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:cc227258e87a1f6ba5f6a6a0ff81ad6aad1648785525827726419eb1cdbba8ea
+oid sha256:da33b8cd502c5040bf8ee3ecf8ef3aeca2b8fdf42cd6455a3a297fbbe4abb784
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71705c29034cbdc4460a30dd75e38c49bbc40e5cb46ae425d5d7fc9fb2940aec
+oid sha256:4bd3dba1d55d25e70411df3032e8551e28f410a083ae5c1babf3108a666de946
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79bf8ebcb249beccd05145daa4ffcfc686ad5a5865005baa6ff3cdad29c138c
+oid sha256:f6fbed7f002e0a36d46cfcf55f056cd93ce50fb21ed9f550b59e1a3e4a227136
 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": 0.007829627309740057,
+  "epoch": 0.011744440964610085,
   "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": 1.2211,
       "step": 50
+    },
+    {
+      "epoch": 0.007986219855934857,
+      "grad_norm": 0.6526830196380615,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.5053,
+      "step": 51
+    },
+    {
+      "epoch": 0.008142812402129659,
+      "grad_norm": 0.5835939049720764,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.1738,
+      "step": 52
+    },
+    {
+      "epoch": 0.00829940494832446,
+      "grad_norm": 0.5789561867713928,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.4458,
+      "step": 53
+    },
+    {
+      "epoch": 0.00845599749451926,
+      "grad_norm": 0.6865813136100769,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.0369,
+      "step": 54
+    },
+    {
+      "epoch": 0.00845599749451926,
+      "eval_loss": 1.1971049308776855,
+      "eval_runtime": 341.6362,
+      "eval_samples_per_second": 15.742,
+      "eval_steps_per_second": 1.97,
+      "step": 54
+    },
+    {
+      "epoch": 0.008612590040714062,
+      "grad_norm": 0.5503248572349548,
+      "learning_rate": 5e-05,
+      "loss": 1.2641,
+      "step": 55
+    },
+    {
+      "epoch": 0.008769182586908864,
+      "grad_norm": 0.5388333201408386,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5671,
+      "step": 56
+    },
+    {
+      "epoch": 0.008925775133103664,
+      "grad_norm": 0.5866682529449463,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0836,
+      "step": 57
+    },
+    {
+      "epoch": 0.009082367679298466,
+      "grad_norm": 0.49063777923583984,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4806,
+      "step": 58
+    },
+    {
+      "epoch": 0.009238960225493267,
+      "grad_norm": 0.5331360101699829,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 1.3006,
+      "step": 59
+    },
+    {
+      "epoch": 0.009395552771688067,
+      "grad_norm": 0.5101089477539062,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1633,
+      "step": 60
+    },
+    {
+      "epoch": 0.009552145317882869,
+      "grad_norm": 0.5948686599731445,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.9675,
+      "step": 61
+    },
+    {
+      "epoch": 0.009708737864077669,
+      "grad_norm": 0.49615660309791565,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.5511,
+      "step": 62
+    },
+    {
+      "epoch": 0.00986533041027247,
+      "grad_norm": 0.5018711090087891,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.241,
+      "step": 63
+    },
+    {
+      "epoch": 0.00986533041027247,
+      "eval_loss": 1.130515694618225,
+      "eval_runtime": 341.6235,
+      "eval_samples_per_second": 15.742,
+      "eval_steps_per_second": 1.97,
+      "step": 63
+    },
+    {
+      "epoch": 0.010021922956467273,
+      "grad_norm": 0.6017839908599854,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.2535,
+      "step": 64
+    },
+    {
+      "epoch": 0.010178515502662073,
+      "grad_norm": 0.5347826480865479,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.1951,
+      "step": 65
+    },
+    {
+      "epoch": 0.010335108048856874,
+      "grad_norm": 0.5654888153076172,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7469,
+      "step": 66
+    },
+    {
+      "epoch": 0.010491700595051676,
+      "grad_norm": 0.5342015624046326,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 1.1084,
+      "step": 67
+    },
+    {
+      "epoch": 0.010648293141246476,
+      "grad_norm": 0.5312244296073914,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.301,
+      "step": 68
+    },
+    {
+      "epoch": 0.010804885687441278,
+      "grad_norm": 0.5925493240356445,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.0394,
+      "step": 69
+    },
+    {
+      "epoch": 0.01096147823363608,
+      "grad_norm": 0.6024527549743652,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3372,
+      "step": 70
+    },
+    {
+      "epoch": 0.01111807077983088,
+      "grad_norm": 0.5528858304023743,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.0018,
+      "step": 71
+    },
+    {
+      "epoch": 0.011274663326025681,
+      "grad_norm": 0.5777594447135925,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0069,
+      "step": 72
+    },
+    {
+      "epoch": 0.011274663326025681,
+      "eval_loss": 1.09247887134552,
+      "eval_runtime": 341.6437,
+      "eval_samples_per_second": 15.742,
+      "eval_steps_per_second": 1.97,
+      "step": 72
+    },
+    {
+      "epoch": 0.011431255872220483,
+      "grad_norm": 0.5311472415924072,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.3165,
+      "step": 73
+    },
+    {
+      "epoch": 0.011587848418415283,
+      "grad_norm": 0.5156391263008118,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.93,
+      "step": 74
+    },
+    {
+      "epoch": 0.011744440964610085,
+      "grad_norm": 0.5066985487937927,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.6743,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.02936877203456e+16,
+  "total_flos": 1.54405315805184e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null