Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7511c2605cd169f9d4925ef16d0aab1204009d184f031c3e7da4d154628430
+oid sha256:3cd890db48dacc3d3b3df0971ab6f506777ee6324b5fe98afa58345c1314ac67
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4450e064cd4e1c2b71c64918ea5ef37084002b46be2aef8983814714f6dfcb31
+oid sha256:f50b123a4aeda0cacc062ede7b0235cc81f9613e4e55cf6e5de746a463a52fea
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3db7d037567f9907c679104cc622f6046bdf2f33143ca3a29365b2fa4072ce8
+oid sha256:4ca9142fcbd976a2b9880762578e5776f18d9cad34016a627060f41ab78ec47d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ff073b2d9654300593116ff77249d188bd5752ecbe3d0cb800964ea5d21c80
+oid sha256:e8974fc0327a603be8a90ee235d3ef81c4ee4af2818c873bdeb9bfb38f108e1a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7166430950164795,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 26.08695652173913,
+  "epoch": 32.608695652173914,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -587,6 +587,151 @@
       "EMA_steps_per_second": 23.585,
       "epoch": 26.08695652173913,
       "step": 600
+    },
+    {
+      "epoch": 26.52173913043478,
+      "grad_norm": 1.0925955772399902,
+      "learning_rate": 2.9992268514282142e-05,
+      "loss": 0.5116,
+      "step": 610
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 1.343130111694336,
+      "learning_rate": 2.999196237360452e-05,
+      "loss": 0.4316,
+      "step": 620
+    },
+    {
+      "epoch": 27.391304347826086,
+      "grad_norm": 1.203368902206421,
+      "learning_rate": 2.9991650290592016e-05,
+      "loss": 0.4756,
+      "step": 630
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 1.3935104608535767,
+      "learning_rate": 2.999133226536832e-05,
+      "loss": 0.501,
+      "step": 640
+    },
+    {
+      "epoch": 28.26086956521739,
+      "grad_norm": 1.412856936454773,
+      "learning_rate": 2.9991008298059493e-05,
+      "loss": 0.4107,
+      "step": 650
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 1.5606491565704346,
+      "learning_rate": 2.9990678388793944e-05,
+      "loss": 0.5064,
+      "step": 660
+    },
+    {
+      "epoch": 29.130434782608695,
+      "grad_norm": 1.315181016921997,
+      "learning_rate": 2.999034253770244e-05,
+      "loss": 0.4347,
+      "step": 670
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 1.077691674232483,
+      "learning_rate": 2.9990000744918097e-05,
+      "loss": 0.4705,
+      "step": 680
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.501568078994751,
+      "learning_rate": 2.9989653010576392e-05,
+      "loss": 0.4145,
+      "step": 690
+    },
+    {
+      "epoch": 30.434782608695652,
+      "grad_norm": 1.3340367078781128,
+      "learning_rate": 2.9989299334815158e-05,
+      "loss": 0.4764,
+      "step": 700
+    },
+    {
+      "epoch": 30.869565217391305,
+      "grad_norm": 1.6282958984375,
+      "learning_rate": 2.9988939717774578e-05,
+      "loss": 0.4118,
+      "step": 710
+    },
+    {
+      "epoch": 31.304347826086957,
+      "grad_norm": 0.9019575119018555,
+      "learning_rate": 2.9988574159597194e-05,
+      "loss": 0.4244,
+      "step": 720
+    },
+    {
+      "epoch": 31.73913043478261,
+      "grad_norm": 1.6408599615097046,
+      "learning_rate": 2.9988202660427907e-05,
+      "loss": 0.4821,
+      "step": 730
+    },
+    {
+      "epoch": 32.17391304347826,
+      "grad_norm": 1.1973698139190674,
+      "learning_rate": 2.9987825220413958e-05,
+      "loss": 0.4385,
+      "step": 740
+    },
+    {
+      "epoch": 32.608695652173914,
+      "grad_norm": 1.7692193984985352,
+      "learning_rate": 2.998744183970496e-05,
+      "loss": 0.4738,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.731913149356842,
+      "eval_runtime": 0.5751,
+      "eval_samples_per_second": 17.389,
+      "eval_steps_per_second": 17.389,
+      "step": 750
+    },
+    {
+      "Start_State_loss": 0.8601926565170288,
+      "Start_State_runtime": 0.4166,
+      "Start_State_samples_per_second": 24.004,
+      "Start_State_steps_per_second": 24.004,
+      "epoch": 32.608695652173914,
+      "step": 750
+    },
+    {
+      "Raw_Model_loss": 0.731913149356842,
+      "Raw_Model_runtime": 0.402,
+      "Raw_Model_samples_per_second": 24.875,
+      "Raw_Model_steps_per_second": 24.875,
+      "epoch": 32.608695652173914,
+      "step": 750
+    },
+    {
+      "SWA_loss": 0.7290045022964478,
+      "SWA_runtime": 0.4054,
+      "SWA_samples_per_second": 24.666,
+      "SWA_steps_per_second": 24.666,
+      "epoch": 32.608695652173914,
+      "step": 750
+    },
+    {
+      "EMA_loss": 0.8603373765945435,
+      "EMA_runtime": 0.4026,
+      "EMA_samples_per_second": 24.839,
+      "EMA_steps_per_second": 24.839,
+      "epoch": 32.608695652173914,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -606,7 +751,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5363065839583232e+16,
+  "total_flos": 1.9231766387195904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null