Training in progress, step 9400, checkpoint

last-checkpoint/README.md

@@ -1209,6 +1209,10 @@ You can finetune this model on your own dataset.
 | 0.1608 | 9100 | 0.3634        |
 | 0.1617 | 9150 | 0.4252        |
 | 0.1626 | 9200 | 0.3899        |
+| 0.1635 | 9250 | 0.4335        |
+| 0.1643 | 9300 | 0.4204        |
+| 0.1652 | 9350 | 0.5576        |
+| 0.1661 | 9400 | 0.4712        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880e624eb7279ea2c15d3d6797440086ddb9b6116f0e9bd2fea229b00f3eafcc
+oid sha256:5e974a383273411df15409a82c6a1b9f0831a59d058b967a3d435ccbc1f48583
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8dea7d6f8279c47cc3d797dc40c5bd4cbb324255364a56bfc64a2536ad6b318
+oid sha256:b870ccf7b86ba6d235904225aaace7fb586b191e7940b6dc707df695b5dd9282
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb5381b8cfab2c43d778d817204fe174c7b328e5f3861902f2432aa4cc89685
+oid sha256:b7adf907e945b62166980022a68a400535d3ff6272023bde8d2c138ada9021e2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2589efb63b68f20dc42380f13074262282edb3a23f326bcb9e05c733236848
+oid sha256:12e1fb2bcfe11259f3983e51e8c93f656c6150bd91d84aeb3343965e94c4460e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb87116cd3b0b49516d866a0e3b848d38858f80863640384bfc6aab2a1d3a1d
+oid sha256:4d745bf9d75c40b1bcb1a39a8a08fa030d79ce77aa08ff337210102fd029a211
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1625700199678394,
+  "epoch": 0.1661041508367055,
   "eval_steps": 500,
-  "global_step": 9200,
+  "global_step": 9400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1296,6 +1296,34 @@
       "learning_rate": 4.6525691621998393e-05,
       "loss": 0.3899,
       "step": 9200
+    },
+    {
+      "epoch": 0.16345355268505593,
+      "grad_norm": 1.8728185892105103,
+      "learning_rate": 4.647660560365986e-05,
+      "loss": 0.4335,
+      "step": 9250
+    },
+    {
+      "epoch": 0.16433708540227246,
+      "grad_norm": 1.977250576019287,
+      "learning_rate": 4.642751958532132e-05,
+      "loss": 0.4204,
+      "step": 9300
+    },
+    {
+      "epoch": 0.16522061811948896,
+      "grad_norm": 4.992434978485107,
+      "learning_rate": 4.637843356698278e-05,
+      "loss": 0.5576,
+      "step": 9350
+    },
+    {
+      "epoch": 0.1661041508367055,
+      "grad_norm": 1.673086166381836,
+      "learning_rate": 4.6329347548644245e-05,
+      "loss": 0.4712,
+      "step": 9400
     }
   ],
   "logging_steps": 50,