Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad784809b759ba2428e57ee2de806ed9a59b68df6a53a884daf579a6e167879
+oid sha256:a5d740eaf72908230686637bcc00387c1a410c7e2f20b3c286191aeaefd47463
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e115f5eb1e1e3bfb384f9aab7758ade810436228c390585e80ec325e382cb254
+oid sha256:643f0f9950e1447c826a4a22f4302c20dac84abe0054a97e88d78e5ad73d00b7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36dcad3ea90927af00d356d5048ebd52fa23fbe5b6c29ff960398199456800eb
+oid sha256:31621e6489c54fe77a453f92f7f94d60894cf468bd36c452018ffd1e3feae7eb
 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": 0.4149377593360996,
+  "epoch": 0.6224066390041494,
   "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": 0.1488,
       "step": 50
+    },
+    {
+      "epoch": 0.42323651452282157,
+      "grad_norm": 0.5023450255393982,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.6348,
+      "step": 51
+    },
+    {
+      "epoch": 0.4315352697095436,
+      "grad_norm": 0.23465168476104736,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1158,
+      "step": 52
+    },
+    {
+      "epoch": 0.43983402489626555,
+      "grad_norm": 0.34985145926475525,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.1243,
+      "step": 53
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "grad_norm": 0.1788734644651413,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.165,
+      "step": 54
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "eval_loss": 0.22840574383735657,
+      "eval_runtime": 20.8342,
+      "eval_samples_per_second": 4.896,
+      "eval_steps_per_second": 0.624,
+      "step": 54
+    },
+    {
+      "epoch": 0.45643153526970953,
+      "grad_norm": 0.24725890159606934,
+      "learning_rate": 5e-05,
+      "loss": 0.1135,
+      "step": 55
+    },
+    {
+      "epoch": 0.46473029045643155,
+      "grad_norm": 0.20031580328941345,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1122,
+      "step": 56
+    },
+    {
+      "epoch": 0.4730290456431535,
+      "grad_norm": 0.2718360126018524,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.1847,
+      "step": 57
+    },
+    {
+      "epoch": 0.48132780082987553,
+      "grad_norm": 0.30479809641838074,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1487,
+      "step": 58
+    },
+    {
+      "epoch": 0.4896265560165975,
+      "grad_norm": 0.31583982706069946,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.6241,
+      "step": 59
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "grad_norm": 0.2300901710987091,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1186,
+      "step": 60
+    },
+    {
+      "epoch": 0.5062240663900415,
+      "grad_norm": 0.24245917797088623,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1174,
+      "step": 61
+    },
+    {
+      "epoch": 0.5145228215767634,
+      "grad_norm": 0.30403587222099304,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.1879,
+      "step": 62
+    },
+    {
+      "epoch": 0.5228215767634855,
+      "grad_norm": 0.22756731510162354,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1182,
+      "step": 63
+    },
+    {
+      "epoch": 0.5228215767634855,
+      "eval_loss": 0.22431056201457977,
+      "eval_runtime": 20.8796,
+      "eval_samples_per_second": 4.885,
+      "eval_steps_per_second": 0.623,
+      "step": 63
+    },
+    {
+      "epoch": 0.5311203319502075,
+      "grad_norm": 0.2197120040655136,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1106,
+      "step": 64
+    },
+    {
+      "epoch": 0.5394190871369294,
+      "grad_norm": 0.2344292849302292,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0985,
+      "step": 65
+    },
+    {
+      "epoch": 0.5477178423236515,
+      "grad_norm": 0.22797583043575287,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.1015,
+      "step": 66
+    },
+    {
+      "epoch": 0.5560165975103735,
+      "grad_norm": 0.2751520872116089,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.2086,
+      "step": 67
+    },
+    {
+      "epoch": 0.5643153526970954,
+      "grad_norm": 0.2529605031013489,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1148,
+      "step": 68
+    },
+    {
+      "epoch": 0.5726141078838174,
+      "grad_norm": 0.2754276990890503,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.1237,
+      "step": 69
+    },
+    {
+      "epoch": 0.5809128630705395,
+      "grad_norm": 0.263017863035202,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3886,
+      "step": 70
+    },
+    {
+      "epoch": 0.5892116182572614,
+      "grad_norm": 0.23464225232601166,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.1013,
+      "step": 71
+    },
+    {
+      "epoch": 0.5975103734439834,
+      "grad_norm": 0.33201128244400024,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.1089,
+      "step": 72
+    },
+    {
+      "epoch": 0.5975103734439834,
+      "eval_loss": 0.22274896502494812,
+      "eval_runtime": 20.8128,
+      "eval_samples_per_second": 4.901,
+      "eval_steps_per_second": 0.625,
+      "step": 72
+    },
+    {
+      "epoch": 0.6058091286307054,
+      "grad_norm": 0.27148982882499695,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.3075,
+      "step": 73
+    },
+    {
+      "epoch": 0.6141078838174274,
+      "grad_norm": 0.21130910515785217,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.1422,
+      "step": 74
+    },
+    {
+      "epoch": 0.6224066390041494,
+      "grad_norm": 0.18204365670681,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1057,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.306041910263808e+16,
+  "total_flos": 9.42196850121769e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null