Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64427f25569a563b8c2defbd84ca69ba4d90afd505c9e406a4c8f353022714a8
+oid sha256:9c5d79e8c2e94c67533fc70310de79aa3786b10184d51dc840e2054df304b736
 size 959732416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9fe8d213c768c62a0886a9765a45bf43aa8b4e68e16590e5b09647c80ca6fc6
+oid sha256:d37ef3d72b111b30b960c34f8c87d69674e7593e24d93b982e48b58f9fae6871
 size 1919732806

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e900a969e8846016f93435d082cd2003d0d6d8a749d2feaf16f2a2d17a65f38
+oid sha256:9c881ad54e2aae8feeb160e05a97e39cf1c147f9aae0937a1b7e41a0710f93d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e84bdec20434ed7e461167492f3ba162916331ef4833923d73a78f7731f8135
+oid sha256:08c589f3acbeec5c6e36834591171153e8af682ebbd66860ce42dbcde5e025a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,267 +1,95 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 1.676727028839705,
   "eval_steps": 500,
-  "global_step": 14910,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1676727028839705,
-      "grad_norm": 0.24329866468906403,
+      "grad_norm": 0.5760945677757263,
       "learning_rate": 4.83232729711603e-05,
-      "loss": 0.2725,
+      "loss": 0.2766,
       "step": 500
     },
     {
       "epoch": 0.335345405767941,
-      "grad_norm": 0.3848712146282196,
+      "grad_norm": 0.3646267056465149,
       "learning_rate": 4.6646545942320594e-05,
-      "loss": 0.2125,
+      "loss": 0.2008,
       "step": 1000
     },
     {
       "epoch": 0.5030181086519114,
-      "grad_norm": 0.3457760214805603,
+      "grad_norm": 0.3581697344779968,
       "learning_rate": 4.4969818913480886e-05,
-      "loss": 0.1794,
+      "loss": 0.1872,
       "step": 1500
     },
     {
       "epoch": 0.670690811535882,
-      "grad_norm": 0.4547400176525116,
+      "grad_norm": 0.26507869362831116,
       "learning_rate": 4.3293091884641186e-05,
-      "loss": 0.1597,
+      "loss": 0.164,
       "step": 2000
     },
     {
       "epoch": 0.8383635144198525,
-      "grad_norm": 0.37468263506889343,
+      "grad_norm": 0.2440381944179535,
       "learning_rate": 4.161636485580148e-05,
-      "loss": 0.1498,
+      "loss": 0.1504,
       "step": 2500
     },
     {
       "epoch": 1.0,
       "eval_gen_len": 100.0,
-      "eval_loss": 0.11297082155942917,
-      "eval_rouge1": 0.1508,
-      "eval_rouge2": 0.1508,
-      "eval_rougeL": 0.1508,
-      "eval_rougeLsum": 0.1508,
-      "eval_runtime": 1532.6018,
-      "eval_samples_per_second": 0.865,
-      "eval_steps_per_second": 0.217,
+      "eval_loss": 0.10272549837827682,
+      "eval_rouge1": 0.2262,
+      "eval_rouge2": 0.2262,
+      "eval_rougeL": 0.2262,
+      "eval_rougeLsum": 0.2262,
+      "eval_runtime": 1543.4357,
+      "eval_samples_per_second": 0.859,
+      "eval_steps_per_second": 0.215,
       "step": 2982
     },
     {
       "epoch": 1.0060362173038229,
-      "grad_norm": 0.40761449933052063,
+      "grad_norm": 0.48001933097839355,
       "learning_rate": 3.993963782696177e-05,
-      "loss": 0.1293,
+      "loss": 0.1343,
       "step": 3000
     },
     {
       "epoch": 1.1737089201877935,
-      "grad_norm": 0.3620559573173523,
+      "grad_norm": 0.47931984066963196,
       "learning_rate": 3.826291079812207e-05,
-      "loss": 0.1038,
+      "loss": 0.0978,
       "step": 3500
     },
     {
       "epoch": 1.341381623071764,
-      "grad_norm": 0.3626340925693512,
+      "grad_norm": 0.42881467938423157,
       "learning_rate": 3.658618376928236e-05,
-      "loss": 0.0899,
+      "loss": 0.0866,
       "step": 4000
     },
     {
       "epoch": 1.5090543259557343,
-      "grad_norm": 0.5226974487304688,
+      "grad_norm": 0.4142566919326782,
       "learning_rate": 3.490945674044266e-05,
-      "loss": 0.0818,
+      "loss": 0.0882,
       "step": 4500
     },
     {
       "epoch": 1.676727028839705,
-      "grad_norm": 0.4590921700000763,
+      "grad_norm": 0.13182227313518524,
       "learning_rate": 3.323272971160295e-05,
-      "loss": 0.0746,
+      "loss": 0.0759,
       "step": 5000
-    },
-    {
-      "epoch": 1.8443997317236756,
-      "grad_norm": 0.31091028451919556,
-      "learning_rate": 3.1556002682763246e-05,
-      "loss": 0.0668,
-      "step": 5500
-    },
-    {
-      "epoch": 2.0,
-      "eval_gen_len": 100.0,
-      "eval_loss": 0.05176199600100517,
-      "eval_rouge1": 2.443,
-      "eval_rouge2": 1.3413,
-      "eval_rougeL": 2.4246,
-      "eval_rougeLsum": 2.4731,
-      "eval_runtime": 1529.3226,
-      "eval_samples_per_second": 0.867,
-      "eval_steps_per_second": 0.217,
-      "step": 5964
-    },
-    {
-      "epoch": 2.0120724346076457,
-      "grad_norm": 0.409631609916687,
-      "learning_rate": 2.9879275653923545e-05,
-      "loss": 0.0591,
-      "step": 6000
-    },
-    {
-      "epoch": 2.1797451374916164,
-      "grad_norm": 0.44650885462760925,
-      "learning_rate": 2.8202548625083835e-05,
-      "loss": 0.0408,
-      "step": 6500
-    },
-    {
-      "epoch": 2.347417840375587,
-      "grad_norm": 0.3755093812942505,
-      "learning_rate": 2.6525821596244134e-05,
-      "loss": 0.0376,
-      "step": 7000
-    },
-    {
-      "epoch": 2.515090543259557,
-      "grad_norm": 0.2583145499229431,
-      "learning_rate": 2.4849094567404426e-05,
-      "loss": 0.0342,
-      "step": 7500
-    },
-    {
-      "epoch": 2.682763246143528,
-      "grad_norm": 0.5501976609230042,
-      "learning_rate": 2.3172367538564725e-05,
-      "loss": 0.0317,
-      "step": 8000
-    },
-    {
-      "epoch": 2.8504359490274984,
-      "grad_norm": 0.3406773507595062,
-      "learning_rate": 2.1495640509725018e-05,
-      "loss": 0.0284,
-      "step": 8500
-    },
-    {
-      "epoch": 3.0,
-      "eval_gen_len": 100.0,
-      "eval_loss": 0.02168501727283001,
-      "eval_rouge1": 5.9838,
-      "eval_rouge2": 3.3142,
-      "eval_rougeL": 5.9543,
-      "eval_rougeLsum": 5.9938,
-      "eval_runtime": 1529.7745,
-      "eval_samples_per_second": 0.867,
-      "eval_steps_per_second": 0.217,
-      "step": 8946
-    },
-    {
-      "epoch": 3.0181086519114686,
-      "grad_norm": 0.08470600098371506,
-      "learning_rate": 1.9818913480885314e-05,
-      "loss": 0.0248,
-      "step": 9000
-    },
-    {
-      "epoch": 3.1857813547954392,
-      "grad_norm": 0.2213999181985855,
-      "learning_rate": 1.814218645204561e-05,
-      "loss": 0.0171,
-      "step": 9500
-    },
-    {
-      "epoch": 3.35345405767941,
-      "grad_norm": 0.25770503282546997,
-      "learning_rate": 1.6465459423205902e-05,
-      "loss": 0.0164,
-      "step": 10000
-    },
-    {
-      "epoch": 3.52112676056338,
-      "grad_norm": 0.18832048773765564,
-      "learning_rate": 1.4788732394366198e-05,
-      "loss": 0.0145,
-      "step": 10500
-    },
-    {
-      "epoch": 3.6887994634473507,
-      "grad_norm": 0.2905516028404236,
-      "learning_rate": 1.3112005365526492e-05,
-      "loss": 0.0136,
-      "step": 11000
-    },
-    {
-      "epoch": 3.8564721663313213,
-      "grad_norm": 0.187967449426651,
-      "learning_rate": 1.1435278336686788e-05,
-      "loss": 0.0126,
-      "step": 11500
-    },
-    {
-      "epoch": 4.0,
-      "eval_gen_len": 100.0,
-      "eval_loss": 0.010295581072568893,
-      "eval_rouge1": 11.5414,
-      "eval_rouge2": 6.9713,
-      "eval_rougeL": 11.5097,
-      "eval_rougeLsum": 11.6223,
-      "eval_runtime": 1527.8852,
-      "eval_samples_per_second": 0.868,
-      "eval_steps_per_second": 0.217,
-      "step": 11928
-    },
-    {
-      "epoch": 4.0241448692152915,
-      "grad_norm": 0.2498534917831421,
-      "learning_rate": 9.758551307847083e-06,
-      "loss": 0.0112,
-      "step": 12000
-    },
-    {
-      "epoch": 4.1918175720992625,
-      "grad_norm": 0.2614792585372925,
-      "learning_rate": 8.08182427900738e-06,
-      "loss": 0.0083,
-      "step": 12500
-    },
-    {
-      "epoch": 4.359490274983233,
-      "grad_norm": 0.19220410287380219,
-      "learning_rate": 6.4050972501676726e-06,
-      "loss": 0.0081,
-      "step": 13000
-    },
-    {
-      "epoch": 4.527162977867203,
-      "grad_norm": 0.14213241636753082,
-      "learning_rate": 4.7283702213279675e-06,
-      "loss": 0.0074,
-      "step": 13500
-    },
-    {
-      "epoch": 4.694835680751174,
-      "grad_norm": 0.15386663377285004,
-      "learning_rate": 3.051643192488263e-06,
-      "loss": 0.0083,
-      "step": 14000
-    },
-    {
-      "epoch": 4.862508383635144,
-      "grad_norm": 0.3057624101638794,
-      "learning_rate": 1.3749161636485581e-06,
-      "loss": 0.0071,
-      "step": 14500
     }
   ],
   "logging_steps": 500,
@@ -276,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0760159508037632e+19,
+  "total_flos": 3.6087364307291996e+18,
   "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:fb3be77d244f10d48dc812b520eeb95e50cd4ecbd995ee8774502bcfbdb56d5c
+oid sha256:78c7893516d4a0bbebca188470bd21f7f2eb6d5faa564ec8c10bf421cd471a32
 size 5368