Training in progress, step 4950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a48677be121fbdceeeabfe986e73dec1b480151800c1936b91cc4ace7b80e51
-size 1266749168
+oid sha256:f5ef156f9d60232c47caba6b4769b54973aaa74da4450d27d25fa35eff601d5c
+size 4418777208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e4a6a867bbc060d0c9facba78b7da76aadb4c3e6f9cafb001ecea1e69880d2
+oid sha256:40d31e86fb3b6de80883470d4ce17a9b1a506b44fb2ceb7dc1ff790daa5f0db0
 size 2499769978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e347613182c5807d2f6db7accfb1c61cd49dff9dda43fd034155068ae72f90f
+oid sha256:2d167f207748dc95c9dcda746fc5ce0dae8e8f9d3544099aa270f86a99297608
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8493cf662a0ef9cc409c1e71c561b4f018c668b3acc0b65f5c029d848604c14
+oid sha256:848d7aad2c2d474b8df3e1c4a379fb71bd6c1fcc4154ae3a9b8234e5418c2c78
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8088018894195557,
-  "best_model_checkpoint": "./output/checkpoint-4800",
-  "epoch": 0.15402881622436865,
+  "best_metric": 2.808562994003296,
+  "best_model_checkpoint": "./output/checkpoint-4950",
+  "epoch": 0.15884221673138016,
   "eval_steps": 150,
-  "global_step": 4800,
+  "global_step": 4950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3623,6 +3623,119 @@
       "eval_samples_per_second": 11.221,
       "eval_steps_per_second": 11.221,
       "step": 4800
+    },
+    {
+      "epoch": 0.15434970959150274,
+      "grad_norm": 12.37609577178955,
+      "learning_rate": 3.7052513621674843e-07,
+      "loss": 2.895,
+      "step": 4810
+    },
+    {
+      "epoch": 0.15467060295863685,
+      "grad_norm": 17.5330753326416,
+      "learning_rate": 3.325910369220976e-07,
+      "loss": 2.7705,
+      "step": 4820
+    },
+    {
+      "epoch": 0.15499149632577094,
+      "grad_norm": 13.448247909545898,
+      "learning_rate": 2.9669857027598287e-07,
+      "loss": 2.7588,
+      "step": 4830
+    },
+    {
+      "epoch": 0.15531238969290503,
+      "grad_norm": 12.854496955871582,
+      "learning_rate": 2.628492116771298e-07,
+      "loss": 2.8088,
+      "step": 4840
+    },
+    {
+      "epoch": 0.15563328306003915,
+      "grad_norm": 18.642213821411133,
+      "learning_rate": 2.3104435254008856e-07,
+      "loss": 2.8231,
+      "step": 4850
+    },
+    {
+      "epoch": 0.15595417642717324,
+      "grad_norm": 16.102710723876953,
+      "learning_rate": 2.0128530023804664e-07,
+      "loss": 2.8234,
+      "step": 4860
+    },
+    {
+      "epoch": 0.15627506979430736,
+      "grad_norm": 13.156707763671875,
+      "learning_rate": 1.7357327804908846e-07,
+      "loss": 2.6889,
+      "step": 4870
+    },
+    {
+      "epoch": 0.15659596316144145,
+      "grad_norm": 21.432458877563477,
+      "learning_rate": 1.479094251059077e-07,
+      "loss": 2.6573,
+      "step": 4880
+    },
+    {
+      "epoch": 0.15691685652857557,
+      "grad_norm": 17.190486907958984,
+      "learning_rate": 1.2429479634897272e-07,
+      "loss": 2.6614,
+      "step": 4890
+    },
+    {
+      "epoch": 0.15723774989570966,
+      "grad_norm": 15.629843711853027,
+      "learning_rate": 1.0273036248318327e-07,
+      "loss": 2.5595,
+      "step": 4900
+    },
+    {
+      "epoch": 0.15755864326284374,
+      "grad_norm": 14.262920379638672,
+      "learning_rate": 8.321700993795814e-08,
+      "loss": 2.6362,
+      "step": 4910
+    },
+    {
+      "epoch": 0.15787953662997786,
+      "grad_norm": 45.12715148925781,
+      "learning_rate": 6.575554083078086e-08,
+      "loss": 2.8154,
+      "step": 4920
+    },
+    {
+      "epoch": 0.15820042999711195,
+      "grad_norm": 17.036636352539062,
+      "learning_rate": 5.034667293427055e-08,
+      "loss": 2.7985,
+      "step": 4930
+    },
+    {
+      "epoch": 0.15852132336424607,
+      "grad_norm": 17.798555374145508,
+      "learning_rate": 3.6991039646616666e-08,
+      "loss": 2.7622,
+      "step": 4940
+    },
+    {
+      "epoch": 0.15884221673138016,
+      "grad_norm": 15.753199577331543,
+      "learning_rate": 2.5689189965605327e-08,
+      "loss": 2.7289,
+      "step": 4950
+    },
+    {
+      "epoch": 0.15884221673138016,
+      "eval_loss": 2.808562994003296,
+      "eval_runtime": 45.1194,
+      "eval_samples_per_second": 11.082,
+      "eval_steps_per_second": 11.082,
+      "step": 4950
     }
   ],
   "logging_steps": 10,
@@ -3642,7 +3755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.062562841064975e+17,
+  "total_flos": 7.268168492012636e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null