Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf8863cd81a04f9b8f77a944dca1a63f90b3c5ca3eae59bb8183a29cbf035f4
+oid sha256:75557017071a7b3ff7b9580c147ef7b9df1e16089651df4962d9bcbcd41e748b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e8a7178693c447fbded998e3d47173bf595a3157bbecd0abad3e165120743e
+oid sha256:641794e88e031fe62733cc33906fe5ba1c803b7c4be87850d48688ef75570441
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d841eda044e2a0b4625c1a49f398ba41b30f358c4216b4153690415e794a13
+oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
 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": 0.04764173415912339,
+  "epoch": 0.07146260123868509,
   "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": 2.0037,
       "step": 50
+    },
+    {
+      "epoch": 0.04859456884230586,
+      "grad_norm": 0.9991522431373596,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.2485,
+      "step": 51
+    },
+    {
+      "epoch": 0.04954740352548833,
+      "grad_norm": 1.1253869533538818,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0507,
+      "step": 52
+    },
+    {
+      "epoch": 0.0505002382086708,
+      "grad_norm": 0.9809867739677429,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.038,
+      "step": 53
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "grad_norm": 1.0923676490783691,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.4383,
+      "step": 54
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "eval_loss": 2.2689011096954346,
+      "eval_runtime": 195.1248,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 0.569,
+      "step": 54
+    },
+    {
+      "epoch": 0.05240590757503573,
+      "grad_norm": 1.0306025743484497,
+      "learning_rate": 5e-05,
+      "loss": 2.1825,
+      "step": 55
+    },
+    {
+      "epoch": 0.0533587422582182,
+      "grad_norm": 1.4191091060638428,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.6339,
+      "step": 56
+    },
+    {
+      "epoch": 0.054311576941400666,
+      "grad_norm": 1.2226223945617676,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.204,
+      "step": 57
+    },
+    {
+      "epoch": 0.055264411624583135,
+      "grad_norm": 5.3369951248168945,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0067,
+      "step": 58
+    },
+    {
+      "epoch": 0.0562172463077656,
+      "grad_norm": 1.2273885011672974,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.2786,
+      "step": 59
+    },
+    {
+      "epoch": 0.05717008099094807,
+      "grad_norm": 1.1748491525650024,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.415,
+      "step": 60
+    },
+    {
+      "epoch": 0.05812291567413054,
+      "grad_norm": 1.1600786447525024,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.2855,
+      "step": 61
+    },
+    {
+      "epoch": 0.05907575035731301,
+      "grad_norm": 1.1740864515304565,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2457,
+      "step": 62
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "grad_norm": 0.8164812922477722,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.0255,
+      "step": 63
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "eval_loss": 2.2617905139923096,
+      "eval_runtime": 195.3121,
+      "eval_samples_per_second": 4.526,
+      "eval_steps_per_second": 0.568,
+      "step": 63
+    },
+    {
+      "epoch": 0.06098141972367794,
+      "grad_norm": 1.8397961854934692,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3015,
+      "step": 64
+    },
+    {
+      "epoch": 0.06193425440686041,
+      "grad_norm": 1.4221397638320923,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.1798,
+      "step": 65
+    },
+    {
+      "epoch": 0.06288708909004288,
+      "grad_norm": 5.245110034942627,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2569,
+      "step": 66
+    },
+    {
+      "epoch": 0.06383992377322535,
+      "grad_norm": 1.1781222820281982,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.11,
+      "step": 67
+    },
+    {
+      "epoch": 0.06479275845640782,
+      "grad_norm": 1.3529887199401855,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.2486,
+      "step": 68
+    },
+    {
+      "epoch": 0.06574559313959027,
+      "grad_norm": 1.1169679164886475,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.1643,
+      "step": 69
+    },
+    {
+      "epoch": 0.06669842782277274,
+      "grad_norm": 1.144498586654663,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2978,
+      "step": 70
+    },
+    {
+      "epoch": 0.06765126250595521,
+      "grad_norm": 1.211686611175537,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.1954,
+      "step": 71
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "grad_norm": 1.1945290565490723,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2826,
+      "step": 72
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "eval_loss": 2.2520430088043213,
+      "eval_runtime": 195.2934,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 0.568,
+      "step": 72
+    },
+    {
+      "epoch": 0.06955693187232015,
+      "grad_norm": 0.8045013546943665,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0106,
+      "step": 73
+    },
+    {
+      "epoch": 0.07050976655550262,
+      "grad_norm": 0.9519303441047668,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1426,
+      "step": 74
+    },
+    {
+      "epoch": 0.07146260123868509,
+      "grad_norm": 0.9403889775276184,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.1034,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.41887283560448e+16,
+  "total_flos": 1.112830925340672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null