Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb570867b39da8ca5f9dcb5a985b279fec72307f9c34b27d25f5a270d849bb9
+oid sha256:7217176b2cddaa72e46eb30c9cc84a5be813fd6776facbaf277dcc8d7979eabd
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2a8d621b78697c67005e055c00235f3d9085c1c8d486bb9edd4ae03d403f83
+oid sha256:92f7dc1fcda761e3cebe060c99e1b3c732d2e254c2fdc7fe7c567151a7818c1f
 size 1049049442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3dd9835961741b97ed6bc0c71057c6d15eaf84418093825034d870f676dd7ea
+oid sha256:a2759f9dc525a7c6daf5d5bb9e1a98fb5fce6ddd8bd5344b2dc8d63886281857
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d349b525fc7c7eff553c27846b0059879b2d31c63b4e246efacc449795c47e3
+oid sha256:36ecce3e1177343d53ff5033f14f9aeebc8d978f05d309eda4e2cfafa92535e9
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2499778270721436,
-  "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 0.020156774916013438,
+  "best_metric": 1.2407419681549072,
+  "best_model_checkpoint": "./output/checkpoint-600",
+  "epoch": 0.026875699888017916,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -346,6 +346,119 @@
       "eval_samples_per_second": 9.69,
       "eval_steps_per_second": 9.69,
       "step": 450
+    },
+    {
+      "epoch": 0.020604703247480403,
+      "grad_norm": 3.672325372695923,
+      "learning_rate": 7.400554539316894e-06,
+      "loss": 1.1627,
+      "step": 460
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 4.949635982513428,
+      "learning_rate": 7.394979347953081e-06,
+      "loss": 1.3115,
+      "step": 470
+    },
+    {
+      "epoch": 0.021500559910414333,
+      "grad_norm": 4.03855037689209,
+      "learning_rate": 7.389254325764681e-06,
+      "loss": 1.1176,
+      "step": 480
+    },
+    {
+      "epoch": 0.0219484882418813,
+      "grad_norm": 4.981250762939453,
+      "learning_rate": 7.383379708084934e-06,
+      "loss": 1.0668,
+      "step": 490
+    },
+    {
+      "epoch": 0.022396416573348264,
+      "grad_norm": 4.68571138381958,
+      "learning_rate": 7.377355736396362e-06,
+      "loss": 1.1235,
+      "step": 500
+    },
+    {
+      "epoch": 0.02284434490481523,
+      "grad_norm": 5.7003326416015625,
+      "learning_rate": 7.371182658320847e-06,
+      "loss": 1.0535,
+      "step": 510
+    },
+    {
+      "epoch": 0.023292273236282194,
+      "grad_norm": 2.357079029083252,
+      "learning_rate": 7.36486072760945e-06,
+      "loss": 0.9768,
+      "step": 520
+    },
+    {
+      "epoch": 0.02374020156774916,
+      "grad_norm": 4.828664779663086,
+      "learning_rate": 7.358390204131984e-06,
+      "loss": 1.0385,
+      "step": 530
+    },
+    {
+      "epoch": 0.024188129899216124,
+      "grad_norm": 3.4303321838378906,
+      "learning_rate": 7.3517713538663235e-06,
+      "loss": 0.9826,
+      "step": 540
+    },
+    {
+      "epoch": 0.02463605823068309,
+      "grad_norm": 8.705097198486328,
+      "learning_rate": 7.345004448887478e-06,
+      "loss": 1.0988,
+      "step": 550
+    },
+    {
+      "epoch": 0.025083986562150055,
+      "grad_norm": 4.806099891662598,
+      "learning_rate": 7.3380897673564085e-06,
+      "loss": 1.2765,
+      "step": 560
+    },
+    {
+      "epoch": 0.02553191489361702,
+      "grad_norm": 3.948829174041748,
+      "learning_rate": 7.33102759350859e-06,
+      "loss": 1.2548,
+      "step": 570
+    },
+    {
+      "epoch": 0.025979843225083985,
+      "grad_norm": 8.706982612609863,
+      "learning_rate": 7.323818217642328e-06,
+      "loss": 1.1907,
+      "step": 580
+    },
+    {
+      "epoch": 0.02642777155655095,
+      "grad_norm": 4.196287155151367,
+      "learning_rate": 7.316461936106827e-06,
+      "loss": 1.1541,
+      "step": 590
+    },
+    {
+      "epoch": 0.026875699888017916,
+      "grad_norm": 4.2185187339782715,
+      "learning_rate": 7.3089590512900084e-06,
+      "loss": 1.0761,
+      "step": 600
+    },
+    {
+      "epoch": 0.026875699888017916,
+      "eval_loss": 1.2407419681549072,
+      "eval_runtime": 51.6589,
+      "eval_samples_per_second": 9.679,
+      "eval_steps_per_second": 9.679,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -365,7 +478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.76911261749248e+16,
+  "total_flos": 7.7474464828416e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null