Training in progress, step 29800, checkpoint

last-checkpoint/README.md

@@ -1253,6 +1253,10 @@ You can finetune this model on your own dataset.
 | 0.5213 | 29500 | 0.3322        |
 | 0.5222 | 29550 | 0.3053        |
 | 0.5231 | 29600 | 0.2486        |
+| 0.5239 | 29650 | 0.282         |
+| 0.5248 | 29700 | 0.3791        |
+| 0.5257 | 29750 | 0.3346        |
+| 0.5266 | 29800 | 0.2743        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144dc908d4b1ad90ee4a018b09fcaa7382467917152ff08210428196e07231f5
+oid sha256:f825b875fd3411a67519723584f534dbb07906a94fc074203b6899cfdda34fb1
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ca3e8ce7625e03c0718ab68f669eeba24f2a5b3e90913a5232a2578f9fb9e5
+oid sha256:bc4f7f00258615a01948f967086a40fe67b9d0f30411b6eeb7956c1d0e25c22c
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:029654d250d0a06a53ab2b4254f6c488ff21281306f583e5ec84fbf77c6593a0
+oid sha256:96c8b292b591500813d59792390c9a1e49d14483b29c2cccf2081a971b6f3cb9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b527e96b4627964f9c26d5047552177b51a31ae414fb5194c8647b133292f2b4
+oid sha256:701ad9ee8b64e03a45e44d6fd168805d271251720d2ba20141feedf9e8d7209a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786920dde07982614e5d3db4362f9f0f309e2cae4493573be6138429ecf70b07
+oid sha256:5f1bd9cc4f297f5700001cd99fe1f86afbb411b53d2ea438dae9c8e2c077cfdb
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5230513685921789,
+  "epoch": 0.526585499461045,
   "eval_steps": 500,
-  "global_step": 29600,
+  "global_step": 29800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4152,6 +4152,34 @@
       "learning_rate": 2.6507431623176455e-05,
       "loss": 0.2486,
       "step": 29600
+    },
+    {
+      "epoch": 0.5239349013093955,
+      "grad_norm": 1.199449062347412,
+      "learning_rate": 2.645834560483792e-05,
+      "loss": 0.282,
+      "step": 29650
+    },
+    {
+      "epoch": 0.524818434026612,
+      "grad_norm": 0.9432544112205505,
+      "learning_rate": 2.6409259586499385e-05,
+      "loss": 0.3791,
+      "step": 29700
+    },
+    {
+      "epoch": 0.5257019667438285,
+      "grad_norm": 2.9582953453063965,
+      "learning_rate": 2.6360173568160846e-05,
+      "loss": 0.3346,
+      "step": 29750
+    },
+    {
+      "epoch": 0.526585499461045,
+      "grad_norm": 1.5263501405715942,
+      "learning_rate": 2.631108754982231e-05,
+      "loss": 0.2743,
+      "step": 29800
     }
   ],
   "logging_steps": 50,