Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d009fa9acb2b78f813d89270550f919a3f4b577a7460370dfe12fa03ff7af2
+oid sha256:024e31774972ff3820090308d6a53b1687a81cbc1c1e120faa23fe6f2736a792
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2947112888e0b0a163210d845429170c50382af84dbf994949e4e6f9ab23162a
+oid sha256:3e0e2871711a7f1cbd51c0e9c8d6a1661a58c09dd8132528c56df9afa8fc214b
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4799eb2d919a7e0ac96b4d1b7ad46d7dd1d0d16fcd886aff21cf516bc01cd21
+oid sha256:44c880a200501ba0b67082f3081094988ba079c54e1ac9a1deb1603230cd2f05
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456186d80ba1cb08cf09751e950cd6ffaa49f7521ab8872f1128630a6572e66b
+oid sha256:7556a6d66035d11bc10a3374d5ff7bbff46c4fa1cc48d9d21c51bdde6df224e5
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b44fb2a9542e90532b93ebac4a5e8666f98d6d7698a2bf80999186ee0ee3983
+oid sha256:6901005092102ab95f1173ef27f9dc91cdbf890535e1b1d5bd4fdb92b6125b7d
 size 1465

last-checkpoint/trainer_state.json

@@ -1,262 +1,96 @@
 {
-  "best_global_step": 1500,
-  "best_metric": 50.35,
-  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1500",
-  "epoch": 0.517821696729093,
+  "best_global_step": 500,
+  "best_metric": 49.82,
+  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-500",
+  "epoch": 0.17260723224303098,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0172607232243031,
-      "grad_norm": 4.3670196533203125,
+      "grad_norm": 3.8177006244659424,
       "learning_rate": 1.2250000000000001e-06,
-      "loss": 0.4652,
+      "loss": 0.4507,
       "step": 50
     },
     {
       "epoch": 0.0345214464486062,
-      "grad_norm": 2.652766227722168,
+      "grad_norm": Infinity,
       "learning_rate": 2.475e-06,
-      "loss": 0.4123,
+      "loss": 0.4331,
       "step": 100
     },
     {
       "epoch": 0.051782169672909294,
-      "grad_norm": 2.76326060295105,
+      "grad_norm": 2.9417564868927,
       "learning_rate": 3.7250000000000003e-06,
-      "loss": 0.3568,
+      "loss": 0.4042,
       "step": 150
     },
     {
       "epoch": 0.0690428928972124,
-      "grad_norm": 2.748229503631592,
+      "grad_norm": 2.8877062797546387,
       "learning_rate": 4.975000000000001e-06,
-      "loss": 0.3339,
+      "loss": 0.397,
       "step": 200
     },
     {
       "epoch": 0.08630361612151549,
-      "grad_norm": 3.13151216506958,
+      "grad_norm": 3.343304395675659,
       "learning_rate": 4.956203074722918e-06,
-      "loss": 0.3069,
+      "loss": 0.3892,
       "step": 250
     },
     {
       "epoch": 0.10356433934581859,
-      "grad_norm": 3.117373466491699,
+      "grad_norm": 3.0275661945343018,
       "learning_rate": 4.911512334644262e-06,
-      "loss": 0.2919,
+      "loss": 0.3891,
       "step": 300
     },
     {
       "epoch": 0.12082506257012168,
-      "grad_norm": 2.7164409160614014,
+      "grad_norm": 3.045884847640991,
       "learning_rate": 4.866821594565607e-06,
-      "loss": 0.2472,
+      "loss": 0.3656,
       "step": 350
     },
     {
       "epoch": 0.1380857857944248,
-      "grad_norm": 2.6755988597869873,
+      "grad_norm": 2.7904183864593506,
       "learning_rate": 4.82213085448695e-06,
-      "loss": 0.228,
+      "loss": 0.365,
       "step": 400
     },
     {
       "epoch": 0.15534650901872787,
-      "grad_norm": 3.35945987701416,
+      "grad_norm": 3.6787497997283936,
       "learning_rate": 4.777440114408295e-06,
-      "loss": 0.206,
+      "loss": 0.3594,
       "step": 450
     },
     {
       "epoch": 0.17260723224303098,
-      "grad_norm": 3.0900039672851562,
+      "grad_norm": 3.1564106941223145,
       "learning_rate": 4.732749374329639e-06,
-      "loss": 0.2078,
+      "loss": 0.3719,
       "step": 500
     },
     {
       "epoch": 0.17260723224303098,
-      "eval_gen_len": 56.09703315881326,
-      "eval_loss": 0.716594398021698,
-      "eval_rouge1": 49.17,
-      "eval_rouge2": 34.51,
-      "eval_rougeL": 42.36,
-      "eval_rougeLsum": 42.96,
-      "eval_runtime": 3665.3213,
-      "eval_samples_per_second": 1.563,
-      "eval_steps_per_second": 0.391,
+      "eval_gen_len": 55.68621291448517,
+      "eval_loss": 0.5641192197799683,
+      "eval_rouge1": 49.82,
+      "eval_rouge2": 35.56,
+      "eval_rougeL": 43.37,
+      "eval_rougeLsum": 43.9,
+      "eval_runtime": 5387.3225,
+      "eval_samples_per_second": 1.064,
+      "eval_steps_per_second": 0.266,
       "step": 500
-    },
-    {
-      "epoch": 0.1898679554673341,
-      "grad_norm": 3.162104606628418,
-      "learning_rate": 4.688058634250984e-06,
-      "loss": 0.2517,
-      "step": 550
-    },
-    {
-      "epoch": 0.20712867869163717,
-      "grad_norm": 3.1047537326812744,
-      "learning_rate": 4.643367894172328e-06,
-      "loss": 0.2498,
-      "step": 600
-    },
-    {
-      "epoch": 0.22438940191594028,
-      "grad_norm": 14.000798225402832,
-      "learning_rate": 4.598677154093672e-06,
-      "loss": 0.2641,
-      "step": 650
-    },
-    {
-      "epoch": 0.24165012514024337,
-      "grad_norm": 2.8678536415100098,
-      "learning_rate": 4.553986414015016e-06,
-      "loss": 0.2483,
-      "step": 700
-    },
-    {
-      "epoch": 0.2589108483645465,
-      "grad_norm": 2.264373302459717,
-      "learning_rate": 4.509295673936361e-06,
-      "loss": 0.2488,
-      "step": 750
-    },
-    {
-      "epoch": 0.2761715715888496,
-      "grad_norm": 2.9525506496429443,
-      "learning_rate": 4.464604933857705e-06,
-      "loss": 0.2489,
-      "step": 800
-    },
-    {
-      "epoch": 0.2934322948131527,
-      "grad_norm": 3.6344923973083496,
-      "learning_rate": 4.419914193779049e-06,
-      "loss": 0.25,
-      "step": 850
-    },
-    {
-      "epoch": 0.31069301803745575,
-      "grad_norm": 2.6605496406555176,
-      "learning_rate": 4.375223453700393e-06,
-      "loss": 0.2501,
-      "step": 900
-    },
-    {
-      "epoch": 0.32795374126175886,
-      "grad_norm": 2.7597107887268066,
-      "learning_rate": 4.330532713621738e-06,
-      "loss": 0.2349,
-      "step": 950
-    },
-    {
-      "epoch": 0.34521446448606197,
-      "grad_norm": 6.881639003753662,
-      "learning_rate": 4.285841973543082e-06,
-      "loss": 0.2758,
-      "step": 1000
-    },
-    {
-      "epoch": 0.34521446448606197,
-      "eval_gen_len": 53.343979057591625,
-      "eval_loss": 0.6903564929962158,
-      "eval_rouge1": 49.95,
-      "eval_rouge2": 34.95,
-      "eval_rougeL": 43.07,
-      "eval_rougeLsum": 43.54,
-      "eval_runtime": 3366.7702,
-      "eval_samples_per_second": 1.702,
-      "eval_steps_per_second": 0.426,
-      "step": 1000
-    },
-    {
-      "epoch": 0.3624751877103651,
-      "grad_norm": 4.618715286254883,
-      "learning_rate": 4.241151233464427e-06,
-      "loss": 0.4252,
-      "step": 1050
-    },
-    {
-      "epoch": 0.3797359109346682,
-      "grad_norm": 3.20849871635437,
-      "learning_rate": 4.19646049338577e-06,
-      "loss": 0.4157,
-      "step": 1100
-    },
-    {
-      "epoch": 0.39699663415897124,
-      "grad_norm": 2.707479238510132,
-      "learning_rate": 4.151769753307115e-06,
-      "loss": 0.4099,
-      "step": 1150
-    },
-    {
-      "epoch": 0.41425735738327435,
-      "grad_norm": 3.7561733722686768,
-      "learning_rate": 4.107079013228459e-06,
-      "loss": 0.3867,
-      "step": 1200
-    },
-    {
-      "epoch": 0.43151808060757746,
-      "grad_norm": 3.146683692932129,
-      "learning_rate": 4.062388273149804e-06,
-      "loss": 0.3949,
-      "step": 1250
-    },
-    {
-      "epoch": 0.44877880383188057,
-      "grad_norm": 2.949275255203247,
-      "learning_rate": 4.017697533071148e-06,
-      "loss": 0.4018,
-      "step": 1300
-    },
-    {
-      "epoch": 0.4660395270561837,
-      "grad_norm": 3.40734601020813,
-      "learning_rate": 3.973006792992492e-06,
-      "loss": 0.4169,
-      "step": 1350
-    },
-    {
-      "epoch": 0.48330025028048673,
-      "grad_norm": 3.736387014389038,
-      "learning_rate": 3.928316052913836e-06,
-      "loss": 0.3897,
-      "step": 1400
-    },
-    {
-      "epoch": 0.5005609735047899,
-      "grad_norm": 3.2508416175842285,
-      "learning_rate": 3.883625312835181e-06,
-      "loss": 0.4062,
-      "step": 1450
-    },
-    {
-      "epoch": 0.517821696729093,
-      "grad_norm": 2.803189754486084,
-      "learning_rate": 3.838934572756525e-06,
-      "loss": 0.4158,
-      "step": 1500
-    },
-    {
-      "epoch": 0.517821696729093,
-      "eval_gen_len": 54.936474694589876,
-      "eval_loss": 0.5606315732002258,
-      "eval_rouge1": 50.35,
-      "eval_rouge2": 36.21,
-      "eval_rougeL": 43.87,
-      "eval_rougeLsum": 44.34,
-      "eval_runtime": 3383.5495,
-      "eval_samples_per_second": 1.693,
-      "eval_steps_per_second": 0.424,
-      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -285,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.1502595309568e+16,
+  "total_flos": 1.7167531769856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65214ff5af820f90cc07ae61977d659e8042ee6cf4c1339d9bceafffaa1e0bf
+oid sha256:19ffefef99189ef3675e3a83b1d4b98cef78e97ab875630a491095265a0370a0
 size 6033