Training in progress, step 4950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7603902b76dfb153996cd58830ff2244b1c85eb06a0dbd52e2c83aa4db919240
+oid sha256:9010627970909f58b28a32a9e1357ab8654f5b0425229dfbd38b99ab4cfdad18
 size 144748392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7049d10ee3c694bd2470145a49ede9bec92ae46b8a0cfd24b342730ad05e3c
+oid sha256:0ba0b229ad267c947c651ea9d2e1d896a6032cb0fd1c50c5267d958d12c3f73f
 size 289690562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e8894b47240b5e938409bdde12ef850338a078ac443b39608ef1f61c6d50e9
+oid sha256:1f055733d5cde189e3e76b84ea53a9d0b33684eaf5a7ed4900b4ec7409362096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741e5a74b4b8a7e18ee94356eb03e28c998d3e32cf81a6bc98c8f2bfb8fb01d7
+oid sha256:10a0f55d24fa7f397f288a11330d31c57855416af9f1e0cdf88c93033ba0b0e8
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8962866067886353,
   "best_model_checkpoint": "./output/checkpoint-4800",
-  "epoch": 0.30592734225621415,
+  "epoch": 0.3154875717017208,
   "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": 11.228,
       "eval_steps_per_second": 11.228,
       "step": 4800
+    },
+    {
+      "epoch": 0.3065646908859146,
+      "grad_norm": 0.6696013808250427,
+      "learning_rate": 4.631564202709354e-07,
+      "loss": 0.8851,
+      "step": 4810
+    },
+    {
+      "epoch": 0.30720203951561503,
+      "grad_norm": 0.6419965028762817,
+      "learning_rate": 4.1573879615262185e-07,
+      "loss": 0.8941,
+      "step": 4820
+    },
+    {
+      "epoch": 0.3078393881453155,
+      "grad_norm": 0.6661477088928223,
+      "learning_rate": 3.708732128449785e-07,
+      "loss": 0.8848,
+      "step": 4830
+    },
+    {
+      "epoch": 0.3084767367750159,
+      "grad_norm": 0.6392946839332581,
+      "learning_rate": 3.2856151459641216e-07,
+      "loss": 0.8847,
+      "step": 4840
+    },
+    {
+      "epoch": 0.30911408540471635,
+      "grad_norm": 0.6320896744728088,
+      "learning_rate": 2.888054406751106e-07,
+      "loss": 0.8589,
+      "step": 4850
+    },
+    {
+      "epoch": 0.30975143403441685,
+      "grad_norm": 0.6730213761329651,
+      "learning_rate": 2.5160662529755823e-07,
+      "loss": 0.901,
+      "step": 4860
+    },
+    {
+      "epoch": 0.3103887826641173,
+      "grad_norm": 0.6767361164093018,
+      "learning_rate": 2.169665975613605e-07,
+      "loss": 0.9146,
+      "step": 4870
+    },
+    {
+      "epoch": 0.31102613129381773,
+      "grad_norm": 0.6694763898849487,
+      "learning_rate": 1.8488678138238456e-07,
+      "loss": 0.8884,
+      "step": 4880
+    },
+    {
+      "epoch": 0.31166347992351817,
+      "grad_norm": 0.6107333302497864,
+      "learning_rate": 1.5536849543621584e-07,
+      "loss": 0.9127,
+      "step": 4890
+    },
+    {
+      "epoch": 0.3123008285532186,
+      "grad_norm": 0.6185479164123535,
+      "learning_rate": 1.2841295310397905e-07,
+      "loss": 0.9108,
+      "step": 4900
+    },
+    {
+      "epoch": 0.31293817718291905,
+      "grad_norm": 0.6723112463951111,
+      "learning_rate": 1.0402126242244764e-07,
+      "loss": 0.8672,
+      "step": 4910
+    },
+    {
+      "epoch": 0.3135755258126195,
+      "grad_norm": 0.6152687668800354,
+      "learning_rate": 8.219442603847605e-08,
+      "loss": 0.8967,
+      "step": 4920
+    },
+    {
+      "epoch": 0.31421287444231993,
+      "grad_norm": 0.6387733817100525,
+      "learning_rate": 6.293334116783817e-08,
+      "loss": 0.9095,
+      "step": 4930
+    },
+    {
+      "epoch": 0.3148502230720204,
+      "grad_norm": 0.6692641377449036,
+      "learning_rate": 4.623879955827082e-08,
+      "loss": 0.8861,
+      "step": 4940
+    },
+    {
+      "epoch": 0.3154875717017208,
+      "grad_norm": 0.6291835904121399,
+      "learning_rate": 3.211148745700665e-08,
+      "loss": 0.8824,
+      "step": 4950
+    },
+    {
+      "epoch": 0.3154875717017208,
+      "eval_loss": 0.8967909216880798,
+      "eval_runtime": 43.4282,
+      "eval_samples_per_second": 11.513,
+      "eval_steps_per_second": 11.513,
+      "step": 4950
     }
   ],
   "logging_steps": 10,
@@ -3642,7 +3755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3399278300168192e+17,
+  "total_flos": 1.3818563054272512e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null