Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2e2a7a69875b07ff44bb7705aae92322fd74f2cf5b3c3fc0ce5ff7a536e93d
+oid sha256:f00f705443798530a93088164d1ed8aabdfd21332275607cd477302b6b6d67ec
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84fb90d40c7774ad8b3a73bff13e4207b857c5fe6687515354ea196f62a8ce98
+oid sha256:e9f7d33cfd664ae3ee1de3da2ea9ab10a8a8f8d352de893d2aaa7dd333c7a8ee
 size 3250759392

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25f0989e8e91af9e8637f85210bc8171a9ace36462fb90ce2e6d3e8f7ae2fa2
+oid sha256:0c06cd809d24fd6588d7182ae83a04c71980b17187bed1fed3de7b640efbf43a
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b479a091e6482cdb8085a5931fe45bae60997ab8939a20b371d61d6be6f7199
+oid sha256:d98840f1bd538384bd346ab5c327bc2442f29a1ac444804968cb107c6bc2fcc7
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5955ff7ae3c292679cb2d15dfab21a83841dbd226cd7e259de6ef2a4c905fc
+oid sha256:6901005092102ab95f1173ef27f9dc91cdbf890535e1b1d5bd4fdb92b6125b7d
 size 1465

last-checkpoint/trainer_state.json

@@ -1,179 +1,96 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 50.2,
-  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-1000",
-  "epoch": 0.34521446448606197,
+  "best_global_step": 500,
+  "best_metric": 49.17,
+  "best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-500",
+  "epoch": 0.17260723224303098,
   "eval_steps": 500,
-  "global_step": 1000,
+  "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": 3.641310691833496,
+      "grad_norm": 4.3670196533203125,
       "learning_rate": 1.2250000000000001e-06,
-      "loss": 0.4528,
+      "loss": 0.4652,
       "step": 50
     },
     {
       "epoch": 0.0345214464486062,
-      "grad_norm": 2.5743606090545654,
+      "grad_norm": 2.652766227722168,
       "learning_rate": 2.475e-06,
-      "loss": 0.4354,
+      "loss": 0.4123,
       "step": 100
     },
     {
       "epoch": 0.051782169672909294,
-      "grad_norm": 2.6847357749938965,
+      "grad_norm": 2.76326060295105,
       "learning_rate": 3.7250000000000003e-06,
-      "loss": 0.4015,
+      "loss": 0.3568,
       "step": 150
     },
     {
       "epoch": 0.0690428928972124,
-      "grad_norm": 2.5933823585510254,
+      "grad_norm": 2.748229503631592,
       "learning_rate": 4.975000000000001e-06,
-      "loss": 0.3952,
+      "loss": 0.3339,
       "step": 200
     },
     {
       "epoch": 0.08630361612151549,
-      "grad_norm": 2.950077772140503,
+      "grad_norm": 3.13151216506958,
       "learning_rate": 4.956203074722918e-06,
-      "loss": 0.3744,
+      "loss": 0.3069,
       "step": 250
     },
     {
       "epoch": 0.10356433934581859,
-      "grad_norm": 2.7843117713928223,
+      "grad_norm": 3.117373466491699,
       "learning_rate": 4.911512334644262e-06,
-      "loss": 0.3613,
+      "loss": 0.2919,
       "step": 300
     },
     {
       "epoch": 0.12082506257012168,
-      "grad_norm": 2.70448637008667,
+      "grad_norm": 2.7164409160614014,
       "learning_rate": 4.866821594565607e-06,
-      "loss": 0.321,
+      "loss": 0.2472,
       "step": 350
     },
     {
       "epoch": 0.1380857857944248,
-      "grad_norm": 2.6096677780151367,
+      "grad_norm": 2.6755988597869873,
       "learning_rate": 4.82213085448695e-06,
-      "loss": 0.3028,
+      "loss": 0.228,
       "step": 400
     },
     {
       "epoch": 0.15534650901872787,
-      "grad_norm": 9.160786628723145,
+      "grad_norm": 3.35945987701416,
       "learning_rate": 4.777440114408295e-06,
-      "loss": 0.2841,
+      "loss": 0.206,
       "step": 450
     },
     {
       "epoch": 0.17260723224303098,
-      "grad_norm": 3.1601881980895996,
+      "grad_norm": 3.0900039672851562,
       "learning_rate": 4.732749374329639e-06,
-      "loss": 0.2866,
+      "loss": 0.2078,
       "step": 500
     },
     {
       "epoch": 0.17260723224303098,
-      "eval_gen_len": 56.13717277486911,
-      "eval_loss": 0.6366580128669739,
-      "eval_rouge1": 49.45,
-      "eval_rouge2": 34.98,
-      "eval_rougeL": 42.83,
-      "eval_rougeLsum": 43.35,
-      "eval_runtime": 3578.4556,
-      "eval_samples_per_second": 1.601,
-      "eval_steps_per_second": 0.4,
+      "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,
       "step": 500
-    },
-    {
-      "epoch": 0.1898679554673341,
-      "grad_norm": 3.390817642211914,
-      "learning_rate": 4.688058634250984e-06,
-      "loss": 0.3289,
-      "step": 550
-    },
-    {
-      "epoch": 0.20712867869163717,
-      "grad_norm": 2.9106905460357666,
-      "learning_rate": 4.643367894172328e-06,
-      "loss": 0.3245,
-      "step": 600
-    },
-    {
-      "epoch": 0.22438940191594028,
-      "grad_norm": 11.3765287399292,
-      "learning_rate": 4.598677154093672e-06,
-      "loss": 0.3335,
-      "step": 650
-    },
-    {
-      "epoch": 0.24165012514024337,
-      "grad_norm": 2.70393967628479,
-      "learning_rate": 4.553986414015016e-06,
-      "loss": 0.3212,
-      "step": 700
-    },
-    {
-      "epoch": 0.2589108483645465,
-      "grad_norm": 2.325925827026367,
-      "learning_rate": 4.509295673936361e-06,
-      "loss": 0.3188,
-      "step": 750
-    },
-    {
-      "epoch": 0.2761715715888496,
-      "grad_norm": 2.699869155883789,
-      "learning_rate": 4.464604933857705e-06,
-      "loss": 0.3198,
-      "step": 800
-    },
-    {
-      "epoch": 0.2934322948131527,
-      "grad_norm": 3.212961435317993,
-      "learning_rate": 4.419914193779049e-06,
-      "loss": 0.3158,
-      "step": 850
-    },
-    {
-      "epoch": 0.31069301803745575,
-      "grad_norm": 2.4674649238586426,
-      "learning_rate": 4.375223453700393e-06,
-      "loss": 0.3145,
-      "step": 900
-    },
-    {
-      "epoch": 0.32795374126175886,
-      "grad_norm": 2.870105504989624,
-      "learning_rate": 4.330532713621738e-06,
-      "loss": 0.2977,
-      "step": 950
-    },
-    {
-      "epoch": 0.34521446448606197,
-      "grad_norm": 5.365257263183594,
-      "learning_rate": 4.285841973543082e-06,
-      "loss": 0.3293,
-      "step": 1000
-    },
-    {
-      "epoch": 0.34521446448606197,
-      "eval_gen_len": 52.97696335078534,
-      "eval_loss": 0.6229833960533142,
-      "eval_rouge1": 50.2,
-      "eval_rouge2": 35.42,
-      "eval_rougeL": 43.42,
-      "eval_rougeLsum": 43.84,
-      "eval_runtime": 3432.2153,
-      "eval_samples_per_second": 1.669,
-      "eval_steps_per_second": 0.418,
-      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -202,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4335063539712e+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 sha256:7f20b49f2dc6c4d7679794c60ed6790a8246180ab315db49774772c1eaa1eee7
+oid sha256:f65214ff5af820f90cc07ae61977d659e8042ee6cf4c1339d9bceafffaa1e0bf
 size 6033