Training in progress, step 20200, checkpoint

last-checkpoint/README.md

@@ -1427,6 +1427,10 @@ You can finetune this model on your own dataset.
 | 0.3516 | 19900 | 0.3636        |
 | 0.3525 | 19950 | 0.3704        |
 | 0.3534 | 20000 | 0.3459        |
+| 0.3543 | 20050 | 0.3226        |
+| 0.3552 | 20100 | 0.3256        |
+| 0.3561 | 20150 | 0.3179        |
+| 0.3569 | 20200 | 0.4226        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7072d59f5aacf209413bfe1b68393d31e61f586cffca0291db2c96c4018ed70
+oid sha256:0ef29b19104cdd2fee93b8217bc742ea19781fda755240150a391d0a52137790
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ace23ee1b367e732fb2aa3f1a05392e0e438a9535dad79c057fb1b8e02b9d68
+oid sha256:b84ead54747767096d47dd620e6c1d4484392809c929ebd262e713e54fdf126a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14dd25fc849fe74831fabbde14139b26a0f4aad6b8e087440c778d9e11ab8d7e
+oid sha256:67d7c2b4ab7e82df68b4a7c174bebe88de85db56b4421a6d44a9a14dfc374b05
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313073d5ed3020eae2b8815f959d08ffdd33605f3a4a238421bfb13a6954c251
+oid sha256:75cb2a5d4e61624cc82e548180286aa5f7b7073a2bd43f3a7494227c84590e41
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde16ded14375bc47c997c2d556dc8340b61e53a3892d07fbf99a72d763ffa8d
+oid sha256:a28e3c14c246edc1f658e8b3ed3e4804f86c97afddb1e9e8b6cfd065ec104723
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3534130868866074,
+  "epoch": 0.3569472177554735,
   "eval_steps": 500,
-  "global_step": 20000,
+  "global_step": 20200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2808,6 +2808,34 @@
       "learning_rate": 3.5928020262708373e-05,
       "loss": 0.3459,
       "step": 20000
+    },
+    {
+      "epoch": 0.3542966196038239,
+      "grad_norm": 2.97851824760437,
+      "learning_rate": 3.587893424436983e-05,
+      "loss": 0.3226,
+      "step": 20050
+    },
+    {
+      "epoch": 0.35518015232104044,
+      "grad_norm": 2.1979775428771973,
+      "learning_rate": 3.5829848226031296e-05,
+      "loss": 0.3256,
+      "step": 20100
+    },
+    {
+      "epoch": 0.35606368503825697,
+      "grad_norm": 1.762453556060791,
+      "learning_rate": 3.578076220769276e-05,
+      "loss": 0.3179,
+      "step": 20150
+    },
+    {
+      "epoch": 0.3569472177554735,
+      "grad_norm": 1.4908533096313477,
+      "learning_rate": 3.5731676189354225e-05,
+      "loss": 0.4226,
+      "step": 20200
     }
   ],
   "logging_steps": 50,