Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5d79e8c2e94c67533fc70310de79aa3786b10184d51dc840e2054df304b736
+oid sha256:1a83f1be33217b1b069056dacb0ff8ae37760d3cda76a1ebd1a3907d70c03df0
 size 959732416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37ef3d72b111b30b960c34f8c87d69674e7593e24d93b982e48b58f9fae6871
+oid sha256:7e60223a37bbcf405c01528488fe445b676105c6f23500b842ac3f6ab1b5b6eb
 size 1919732806

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c881ad54e2aae8feeb160e05a97e39cf1c147f9aae0937a1b7e41a0710f93d0
+oid sha256:95bd719bf1326b1281aa016ff1c8f48d41524f5feaf22af9267d2acf3daac222
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c589f3acbeec5c6e36834591171153e8af682ebbd66860ce42dbcde5e025a9
+oid sha256:ddcca23b21d6bdd8ad51b065d4aa1989126b3480f39bbd5a003d90f3b5366d5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.676727028839705,
+  "epoch": 3.35345405767941,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,102 @@
       "learning_rate": 3.323272971160295e-05,
       "loss": 0.0759,
       "step": 5000
+    },
+    {
+      "epoch": 1.8443997317236756,
+      "grad_norm": 0.3671654164791107,
+      "learning_rate": 3.1556002682763246e-05,
+      "loss": 0.0664,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 100.0,
+      "eval_loss": 0.045729078352451324,
+      "eval_rouge1": 1.7181,
+      "eval_rouge2": 1.2785,
+      "eval_rougeL": 1.7523,
+      "eval_rougeLsum": 1.7256,
+      "eval_runtime": 1544.7805,
+      "eval_samples_per_second": 0.858,
+      "eval_steps_per_second": 0.215,
+      "step": 5964
+    },
+    {
+      "epoch": 2.0120724346076457,
+      "grad_norm": 0.25756004452705383,
+      "learning_rate": 2.9879275653923545e-05,
+      "loss": 0.0643,
+      "step": 6000
+    },
+    {
+      "epoch": 2.1797451374916164,
+      "grad_norm": 0.3812272548675537,
+      "learning_rate": 2.8202548625083835e-05,
+      "loss": 0.0392,
+      "step": 6500
+    },
+    {
+      "epoch": 2.347417840375587,
+      "grad_norm": 0.38306811451911926,
+      "learning_rate": 2.6525821596244134e-05,
+      "loss": 0.0373,
+      "step": 7000
+    },
+    {
+      "epoch": 2.515090543259557,
+      "grad_norm": 0.4030314087867737,
+      "learning_rate": 2.4849094567404426e-05,
+      "loss": 0.0372,
+      "step": 7500
+    },
+    {
+      "epoch": 2.682763246143528,
+      "grad_norm": 0.309796541929245,
+      "learning_rate": 2.3172367538564725e-05,
+      "loss": 0.0324,
+      "step": 8000
+    },
+    {
+      "epoch": 2.8504359490274984,
+      "grad_norm": 0.19243386387825012,
+      "learning_rate": 2.1495640509725018e-05,
+      "loss": 0.0281,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 100.0,
+      "eval_loss": 0.0184603463858366,
+      "eval_rouge1": 5.3843,
+      "eval_rouge2": 3.3178,
+      "eval_rougeL": 5.4006,
+      "eval_rougeLsum": 5.4032,
+      "eval_runtime": 1543.3574,
+      "eval_samples_per_second": 0.859,
+      "eval_steps_per_second": 0.215,
+      "step": 8946
+    },
+    {
+      "epoch": 3.0181086519114686,
+      "grad_norm": 0.09871068596839905,
+      "learning_rate": 1.9818913480885314e-05,
+      "loss": 0.0248,
+      "step": 9000
+    },
+    {
+      "epoch": 3.1857813547954392,
+      "grad_norm": 0.6722275614738464,
+      "learning_rate": 1.814218645204561e-05,
+      "loss": 0.018,
+      "step": 9500
+    },
+    {
+      "epoch": 3.35345405767941,
+      "grad_norm": 0.2110537886619568,
+      "learning_rate": 1.6465459423205902e-05,
+      "loss": 0.0166,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -109,7 +205,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.6087364307291996e+18,
+  "total_flos": 7.216931469785039e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null