Training in progress, step 52600, checkpoint

last-checkpoint/README.md

@@ -1205,6 +1205,10 @@ You can finetune this model on your own dataset.
 | 0.9242 | 52300 | 0.3196        |
 | 0.9251 | 52350 | 0.3322        |
 | 0.9259 | 52400 | 0.3258        |
+| 0.9268 | 52450 | 0.3419        |
+| 0.9277 | 52500 | 0.2997        |
+| 0.9286 | 52550 | 0.2425        |
+| 0.9295 | 52600 | 0.2708        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b6ccee8235180e0fcb744d9c9527b2c600512f7ecc4b3d25488b384822838a3
+oid sha256:2d488dc3a5445f93dc6d891e374112fcf40bd92f3df49a02fa164a7b7e3f0939
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002e9ce3d93da778bb4fe1c95037789e052796647a41c67b89002e6d3a8a69ff
+oid sha256:2ade7229380655a5e5d3053eb6b8da0b8461494cbbd9ca16bd058175900faab5
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3763a2915178d87a90c93bc33c9a17dd8d33e1ee286d4f530459bdee03d15b6d
+oid sha256:d8bc5e9aadcf53514c913a3f624aee68ac8959f84c12938e1ebd53df4add3fd5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0315f631d073b9e84cefc9abe7ee2e75af036769039c7a2bf20f3d81a5e6f752
+oid sha256:16fabdbfb525bb124af89aae1d7ac043f5eac6bfe2d8462a555cfc01bdf7a82a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf725a620db2293e4b5f5ac9e35cb4f2f88cf44a5a0884c22a06b906efee164
+oid sha256:e0c8184ff5d3c53c23e51683855f8ef56aed39b4067ed958d2a6305ca37d4bf3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9259422876429114,
+  "epoch": 0.9294764185117775,
   "eval_steps": 500,
-  "global_step": 52400,
+  "global_step": 52600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7344,6 +7344,34 @@
       "learning_rate": 4.135006184838311e-06,
       "loss": 0.3258,
       "step": 52400
+    },
+    {
+      "epoch": 0.926825820360128,
+      "grad_norm": 4.394749164581299,
+      "learning_rate": 4.085920166499775e-06,
+      "loss": 0.3419,
+      "step": 52450
+    },
+    {
+      "epoch": 0.9277093530773445,
+      "grad_norm": 0.856221616268158,
+      "learning_rate": 4.036834148161238e-06,
+      "loss": 0.2997,
+      "step": 52500
+    },
+    {
+      "epoch": 0.928592885794561,
+      "grad_norm": 1.1520658731460571,
+      "learning_rate": 3.9877481298227014e-06,
+      "loss": 0.2425,
+      "step": 52550
+    },
+    {
+      "epoch": 0.9294764185117775,
+      "grad_norm": 1.2415558099746704,
+      "learning_rate": 3.938662111484165e-06,
+      "loss": 0.2708,
+      "step": 52600
     }
   ],
   "logging_steps": 50,