Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f38ca1fc25a84a7ec2bd3fc7d4f1e8a3bf3f63971683172392767ac5c6f8bd7
+oid sha256:6e5a164617ca722b42e5e8fde3cd78a5eeb9ffce771943ce6f896040ef2f01ee
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2a490fbcd5f215f83bc6f6052b8f5a6f211f6385ee02e191bbbfbc56b42974
+oid sha256:8d4aff18958ef755e9c9a3a6e411d0b54cab17885e9b052cf881802ab6dbafbf
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5942a44aa0d538b32aea816d262432563c814d3a5c461aa25994dc7e1892c2a4
+oid sha256:03c86b8cb9cf7d4aa12029d2c56f7ad5767a9d9029213bbbd55c9ff2f0cad5bf
 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": 0.015535187199005748,
+  "epoch": 0.023302780798508622,
   "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": 0.0687,
       "step": 50
+    },
+    {
+      "epoch": 0.015845890942985864,
+      "grad_norm": 0.3204256296157837,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.1,
+      "step": 51
+    },
+    {
+      "epoch": 0.016156594686965977,
+      "grad_norm": 0.31012028455734253,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0815,
+      "step": 52
+    },
+    {
+      "epoch": 0.016467298430946093,
+      "grad_norm": 0.3400692343711853,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0901,
+      "step": 53
+    },
+    {
+      "epoch": 0.01677800217492621,
+      "grad_norm": 0.3835544288158417,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0983,
+      "step": 54
+    },
+    {
+      "epoch": 0.01677800217492621,
+      "eval_loss": 0.1074644923210144,
+      "eval_runtime": 476.89,
+      "eval_samples_per_second": 5.685,
+      "eval_steps_per_second": 0.711,
+      "step": 54
+    },
+    {
+      "epoch": 0.01708870591890632,
+      "grad_norm": 0.29666757583618164,
+      "learning_rate": 5e-05,
+      "loss": 0.0944,
+      "step": 55
+    },
+    {
+      "epoch": 0.017399409662886438,
+      "grad_norm": 0.427259236574173,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0895,
+      "step": 56
+    },
+    {
+      "epoch": 0.017710113406866554,
+      "grad_norm": 0.5842662453651428,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.1279,
+      "step": 57
+    },
+    {
+      "epoch": 0.018020817150846666,
+      "grad_norm": 0.3031122386455536,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0649,
+      "step": 58
+    },
+    {
+      "epoch": 0.018331520894826783,
+      "grad_norm": 0.6648306250572205,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.1514,
+      "step": 59
+    },
+    {
+      "epoch": 0.0186422246388069,
+      "grad_norm": 0.515338122844696,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1075,
+      "step": 60
+    },
+    {
+      "epoch": 0.01895292838278701,
+      "grad_norm": 0.42272016406059265,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.2258,
+      "step": 61
+    },
+    {
+      "epoch": 0.019263632126767127,
+      "grad_norm": 0.3235437870025635,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0793,
+      "step": 62
+    },
+    {
+      "epoch": 0.019574335870747243,
+      "grad_norm": 0.7144022583961487,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.2682,
+      "step": 63
+    },
+    {
+      "epoch": 0.019574335870747243,
+      "eval_loss": 0.09928452968597412,
+      "eval_runtime": 476.7575,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 0.711,
+      "step": 63
+    },
+    {
+      "epoch": 0.019885039614727356,
+      "grad_norm": 0.3919568955898285,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0866,
+      "step": 64
+    },
+    {
+      "epoch": 0.020195743358707472,
+      "grad_norm": 0.2596946656703949,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1011,
+      "step": 65
+    },
+    {
+      "epoch": 0.020506447102687588,
+      "grad_norm": 0.619389533996582,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2114,
+      "step": 66
+    },
+    {
+      "epoch": 0.0208171508466677,
+      "grad_norm": 0.5929703116416931,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.1019,
+      "step": 67
+    },
+    {
+      "epoch": 0.021127854590647817,
+      "grad_norm": 0.2772235870361328,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0602,
+      "step": 68
+    },
+    {
+      "epoch": 0.021438558334627933,
+      "grad_norm": 0.6497057676315308,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.1489,
+      "step": 69
+    },
+    {
+      "epoch": 0.021749262078608046,
+      "grad_norm": 0.3832882344722748,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0773,
+      "step": 70
+    },
+    {
+      "epoch": 0.02205996582258816,
+      "grad_norm": 0.2511863112449646,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.112,
+      "step": 71
+    },
+    {
+      "epoch": 0.022370669566568278,
+      "grad_norm": 0.7245559096336365,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.153,
+      "step": 72
+    },
+    {
+      "epoch": 0.022370669566568278,
+      "eval_loss": 0.09493355453014374,
+      "eval_runtime": 476.8146,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 0.711,
+      "step": 72
+    },
+    {
+      "epoch": 0.022681373310548394,
+      "grad_norm": 0.31734803318977356,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.048,
+      "step": 73
+    },
+    {
+      "epoch": 0.022992077054528506,
+      "grad_norm": 0.42933279275894165,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.1131,
+      "step": 74
+    },
+    {
+      "epoch": 0.023302780798508622,
+      "grad_norm": 0.30525970458984375,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0717,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.255494025576448e+16,
+  "total_flos": 3.407936228425728e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null