Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbc6b95810dcb50be90267d09a2de619e733a7542795622795b47e22e431601
+oid sha256:75d2f7e4f1c095ec0e4631cd524d2e283a06849f337e3dadd87db0a9f6043405
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27f3196797657ad6e46f8c6b6c2fd466d8217bd3d1ba43e2d33ca3a6ea25275
+oid sha256:5cda95b964ed8777b8a66181e3e64d8af3591aa05a65f4a9be75bbb7a5c1d3fc
 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": 0.05963029218843172,
+  "epoch": 0.08944543828264759,
   "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": 10.3662,
       "step": 50
+    },
+    {
+      "epoch": 0.06082289803220036,
+      "grad_norm": 0.04697554558515549,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3749,
+      "step": 51
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 0.04818224534392357,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3719,
+      "step": 52
+    },
+    {
+      "epoch": 0.06320810971973763,
+      "grad_norm": 0.05981869250535965,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3733,
+      "step": 53
+    },
+    {
+      "epoch": 0.06440071556350627,
+      "grad_norm": 0.03551531583070755,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3679,
+      "step": 54
+    },
+    {
+      "epoch": 0.06440071556350627,
+      "eval_loss": 10.370601654052734,
+      "eval_runtime": 1.407,
+      "eval_samples_per_second": 501.781,
+      "eval_steps_per_second": 63.256,
+      "step": 54
+    },
+    {
+      "epoch": 0.06559332140727489,
+      "grad_norm": 0.054153647273778915,
+      "learning_rate": 5e-05,
+      "loss": 10.3686,
+      "step": 55
+    },
+    {
+      "epoch": 0.06678592725104353,
+      "grad_norm": 0.056153807789087296,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3693,
+      "step": 56
+    },
+    {
+      "epoch": 0.06797853309481217,
+      "grad_norm": 0.059691403061151505,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3712,
+      "step": 57
+    },
+    {
+      "epoch": 0.0691711389385808,
+      "grad_norm": 0.05296963453292847,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3684,
+      "step": 58
+    },
+    {
+      "epoch": 0.07036374478234943,
+      "grad_norm": 0.05294171720743179,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3702,
+      "step": 59
+    },
+    {
+      "epoch": 0.07155635062611806,
+      "grad_norm": 0.058304980397224426,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3684,
+      "step": 60
+    },
+    {
+      "epoch": 0.0727489564698867,
+      "grad_norm": 0.05720147863030434,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3688,
+      "step": 61
+    },
+    {
+      "epoch": 0.07394156231365534,
+      "grad_norm": 0.05712497606873512,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3677,
+      "step": 62
+    },
+    {
+      "epoch": 0.07513416815742398,
+      "grad_norm": 0.05657053366303444,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.369,
+      "step": 63
+    },
+    {
+      "epoch": 0.07513416815742398,
+      "eval_loss": 10.3699312210083,
+      "eval_runtime": 1.3966,
+      "eval_samples_per_second": 505.497,
+      "eval_steps_per_second": 63.724,
+      "step": 63
+    },
+    {
+      "epoch": 0.0763267740011926,
+      "grad_norm": 0.06129881739616394,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3663,
+      "step": 64
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 0.05678679794073105,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3734,
+      "step": 65
+    },
+    {
+      "epoch": 0.07871198568872988,
+      "grad_norm": 0.054665569216012955,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3676,
+      "step": 66
+    },
+    {
+      "epoch": 0.07990459153249851,
+      "grad_norm": 0.053208716213703156,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3679,
+      "step": 67
+    },
+    {
+      "epoch": 0.08109719737626714,
+      "grad_norm": 0.06714367121458054,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3629,
+      "step": 68
+    },
+    {
+      "epoch": 0.08228980322003578,
+      "grad_norm": 0.05434398725628853,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3735,
+      "step": 69
+    },
+    {
+      "epoch": 0.08348240906380441,
+      "grad_norm": 0.06771057844161987,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3695,
+      "step": 70
+    },
+    {
+      "epoch": 0.08467501490757305,
+      "grad_norm": 0.053727179765701294,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.3692,
+      "step": 71
+    },
+    {
+      "epoch": 0.08586762075134168,
+      "grad_norm": 0.0703674703836441,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3643,
+      "step": 72
+    },
+    {
+      "epoch": 0.08586762075134168,
+      "eval_loss": 10.369429588317871,
+      "eval_runtime": 1.3413,
+      "eval_samples_per_second": 526.339,
+      "eval_steps_per_second": 66.352,
+      "step": 72
+    },
+    {
+      "epoch": 0.08706022659511031,
+      "grad_norm": 0.05981586128473282,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3704,
+      "step": 73
+    },
+    {
+      "epoch": 0.08825283243887895,
+      "grad_norm": 0.054827235639095306,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3701,
+      "step": 74
+    },
+    {
+      "epoch": 0.08944543828264759,
+      "grad_norm": 0.06241114065051079,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3686,
+      "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