Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd82b375151b5b5f9f0a58b8286fa2a7b7e910cea5c2d600b74e22d38bdbcca
+oid sha256:593eb37c50a4439ba03e83ada103a9e73c7a6cc5e2190f9a48dcfe15e287b91a
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e869796afac1a7a34f750f8422f24ec974478aafa79ce79e006a42fe78f21d
+oid sha256:540ae6c9df4b9fc1733ab8364067bef7b8eed491e5133d225a8fa424852ac127
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2616293446c1c2f2c6b0e270c4bb50dd25782b075145433b30550e3bb3a1845c
+oid sha256:280ae9c0809eceeb464f568a46cee1cc6c997124b85d7c1db2a216ff1d3932aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
+oid sha256:b5ff073b2d9654300593116ff77249d188bd5752ecbe3d0cb800964ea5d21c80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7168648838996887,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 19.565217391304348,
+  "epoch": 26.08695652173913,
   "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": 16.41,
       "eval_steps_per_second": 16.41,
       "step": 450
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.1229870319366455,
+      "learning_rate": 2.9996147467351856e-05,
+      "loss": 0.5146,
+      "step": 460
+    },
+    {
+      "epoch": 20.434782608695652,
+      "grad_norm": 1.2757331132888794,
+      "learning_rate": 2.9995930474939773e-05,
+      "loss": 0.4783,
+      "step": 470
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 1.4738444089889526,
+      "learning_rate": 2.9995707538619975e-05,
+      "loss": 0.5707,
+      "step": 480
+    },
+    {
+      "epoch": 21.304347826086957,
+      "grad_norm": 1.3224209547042847,
+      "learning_rate": 2.9995478658480822e-05,
+      "loss": 0.5163,
+      "step": 490
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 1.2427003383636475,
+      "learning_rate": 2.9995243834613043e-05,
+      "loss": 0.5206,
+      "step": 500
+    },
+    {
+      "epoch": 22.17391304347826,
+      "grad_norm": 1.7819838523864746,
+      "learning_rate": 2.9995003067109707e-05,
+      "loss": 0.4836,
+      "step": 510
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 1.531520128250122,
+      "learning_rate": 2.9994756356066246e-05,
+      "loss": 0.5615,
+      "step": 520
+    },
+    {
+      "epoch": 23.043478260869566,
+      "grad_norm": 1.7395285367965698,
+      "learning_rate": 2.999450370158046e-05,
+      "loss": 0.4929,
+      "step": 530
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 1.3100509643554688,
+      "learning_rate": 2.9994245103752478e-05,
+      "loss": 0.4383,
+      "step": 540
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 1.2314648628234863,
+      "learning_rate": 2.999398056268481e-05,
+      "loss": 0.5265,
+      "step": 550
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 1.4086766242980957,
+      "learning_rate": 2.9993710078482306e-05,
+      "loss": 0.5204,
+      "step": 560
+    },
+    {
+      "epoch": 24.782608695652176,
+      "grad_norm": 0.9533238410949707,
+      "learning_rate": 2.9993433651252185e-05,
+      "loss": 0.4432,
+      "step": 570
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 1.7112679481506348,
+      "learning_rate": 2.9993151281104006e-05,
+      "loss": 0.5326,
+      "step": 580
+    },
+    {
+      "epoch": 25.652173913043477,
+      "grad_norm": 1.1396631002426147,
+      "learning_rate": 2.9992862968149695e-05,
+      "loss": 0.4736,
+      "step": 590
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 1.1695138216018677,
+      "learning_rate": 2.9992568712503533e-05,
+      "loss": 0.4608,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7204726934432983,
+      "eval_runtime": 0.6002,
+      "eval_samples_per_second": 16.662,
+      "eval_steps_per_second": 16.662,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -365,7 +478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 1.5363065839583232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null