,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.2363,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.60170128490496e+16,
+  "total_flos": 9.8390740303872e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null