Training in progress, step 28200, checkpoint

last-checkpoint/README.md

@@ -1221,6 +1221,10 @@ You can finetune this model on your own dataset.
 | 0.4930 | 27900 | 0.4098        |
 | 0.4939 | 27950 | 0.3364        |
 | 0.4948 | 28000 | 0.3354        |
+| 0.4957 | 28050 | 0.2879        |
+| 0.4965 | 28100 | 0.3604        |
+| 0.4974 | 28150 | 0.2612        |
+| 0.4983 | 28200 | 0.3593        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68ecb62cb177a69e2ea7a2d8815c238cc32cec342188055a5fefa4de66dcc5
+oid sha256:aa1965a5554a69ff8c5d7634a28c5f04a03c69dd137851c93b70cebbac2f7e99
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99ec639b3e9bec0cbb3889051137c9795f5cf34c03f83c5e27e4203004378a8
+oid sha256:22731b099d557e9c813459e9016c90f95f238923990688ebd670d8401d82293f
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2bb1065a03f3a3cc81b13be34dd1b158c384419d61db5c56d91448ea10ea2e
+oid sha256:d49299668d565a8fbf28b1ad8ad6ea4712f5b9b7d3472cc8d598ff75082532ee
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46b4db6042cc9cc0d2e82b27079ac2205bbc9a103068ad0178d3c56c11b3021
+oid sha256:2a77e32486116fb80a72650dd1d3f8b1c3fcfe6b44b779b1f8fb0e11f75bb318
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4cd14cf09830d2d2a5966f0c329a3b566132e79593057303cd71a113d5be9d
+oid sha256:be316569338339522180d5bdc62cd0944e9a3d23a5127275cdd38048e9eeda36
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.49477832164125035,
+  "epoch": 0.49831245251011647,
   "eval_steps": 500,
-  "global_step": 28000,
+  "global_step": 28200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3928,6 +3928,34 @@
       "learning_rate": 2.8078184210009623e-05,
       "loss": 0.3354,
       "step": 28000
+    },
+    {
+      "epoch": 0.4956618543584669,
+      "grad_norm": 1.141662359237671,
+      "learning_rate": 2.8029098191671088e-05,
+      "loss": 0.2879,
+      "step": 28050
+    },
+    {
+      "epoch": 0.4965453870756834,
+      "grad_norm": 1.5769354104995728,
+      "learning_rate": 2.798001217333255e-05,
+      "loss": 0.3604,
+      "step": 28100
+    },
+    {
+      "epoch": 0.49742891979289994,
+      "grad_norm": 2.3104453086853027,
+      "learning_rate": 2.7930926154994014e-05,
+      "loss": 0.2612,
+      "step": 28150
+    },
+    {
+      "epoch": 0.49831245251011647,
+      "grad_norm": 0.764305830001831,
+      "learning_rate": 2.7881840136655475e-05,
+      "loss": 0.3593,
+      "step": 28200
     }
   ],
   "logging_steps": 50,