Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342371ecd22f7384f330a79e7494cdbe4d24919382d4c853309a2613269efb64
+oid sha256:9e80a6c8762a2d1ee3d17256f00a85ccb75fcf39c1357ea753eb11d98df92abf
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee7d1e25957003634d97649ecbfbf1175fe964c835c02ecc9c562b0f963f399
+oid sha256:5fc1df209e5a6fb1921954e8d2ff92d1b777f2f8c0b3bd49f73324d552ac8058
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3344973d40d4c956ed30b03d5d12a21c82e15ee5d80b604c30ccc8b2a31552dc
+oid sha256:2a6083a3878e51f34e5c4b395c7db9a7f132c5bba487d7f92b48737bdfd6710d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00027945450480661746,
+  "epoch": 0.0005589090096132349,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 3.806,
       "eval_steps_per_second": 3.806,
       "step": 25
+    },
+    {
+      "epoch": 0.00033534540576794097,
+      "grad_norm": 8.198873519897461,
+      "learning_rate": 5e-05,
+      "loss": 0.4893,
+      "step": 30
+    },
+    {
+      "epoch": 0.0003912363067292645,
+      "grad_norm": 3.9584426879882812,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6039,
+      "step": 35
+    },
+    {
+      "epoch": 0.000447127207690588,
+      "grad_norm": 3.658045768737793,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8857,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005030181086519115,
+      "grad_norm": 3.1578454971313477,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4418,
+      "step": 45
+    },
+    {
+      "epoch": 0.0005589090096132349,
+      "grad_norm": 6.337815761566162,
+      "learning_rate": 0.0,
+      "loss": 0.3068,
+      "step": 50
+    },
+    {
+      "epoch": 0.0005589090096132349,
+      "eval_loss": 0.42810094356536865,
+      "eval_runtime": 2596.8666,
+      "eval_samples_per_second": 3.828,
+      "eval_steps_per_second": 3.828,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 908323952001024.0,
+  "total_flos": 1851583440617472.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null