Training in progress, step 4950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ce6cd87a58d319ec63299b75748b61bfdb4e346f3b747f801112620b793641
+oid sha256:78a9bfdece9010ecb7f4375813e863284c98d8be9db101229212b31d7f381ff1
 size 40385208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b309358843a3c7375f6aff973ed751e0aa5dc9f487550bfdb5b7515afbc7c65
+oid sha256:e0c08c7fddeef1a5f0b2cfbd256784c6e4044ed35c8c63fddcd15ba5f7bd6029
 size 80835258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873023bfc22837f4b865eeb0b902a00abd8961cd65d438841de64d0c61be6dfa
+oid sha256:667e2f2ca7503f810d6bcf4d9ce14efd3ee1dfb37e4f3d9c9167717670c4e069
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa57dde97277e3ea991e32bd89d96081667572958c56d89a2fb6b0a6f8e1923
+oid sha256:3fe7f1bf39a2a21ec6453d647a430741165accfbd545b7df5e312cd5fa0c7360
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.171341896057129,
-  "best_model_checkpoint": "./output/checkpoint-4800",
-  "epoch": 0.39480177660799476,
+  "best_metric": 2.171261787414551,
+  "best_model_checkpoint": "./output/checkpoint-4950",
+  "epoch": 0.40713933212699455,
   "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": 14.084,
       "eval_steps_per_second": 14.084,
       "step": 4800
+    },
+    {
+      "epoch": 0.3956242803092614,
+      "grad_norm": 4.908514976501465,
+      "learning_rate": 2.0378882491921159e-07,
+      "loss": 2.0785,
+      "step": 4810
+    },
+    {
+      "epoch": 0.3964467840105281,
+      "grad_norm": 2.5932555198669434,
+      "learning_rate": 1.8292507030715362e-07,
+      "loss": 2.1721,
+      "step": 4820
+    },
+    {
+      "epoch": 0.3972692877117947,
+      "grad_norm": 3.241213798522949,
+      "learning_rate": 1.6318421365179055e-07,
+      "loss": 2.013,
+      "step": 4830
+    },
+    {
+      "epoch": 0.39809179141306134,
+      "grad_norm": 2.6974222660064697,
+      "learning_rate": 1.4456706642242134e-07,
+      "loss": 2.0443,
+      "step": 4840
+    },
+    {
+      "epoch": 0.398914295114328,
+      "grad_norm": 3.2674508094787598,
+      "learning_rate": 1.2707439389704867e-07,
+      "loss": 2.0838,
+      "step": 4850
+    },
+    {
+      "epoch": 0.39973679881559465,
+      "grad_norm": 3.7937417030334473,
+      "learning_rate": 1.1070691513092563e-07,
+      "loss": 2.1389,
+      "step": 4860
+    },
+    {
+      "epoch": 0.40055930251686134,
+      "grad_norm": 3.057102918624878,
+      "learning_rate": 9.546530292699863e-08,
+      "loss": 2.1237,
+      "step": 4870
+    },
+    {
+      "epoch": 0.40138180621812797,
+      "grad_norm": 4.695780277252197,
+      "learning_rate": 8.135018380824921e-08,
+      "loss": 2.2169,
+      "step": 4880
+    },
+    {
+      "epoch": 0.40220430991939465,
+      "grad_norm": 2.8882594108581543,
+      "learning_rate": 6.836213799193497e-08,
+      "loss": 1.9741,
+      "step": 4890
+    },
+    {
+      "epoch": 0.4030268136206613,
+      "grad_norm": 2.6791446208953857,
+      "learning_rate": 5.6501699365750784e-08,
+      "loss": 2.0918,
+      "step": 4900
+    },
+    {
+      "epoch": 0.40384931732192797,
+      "grad_norm": 3.95194149017334,
+      "learning_rate": 4.5769355465876964e-08,
+      "loss": 2.1226,
+      "step": 4910
+    },
+    {
+      "epoch": 0.4046718210231946,
+      "grad_norm": 3.425246477127075,
+      "learning_rate": 3.616554745692946e-08,
+      "loss": 2.1889,
+      "step": 4920
+    },
+    {
+      "epoch": 0.4054943247244613,
+      "grad_norm": 1.4839180707931519,
+      "learning_rate": 2.7690670113848792e-08,
+      "loss": 2.0094,
+      "step": 4930
+    },
+    {
+      "epoch": 0.4063168284257279,
+      "grad_norm": 3.0070793628692627,
+      "learning_rate": 2.034507180563916e-08,
+      "loss": 2.0609,
+      "step": 4940
+    },
+    {
+      "epoch": 0.40713933212699455,
+      "grad_norm": 4.635149955749512,
+      "learning_rate": 1.4129054481082926e-08,
+      "loss": 2.182,
+      "step": 4950
+    },
+    {
+      "epoch": 0.40713933212699455,
+      "eval_loss": 2.171261787414551,
+      "eval_runtime": 35.5515,
+      "eval_samples_per_second": 14.064,
+      "eval_steps_per_second": 14.064,
+      "step": 4950
     }
   ],
   "logging_steps": 10,
@@ -3642,7 +3755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0733717283098624e+17,
+  "total_flos": 2.1414825101021184e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null