Training in progress, step 34000, checkpoint

last-checkpoint/README.md

@@ -1193,6 +1193,10 @@ You can finetune this model on your own dataset.
 | 0.5955 | 33700 | 0.2754        |
 | 0.5964 | 33750 | 0.3434        |
 | 0.5973 | 33800 | 0.2541        |
+| 0.5982 | 33850 | 0.2923        |
+| 0.5990 | 33900 | 0.2361        |
+| 0.5999 | 33950 | 0.4459        |
+| 0.6008 | 34000 | 0.3169        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f44c393193a7debcaa9fe116b2e33229c62b31c7228329c28ad0491e8701e1a
+oid sha256:864337e54b0d99195a63884a96e6fc0a3ba7ad47ef988a3eb797527a137e5a93
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620d6a0f0e8b3c0b610d1a9d8d426a0e427c22a7ec7ed38356be652403968d4e
+oid sha256:2fb36dbae403fd4e5ed4b762c80bac9104bf77e8de0d5c4f5e8c6eaad4c7e78a
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba676fcdff1c56d78801dd51dede93231c1d56645e7877743bcba848aec097a
+oid sha256:d5828bcbe6e1a072cf5e6743b55a27970aa81f22da119739e72fdd503508aec8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b205c3d2c6273622b727175547a26240710159f4256bcd6246156ce73b10ee3f
+oid sha256:3ca4bb4a820d3aea8a0a082f1aadfd9af93af513ae74063f47c2633f52672d6e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff383a89d52f883cafae387eb5146463fb8074271a1417f846316599e03e648
+oid sha256:4bf428199bdc10b835fdf8661e7d1632cc44c4e8393f3c5779cb4131e9a11ef8
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5972681168383666,
+  "epoch": 0.6008022477072326,
   "eval_steps": 500,
-  "global_step": 33800,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4740,6 +4740,34 @@
       "learning_rate": 2.2386169523472935e-05,
       "loss": 0.2541,
       "step": 33800
+    },
+    {
+      "epoch": 0.5981516495555831,
+      "grad_norm": 1.532326102256775,
+      "learning_rate": 2.23370835051344e-05,
+      "loss": 0.2923,
+      "step": 33850
+    },
+    {
+      "epoch": 0.5990351822727996,
+      "grad_norm": 1.543256402015686,
+      "learning_rate": 2.228799748679586e-05,
+      "loss": 0.2361,
+      "step": 33900
+    },
+    {
+      "epoch": 0.599918714990016,
+      "grad_norm": 1.5733423233032227,
+      "learning_rate": 2.2238911468457326e-05,
+      "loss": 0.4459,
+      "step": 33950
+    },
+    {
+      "epoch": 0.6008022477072326,
+      "grad_norm": 1.2398439645767212,
+      "learning_rate": 2.218982545011879e-05,
+      "loss": 0.3169,
+      "step": 34000
     }
   ],
   "logging_steps": 50,