Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fd01a8bae891e64aa1a626cc333858550e0cb6e36fcb7777c30999ee762d5e
+oid sha256:ea2ad4c7c610b5e4ef126bc494685c8d4930ad390366ab2e84a4faeb7d420766
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf48b20262fa5e0455f8bf8dec46b89425e9f2d27bcf272b7ece12dbc3f48cb
+oid sha256:6c39f051c45f03d6dcadc277c1454a36b0adc05bc85d9ce17d6a180588b3cad4
 size 735625370

last-checkpoint/trainer_state.json

@@ -11,53 +11,53 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 2.6000850200653076,
-      "eval_runtime": 5.1412,
-      "eval_samples_per_second": 292.148,
-      "eval_steps_per_second": 18.284,
+      "eval_runtime": 4.9168,
+      "eval_samples_per_second": 305.481,
+      "eval_steps_per_second": 19.118,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 4.21875,
+      "grad_norm": 4.3125,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.4519,
+      "loss": 2.4524,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
       "grad_norm": 1.15625,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 2.4462,
+      "loss": 2.4454,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 2.592799425125122,
-      "eval_runtime": 5.3446,
-      "eval_samples_per_second": 281.033,
-      "eval_steps_per_second": 17.588,
+      "eval_loss": 2.5929689407348633,
+      "eval_runtime": 5.1638,
+      "eval_samples_per_second": 290.869,
+      "eval_steps_per_second": 18.204,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 3.9375,
+      "grad_norm": 4.0,
       "learning_rate": 4.8e-05,
-      "loss": 2.5891,
+      "loss": 2.5904,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
       "grad_norm": 1.5,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.4169,
+      "loss": 2.4156,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 2.5311338901519775,
-      "eval_runtime": 5.3509,
-      "eval_samples_per_second": 280.702,
-      "eval_steps_per_second": 17.567,
+      "eval_loss": 2.5310535430908203,
+      "eval_runtime": 5.1508,
+      "eval_samples_per_second": 291.604,
+      "eval_steps_per_second": 18.249,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56abc2533c0578396c842febb0d8251535aeccfdad6e84eb864bab834fbe822f
+oid sha256:f671da996f9974e01b0bb6a782a1b157ff77bf2c5559d84c73598d7fc8d1f978
 size 6712