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:f3c3d59965295ce7450641ca00b68f5a92f415b6fac45dff70940bd51e95cf96
+oid sha256:ba7511c2605cd169f9d4925ef16d0aab1204009d184f031c3e7da4d154628430
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3548425916972973cfad6bfd0e5b8015f30a53f0657f6ef6e17a1ab45db45c4c
+oid sha256:4450e064cd4e1c2b71c64918ea5ef37084002b46be2aef8983814714f6dfcb31
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76c4c2dca19bfb0a463693a0e409b44510488650d816e566bccd2a2851e9524
+oid sha256:b3db7d037567f9907c679104cc622f6046bdf2f33143ca3a29365b2fa4072ce8
 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": 0.7166430950164795,
   "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,
@@ -442,6 +442,151 @@
       "EMA_steps_per_second": 23.424,
       "epoch": 19.565217391304348,
       "step": 450
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.1295206546783447,
+      "learning_rate": 2.9996147467351856e-05,
+      "loss": 0.5146,
+      "step": 460
+    },
+    {
+      "epoch": 20.434782608695652,
+      "grad_norm": 1.2770106792449951,
+      "learning_rate": 2.9995930474939773e-05,
+      "loss": 0.4784,
+      "step": 470
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 1.4706833362579346,
+      "learning_rate": 2.9995707538619975e-05,
+      "loss": 0.5705,
+      "step": 480
+    },
+    {
+      "epoch": 21.304347826086957,
+      "grad_norm": 1.3234336376190186,
+      "learning_rate": 2.9995478658480822e-05,
+      "loss": 0.5167,
+      "step": 490
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 1.242873191833496,
+      "learning_rate": 2.9995243834613043e-05,
+      "loss": 0.5207,
+      "step": 500
+    },
+    {
+      "epoch": 22.17391304347826,
+      "grad_norm": 1.77828049659729,
+      "learning_rate": 2.9995003067109707e-05,
+      "loss": 0.4832,
+      "step": 510
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 1.5282888412475586,
+      "learning_rate": 2.9994756356066246e-05,
+      "loss": 0.5615,
+      "step": 520
+    },
+    {
+      "epoch": 23.043478260869566,
+      "grad_norm": 1.7345402240753174,
+      "learning_rate": 2.999450370158046e-05,
+      "loss": 0.4929,
+      "step": 530
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 1.3091520071029663,
+      "learning_rate": 2.9994245103752478e-05,
+      "loss": 0.4383,
+      "step": 540
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 1.2344285249710083,
+      "learning_rate": 2.999398056268481e-05,
+      "loss": 0.5264,
+      "step": 550
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 1.409712791442871,
+      "learning_rate": 2.9993710078482306e-05,
+      "loss": 0.5206,
+      "step": 560
+    },
+    {
+      "epoch": 24.782608695652176,
+      "grad_norm": 0.9513388872146606,
+      "learning_rate": 2.9993433651252185e-05,
+      "loss": 0.443,
+      "step": 570
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 1.7172473669052124,
+      "learning_rate": 2.9993151281104006e-05,
+      "loss": 0.5329,
+      "step": 580
+    },
+    {
+      "epoch": 25.652173913043477,
+      "grad_norm": 1.1298749446868896,
+      "learning_rate": 2.9992862968149695e-05,
+      "loss": 0.4737,
+      "step": 590
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 1.1705174446105957,
+      "learning_rate": 2.9992568712503533e-05,
+      "loss": 0.4611,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7199234366416931,
+      "eval_runtime": 0.4236,
+      "eval_samples_per_second": 23.605,
+      "eval_steps_per_second": 23.605,
+      "step": 600
+    },
+    {
+      "Start_State_loss": 0.8601926565170288,
+      "Start_State_runtime": 0.4141,
+      "Start_State_samples_per_second": 24.146,
+      "Start_State_steps_per_second": 24.146,
+      "epoch": 26.08695652173913,
+      "step": 600
+    },
+    {
+      "Raw_Model_loss": 0.7199234366416931,
+      "Raw_Model_runtime": 0.4101,
+      "Raw_Model_samples_per_second": 24.387,
+      "Raw_Model_steps_per_second": 24.387,
+      "epoch": 26.08695652173913,
+      "step": 600
+    },
+    {
+      "SWA_loss": 0.7341524362564087,
+      "SWA_runtime": 0.4412,
+      "SWA_samples_per_second": 22.668,
+      "SWA_steps_per_second": 22.668,
+      "epoch": 26.08695652173913,
+      "step": 600
+    },
+    {
+      "EMA_loss": 0.8609703183174133,
+      "EMA_runtime": 0.424,
+      "EMA_samples_per_second": 23.585,
+      "EMA_steps_per_second": 23.585,
+      "epoch": 26.08695652173913,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -461,7 +606,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 1.5363065839583232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null