Training in progress, step 4650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5a6f82a282e6ee513038360740bfa6163feb4b1d4b1bb3319d6b0ef1f4751f
+oid sha256:7c2fa6d7c57abe80b81e686c5bb261331348a26463db489c0057496c21099267
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71d3e09cfa9bcbe2ed92701fe51af492bac444d4e688ae56a471982c181c9e9
+oid sha256:798f7293795a2261c83bf45e42597af80061bea9a6acf124906fd2023d47a1d7
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802e223144d189244ce5a768642009b3c15e29f14e41b4808f514470d4c7be6e
+oid sha256:4b03ef6d89f6c10452a8bc84393b1dc225e370d174364da48043ff472b287411
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e092ded0b8103aeaa278f39556d48ebee944cc0f4cd6e8f95b6ba39b7752813
+oid sha256:f96e2618e1c452343a3740c32bea2247d1da5a3f0e229791fe5ed8f1e4e8eb3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7166205048561096,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 195.65217391304347,
+  "epoch": 202.17391304347825,
   "eval_steps": 150,
-  "global_step": 4500,
+  "global_step": 4650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4357,6 +4357,151 @@
       "EMA_steps_per_second": 25.401,
       "epoch": 195.65217391304347,
       "step": 4500
+    },
+    {
+      "epoch": 196.08695652173913,
+      "grad_norm": 2.102900981903076,
+      "learning_rate": 1.5299080151617038e-06,
+      "loss": 0.2645,
+      "step": 4510
+    },
+    {
+      "epoch": 196.52173913043478,
+      "grad_norm": 2.1095998287200928,
+      "learning_rate": 1.5299014962042341e-06,
+      "loss": 0.2165,
+      "step": 4520
+    },
+    {
+      "epoch": 196.95652173913044,
+      "grad_norm": 2.1897032260894775,
+      "learning_rate": 1.5298946740592704e-06,
+      "loss": 0.2351,
+      "step": 4530
+    },
+    {
+      "epoch": 197.3913043478261,
+      "grad_norm": 1.8536592721939087,
+      "learning_rate": 1.5298875487295168e-06,
+      "loss": 0.2502,
+      "step": 4540
+    },
+    {
+      "epoch": 197.82608695652175,
+      "grad_norm": 1.948095679283142,
+      "learning_rate": 1.5298801202177976e-06,
+      "loss": 0.2185,
+      "step": 4550
+    },
+    {
+      "epoch": 198.2608695652174,
+      "grad_norm": 2.084287643432617,
+      "learning_rate": 1.529872388527057e-06,
+      "loss": 0.2297,
+      "step": 4560
+    },
+    {
+      "epoch": 198.69565217391303,
+      "grad_norm": 1.5842596292495728,
+      "learning_rate": 1.5298643536603602e-06,
+      "loss": 0.2311,
+      "step": 4570
+    },
+    {
+      "epoch": 199.1304347826087,
+      "grad_norm": 2.214616537094116,
+      "learning_rate": 1.5298560156208912e-06,
+      "loss": 0.1927,
+      "step": 4580
+    },
+    {
+      "epoch": 199.56521739130434,
+      "grad_norm": 1.5991625785827637,
+      "learning_rate": 1.5298473744119554e-06,
+      "loss": 0.2538,
+      "step": 4590
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 3.232147455215454,
+      "learning_rate": 1.5298384300369777e-06,
+      "loss": 0.1878,
+      "step": 4600
+    },
+    {
+      "epoch": 200.43478260869566,
+      "grad_norm": 1.8239914178848267,
+      "learning_rate": 1.5298291824995035e-06,
+      "loss": 0.2398,
+      "step": 4610
+    },
+    {
+      "epoch": 200.8695652173913,
+      "grad_norm": 1.616271734237671,
+      "learning_rate": 1.5298196318031983e-06,
+      "loss": 0.2276,
+      "step": 4620
+    },
+    {
+      "epoch": 201.30434782608697,
+      "grad_norm": 1.999419093132019,
+      "learning_rate": 1.5298097779518473e-06,
+      "loss": 0.2271,
+      "step": 4630
+    },
+    {
+      "epoch": 201.7391304347826,
+      "grad_norm": 2.4747536182403564,
+      "learning_rate": 1.5297996209493567e-06,
+      "loss": 0.1894,
+      "step": 4640
+    },
+    {
+      "epoch": 202.17391304347825,
+      "grad_norm": 1.546221137046814,
+      "learning_rate": 1.5297891607997524e-06,
+      "loss": 0.2233,
+      "step": 4650
+    },
+    {
+      "epoch": 202.17391304347825,
+      "eval_loss": 0.9768635034561157,
+      "eval_runtime": 0.3903,
+      "eval_samples_per_second": 25.62,
+      "eval_steps_per_second": 25.62,
+      "step": 4650
+    },
+    {
+      "Start_State_loss": 0.8609819412231445,
+      "Start_State_runtime": 0.3895,
+      "Start_State_samples_per_second": 25.672,
+      "Start_State_steps_per_second": 25.672,
+      "epoch": 202.17391304347825,
+      "step": 4650
+    },
+    {
+      "Raw_Model_loss": 0.9768635034561157,
+      "Raw_Model_runtime": 0.3902,
+      "Raw_Model_samples_per_second": 25.625,
+      "Raw_Model_steps_per_second": 25.625,
+      "epoch": 202.17391304347825,
+      "step": 4650
+    },
+    {
+      "SWA_loss": 0.8143197894096375,
+      "SWA_runtime": 0.3924,
+      "SWA_samples_per_second": 25.484,
+      "SWA_steps_per_second": 25.484,
+      "epoch": 202.17391304347825,
+      "step": 4650
+    },
+    {
+      "EMA_loss": 0.8591374158859253,
+      "EMA_runtime": 0.3893,
+      "EMA_samples_per_second": 25.688,
+      "EMA_steps_per_second": 25.688,
+      "epoch": 202.17391304347825,
+      "step": 4650
     }
   ],
   "logging_steps": 10,
@@ -4376,7 +4521,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1587388919393485e+17,
+  "total_flos": 1.1967994202384794e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null