Training in progress, step 50, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:160db84884c852936290c2dbabae2e7aef7f29215bea95251f3d7c6279739be7
+oid sha256:5edb98a1e6c523dcd5a3c5cf784f7b65a32ca68720e44b415cbd6e8cffabaab7
 size 91951912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871faa733ae16c56f62ff4acb9dc36002b66d420908dd14f8542137ab911d7ef
+oid sha256:79058ecee9f122e8a7141d1a9505f3c5fe3a358112e64619fd215c1937bbe280
 size 183993547

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
+oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d8446916771bdbc3272fb5483d27a47f792f342be43af6bfbcc122b7703745
+oid sha256:1c414e5d294244b6e3f30629a4eba6627304506f72ac598738943e55c96b2fce
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004,
+  "epoch": 0.005,
   "eval_steps": 10,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -320,6 +320,84 @@
       "eval_samples_per_second": 14.667,
       "eval_steps_per_second": 1.833,
       "step": 40
+    },
+    {
+      "epoch": 0.0041,
+      "grad_norm": 1.7677608728408813,
+      "learning_rate": 0.0004,
+      "loss": 9.2559,
+      "step": 41
+    },
+    {
+      "epoch": 0.0042,
+      "grad_norm": 1.4745514392852783,
+      "learning_rate": 0.00041,
+      "loss": 7.3328,
+      "step": 42
+    },
+    {
+      "epoch": 0.0043,
+      "grad_norm": 1.3988405466079712,
+      "learning_rate": 0.00042000000000000007,
+      "loss": 7.0773,
+      "step": 43
+    },
+    {
+      "epoch": 0.0044,
+      "grad_norm": 1.1933400630950928,
+      "learning_rate": 0.00043000000000000004,
+      "loss": 5.9391,
+      "step": 44
+    },
+    {
+      "epoch": 0.0045,
+      "grad_norm": 1.4306049346923828,
+      "learning_rate": 0.00044,
+      "loss": 6.1685,
+      "step": 45
+    },
+    {
+      "epoch": 0.0046,
+      "grad_norm": 1.0445979833602905,
+      "learning_rate": 0.00045,
+      "loss": 4.2649,
+      "step": 46
+    },
+    {
+      "epoch": 0.0047,
+      "grad_norm": 0.9933378100395203,
+      "learning_rate": 0.00045999999999999996,
+      "loss": 4.1511,
+      "step": 47
+    },
+    {
+      "epoch": 0.0048,
+      "grad_norm": 1.1010223627090454,
+      "learning_rate": 0.00047000000000000004,
+      "loss": 4.194,
+      "step": 48
+    },
+    {
+      "epoch": 0.0049,
+      "grad_norm": 3.0977938175201416,
+      "learning_rate": 0.00048,
+      "loss": 4.409,
+      "step": 49
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 0.9864963293075562,
+      "learning_rate": 0.00049,
+      "loss": 3.0262,
+      "step": 50
+    },
+    {
+      "epoch": 0.005,
+      "eval_loss": 0.34309181571006775,
+      "eval_runtime": 680.6754,
+      "eval_samples_per_second": 14.691,
+      "eval_steps_per_second": 1.836,
+      "step": 50
     }
   ],
   "logging_steps": 1,