Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558bd7240ae36bf407fa59d99bc87b4f2a83238e3eefe9e7d80228b0d675c5f2
+oid sha256:023bdf4fb37105c005af155a89b3617ec253742740b1c443640c3cfd919b153c
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c44e87a84da7f09944098b8b24a46d1e1784343e14aa00f21290dad1d35d03
+oid sha256:ee34169c145fc9db54236abebff2e7bbd35b77780ea424fc21c3c1a2442d1d2d
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b99872e409bc674b8b81f4e59047c6dd181202eceec2bd8ec5e0879c5adbc8fc
+oid sha256:0245389a7bc82d29e971a63bfd36a481643b7f85d29704591ececfc67d58955b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b6379912da098573e94d032fbbd0f173cdb17e7336f428aac213f60f9a5145
+oid sha256:a1bce2a8653bdd97c984ac0cb8f8fc01c58c1e2c98ab50a771eb0dc001a601b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7177689671516418,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 84.78260869565217,
+  "epoch": 91.30434782608695,
   "eval_steps": 150,
-  "global_step": 1950,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1892,6 +1892,151 @@
       "EMA_steps_per_second": 25.224,
       "epoch": 84.78260869565217,
       "step": 1950
+    },
+    {
+      "epoch": 85.21739130434783,
+      "grad_norm": 2.3564674854278564,
+      "learning_rate": 7.487875215855521e-07,
+      "loss": 0.265,
+      "step": 1960
+    },
+    {
+      "epoch": 85.65217391304348,
+      "grad_norm": 1.8858447074890137,
+      "learning_rate": 1.4975750431711041e-06,
+      "loss": 0.2704,
+      "step": 1970
+    },
+    {
+      "epoch": 86.08695652173913,
+      "grad_norm": 2.1835811138153076,
+      "learning_rate": 2.2463625647566557e-06,
+      "loss": 0.2531,
+      "step": 1980
+    },
+    {
+      "epoch": 86.52173913043478,
+      "grad_norm": 1.674813985824585,
+      "learning_rate": 2.9951500863422082e-06,
+      "loss": 0.2767,
+      "step": 1990
+    },
+    {
+      "epoch": 86.95652173913044,
+      "grad_norm": 2.0097134113311768,
+      "learning_rate": 3.74393760792776e-06,
+      "loss": 0.2766,
+      "step": 2000
+    },
+    {
+      "epoch": 87.3913043478261,
+      "grad_norm": 1.4214787483215332,
+      "learning_rate": 4.4927251295133115e-06,
+      "loss": 0.2779,
+      "step": 2010
+    },
+    {
+      "epoch": 87.82608695652173,
+      "grad_norm": 2.0007896423339844,
+      "learning_rate": 5.241512651098863e-06,
+      "loss": 0.2588,
+      "step": 2020
+    },
+    {
+      "epoch": 88.26086956521739,
+      "grad_norm": 2.0449113845825195,
+      "learning_rate": 5.9903001726844164e-06,
+      "loss": 0.2614,
+      "step": 2030
+    },
+    {
+      "epoch": 88.69565217391305,
+      "grad_norm": 1.7983092069625854,
+      "learning_rate": 6.739087694269968e-06,
+      "loss": 0.2852,
+      "step": 2040
+    },
+    {
+      "epoch": 89.1304347826087,
+      "grad_norm": 1.8373875617980957,
+      "learning_rate": 7.48787521585552e-06,
+      "loss": 0.2914,
+      "step": 2050
+    },
+    {
+      "epoch": 89.56521739130434,
+      "grad_norm": 1.543720006942749,
+      "learning_rate": 7.487874473866896e-06,
+      "loss": 0.2467,
+      "step": 2060
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 1.6378145217895508,
+      "learning_rate": 7.487872247901318e-06,
+      "loss": 0.2524,
+      "step": 2070
+    },
+    {
+      "epoch": 90.43478260869566,
+      "grad_norm": 1.8025075197219849,
+      "learning_rate": 7.4878685379596685e-06,
+      "loss": 0.2572,
+      "step": 2080
+    },
+    {
+      "epoch": 90.8695652173913,
+      "grad_norm": 1.7167291641235352,
+      "learning_rate": 7.487863344043418e-06,
+      "loss": 0.283,
+      "step": 2090
+    },
+    {
+      "epoch": 91.30434782608695,
+      "grad_norm": 1.7985183000564575,
+      "learning_rate": 7.487856666154626e-06,
+      "loss": 0.2721,
+      "step": 2100
+    },
+    {
+      "epoch": 91.30434782608695,
+      "eval_loss": 0.8964352607727051,
+      "eval_runtime": 0.4971,
+      "eval_samples_per_second": 20.118,
+      "eval_steps_per_second": 20.118,
+      "step": 2100
+    },
+    {
+      "Start_State_loss": 0.861186683177948,
+      "Start_State_runtime": 0.5202,
+      "Start_State_samples_per_second": 19.223,
+      "Start_State_steps_per_second": 19.223,
+      "epoch": 91.30434782608695,
+      "step": 2100
+    },
+    {
+      "Raw_Model_loss": 0.8964352607727051,
+      "Raw_Model_runtime": 0.4702,
+      "Raw_Model_samples_per_second": 21.269,
+      "Raw_Model_steps_per_second": 21.269,
+      "epoch": 91.30434782608695,
+      "step": 2100
+    },
+    {
+      "SWA_loss": 0.7461259365081787,
+      "SWA_runtime": 0.3981,
+      "SWA_samples_per_second": 25.122,
+      "SWA_steps_per_second": 25.122,
+      "epoch": 91.30434782608695,
+      "step": 2100
+    },
+    {
+      "EMA_loss": 0.8607404828071594,
+      "EMA_runtime": 0.3991,
+      "EMA_samples_per_second": 25.058,
+      "EMA_steps_per_second": 25.058,
+      "epoch": 91.30434782608695,
+      "step": 2100
     }
   ],
   "logging_steps": 10,
@@ -1911,7 +2056,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.02053291067392e+16,
+  "total_flos": 5.411670961736909e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null