Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5407db02f2d5db8097ead4f9c2a8b0b31cb387a7431b1c6f38e1d993980400c9
+oid sha256:2ba79555c3c3efdec97edd16076639700328263b318a1b74af3683d0725d022a
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd64b8e862b1830e591121d1f7e3ffcaa2e260cabff3db6007ff8e2f5b846fef
+oid sha256:b4e708dc4a1735af4b8afbf7be39cec4a4d655c4d0822adab89c56c114b0e68a
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c742876dbc7023e2848d7bb1b55279fe9f0c050c2c6db00f82a2c0bd875952
+oid sha256:c2baafb56fe3a2619cfc0fecd20a068c58a057e4c42cd93b97063a3d1ac12cb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
+oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012525050100200401,
+  "epoch": 0.025050100200400802,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 89.694,
       "eval_steps_per_second": 44.874,
       "step": 50
+    },
+    {
+      "epoch": 0.01377755511022044,
+      "grad_norm": 1.3579661846160889,
+      "learning_rate": 8.678619553365659e-05,
+      "loss": 2.561,
+      "step": 55
+    },
+    {
+      "epoch": 0.01503006012024048,
+      "grad_norm": 1.8097760677337646,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 2.5397,
+      "step": 60
+    },
+    {
+      "epoch": 0.01628256513026052,
+      "grad_norm": 1.3172852993011475,
+      "learning_rate": 8.07106356344834e-05,
+      "loss": 2.4455,
+      "step": 65
+    },
+    {
+      "epoch": 0.01753507014028056,
+      "grad_norm": 2.0352325439453125,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 2.4834,
+      "step": 70
+    },
+    {
+      "epoch": 0.018787575150300603,
+      "grad_norm": 1.3835731744766235,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 2.4561,
+      "step": 75
+    },
+    {
+      "epoch": 0.02004008016032064,
+      "grad_norm": 1.4761914014816284,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 2.3603,
+      "step": 80
+    },
+    {
+      "epoch": 0.021292585170340682,
+      "grad_norm": 1.3032515048980713,
+      "learning_rate": 6.623497346023418e-05,
+      "loss": 2.2767,
+      "step": 85
+    },
+    {
+      "epoch": 0.022545090180360723,
+      "grad_norm": 1.3516151905059814,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 2.3037,
+      "step": 90
+    },
+    {
+      "epoch": 0.02379759519038076,
+      "grad_norm": 1.2633843421936035,
+      "learning_rate": 5.8229729514036705e-05,
+      "loss": 2.3047,
+      "step": 95
+    },
+    {
+      "epoch": 0.025050100200400802,
+      "grad_norm": 2.345054864883423,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 2.3067,
+      "step": 100
+    },
+    {
+      "epoch": 0.025050100200400802,
+      "eval_loss": 2.3011841773986816,
+      "eval_runtime": 18.2416,
+      "eval_samples_per_second": 92.152,
+      "eval_steps_per_second": 46.103,
+      "step": 100
     }
   ],
   "logging_steps": 5,
@@ -112,7 +190,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 342926504755200.0,
+  "total_flos": 685853009510400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null