hshankar113/multilingual-chat-slm

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ede9e7cf02cf9741732c58b51becd5670e199835b1af9b3efac89447877c2bc
+oid sha256:8a065c3cf5b9387779c0a98f69b547877fac0b0987c23d932a2def224670d216
 size 1080120048

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.0000333333333333,
   "eval_steps": 500,
-  "global_step": 30000,
+  "global_step": 30001,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2110,13 +2110,13 @@
       "step": 30000
     },
     {
-      "epoch": 1.0,
-      "step": 30000,
-      "total_flos": 4.0980178796544e+17,
-      "train_loss": 4.49529921875,
-      "train_runtime": 18816.3377,
-      "train_samples_per_second": 25.51,
-      "train_steps_per_second": 1.594
+      "epoch": 1.0000333333333333,
+      "step": 30001,
+      "total_flos": 4.0981544802503885e+17,
+      "train_loss": 0.00044824120156077804,
+      "train_runtime": 24.4073,
+      "train_samples_per_second": 19666.274,
+      "train_steps_per_second": 1229.142
     }
   ],
   "logging_steps": 100,
@@ -2136,7 +2136,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.0980178796544e+17,
+  "total_flos": 4.0981544802503885e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null