Training in progress, step 50800, checkpoint

last-checkpoint/README.md

@@ -1307,6 +1307,10 @@ You can finetune this model on your own dataset.
 | 0.8924 | 50500 | 0.3035        |
 | 0.8933 | 50550 | 0.2654        |
 | 0.8941 | 50600 | 0.2742        |
+| 0.8950 | 50650 | 0.3435        |
+| 0.8959 | 50700 | 0.2947        |
+| 0.8968 | 50750 | 0.3013        |
+| 0.8977 | 50800 | 0.3845        |
 
 </details>
 

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c4343fcf9b81ee5a6a389eb06b051ae53e0aa443077eb13f9892dc66deceec
+oid sha256:735447a9bf44cea3982a63ea1f966e08b7318fb0e661723166d288f02b87e519
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5af64aade248d58122340358b0197dce309cca03ffce8ae549b8f07d208db3
+oid sha256:a2850e2599deef45e89d0f9a762b74aca5edd8c76810f98fd68acb5fea8d7226
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5bc13ec5ce0dc9f4391185df8ee21467fa45863b467072b951e2bda0426e6a
+oid sha256:65c5b25f41326cbbfda1e3a08018f1c0a2d702a29def2a1a126e092c108f1e2b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdc3fca57fcb200a77e9e8cef345de9804f9877d6a37468a61a5b2e8c3dd1d5
+oid sha256:2eecf2b6d210d44959e71df0344547cefe9b13a61cd7bf96084fa2fabddd2a6b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9f1c43d41c176471993abe4ddcdbee9a97b13ab57ea41f5ea87ce032c51df5
+oid sha256:3068e69bbcee94c299b9e89630d72a89daebc924a613171ca109523fc3200153
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8941351098231167,
+  "epoch": 0.8976692406919828,
   "eval_steps": 500,
-  "global_step": 50600,
+  "global_step": 50800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7092,6 +7092,34 @@
       "learning_rate": 5.901121124658853e-06,
       "loss": 0.2742,
       "step": 50600
+    },
+    {
+      "epoch": 0.8950186425403333,
+      "grad_norm": 1.4973150491714478,
+      "learning_rate": 5.852035106320316e-06,
+      "loss": 0.3435,
+      "step": 50650
+    },
+    {
+      "epoch": 0.8959021752575498,
+      "grad_norm": 1.2695672512054443,
+      "learning_rate": 5.80294908798178e-06,
+      "loss": 0.2947,
+      "step": 50700
+    },
+    {
+      "epoch": 0.8967857079747663,
+      "grad_norm": 0.9303974509239197,
+      "learning_rate": 5.753863069643243e-06,
+      "loss": 0.3013,
+      "step": 50750
+    },
+    {
+      "epoch": 0.8976692406919828,
+      "grad_norm": 1.5696642398834229,
+      "learning_rate": 5.704777051304706e-06,
+      "loss": 0.3845,
+      "step": 50800
     }
   ],
   "logging_steps": 50,