Training in progress, step 48600, checkpoint

last-checkpoint/README.md

@@ -1261,6 +1261,10 @@ You can finetune this model on your own dataset.
 | 0.8535 | 48300 | 0.2645        |
 | 0.8544 | 48350 | 0.3358        |
 | 0.8553 | 48400 | 0.2939        |
+| 0.8561 | 48450 | 0.4063        |
+| 0.8570 | 48500 | 0.3492        |
+| 0.8579 | 48550 | 0.2794        |
+| 0.8588 | 48600 | 0.2854        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3690fa2a143ecb0d4643a209624dc7188c601389b80bc7eadb77baedd884c8
+oid sha256:d3f97e4be59707659beabd834e11f6a65a7292265dfb49c2caf9bc89b0c6716a
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68bdb8f5b522fdce4d5c267f15db43e12a7fbffda0d7ac355cca5fe6e2293a9
+oid sha256:48984ae26e348d11908c5f2745c34cd2def85ea7c810d9fbea301d1fb62f8737
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1337b9c73878b431640eabbf713a3fc3ffa1889559f5fe2e1f50b06fa34639d6
+oid sha256:d7b99c2c71b3197a1fb7e795c175200808e384737d0136671189f7f54df62c39
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78f9ce48aa6920e09eb307b60e2b49742b779f95ad33075f31c6652ec108e55
+oid sha256:05d2345a7bbddb12fb6a365e62bd73e47296785a601a5379725821a73d3794f3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd8a22cf09f7fa5f8eaecff8876d6b0aa930d2f190895e8ce37c95ed1dd7a48
+oid sha256:53bf9eae9141600b1f20ec91bc52ae342d59856e71a200d65bc37505fde53a5f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8552596702655899,
+  "epoch": 0.858793801134456,
   "eval_steps": 500,
-  "global_step": 48400,
+  "global_step": 48600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6784,6 +6784,34 @@
       "learning_rate": 8.059924211187687e-06,
       "loss": 0.2939,
       "step": 48400
+    },
+    {
+      "epoch": 0.8561432029828064,
+      "grad_norm": 4.159787654876709,
+      "learning_rate": 8.010838192849148e-06,
+      "loss": 0.4063,
+      "step": 48450
+    },
+    {
+      "epoch": 0.857026735700023,
+      "grad_norm": 2.129241466522217,
+      "learning_rate": 7.961752174510613e-06,
+      "loss": 0.3492,
+      "step": 48500
+    },
+    {
+      "epoch": 0.8579102684172395,
+      "grad_norm": 1.48981511592865,
+      "learning_rate": 7.912666156172076e-06,
+      "loss": 0.2794,
+      "step": 48550
+    },
+    {
+      "epoch": 0.858793801134456,
+      "grad_norm": 2.017918348312378,
+      "learning_rate": 7.86358013783354e-06,
+      "loss": 0.2854,
+      "step": 48600
     }
   ],
   "logging_steps": 50,