Training in progress, step 4950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e23297dc630c45b94f41c19944945a6a527d5803dfc2b626e661efc2c9f7736
+oid sha256:eb9e240cb8b429ce38d2c1deff794ef4392828b0667115cea4200713262ecb98
 size 19271144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5d28addd63ba2e473a112387b3a0ed460337f1dc35e43c1db46d2dfcb13de4
+oid sha256:a48474684272b1f9b00f7d0169411490103bce7e4c26292f6a3940d61ca50293
 size 25701388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917af671e95088f072369522f2fe0394ebfc55408545752527ca660de6a00129
+oid sha256:805985afcbec732e88c04e2e12fc965b3ae0acfe6106c73c421c187e4972e2c6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54129884a43fac233d16f8f024313b97a23fce2899d2b6122913d1d94ddf2e29
+oid sha256:b37476d32aa5db3379ce45e7fd4ee6e79ae1feca845e01cbbd94f9ebb9c76496
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.272429466247559,
-  "best_model_checkpoint": "./output/checkpoint-4800",
-  "epoch": 21.91780821917808,
+  "best_metric": 10.272299766540527,
+  "best_model_checkpoint": "./output/checkpoint-4950",
+  "epoch": 22.602739726027398,
   "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": 85.794,
       "eval_steps_per_second": 85.794,
       "step": 4800
+    },
+    {
+      "epoch": 21.963470319634702,
+      "grad_norm": 0.4868674874305725,
+      "learning_rate": 3.705251362167482e-07,
+      "loss": 10.2584,
+      "step": 4810
+    },
+    {
+      "epoch": 22.009132420091323,
+      "grad_norm": 0.4969540238380432,
+      "learning_rate": 3.3259103692209737e-07,
+      "loss": 10.2206,
+      "step": 4820
+    },
+    {
+      "epoch": 22.054794520547944,
+      "grad_norm": 0.4795879125595093,
+      "learning_rate": 2.966985702759827e-07,
+      "loss": 10.244,
+      "step": 4830
+    },
+    {
+      "epoch": 22.100456621004565,
+      "grad_norm": 0.48041990399360657,
+      "learning_rate": 2.628492116771297e-07,
+      "loss": 10.263,
+      "step": 4840
+    },
+    {
+      "epoch": 22.146118721461185,
+      "grad_norm": 0.4863426685333252,
+      "learning_rate": 2.3104435254008842e-07,
+      "loss": 10.2607,
+      "step": 4850
+    },
+    {
+      "epoch": 22.19178082191781,
+      "grad_norm": 0.48450392484664917,
+      "learning_rate": 2.0128530023804653e-07,
+      "loss": 10.2491,
+      "step": 4860
+    },
+    {
+      "epoch": 22.23744292237443,
+      "grad_norm": 0.5094718933105469,
+      "learning_rate": 1.7357327804908836e-07,
+      "loss": 10.2375,
+      "step": 4870
+    },
+    {
+      "epoch": 22.28310502283105,
+      "grad_norm": 0.5187403559684753,
+      "learning_rate": 1.479094251059076e-07,
+      "loss": 10.252,
+      "step": 4880
+    },
+    {
+      "epoch": 22.328767123287673,
+      "grad_norm": 0.4854632616043091,
+      "learning_rate": 1.2429479634897264e-07,
+      "loss": 10.2572,
+      "step": 4890
+    },
+    {
+      "epoch": 22.374429223744293,
+      "grad_norm": 0.49426454305648804,
+      "learning_rate": 1.0273036248318322e-07,
+      "loss": 10.2529,
+      "step": 4900
+    },
+    {
+      "epoch": 22.420091324200914,
+      "grad_norm": 0.48748934268951416,
+      "learning_rate": 8.321700993795809e-08,
+      "loss": 10.2514,
+      "step": 4910
+    },
+    {
+      "epoch": 22.465753424657535,
+      "grad_norm": 0.4993211328983307,
+      "learning_rate": 6.575554083078082e-08,
+      "loss": 10.2496,
+      "step": 4920
+    },
+    {
+      "epoch": 22.511415525114156,
+      "grad_norm": 0.5011383891105652,
+      "learning_rate": 5.034667293427052e-08,
+      "loss": 10.2408,
+      "step": 4930
+    },
+    {
+      "epoch": 22.557077625570777,
+      "grad_norm": 0.5127740502357483,
+      "learning_rate": 3.6991039646616646e-08,
+      "loss": 10.2542,
+      "step": 4940
+    },
+    {
+      "epoch": 22.602739726027398,
+      "grad_norm": 0.49984294176101685,
+      "learning_rate": 2.5689189965605314e-08,
+      "loss": 10.2478,
+      "step": 4950
+    },
+    {
+      "epoch": 22.602739726027398,
+      "eval_loss": 10.272299766540527,
+      "eval_runtime": 2.293,
+      "eval_samples_per_second": 84.606,
+      "eval_steps_per_second": 84.606,
+      "step": 4950
     }
   ],
   "logging_steps": 10,
@@ -3642,7 +3755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 963103912667664.0,
+  "total_flos": 992906666382720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null