Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ab5d57fe29db7668151d63a1c0d3ca9373061f30a115360ba85f3f0c8ba930
+oid sha256:d365c6280c8e4e83271d6da15ba847e305ade635513bd707a1feb8fc143efa39
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5159108294a2cbc3b2f9820ff5d79b5960079f18420ec21d1c7a369d49a248
+oid sha256:7027ded9aa14d01271c4d002e790da95fccd98c71340d635b8a4775d0872c804
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4422b3d1f964db21d93a8ffbd30ae226dcced1cd77f55c1377a3731485311e
+oid sha256:fc7d0343bb4a4510d1b39011ff93bf12d532b23ca006000ab6087a87acc566ab
 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": 0.007093707881109456,
+  "epoch": 0.010640561821664184,
   "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": 0.8714,
       "step": 50
+    },
+    {
+      "epoch": 0.0072355820387316454,
+      "grad_norm": 6.460239410400391,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.8425,
+      "step": 51
+    },
+    {
+      "epoch": 0.007377456196353834,
+      "grad_norm": 7.313208103179932,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.9399,
+      "step": 52
+    },
+    {
+      "epoch": 0.007519330353976023,
+      "grad_norm": 5.7543206214904785,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.8304,
+      "step": 53
+    },
+    {
+      "epoch": 0.007661204511598212,
+      "grad_norm": 8.54841136932373,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1842,
+      "step": 54
+    },
+    {
+      "epoch": 0.007661204511598212,
+      "eval_loss": 0.4334222078323364,
+      "eval_runtime": 541.1045,
+      "eval_samples_per_second": 10.97,
+      "eval_steps_per_second": 1.371,
+      "step": 54
+    },
+    {
+      "epoch": 0.007803078669220402,
+      "grad_norm": 3.552095651626587,
+      "learning_rate": 5e-05,
+      "loss": 0.5944,
+      "step": 55
+    },
+    {
+      "epoch": 0.00794495282684259,
+      "grad_norm": 4.194748401641846,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7586,
+      "step": 56
+    },
+    {
+      "epoch": 0.008086826984464779,
+      "grad_norm": 6.412907600402832,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.9264,
+      "step": 57
+    },
+    {
+      "epoch": 0.008228701142086969,
+      "grad_norm": 5.4873785972595215,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.9442,
+      "step": 58
+    },
+    {
+      "epoch": 0.008370575299709158,
+      "grad_norm": 5.020580768585205,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.7963,
+      "step": 59
+    },
+    {
+      "epoch": 0.008512449457331346,
+      "grad_norm": 9.607460975646973,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6891,
+      "step": 60
+    },
+    {
+      "epoch": 0.008654323614953536,
+      "grad_norm": 11.415412902832031,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.1025,
+      "step": 61
+    },
+    {
+      "epoch": 0.008796197772575726,
+      "grad_norm": 4.338674068450928,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.5018,
+      "step": 62
+    },
+    {
+      "epoch": 0.008938071930197914,
+      "grad_norm": 8.46346664428711,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.7072,
+      "step": 63
+    },
+    {
+      "epoch": 0.008938071930197914,
+      "eval_loss": 0.4158031642436981,
+      "eval_runtime": 541.0438,
+      "eval_samples_per_second": 10.971,
+      "eval_steps_per_second": 1.371,
+      "step": 63
+    },
+    {
+      "epoch": 0.009079946087820104,
+      "grad_norm": 5.24552583694458,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5167,
+      "step": 64
+    },
+    {
+      "epoch": 0.009221820245442292,
+      "grad_norm": 4.212309837341309,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.5451,
+      "step": 65
+    },
+    {
+      "epoch": 0.009363694403064482,
+      "grad_norm": 4.912107944488525,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7611,
+      "step": 66
+    },
+    {
+      "epoch": 0.009505568560686671,
+      "grad_norm": 5.346253871917725,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.624,
+      "step": 67
+    },
+    {
+      "epoch": 0.00964744271830886,
+      "grad_norm": 4.815743446350098,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.5705,
+      "step": 68
+    },
+    {
+      "epoch": 0.00978931687593105,
+      "grad_norm": 3.5380396842956543,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.4037,
+      "step": 69
+    },
+    {
+      "epoch": 0.009931191033553239,
+      "grad_norm": 4.5514044761657715,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6228,
+      "step": 70
+    },
+    {
+      "epoch": 0.010073065191175427,
+      "grad_norm": 6.931221008300781,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.9966,
+      "step": 71
+    },
+    {
+      "epoch": 0.010214939348797617,
+      "grad_norm": 8.248758316040039,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0049,
+      "step": 72
+    },
+    {
+      "epoch": 0.010214939348797617,
+      "eval_loss": 0.38347503542900085,
+      "eval_runtime": 541.0584,
+      "eval_samples_per_second": 10.971,
+      "eval_steps_per_second": 1.371,
+      "step": 72
+    },
+    {
+      "epoch": 0.010356813506419805,
+      "grad_norm": 7.816049575805664,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8902,
+      "step": 73
+    },
+    {
+      "epoch": 0.010498687664041995,
+      "grad_norm": 14.4616060256958,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.985,
+      "step": 74
+    },
+    {
+      "epoch": 0.010640561821664184,
+      "grad_norm": 5.556700229644775,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.8064,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.26729100951552e+16,
+  "total_flos": 4.90093651427328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null