Training in progress, step 2550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7314d8b5f35930722e1c3d90a6061192742967a1457d59859792a0878fce57
+oid sha256:16a48e299ffea4a1305480644e0252c4aab5e02d9191b6e951f282025c021c36
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e4902bbfa6e4e56f6e17ab398c622f809713c649baa3c6fd399c0f05448a5f
+oid sha256:ccb7656d0058945a544e068c4c181cbcbae03cf7066df76778cb4579b9066242
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684fee310519fed9cc8ee66dc9698ba16f4e9489a577756f84e7b21aa51e01d4
+oid sha256:33335d8e454fa636f80bfcf35b73daf17e2d9682ef2741d0ad1097e25ee4742d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3530fffdeb6293174ae0b25b4bed0ccc682e606b6e29d3d50fec77e3192eef
+oid sha256:6f98b757d648be3e63607e2156858bad579d6a12d490a3cb2c8748d9ae2cce45
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7177689671516418,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 104.34782608695652,
+  "epoch": 110.8695652173913,
   "eval_steps": 150,
-  "global_step": 2400,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2327,6 +2327,151 @@
       "EMA_steps_per_second": 24.683,
       "epoch": 104.34782608695652,
       "step": 2400
+    },
+    {
+      "epoch": 104.78260869565217,
+      "grad_norm": 2.10827898979187,
+      "learning_rate": 7.486913639731043e-06,
+      "loss": 0.2495,
+      "step": 2410
+    },
+    {
+      "epoch": 105.21739130434783,
+      "grad_norm": 2.025355815887451,
+      "learning_rate": 7.48685947932756e-06,
+      "loss": 0.2637,
+      "step": 2420
+    },
+    {
+      "epoch": 105.65217391304348,
+      "grad_norm": 1.9276680946350098,
+      "learning_rate": 7.4868038353494355e-06,
+      "loss": 0.2603,
+      "step": 2430
+    },
+    {
+      "epoch": 106.08695652173913,
+      "grad_norm": 2.324167490005493,
+      "learning_rate": 7.486746707818724e-06,
+      "loss": 0.2141,
+      "step": 2440
+    },
+    {
+      "epoch": 106.52173913043478,
+      "grad_norm": 1.4006412029266357,
+      "learning_rate": 7.486688096758069e-06,
+      "loss": 0.2816,
+      "step": 2450
+    },
+    {
+      "epoch": 106.95652173913044,
+      "grad_norm": 1.8922216892242432,
+      "learning_rate": 7.486628002190702e-06,
+      "loss": 0.2444,
+      "step": 2460
+    },
+    {
+      "epoch": 107.3913043478261,
+      "grad_norm": 2.3611834049224854,
+      "learning_rate": 7.486566424140442e-06,
+      "loss": 0.3039,
+      "step": 2470
+    },
+    {
+      "epoch": 107.82608695652173,
+      "grad_norm": 2.2470717430114746,
+      "learning_rate": 7.486503362631699e-06,
+      "loss": 0.2188,
+      "step": 2480
+    },
+    {
+      "epoch": 108.26086956521739,
+      "grad_norm": 2.0604355335235596,
+      "learning_rate": 7.486438817689465e-06,
+      "loss": 0.2706,
+      "step": 2490
+    },
+    {
+      "epoch": 108.69565217391305,
+      "grad_norm": 1.6355359554290771,
+      "learning_rate": 7.486372789339326e-06,
+      "loss": 0.2454,
+      "step": 2500
+    },
+    {
+      "epoch": 109.1304347826087,
+      "grad_norm": 1.6156138181686401,
+      "learning_rate": 7.486305277607452e-06,
+      "loss": 0.2437,
+      "step": 2510
+    },
+    {
+      "epoch": 109.56521739130434,
+      "grad_norm": 1.3432440757751465,
+      "learning_rate": 7.486236282520606e-06,
+      "loss": 0.2309,
+      "step": 2520
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 3.2272891998291016,
+      "learning_rate": 7.48616580410613e-06,
+      "loss": 0.2874,
+      "step": 2530
+    },
+    {
+      "epoch": 110.43478260869566,
+      "grad_norm": 1.7123788595199585,
+      "learning_rate": 7.486093842391963e-06,
+      "loss": 0.2452,
+      "step": 2540
+    },
+    {
+      "epoch": 110.8695652173913,
+      "grad_norm": 1.8407248258590698,
+      "learning_rate": 7.486020397406629e-06,
+      "loss": 0.2698,
+      "step": 2550
+    },
+    {
+      "epoch": 110.8695652173913,
+      "eval_loss": 0.9264782071113586,
+      "eval_runtime": 0.5916,
+      "eval_samples_per_second": 16.903,
+      "eval_steps_per_second": 16.903,
+      "step": 2550
+    },
+    {
+      "Start_State_loss": 0.861186683177948,
+      "Start_State_runtime": 0.4032,
+      "Start_State_samples_per_second": 24.805,
+      "Start_State_steps_per_second": 24.805,
+      "epoch": 110.8695652173913,
+      "step": 2550
+    },
+    {
+      "Raw_Model_loss": 0.9264782071113586,
+      "Raw_Model_runtime": 0.4014,
+      "Raw_Model_samples_per_second": 24.913,
+      "Raw_Model_steps_per_second": 24.913,
+      "epoch": 110.8695652173913,
+      "step": 2550
+    },
+    {
+      "SWA_loss": 0.759516716003418,
+      "SWA_runtime": 0.403,
+      "SWA_samples_per_second": 24.814,
+      "SWA_steps_per_second": 24.814,
+      "epoch": 110.8695652173913,
+      "step": 2550
+    },
+    {
+      "EMA_loss": 0.8597530126571655,
+      "EMA_runtime": 0.415,
+      "EMA_samples_per_second": 24.098,
+      "EMA_steps_per_second": 24.098,
+      "epoch": 110.8695652173913,
+      "step": 2550
     }
   ],
   "logging_steps": 10,
@@ -2346,7 +2491,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.183025621814477e+16,
+  "total_flos": 6.568246037407334e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null