Training in progress, step 44600, checkpoint

last-checkpoint/README.md

@@ -1407,6 +1407,10 @@ You can finetune this model on your own dataset.
 | 0.7828 | 44300 | 0.2678        |
 | 0.7837 | 44350 | 0.3625        |
 | 0.7846 | 44400 | 0.311         |
+| 0.7855 | 44450 | 0.2924        |
+| 0.7863 | 44500 | 0.2602        |
+| 0.7872 | 44550 | 0.3936        |
+| 0.7881 | 44600 | 0.229         |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0590fb55aab08f3535397ce8dcef99c8680506c32302ba2d6e910a8249da6224
+oid sha256:fce513425ee78d82ca94654cdc0a4320210e5ec028784be1406c877832c93919
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abff80a73aec9612ce24bcd8cc146093b60dfe7bfd2e43a1f500d834e46d5802
+oid sha256:382cb2a8e601a053bb0ea3969b939edccc79edf806fa2fb79934a1132c941d31
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb5618265930c1ad5f9342c3f992eaed8023f41d629ef3773582c7b22437a29
+oid sha256:6bf11240eaa3ac15b3a592742695066b7826256894b145544defe57b1a51d2f5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9756468f8fd1e049c0f34546e465c8cf6b5e4ecebc81c7ebf057569a23c46ac
+oid sha256:47e00c9999dcddbc2f016707d637f020dd9c8d184d501770291cf9d13b707305
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdfed137404ca82aee02dc12b81b45bc0fb558d702987085b73e2f3d6d8e8b76
+oid sha256:7f34973fe7d7e41a1f8ad1f0f8cd4803fde065c5148acc0e939fcacd0a4b92d9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7845770528882684,
+  "epoch": 0.7881111837571345,
   "eval_steps": 500,
-  "global_step": 44400,
+  "global_step": 44600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6224,6 +6224,34 @@
       "learning_rate": 1.1984842237537062e-05,
       "loss": 0.311,
       "step": 44400
+    },
+    {
+      "epoch": 0.7854605856054849,
+      "grad_norm": 1.2201918363571167,
+      "learning_rate": 1.1935756219198523e-05,
+      "loss": 0.2924,
+      "step": 44450
+    },
+    {
+      "epoch": 0.7863441183227015,
+      "grad_norm": 1.6248202323913574,
+      "learning_rate": 1.1886670200859988e-05,
+      "loss": 0.2602,
+      "step": 44500
+    },
+    {
+      "epoch": 0.787227651039918,
+      "grad_norm": 2.032122850418091,
+      "learning_rate": 1.183758418252145e-05,
+      "loss": 0.3936,
+      "step": 44550
+    },
+    {
+      "epoch": 0.7881111837571345,
+      "grad_norm": 1.149383783340454,
+      "learning_rate": 1.1788498164182915e-05,
+      "loss": 0.229,
+      "step": 44600
     }
   ],
   "logging_steps": 50,