Training in progress, step 51200, checkpoint

last-checkpoint/README.md

@@ -1315,6 +1315,10 @@ You can finetune this model on your own dataset.
 | 0.8994 | 50900 | 0.3639        |
 | 0.9003 | 50950 | 0.2332        |
 | 0.9012 | 51000 | 0.3363        |
+| 0.9021 | 51050 | 0.2674        |
+| 0.9030 | 51100 | 0.331         |
+| 0.9039 | 51150 | 0.2881        |
+| 0.9047 | 51200 | 0.3553        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5b296e1f58fde06ca25a671f7290066af40d31d74f593dd71beb56e81f618e
+oid sha256:17ad1d70cc9a9203e1932e7a5399b2ea38220c472d491a93ade1e1841ba94da7
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cec233f06e1ea5350dc36447e7fd4afa810289f7a83dc18968cd19ae207a12
+oid sha256:e0c9ea94de1bc6171fc560eb6edc6e3bb30de3a6197d7f6bdc43b28fa6e8b63a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b900393780cdd3cbb99d501f19a790b00c5891d77d31ffa5ebe767f48b02bb
+oid sha256:697766d9762a48456880b2166b1f5fb91392394ad67b7232020fe661b72f67bd
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c99faa590c236be1e60450ac31ef6bbc0d8a5408817f47526e33c981695098
+oid sha256:4f620a353823eb6b71c8ccf047459bfd67f2ce79246e53f2aa937b07f9d71d34
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2640c4dcf9a6fa010a98a2ceb775abaf0e70fd53baf808dd65285ab30eadea3f
+oid sha256:2fadf44129acc4700f11541025d2dded44dc62ab2fdbe50e09f45fc382b24055
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.901203371560849,
+  "epoch": 0.904737502429715,
   "eval_steps": 500,
-  "global_step": 51000,
+  "global_step": 51200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7148,6 +7148,34 @@
       "learning_rate": 5.508432977950561e-06,
       "loss": 0.3363,
       "step": 51000
+    },
+    {
+      "epoch": 0.9020869042780654,
+      "grad_norm": 1.782301664352417,
+      "learning_rate": 5.459346959612025e-06,
+      "loss": 0.2674,
+      "step": 51050
+    },
+    {
+      "epoch": 0.9029704369952819,
+      "grad_norm": 1.5983684062957764,
+      "learning_rate": 5.411242661640259e-06,
+      "loss": 0.331,
+      "step": 51100
+    },
+    {
+      "epoch": 0.9038539697124984,
+      "grad_norm": 1.749089002609253,
+      "learning_rate": 5.362156643301722e-06,
+      "loss": 0.2881,
+      "step": 51150
+    },
+    {
+      "epoch": 0.904737502429715,
+      "grad_norm": 1.2461782693862915,
+      "learning_rate": 5.313070624963186e-06,
+      "loss": 0.3553,
+      "step": 51200
     }
   ],
   "logging_steps": 50,