Training in progress, step 2700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a48e299ffea4a1305480644e0252c4aab5e02d9191b6e951f282025c021c36
+oid sha256:f33daf140fd585464eee41484de04e2474d8e47d63abe817dceaf9b00888e076
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb7656d0058945a544e068c4c181cbcbae03cf7066df76778cb4579b9066242
+oid sha256:d6902f4a187e909e2a61310381b65d1586200f826c3f0696581929350cf563d6
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33335d8e454fa636f80bfcf35b73daf17e2d9682ef2741d0ad1097e25ee4742d
+oid sha256:43e4de9332de0a821c86e7798fc265e5a2e1afe5f2f6b38a27a1659456e57185
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f98b757d648be3e63607e2156858bad579d6a12d490a3cb2c8748d9ae2cce45
+oid sha256:f7ceceb1b964f59d3125423a0c5ef9d004a1142d04972a62dc4fa7ae95e8eed4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7177689671516418,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 110.8695652173913,
+  "epoch": 117.3913043478261,
   "eval_steps": 150,
-  "global_step": 2550,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2472,6 +2472,151 @@
       "EMA_steps_per_second": 24.098,
       "epoch": 110.8695652173913,
       "step": 2550
+    },
+    {
+      "epoch": 111.30434782608695,
+      "grad_norm": 2.409362554550171,
+      "learning_rate": 7.485945469179237e-06,
+      "loss": 0.2816,
+      "step": 2560
+    },
+    {
+      "epoch": 111.73913043478261,
+      "grad_norm": 2.021090030670166,
+      "learning_rate": 7.485869057739486e-06,
+      "loss": 0.228,
+      "step": 2570
+    },
+    {
+      "epoch": 112.17391304347827,
+      "grad_norm": 2.0017611980438232,
+      "learning_rate": 7.485791163117665e-06,
+      "loss": 0.2461,
+      "step": 2580
+    },
+    {
+      "epoch": 112.6086956521739,
+      "grad_norm": 1.6572258472442627,
+      "learning_rate": 7.485711785344648e-06,
+      "loss": 0.2461,
+      "step": 2590
+    },
+    {
+      "epoch": 113.04347826086956,
+      "grad_norm": 2.1028172969818115,
+      "learning_rate": 7.485630924451897e-06,
+      "loss": 0.2658,
+      "step": 2600
+    },
+    {
+      "epoch": 113.47826086956522,
+      "grad_norm": 1.8281258344650269,
+      "learning_rate": 7.485548580471464e-06,
+      "loss": 0.2257,
+      "step": 2610
+    },
+    {
+      "epoch": 113.91304347826087,
+      "grad_norm": 2.1749765872955322,
+      "learning_rate": 7.485464753435987e-06,
+      "loss": 0.2756,
+      "step": 2620
+    },
+    {
+      "epoch": 114.34782608695652,
+      "grad_norm": 2.009671688079834,
+      "learning_rate": 7.485379443378693e-06,
+      "loss": 0.2447,
+      "step": 2630
+    },
+    {
+      "epoch": 114.78260869565217,
+      "grad_norm": 2.52178955078125,
+      "learning_rate": 7.485292650333394e-06,
+      "loss": 0.2289,
+      "step": 2640
+    },
+    {
+      "epoch": 115.21739130434783,
+      "grad_norm": 1.7975748777389526,
+      "learning_rate": 7.485204374334494e-06,
+      "loss": 0.2551,
+      "step": 2650
+    },
+    {
+      "epoch": 115.65217391304348,
+      "grad_norm": 1.9182255268096924,
+      "learning_rate": 7.485114615416982e-06,
+      "loss": 0.2721,
+      "step": 2660
+    },
+    {
+      "epoch": 116.08695652173913,
+      "grad_norm": 2.3910796642303467,
+      "learning_rate": 7.485023373616437e-06,
+      "loss": 0.2156,
+      "step": 2670
+    },
+    {
+      "epoch": 116.52173913043478,
+      "grad_norm": 2.55471134185791,
+      "learning_rate": 7.484930648969023e-06,
+      "loss": 0.2447,
+      "step": 2680
+    },
+    {
+      "epoch": 116.95652173913044,
+      "grad_norm": 1.5849785804748535,
+      "learning_rate": 7.484836441511492e-06,
+      "loss": 0.2441,
+      "step": 2690
+    },
+    {
+      "epoch": 117.3913043478261,
+      "grad_norm": 1.6347429752349854,
+      "learning_rate": 7.484740751281187e-06,
+      "loss": 0.2362,
+      "step": 2700
+    },
+    {
+      "epoch": 117.3913043478261,
+      "eval_loss": 0.9330541491508484,
+      "eval_runtime": 0.4063,
+      "eval_samples_per_second": 24.614,
+      "eval_steps_per_second": 24.614,
+      "step": 2700
+    },
+    {
+      "Start_State_loss": 0.861186683177948,
+      "Start_State_runtime": 0.4124,
+      "Start_State_samples_per_second": 24.246,
+      "Start_State_steps_per_second": 24.246,
+      "epoch": 117.3913043478261,
+      "step": 2700
+    },
+    {
+      "Raw_Model_loss": 0.9330541491508484,
+      "Raw_Model_runtime": 0.4024,
+      "Raw_Model_samples_per_second": 24.852,
+      "Raw_Model_steps_per_second": 24.852,
+      "epoch": 117.3913043478261,
+      "step": 2700
+    },
+    {
+      "SWA_loss": 0.7649438977241516,
+      "SWA_runtime": 0.4267,
+      "SWA_samples_per_second": 23.437,
+      "SWA_steps_per_second": 23.437,
+      "epoch": 117.3913043478261,
+      "step": 2700
+    },
+    {
+      "EMA_loss": 0.8608808517456055,
+      "EMA_runtime": 0.4102,
+      "EMA_samples_per_second": 24.381,
+      "EMA_steps_per_second": 24.381,
+      "epoch": 117.3913043478261,
+      "step": 2700
     }
   ],
   "logging_steps": 10,
@@ -2491,7 +2636,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.568246037407334e+16,
+  "total_flos": 6.95112550820905e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null