Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a660381d79264a17d2550ea5e5a429959f0b9c28eb96332197a2a8a9c4f6fb3
+oid sha256:356e77737e1ae57c572cefec580a243ff3bf580fbabb7d8184cf96c4dc8f3524
 size 723676832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e06f5b51db696407df34b9e2582d449c160e769f799d7cfe185bcb41183b88
+oid sha256:ceb1e871d2adeb06e378f9b3dd9f505b3cc3347052040d028a70c5698d6ed5f4
 size 735627290

last-checkpoint/trainer_state.json

@@ -11,53 +11,53 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 2.9618937969207764,
-      "eval_runtime": 5.1254,
-      "eval_samples_per_second": 293.049,
-      "eval_steps_per_second": 18.34,
+      "eval_runtime": 5.2129,
+      "eval_samples_per_second": 288.133,
+      "eval_steps_per_second": 18.032,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
       "grad_norm": 4.4375,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.655,
+      "loss": 2.6559,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
       "grad_norm": 1.6328125,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 2.7917,
+      "loss": 2.7912,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 2.933722734451294,
-      "eval_runtime": 5.4063,
-      "eval_samples_per_second": 277.826,
-      "eval_steps_per_second": 17.387,
+      "eval_loss": 2.9339327812194824,
+      "eval_runtime": 5.5967,
+      "eval_samples_per_second": 268.371,
+      "eval_steps_per_second": 16.796,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 6.3125,
+      "grad_norm": 6.34375,
       "learning_rate": 4.8e-05,
-      "loss": 2.8946,
+      "loss": 2.8945,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
-      "grad_norm": 2.15625,
+      "grad_norm": 2.1875,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.7579,
+      "loss": 2.7552,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 2.718113899230957,
-      "eval_runtime": 5.4545,
-      "eval_samples_per_second": 275.368,
-      "eval_steps_per_second": 17.233,
+      "eval_loss": 2.7184391021728516,
+      "eval_runtime": 5.6084,
+      "eval_samples_per_second": 267.814,
+      "eval_steps_per_second": 16.761,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe03fc40c2f60afb467f9fe9d85c4aa58d6394a9d6b88eb6bbad1750f4faa0d
+oid sha256:7337b093c5d7d6a10f8669867e0be91b7b9af804f42fa136237f8529e7181224
 size 6840