Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4d79e2464895675fb45fb1600501af10923c12b0fdd97976568edf1255652f
+oid sha256:a633188d2efdac824842e56b34bdf7fe1864b175df74e779f9a0f87377f936b1
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b275b6e7c8a63b18b2820ef953fb0e2e91be1a090b0abf8666ea07b6b9b5a435
+oid sha256:403e65bc245232b8edc411e5e1b98f4d9649f0a669482dbe3e6d3710ccc390e1
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3106355f9a72cbb0d48c2bb836220850cc5e0d3788df605cde0757b610123abb
+oid sha256:88b8b7fdbb0038d803236f1633845ecce37524bd143e91f086bca54a6d6e08ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1949317738791423,
+  "epoch": 0.3898635477582846,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 148.088,
       "eval_steps_per_second": 74.723,
       "step": 25
+    },
+    {
+      "epoch": 0.20272904483430798,
+      "grad_norm": 0.803300678730011,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3143,
+      "step": 26
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.6602361798286438,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3813,
+      "step": 27
+    },
+    {
+      "epoch": 0.21832358674463936,
+      "grad_norm": 0.739231526851654,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3064,
+      "step": 28
+    },
+    {
+      "epoch": 0.22612085769980506,
+      "grad_norm": 0.7824051380157471,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.3064,
+      "step": 29
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 1.0254789590835571,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3585,
+      "step": 30
+    },
+    {
+      "epoch": 0.24171539961013644,
+      "grad_norm": 0.8810551762580872,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3302,
+      "step": 31
+    },
+    {
+      "epoch": 0.24951267056530213,
+      "grad_norm": 1.4386115074157715,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.4164,
+      "step": 32
+    },
+    {
+      "epoch": 0.2573099415204678,
+      "grad_norm": 0.4788445234298706,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3391,
+      "step": 33
+    },
+    {
+      "epoch": 0.2651072124756335,
+      "grad_norm": 0.47968441247940063,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.3176,
+      "step": 34
+    },
+    {
+      "epoch": 0.2729044834307992,
+      "grad_norm": 0.5276753902435303,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3632,
+      "step": 35
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.607767641544342,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.3526,
+      "step": 36
+    },
+    {
+      "epoch": 0.2884990253411306,
+      "grad_norm": 0.6070165634155273,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.2895,
+      "step": 37
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.8148685097694397,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3767,
+      "step": 38
+    },
+    {
+      "epoch": 0.30409356725146197,
+      "grad_norm": 0.6928004622459412,
+      "learning_rate": 5e-05,
+      "loss": 10.3613,
+      "step": 39
+    },
+    {
+      "epoch": 0.31189083820662766,
+      "grad_norm": 0.647136390209198,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3009,
+      "step": 40
+    },
+    {
+      "epoch": 0.31968810916179335,
+      "grad_norm": 0.6418548822402954,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.3371,
+      "step": 41
+    },
+    {
+      "epoch": 0.32748538011695905,
+      "grad_norm": 0.6654731631278992,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3056,
+      "step": 42
+    },
+    {
+      "epoch": 0.33528265107212474,
+      "grad_norm": 0.6930279731750488,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.315,
+      "step": 43
+    },
+    {
+      "epoch": 0.34307992202729043,
+      "grad_norm": 0.8335940837860107,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3535,
+      "step": 44
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.7898197770118713,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3541,
+      "step": 45
+    },
+    {
+      "epoch": 0.3586744639376218,
+      "grad_norm": 0.9156711101531982,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.3129,
+      "step": 46
+    },
+    {
+      "epoch": 0.3664717348927875,
+      "grad_norm": 0.7727612853050232,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.2579,
+      "step": 47
+    },
+    {
+      "epoch": 0.3742690058479532,
+      "grad_norm": 0.8964085578918457,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.35,
+      "step": 48
+    },
+    {
+      "epoch": 0.3820662768031189,
+      "grad_norm": 0.8759742975234985,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.2866,
+      "step": 49
+    },
+    {
+      "epoch": 0.3898635477582846,
+      "grad_norm": 0.8049792647361755,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.343,
+      "step": 50
+    },
+    {
+      "epoch": 0.3898635477582846,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7541,
+      "eval_samples_per_second": 144.545,
+      "eval_steps_per_second": 72.936,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2673003724800.0,
+  "total_flos": 5346007449600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null