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:b2185809297ec41828ec9b22b17d90c068a1be1c9e7367979abb621610e37158
+oid sha256:25bfdf8b73a7808d768ee875de725f68ed4cf802558481cb5d16c4ebbb540f5b
 size 16505096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d024a0b877e7e9e99b034e7bd29640b9cadb757d1ab860be6f6868439efddf5
+oid sha256:577fc89d1865fa0ee8b22e09034d283d4b38fb6b6d67706712d1841a4724ef8c
 size 16603054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091ef73efa5772acd39432c8f4330e75da07720da8e6b98ac6e10d95f7d408ef
+oid sha256:b61e7519f95c5c547cbe5d9595be782731b3e32c1e168d4825707212a753784f
 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": 2.961325168609619,
-  "best_model_checkpoint": "./output/checkpoint-4800",
-  "epoch": 0.609833566255876,
+  "best_metric": 2.961240768432617,
+  "best_model_checkpoint": "./output/checkpoint-4950",
+  "epoch": 0.6288908652013722,
   "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": 154.478,
       "eval_steps_per_second": 154.478,
       "step": 4800
+    },
+    {
+      "epoch": 0.6111040528522425,
+      "grad_norm": 4.158885478973389,
+      "learning_rate": 3.705251362167482e-07,
+      "loss": 3.1064,
+      "step": 4810
+    },
+    {
+      "epoch": 0.6123745394486089,
+      "grad_norm": 3.642362356185913,
+      "learning_rate": 3.3259103692209737e-07,
+      "loss": 3.0982,
+      "step": 4820
+    },
+    {
+      "epoch": 0.6136450260449752,
+      "grad_norm": 4.46030855178833,
+      "learning_rate": 2.966985702759827e-07,
+      "loss": 3.0865,
+      "step": 4830
+    },
+    {
+      "epoch": 0.6149155126413416,
+      "grad_norm": 3.290504217147827,
+      "learning_rate": 2.628492116771297e-07,
+      "loss": 3.1245,
+      "step": 4840
+    },
+    {
+      "epoch": 0.616185999237708,
+      "grad_norm": 3.5559308528900146,
+      "learning_rate": 2.3104435254008842e-07,
+      "loss": 3.103,
+      "step": 4850
+    },
+    {
+      "epoch": 0.6174564858340744,
+      "grad_norm": 3.685878276824951,
+      "learning_rate": 2.0128530023804653e-07,
+      "loss": 3.0828,
+      "step": 4860
+    },
+    {
+      "epoch": 0.6187269724304408,
+      "grad_norm": 3.95636248588562,
+      "learning_rate": 1.7357327804908836e-07,
+      "loss": 3.1101,
+      "step": 4870
+    },
+    {
+      "epoch": 0.6199974590268073,
+      "grad_norm": 3.837711811065674,
+      "learning_rate": 1.479094251059076e-07,
+      "loss": 3.1126,
+      "step": 4880
+    },
+    {
+      "epoch": 0.6212679456231737,
+      "grad_norm": 3.555655002593994,
+      "learning_rate": 1.2429479634897264e-07,
+      "loss": 3.1094,
+      "step": 4890
+    },
+    {
+      "epoch": 0.6225384322195401,
+      "grad_norm": 3.6717865467071533,
+      "learning_rate": 1.0273036248318322e-07,
+      "loss": 3.1114,
+      "step": 4900
+    },
+    {
+      "epoch": 0.6238089188159065,
+      "grad_norm": 3.554436445236206,
+      "learning_rate": 8.321700993795809e-08,
+      "loss": 3.123,
+      "step": 4910
+    },
+    {
+      "epoch": 0.6250794054122729,
+      "grad_norm": 3.458787202835083,
+      "learning_rate": 6.575554083078082e-08,
+      "loss": 3.0897,
+      "step": 4920
+    },
+    {
+      "epoch": 0.6263498920086393,
+      "grad_norm": 2.9243547916412354,
+      "learning_rate": 5.034667293427052e-08,
+      "loss": 3.0853,
+      "step": 4930
+    },
+    {
+      "epoch": 0.6276203786050057,
+      "grad_norm": 4.113716125488281,
+      "learning_rate": 3.6991039646616646e-08,
+      "loss": 3.1065,
+      "step": 4940
+    },
+    {
+      "epoch": 0.6288908652013722,
+      "grad_norm": 3.806378126144409,
+      "learning_rate": 2.5689189965605314e-08,
+      "loss": 3.1004,
+      "step": 4950
+    },
+    {
+      "epoch": 0.6288908652013722,
+      "eval_loss": 2.961240768432617,
+      "eval_runtime": 3.2716,
+      "eval_samples_per_second": 152.832,
+      "eval_steps_per_second": 152.832,
+      "step": 4950
     }
   ],
   "logging_steps": 10,
@@ -3642,7 +3755,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5909475999744000.0,
+  "total_flos": 6094147124736000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null