Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342f17a956464ba7f4e2721574d92ef1cbb3ad8eec6f68373f23694c83772635
+oid sha256:8831358bf45f54756e3ee2363320466f18c85192b2cbdcde06ad096fa9fdb24a
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477364cd718f8e9c059fd863db9c00bae5a40f6579131d935c7f677f26f381ea
+oid sha256:caa15eae934bb5d69aa6f53eea85e92658da6e9662418e780a1d863c052417b5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
+oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
 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": 0.09813542688910697,
+  "epoch": 0.14720314033366044,
   "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": 0.0453,
       "step": 50
+    },
+    {
+      "epoch": 0.10009813542688911,
+      "grad_norm": 0.6971419453620911,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0857,
+      "step": 51
+    },
+    {
+      "epoch": 0.10206084396467124,
+      "grad_norm": 1.4667972326278687,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1401,
+      "step": 52
+    },
+    {
+      "epoch": 0.10402355250245339,
+      "grad_norm": 0.5915104150772095,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0572,
+      "step": 53
+    },
+    {
+      "epoch": 0.10598626104023552,
+      "grad_norm": 0.9713770747184753,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0795,
+      "step": 54
+    },
+    {
+      "epoch": 0.10598626104023552,
+      "eval_loss": 0.07904753088951111,
+      "eval_runtime": 51.8493,
+      "eval_samples_per_second": 8.274,
+      "eval_steps_per_second": 1.041,
+      "step": 54
+    },
+    {
+      "epoch": 0.10794896957801767,
+      "grad_norm": 0.7951352596282959,
+      "learning_rate": 5e-05,
+      "loss": 0.0704,
+      "step": 55
+    },
+    {
+      "epoch": 0.1099116781157998,
+      "grad_norm": 2.8656163215637207,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1262,
+      "step": 56
+    },
+    {
+      "epoch": 0.11187438665358194,
+      "grad_norm": 0.786283016204834,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0959,
+      "step": 57
+    },
+    {
+      "epoch": 0.11383709519136408,
+      "grad_norm": 0.9875638484954834,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0507,
+      "step": 58
+    },
+    {
+      "epoch": 0.11579980372914622,
+      "grad_norm": 0.8965640068054199,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0643,
+      "step": 59
+    },
+    {
+      "epoch": 0.11776251226692837,
+      "grad_norm": 0.4218522608280182,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0271,
+      "step": 60
+    },
+    {
+      "epoch": 0.1197252208047105,
+      "grad_norm": 1.05173659324646,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0416,
+      "step": 61
+    },
+    {
+      "epoch": 0.12168792934249265,
+      "grad_norm": 0.9266757965087891,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0968,
+      "step": 62
+    },
+    {
+      "epoch": 0.12365063788027478,
+      "grad_norm": 2.450507164001465,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1366,
+      "step": 63
+    },
+    {
+      "epoch": 0.12365063788027478,
+      "eval_loss": 0.06722546368837357,
+      "eval_runtime": 51.8533,
+      "eval_samples_per_second": 8.273,
+      "eval_steps_per_second": 1.041,
+      "step": 63
+    },
+    {
+      "epoch": 0.1256133464180569,
+      "grad_norm": 0.7940893769264221,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0558,
+      "step": 64
+    },
+    {
+      "epoch": 0.12757605495583907,
+      "grad_norm": 1.0147578716278076,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0655,
+      "step": 65
+    },
+    {
+      "epoch": 0.1295387634936212,
+      "grad_norm": 0.7361927032470703,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0467,
+      "step": 66
+    },
+    {
+      "epoch": 0.13150147203140333,
+      "grad_norm": 0.8373685479164124,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0838,
+      "step": 67
+    },
+    {
+      "epoch": 0.13346418056918546,
+      "grad_norm": 0.41943085193634033,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0278,
+      "step": 68
+    },
+    {
+      "epoch": 0.13542688910696762,
+      "grad_norm": 0.35588350892066956,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.025,
+      "step": 69
+    },
+    {
+      "epoch": 0.13738959764474976,
+      "grad_norm": 0.7751619219779968,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0516,
+      "step": 70
+    },
+    {
+      "epoch": 0.1393523061825319,
+      "grad_norm": 0.735934853553772,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0708,
+      "step": 71
+    },
+    {
+      "epoch": 0.14131501472031405,
+      "grad_norm": 0.5799421668052673,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0559,
+      "step": 72
+    },
+    {
+      "epoch": 0.14131501472031405,
+      "eval_loss": 0.06862723082304001,
+      "eval_runtime": 51.8315,
+      "eval_samples_per_second": 8.277,
+      "eval_steps_per_second": 1.042,
+      "step": 72
+    },
+    {
+      "epoch": 0.14327772325809618,
+      "grad_norm": 1.0606155395507812,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0798,
+      "step": 73
+    },
+    {
+      "epoch": 0.1452404317958783,
+      "grad_norm": 0.8018274903297424,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0536,
+      "step": 74
+    },
+    {
+      "epoch": 0.14720314033366044,
+      "grad_norm": 0.9818136692047119,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.076,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.70943843106816e+16,
+  "total_flos": 5.56415764660224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null