Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f2359775ec058105a768a27e0aec2fd7b09c0fef450becc3fea6a2140d5551
+oid sha256:460e8e8695016d7fb3fe1981d689ac748c31bfbaa2f5af7cb550b10ae4a2bdf6
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b0e07d88b69f37af8463bb1ac2f6ff8e912db26c18c2ee123c3a1948596d38
+oid sha256:9f6dd162a8f76ef782100cbd4cc1329e64448d85f627b9bf81ba66e937483b4c
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0e93581e91c352d5ee493f505f8757c94a31fb5b16f71a9d85577535431525
+oid sha256:488cbcf14a0f8a4794af20845693e7c92cc4e0193e27f71cfb8b870a8f1fae2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b7c8be324c8b4289d82c59d6cbd2a46df58415895691106518590654dd09ba
+oid sha256:e87b12dd89c08406ca001c2f9dadca3ff34969fd8915b971b04b981fc47351e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7166205048561096,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 163.04347826086956,
+  "epoch": 169.56521739130434,
   "eval_steps": 150,
-  "global_step": 3750,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3632,6 +3632,151 @@
       "EMA_steps_per_second": 25.904,
       "epoch": 163.04347826086956,
       "step": 3750
+    },
+    {
+      "epoch": 163.47826086956522,
+      "grad_norm": 2.0019257068634033,
+      "learning_rate": 2.5259232470433596e-06,
+      "loss": 0.2364,
+      "step": 3760
+    },
+    {
+      "epoch": 163.91304347826087,
+      "grad_norm": 2.179541826248169,
+      "learning_rate": 2.525912484052346e-06,
+      "loss": 0.2379,
+      "step": 3770
+    },
+    {
+      "epoch": 164.34782608695653,
+      "grad_norm": 1.2639409303665161,
+      "learning_rate": 2.5259012204898387e-06,
+      "loss": 0.2234,
+      "step": 3780
+    },
+    {
+      "epoch": 164.7826086956522,
+      "grad_norm": 2.0140252113342285,
+      "learning_rate": 2.5258894563603038e-06,
+      "loss": 0.2327,
+      "step": 3790
+    },
+    {
+      "epoch": 165.2173913043478,
+      "grad_norm": 2.1268043518066406,
+      "learning_rate": 2.525877191668403e-06,
+      "loss": 0.2606,
+      "step": 3800
+    },
+    {
+      "epoch": 165.65217391304347,
+      "grad_norm": 1.9044567346572876,
+      "learning_rate": 2.525864426418998e-06,
+      "loss": 0.2372,
+      "step": 3810
+    },
+    {
+      "epoch": 166.08695652173913,
+      "grad_norm": 2.487705945968628,
+      "learning_rate": 2.5258511606171487e-06,
+      "loss": 0.1812,
+      "step": 3820
+    },
+    {
+      "epoch": 166.52173913043478,
+      "grad_norm": 2.743502616882324,
+      "learning_rate": 2.525837394268113e-06,
+      "loss": 0.2569,
+      "step": 3830
+    },
+    {
+      "epoch": 166.95652173913044,
+      "grad_norm": 1.6789222955703735,
+      "learning_rate": 2.5258231273773474e-06,
+      "loss": 0.2355,
+      "step": 3840
+    },
+    {
+      "epoch": 167.3913043478261,
+      "grad_norm": 2.9776694774627686,
+      "learning_rate": 2.525808359950507e-06,
+      "loss": 0.2192,
+      "step": 3850
+    },
+    {
+      "epoch": 167.82608695652175,
+      "grad_norm": 3.056367874145508,
+      "learning_rate": 2.525793091993445e-06,
+      "loss": 0.2178,
+      "step": 3860
+    },
+    {
+      "epoch": 168.2608695652174,
+      "grad_norm": 2.032916307449341,
+      "learning_rate": 2.5257773235122136e-06,
+      "loss": 0.2873,
+      "step": 3870
+    },
+    {
+      "epoch": 168.69565217391303,
+      "grad_norm": 1.8345348834991455,
+      "learning_rate": 2.5257610545130627e-06,
+      "loss": 0.2126,
+      "step": 3880
+    },
+    {
+      "epoch": 169.1304347826087,
+      "grad_norm": 2.1053850650787354,
+      "learning_rate": 2.52574428500244e-06,
+      "loss": 0.1979,
+      "step": 3890
+    },
+    {
+      "epoch": 169.56521739130434,
+      "grad_norm": 1.8270847797393799,
+      "learning_rate": 2.525727014986994e-06,
+      "loss": 0.245,
+      "step": 3900
+    },
+    {
+      "epoch": 169.56521739130434,
+      "eval_loss": 0.9649088978767395,
+      "eval_runtime": 0.4578,
+      "eval_samples_per_second": 21.844,
+      "eval_steps_per_second": 21.844,
+      "step": 3900
+    },
+    {
+      "Start_State_loss": 0.8609819412231445,
+      "Start_State_runtime": 0.3852,
+      "Start_State_samples_per_second": 25.962,
+      "Start_State_steps_per_second": 25.962,
+      "epoch": 169.56521739130434,
+      "step": 3900
+    },
+    {
+      "Raw_Model_loss": 0.9649088978767395,
+      "Raw_Model_runtime": 0.3849,
+      "Raw_Model_samples_per_second": 25.982,
+      "Raw_Model_steps_per_second": 25.982,
+      "epoch": 169.56521739130434,
+      "step": 3900
+    },
+    {
+      "SWA_loss": 0.7992776036262512,
+      "SWA_runtime": 0.386,
+      "SWA_samples_per_second": 25.91,
+      "SWA_steps_per_second": 25.91,
+      "epoch": 169.56521739130434,
+      "step": 3900
+    },
+    {
+      "EMA_loss": 0.8593554496765137,
+      "EMA_runtime": 0.3885,
+      "EMA_samples_per_second": 25.739,
+      "EMA_steps_per_second": 25.739,
+      "epoch": 169.56521739130434,
+      "step": 3900
     }
   ],
   "logging_steps": 10,
@@ -3651,7 +3796,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.668631592798618e+16,
+  "total_flos": 1.0061040993472512e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null