Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2a8d90aa234ac44475d39409dfbfa4fdb26f65d52a62de6861c428091b8ec8
+oid sha256:cd46c74284ba73b1189e2b45420e99399bb6205659df2d2c1b122e35dda7736f
 size 557116312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24858682d1d6129b19e305ab6bb61cdca3709f8c6b2b91eaf6b426db53a7515
+oid sha256:79564fb6cc7e990450c02dc917f0c75912df3a4125a5bac3ef68dfb81133c309
 size 1113991930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2b170a520baa1ce18377bdacbbdccab7978596a4a772af3bdbdf4cfda617a7
+oid sha256:59624509e89bbc9b94c591ed4735982e33caa7e6875690c4ff16d1a97717d87c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be41d27c52015159c12ea1a39d342a8acabee4a3e8b9b9a41f77607cbb01aef6
+oid sha256:55dc22eb808a1fd1052bfc779bf751672ec8d853af74b32b8aa1627bdf5827cf
 size 1064

last-checkpoint/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

last-checkpoint/trainer_state.json

@@ -1,84 +1,50 @@
 {
-  "best_metric": 3.0744,
-  "best_model_checkpoint": "my-model/checkpoint-3056",
-  "epoch": 2.0,
+  "best_metric": 24.8013,
+  "best_model_checkpoint": "my-model/checkpoint-1528",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 3056,
+  "global_step": 1528,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.32722513089005234,
-      "grad_norm": 1.1695204973220825,
-      "learning_rate": 4.454624781849913e-05,
-      "loss": 0.0198,
+      "grad_norm": 1.6467379331588745,
+      "learning_rate": 4.5909685863874345e-05,
+      "loss": 0.0168,
       "step": 500
     },
     {
       "epoch": 0.6544502617801047,
-      "grad_norm": 1.4851537942886353,
-      "learning_rate": 3.909249563699826e-05,
-      "loss": 0.0253,
+      "grad_norm": 1.3730037212371826,
+      "learning_rate": 4.181937172774869e-05,
+      "loss": 0.0246,
       "step": 1000
     },
     {
       "epoch": 0.981675392670157,
-      "grad_norm": 1.3880701065063477,
-      "learning_rate": 3.3638743455497386e-05,
-      "loss": 0.0289,
+      "grad_norm": 1.1599562168121338,
+      "learning_rate": 3.7729057591623044e-05,
+      "loss": 0.0308,
       "step": 1500
     },
     {
       "epoch": 1.0,
-      "eval_loss": 5.387067794799805,
-      "eval_rouge1": 2.6116,
-      "eval_rouge2": 0.1215,
-      "eval_rougeL": 2.579,
-      "eval_rougeLsum": 2.5866,
-      "eval_runtime": 422.0957,
-      "eval_samples_per_second": 5.2,
-      "eval_steps_per_second": 0.521,
+      "eval_loss": 5.495022296905518,
+      "eval_rouge1": 24.8013,
+      "eval_rouge2": 9.5895,
+      "eval_rougeL": 21.5936,
+      "eval_runtime": 434.7617,
+      "eval_samples_per_second": 5.049,
+      "eval_steps_per_second": 0.506,
       "step": 1528
-    },
-    {
-      "epoch": 1.3089005235602094,
-      "grad_norm": 3.5784597396850586,
-      "learning_rate": 2.8184991273996508e-05,
-      "loss": 0.0605,
-      "step": 2000
-    },
-    {
-      "epoch": 1.6361256544502618,
-      "grad_norm": 3.948634624481201,
-      "learning_rate": 2.273123909249564e-05,
-      "loss": 0.1013,
-      "step": 2500
-    },
-    {
-      "epoch": 1.9633507853403143,
-      "grad_norm": 5.947019577026367,
-      "learning_rate": 1.7277486910994763e-05,
-      "loss": 0.2594,
-      "step": 3000
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 4.7294816970825195,
-      "eval_rouge1": 3.0744,
-      "eval_rouge2": 0.2582,
-      "eval_rougeL": 3.0319,
-      "eval_rougeLsum": 3.0448,
-      "eval_runtime": 416.9983,
-      "eval_samples_per_second": 5.264,
-      "eval_steps_per_second": 0.528,
-      "step": 3056
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4584,
+  "max_steps": 6112,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -92,7 +58,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4662889498529792e+16,
+  "total_flos": 7327420304523264.0,
   "train_batch_size": 10,
   "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:d4c6c2ba2ea3424d788a8dfe9538b56c56b827a5c71eff9ff7dc67a5445f3d0a
-size 6904
+oid sha256:408bb8b25e44f1ecf1923d9e22dabb6474162771a082c1a83b55da4bd5267fc0
+size 6968