Training in progress, step 462, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206183a2c99fca5965a2c3ad9629779d179ddd58a11f46227151b1b3c3c15bb7
+oid sha256:fd9ad15d29deb18d7163bbcaaba1f33909384d83d67f8c9f379c9aa241eb789b
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870b066dde9df96bf56be9482f9ed2fef198f645980e68d46f8741963c7929a8
+oid sha256:9c27e39946f3eacdee6bd6c425f1858f6ace622df8d4e7314e81174ca9b2209b
 size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf598a3ab84e12b7b9b0f1cf713464c6133fe6762dd3be870c678737b1f8aaa
+oid sha256:6f36562187cf3b52a09213050f690637853db506cc488d604d4a5bde81a2629d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0880410858400587,
+  "epoch": 0.09684519442406456,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 48.659,
       "eval_steps_per_second": 6.086,
       "step": 420
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 0.4187450110912323,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 1.0578,
+      "step": 423
+    },
+    {
+      "epoch": 0.08929881563777382,
+      "grad_norm": 0.3692411780357361,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 1.0522,
+      "step": 426
+    },
+    {
+      "epoch": 0.08992768053663137,
+      "grad_norm": 0.4078660309314728,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 1.0434,
+      "step": 429
+    },
+    {
+      "epoch": 0.09055654543548894,
+      "grad_norm": 0.4134742319583893,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 1.074,
+      "step": 432
+    },
+    {
+      "epoch": 0.0911854103343465,
+      "grad_norm": 0.36238303780555725,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 1.0455,
+      "step": 435
+    },
+    {
+      "epoch": 0.09181427523320407,
+      "grad_norm": 0.4054090976715088,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 1.0706,
+      "step": 438
+    },
+    {
+      "epoch": 0.09244314013206163,
+      "grad_norm": 0.3747381567955017,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 1.0354,
+      "step": 441
+    },
+    {
+      "epoch": 0.0930720050309192,
+      "grad_norm": 0.3801961839199066,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 1.0818,
+      "step": 444
+    },
+    {
+      "epoch": 0.09370086992977675,
+      "grad_norm": 0.3710772395133972,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 1.0605,
+      "step": 447
+    },
+    {
+      "epoch": 0.09432973482863431,
+      "grad_norm": 0.3717288672924042,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 1.0153,
+      "step": 450
+    },
+    {
+      "epoch": 0.09495859972749188,
+      "grad_norm": 0.370351105928421,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 1.037,
+      "step": 453
+    },
+    {
+      "epoch": 0.09558746462634944,
+      "grad_norm": 0.38800954818725586,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 1.0668,
+      "step": 456
+    },
+    {
+      "epoch": 0.096216329525207,
+      "grad_norm": 0.39085131883621216,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 1.0601,
+      "step": 459
+    },
+    {
+      "epoch": 0.09684519442406456,
+      "grad_norm": 0.38424739241600037,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 1.0742,
+      "step": 462
+    },
+    {
+      "epoch": 0.09684519442406456,
+      "eval_loss": 1.0629161596298218,
+      "eval_runtime": 165.0993,
+      "eval_samples_per_second": 48.668,
+      "eval_steps_per_second": 6.087,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.959220980383744e+16,
+  "total_flos": 9.855143078422118e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null