Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0afa22ccef3c9a0ea3428b0ce49c7b49b701311e5530f6aed60817e79bf7b8
+oid sha256:7a06d3e4983c41dc765c1eeb6d6658168972c5471a58499281b23d7c94887016
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81aa75d70b877656bae98d60d9c24f3b5ef7089addac00c7ceb5e35601234b5b
+oid sha256:4de60ec340a338ae4512a57938b518f19425ddce90de24fb45b35add85e7ffcf
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d5c80c4317aec1cdd8b32ba40e7d9a283d92dfcce7300ea3ed6edd63c76074
+oid sha256:8a55af3df2d414ccfff007ed59f001ee92e87d61217a24dace06b2b7ddba80fa
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d75c8ad1707fd318e0f938501ec9134a4023e423bf08958c45c5e922653226
+oid sha256:4ab5189814d428569ba62b550ae72cffeac88caf85e39082cf01ca7e7f9f982e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56,
+  "epoch": 0.6,
   "eval_steps": 1000,
-  "global_step": 28000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2220,6 +2220,164 @@
       "eval_samples_per_second": 73.281,
       "eval_steps_per_second": 0.586,
       "step": 28000
+    },
+    {
+      "epoch": 0.562,
+      "grad_norm": 0.15159651637077332,
+      "learning_rate": 0.00087801395378568,
+      "loss": 3.3107,
+      "step": 28100
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 0.16269639134407043,
+      "learning_rate": 0.0008714521840775893,
+      "loss": 3.3182,
+      "step": 28200
+    },
+    {
+      "epoch": 0.566,
+      "grad_norm": 0.16659656167030334,
+      "learning_rate": 0.0008648960374674042,
+      "loss": 3.3197,
+      "step": 28300
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.1418466717004776,
+      "learning_rate": 0.0008583458007422165,
+      "loss": 3.3122,
+      "step": 28400
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.14337651431560516,
+      "learning_rate": 0.0008518017604306002,
+      "loss": 3.3163,
+      "step": 28500
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 0.16096735000610352,
+      "learning_rate": 0.0008452642027900783,
+      "loss": 3.3061,
+      "step": 28600
+    },
+    {
+      "epoch": 0.574,
+      "grad_norm": 0.18552157282829285,
+      "learning_rate": 0.0008387334137946008,
+      "loss": 3.318,
+      "step": 28700
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.16036978363990784,
+      "learning_rate": 0.0008322096791220355,
+      "loss": 3.3109,
+      "step": 28800
+    },
+    {
+      "epoch": 0.578,
+      "grad_norm": 0.16824260354042053,
+      "learning_rate": 0.0008256932841416705,
+      "loss": 3.3074,
+      "step": 28900
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.16867192089557648,
+      "learning_rate": 0.0008191845139017326,
+      "loss": 3.3225,
+      "step": 29000
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.38399021526418786,
+      "eval_loss": 3.3025898933410645,
+      "eval_runtime": 11.9945,
+      "eval_samples_per_second": 83.372,
+      "eval_steps_per_second": 0.667,
+      "step": 29000
+    },
+    {
+      "epoch": 0.582,
+      "grad_norm": 0.1469780057668686,
+      "learning_rate": 0.0008126836531169177,
+      "loss": 3.3142,
+      "step": 29100
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.15736377239227295,
+      "learning_rate": 0.0008061909861559362,
+      "loss": 3.2969,
+      "step": 29200
+    },
+    {
+      "epoch": 0.586,
+      "grad_norm": 0.1577884554862976,
+      "learning_rate": 0.0007997067970290741,
+      "loss": 3.3034,
+      "step": 29300
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 0.1637413501739502,
+      "learning_rate": 0.0007932313693757703,
+      "loss": 3.3052,
+      "step": 29400
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.19296114146709442,
+      "learning_rate": 0.0007867649864522074,
+      "loss": 3.3069,
+      "step": 29500
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.14899814128875732,
+      "learning_rate": 0.0007803079311189227,
+      "loss": 3.3026,
+      "step": 29600
+    },
+    {
+      "epoch": 0.594,
+      "grad_norm": 0.1329040378332138,
+      "learning_rate": 0.0007738604858284345,
+      "loss": 3.2944,
+      "step": 29700
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 0.15727417171001434,
+      "learning_rate": 0.0007674229326128867,
+      "loss": 3.3166,
+      "step": 29800
+    },
+    {
+      "epoch": 0.598,
+      "grad_norm": 0.15141139924526215,
+      "learning_rate": 0.0007609955530717117,
+      "loss": 3.2907,
+      "step": 29900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.13476119935512543,
+      "learning_rate": 0.0007545786283593116,
+      "loss": 3.2933,
+      "step": 30000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.38492172211350295,
+      "eval_loss": 3.2943880558013916,
+      "eval_runtime": 11.9455,
+      "eval_samples_per_second": 83.713,
+      "eval_steps_per_second": 0.67,
+      "step": 30000
     }
   ],
   "logging_steps": 100,