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:a220f7119a8b80d5016ac1063fbc9179cd9cbf454ec7fca26523fc0986b0a910
+oid sha256:80195594ad249235c8b480b72538efc487daa7ab87d3f5d4481d0eff5e53cfcc
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7ef06f6f0e8aeee0aae9097ff6d97491ad6af5e1371c8e9b0186be778adaf6
+oid sha256:a3de26b3b1d2667d02ccd942180a572b88ec595ec41470ec213382da7a81a2ff
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d907e3f0eb7a063696393376fd52287cddfed552924991b8534c473353d657f
+oid sha256:26ed3f697f118b04714a0d0be23fcf6b409f264523cdd46888057f6b74c9d12e
 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": 0.1091703056768559,
+  "epoch": 0.16375545851528384,
   "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": 10.3754,
       "step": 50
+    },
+    {
+      "epoch": 0.11135371179039301,
+      "grad_norm": 0.043586429208517075,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3735,
+      "step": 51
+    },
+    {
+      "epoch": 0.11353711790393013,
+      "grad_norm": 0.05137532204389572,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3771,
+      "step": 52
+    },
+    {
+      "epoch": 0.11572052401746726,
+      "grad_norm": 0.05210437253117561,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3781,
+      "step": 53
+    },
+    {
+      "epoch": 0.11790393013100436,
+      "grad_norm": 0.04989282786846161,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3751,
+      "step": 54
+    },
+    {
+      "epoch": 0.11790393013100436,
+      "eval_loss": 10.374601364135742,
+      "eval_runtime": 3.9288,
+      "eval_samples_per_second": 98.248,
+      "eval_steps_per_second": 12.472,
+      "step": 54
+    },
+    {
+      "epoch": 0.12008733624454149,
+      "grad_norm": 0.04939981922507286,
+      "learning_rate": 5e-05,
+      "loss": 10.3746,
+      "step": 55
+    },
+    {
+      "epoch": 0.1222707423580786,
+      "grad_norm": 0.05482238158583641,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3771,
+      "step": 56
+    },
+    {
+      "epoch": 0.12445414847161572,
+      "grad_norm": 0.05761481076478958,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3783,
+      "step": 57
+    },
+    {
+      "epoch": 0.12663755458515283,
+      "grad_norm": 0.058475080877542496,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3722,
+      "step": 58
+    },
+    {
+      "epoch": 0.12882096069868995,
+      "grad_norm": 0.056109070777893066,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3754,
+      "step": 59
+    },
+    {
+      "epoch": 0.13100436681222707,
+      "grad_norm": 0.04790722578763962,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3771,
+      "step": 60
+    },
+    {
+      "epoch": 0.1331877729257642,
+      "grad_norm": 0.05564436689019203,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.373,
+      "step": 61
+    },
+    {
+      "epoch": 0.13537117903930132,
+      "grad_norm": 0.054479893296957016,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3733,
+      "step": 62
+    },
+    {
+      "epoch": 0.13755458515283842,
+      "grad_norm": 0.053394876420497894,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3721,
+      "step": 63
+    },
+    {
+      "epoch": 0.13755458515283842,
+      "eval_loss": 10.37381362915039,
+      "eval_runtime": 4.0391,
+      "eval_samples_per_second": 95.565,
+      "eval_steps_per_second": 12.131,
+      "step": 63
+    },
+    {
+      "epoch": 0.13973799126637554,
+      "grad_norm": 0.04594835266470909,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3752,
+      "step": 64
+    },
+    {
+      "epoch": 0.14192139737991266,
+      "grad_norm": 0.04905980825424194,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3755,
+      "step": 65
+    },
+    {
+      "epoch": 0.14410480349344978,
+      "grad_norm": 0.059114981442689896,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3746,
+      "step": 66
+    },
+    {
+      "epoch": 0.1462882096069869,
+      "grad_norm": 0.05878229811787605,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3718,
+      "step": 67
+    },
+    {
+      "epoch": 0.14847161572052403,
+      "grad_norm": 0.06435633450746536,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3748,
+      "step": 68
+    },
+    {
+      "epoch": 0.15065502183406113,
+      "grad_norm": 0.056570664048194885,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3726,
+      "step": 69
+    },
+    {
+      "epoch": 0.15283842794759825,
+      "grad_norm": 0.05326728895306587,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3778,
+      "step": 70
+    },
+    {
+      "epoch": 0.15502183406113537,
+      "grad_norm": 0.05503324419260025,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3758,
+      "step": 71
+    },
+    {
+      "epoch": 0.1572052401746725,
+      "grad_norm": 0.05148668959736824,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3719,
+      "step": 72
+    },
+    {
+      "epoch": 0.1572052401746725,
+      "eval_loss": 10.373261451721191,
+      "eval_runtime": 4.0392,
+      "eval_samples_per_second": 95.564,
+      "eval_steps_per_second": 12.131,
+      "step": 72
+    },
+    {
+      "epoch": 0.15938864628820962,
+      "grad_norm": 0.05448348820209503,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.375,
+      "step": 73
+    },
+    {
+      "epoch": 0.1615720524017467,
+      "grad_norm": 0.0521056167781353,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.375,
+      "step": 74
+    },
+    {
+      "epoch": 0.16375545851528384,
+      "grad_norm": 0.06789226830005646,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3729,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5230244659200.0,
+  "total_flos": 7845366988800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null