Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb57f7dc6f730938a1b21f1ba76d9063da018d55bc2f2d220f8d40c729951e2
+oid sha256:9256dc4e2945ea2c6a8568bc8e53cba5fb593c09eca385ce2a3c0fe09fd61081
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929edd88751a93008e26c4b33cf38b705c3d720e1113ec55637b2c32f9cb5d80
+oid sha256:c493a59cfe4ddfea6f217b524810c6345f037ba038c02ca881252662c4fbe1af
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
+oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
 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": 0.0067613252197430695,
+  "epoch": 0.010141987829614604,
   "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": 10.366,
       "step": 50
+    },
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 0.2752968370914459,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3447,
+      "step": 51
+    },
+    {
+      "epoch": 0.007031778228532792,
+      "grad_norm": 0.14523477852344513,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3655,
+      "step": 52
+    },
+    {
+      "epoch": 0.007167004732927654,
+      "grad_norm": 0.1733541488647461,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3647,
+      "step": 53
+    },
+    {
+      "epoch": 0.007302231237322515,
+      "grad_norm": 0.1748340129852295,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3705,
+      "step": 54
+    },
+    {
+      "epoch": 0.007302231237322515,
+      "eval_loss": 10.36203384399414,
+      "eval_runtime": 40.7225,
+      "eval_samples_per_second": 152.938,
+      "eval_steps_per_second": 19.129,
+      "step": 54
+    },
+    {
+      "epoch": 0.0074374577417173765,
+      "grad_norm": 0.12748098373413086,
+      "learning_rate": 5e-05,
+      "loss": 10.3647,
+      "step": 55
+    },
+    {
+      "epoch": 0.007572684246112238,
+      "grad_norm": 0.23120729625225067,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3612,
+      "step": 56
+    },
+    {
+      "epoch": 0.007707910750507099,
+      "grad_norm": 0.08134011179208755,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3731,
+      "step": 57
+    },
+    {
+      "epoch": 0.00784313725490196,
+      "grad_norm": 0.2719850540161133,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3667,
+      "step": 58
+    },
+    {
+      "epoch": 0.007978363759296822,
+      "grad_norm": 0.1496485471725464,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3562,
+      "step": 59
+    },
+    {
+      "epoch": 0.008113590263691683,
+      "grad_norm": 0.16650433838367462,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3546,
+      "step": 60
+    },
+    {
+      "epoch": 0.008248816768086545,
+      "grad_norm": 0.15551519393920898,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3711,
+      "step": 61
+    },
+    {
+      "epoch": 0.008384043272481406,
+      "grad_norm": 0.1664876788854599,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3558,
+      "step": 62
+    },
+    {
+      "epoch": 0.008519269776876268,
+      "grad_norm": 0.22050045430660248,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3618,
+      "step": 63
+    },
+    {
+      "epoch": 0.008519269776876268,
+      "eval_loss": 10.359942436218262,
+      "eval_runtime": 40.9328,
+      "eval_samples_per_second": 152.152,
+      "eval_steps_per_second": 19.031,
+      "step": 63
+    },
+    {
+      "epoch": 0.008654496281271129,
+      "grad_norm": 0.19365984201431274,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3598,
+      "step": 64
+    },
+    {
+      "epoch": 0.00878972278566599,
+      "grad_norm": 0.13088227808475494,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3575,
+      "step": 65
+    },
+    {
+      "epoch": 0.008924949290060852,
+      "grad_norm": 0.3167434334754944,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3557,
+      "step": 66
+    },
+    {
+      "epoch": 0.009060175794455713,
+      "grad_norm": 0.12147484719753265,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3661,
+      "step": 67
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": 0.36501771211624146,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3538,
+      "step": 68
+    },
+    {
+      "epoch": 0.009330628803245436,
+      "grad_norm": 0.24930152297019958,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3536,
+      "step": 69
+    },
+    {
+      "epoch": 0.009465855307640297,
+      "grad_norm": 0.1812044084072113,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3599,
+      "step": 70
+    },
+    {
+      "epoch": 0.009601081812035159,
+      "grad_norm": 0.2339591383934021,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3605,
+      "step": 71
+    },
+    {
+      "epoch": 0.00973630831643002,
+      "grad_norm": 0.23646140098571777,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3559,
+      "step": 72
+    },
+    {
+      "epoch": 0.00973630831643002,
+      "eval_loss": 10.358288764953613,
+      "eval_runtime": 40.9322,
+      "eval_samples_per_second": 152.154,
+      "eval_steps_per_second": 19.031,
+      "step": 72
+    },
+    {
+      "epoch": 0.009871534820824882,
+      "grad_norm": 0.15088936686515808,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3794,
+      "step": 73
+    },
+    {
+      "epoch": 0.010006761325219743,
+      "grad_norm": 0.15647698938846588,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3718,
+      "step": 74
+    },
+    {
+      "epoch": 0.010141987829614604,
+      "grad_norm": 0.3020474910736084,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3613,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2615122329600.0,
+  "total_flos": 3922683494400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null