Training in progress, step 10, checkpoint

last-checkpoint/config.json

@@ -40,7 +40,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.50.3",
   "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51871

last-checkpoint/generation_config.json

@@ -170,6 +170,6 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.50.3",
   "use_cache": false
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d03d7d5427d8ddad59eb7036deb2e4f723a176beb09e67e2de242f9604ff47d
+oid sha256:015cd4067c182630d745f697676defa8ae8a26985817aa4f9ca4f02ae2bd786b
 size 967013512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397e1dd8eebce11f1fe5c3a428adf088cf62cc5a1d09f4eaafedab2629cf3881
+oid sha256:a4c54ce75022b03e1e5c9f8016fef653aa2c3761ba9375735aeb8eb95c64cdc1
 size 1925100908

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
   "log_history": [
     {
       "epoch": 10.0,
-      "grad_norm": 24.6931095123291,
+      "grad_norm": 19.040071487426758,
       "learning_rate": 7.000000000000001e-06,
-      "loss": 2.448,
+      "loss": 2.5812,
       "step": 10
     }
   ],