Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33daf140fd585464eee41484de04e2474d8e47d63abe817dceaf9b00888e076
+oid sha256:b4376c34886456cb2899c7f6beeadbdd0369c3eb2c8cb577a4c24d977132e673
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6902f4a187e909e2a61310381b65d1586200f826c3f0696581929350cf563d6
+oid sha256:c5822d4454f023f2e758e0371b888496dd2a0767e11534488d6f9c822d136956
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e4de9332de0a821c86e7798fc265e5a2e1afe5f2f6b38a27a1659456e57185
+oid sha256:41879b6be867dc93cfdfe9c095241e1809219ed8cb44d663d4b21de0f8b8f617
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ceceb1b964f59d3125423a0c5ef9d004a1142d04972a62dc4fa7ae95e8eed4
+oid sha256:040a1b5835b5527454d21946072fd417fbebea1df191d3f188daffdb17ff5507
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7177689671516418,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 117.3913043478261,
+  "epoch": 123.91304347826087,
   "eval_steps": 150,
-  "global_step": 2700,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2617,6 +2617,151 @@
       "EMA_steps_per_second": 24.381,
       "epoch": 117.3913043478261,
       "step": 2700
+    },
+    {
+      "epoch": 117.82608695652173,
+      "grad_norm": 3.383168935775757,
+      "learning_rate": 3.9100869016093776e-07,
+      "loss": 0.2406,
+      "step": 2710
+    },
+    {
+      "epoch": 118.26086956521739,
+      "grad_norm": 1.8521851301193237,
+      "learning_rate": 7.820173803218755e-07,
+      "loss": 0.2516,
+      "step": 2720
+    },
+    {
+      "epoch": 118.69565217391305,
+      "grad_norm": 2.2895267009735107,
+      "learning_rate": 1.1730260704828132e-06,
+      "loss": 0.2411,
+      "step": 2730
+    },
+    {
+      "epoch": 119.1304347826087,
+      "grad_norm": 2.308509349822998,
+      "learning_rate": 1.564034760643751e-06,
+      "loss": 0.2601,
+      "step": 2740
+    },
+    {
+      "epoch": 119.56521739130434,
+      "grad_norm": 2.1916897296905518,
+      "learning_rate": 1.9550434508046887e-06,
+      "loss": 0.2596,
+      "step": 2750
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 4.756087779998779,
+      "learning_rate": 2.3460521409656263e-06,
+      "loss": 0.2188,
+      "step": 2760
+    },
+    {
+      "epoch": 120.43478260869566,
+      "grad_norm": 1.9395239353179932,
+      "learning_rate": 2.737060831126564e-06,
+      "loss": 0.2546,
+      "step": 2770
+    },
+    {
+      "epoch": 120.8695652173913,
+      "grad_norm": 1.7763605117797852,
+      "learning_rate": 3.128069521287502e-06,
+      "loss": 0.219,
+      "step": 2780
+    },
+    {
+      "epoch": 121.30434782608695,
+      "grad_norm": 1.3847345113754272,
+      "learning_rate": 3.5190782114484397e-06,
+      "loss": 0.2731,
+      "step": 2790
+    },
+    {
+      "epoch": 121.73913043478261,
+      "grad_norm": 2.002622365951538,
+      "learning_rate": 3.910086901609377e-06,
+      "loss": 0.2701,
+      "step": 2800
+    },
+    {
+      "epoch": 122.17391304347827,
+      "grad_norm": 2.062542200088501,
+      "learning_rate": 3.910086514150998e-06,
+      "loss": 0.2201,
+      "step": 2810
+    },
+    {
+      "epoch": 122.6086956521739,
+      "grad_norm": 1.7233972549438477,
+      "learning_rate": 3.910085351776012e-06,
+      "loss": 0.2632,
+      "step": 2820
+    },
+    {
+      "epoch": 123.04347826086956,
+      "grad_norm": 1.894426703453064,
+      "learning_rate": 3.91008341448488e-06,
+      "loss": 0.2512,
+      "step": 2830
+    },
+    {
+      "epoch": 123.47826086956522,
+      "grad_norm": 2.2210731506347656,
+      "learning_rate": 3.910080702278371e-06,
+      "loss": 0.2425,
+      "step": 2840
+    },
+    {
+      "epoch": 123.91304347826087,
+      "grad_norm": 2.2751896381378174,
+      "learning_rate": 3.91007721515756e-06,
+      "loss": 0.2389,
+      "step": 2850
+    },
+    {
+      "epoch": 123.91304347826087,
+      "eval_loss": 0.9399979710578918,
+      "eval_runtime": 0.5741,
+      "eval_samples_per_second": 17.419,
+      "eval_steps_per_second": 17.419,
+      "step": 2850
+    },
+    {
+      "Start_State_loss": 0.861186683177948,
+      "Start_State_runtime": 0.5559,
+      "Start_State_samples_per_second": 17.99,
+      "Start_State_steps_per_second": 17.99,
+      "epoch": 123.91304347826087,
+      "step": 2850
+    },
+    {
+      "Raw_Model_loss": 0.9399979710578918,
+      "Raw_Model_runtime": 0.5508,
+      "Raw_Model_samples_per_second": 18.155,
+      "Raw_Model_steps_per_second": 18.155,
+      "epoch": 123.91304347826087,
+      "step": 2850
+    },
+    {
+      "SWA_loss": 0.7678512334823608,
+      "SWA_runtime": 0.554,
+      "SWA_samples_per_second": 18.049,
+      "SWA_steps_per_second": 18.049,
+      "epoch": 123.91304347826087,
+      "step": 2850
+    },
+    {
+      "EMA_loss": 0.8602371215820312,
+      "EMA_runtime": 0.5253,
+      "EMA_samples_per_second": 19.037,
+      "EMA_steps_per_second": 19.037,
+      "epoch": 123.91304347826087,
+      "step": 2850
     }
   ],
   "logging_steps": 10,
@@ -2636,7 +2781,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.95112550820905e+16,
+  "total_flos": 7.337359146420634e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null