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:dfcf2bbc8d5d6bf79bdde83bd83276789a97ff7e04daab87f9bc8a9aef974380
+oid sha256:4ebb1c811c278da61d8417db8a68ff2842ef87beb2f81bcceb2f3142567de8dc
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb128ea1ef237d9db57944c2818d6e329c8a32d1792ad43bf7635c9255e50d1e
+oid sha256:fba02a14c6f771bb617f25e19a99a07de9a6b3bc77bba3b2b5d39f299abd6e05
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33feb238edb291cd05db2a1f78c61ea97195145e02e941fc757930ac6bc0675
+oid sha256:94e22754a50989957f67d01fa4c0776a1096e12a9d53d6690d9918c79bd28901
 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": 0.07077140835102619,
+  "epoch": 0.10615711252653928,
   "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": 0.0913,
       "step": 50
+    },
+    {
+      "epoch": 0.07218683651804671,
+      "grad_norm": 1.8043497800827026,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.1411,
+      "step": 51
+    },
+    {
+      "epoch": 0.07360226468506724,
+      "grad_norm": 0.7669022679328918,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1089,
+      "step": 52
+    },
+    {
+      "epoch": 0.07501769285208776,
+      "grad_norm": 0.8200987577438354,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.1072,
+      "step": 53
+    },
+    {
+      "epoch": 0.07643312101910828,
+      "grad_norm": 1.5350964069366455,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.1279,
+      "step": 54
+    },
+    {
+      "epoch": 0.07643312101910828,
+      "eval_loss": 0.10821533203125,
+      "eval_runtime": 127.087,
+      "eval_samples_per_second": 4.682,
+      "eval_steps_per_second": 0.59,
+      "step": 54
+    },
+    {
+      "epoch": 0.07784854918612881,
+      "grad_norm": 0.5155397057533264,
+      "learning_rate": 5e-05,
+      "loss": 0.1156,
+      "step": 55
+    },
+    {
+      "epoch": 0.07926397735314933,
+      "grad_norm": 0.41658011078834534,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1141,
+      "step": 56
+    },
+    {
+      "epoch": 0.08067940552016985,
+      "grad_norm": 0.986137330532074,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.1358,
+      "step": 57
+    },
+    {
+      "epoch": 0.08209483368719038,
+      "grad_norm": 1.5772260427474976,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1149,
+      "step": 58
+    },
+    {
+      "epoch": 0.0835102618542109,
+      "grad_norm": 1.9692206382751465,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.146,
+      "step": 59
+    },
+    {
+      "epoch": 0.08492569002123142,
+      "grad_norm": 0.8698508739471436,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1009,
+      "step": 60
+    },
+    {
+      "epoch": 0.08634111818825195,
+      "grad_norm": 2.1218152046203613,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1416,
+      "step": 61
+    },
+    {
+      "epoch": 0.08775654635527247,
+      "grad_norm": 1.7425721883773804,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.1384,
+      "step": 62
+    },
+    {
+      "epoch": 0.08917197452229299,
+      "grad_norm": 2.9890897274017334,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1707,
+      "step": 63
+    },
+    {
+      "epoch": 0.08917197452229299,
+      "eval_loss": 0.1412888765335083,
+      "eval_runtime": 127.0555,
+      "eval_samples_per_second": 4.683,
+      "eval_steps_per_second": 0.59,
+      "step": 63
+    },
+    {
+      "epoch": 0.09058740268931352,
+      "grad_norm": 3.2205963134765625,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1843,
+      "step": 64
+    },
+    {
+      "epoch": 0.09200283085633404,
+      "grad_norm": 0.5274741053581238,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0972,
+      "step": 65
+    },
+    {
+      "epoch": 0.09341825902335456,
+      "grad_norm": 1.1009308099746704,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.1413,
+      "step": 66
+    },
+    {
+      "epoch": 0.09483368719037509,
+      "grad_norm": 1.007982611656189,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.1176,
+      "step": 67
+    },
+    {
+      "epoch": 0.09624911535739561,
+      "grad_norm": 1.1018102169036865,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1269,
+      "step": 68
+    },
+    {
+      "epoch": 0.09766454352441614,
+      "grad_norm": 0.3432563841342926,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0989,
+      "step": 69
+    },
+    {
+      "epoch": 0.09907997169143666,
+      "grad_norm": 2.0502262115478516,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1301,
+      "step": 70
+    },
+    {
+      "epoch": 0.10049539985845718,
+      "grad_norm": 0.684442937374115,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0976,
+      "step": 71
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 1.1942218542099,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.1241,
+      "step": 72
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "eval_loss": 0.10807202756404877,
+      "eval_runtime": 127.0721,
+      "eval_samples_per_second": 4.682,
+      "eval_steps_per_second": 0.59,
+      "step": 72
+    },
+    {
+      "epoch": 0.10332625619249823,
+      "grad_norm": 1.5802924633026123,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1139,
+      "step": 73
+    },
+    {
+      "epoch": 0.10474168435951875,
+      "grad_norm": 0.271753191947937,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.1051,
+      "step": 74
+    },
+    {
+      "epoch": 0.10615711252653928,
+      "grad_norm": 1.833114504814148,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1629,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.085023558002278e+16,
+  "total_flos": 1.0534799426558362e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null