Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cacd27c99ee481d08b39aebfdeb2316c2bbfd2d558f9452ef4a1e210bb4eeb
+oid sha256:38f0369b6d301c6203f48a1f2d1aa1b1fcfd5879d3c98cd14459266c4a3f66ba
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a9465e9b84798b9a1b21653f7afb6ed9212ab8bc79b12d24e5073a40bf194a
+oid sha256:185d99cbc990f4fc721842ffab925be7d15d74e7b08db3922f9b6683379a554b
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af78c41e82afcf3f5c18e1cebb33f3d406acc2ea6eff7ca91dc677e007bab9a
+oid sha256:f57b35f81216c730d5741994e704216871509207a06fc84a3e1635f766915869
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002042312526183494,
+  "epoch": 0.002618349392542941,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 44.1994,
       "step": 35
+    },
+    {
+      "epoch": 0.0020946795140343527,
+      "grad_norm": 1.4559333324432373,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.1904,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020946795140343527,
+      "eval_loss": 11.042880058288574,
+      "eval_runtime": 62.11,
+      "eval_samples_per_second": 129.464,
+      "eval_steps_per_second": 64.74,
+      "step": 40
+    },
+    {
+      "epoch": 0.0023565144532886467,
+      "grad_norm": 1.4452019929885864,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.1758,
+      "step": 45
+    },
+    {
+      "epoch": 0.002618349392542941,
+      "grad_norm": 1.5328729152679443,
+      "learning_rate": 0.0,
+      "loss": 44.1714,
+      "step": 50
+    },
+    {
+      "epoch": 0.002618349392542941,
+      "eval_loss": 11.04096794128418,
+      "eval_runtime": 61.9724,
+      "eval_samples_per_second": 129.751,
+      "eval_steps_per_second": 64.884,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 752294559744.0,
+  "total_flos": 964480204800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null